chore: bump version to 3.3.12

Co-authored-by: Codex <noreply@openai.com>

.github/dependabot.yml

@@ -21,6 +21,11 @@ updates:
       day: monday
       time: '09:10'
       timezone: Asia/Shanghai
+    # 固定官方 Codex Desktop 的 TLS 指纹；升级前必须抓取握手并比对扩展顺序。
+    ignore:
+      - dependency-name: hyper-rustls
+      - dependency-name: reqwest
+      - dependency-name: rustls
     groups:
       minor-and-patch:
         update-types:

.github/workflows/_container.yml

@@ -40,12 +40,12 @@ jobs:
           } >> "$GITHUB_ENV"
 
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ inputs.ref }}
 
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
 
       - name: Build runtime image
         uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
@@ -55,6 +55,9 @@ jobs:
           target: runtime
           load: true
           tags: ${{ env.CPR_IMAGE }}
+          no-cache-filters: |
+            runtime-base
+            runtime
           cache-from: type=gha,scope=runtime-ci
           cache-to: type=gha,mode=max,scope=runtime-ci
 
@@ -76,7 +79,7 @@ jobs:
           ${{ hashFiles('trivy-results.sarif') != '' &&
               (github.event_name != 'pull_request' ||
                github.event.pull_request.head.repo.full_name == github.repository) }}
-        uses: github/codeql-action/upload-sarif@7188fc363630916deb702c7fdcf4e481b751f97a # v4.37.1
+        uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
         with:
           sarif_file: trivy-results.sarif
           category: runtime-container

.github/workflows/_quality.yml

@@ -61,9 +61,44 @@ jobs:
           --health-retries 10
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ inputs.ref }}
+          # PR 场景需要 base 提交做冻结清单的 append-only 比对。
+          fetch-depth: ${{ github.event_name == 'pull_request' && 0 || 1 }}
+
+      # 已应用迁移的字节被 sqlx 启动校验钉死：改动已发布迁移会让所有
+      # 存量部署重启即失败。冻结清单保证旧文件不被改、新文件必须入册。
+      - name: Migration freeze check
+        working-directory: backend/migrations
+        shell: bash
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          set -euo pipefail
+          sha256sum --check --strict .frozen-sha256
+          for file in *.sql; do
+            if ! awk '{print $2}' .frozen-sha256 | grep -Fxq "$file"; then
+              echo "::error file=backend/migrations/$file::migration $file is not frozen; append its sha256 to backend/migrations/.frozen-sha256"
+              exit 1
+            fi
+          done
+          # 清单自证不足以防「改迁移 + 同 PR 刷新清单行」：校验对新哈希通过。
+          # 对 PR，断言 .frozen-sha256 相对 base 只增不改——base 里的每一行
+          # 必须原样保留（改哈希＝删行，删迁移＝删行，都会被挡）。
+          if [ -n "${BASE_SHA:-}" ]; then
+            base_manifest="$(git show "${BASE_SHA}:backend/migrations/.frozen-sha256" 2>/dev/null || true)"
+            if [ -n "$base_manifest" ]; then
+              while IFS= read -r line; do
+                [ -z "$line" ] && continue
+                if ! grep -Fxq "$line" .frozen-sha256; then
+                  file="$(printf '%s' "$line" | awk '{print $2}')"
+                  echo "::error file=backend/migrations/.frozen-sha256::frozen migration $file was modified or removed; released migrations are append-only — add a new numbered migration instead"
+                  exit 1
+                fi
+              done <<< "$base_manifest"
+            fi
+          fi
 
       - name: Setup Rust
         uses: dtolnay/rust-toolchain@1a3a6d54512beeaffd394f8d516ca16f2c506a20 # 1.97
@@ -71,7 +106,7 @@ jobs:
           components: rustfmt,clippy
 
       - name: Cache Rust
-        uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+        uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
         with:
           workspaces: backend -> target
 
@@ -117,12 +152,12 @@ jobs:
       CI: 'true'
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ inputs.ref }}
 
       - name: Setup pnpm
-        uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
+        uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6.0.10
         with:
           version: 11.7.0
 
@@ -156,7 +191,7 @@ jobs:
     timeout-minutes: 5
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ inputs.ref }}
 

.github/workflows/ci.yml

@@ -4,6 +4,8 @@ on:
   push:
     branches:
       - main
+    paths-ignore:
+      - 'release/version.yaml'
   pull_request:
     branches:
       - main
@@ -25,14 +27,14 @@ jobs:
       container: ${{ steps.filter.outputs.container }}
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
           fetch-depth: 0
 
       - name: Detect affected checks
         id: filter
-        uses: dorny/paths-filter@7b450fff21473bca461d4b92ce414b9d0420d706 # v4.0.2
+        uses: dorny/paths-filter@ceb8a2b8f2d89434be7ff52d3de7ec3738c5cc9d # v4.0.3
         with:
           filters: |
             backend:

.github/workflows/release.yml

@@ -1,9 +1,6 @@
 name: Release
 
 on:
-  push:
-    tags:
-      - 'v*'
   workflow_dispatch:
     inputs:
       tag:
@@ -15,7 +12,7 @@ permissions:
   contents: read
 
 concurrency:
-  group: release-${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.ref_name }}
+  group: release-${{ inputs.tag }}
   cancel-in-progress: false
 
 env:
@@ -29,6 +26,7 @@ jobs:
     outputs:
       tag: ${{ steps.version.outputs.tag }}
       version: ${{ steps.version.outputs.version }}
+      docker_version: ${{ steps.version.outputs.docker_version }}
       build_time: ${{ steps.version.outputs.build_time }}
       git_sha: ${{ steps.version.outputs.git_sha }}
       platform_matrix: ${{ steps.version.outputs.platform_matrix }}
@@ -40,16 +38,16 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
-          ref: ${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.ref }}
+          ref: ${{ inputs.tag }}
           fetch-depth: 0
 
       - name: Read release metadata
         id: version
         shell: bash
         env:
-          RELEASE_TAG: ${{ github.event_name == 'workflow_dispatch' && inputs.tag || github.ref_name }}
+          RELEASE_TAG: ${{ inputs.tag }}
         run: |
           ruby <<'RUBY' >> "$GITHUB_OUTPUT"
           require "json"
@@ -104,7 +102,7 @@ jobs:
               require_string(platform, key, "#{platforms_path}: platforms[#{index}]")
             end
             archive = platform["archive"]
-            fail("#{platforms_path}: platforms[#{index}].archive must be tar.gz or zip") unless ["tar.gz", "zip"].include?(archive)
+            fail("#{platforms_path}: platforms[#{index}].archive must be tar.gz") unless archive == "tar.gz"
             platform_key = "#{platform["os"]}-#{platform["arch"]}"
             fail("#{platforms_path}: duplicate platform #{platform_key}") if seen_platforms[platform_key]
             seen_platforms[platform_key] = true
@@ -146,6 +144,8 @@ jobs:
 
           puts "tag=#{release_tag}"
           puts "version=#{version}"
+          # Docker tags forbid "+", so semver build metadata maps to "-" in image tags.
+          puts "docker_version=#{version.tr("+", "-")}"
           puts "build_time=#{Time.now.utc.iso8601}"
           puts "git_sha=#{git_sha.strip}"
           puts "platform_matrix=#{matrix}"
@@ -163,6 +163,15 @@ jobs:
       ref: ${{ needs.release-info.outputs.git_sha }}
       upload_frontend: true
 
+  container:
+    needs: [release-info]
+    permissions:
+      contents: read
+      security-events: write
+    uses: ./.github/workflows/_container.yml
+    with:
+      ref: ${{ needs.release-info.outputs.git_sha }}
+
   build-docker-binary:
     name: build-docker-binary (${{ matrix.os }}-${{ matrix.arch }})
     needs: release-info
@@ -174,7 +183,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
@@ -185,9 +194,9 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             backend/target
-          key: cargo-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock') }}
+          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
           restore-keys: |
-            cargo-${{ runner.os }}-${{ matrix.target }}-
+            cargo-v2-${{ runner.os }}-${{ matrix.target }}-
 
       - name: Build binary
         shell: bash
@@ -234,7 +243,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
@@ -250,9 +259,9 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             backend/target
-          key: cargo-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock') }}
+          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
           restore-keys: |
-            cargo-${{ runner.os }}-${{ matrix.target }}-
+            cargo-v2-${{ runner.os }}-${{ matrix.target }}-
 
       - name: Build binary
         shell: bash
@@ -286,7 +295,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
@@ -321,7 +330,6 @@ jobs:
           import pathlib
           import shutil
           import tarfile
-          import zipfile
 
           APP_NAME = "codex-proxy-rs"
 
@@ -357,8 +365,7 @@ jobs:
 
               binary_dest = package_root / platform["binary"]
               shutil.copy2(binary_src, binary_dest)
-              if platform["os"] != "windows":
-                  binary_dest.chmod(0o755)
+              binary_dest.chmod(0o755)
               shutil.copytree(frontend_dir, web_dist, dirs_exist_ok=True)
 
               archive_name = f"{APP_NAME}_{version}_{platform['os']}_{platform['arch']}.{platform['archive']}"
@@ -366,11 +373,6 @@ jobs:
               if platform["archive"] == "tar.gz":
                   with tarfile.open(archive_path, "w:gz") as archive:
                       archive.add(package_root, arcname=APP_NAME)
-              elif platform["archive"] == "zip":
-                  with zipfile.ZipFile(archive_path, "w", zipfile.ZIP_DEFLATED) as archive:
-                      for path in sorted(package_root.rglob("*")):
-                          if path.is_file():
-                              archive.write(path, path.relative_to(package_dir))
               else:
                   raise SystemExit(f"Unsupported archive format: {platform['archive']}")
               archives.append(archive_path)
@@ -382,7 +384,7 @@ jobs:
           PY
 
       - name: Generate release asset provenance
-        uses: actions/attest@f7c74d28b9d84cb8768d0b8ca14a4bac6ef463e6 # v4.2.0
+        uses: actions/attest@1e69f48acb82d1966a394da916b4c1698aa569d6 # v4.2.2
         with:
           subject-path: dist/release/*
 
@@ -412,7 +414,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
@@ -455,10 +457,10 @@ jobs:
           PY
 
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
 
       - name: Login to GHCR
-        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 # v4.4.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
@@ -475,8 +477,11 @@ jobs:
           push: true
           build-args: |
             CPR_PREBUILT_DIR=dist/docker
-          cache-from: type=gha,scope=runtime-prebuilt-${{ matrix.os }}-${{ matrix.arch }}
-          cache-to: type=gha,mode=max,scope=runtime-prebuilt-${{ matrix.os }}-${{ matrix.arch }}
+          no-cache-filters: |
+            runtime-base
+            runtime-prebuilt
+          cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:buildcache-${{ matrix.os }}-${{ matrix.arch }}
+          cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:buildcache-${{ matrix.os }}-${{ matrix.arch }},mode=min
           provenance: mode=max
           sbom: true
           labels: |
@@ -501,7 +506,7 @@ jobs:
           exit-code: '1'
 
   publish:
-    needs: [release-info, package-assets, build-docker-image]
+    needs: [release-info, package-assets, build-docker-image, container]
     runs-on: ubuntu-latest
     timeout-minutes: 20
     permissions:
@@ -512,7 +517,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
@@ -523,13 +528,13 @@ jobs:
           path: dist/release
 
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
 
       - name: Install Cosign
         uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2
 
       - name: Login to GHCR
-        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 # v4.4.0
+        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
         with:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
@@ -539,7 +544,7 @@ jobs:
         id: manifest
         shell: bash
         env:
-          VERSION: ${{ needs.release-info.outputs.version }}
+          DOCKER_VERSION: ${{ needs.release-info.outputs.docker_version }}
           GIT_SHA: ${{ needs.release-info.outputs.git_sha }}
           DOCKER_PLATFORMS: ${{ needs.release-info.outputs.docker_platforms }}
           PRERELEASE: ${{ needs.release-info.outputs.prerelease }}
@@ -562,7 +567,7 @@ jobs:
           fi
 
           target_args=(
-            -t "${image}:${VERSION}"
+            -t "${image}:${DOCKER_VERSION}"
             -t "${image}:sha-${GIT_SHA}"
           )
           if [ "$PRERELEASE" != true ]; then
@@ -570,7 +575,7 @@ jobs:
           fi
           docker buildx imagetools create "${target_args[@]}" "${sources[@]}"
 
-          inspect_output="$(docker buildx imagetools inspect "${image}:${VERSION}")"
+          inspect_output="$(docker buildx imagetools inspect "${image}:${DOCKER_VERSION}")"
           platform_list="$(awk '$1 == "Platform:" { print $2 }' <<< "${inspect_output}")"
           for platform in "${platforms[@]}"; do
             if ! grep -Eq "^${platform}(/|$)" <<< "${platform_list}"; then
@@ -580,7 +585,7 @@ jobs:
             fi
           done
 
-          digest="$(docker buildx imagetools inspect "${image}:${VERSION}" --format '{{ .Manifest.Digest }}')"
+          digest="$(docker buildx imagetools inspect "${image}:${DOCKER_VERSION}" --format '{{ .Manifest.Digest }}')"
           if [ -z "${digest}" ]; then
             echo "missing image digest"
             exit 1
@@ -588,7 +593,7 @@ jobs:
           echo "digest=${digest}" >> "$GITHUB_OUTPUT"
 
       - name: Generate container provenance attestation
-        uses: actions/attest@f7c74d28b9d84cb8768d0b8ca14a4bac6ef463e6 # v4.2.0
+        uses: actions/attest@1e69f48acb82d1966a394da916b4c1698aa569d6 # v4.2.2
         with:
           subject-name: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
           subject-digest: ${{ steps.manifest.outputs.digest }}
@@ -598,7 +603,7 @@ jobs:
         shell: bash
         env:
           DIGEST: ${{ steps.manifest.outputs.digest }}
-          VERSION: ${{ needs.release-info.outputs.version }}
+          DOCKER_VERSION: ${{ needs.release-info.outputs.docker_version }}
           GIT_SHA: ${{ needs.release-info.outputs.git_sha }}
           PRERELEASE: ${{ needs.release-info.outputs.prerelease }}
         run: |
@@ -609,7 +614,7 @@ jobs:
           fi
 
           image="${REGISTRY}/${IMAGE_NAME}"
-          tags=("${image}:${VERSION}" "${image}:sha-${GIT_SHA}")
+          tags=("${image}:${DOCKER_VERSION}" "${image}:sha-${GIT_SHA}")
           if [ "$PRERELEASE" != true ]; then
             tags+=("${image}:latest")
           fi
@@ -629,12 +634,15 @@ jobs:
           prerelease: ${{ needs.release-info.outputs.prerelease == 'true' }}
           make_latest: ${{ needs.release-info.outputs.prerelease == 'true' && 'false' || 'true' }}
           body: |
+            > [!WARNING]
+            > **Upgrading across major versions?** Online upgrades across major versions are not supported. Deploy the new major fresh with a new `.runtime/` data directory, then re-import or re-authorize provider accounts and client keys. See the [upgrade notes](https://github.com/${{ github.repository }}/blob/main/deploy/README.md#镜像升级与源码构建).
+
             ## 📥 Installation
 
             **Docker:**
             ```bash
             # GitHub Container Registry
-            docker pull ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ needs.release-info.outputs.version }}
+            docker pull ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ needs.release-info.outputs.docker_version }}
             ```
 
             **Manual download:**

.github/workflows/security-scan.yml

@@ -23,7 +23,7 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
@@ -31,7 +31,7 @@ jobs:
         uses: dtolnay/rust-toolchain@1a3a6d54512beeaffd394f8d516ca16f2c506a20 # 1.97
 
       - name: Cache Rust
-        uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
+        uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
         with:
           workspaces: backend -> target
 
@@ -47,12 +47,12 @@ jobs:
     timeout-minutes: 15
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Setup pnpm
-        uses: pnpm/action-setup@0ebf47130e4866e96fce0953f49152a61190b271 # v6.0.9
+        uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6.0.10
         with:
           version: 11.7.0
 

.gitignore

@@ -35,6 +35,7 @@ Thumbs.db
 /.codex-ws-audit/
 /.agents/
 /.reasonix/
+/.claude
 /.worktrees/
 /worktrees/
 /.cargo/

README.md

@@ -12,30 +12,32 @@
 [![GHCR](https://img.shields.io/badge/GHCR-codex--proxy--rs-2496ED?logo=docker&logoColor=white&style=flat-square)](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)
 [![MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://opensource.org/license/mit)
 
-[快速开始](#快速开始) · [客户端接入](#客户端接入) · [运维](#运维) · [部署](deploy/README.md) · [接口](docs/api.md) · [架构](docs/architecture.md)
+[快速开始](#快速开始) · [客户端接入](#客户端接入) · [运行维护](#运行维护) · [部署](deploy/README.md) · [接口](docs/api.md) · [架构](docs/architecture.md)
 
 </div>
 
 > [!NOTE]
-> 只支持 OpenAI Responses API，不提供 `/v1/chat/completions`。
+> 数据面支持 OpenAI Responses、Images 和模型目录协议，不提供 `/v1/chat/completions`。
 
-## 能力
+## 功能
 
-| 领域     | 实现                                                                        |
-| -------- | --------------------------------------------------------------------------- |
-| 协议     | OpenAI Responses JSON、SSE、WebSocket 与模型目录                             |
-| Provider | 固定 OpenAI、xAI 两个 Provider；各自管理 OAuth、账号、额度与模型目录          |
-| 路由     | Client Key 绑定 Provider、全局模型映射、会话亲和与同 Provider 安全 fallback   |
-| 透明边界 | OpenAI 保持 Responses 语义透明；xAI 的协议适配只驻留在 `providers/xai`         |
-| 延续     | OpenAI native/replay continuation；xAI 使用客户端提交的完整历史                |
-| 管理     | Client Key、账号、模型目录、设置、观测、系统更新与 OAuth                       |
-| 计量     | 模型请求 Token、费用、延迟、账号与 Provider 归因                               |
+| 领域 | 当前能力 |
+| --- | --- |
+| 数据面 | Responses JSON、SSE、WebSocket、review 子代理、Images 生成/编辑与模型目录 |
+| Provider | 固定 `openai`、`xai` 两个 Provider，各自拥有 OAuth、credential、额度、目录与 transport |
+| 路由 | Client Key 限定账号分组；按模型能力编译 Provider 候选；支持全局精确模型映射、会话亲和和安全 fallback |
+| 透明边界 | OpenAI 保留未知请求字段及字段顺序，并原样转发 SSE、WebSocket 与 Images 业务字节；xAI 在 Provider 内转换协议 |
+| 账号 | OAuth、OpenAI AT/RT 与账号文件导入，credential/额度刷新、账号恢复及主动额度重置卡 |
+| 管理 | 账号与分组、Client Key、运行设置、用量/错误观测、S3/R2 备份、系统更新与回滚 |
+| 计量 | Token、图片、费用、延迟、账号与 Provider 归因，并记录上游响应确认的实际 `service_tier` |
+
+架构边界、状态所有权和请求不变量见 [架构文档](docs/architecture.md)。
 
 ## 快速开始
 
 需要 Docker Engine 与 Docker Compose Plugin。
 
-### 1. 准备
+### 1. 准备配置和目录
 
 ```bash
 git clone https://github.com/zyycn/codex-proxy-rs.git
@@ -55,16 +57,16 @@ openssl rand -hex 24
 openssl rand -hex 24
 ```
 
-把两个结果写入 `deploy/config.yaml`，并单独设置管理员初始密码：
+把两个结果分别写入 `deploy/config.yaml`，再设置管理员初始密码：
 
-| 配置                       | 约束                         |
-| -------------------------- | ---------------------------- |
-| `store.database.password`  | 48 位十六进制                 |
-| `store.redis.password`     | 48 位十六进制                 |
-| `admin.default_password`   | 至少 12 位，不能包含 `$`      |
+| 配置 | 约束 |
+| --- | --- |
+| `store.database.password` | 48 位十六进制 |
+| `store.redis.password` | 48 位十六进制 |
+| `admin.default_password` | 至少 12 位，不能包含 `$` |
 
-PostgreSQL、Redis 容器和应用通过同一份 `config.yaml` 使用这两个基础设施密码，不需要额外
-导出环境变量。管理员密码只在首次创建管理员时生效。
+PostgreSQL、Redis 和应用从同一份 `config.yaml` 读取基础设施密码，不需要额外导出环境变量。
+管理员密码只在首次创建管理员时生效。
 
 Linux 需要允许容器组写入运行目录：
 
@@ -82,32 +84,36 @@ docker compose -f deploy/compose.yaml up -d --no-build
 curl -i http://127.0.0.1:8080/healthz
 ```
 
-`204 No Content` 表示应用、PostgreSQL 与 Redis 均可用。管理端地址：
+`204 No Content` 表示应用、PostgreSQL 与 Redis 均可用。管理端地址为
 `http://127.0.0.1:8080`。
 
-### 3. 初始化
+### 3. 初始化网关
 
 1. 使用 `admin@cpr.local` 与初始密码登录。
-2. 在账号页选择对应 Provider：OpenAI 支持 OAuth、账号文件与 Agent Identity；xAI 支持 OAuth
-   和兼容账号文件导入。
-3. 按需配置客户端模型到上游模型的全局映射；未命中映射的模型名原样透传。
-4. 创建 `sk_...` Client Key，绑定 `openai` 或 `xai`，并设置模型范围、速率与并发限制。
+2. 导入或授权 Provider 账号：OpenAI 支持 OAuth、逐行 AT/RT 与 OAuth JSON；
+   xAI 支持 OAuth 和账号 JSON。
+3. 创建账号分组并按需配置全局模型映射。未命中的模型名原样交给候选 Provider。
+4. 创建 `sk_...` Client Key，选择可用账号分组，并设置速率和并发限制；空分组范围表示全部账号。
+
+OpenAI RT 导入会先向官方 token endpoint 换取 AT；仅 AT 的账号不具备自动续期能力，
+能否参与调度仍取决于 token 中可验证的身份与后续上游事实。账号导入和首次 OAuth 创建会尽力读取一次额度，
+额度上游暂时失败不会回滚已提交的账号。
+
+OpenAI 账号的主动重置卡只在用户打开相应弹窗或手工刷新时查询。消费成功后管理端重新查询卡片与额度；
+系统不会通过修改本地 `reset_at` 伪造重置。完整账号合同见 [账号接口](docs/api.md#5-账号)。
 
 > [!IMPORTANT]
 > xAI 使用 OAuth session，不支持把 xAI API Key 作为上游 credential。
 
-> [!NOTE]
-> `admin.default_password` 只在首次创建管理员时生效。
-
-完整部署、权限和密码轮换规则见 [deploy/README.md](deploy/README.md)。
+完整的权限、密码轮换、备份和升级规则见 [部署文档](deploy/README.md)。
 
 ## 客户端接入
 
-| 配置     | 值                                       |
-| -------- | ---------------------------------------- |
-| Base URL | `http://127.0.0.1:8080/v1`               |
-| API Key  | 管理端创建的 `sk_...`                    |
-| 鉴权     | `Authorization: Bearer <client-api-key>` |
+| 配置 | 值 |
+| --- | --- |
+| Base URL | `http://127.0.0.1:8080/v1` |
+| API Key | 管理端创建的 `sk_...` |
+| 鉴权 | `Authorization: Bearer <client-api-key>` |
 
 ```bash
 curl http://127.0.0.1:8080/v1/models \
@@ -124,61 +130,70 @@ curl http://127.0.0.1:8080/v1/responses \
 ```
 
 <details>
-<summary>API 路由</summary>
+<summary>公开数据面路由</summary>
 
-| 路由                               | 用途                           |
-| ---------------------------------- | ------------------------------ |
-| `POST /v1/responses`               | JSON 响应或 SSE Responses 流    |
-| `GET /v1/responses`                | Responses WebSocket 升级        |
-| `POST /v1/responses/review`        | review 子代理请求               |
-| `GET /v1/models`                   | 当前 Client Key 可用的模型列表   |
-| `GET /v1/models/catalog`           | Codex 客户端展示用模型目录      |
-| `GET /v1/models/{model_id}/info`   | Codex 客户端展示用模型详情      |
-| `GET /v1/models/{model_id}`        | OpenAI 兼容模型详情             |
+| 路由 | 用途 |
+| --- | --- |
+| `POST /v1/responses` | JSON 响应或 SSE Responses 流 |
+| `GET /v1/responses` | Responses WebSocket 升级 |
+| `POST /v1/responses/review` | review 子代理请求 |
+| `POST /v1/images/generations` | OpenAI Images 生成 JSON 透明转发 |
+| `POST /v1/images/edits` | OpenAI Images 编辑 JSON 透明转发 |
+| `GET /v1/models` | 当前 Client Key 账号范围内的模型列表 |
+| `GET /v1/models/catalog` | Codex 客户端展示用模型目录 |
+| `GET /v1/models/{model_id}/info` | Codex 客户端展示用模型详情 |
+| `GET /v1/models/{model_id}` | OpenAI 兼容模型详情 |
 
-所有 `/v1/*` 路由都需要客户端 API Key。
+所有 `/v1/*` 路由都需要 Client Key。Images 是 OpenAI Provider 自有端点，不读取模型字段，也不参与
+文本模型映射。
 
 </details>
 
-完整的客户端与管理端路由、鉴权和 mutation 规则见 [接口文档](docs/api.md)。
+完整的客户端与管理端路由、鉴权、请求字段和 mutation 语义见 [接口文档](docs/api.md)。
 
-## 运维
+## 运行维护
 
 ```bash
-# 升级
+# 同一大版本内升级发布镜像
 docker compose -f deploy/compose.yaml pull codex-proxy-rs
 docker compose -f deploy/compose.yaml up -d --no-build
 
-# 日志
+# 查看日志
 docker compose -f deploy/compose.yaml logs -f codex-proxy-rs
 
-# 从源码构建
+# 从当前源码构建
 docker compose -f deploy/compose.yaml build codex-proxy-rs
 docker compose -f deploy/compose.yaml up -d
 ```
 
 > [!IMPORTANT]
-> `.runtime/` 保存 PostgreSQL、Redis、日志、OpenAI 会话锚点和自更新状态。删除该目录会永久清除
-> 运行状态。
+> `.runtime/` 保存 PostgreSQL、Redis、日志、OpenAI 会话锚点和在线更新状态。删除该目录会永久清除
+> 本地运行状态。
 
-Compose 默认只绑定 `127.0.0.1`。公网接入应使用 HTTPS 反向代理，转发 WebSocket
-upgrade 与真实客户端 IP；不要暴露 PostgreSQL 或 Redis。
+> [!WARNING]
+> 不支持跨大版本在线升级。升级到新的大版本时请使用全新的 `.runtime/` 数据目录，并重新导入或授权
+> Provider 账号与 Client Key。
+
+Compose 默认只绑定 `127.0.0.1`。公网接入应使用 HTTPS 反向代理，转发 WebSocket upgrade 与真实客户端
+IP；不要暴露 PostgreSQL 或 Redis。当前运行拓扑为单副本，不能通过复制应用容器扩容。
 
 ## 维护与发布
 
-发布仓库版本必须从干净、已同步上游的发布分支运行：
+仓库版本只能从干净、已同步上游的发布分支发布：
 
 ```bash
 release/publish <version>
 ```
 
-脚本会更新 `release/version.yaml`、创建约定提交与带注释的 `v<version>` tag，并原子推送分支和 tag。
-不要手工修改版本后单独打 tag。
+脚本依赖已登录的 GitHub CLI（`gh auth login`），会更新 `release/version.yaml`、创建约定提交和带注释的
+`v<version>` tag，原子推送分支与 tag，再触发 Release 构建。源码提交、仓库发版和运行实例升级是三个
+独立状态；脚本不会登录服务器或改变任何运行实例。
 
 ## 文档
 
-- [部署](deploy/README.md)
+- [部署与运维](deploy/README.md)
 - [客户端与管理端接口](docs/api.md)
-- [架构与数据边界](docs/architecture.md)
+- [系统架构](docs/architecture.md)
+- [数据库迁移规则](backend/migrations/README.md)
 - [Release](https://github.com/zyycn/codex-proxy-rs/releases)
 - [容器镜像](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)

backend/apps/gateway/Cargo.toml

@@ -25,7 +25,8 @@ tokio = { version = "1.52.3", default-features = false, features = ["rt-multi-th
 
 [dev-dependencies]
 config = { version = "0.15.23", default-features = false, features = ["yaml"] }
-syn = { version = "2.0.118", features = ["full"] }
+serde_json = "1"
+syn = { version = "3.0.3", features = ["full"] }
 tempfile = "3.27.0"
 
 [lints]

backend/apps/gateway/src/bootstrap.rs

@@ -27,8 +27,9 @@ impl LoadableConfig for GatewayConfig {
             return Err(ConfigError::InvalidField("schema_version"));
         }
         self.host.resolve_and_validate(source_dir)?;
+        let runtime_data_dir = self.host.runtime_data_dir().to_path_buf();
         self.store
-            .resolve_and_validate(source_dir)
+            .resolve_and_validate(&runtime_data_dir)
             .map_err(|_| ConfigError::InvalidField("store"))?;
         self.admin
             .resolve_and_validate(source_dir)
@@ -37,7 +38,7 @@ impl LoadableConfig for GatewayConfig {
             .resolve_and_validate(source_dir)
             .map_err(|_| ConfigError::InvalidField("api"))?;
         self.openai
-            .resolve_and_validate(source_dir)
+            .resolve_and_validate(&runtime_data_dir)
             .map_err(|_| ConfigError::InvalidField("openai"))?;
         self.xai
             .resolve_and_validate(source_dir)
@@ -72,7 +73,7 @@ pub async fn run() -> Result<(), BootstrapError> {
     let providers = ProviderRegistry::new([openai.core_provider(), xai.core_provider()])?;
     let mut core = gateway_core::initialize(store.core_ports(), providers).await?;
     host.report_startup_ready("Core");
-    let admin = gateway_admin::initialize(
+    let mut admin = gateway_admin::initialize(
         admin,
         store.admin_ports(),
         vec![openai.admin_provider(), xai.admin_provider()],
@@ -99,6 +100,7 @@ pub async fn run() -> Result<(), BootstrapError> {
     plan.extend(core.take_worker_contributions());
     plan.extend(openai.take_worker_contributions());
     plan.extend(xai.take_worker_contributions());
+    plan.extend(admin.take_worker_contributions());
     host.start_workers(plan, store.worker_leader_lease())?;
     host.report_startup_ready("Workers");
     host.serve(api.router()).await?;

backend/apps/gateway/src/main.rs

@@ -1,6 +1,9 @@
 use std::{env, error::Error, io};
 
+use provider_openai::transport::tls::ensure_rustls_provider;
+
 fn main() -> Result<(), Box<dyn Error + Send + Sync>> {
+    ensure_rustls_provider();
     let mut arguments = env::args_os().skip(1);
     match arguments.next().as_deref().and_then(|value| value.to_str()) {
         None | Some("serve") => {

backend/apps/gateway/tests/architecture.rs

@@ -0,0 +1,238 @@
+//! docs/architecture.md 依赖 DAG 与生产源码纪律的 workspace 级机器校验。
+
+use std::{
+    fs,
+    path::{Path, PathBuf},
+};
+
+/// workspace 成员冻结清单;新增 crate 必须同步扩展本文件的依赖规则。
+const WORKSPACE_MEMBERS: &[&str] = &[
+    "apps/gateway",
+    "crates/gateway-admin",
+    "crates/gateway-api",
+    "crates/gateway-core",
+    "crates/gateway-host",
+    "crates/gateway-protocol",
+    "crates/gateway-store",
+    "crates/providers/openai",
+    "crates/providers/xai",
+];
+
+#[test]
+fn workspace_member_list_matches_the_frozen_dag_scope() {
+    let manifest =
+        fs::read_to_string(backend_root().join("Cargo.toml")).expect("read workspace manifest");
+    for member in WORKSPACE_MEMBERS {
+        assert!(
+            manifest.contains(&format!("\"{member}\"")),
+            "workspace must include {member}"
+        );
+    }
+    let member_count = manifest
+        .lines()
+        .map(str::trim)
+        .filter(|line| line.starts_with("\"apps/") || line.starts_with("\"crates/"))
+        .count();
+    assert_eq!(
+        member_count,
+        WORKSPACE_MEMBERS.len(),
+        "new workspace members must extend the dependency DAG rules"
+    );
+}
+
+#[test]
+fn gateway_core_depends_on_no_http_db_redis_or_provider_crate() {
+    assert_no_dependency(
+        "crates/gateway-core",
+        &[
+            "axum",
+            "hyper",
+            "reqwest",
+            "sqlx",
+            "redis",
+            "gateway-host",
+            "gateway-store",
+            "provider-openai",
+            "provider-xai",
+        ],
+    );
+}
+
+#[test]
+fn gateway_protocol_has_no_workspace_dependencies() {
+    for name in dependency_names("crates/gateway-protocol") {
+        assert!(
+            !name.starts_with("gateway-") && !name.starts_with("provider-"),
+            "gateway-protocol must not depend on workspace crate `{name}`"
+        );
+    }
+}
+
+#[test]
+fn provider_crates_do_not_depend_on_each_other() {
+    assert_no_dependency("crates/providers/openai", &["provider-xai"]);
+    assert_no_dependency("crates/providers/xai", &["provider-openai"]);
+}
+
+#[test]
+fn gateway_admin_stays_free_of_infrastructure_dependencies() {
+    assert_no_dependency(
+        "crates/gateway-admin",
+        &["axum", "sqlx", "redis", "reqwest"],
+    );
+}
+
+/// workspace 包名到冻结成员路径的映射。
+const PACKAGE_TO_MEMBER: &[(&str, &str)] = &[
+    ("codex-proxy-rs", "apps/gateway"),
+    ("gateway-admin", "crates/gateway-admin"),
+    ("gateway-api", "crates/gateway-api"),
+    ("gateway-core", "crates/gateway-core"),
+    ("gateway-host", "crates/gateway-host"),
+    ("gateway-protocol", "crates/gateway-protocol"),
+    ("gateway-store", "crates/gateway-store"),
+    ("provider-openai", "crates/providers/openai"),
+    ("provider-xai", "crates/providers/xai"),
+];
+
+/// 冻结的 workspace 内部运行时依赖边；新增/删除任何边都必须同步本表。
+const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
+    ("codex-proxy-rs", "gateway-admin"),
+    ("codex-proxy-rs", "gateway-api"),
+    ("codex-proxy-rs", "gateway-core"),
+    ("codex-proxy-rs", "gateway-host"),
+    ("codex-proxy-rs", "gateway-store"),
+    ("codex-proxy-rs", "provider-openai"),
+    ("codex-proxy-rs", "provider-xai"),
+    ("gateway-admin", "gateway-core"),
+    ("gateway-api", "gateway-admin"),
+    ("gateway-api", "gateway-core"),
+    ("gateway-api", "gateway-protocol"),
+    ("gateway-host", "gateway-admin"),
+    ("gateway-host", "gateway-core"),
+    ("gateway-store", "gateway-admin"),
+    ("gateway-store", "gateway-core"),
+    ("provider-openai", "gateway-admin"),
+    ("provider-openai", "gateway-core"),
+    ("provider-openai", "gateway-protocol"),
+    ("provider-xai", "gateway-admin"),
+    ("provider-xai", "gateway-core"),
+    ("provider-xai", "gateway-protocol"),
+];
+
+#[test]
+fn workspace_internal_dependency_edges_match_frozen_dag() {
+    let metadata = cargo_metadata_json();
+    let packages = metadata["packages"]
+        .as_array()
+        .expect("cargo metadata packages");
+    let internal_names: std::collections::BTreeSet<&str> =
+        PACKAGE_TO_MEMBER.iter().map(|(name, _)| *name).collect();
+
+    let mut actual: Vec<(String, String)> = Vec::new();
+    for package in packages {
+        let name = package["name"].as_str().expect("package name");
+        if !internal_names.contains(name) {
+            continue;
+        }
+        for dependency in package["dependencies"].as_array().into_iter().flatten() {
+            let dep_name = dependency["name"].as_str().expect("dependency name");
+            if !internal_names.contains(dep_name) {
+                continue;
+            }
+            let is_runtime_edge = dependency["dep_kinds"]
+                .as_array()
+                .map(|kinds| {
+                    kinds
+                        .iter()
+                        .any(|kind| kind["kind"].as_str() == Some("normal"))
+                })
+                .unwrap_or(true);
+            if is_runtime_edge {
+                actual.push((name.to_owned(), dep_name.to_owned()));
+            }
+        }
+    }
+
+    let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
+        .iter()
+        .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
+        .collect();
+    actual.sort();
+    expected.sort();
+
+    assert_eq!(
+        actual, expected,
+        "workspace internal dependency edges diverged from the frozen DAG"
+    );
+}
+
+#[test]
+fn production_sources_do_not_host_tests() {
+    for member in WORKSPACE_MEMBERS {
+        let src = backend_root().join(member).join("src");
+        let sources = super::rust_files(&src);
+        assert!(!sources.is_empty(), "{member} has no production sources");
+        for relative in sources {
+            let path = src.join(relative);
+            let source = fs::read_to_string(&path).expect("read production source");
+            assert!(
+                !source.contains("#[cfg(test)]"),
+                "{} hosts tests in production src",
+                path.display()
+            );
+        }
+    }
+}
+
+fn backend_root() -> PathBuf {
+    Path::new(env!("CARGO_MANIFEST_DIR"))
+        .join("../..")
+        .canonicalize()
+        .expect("backend workspace root")
+}
+
+fn cargo_metadata_json() -> serde_json::Value {
+    let output = std::process::Command::new("cargo")
+        .args(["metadata", "--format-version", "1", "--no-deps"])
+        .current_dir(backend_root())
+        .output()
+        .expect("run cargo metadata");
+    assert!(
+        output.status.success(),
+        "cargo metadata failed: {}",
+        String::from_utf8_lossy(&output.stderr)
+    );
+    serde_json::from_slice(&output.stdout).expect("parse cargo metadata")
+}
+
+/// 提取成员 `[dependencies]` 段内声明的依赖名;段落以下一个 `[` 表头结束。
+fn dependency_names(member: &str) -> Vec<String> {
+    let manifest = fs::read_to_string(backend_root().join(member).join("Cargo.toml"))
+        .expect("read member manifest");
+    let mut in_dependencies = false;
+    let mut names = Vec::new();
+    for line in manifest.lines() {
+        let line = line.trim();
+        if line.starts_with('[') {
+            in_dependencies = line == "[dependencies]";
+            continue;
+        }
+        if !in_dependencies || line.is_empty() || line.starts_with('#') {
+            continue;
+        }
+        if let Some((name, _)) = line.split_once('=') {
+            names.push(name.trim().to_owned());
+        }
+    }
+    names
+}
+
+fn assert_no_dependency(member: &str, forbidden: &[&str]) {
+    for name in dependency_names(member) {
+        assert!(
+            !forbidden.contains(&name.as_str()),
+            "{member} must not depend on `{name}`"
+        );
+    }
+}

backend/apps/gateway/tests/bootstrap.rs

@@ -18,10 +18,18 @@ fn config_loader_should_load_complete_terminal_example() {
 fn config_loader_should_resolve_paths_relative_to_config_file() {
     let (config, _directory) = parse_config(&valid_config()).expect("resolved config");
     let debug = format!("{config:?}");
+    assert!(debug.contains(".runtime/data"));
     assert!(debug.contains(".runtime/logs"));
     assert!(debug.contains("frontend/dist"));
 }
 
+#[test]
+fn config_loader_should_reject_missing_runtime_data_dir() {
+    let config = valid_config().replace("  runtime_data_dir: '../.runtime/data'\n", "");
+
+    assert!(parse_config(&config).is_err());
+}
+
 #[test]
 fn config_loader_should_inject_connection_passwords_into_urls() {
     parse_config(&valid_config()).expect("Store validates password injection into both URLs");
@@ -134,8 +142,11 @@ fn config_loader_should_reject_removed_fingerprint_section() {
 }
 
 #[test]
-fn config_loader_should_reject_invalid_codex_core_version() {
-    assert_rejected(valid_config().replace("codex_version: '0.145.0'", "codex_version: 'latest'"));
+fn config_loader_should_reject_invalid_codex_cli_version() {
+    assert_rejected(valid_config().replace(
+        "codex_version: '0.147.0-alpha.6.6'",
+        "codex_version: 'latest'",
+    ));
 }
 
 #[test]
@@ -154,7 +165,7 @@ fn config_loader_should_reject_zero_server_port() {
 
 #[test]
 fn config_loader_should_reject_invalid_desktop_profile_fields() {
-    assert_rejected(valid_config().replace("desktop_build: '5828'", "desktop_build: 'build'"));
+    assert_rejected(valid_config().replace("desktop_build: '6415'", "desktop_build: 'build'"));
 }
 
 fn assert_rejected(config: String) {

backend/apps/gateway/tests/main.rs

@@ -1,3 +1,4 @@
+mod architecture;
 mod bootstrap;
 
 use std::{
@@ -21,7 +22,11 @@ fn app_tree_matches_frozen_terminal_manifest() {
     );
     assert_eq!(
         rust_files(&root.join("tests")),
-        BTreeSet::from([PathBuf::from("bootstrap.rs"), PathBuf::from("main.rs")]),
+        BTreeSet::from([
+            PathBuf::from("architecture.rs"),
+            PathBuf::from("bootstrap.rs"),
+            PathBuf::from("main.rs"),
+        ]),
     );
 }
 

backend/crates/gateway-admin/Cargo.toml

@@ -12,9 +12,10 @@ name = "main"
 path = "tests/main.rs"
 
 [dependencies]
-argon2 = "0.5.3"
+argon2 = "0.6.0"
 async-trait = "0.1.89"
-base64 = "0.22.1"
+base64 = "0.23.0"
+bytes = "1.11.1"
 chrono = "0.4.45"
 futures = "0.3.32"
 gateway-core = { path = "../gateway-core" }
@@ -24,9 +25,16 @@ serde = { version = "1.0.228", features = ["derive"] }
 secrecy = { version = "0.10.3", features = ["serde"] }
 subtle = "2.6.1"
 thiserror = "2.0.18"
+tracing = "0.1.44"
 uuid = { version = "1.23.3", features = ["v7"] }
+cron = "0.17"
+chrono-tz = "0.10"
+tokio = { version = "1.52", features = ["rt", "time", "macros", "sync"] }
 
 [dev-dependencies]
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
+sha2 = "0.11"
+tempfile = "3"
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }
 
 [lints]

backend/crates/gateway-admin/src/backup/mod.rs

@@ -0,0 +1,4 @@
+//! 备份纯策略与 Worker 任务。
+
+pub mod policy;
+pub mod task;

backend/crates/gateway-admin/src/backup/policy.rs

@@ -0,0 +1,161 @@
+//! 备份纯策略：Cron 推进与保留候选。
+//!
+//! 本模块不持有任何端口或对象，是 `BackupService` 与 `BackupTask` 共用的纯函数集。
+
+use std::str::FromStr;
+
+use chrono::{DateTime, Duration, TimeZone as _, Utc};
+use chrono_tz::Tz;
+use cron::Schedule;
+
+use crate::model::backup::{BackupError, BackupRecord, BackupStatus, code};
+
+/// 向历史回溯的最大范围（分钟）。覆盖 Feb 29 + 特定星期等罕见组合的最长间隔。
+const MAX_BACKDATE_MINUTES: i64 = 40 * 366 * 24 * 60;
+
+/// 已解析并校验的备份计划。
+#[derive(Debug, Clone)]
+pub struct BackupSchedule {
+    schedule: Schedule,
+    timezone: Tz,
+}
+
+impl BackupSchedule {
+    /// 解析并校验 5 段 Cron 与 IANA 时区。
+    ///
+    /// # Errors
+    ///
+    /// Cron 非法或时区不是 IANA 名称时返回 [`BackupError`]。
+    pub fn parse(cron_expression: &str, schedule_timezone: &str) -> Result<Self, BackupError> {
+        let expression = format!("0 {cron_expression}");
+        let schedule = Schedule::from_str(&expression).map_err(|_| {
+            BackupError::new(code::INVALID_CRON, "Cron 表达式必须是 5 段格式".to_owned())
+        })?;
+        let timezone = schedule_timezone.parse::<Tz>().map_err(|_| {
+            BackupError::new(code::INVALID_TIMEZONE, "时区必须是 IANA 名称".to_owned())
+        })?;
+        Ok(Self { schedule, timezone })
+    }
+
+    /// 返回最接近 `at`（含 `at` 所在分钟）的最近一次触发时间。
+    ///
+    /// 若过去 `MAX_BACKDATE_MINUTES` 内没有任何触发（极罕见的稀疏计划或超长停机），
+    /// 返回 `None`，调用方不应为历史点补任务。
+    #[must_use]
+    pub fn last_firing_at_or_before(&self, at: DateTime<Utc>) -> Option<DateTime<Utc>> {
+        let high_min = at.timestamp().div_euclid(60);
+        let low_min = high_min.saturating_sub(MAX_BACKDATE_MINUTES);
+
+        // 检查窗口内是否存在触发；不存在则直接返回 None。
+        let low_instant = instant(low_min, self.timezone)?;
+        if self
+            .schedule
+            .after(&low_instant)
+            .next()
+            .is_none_or(|firing| firing.timestamp() > high_min * 60 + 59)
+        {
+            return None;
+        }
+
+        // 二分查找最小的 u（分钟）使 after(u) > high；prev = after(u - 1 分钟)。
+        let mut lo = low_min;
+        let mut hi = high_min;
+        while lo < hi {
+            let mid = lo + (hi - lo) / 2;
+            if self
+                .firing_after(mid)
+                .is_some_and(|firing| firing > high_min)
+            {
+                hi = mid;
+            } else {
+                lo = mid + 1;
+            }
+        }
+        self.firing_after(lo - 1)
+            .filter(|&firing| firing <= high_min)
+            .and_then(|firing| Utc.timestamp_opt(firing * 60, 0).single())
+    }
+
+    /// 返回第一个严格晚于 `at` 的触发时间。
+    #[must_use]
+    pub fn next_after(&self, at: DateTime<Utc>) -> Option<DateTime<Utc>> {
+        let local = at.with_timezone(&self.timezone);
+        self.schedule
+            .after(&local)
+            .next()
+            .map(|firing| firing.with_timezone(&Utc))
+    }
+
+    /// `after(u 分钟)` 返回的第一个触发时间（分钟索引），用于二分搜索。
+    fn firing_after(&self, minute_index: i64) -> Option<i64> {
+        let instant = instant(minute_index, self.timezone)?;
+        self.schedule
+            .after(&instant)
+            .next()
+            .map(|firing| firing.timestamp().div_euclid(60))
+    }
+}
+
+/// 构造指定分钟索引（UTC epoch 分钟）在目标时区下的 `DateTime`。
+fn instant(minute_index: i64, timezone: Tz) -> Option<DateTime<Tz>> {
+    timezone.timestamp_opt(minute_index * 60, 0).single()
+}
+
+/// 一条记录被纳入删除流程的原因。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum RetentionReason {
+    /// 超过 `retention_days`。
+    Days,
+    /// 超过 `retention_count`。
+    Count,
+}
+
+/// 保留决策。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct RetentionDecision {
+    pub record_id: String,
+    pub reason: RetentionReason,
+}
+
+/// 从按完成时间倒序的 completed 计划备份中决定纳入删除流程的记录。
+///
+/// 自动保留规则：
+/// - `retentionDays = 0` 时不按天数清理；`retentionCount = 0` 时不按份数清理。
+/// - 自动计划备份满足任一启用阈值即可进入删除。
+/// - 无论阈值如何，至少保留最近一个成功的计划备份（倒序下标 0）。
+/// - 手动备份不进入本规则；手工/计划记录各自的 `expires_at` 由到期扫描处理。
+#[must_use]
+pub fn decide_retention(
+    retention_days: u32,
+    retention_count: u32,
+    now: DateTime<Utc>,
+    scheduled_completed_desc: &[BackupRecord],
+) -> Vec<RetentionDecision> {
+    let mut decisions = Vec::new();
+    for (index, record) in scheduled_completed_desc.iter().enumerate() {
+        if record.status != BackupStatus::Completed {
+            continue;
+        }
+        // 最近一个成功的计划备份永远保留。
+        if index == 0 {
+            continue;
+        }
+        let expired_by_days = retention_days > 0
+            && record.completed_at.is_some_and(|completed_at| {
+                completed_at <= now - Duration::days(i64::from(retention_days))
+            });
+        let exceeded_count =
+            retention_count > 0 && index >= usize::try_from(retention_count).unwrap_or(usize::MAX);
+        if expired_by_days || exceeded_count {
+            decisions.push(RetentionDecision {
+                record_id: record.id.clone(),
+                reason: if expired_by_days {
+                    RetentionReason::Days
+                } else {
+                    RetentionReason::Count
+                },
+            });
+        }
+    }
+    decisions
+}

backend/crates/gateway-admin/src/backup/task.rs

@@ -0,0 +1,648 @@
+//! Backup Worker 贡献：单个可取消 `DaemonTask` 承担调度、执行、删除收敛与保留清理。
+//!
+//! 当前部署边界是单副本，因此不需要 Redis lease、fencing token 或 heartbeat。长时间
+//! `pg_dump` 与上传由本 Daemon 自身持有；Host 只负责 panic 后重启、健康与关闭。
+
+use std::sync::Arc;
+use std::time::Duration;
+
+use chrono::{DateTime, Utc};
+use futures::future::BoxFuture;
+use gateway_core::{
+    engine::CancellationToken,
+    task::{DaemonTask, WorkerTaskError},
+};
+use tracing::{info, warn};
+
+use crate::{
+    model::backup::{
+        BackupError, BackupObjectMetadata, BackupRecord, BackupStatus, BackupStorageConfig,
+        BackupTriggerKind, build_backup_seed, code,
+    },
+    ports::backup::{
+        BackupObjectStorePort, BackupRepository, DatabaseDumpPort, DumpRequest,
+        StatusTransitionUpdate, UploadObjectRequest,
+    },
+};
+
+impl From<BackupError> for WorkerTaskError {
+    fn from(error: BackupError) -> Self {
+        WorkerTaskError::safe(error.message())
+    }
+}
+
+use super::policy::{BackupSchedule, decide_retention};
+
+/// 循环间隔：管理员修改 Cron 后该时长内生效；无工作时可取消等待。
+const BACKUP_LOOP_INTERVAL: Duration = Duration::from_secs(30);
+/// 每个循环最多执行的保留删除数量。
+const RETENTION_BATCH_SIZE: usize = 10;
+/// 保留扫描一次读取的 completed 计划备份上限。
+const RETENTION_SCAN_LIMIT: u32 = 1000;
+/// 每个循环最多完成的待删除记录数量。
+const PENDING_DELETION_BATCH: u32 = 20;
+
+/// 备份 Daemon 任务。
+pub struct BackupTask {
+    repository: Arc<dyn BackupRepository>,
+    dump: Arc<dyn DatabaseDumpPort>,
+    object_store: Arc<dyn BackupObjectStorePort>,
+}
+
+impl BackupTask {
+    /// 组合仓储、导出器与对象存储适配器。
+    #[must_use]
+    pub fn new(
+        repository: Arc<dyn BackupRepository>,
+        dump: Arc<dyn DatabaseDumpPort>,
+        object_store: Arc<dyn BackupObjectStorePort>,
+    ) -> Self {
+        Self {
+            repository,
+            dump,
+            object_store,
+        }
+    }
+}
+
+impl DaemonTask for BackupTask {
+    fn run(&self, cancellation: CancellationToken) -> BoxFuture<'_, Result<(), WorkerTaskError>> {
+        Box::pin(async move { self.run_daemon(cancellation).await })
+    }
+}
+
+impl BackupTask {
+    async fn run_daemon(&self, cancellation: CancellationToken) -> Result<(), WorkerTaskError> {
+        loop {
+            if cancellation.is_cancelled() {
+                return Ok(());
+            }
+            self.run_cycle(&cancellation).await?;
+
+            tokio::select! {
+                _ = cancellation.cancelled() => return Ok(()),
+                _ = tokio::time::sleep(BACKUP_LOOP_INTERVAL) => {}
+            }
+        }
+    }
+
+    /// 执行一个周期：推进计划、恢复中间态、删除收敛、领取执行一个任务、保留清理。
+    ///
+    /// 对外暴露以便集成测试逐周期驱动；daemon 循环内部复用。
+    ///
+    /// # Errors
+    ///
+    /// 仓储或基础设施不可用、任务执行失败时返回 [`WorkerTaskError`]。
+    pub async fn run_cycle(&self, cancellation: &CancellationToken) -> Result<(), WorkerTaskError> {
+        if cancellation.is_cancelled() {
+            return Ok(());
+        }
+        self.advance_schedule(Utc::now()).await?;
+        self.recover_intermediate(cancellation).await?;
+        self.finish_pending_deletions().await?;
+        self.process_next_task(cancellation).await?;
+        self.run_retention_batch(Utc::now()).await?;
+        Ok(())
+    }
+
+    /// 推进到期计划并幂等插入 scheduled 任务。
+    async fn advance_schedule(&self, now: DateTime<Utc>) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        if !settings.schedule_enabled {
+            return Ok(());
+        }
+        let cron = settings.cron_expression.as_deref().unwrap_or_default();
+        let timezone = settings.schedule_timezone.as_deref().unwrap_or_default();
+        if cron.is_empty() || timezone.is_empty() {
+            return Ok(());
+        }
+        let schedule = BackupSchedule::parse(cron, timezone)
+            .map_err(|_| WorkerTaskError::safe("backup schedule is invalid"))?;
+
+        let due = match settings.next_run_at {
+            Some(next_run_at) if next_run_at <= now => true,
+            Some(_) => false,
+            None => {
+                // 刚启用计划但尚无游标：直接初始化。
+                if let Some(next_run_at) = schedule.next_after(now) {
+                    let _ = self
+                        .repository
+                        .advance_schedule_cursor(next_run_at, cron, timezone)
+                        .await
+                        .map_err(repo_error)?;
+                }
+                return Ok(());
+            }
+        };
+        if !due {
+            return Ok(());
+        }
+
+        let scheduled_at = match schedule.last_firing_at_or_before(now) {
+            Some(scheduled_at) => scheduled_at,
+            None => {
+                // 无法从计划推导最近到期时间：推进游标避免反复触发。
+                if let Some(next_run_at) = schedule.next_after(now) {
+                    let _ = self
+                        .repository
+                        .advance_schedule_cursor(next_run_at, cron, timezone)
+                        .await
+                        .map_err(repo_error)?;
+                }
+                return Ok(());
+            }
+        };
+        let prefix = settings.prefix.as_deref().unwrap_or_default();
+        let expires_at = if settings.retention_days > 0 {
+            Some(now + chrono::Duration::days(i64::from(settings.retention_days)))
+        } else {
+            None
+        };
+        let seed = build_backup_seed(
+            BackupTriggerKind::Scheduled,
+            Some(scheduled_at),
+            prefix,
+            now,
+            expires_at,
+        )
+        .map_err(infra_error)?;
+        let inserted = self
+            .repository
+            .insert_scheduled_record(seed)
+            .await
+            .map_err(repo_error)?;
+        if inserted {
+            info!(scheduled_at = %scheduled_at, "计划备份任务已创建");
+        } else {
+            warn!(scheduled_at = %scheduled_at, "计划时间点冲突，跳过并推进游标");
+        }
+        if let Some(next_run_at) = schedule.next_after(now) {
+            let _ = self
+                .repository
+                .advance_schedule_cursor(next_run_at, cron, timezone)
+                .await
+                .map_err(repo_error)?;
+        }
+        Ok(())
+    }
+
+    /// 恢复中间状态（dumping/uploading/deleting）。
+    async fn recover_intermediate(
+        &self,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        let records = self
+            .repository
+            .list_intermediate_records()
+            .await
+            .map_err(repo_error)?;
+        for record in records {
+            match record.status {
+                BackupStatus::Dumping => self.recover_dumping(&record, cancellation).await?,
+                BackupStatus::Uploading => self.recover_uploading(&record, cancellation).await?,
+                _ => {}
+            }
+        }
+        Ok(())
+    }
+
+    /// dumping：有完整暂存则继续上传，否则清理暂存并标记失败。
+    async fn recover_dumping(
+        &self,
+        record: &BackupRecord,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        match self.dump.inspect_staging(&record.id).await? {
+            Some(artifact) => {
+                let now = Utc::now();
+                let update = StatusTransitionUpdate {
+                    size_bytes: Some(artifact.size_bytes),
+                    sha256: Some(artifact.sha256.clone()),
+                    ..Default::default()
+                };
+                let Some(uploading_record) = self
+                    .repository
+                    .transition_status(
+                        &record.id,
+                        BackupStatus::Dumping,
+                        BackupStatus::Uploading,
+                        update,
+                        now,
+                    )
+                    .await
+                    .map_err(repo_error)?
+                else {
+                    return Ok(());
+                };
+                self.upload_and_verify(
+                    &uploading_record,
+                    &artifact.path,
+                    artifact.size_bytes,
+                    &artifact.sha256,
+                    now,
+                    cancellation,
+                )
+                .await?;
+            }
+            None => {
+                let _ = self.dump.cleanup_staging(&record.id).await;
+                self.fail_task(record, code::PG_DUMP_FAILED, "导出进程中断，暂存归档不完整")
+                    .await?;
+            }
+        }
+        Ok(())
+    }
+
+    /// uploading：远端匹配则补记完成，有完整暂存则重试上传，否则失败。
+    async fn recover_uploading(
+        &self,
+        record: &BackupRecord,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Ok(());
+        };
+        if let Some(remote) = self
+            .object_store
+            .head_object(&config, &record.object_key)
+            .await?
+            && record.size_bytes == Some(remote.size_bytes)
+            && record.sha256.as_deref() == Some(remote.sha256.as_str())
+        {
+            let now = Utc::now();
+            self.repository
+                .transition_status(
+                    &record.id,
+                    BackupStatus::Uploading,
+                    BackupStatus::Completed,
+                    StatusTransitionUpdate::default(),
+                    now,
+                )
+                .await
+                .map_err(repo_error)?;
+            return Ok(());
+        }
+        match self.dump.inspect_staging(&record.id).await? {
+            Some(artifact) => {
+                self.upload_and_verify(
+                    record,
+                    &artifact.path,
+                    artifact.size_bytes,
+                    &artifact.sha256,
+                    Utc::now(),
+                    cancellation,
+                )
+                .await
+            }
+            None => {
+                self.fail_task(
+                    record,
+                    code::S3_UPLOAD_FAILED,
+                    "远端对象缺失且本地无完整暂存",
+                )
+                .await
+            }
+        }
+    }
+
+    /// 完成待删除记录（deleting → DeleteObject → 硬删除）。
+    async fn finish_pending_deletions(&self) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Ok(());
+        };
+        let records = self
+            .repository
+            .list_pending_deletions(PENDING_DELETION_BATCH)
+            .await
+            .map_err(repo_error)?;
+        for record in records {
+            if self
+                .object_store
+                .delete_object(&config, &record.object_key)
+                .await
+                .is_ok()
+            {
+                self.repository
+                    .delete_record(&record.id)
+                    .await
+                    .map_err(repo_error)?;
+            }
+        }
+        Ok(())
+    }
+
+    /// 领取一个 queued 任务并执行导出、上传与远端校验。
+    async fn process_next_task(
+        &self,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        let now = Utc::now();
+        let Some(record) = self
+            .repository
+            .claim_next_queued(now)
+            .await
+            .map_err(repo_error)?
+        else {
+            return Ok(());
+        };
+        info!(
+            backup_id = %record.id,
+            attempt = record.attempt_count,
+            "领取备份任务"
+        );
+        if let Err(error) = self.execute_task(&record, cancellation).await {
+            warn!(backup_id = %record.id, error = %error, "备份任务执行失败");
+        }
+        Ok(())
+    }
+
+    /// 执行单个任务；内部处理全部状态迁移。
+    async fn execute_task(
+        &self,
+        record: &BackupRecord,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        if BackupStorageConfig::from_settings(&settings).is_none() {
+            return self
+                .fail_task(record, code::INVALID_CONFIG, "备份存储配置不完整")
+                .await;
+        }
+        if !settings.storage_verified() {
+            return self
+                .fail_task(record, code::INVALID_CONFIG, "备份存储配置尚未通过连接测试")
+                .await;
+        }
+
+        let now = Utc::now();
+        let artifact = match self
+            .dump
+            .dump(DumpRequest {
+                backup_id: record.id.clone(),
+                cancellation: cancellation.clone(),
+            })
+            .await
+        {
+            Ok(artifact) => artifact,
+            Err(error) => {
+                let (error_code, message) = classify_dump_error(error);
+                return self.fail_task(record, error_code, message).await;
+            }
+        };
+
+        // dumping → uploading，持久化 size/sha256。
+        let update = StatusTransitionUpdate {
+            size_bytes: Some(artifact.size_bytes),
+            sha256: Some(artifact.sha256.clone()),
+            ..Default::default()
+        };
+        let Some(uploading_record) = self
+            .repository
+            .transition_status(
+                &record.id,
+                BackupStatus::Dumping,
+                BackupStatus::Uploading,
+                update,
+                now,
+            )
+            .await
+            .map_err(repo_error)?
+        else {
+            return Ok(());
+        };
+
+        self.upload_and_verify(
+            &uploading_record,
+            &artifact.path,
+            artifact.size_bytes,
+            &artifact.sha256,
+            now,
+            cancellation,
+        )
+        .await?;
+        let _ = self.dump.cleanup_staging(&record.id).await;
+        Ok(())
+    }
+
+    /// 上传 + 远端校验，内部完成终态迁移。
+    async fn upload_and_verify(
+        &self,
+        record: &BackupRecord,
+        source: &std::path::Path,
+        size_bytes: u64,
+        sha256: &str,
+        now: DateTime<Utc>,
+        cancellation: &CancellationToken,
+    ) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Ok(());
+        };
+        let store = self.object_store.clone();
+        let metadata =
+            BackupObjectMetadata::new(record.id.clone(), sha256.to_owned(), now, size_bytes);
+        if let Err(error) = store
+            .upload_file(
+                &config,
+                UploadObjectRequest {
+                    object_key: record.object_key.clone(),
+                    source: source.to_path_buf(),
+                    metadata,
+                    cancellation: cancellation.clone(),
+                },
+            )
+            .await
+        {
+            let _ = store.delete_object(&config, &record.object_key).await;
+            self.fail_task(
+                record,
+                error.code(),
+                format!("上传到对象存储失败：{}", error.message()),
+            )
+            .await?;
+            return Ok(());
+        }
+
+        match store.head_object(&config, &record.object_key).await {
+            Ok(Some(remote)) if remote.size_bytes == size_bytes && remote.sha256 == sha256 => {
+                if self
+                    .repository
+                    .transition_status(
+                        &record.id,
+                        BackupStatus::Uploading,
+                        BackupStatus::Completed,
+                        StatusTransitionUpdate::default(),
+                        Utc::now(),
+                    )
+                    .await
+                    .map_err(repo_error)?
+                    .is_some()
+                {
+                    info!(
+                        backup_id = %record.id,
+                        size_bytes,
+                        "备份完成"
+                    );
+                }
+            }
+            Ok(Some(remote)) => {
+                let size_matches = remote.size_bytes == size_bytes;
+                let sha256_matches = remote.sha256 == sha256;
+                warn!(
+                    backup_id = %record.id,
+                    expected_size_bytes = size_bytes,
+                    remote_size_bytes = remote.size_bytes,
+                    sha256_matches,
+                    "备份远端对象校验不一致"
+                );
+                let _ = store.delete_object(&config, &record.object_key).await;
+                self.fail_task(
+                    record,
+                    code::REMOTE_VERIFICATION_FAILED,
+                    match (size_matches, sha256_matches) {
+                        (false, true) => "远端对象大小不一致",
+                        (true, false) => "远端对象 sha256 校验值不一致",
+                        (false, false) => "远端对象大小和 sha256 校验值均不一致",
+                        (true, true) => "远端对象校验状态异常",
+                    },
+                )
+                .await?;
+            }
+            Ok(None) => {
+                warn!(backup_id = %record.id, "上传完成后未找到远端对象");
+                self.fail_task(
+                    record,
+                    code::REMOTE_VERIFICATION_FAILED,
+                    "上传完成后未找到远端对象",
+                )
+                .await?;
+            }
+            Err(error) => {
+                let _ = store.delete_object(&config, &record.object_key).await;
+                self.fail_task(
+                    record,
+                    error.code(),
+                    format!("远端对象校验失败：{}", error.message()),
+                )
+                .await?;
+            }
+        }
+        Ok(())
+    }
+
+    /// 把活跃任务写入失败终态并清理暂存。
+    async fn fail_task(
+        &self,
+        record: &BackupRecord,
+        error_code: &'static str,
+        message: impl Into<String>,
+    ) -> Result<(), WorkerTaskError> {
+        let message = message.into();
+        warn!(
+            backup_id = %record.id,
+            error_code,
+            error_message = %message,
+            "备份任务失败"
+        );
+        let now = Utc::now();
+        let update = StatusTransitionUpdate {
+            error_code: Some(error_code.to_string()),
+            error_message: Some(message),
+            completed_at: Some(now),
+            ..Default::default()
+        };
+        let _ = self
+            .repository
+            .transition_status(&record.id, record.status, BackupStatus::Failed, update, now)
+            .await
+            .map_err(repo_error)?;
+        let _ = self.dump.cleanup_staging(&record.id).await;
+        Ok(())
+    }
+
+    /// 执行一小批到期保留清理：先处理 `expires_at` 已到期的记录，再按天数/份数清理计划备份。
+    async fn run_retention_batch(&self, now: DateTime<Utc>) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+
+        // 1. expires_at 已到期的记录（手动或计划）无条件进入删除。
+        let expired = self
+            .repository
+            .list_expired_records(RETENTION_BATCH_SIZE as u32)
+            .await
+            .map_err(repo_error)?;
+        for record in expired {
+            let Some(record) = self
+                .repository
+                .transition_to_deleting(&record.id, now)
+                .await
+                .map_err(repo_error)?
+            else {
+                continue;
+            };
+            self.finalize_deletion(&record).await?;
+        }
+
+        // 2. 计划备份按 retentionDays / retentionCount 清理。
+        let records = self
+            .repository
+            .list_scheduled_completed_desc(RETENTION_SCAN_LIMIT)
+            .await
+            .map_err(repo_error)?;
+        let decisions = decide_retention(
+            settings.retention_days,
+            settings.retention_count,
+            now,
+            &records,
+        );
+        for decision in decisions.into_iter().take(RETENTION_BATCH_SIZE) {
+            let Some(record) = self
+                .repository
+                .transition_to_deleting(&decision.record_id, now)
+                .await
+                .map_err(repo_error)?
+            else {
+                continue;
+            };
+            self.finalize_deletion(&record).await?;
+        }
+        Ok(())
+    }
+
+    /// 对已进入 deleting 的记录执行对象删除并硬删除记录行。
+    async fn finalize_deletion(&self, record: &BackupRecord) -> Result<(), WorkerTaskError> {
+        let settings = self.repository.load_settings().await.map_err(repo_error)?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Ok(());
+        };
+        if self
+            .object_store
+            .delete_object(&config, &record.object_key)
+            .await
+            .is_ok()
+        {
+            self.repository
+                .delete_record(&record.id)
+                .await
+                .map_err(repo_error)?;
+        }
+        Ok(())
+    }
+}
+
+fn classify_dump_error(error: BackupError) -> (&'static str, &'static str) {
+    match error.code() {
+        code::CANCELLED => (code::CANCELLED, "备份已取消"),
+        code::STAGING_SPACE_EXHAUSTED => (code::STAGING_SPACE_EXHAUSTED, "暂存磁盘空间不足"),
+        _ => (code::PG_DUMP_FAILED, "数据库导出失败"),
+    }
+}
+
+fn repo_error(error: crate::ports::store::AdminStoreError) -> WorkerTaskError {
+    WorkerTaskError::safe(format!("backup store failed: {error}"))
+}
+
+fn infra_error(error: BackupError) -> WorkerTaskError {
+    WorkerTaskError::safe(error.message())
+}

backend/crates/gateway-admin/src/lib.rs

@@ -2,23 +2,28 @@
 //!
 //! 本 crate 不包含 HTTP wire、数据库实现或具体 Provider 实现。
 
-use std::{fmt, path::Path, sync::Arc};
+use std::{fmt, path::Path, sync::Arc, time::Duration};
 
 use gateway_core::{
     engine::probe::AccountProbe,
     routing::{ProviderKind, snapshot::SnapshotControl},
+    task::{
+        DaemonRestartPolicy, WorkerContribution, WorkerId, WorkerKind, WorkerRegistration,
+        WorkerRunnable,
+    },
 };
 use secrecy::{ExposeSecret as _, SecretString};
 use serde::Deserialize;
 
+pub mod backup;
 pub mod model;
 pub mod ports;
 mod use_case;
 
 pub use use_case::{
-    accounts::AccountsService, auth::AuthService, client_keys::ClientKeyService,
-    observability::ObservabilityService, openai::OpenAiService, settings::SettingsService,
-    system::SystemService, xai::XaiService,
+    account_groups::AccountGroupService, accounts::AccountsService, auth::AuthService,
+    backup::BackupService, client_keys::ClientKeyService, observability::ObservabilityService,
+    openai::OpenAiService, settings::SettingsService, system::SystemService, xai::XaiService,
 };
 
 use model::{AdminError, AdminErrorKind};
@@ -28,10 +33,10 @@ use ports::{
     system::SystemOperations,
 };
 use use_case::{
-    accounts::DefaultAccountsService, auth::DefaultAuthService,
-    client_keys::DefaultClientKeyService, observability::DefaultObservabilityService,
-    openai::DefaultOpenAiService, settings::DefaultSettingsService, system::DefaultSystemService,
-    xai::DefaultXaiService,
+    account_groups::DefaultAccountGroupService, accounts::DefaultAccountsService,
+    auth::DefaultAuthService, backup::DefaultBackupService, client_keys::DefaultClientKeyService,
+    observability::DefaultObservabilityService, openai::DefaultOpenAiService,
+    settings::DefaultSettingsService, system::DefaultSystemService, xai::DefaultXaiService,
 };
 
 const OPENAI_PROVIDER_KIND: &str = "openai";
@@ -48,6 +53,8 @@ const WEAK_INITIAL_PASSWORDS: &[&str] = &[
     "codex-proxy-rs",
 ];
 
+const BACKUP_WORKER_OWNER: &str = "backup";
+
 /// 只用于首次幂等创建默认管理员的启动密码。
 #[derive(Clone, Deserialize)]
 #[serde(transparent)]
@@ -127,9 +134,9 @@ impl fmt::Debug for AdminConfig {
 /// Admin-owned 启动配置错误；不回显任何配置值。
 #[derive(Debug, Clone, Copy, PartialEq, Eq, thiserror::Error)]
 pub enum AdminConfigError {
-    #[error("configuration field `{0}` is invalid")]
+    #[error("配置字段 `{0}` 不合法")]
     InvalidField(&'static str),
-    #[error("admin.default_password does not meet the initial password policy")]
+    #[error("admin.default_password 不符合初始密码策略")]
     WeakInitialPassword,
 }
 
@@ -140,12 +147,14 @@ pub enum AdminConfigError {
 pub struct AdminServices {
     auth: Arc<dyn AuthService>,
     accounts: Arc<dyn AccountsService>,
+    account_groups: Arc<dyn AccountGroupService>,
     client_keys: Arc<dyn ClientKeyService>,
     observability: Arc<dyn ObservabilityService>,
     settings: Arc<dyn SettingsService>,
     system: Arc<dyn SystemService>,
     openai: Arc<dyn OpenAiService>,
     xai: Arc<dyn XaiService>,
+    backups: Arc<dyn BackupService>,
 }
 
 impl AdminServices {
@@ -159,6 +168,11 @@ impl AdminServices {
         self.accounts.as_ref()
     }
 
+    #[must_use]
+    pub fn account_groups(&self) -> &dyn AccountGroupService {
+        self.account_groups.as_ref()
+    }
+
     #[must_use]
     pub fn client_keys(&self) -> &dyn ClientKeyService {
         self.client_keys.as_ref()
@@ -188,11 +202,17 @@ impl AdminServices {
     pub fn xai(&self) -> &dyn XaiService {
         self.xai.as_ref()
     }
+
+    #[must_use]
+    pub fn backups(&self) -> &dyn BackupService {
+        self.backups.as_ref()
+    }
 }
 
 /// Admin 初始化完成后的封闭能力包。
 pub struct AdminBundle {
     services: AdminServices,
+    worker_contributions: Vec<WorkerContribution>,
 }
 
 impl AdminBundle {
@@ -200,6 +220,11 @@ impl AdminBundle {
     pub fn services(&self) -> AdminServices {
         self.services.clone()
     }
+
+    /// 取出 Backup Worker 贡献；只能调用一次，与其它 Bundle 的贡献一并交给 Host。
+    pub fn take_worker_contributions(&mut self) -> Vec<WorkerContribution> {
+        std::mem::take(&mut self.worker_contributions)
+    }
 }
 
 /// 校验配置、建立动态 Provider 注册表并完成默认管理员幂等初始化。
@@ -236,14 +261,31 @@ pub async fn initialize(
 
     let accounts = Arc::new(DefaultAccountsService::new(
         store.accounts(),
-        store.settings(),
+        store.account_runtime(),
         registry.clone(),
         snapshot.clone(),
         probe.clone(),
     ));
+    let backup_ports = store.backup();
+    let backups = Arc::new(DefaultBackupService::new(
+        backup_ports.repository(),
+        backup_ports.object_store(),
+        store.auth(),
+        snapshot.clone(),
+    ));
+    let backup_task = backup::task::BackupTask::new(
+        backup_ports.repository(),
+        backup_ports.dump(),
+        backup_ports.object_store(),
+    );
     let services = AdminServices {
         auth,
         accounts,
+        account_groups: Arc::new(DefaultAccountGroupService::new(
+            store.account_groups(),
+            store.account_runtime(),
+            snapshot.clone(),
+        )),
         client_keys: Arc::new(DefaultClientKeyService::new(
             store.client_keys(),
             snapshot.clone(),
@@ -268,12 +310,36 @@ pub async fn initialize(
             store.accounts(),
             snapshot.clone(),
         )),
+        backups,
     };
-    Ok(AdminBundle { services })
+    let worker_contributions = backup_worker_contribution(backup_task)?;
+    Ok(AdminBundle {
+        services,
+        worker_contributions,
+    })
+}
+
+/// Backup Worker 注册：单个可取消 Daemon，owner 固定为 `backup`。
+fn backup_worker_contribution(
+    task: backup::task::BackupTask,
+) -> Result<Vec<WorkerContribution>, AdminError> {
+    let id = WorkerId::try_new(WorkerKind::Backup, BACKUP_WORKER_OWNER)
+        .map_err(|_| AdminError::internal("备份 Worker ID 不合法"))?;
+    let restart = DaemonRestartPolicy::try_new(Duration::from_secs(1), Duration::from_secs(60))
+        .map_err(|_| AdminError::internal("备份 Worker 重启策略不合法"))?;
+    let registration = WorkerRegistration::try_new(
+        id,
+        WorkerRunnable::Daemon {
+            restart,
+            task: Box::new(task),
+        },
+    )
+    .map_err(|_| AdminError::internal("备份 Worker 注册信息不合法"))?;
+    Ok(vec![WorkerContribution::Registration(registration)])
 }
 
 fn provider_kind(value: &'static str) -> Result<ProviderKind, AdminError> {
-    ProviderKind::new(value).map_err(|_| AdminError::internal("Built-in Provider kind is invalid"))
+    ProviderKind::new(value).map_err(|_| AdminError::internal("内置 Provider 类型不合法"))
 }
 
 fn map_provider_registry_error(error: ProviderAdminError) -> AdminError {
@@ -283,8 +349,12 @@ fn map_provider_registry_error(error: ProviderAdminError) -> AdminError {
         }
         ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
         ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
-        ProviderAdminErrorKind::Unavailable => AdminErrorKind::Unavailable,
+        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
+        ProviderAdminErrorKind::Unavailable | ProviderAdminErrorKind::CredentialRefreshRequired => {
+            AdminErrorKind::Unavailable
+        }
+        ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
         ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
     };
-    AdminError::new(kind, "Provider registry initialization failed")
+    AdminError::new(kind, "Provider 注册表初始化失败")
 }

backend/crates/gateway-admin/src/model/account_groups.rs

@@ -0,0 +1,152 @@
+//! Provider-neutral account group commands and projections.
+
+use std::collections::BTreeMap;
+
+use chrono::{DateTime, Utc};
+use gateway_core::{engine::credential::AccountStatusFacts, routing::AccountGroupId};
+
+use super::{PageSize, Revision, observability::DecimalAmount};
+
+/// Canonical `#RRGGBBAA` color persisted with an account group.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupColor(String);
+
+impl AccountGroupColor {
+    #[must_use]
+    pub fn as_str(&self) -> &str {
+        &self.0
+    }
+
+    #[must_use]
+    pub fn parse(value: &str) -> Option<Self> {
+        (value.len() == 9
+            && value.starts_with('#')
+            && value[1..].bytes().all(|byte| byte.is_ascii_hexdigit()))
+        .then(|| Self(value.to_ascii_uppercase()))
+    }
+}
+
+/// Group member availability at the current observation time.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct AccountGroupAccountSummary {
+    pub available: u64,
+    pub limited: u64,
+    pub total: u64,
+}
+
+/// Group scheduling slots derived from available accounts and runtime leases.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub struct AccountGroupCapacity {
+    pub used_slots: Option<u64>,
+    pub total_slots: u64,
+}
+
+/// Successful, downstream-committed USD request costs for group accounts.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupUsage {
+    pub today_usd: DecimalAmount,
+    /// 当前 usage retention 窗口内、按请求发生时 routing group 快照归属的累计成本。
+    pub retained_total_usd: DecimalAmount,
+}
+
+/// 当前页账号组 membership 对应的持久账号事实；运行态在 Admin query service 合并。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupMemberFact {
+    pub group_id: AccountGroupId,
+    pub account_id: String,
+    pub status: AccountStatusFacts,
+    pub total_slots: u64,
+}
+
+/// Lightweight group reference embedded in account and client-key views.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupRef {
+    pub id: AccountGroupId,
+    pub name: String,
+    pub color: AccountGroupColor,
+    pub enabled: bool,
+}
+
+/// Account group list query.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupListQuery {
+    pub page: u32,
+    pub page_size: PageSize,
+    pub search: Option<String>,
+    pub enabled: Option<bool>,
+}
+
+/// Complete account group summary.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupRecord {
+    pub id: AccountGroupId,
+    pub name: String,
+    pub description: Option<String>,
+    pub color: AccountGroupColor,
+    pub enabled: bool,
+    pub member_count: u64,
+    pub provider_counts: BTreeMap<String, u64>,
+    pub client_key_count: u64,
+    pub account_summary: AccountGroupAccountSummary,
+    pub capacity: AccountGroupCapacity,
+    pub usage: AccountGroupUsage,
+    pub created_at: DateTime<Utc>,
+    pub updated_at: DateTime<Utc>,
+}
+
+/// Paginated account groups.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupPage {
+    pub config_revision: Revision,
+    pub items: Vec<AccountGroupRecord>,
+    pub total: u64,
+    pub page: u32,
+    pub page_size: u16,
+}
+
+/// Create an account group.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct CreateAccountGroup {
+    pub name: String,
+    pub description: Option<String>,
+    pub color: AccountGroupColor,
+}
+
+/// Store-ready create command with a generated stable ID.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct NewAccountGroup {
+    pub id: AccountGroupId,
+    pub name: String,
+    pub description: Option<String>,
+    pub color: AccountGroupColor,
+}
+
+/// Update an account group's descriptive fields.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UpdateAccountGroup {
+    pub id: AccountGroupId,
+    pub name: String,
+    pub description: Option<String>,
+    pub color: AccountGroupColor,
+}
+
+/// Enable or disable an account group.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct SetAccountGroupEnabled {
+    pub id: AccountGroupId,
+    pub enabled: bool,
+}
+
+/// Delete an account group that is not referenced by a client key.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct DeleteAccountGroup {
+    pub id: AccountGroupId,
+}
+
+/// Result of any account-group mutation.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupMutation {
+    pub config_revision: Revision,
+    pub id: AccountGroupId,
+    pub record: Option<AccountGroupRecord>,
+}

backend/crates/gateway-admin/src/model/accounts.rs

@@ -1,36 +1,23 @@
 //! 多 Provider 账号目录与连接测试的公共事实。
 
-use std::pin::Pin;
+use std::{collections::BTreeMap, pin::Pin};
 
 use chrono::{DateTime, Utc};
 use futures::Stream;
 
-use gateway_core::routing::ProviderKind;
+use gateway_core::{
+    engine::{UpstreamSendState, probe::AccountProbeErrorSource},
+    error::GatewayErrorKind,
+    routing::ProviderKind,
+};
 
-use super::{PageSize, Revision, observability::TimeRange};
+use super::{PageSize, Revision, account_groups::AccountGroupRef, observability::TimeRange};
 
-/// Provider 账号当前可用性。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum AccountAvailability {
-    Unknown,
-    Ready,
-    Cooldown,
-    QuotaExhausted,
-    Expired,
-    Banned,
-    Invalid,
-}
-
-/// 管理页使用的归一化账号状态。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum AccountStatus {
-    Active,
-    Expired,
-    QuotaExhausted,
-    Disabled,
-    Banned,
-    Attention,
-}
+pub use gateway_core::engine::credential::{
+    AccountConcurrencyLimit, AccountErrorReason, AccountStatus, AccountStatusFacts,
+    AccountStatusProjection, AccountWeight, CredentialState, QuotaAccessState, QuotaEvidence,
+    QuotaState, resolve_account_status,
+};
 
 /// 账号列表排序字段。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
@@ -63,19 +50,36 @@ pub struct AccountListQuery {
     pub page: u32,
     pub page_size: PageSize,
     pub provider_kind: Option<ProviderKind>,
+    pub group_filter: Option<AccountGroupFilter>,
     pub search: Option<String>,
     pub status: Option<AccountStatus>,
     pub sort: Option<AccountSort>,
 }
 
+/// Admin query service 从运行态存储取得的当前账号冷却快照。
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct AccountRuntimeSnapshot {
+    pub rate_limited_until: BTreeMap<String, DateTime<Utc>>,
+    /// `None` 表示实时 lease 存储不可用；`Some` 中未出现的账号当前使用量为零。
+    pub in_flight: Option<BTreeMap<String, u64>>,
+}
+
+/// Optional account membership filter.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum AccountGroupFilter {
+    Group(gateway_core::routing::AccountGroupId),
+    Ungrouped,
+}
+
 /// 账号公共存储投影；Provider 专属字段不进入此结构。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountRecord {
     pub id: String,
     pub provider_kind: ProviderKind,
+    pub groups: Vec<AccountGroupRef>,
     pub name: String,
     pub email: Option<String>,
-    pub upstream_user_id: String,
+    pub upstream_user_id: Option<String>,
     pub upstream_account_id: Option<String>,
     pub plan_type: Option<String>,
     pub authentication_kind: String,
@@ -84,11 +88,13 @@ pub struct AccountRecord {
     pub access_token_expires_at: Option<DateTime<Utc>>,
     pub next_refresh_at: Option<DateTime<Utc>>,
     pub enabled: bool,
-    pub availability: AccountAvailability,
-    pub availability_reason: Option<String>,
-    pub cooldown_until: Option<DateTime<Utc>>,
-    pub availability_observed_at: DateTime<Utc>,
-    pub quota_observed_at: Option<DateTime<Utc>>,
+    pub concurrency_limit: Option<AccountConcurrencyLimit>,
+    pub weight: AccountWeight,
+    pub credential_state: CredentialState,
+    pub credential_observed_at: DateTime<Utc>,
+    pub quota: QuotaState,
+    pub last_error_reason: Option<AccountErrorReason>,
+    pub last_error_message: Option<String>,
     pub created_at: DateTime<Utc>,
     pub updated_at: DateTime<Utc>,
 }
@@ -173,32 +179,68 @@ pub struct AccountUsageWindowResult {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountPage {
     pub config_revision: Revision,
-    pub items: Vec<AccountRecord>,
+    pub items: Vec<AccountPageItem>,
     pub total: u64,
     pub summary: AccountSummary,
 }
 
+/// 同一状态快照下的账号事实与唯一状态投影。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountPageItem {
+    pub account: AccountRecord,
+    pub projection: AccountStatusProjection,
+}
+
 /// 统一账号目录的全局状态计数，不受当前筛选和分页影响。
+///
+/// 计数与 [`AccountStatus`] 一一对应，由 store 按派生状态聚合。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub struct AccountSummary {
     pub total: u64,
-    pub active: u64,
+    pub normal: u64,
     pub quota_exhausted: u64,
-    pub attention: u64,
+    pub rate_limited: u64,
+    pub disabled: u64,
+    pub error: u64,
 }
 
-/// 账号启停写入命令。
+/// 账号可编辑事实的一次性替换命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
-pub struct SetAccountEnabled {
-    pub expected_config_revision: Revision,
+pub struct UpdateAccount {
     pub account_id: String,
     pub enabled: bool,
+    pub concurrency_limit: Option<AccountConcurrencyLimit>,
+    pub weight: AccountWeight,
+    pub group_ids: Vec<gateway_core::routing::AccountGroupId>,
+}
+
+/// 账号更新结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountUpdateResult {
+    pub config_revision: Revision,
+    pub account_id: gateway_core::engine::credential::ProviderAccountId,
+}
+
+/// 一批账号可编辑事实的一次性替换命令。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BatchUpdateAccounts {
+    pub account_ids: Vec<String>,
+    pub enabled: bool,
+    pub concurrency_limit: Option<AccountConcurrencyLimit>,
+    pub weight: AccountWeight,
+    pub group_ids: Vec<gateway_core::routing::AccountGroupId>,
+}
+
+/// 批量账号更新结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountsUpdateResult {
+    pub config_revision: Revision,
+    pub account_ids: Vec<gateway_core::engine::credential::ProviderAccountId>,
 }
 
 /// 账号批量删除命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DeleteAccounts {
-    pub expected_config_revision: Revision,
     pub account_ids: Vec<String>,
 }
 
@@ -217,12 +259,17 @@ pub enum AccountConnectionTestEvent {
     Content {
         text: String,
     },
-    Completed {
-        account_status: AccountStatus,
-    },
+    Completed,
     Failed {
+        source: AccountProbeErrorSource,
+        gateway_error_code: GatewayErrorKind,
+        send_state: Option<UpstreamSendState>,
         message: String,
-        account_status: AccountStatus,
+        provider_error_code: Option<String>,
+        provider_error_type: Option<String>,
+        upstream_status: Option<u16>,
+        upstream_content_type: Option<String>,
+        upstream_body: Option<String>,
     },
 }
 

backend/crates/gateway-admin/src/model/auth.rs

@@ -39,7 +39,6 @@ impl AdminRequestContext {
 pub struct LoginCommand {
     pub username: Option<String>,
     pub password: String,
-    pub source: String,
 }
 
 impl std::fmt::Debug for LoginCommand {
@@ -48,7 +47,6 @@ impl std::fmt::Debug for LoginCommand {
             .debug_struct("LoginCommand")
             .field("username", &self.username)
             .field("password", &"[REDACTED]")
-            .field("source", &self.source)
             .finish()
     }
 }
@@ -65,8 +63,6 @@ pub struct LoginResult {
 pub enum LoginError {
     #[error("invalid administrator credentials")]
     InvalidCredentials,
-    #[error("administrator login is throttled")]
-    Throttled,
     #[error("administrator authentication is unavailable")]
     Unavailable,
 }

backend/crates/gateway-admin/src/model/backup.rs

@@ -0,0 +1,566 @@
+//! S3 备份领域模型、状态机与稳定错误。
+//!
+//! 领域类型只携带事实，不承载基础设施细节。Secret 使用 [`secrecy::SecretString`]，
+//! 全流程不实现 `Serialize`，避免被错误地写入 wire 或日志。管理员身份等审计事实
+//! 只存在于 `admin_audit_events`，本模型不重复保存。
+
+use std::fmt;
+
+use chrono::{DateTime, Utc};
+use secrecy::SecretString;
+use uuid::Uuid;
+
+use super::PageSize;
+
+/// 备份触发来源。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum BackupTriggerKind {
+    Manual,
+    Scheduled,
+}
+
+impl BackupTriggerKind {
+    /// 稳定持久化值。
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::Manual => "manual",
+            Self::Scheduled => "scheduled",
+        }
+    }
+
+    /// 解析持久化值。
+    #[must_use]
+    pub fn parse(value: &str) -> Option<Self> {
+        match value {
+            "manual" => Some(Self::Manual),
+            "scheduled" => Some(Self::Scheduled),
+            _ => None,
+        }
+    }
+}
+
+impl fmt::Display for BackupTriggerKind {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter.write_str(self.as_str())
+    }
+}
+
+/// 备份任务状态机（六状态）。
+///
+/// 迁移 `backup_records_lifecycle_ck` 与字段空值语义共同定义合法持久化行；
+/// [`Self::allows_transition_to`] 只约束领域内的显式状态迁移，两层都必须满足。
+/// 删除成功后记录行被硬删除，因此不存在 `deleted` 终态。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
+pub enum BackupStatus {
+    Queued,
+    Dumping,
+    Uploading,
+    Completed,
+    Failed,
+    Deleting,
+}
+
+impl BackupStatus {
+    /// 稳定持久化值。
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::Queued => "queued",
+            Self::Dumping => "dumping",
+            Self::Uploading => "uploading",
+            Self::Completed => "completed",
+            Self::Failed => "failed",
+            Self::Deleting => "deleting",
+        }
+    }
+
+    /// 解析持久化值。
+    #[must_use]
+    pub fn parse(value: &str) -> Option<Self> {
+        match value {
+            "queued" => Some(Self::Queued),
+            "dumping" => Some(Self::Dumping),
+            "uploading" => Some(Self::Uploading),
+            "completed" => Some(Self::Completed),
+            "failed" => Some(Self::Failed),
+            "deleting" => Some(Self::Deleting),
+            _ => None,
+        }
+    }
+
+    /// 该状态是否消耗全局活跃名额。
+    #[must_use]
+    pub const fn is_active(self) -> bool {
+        matches!(self, Self::Queued | Self::Dumping | Self::Uploading)
+    }
+
+    /// 该状态是否允许进入删除流程。
+    #[must_use]
+    pub const fn can_be_deleted(self) -> bool {
+        matches!(self, Self::Completed | Self::Failed)
+    }
+
+    /// 领域内允许的显式迁移。
+    #[must_use]
+    pub fn allows_transition_to(self, target: BackupStatus) -> bool {
+        matches!(
+            (self, target),
+            (Self::Queued, Self::Dumping)
+                | (Self::Queued, Self::Failed)
+                | (Self::Dumping, Self::Uploading)
+                | (Self::Dumping, Self::Failed)
+                | (Self::Uploading, Self::Completed)
+                | (Self::Uploading, Self::Failed)
+                | (Self::Completed, Self::Deleting)
+                | (Self::Failed, Self::Deleting)
+        )
+    }
+}
+
+impl fmt::Display for BackupStatus {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter.write_str(self.as_str())
+    }
+}
+
+/// S3 存储配置更新命令；`secret_access_key` 为 `None` 表示保留旧值。
+#[derive(Clone)]
+pub struct UpdateBackupStorageCommand {
+    pub endpoint: String,
+    pub region: String,
+    pub bucket: String,
+    pub access_key_id: String,
+    pub secret_access_key: Option<SecretString>,
+    pub prefix: String,
+    pub force_path_style: bool,
+}
+
+impl fmt::Debug for UpdateBackupStorageCommand {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("UpdateBackupStorageCommand")
+            .field("endpoint", &self.endpoint)
+            .field("region", &self.region)
+            .field("bucket", &self.bucket)
+            .field("access_key_id", &self.access_key_id)
+            .field("secret_access_key", &self.secret_access_key.is_some())
+            .field("prefix", &self.prefix)
+            .field("force_path_style", &self.force_path_style)
+            .finish()
+    }
+}
+
+/// 调度配置更新命令。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UpdateBackupScheduleCommand {
+    pub schedule_enabled: bool,
+    pub cron_expression: String,
+    pub schedule_timezone: String,
+    pub retention_days: u32,
+    pub retention_count: u32,
+}
+
+/// 完整保存的备份设置（含 Secret）。
+///
+/// 只从仓储读取；不实现 `Serialize`，防止 Secret 进入 wire 或日志。
+#[derive(Clone)]
+pub struct BackupSettings {
+    pub storage_revision: u64,
+    pub endpoint: Option<String>,
+    pub region: Option<String>,
+    pub bucket: Option<String>,
+    pub access_key_id: Option<String>,
+    pub secret_access_key: Option<SecretString>,
+    pub prefix: Option<String>,
+    pub force_path_style: bool,
+    pub schedule_enabled: bool,
+    pub cron_expression: Option<String>,
+    pub schedule_timezone: Option<String>,
+    pub retention_days: u32,
+    pub retention_count: u32,
+    pub next_run_at: Option<DateTime<Utc>>,
+    pub last_verified_at: Option<DateTime<Utc>>,
+    pub updated_at: DateTime<Utc>,
+}
+
+impl fmt::Debug for BackupSettings {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("BackupSettings")
+            .field("storage_revision", &self.storage_revision)
+            .field("endpoint", &self.endpoint)
+            .field("region", &self.region)
+            .field("bucket", &self.bucket)
+            .field("access_key_id", &self.access_key_id)
+            .field("secret_access_key", &self.secret_access_key.is_some())
+            .field("prefix", &self.prefix)
+            .field("force_path_style", &self.force_path_style)
+            .field("schedule_enabled", &self.schedule_enabled)
+            .field("cron_expression", &self.cron_expression)
+            .field("schedule_timezone", &self.schedule_timezone)
+            .field("retention_days", &self.retention_days)
+            .field("retention_count", &self.retention_count)
+            .field("next_run_at", &self.next_run_at)
+            .field("last_verified_at", &self.last_verified_at)
+            .field("updated_at", &self.updated_at)
+            .finish()
+    }
+}
+
+impl BackupSettings {
+    /// S3 存储配置是否完整（bucket/region/密钥/前缀齐全）。
+    #[must_use]
+    pub fn storage_configured(&self) -> bool {
+        self.endpoint.is_some()
+            && self.region.is_some()
+            && self.bucket.is_some()
+            && self.access_key_id.is_some()
+            && self.secret_access_key.is_some()
+            && self.prefix.is_some()
+    }
+
+    /// 探测是否已对当前 revision 成功；`last_verified_at` 非空即表示当前配置已通过探针。
+    #[must_use]
+    pub fn storage_verified(&self) -> bool {
+        self.last_verified_at.is_some()
+    }
+}
+
+/// 已经校验并可用于对象存储操作的存储配置快照。
+#[derive(Clone)]
+pub struct BackupStorageConfig {
+    pub storage_revision: u64,
+    pub endpoint: String,
+    pub region: String,
+    pub bucket: String,
+    pub access_key_id: String,
+    pub secret_access_key: SecretString,
+    pub prefix: String,
+    pub force_path_style: bool,
+}
+
+impl fmt::Debug for BackupStorageConfig {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("BackupStorageConfig")
+            .field("storage_revision", &self.storage_revision)
+            .field("endpoint", &self.endpoint)
+            .field("region", &self.region)
+            .field("bucket", &self.bucket)
+            .field("access_key_id", &self.access_key_id)
+            .field("secret_access_key", &"[REDACTED]")
+            .field("prefix", &self.prefix)
+            .field("force_path_style", &self.force_path_style)
+            .finish()
+    }
+}
+
+impl BackupStorageConfig {
+    /// 从完整设置推导对象存储配置；设置不完整时返回 `None`。
+    #[must_use]
+    pub fn from_settings(settings: &BackupSettings) -> Option<Self> {
+        Some(Self {
+            storage_revision: settings.storage_revision,
+            endpoint: settings.endpoint.clone()?,
+            region: settings.region.clone()?,
+            bucket: settings.bucket.clone()?,
+            access_key_id: settings.access_key_id.clone()?,
+            secret_access_key: settings.secret_access_key.clone()?,
+            prefix: settings.prefix.clone()?,
+            force_path_style: settings.force_path_style,
+        })
+    }
+}
+
+/// 一条备份记录。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BackupRecord {
+    pub id: String,
+    pub trigger_kind: BackupTriggerKind,
+    pub status: BackupStatus,
+    pub scheduled_at: Option<DateTime<Utc>>,
+    pub object_key: String,
+    pub size_bytes: Option<u64>,
+    pub sha256: Option<String>,
+    pub attempt_count: u32,
+    pub error_code: Option<String>,
+    pub error_message: Option<String>,
+    pub started_at: Option<DateTime<Utc>>,
+    pub completed_at: Option<DateTime<Utc>>,
+    /// 创建时确定的过期时间；手工和计划备份均可设置，到期自动清理。
+    pub expires_at: Option<DateTime<Utc>>,
+    pub created_at: DateTime<Utc>,
+    pub updated_at: DateTime<Utc>,
+}
+
+/// 备份记录分页查询。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BackupRecordListQuery {
+    pub page: u32,
+    pub page_size: PageSize,
+    pub status: Option<BackupStatus>,
+    pub trigger: Option<BackupTriggerKind>,
+}
+
+/// 备份记录分页结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BackupRecordPage {
+    pub items: Vec<BackupRecord>,
+    pub total: u64,
+    pub page: u32,
+    pub page_size: PageSize,
+}
+
+impl BackupRecordPage {
+    /// 计算总页数；空集合视为一页。
+    #[must_use]
+    pub fn total_pages(&self) -> u32 {
+        let size = u64::from(self.page_size.get());
+        if self.total == 0 {
+            1
+        } else {
+            self.total.div_ceil(size).min(u64::from(u32::MAX)) as u32
+        }
+    }
+}
+
+/// 创建备份任务的持久化数据；id 与对象 key 由领域生成。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BackupRecordSeed {
+    pub id: String,
+    pub trigger_kind: BackupTriggerKind,
+    pub scheduled_at: Option<DateTime<Utc>>,
+    pub object_key: String,
+    pub expires_at: Option<DateTime<Utc>>,
+}
+
+/// 连接测试结果；只携带稳定阶段与脱敏消息。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ConnectionTestResult {
+    pub ok: bool,
+    pub stage: &'static str,
+    pub code: Option<&'static str>,
+    pub message: String,
+}
+
+/// 对象存储探测阶段。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ConnectionTestStage {
+    PutObject,
+    HeadObject,
+    GetObject,
+    DeleteObject,
+}
+
+impl ConnectionTestStage {
+    /// 稳定 wire 值。
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::PutObject => "putObject",
+            Self::HeadObject => "headObject",
+            Self::GetObject => "getObject",
+            Self::DeleteObject => "deleteObject",
+        }
+    }
+}
+
+/// 上传到对象存储并期望远端校验的归档 metadata。
+///
+/// `size_bytes` 在上传时不写入 metadata，但 `HeadObject` 会返回远端大小，
+/// 用于与本地归档校验一致。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct BackupObjectMetadata {
+    pub backup_id: String,
+    pub sha256: String,
+    pub created_at: DateTime<Utc>,
+    pub size_bytes: u64,
+}
+
+impl BackupObjectMetadata {
+    /// 构造上传 metadata。
+    #[must_use]
+    pub const fn new(
+        backup_id: String,
+        sha256: String,
+        created_at: DateTime<Utc>,
+        size_bytes: u64,
+    ) -> Self {
+        Self {
+            backup_id,
+            sha256,
+            created_at,
+            size_bytes,
+        }
+    }
+}
+
+/// 短时下载地址结果。
+#[derive(Clone, PartialEq, Eq)]
+pub struct DownloadUrlResult {
+    pub url: String,
+    pub file_name: String,
+    pub expires_in: std::time::Duration,
+}
+
+impl fmt::Debug for DownloadUrlResult {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("DownloadUrlResult")
+            .field("url", &"[REDACTED]")
+            .field("file_name", &self.file_name)
+            .field("expires_in", &self.expires_in)
+            .finish()
+    }
+}
+
+/// 备份基础设施错误：只携带稳定错误码与脱敏消息。
+///
+/// 该类型不构成第二套 kind 枚举；`gateway-admin` 边界统一映射为既有
+/// `AdminErrorKind`。稳定 `error_code` 同时用于任务记录、日志与 UI。
+#[derive(Debug, Clone, PartialEq, Eq, thiserror::Error)]
+#[error("{message}")]
+pub struct BackupError {
+    code: &'static str,
+    message: String,
+}
+
+impl BackupError {
+    /// 构造基础设施错误。
+    #[must_use]
+    pub const fn new(code: &'static str, message: String) -> Self {
+        Self { code, message }
+    }
+
+    /// 稳定错误码，例如 `backup.s3_auth_failed`。
+    #[must_use]
+    pub const fn code(&self) -> &'static str {
+        self.code
+    }
+
+    /// 脱敏后的可操作消息。
+    #[must_use]
+    pub fn message(&self) -> &str {
+        &self.message
+    }
+}
+
+/// 构造稳定错误码常量。
+pub mod code {
+    /// 配置或参数非法。
+    pub const INVALID_CONFIG: &str = "backup.invalid_config";
+    /// Cron 表达式非法。
+    pub const INVALID_CRON: &str = "backup.invalid_cron";
+    /// IANA 时区非法。
+    pub const INVALID_TIMEZONE: &str = "backup.invalid_timezone";
+    /// 记录不存在。
+    pub const RECORD_NOT_FOUND: &str = "backup.record_not_found";
+    /// 已存在活跃任务，拒绝创建。
+    pub const ACTIVE_TASK_CONFLICT: &str = "backup.active_task_conflict";
+    /// 记录状态与期望不符，无法迁移。
+    pub const STATE_CONFLICT: &str = "backup.state_conflict";
+    /// 已有记录时禁止切换存储目标。
+    pub const STORAGE_IDENTITY_LOCKED: &str = "backup.storage_identity_locked";
+    /// `pg_dump` 非零退出或失败。
+    pub const PG_DUMP_FAILED: &str = "backup.pg_dump_failed";
+    /// 暂存磁盘空间不足。
+    pub const STAGING_SPACE_EXHAUSTED: &str = "backup.staging_space_exhausted";
+    /// S3 认证失败。
+    pub const S3_AUTH_FAILED: &str = "backup.s3_auth_failed";
+    /// S3 权限拒绝。
+    pub const S3_PERMISSION_DENIED: &str = "backup.s3_permission_denied";
+    /// S3 上传失败。
+    pub const S3_UPLOAD_FAILED: &str = "backup.s3_upload_failed";
+    /// 远端对象校验失败。
+    pub const REMOTE_VERIFICATION_FAILED: &str = "backup.remote_verification_failed";
+    /// 任务被取消。
+    pub const CANCELLED: &str = "backup.cancelled";
+    /// 仓储或对象存储暂不可用。
+    pub const STORE_UNAVAILABLE: &str = "backup.store_unavailable";
+    /// 上游 S3 服务返回无效或失败响应。
+    pub const UPSTREAM_FAILURE: &str = "backup.upstream_failure";
+}
+
+/// 构建对象 key：`{prefix}/YYYY/MM/DD/codex-proxy-rs_{UTC seconds}_{backup id}.dump`。
+///
+/// 规范化规则：prefix 不得为空、不得以前导 `/` 开头、不得包含 `..`、反斜杠或控制字符；
+/// 输出统一使用 `/` 分隔且不含空段。
+pub fn build_object_key(
+    prefix: &str,
+    backup_id: &str,
+    at: DateTime<Utc>,
+) -> Result<String, BackupError> {
+    let prefix = normalize_prefix(prefix)?;
+    Ok(format!(
+        "{prefix}/{}/{:02}/{:02}/codex-proxy-rs_{}_{}.dump",
+        at.format("%Y"),
+        at.format("%m"),
+        at.format("%d"),
+        at.format("%Y%m%d_%H%M%S"),
+        short_backup_id(backup_id),
+    ))
+}
+
+/// 下载文件名：`codex-proxy-rs_{短 id}.dump`，与对象 key 的文件名一致。
+#[must_use]
+pub fn build_download_file_name(backup_id: &str) -> String {
+    format!("codex-proxy-rs_{}.dump", short_backup_id(backup_id))
+}
+
+/// 截取备份 id 的可读短标识：去掉 `backup_` 前缀，最多保留 8 位 hex。
+#[must_use]
+fn short_backup_id(backup_id: &str) -> String {
+    let hex = backup_id.strip_prefix("backup_").unwrap_or(backup_id);
+    hex.get(..8).unwrap_or(hex).to_owned()
+}
+
+/// 规范化并校验对象 prefix。
+///
+/// 返回去掉尾部 `/` 的规范 prefix；空串、前导 `/`、`..` 段、反斜杠和控制字符均拒绝。
+pub fn normalize_prefix(prefix: &str) -> Result<String, BackupError> {
+    if prefix.is_empty() || prefix.starts_with('/') {
+        return Err(BackupError::new(
+            code::INVALID_CONFIG,
+            "存储对象前缀必须非空且不能以前导 / 开头".to_owned(),
+        ));
+    }
+    if prefix.bytes().any(|byte| byte.is_ascii_control()) || prefix.contains('\\') {
+        return Err(BackupError::new(
+            code::INVALID_CONFIG,
+            "存储对象前缀包含非法字符".to_owned(),
+        ));
+    }
+    if prefix.split('/').any(|segment| segment == "..") {
+        return Err(BackupError::new(
+            code::INVALID_CONFIG,
+            "存储对象前缀不能包含 .. 路径段".to_owned(),
+        ));
+    }
+    Ok(prefix.trim_end_matches('/').to_owned())
+}
+
+/// 生成新的备份记录 id。
+#[must_use]
+pub fn new_backup_id() -> String {
+    format!("backup_{}", Uuid::now_v7().simple())
+}
+
+/// 从触发类型与计划时间构造可持久化 seed；id 与对象 key 一次生成保持一致。
+pub fn build_backup_seed(
+    trigger_kind: BackupTriggerKind,
+    scheduled_at: Option<DateTime<Utc>>,
+    prefix: &str,
+    at: DateTime<Utc>,
+    expires_at: Option<DateTime<Utc>>,
+) -> Result<BackupRecordSeed, BackupError> {
+    let id = new_backup_id();
+    let object_key = build_object_key(prefix, &id, at)?;
+    Ok(BackupRecordSeed {
+        id,
+        trigger_kind,
+        scheduled_at,
+        object_key,
+        expires_at,
+    })
+}

backend/crates/gateway-admin/src/model/client_keys.rs

@@ -6,10 +6,10 @@ use chrono::{DateTime, Utc};
 
 use gateway_core::{
     policy::{ClientApiKeyId, RateLimits},
-    routing::ProviderKind,
+    routing::{AccountGroupId, ProviderKind},
 };
 
-use super::{AdminModelError, Revision};
+use super::{AdminModelError, Revision, account_groups::AccountGroupRef};
 
 /// Client Key 列表保持旧 HTTP 合同允许的完整非零 `u16` 页大小。
 #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
@@ -88,7 +88,8 @@ pub struct ClientKeyRecord {
     pub id: ClientApiKeyId,
     pub name: String,
     pub label: Option<String>,
-    pub provider_kind: ProviderKind,
+    pub groups: Vec<AccountGroupRef>,
+    pub provider_kinds: Vec<ProviderKind>,
     pub prefix: String,
     pub enabled: bool,
     pub limits: RateLimits,
@@ -141,21 +142,19 @@ impl fmt::Debug for ClientKeySecret {
 /// API 提交的 Client Key 创建命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CreateClientKey {
-    pub expected_config_revision: Revision,
     pub name: String,
     pub label: Option<String>,
-    pub provider_kind: ProviderKind,
+    pub group_ids: Vec<AccountGroupId>,
     pub limits: RateLimits,
 }
 
 /// 管理用例生成 ID 与明文后的持久化命令。
 #[derive(Clone, PartialEq, Eq)]
 pub struct NewClientKey {
-    pub expected_config_revision: Revision,
     pub id: ClientApiKeyId,
     pub name: String,
     pub label: Option<String>,
-    pub provider_kind: ProviderKind,
+    pub group_ids: Vec<AccountGroupId>,
     pub limits: RateLimits,
     pub plaintext: String,
 }
@@ -166,7 +165,7 @@ impl fmt::Debug for NewClientKey {
             .debug_struct("NewClientKey")
             .field("id", &self.id)
             .field("name", &self.name)
-            .field("provider_kind", &self.provider_kind)
+            .field("group_ids", &self.group_ids)
             .field("plaintext", &"[REDACTED]")
             .finish_non_exhaustive()
     }
@@ -175,18 +174,16 @@ impl fmt::Debug for NewClientKey {
 /// 修改 Client Key 的公开策略字段。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UpdateClientKey {
-    pub expected_config_revision: Revision,
     pub id: ClientApiKeyId,
     pub name: String,
     pub label: Option<String>,
-    pub provider_kind: ProviderKind,
+    pub group_ids: Vec<AccountGroupId>,
     pub limits: RateLimits,
 }
 
 /// 修改 Client Key 启用状态。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct SetClientKeyEnabled {
-    pub expected_config_revision: Revision,
     pub id: ClientApiKeyId,
     pub enabled: bool,
 }
@@ -194,7 +191,6 @@ pub struct SetClientKeyEnabled {
 /// 删除 Client Key。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DeleteClientKey {
-    pub expected_config_revision: Revision,
     pub id: ClientApiKeyId,
 }
 

backend/crates/gateway-admin/src/model/mod.rs

@@ -2,8 +2,10 @@
 
 use std::num::{NonZeroU16, NonZeroU64};
 
+pub mod account_groups;
 pub mod accounts;
 pub mod auth;
+pub mod backup;
 pub mod client_keys;
 pub mod observability;
 pub mod provider_credentials;
@@ -19,11 +21,12 @@ pub enum AdminErrorKind {
     Conflict,
     RateLimited,
     BadGateway,
+    UpstreamResultUnknown,
     Unavailable,
     Internal,
 }
 
-/// 不携带基础设施细节的管理用例错误。
+/// 不携带基础设施细节、可安全返回给管理员的管理用例错误。
 #[derive(Debug, Clone, PartialEq, Eq, thiserror::Error)]
 #[error("{message}")]
 pub struct AdminError {
@@ -45,11 +48,22 @@ impl AdminError {
         self.kind
     }
 
+    /// 返回已脱敏、可公开给管理员的文案。
+    #[must_use]
+    pub fn message(&self) -> &str {
+        &self.message
+    }
+
     #[must_use]
     pub fn invalid(message: impl Into<String>) -> Self {
         Self::new(AdminErrorKind::Invalid, message)
     }
 
+    #[must_use]
+    pub fn bad_request(message: impl Into<String>) -> Self {
+        Self::new(AdminErrorKind::Invalid, message)
+    }
+
     #[must_use]
     pub fn not_found(message: impl Into<String>) -> Self {
         Self::new(AdminErrorKind::NotFound, message)
@@ -60,6 +74,16 @@ impl AdminError {
         Self::new(AdminErrorKind::Conflict, message)
     }
 
+    #[must_use]
+    pub fn bad_gateway(message: impl Into<String>) -> Self {
+        Self::new(AdminErrorKind::BadGateway, message)
+    }
+
+    #[must_use]
+    pub fn upstream_result_unknown(message: impl Into<String>) -> Self {
+        Self::new(AdminErrorKind::UpstreamResultUnknown, message)
+    }
+
     #[must_use]
     pub fn unavailable(message: impl Into<String>) -> Self {
         Self::new(AdminErrorKind::Unavailable, message)

backend/crates/gateway-admin/src/model/observability.rs

@@ -1,11 +1,21 @@
 //! 用量、成本、健康与错误诊断的 UTC 语义事实。
 
-use std::{num::NonZeroU32, str::FromStr};
+use std::str::FromStr;
 
-use chrono::{DateTime, TimeDelta, Utc};
+use chrono::{DateTime, TimeDelta, Timelike as _, Utc};
 
 use super::{AdminModelError, PageSize};
 
+/// 观测日界所用的东八区(UTC+8)固定偏移秒数。
+const CHINA_OFFSET_SECONDS: i64 = 8 * 60 * 60;
+
+/// 将 UTC 时刻截断到东八区(UTC+8)当日零点,返回值仍为 UTC。
+#[must_use]
+pub fn china_day_start(value: DateTime<Utc>) -> DateTime<Utc> {
+    let elapsed = (value.timestamp() + CHINA_OFFSET_SECONDS).rem_euclid(24 * 60 * 60);
+    value - TimeDelta::seconds(elapsed) - TimeDelta::nanoseconds(i64::from(value.nanosecond()))
+}
+
 /// 外部观测查询的 UTC 时间范围。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub struct TimeRange {
@@ -28,29 +38,6 @@ impl TimeRange {
     }
 }
 
-/// 从一开始的观测页码。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub struct PageNumber(NonZeroU32);
-
-impl PageNumber {
-    #[must_use]
-    pub const fn new(value: NonZeroU32) -> Self {
-        Self(value)
-    }
-
-    #[must_use]
-    pub const fn get(self) -> u32 {
-        self.0.get()
-    }
-}
-
-/// 观测记录的稳定键集游标。
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct ObservabilityCursor {
-    pub observed_at: DateTime<Utc>,
-    pub stable_id: String,
-}
-
 /// 请求结果状态。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum RequestOutcome {
@@ -136,8 +123,7 @@ pub struct UsageFilter {
 pub struct UsageQuery {
     pub range: TimeRange,
     pub filter: UsageFilter,
-    pub cursor: Option<ObservabilityCursor>,
-    pub page: PageNumber,
+    pub current_page: u32,
     pub page_size: PageSize,
 }
 
@@ -149,6 +135,7 @@ pub struct OpsErrorFilter {
     pub provider_kind: Option<String>,
     pub provider_account_ref: Option<String>,
     pub operation: Option<String>,
+    pub endpoint: Option<String>,
     pub model: Option<String>,
     pub transport: Option<String>,
     pub attempt_index: Option<u32>,
@@ -164,8 +151,7 @@ pub struct OpsErrorFilter {
 pub struct OpsErrorQuery {
     pub range: TimeRange,
     pub filter: OpsErrorFilter,
-    pub cursor: Option<ObservabilityCursor>,
-    pub page: PageNumber,
+    pub current_page: u32,
     pub page_size: PageSize,
 }
 
@@ -194,42 +180,22 @@ impl DecimalAmount {
     /// 精确相加两个 `numeric(20,10)` 金额。
     #[must_use]
     pub fn checked_add(&self, other: &Self) -> Option<Self> {
-        let sum = scaled_amount(&self.0)?.checked_add(scaled_amount(&other.0)?)?;
-        Self::from_scaled(sum)
+        Self::from_decimal(self.to_decimal()?.checked_add(other.to_decimal()?)?)
     }
 
     /// 将金额按非零请求数均分，保留最多十位小数。
     #[must_use]
     pub fn checked_div_u64(&self, divisor: u64) -> Option<Self> {
-        let divisor = u128::from(divisor);
-        (divisor != 0)
-            .then(|| scaled_amount(&self.0)?.checked_div(divisor))
-            .flatten()
-            .and_then(Self::from_scaled)
+        Self::from_decimal(self.to_decimal()?.checked_div_u64(divisor)?)
     }
 
-    fn from_scaled(value: u128) -> Option<Self> {
-        if value >= 10_u128.pow(20) {
-            return None;
-        }
-        let whole = value / 10_u128.pow(10);
-        let fraction = value % 10_u128.pow(10);
-        let value = if fraction == 0 {
-            whole.to_string()
-        } else {
-            format!("{whole}.{fraction:010}")
-                .trim_end_matches('0')
-                .to_owned()
-        };
-        Some(Self(value))
+    fn to_decimal(&self) -> Option<gateway_core::accounting::Decimal> {
+        self.0.parse().ok()
     }
-}
 
-fn scaled_amount(value: &str) -> Option<u128> {
-    let (whole, fraction) = value.split_once('.').unwrap_or((value, ""));
-    let whole = whole.parse::<u128>().ok()?;
-    let fraction = format!("{fraction:0<10}").parse::<u128>().ok()?;
-    whole.checked_mul(10_u128.pow(10))?.checked_add(fraction)
+    fn from_decimal(value: gateway_core::accounting::Decimal) -> Option<Self> {
+        Some(Self(value.canonical()))
+    }
 }
 
 impl FromStr for DecimalAmount {
@@ -320,6 +286,7 @@ pub struct LatencyPercentiles {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ProviderBillingInput {
     pub upstream_model_id: String,
+    pub service_tier: Option<String>,
     pub input_tokens: Option<u64>,
     pub output_tokens: Option<u64>,
     pub cached_tokens: Option<u64>,
@@ -335,6 +302,7 @@ pub struct UsageCalculatedBillingFact {
     pub bucket_start: DateTime<Utc>,
     pub provider_kind: String,
     pub upstream_model_id: String,
+    pub service_tier: Option<String>,
     pub input_tokens: Option<u64>,
     pub output_tokens: Option<u64>,
     pub cached_tokens: Option<u64>,
@@ -410,6 +378,16 @@ pub struct RequestMetrics {
     pub max_latency_ms: Option<u64>,
     pub latency_percentiles: LatencyPercentiles,
     pub first_token_latency_percentiles: LatencyPercentiles,
+    pub admission_decision_count: u64,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_count: u64,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_sample_count: u64,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
     pub cache_eligible_request_count: u64,
     pub cache_hit_request_count: u64,
 }
@@ -447,18 +425,15 @@ pub struct RequestMetricPoint {
     pub costs: Vec<CurrencyCost>,
 }
 
-/// 账号池容量统计。
+/// 账号池的统一五态统计。
 #[derive(Debug, Clone, Default, PartialEq, Eq)]
 pub struct AccountPoolMetrics {
     pub total: u64,
-    pub enabled: u64,
-    pub unavailable: u64,
-    pub active: u64,
-    pub expired: u64,
+    pub normal: u64,
     pub quota_exhausted: u64,
-    pub refreshing: Option<u64>,
+    pub rate_limited: u64,
     pub disabled: u64,
-    pub banned: u64,
+    pub error: u64,
 }
 
 /// Dashboard 中一个账号的模型级用量事实。
@@ -489,7 +464,7 @@ pub struct DashboardAccountRequestBucket {
     pub request_count: u64,
 }
 
-/// Dashboard 中一个账号的完整用量与公共状态事实。
+/// Dashboard 中一个账号的完整用量事实。
 #[derive(Debug, Clone, PartialEq)]
 pub struct DashboardAccountUsage {
     pub account_id: String,
@@ -498,8 +473,6 @@ pub struct DashboardAccountUsage {
     pub name: String,
     pub email: Option<String>,
     pub plan_type: Option<String>,
-    pub enabled: bool,
-    pub availability: String,
     pub request_count: u64,
     pub success_count: u64,
     pub input_tokens: Option<u64>,
@@ -526,22 +499,82 @@ pub struct DashboardAccountUsage {
 /// Dashboard 当前账号池的可重建运行时槽位事实。
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 pub struct DashboardRuntimeSlots {
-    /// 与持久账号池指标相同谓词下可参与调度的账号数。
-    pub active_accounts: u64,
+    /// 继承运行参数默认并发上限的可调度账号数。
+    pub inherited_accounts: u64,
+    /// 已配置账号级并发上限的可调度账号槽位总数。
+    pub overridden_slots: u64,
     /// Redis 可用时的实时 in-flight 槽位总数；不可用时为 `None`。
     pub used_slots: Option<u64>,
 }
 
-/// 仪表盘所需的公共观测事实。
+/// 仪表盘卡片脚注展示的全历史累计。
+#[derive(Debug, Clone, Default, PartialEq)]
+pub struct DashboardTotals {
+    pub request_count: u64,
+    pub input_tokens: u64,
+    pub cached_tokens: u64,
+    pub total_tokens: u64,
+    pub billing_usd: Option<DecimalAmount>,
+}
+
+/// 仪表盘所需的当前区间事实及全历史累计。
 #[derive(Debug, Clone, PartialEq)]
 pub struct DashboardObservation {
     pub range: TimeRange,
-    pub requests: RequestMetrics,
-    pub attempts: AttemptMetrics,
+    pub totals: DashboardTotals,
     pub provider_accounts: AccountPoolMetrics,
     pub trend: Vec<RequestMetricPoint>,
     pub account_usage: Vec<DashboardAccountUsage>,
-    pub recent_requests: Vec<UsageRecord>,
+    pub recent_requests: Vec<UsageListRecord>,
+}
+
+/// 使用记录表格的窄读模型。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UsageListRecord {
+    pub id: String,
+    pub endpoint: String,
+    pub client_transport: String,
+    pub requested_model_id: Option<String>,
+    pub provider_kind: Option<String>,
+    pub provider_account_ref: Option<String>,
+    pub provider_account_name: Option<String>,
+    pub provider_account_email: Option<String>,
+    pub provider_account_authentication_kind: Option<String>,
+    pub upstream_model_id: Option<String>,
+    pub upstream_transport: Option<String>,
+    pub service_tier: Option<String>,
+    pub input_tokens: Option<u64>,
+    pub output_tokens: Option<u64>,
+    pub cached_tokens: Option<u64>,
+    pub cache_write_tokens: Option<u64>,
+    pub reasoning_tokens: Option<u64>,
+    pub image_input_tokens: Option<u64>,
+    pub image_output_tokens: Option<u64>,
+    pub total_tokens: Option<u64>,
+    pub cost_source: String,
+    pub cost_amount: Option<DecimalAmount>,
+    pub cost_currency: Option<String>,
+    pub billing: Option<UsageBilling>,
+    pub transport_decision_wait_ms: Option<u64>,
+    pub connect_ms: Option<u64>,
+    pub headers_ms: Option<u64>,
+    pub first_event_ms: Option<u64>,
+    pub first_reasoning_ms: Option<u64>,
+    pub first_text_ms: Option<u64>,
+    pub first_token_ms: Option<u64>,
+    pub provider_processing_ms: Option<u64>,
+    pub latency_ms: Option<u64>,
+    pub admission_decision_ms: Option<u64>,
+    pub account_selection_wait_ms: Option<u64>,
+    pub capacity_used_slots: Option<u64>,
+    pub capacity_total_slots: Option<u64>,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: bool,
+    pub started_at: DateTime<Utc>,
 }
 
 /// 一次完整模型请求的公共观测记录。
@@ -550,11 +583,14 @@ pub struct UsageRecord {
     pub id: String,
     pub client_api_key_ref: String,
     pub config_revision: u64,
+    pub routing_scope: String,
+    pub routing_group_refs: Vec<String>,
+    pub routing_group_names_snapshot: Vec<String>,
     pub protocol: String,
     pub operation: String,
     pub endpoint: String,
     pub client_transport: String,
-    pub requested_model_id: String,
+    pub requested_model_id: Option<String>,
     pub provider_kind: Option<String>,
     pub provider_account_ref: Option<String>,
     pub provider_account_name: Option<String>,
@@ -564,6 +600,7 @@ pub struct UsageRecord {
     pub upstream_transport: Option<String>,
     pub http_version: Option<String>,
     pub websocket_pool: Option<String>,
+    pub service_tier: Option<String>,
     /// Provider 已筛选的专有观测 JSON；管理领域保持不透明。
     pub provider_metadata_json: Option<String>,
     pub attempt_count: u32,
@@ -600,6 +637,10 @@ pub struct UsageRecord {
     pub first_token_ms: Option<u64>,
     pub provider_processing_ms: Option<u64>,
     pub latency_ms: Option<u64>,
+    pub admission_decision_ms: Option<u64>,
+    pub account_selection_wait_ms: Option<u64>,
+    pub capacity_used_slots: Option<u64>,
+    pub capacity_total_slots: Option<u64>,
     pub client_ip: Option<String>,
     pub user_agent: Option<String>,
     pub reasoning_effort: Option<String>,
@@ -617,9 +658,10 @@ pub struct UsageRecord {
 /// 用量分页结果。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UsagePage {
-    pub items: Vec<UsageRecord>,
+    pub items: Vec<UsageListRecord>,
+    pub current_page: u32,
+    pub page_size: u16,
     pub total: u64,
-    pub next_cursor: Option<ObservabilityCursor>,
 }
 
 /// 请求中的一次上游尝试或运维事件。
@@ -632,6 +674,9 @@ pub struct UsageAttempt {
     pub operation: String,
     pub provider_kind: Option<String>,
     pub provider_account_ref: Option<String>,
+    pub provider_account_name: Option<String>,
+    pub provider_account_email: Option<String>,
+    pub provider_account_authentication_kind: Option<String>,
     pub upstream_model_id: Option<String>,
     pub upstream_transport: Option<String>,
     pub upstream_send_state: Option<String>,
@@ -692,6 +737,7 @@ pub struct UsageSummary {
 /// 单个诊断维度值的聚合结果。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DiagnosticObservation {
+    pub key: String,
     pub name: String,
     pub request_count: u64,
     pub success_count: u64,
@@ -699,6 +745,10 @@ pub struct DiagnosticObservation {
     pub attempt_count: u64,
     pub total_tokens: u64,
     pub average_latency_ms: Option<u64>,
+    pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub retry_count: u64,
     pub cost_coverage: CostCoverage,
     pub costs: Vec<CurrencyCost>,
 }
@@ -713,18 +763,34 @@ pub struct OpsError {
     pub client_api_key_ref: Option<String>,
     pub component: String,
     pub operation: String,
+    pub protocol: Option<String>,
+    pub client_transport: Option<String>,
+    pub requested_model_id: Option<String>,
+    pub service_tier: Option<String>,
+    pub endpoint: Option<String>,
     pub provider_kind: Option<String>,
     pub provider_account_ref: Option<String>,
+    pub provider_account_name: Option<String>,
+    pub provider_account_email: Option<String>,
+    pub provider_account_authentication_kind: Option<String>,
     pub upstream_model_id: Option<String>,
     pub upstream_transport: Option<String>,
     pub failure_kind: String,
-    pub status_code: Option<u16>,
+    pub client_status_code: Option<u16>,
+    pub upstream_status_code: Option<u16>,
     pub provider_error_code: Option<String>,
     pub client_response_id: Option<String>,
     pub upstream_request_id: Option<String>,
     pub latency_ms: Option<u64>,
     pub message: String,
     pub occurrence_count: u32,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub request_kind: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: Option<bool>,
     pub occurred_at: DateTime<Utc>,
     pub stable_sort_id: String,
 }
@@ -733,8 +799,9 @@ pub struct OpsError {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct OpsErrorPage {
     pub items: Vec<OpsError>,
+    pub current_page: u32,
+    pub page_size: u16,
     pub total: u64,
-    pub next_cursor: Option<ObservabilityCursor>,
 }
 
 /// 仪表盘趋势指标。
@@ -773,6 +840,9 @@ pub struct TrendSummary {
     pub average_latency_ms: Option<u64>,
     pub max_latency_ms: Option<u64>,
     pub min_latency_ms: Option<u64>,
+    pub peak_first_token_p95_ms: Option<f64>,
+    pub peak_latency_p95_ms: Option<f64>,
+    pub minimum_output_throughput_p50: Option<u64>,
     pub success_rate: Option<f64>,
     pub cache_hit_request_rate: Option<f64>,
     pub costs: Vec<CurrencyCost>,
@@ -921,6 +991,7 @@ pub struct DashboardResult {
 /// 洞察健康时间点的语义结果。
 #[derive(Debug, Clone, PartialEq)]
 pub struct UsageInsightsHealthPoint {
+    pub total_requests: u64,
     pub bucket_start: DateTime<Utc>,
     pub success_requests: u64,
     pub failed_requests: u64,
@@ -940,6 +1011,7 @@ pub struct UsageInsightsHealth {
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
     pub success_rate: f64,
+    pub completion_rate: f64,
     pub points: Vec<UsageInsightsHealthPoint>,
 }
 
@@ -949,6 +1021,13 @@ pub struct UsageInsightsPerformancePoint {
     pub bucket_start: DateTime<Utc>,
     pub latency_percentiles: LatencyPercentiles,
     pub first_token_latency_percentiles: LatencyPercentiles,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
 }
 
 /// 洞察性能汇总与可观测覆盖率。
@@ -958,6 +1037,16 @@ pub struct UsageInsightsPerformance {
     pub first_token_latency_percentiles: LatencyPercentiles,
     pub latency_coverage: f64,
     pub first_token_coverage: f64,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub admission_decision_coverage: f64,
+    pub account_selection_wait_coverage: f64,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
+    pub capacity_coverage: f64,
     pub points: Vec<UsageInsightsPerformancePoint>,
 }
 
@@ -971,6 +1060,8 @@ pub struct UsageInsightsCostPoint {
     pub total_tokens: u64,
     pub estimated_cost: Option<DecimalAmount>,
     pub standard_cost: Option<DecimalAmount>,
+    pub no_cache_cost: Option<DecimalAmount>,
+    pub cache_savings: Option<DecimalAmount>,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
 }
@@ -980,7 +1071,11 @@ pub struct UsageInsightsCostPoint {
 pub struct UsageInsightsCost {
     pub estimated_cost: Option<DecimalAmount>,
     pub standard_cost: Option<DecimalAmount>,
+    pub no_cache_cost: Option<DecimalAmount>,
+    pub cache_savings: Option<DecimalAmount>,
+    pub tier_premium: Option<DecimalAmount>,
     pub cost_per_request: Option<DecimalAmount>,
+    pub cost_per_successful_request: Option<DecimalAmount>,
     pub tokens_per_request: f64,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
@@ -1007,6 +1102,7 @@ pub struct UsageInsights {
 /// 已完成分母计算的诊断项。
 #[derive(Debug, Clone, PartialEq)]
 pub struct DiagnosticsItem {
+    pub key: String,
     pub name: String,
     pub request_count: u64,
     pub success_count: u64,
@@ -1014,6 +1110,13 @@ pub struct DiagnosticsItem {
     pub error_rate: f64,
     pub request_share: f64,
     pub average_latency_ms: Option<u64>,
+    pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub non_completion_rate: f64,
+    pub retry_count: u64,
+    pub retry_rate: f64,
+    pub impact_score: f64,
     pub estimated_cost: Option<DecimalAmount>,
     pub attempt_count: u64,
     pub total_tokens: u64,

backend/crates/gateway-admin/src/model/provider_credentials.rs

@@ -1,16 +1,20 @@
 //! Provider 管理能力交换的中立 Command 与 Result。
 
-use std::fmt;
+use std::{fmt, pin::Pin};
 
-use chrono::{DateTime, Utc};
+use async_trait::async_trait;
+use bytes::Bytes;
+use chrono::{DateTime, NaiveDate, Utc};
+use futures::Stream;
 use gateway_core::{
-    engine::credential::{OpaqueProviderData, ProviderAccountId},
+    engine::credential::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
     routing::{ProviderKind, UpstreamModelId},
 };
+use uuid::Uuid;
 
 use super::{
-    MutationActor, MutationContext, PageSize, Revision,
-    accounts::{AccountAvailability, AccountRecord, AccountStatus, AccountSummary, AccountUsage},
+    AdminError, MutationActor, MutationContext, PageSize, Revision,
+    accounts::{AccountRecord, AccountSummary, AccountUsage, CredentialState},
 };
 
 /// Provider-owned JSON；公共层只搬运且 Debug 不输出值。
@@ -51,24 +55,24 @@ pub struct CredentialCursor {
 /// Provider credential 列表查询。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CredentialListQuery {
-    pub availability: Option<CredentialAvailabilityFilter>,
+    pub credential_state: Option<CredentialStateFilter>,
     pub enabled: Option<bool>,
     pub window: CredentialListWindow,
 }
 
-/// Credential 可用性筛选；支持一个 wire 值对应多个持久状态。
+/// Credential 状态筛选。
 #[derive(Debug, Clone, PartialEq, Eq)]
-pub enum CredentialAvailabilityFilter {
-    Exact(AccountAvailability),
-    AnyOf(Vec<AccountAvailability>),
+pub enum CredentialStateFilter {
+    Exact(CredentialState),
+    AnyOf(Vec<CredentialState>),
 }
 
-impl CredentialAvailabilityFilter {
+impl CredentialStateFilter {
     #[must_use]
-    pub fn matches(&self, availability: AccountAvailability) -> bool {
+    pub fn matches(&self, credential_state: CredentialState) -> bool {
         match self {
-            Self::Exact(expected) => *expected == availability,
-            Self::AnyOf(expected) => expected.contains(&availability),
+            Self::Exact(expected) => *expected == credential_state,
+            Self::AnyOf(expected) => expected.contains(&credential_state),
         }
     }
 }
@@ -101,7 +105,6 @@ pub struct CredentialDetails {
 /// Provider 正式文档批量导入命令。
 pub struct ImportCredentials {
     pub context: MutationContext,
-    pub expected_config_revision: Revision,
     pub document: ProviderDocument,
 }
 
@@ -110,7 +113,6 @@ impl fmt::Debug for ImportCredentials {
         formatter
             .debug_struct("ImportCredentials")
             .field("context", &self.context)
-            .field("expected_config_revision", &self.expected_config_revision)
             .field("document", &self.document)
             .finish()
     }
@@ -144,7 +146,7 @@ pub struct PreparedCredentialCreate {
     pub provider_kind: ProviderKind,
     pub name: String,
     pub email: Option<String>,
-    pub upstream_user_id: String,
+    pub upstream_user_id: Option<String>,
     pub upstream_account_id: Option<String>,
     pub plan_type: Option<String>,
     pub authentication_kind: String,
@@ -153,10 +155,8 @@ pub struct PreparedCredentialCreate {
     pub access_token_expires_at: Option<DateTime<Utc>>,
     pub next_refresh_at: Option<DateTime<Utc>>,
     pub enabled: bool,
-    pub availability: AccountAvailability,
-    pub availability_reason: Option<String>,
-    pub cooldown_until: Option<DateTime<Utc>>,
-    pub availability_observed_at: DateTime<Utc>,
+    pub credential_state: CredentialState,
+    pub credential_observed_at: DateTime<Utc>,
 }
 
 /// Provider 对一份导入文档的完整验证结果。
@@ -169,17 +169,9 @@ pub struct PreparedCredentialImport {
 /// Admin 交给 Store 的导入事务命令。
 #[derive(Debug, Clone, PartialEq)]
 pub struct CredentialImportCommit {
-    pub expected_config_revision: Revision,
     pub prepared: PreparedCredentialImport,
 }
 
-/// 可选的重新授权目标。
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct ReauthorizationTarget {
-    pub account_id: ProviderAccountId,
-    pub credential_revision: Revision,
-}
-
 /// OAuth pending owner 的中立身份；不编码具体 Provider 的 Redis key 或 JSON。
 #[derive(Clone, PartialEq, Eq)]
 pub enum AuthorizationOwner {
@@ -240,21 +232,18 @@ impl fmt::Debug for AuthorizationOwnerBinding {
 }
 
 /// OAuth 完成时应创建新账号还是 CAS 更新既有 credential。
+///
+/// 重新授权只绑定稳定的账号身份：credential revision 由服务端在临近写入时读取，
+/// 长流程期间的后台刷新不得让恢复操作失效。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AuthorizationMutationTarget {
-    Create {
-        name: String,
-    },
-    Reauthorize {
-        account_id: ProviderAccountId,
-        expected_credential_revision: Revision,
-    },
+    Create { name: String },
+    Reauthorize { account_id: ProviderAccountId },
 }
 
 /// 必须完整进入 Provider opaque pending payload、并在 complete 后原样恢复的事务信封。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct PendingAuthorizationMutation {
-    expected_config_revision: Revision,
     provider_kind: ProviderKind,
     target: AuthorizationMutationTarget,
     owner_binding: AuthorizationOwnerBinding,
@@ -263,24 +252,17 @@ pub struct PendingAuthorizationMutation {
 impl PendingAuthorizationMutation {
     #[must_use]
     pub const fn new(
-        expected_config_revision: Revision,
         provider_kind: ProviderKind,
         target: AuthorizationMutationTarget,
         owner_binding: AuthorizationOwnerBinding,
     ) -> Self {
         Self {
-            expected_config_revision,
             provider_kind,
             target,
             owner_binding,
         }
     }
 
-    #[must_use]
-    pub const fn expected_config_revision(&self) -> Revision {
-        self.expected_config_revision
-    }
-
     #[must_use]
     pub const fn provider_kind(&self) -> &ProviderKind {
         &self.provider_kind
@@ -301,9 +283,8 @@ impl PendingAuthorizationMutation {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct StartAuthorization {
     pub context: MutationContext,
-    pub expected_config_revision: Revision,
     pub name: String,
-    pub reauthorization: Option<ReauthorizationTarget>,
+    pub reauthorization: Option<ProviderAccountId>,
 }
 
 /// OAuth 流程启动结果。
@@ -322,6 +303,20 @@ pub trait CredentialCommitGuard: Send + 'static {
     fn finish(self: Box<Self>);
 }
 
+/// OAuth pending claim 在 Store 事务结果确定后执行的显式结算动作。
+///
+/// OAuth provider 必须在 credential 准备阶段持有 claim：Store 提交成功后消费 flow，提交或
+/// 校验失败后释放 flow。异步结算不能依赖 `Drop`，否则请求提前返回会让同一授权流无谓地
+/// 进入短暂的不可重试状态。
+#[async_trait]
+pub trait AuthorizationCommitGuard: Send + 'static {
+    /// Store 已提交 OAuth credential 后消费对应的一次性 flow。
+    async fn commit(self: Box<Self>) -> Result<(), AdminError>;
+
+    /// Store 未提交 OAuth credential 时释放 claim，允许同一 flow 重试。
+    async fn abort(self: Box<Self>) -> Result<(), AdminError>;
+}
+
 /// OAuth complete 后由 Provider 返回的准备结果；Store 仍是唯一提交者。
 pub enum PreparedAuthorizationCredential {
     Create(PreparedCredentialCreate),
@@ -332,6 +327,7 @@ pub enum PreparedAuthorizationCredential {
 pub struct PreparedAuthorizationCommit {
     pub pending: PendingAuthorizationMutation,
     pub credential: PreparedAuthorizationCredential,
+    authorization_guard: Option<Box<dyn AuthorizationCommitGuard>>,
 }
 
 impl fmt::Debug for PreparedAuthorizationCommit {
@@ -358,9 +354,37 @@ pub struct AuthorizationCommit {
     pub credential: AuthorizationCredentialCommit,
 }
 
+/// OAuth 准备结果拆解后的 Store 命令与两个结算 guard。
+///
+/// Store 成功时先结束 credential guard，再消费 OAuth claim；失败时丢弃 credential guard 并
+/// 释放 OAuth claim，使同一授权流可以重试。
+pub(crate) struct AuthorizationCommitSettlement {
+    pub(crate) command: AuthorizationCommit,
+    pub(crate) credential_guard: Option<Box<dyn CredentialCommitGuard>>,
+    pub(crate) authorization_guard: Option<Box<dyn AuthorizationCommitGuard>>,
+}
+
 impl PreparedAuthorizationCommit {
     #[must_use]
-    pub fn into_commit(self) -> (AuthorizationCommit, Option<Box<dyn CredentialCommitGuard>>) {
+    pub fn new(
+        pending: PendingAuthorizationMutation,
+        credential: PreparedAuthorizationCredential,
+    ) -> Self {
+        Self {
+            pending,
+            credential,
+            authorization_guard: None,
+        }
+    }
+
+    /// 让 OAuth claim 覆盖准备完成到 Store 事务结算之间的全部窗口。
+    #[must_use]
+    pub fn with_authorization_guard(mut self, guard: Box<dyn AuthorizationCommitGuard>) -> Self {
+        self.authorization_guard = Some(guard);
+        self
+    }
+
+    pub(crate) fn into_commit(self) -> AuthorizationCommitSettlement {
         let (credential, guard) = match self.credential {
             PreparedAuthorizationCredential::Create(credential) => {
                 (AuthorizationCredentialCommit::Create(credential), None)
@@ -373,13 +397,27 @@ impl PreparedAuthorizationCommit {
                 )
             }
         };
-        (
-            AuthorizationCommit {
+        AuthorizationCommitSettlement {
+            command: AuthorizationCommit {
                 pending: self.pending,
                 credential,
             },
-            guard,
-        )
+            credential_guard: guard,
+            authorization_guard: self.authorization_guard,
+        }
+    }
+
+    pub(crate) async fn abort(self) -> Result<(), AdminError> {
+        let AuthorizationCommitSettlement {
+            credential_guard,
+            authorization_guard,
+            ..
+        } = self.into_commit();
+        drop(credential_guard);
+        if let Some(guard) = authorization_guard {
+            guard.abort().await?;
+        }
+        Ok(())
     }
 }
 
@@ -406,7 +444,6 @@ impl fmt::Debug for CompleteAuthorization {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CredentialMutation {
     pub context: MutationContext,
-    pub expected_config_revision: Revision,
     pub account_id: ProviderAccountId,
 }
 
@@ -422,7 +459,6 @@ pub struct CredentialMutationResult {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct CredentialDeletion {
     pub context: MutationContext,
-    pub expected_config_revision: Revision,
     pub account_ids: Vec<ProviderAccountId>,
 }
 
@@ -436,14 +472,12 @@ pub struct CredentialDeletionResult {
 /// Provider-owned token 轮换命令。
 pub struct RotateCredential {
     pub mutation: CredentialMutation,
-    pub expected_credential_revision: Revision,
     pub provider_material: ProviderDocument,
 }
 
 /// Provider 校验手工轮换材料时所需的非事务输入。
 pub struct PrepareCredentialRotation {
     pub account: AccountRecord,
-    pub expected_credential_revision: Revision,
     pub provider_material: ProviderDocument,
 }
 
@@ -452,10 +486,6 @@ impl fmt::Debug for PrepareCredentialRotation {
         formatter
             .debug_struct("PrepareCredentialRotation")
             .field("account", &self.account)
-            .field(
-                "expected_credential_revision",
-                &self.expected_credential_revision,
-            )
             .field("provider_material", &self.provider_material)
             .finish()
     }
@@ -467,6 +497,7 @@ pub struct PreparedCredentialRotationFacts {
     pub account_id: ProviderAccountId,
     pub provider_kind: ProviderKind,
     pub expected_credential_revision: Revision,
+    pub replacement_identity: Option<ProviderAccountIdentity>,
     pub name: String,
     pub email: Option<String>,
     pub plan_type: Option<String>,
@@ -520,7 +551,6 @@ impl fmt::Debug for PreparedCredentialRotation {
 /// Admin 交给 Store 的轮换或 refresh 事务命令。
 #[derive(Debug, Clone, PartialEq)]
 pub struct CredentialRotationCommit {
-    pub expected_config_revision: Revision,
     pub prepared: PreparedCredentialRotationFacts,
 }
 
@@ -529,25 +559,53 @@ impl fmt::Debug for RotateCredential {
         formatter
             .debug_struct("RotateCredential")
             .field("mutation", &self.mutation)
-            .field(
-                "expected_credential_revision",
-                &self.expected_credential_revision,
-            )
             .field("provider_material", &self.provider_material)
             .finish()
     }
 }
 
+/// 通用账号用量能否可靠归属到一个 Provider quota 窗口。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum QuotaLocalUsageAttribution {
+    /// 窗口覆盖账号的全部请求，可按账号与时间范围聚合。
+    AccountWide,
+    /// 窗口需要 Provider / 模型级归属，通用账号聚合不可用。
+    Unavailable,
+}
+
+/// Provider quota bucket 中窗口的官方位置语义。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ProviderQuotaWindowRole {
+    Primary,
+    Secondary,
+    Monthly,
+}
+
+impl ProviderQuotaWindowRole {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::Primary => "primary",
+            Self::Secondary => "secondary",
+            Self::Monthly => "monthly",
+        }
+    }
+}
+
 /// 一个 Provider quota 窗口的公共投影。
 #[derive(Debug, Clone, PartialEq)]
 pub struct ProviderQuotaWindow {
     pub key: String,
     pub group: String,
     pub label: String,
-    pub source: Option<String>,
+    pub limit_id: Option<String>,
+    pub limit_name: Option<String>,
+    pub role: Option<ProviderQuotaWindowRole>,
+    pub local_usage_attribution: QuotaLocalUsageAttribution,
     pub window_seconds: Option<u64>,
     pub used_percent: Option<f64>,
     pub reset_at: Option<DateTime<Utc>>,
+    pub limit_reached: bool,
     pub local_usage: Option<AccountUsage>,
     pub provider_data: Option<ProviderDocument>,
 }
@@ -566,45 +624,234 @@ pub struct ProviderQuota {
     pub observed_at: Option<DateTime<Utc>>,
     pub refresh_token_expires_at: Option<DateTime<Utc>>,
     pub windows: Vec<ProviderQuotaWindow>,
+    /// 展示用快照级触顶事实（顶层或任一窗口触顶）；不参与账号五态派生。
+    pub limit_reached: bool,
     pub provider_data: Option<ProviderDocument>,
 }
 
+/// Provider 官方个人资料中的累计摘要。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileStatisticsSummary {
+    pub total_text_tokens: Option<u64>,
+    pub peak_tokens: Option<u64>,
+    pub longest_task_duration_ms: Option<u64>,
+    pub current_streak_days: Option<u64>,
+    pub longest_streak_days: Option<u64>,
+}
+
+/// Provider 官方个人资料中的单日 Token bucket。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileDailyUsage {
+    pub date: NaiveDate,
+    pub tokens: u64,
+}
+
+/// Provider 官方个人资料中的插件或 Skill 调用排行。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileInvocation {
+    pub invocation_type: String,
+    pub plugin_id: Option<String>,
+    pub plugin_name: Option<String>,
+    pub skill_id: Option<String>,
+    pub skill_name: Option<String>,
+    pub usage_count: Option<u64>,
+}
+
+/// Provider 官方个人资料中的活动洞察。
+#[derive(Debug, Clone, PartialEq)]
+pub struct ProviderProfileActivityInsights {
+    pub fast_mode_percent: Option<f64>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_effort_percent: Option<f64>,
+    pub skills_explored: Option<u64>,
+    pub total_skills_used: Option<u64>,
+    pub total_threads: Option<u64>,
+    pub invocations: Option<Vec<ProviderProfileInvocation>>,
+}
+
+/// Provider 已解释的官方个人资料统计。
+#[derive(Debug, Clone, PartialEq)]
+pub struct ProviderProfileStatistics {
+    pub display_name: Option<String>,
+    pub username: Option<String>,
+    pub image_url: Option<String>,
+    pub has_stats_error: bool,
+    pub summary: ProviderProfileStatisticsSummary,
+    pub daily_usage: Option<Vec<ProviderProfileDailyUsage>>,
+    pub activity_insights: ProviderProfileActivityInsights,
+}
+
+/// Provider 头像正文的中立字节流；公共层不解释 MIME，也不限制总字节数。
+pub type ProviderProfileAvatarStream =
+    Pin<Box<dyn Stream<Item = Result<Bytes, ProviderProfileAvatarStreamError>> + Send + 'static>>;
+
+/// Provider 头像流在响应开始后的通用失败，不携带上游 URL 或正文。
+#[derive(Debug, thiserror::Error)]
+#[error("provider profile avatar stream failed")]
+pub struct ProviderProfileAvatarStreamError;
+
+/// Provider 已校验并打开的官方头像响应。
+pub struct ProviderProfileAvatar {
+    pub content_type: Option<String>,
+    pub content_length: Option<u64>,
+    pub etag: Option<String>,
+    pub body: ProviderProfileAvatarStream,
+}
+
+impl fmt::Debug for ProviderProfileAvatar {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("ProviderProfileAvatar")
+            .field("content_type", &self.content_type)
+            .field("content_length", &self.content_length)
+            .field("etag", &self.etag)
+            .field("body", &"<stream>")
+            .finish()
+    }
+}
+
+/// Provider 返回的一张安全主动额度重置卡。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderResetCredit {
+    pub id: String,
+    pub status: Option<String>,
+    pub title: Option<String>,
+    pub expires_at: Option<DateTime<Utc>>,
+    pub reset_type: Option<String>,
+}
+
+/// Provider 主动额度重置卡列表。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderResetCredits {
+    pub available_count: u64,
+    pub credits: Vec<ProviderResetCredit>,
+}
+
+/// 一次主动额度重置卡消费命令。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ConsumeProviderResetCredit {
+    pub account_id: ProviderAccountId,
+    pub credit_id: Option<String>,
+    pub redeem_request_id: Uuid,
+}
+
+/// Provider 返回的主动额度重置卡消费结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderResetCreditResult {
+    pub code: String,
+    pub credit: Option<ProviderResetCredit>,
+}
+
 impl ProviderQuota {
-    /// 返回 Dashboard 使用的代表性额度比例。
+    /// 返回账号展开面板使用的当前额度窗口用量。
     ///
-    /// 优先使用短周期窗口，再依次使用周、月和其它窗口；同一优先级取较高的已用比例。
-    /// 这里只解释跨 Provider 共享的窗口语义，绝不读取 Provider 私有 JSON。
+    /// Provider 已提供账号级本地用量时，固定窗口和无固定重置点的滚动窗口
+    /// 都可作为代表用量；优先级与 Dashboard 代表性额度窗口一致，
+    /// 同一优先级保持 Provider 投影顺序。
     #[must_use]
-    pub fn representative_used_percent(&self) -> Option<f64> {
+    pub fn representative_window_usage(&self) -> Option<&AccountUsage> {
         self.windows
             .iter()
+            .enumerate()
+            .filter(|(_, window)| {
+                window.local_usage_attribution == QuotaLocalUsageAttribution::AccountWide
+                    && window.window_seconds.is_some()
+                    && window.local_usage.is_some()
+            })
+            .min_by_key(|(index, window)| (quota_usage_priority(window), *index))
+            .and_then(|(_, window)| window.local_usage.as_ref())
+    }
+
+    /// 返回 Dashboard 使用的代表性额度比例。
+    ///
+    /// 优先使用覆盖账号全部请求的窗口；同一归属范围内再依次使用短周期、周、月
+    /// 和其它窗口，同一优先级取较高的已用比例。这里只解释跨 Provider 共享的窗口
+    /// 语义，绝不读取 Provider 私有 JSON。
+    #[must_use]
+    pub fn representative_used_percent(&self) -> Option<f64> {
+        if self.limit_reached {
+            return Some(100.0);
+        }
+        self.representative_used_window()
+            .map(|(_, used_percent)| used_percent)
+    }
+
+    /// 将已确认的账号级额度耗尽事实投影到展示窗口。
+    ///
+    /// Provider 已指出具体触顶窗口时只归一化这些窗口；否则归一化 Dashboard
+    /// 同样会选择的代表窗口，避免把多个独立额度窗口全部伪造成已用尽。
+    pub fn apply_limit_reached_display(&mut self) {
+        if !self.limit_reached {
+            return;
+        }
+        let reached_windows = self
+            .windows
+            .iter()
+            .enumerate()
+            .filter_map(|(index, window)| window.limit_reached.then_some(index))
+            .collect::<Vec<_>>();
+        if !reached_windows.is_empty() {
+            for index in reached_windows {
+                self.windows[index].used_percent = Some(100.0);
+            }
+            return;
+        }
+        let representative = self
+            .representative_used_window()
+            .map(|(index, _)| index)
+            .or_else(|| {
+                self.windows
+                    .iter()
+                    .enumerate()
+                    .min_by_key(|(index, window)| (quota_usage_priority(window), *index))
+                    .map(|(index, _)| index)
+            });
+        if let Some(index) = representative {
+            self.windows[index].used_percent = Some(100.0);
+            self.windows[index].limit_reached = true;
+        }
+    }
+
+    fn representative_used_window(&self) -> Option<(usize, f64)> {
+        self.windows
+            .iter()
+            .enumerate()
             .filter_map(|window| {
+                let (index, window) = window;
                 let used_percent = window
                     .used_percent
                     .filter(|value| value.is_finite())
                     .map(|value| value.clamp(0.0, 100.0))?;
-                Some((quota_usage_priority(window), used_percent))
+                Some((index, quota_usage_priority(window), used_percent))
             })
-            .fold(None::<(u8, f64)>, |selected, candidate| match selected {
-                Some(current)
-                    if current.0 < candidate.0
-                        || (current.0 == candidate.0 && current.1 >= candidate.1) =>
-                {
+            .fold(
+                None::<(usize, (u8, u8), f64)>,
+                |selected, candidate| match selected {
                     Some(current)
-                }
-                _ => Some(candidate),
-            })
-            .map(|(_, used_percent)| used_percent)
+                        if current.1 < candidate.1
+                            || (current.1 == candidate.1 && current.2 >= candidate.2) =>
+                    {
+                        Some(current)
+                    }
+                    _ => Some(candidate),
+                },
+            )
+            .map(|(index, _, used_percent)| (index, used_percent))
     }
 }
 
-fn quota_usage_priority(window: &ProviderQuotaWindow) -> u8 {
-    match window.group.as_str() {
+fn quota_usage_priority(window: &ProviderQuotaWindow) -> (u8, u8) {
+    let attribution = match window.local_usage_attribution {
+        QuotaLocalUsageAttribution::AccountWide => 0,
+        QuotaLocalUsageAttribution::Unavailable => 1,
+    };
+    let duration = match window.group.as_str() {
         "shortTerm" if window.window_seconds.is_some_and(is_week_window) => 1,
         "shortTerm" => 0,
         "monthly" => 2,
         _ => 3,
-    }
+    };
+    (attribution, duration)
 }
 
 fn is_week_window(seconds: u64) -> bool {
@@ -661,7 +908,7 @@ impl fmt::Debug for ProviderExport {
 #[derive(Debug, Clone, PartialEq)]
 pub struct AccountDirectoryItem {
     pub account: AccountRecord,
-    pub status: AccountStatus,
+    pub projection: gateway_core::engine::credential::AccountStatusProjection,
     pub usage: Option<super::accounts::AccountUsage>,
     pub quota: ProviderQuota,
 }

backend/crates/gateway-admin/src/model/settings.rs

@@ -11,14 +11,8 @@ use super::Revision;
 /// 客户端模型到上游模型的全局精确映射。
 pub type ModelMappings = BTreeMap<PublicModelId, UpstreamModelId>;
 
-/// 账号调度策略。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum RotationStrategy {
-    Smart,
-    QuotaResetPriority,
-    RoundRobin,
-    Sticky,
-}
+/// 账号调度策略；由 Core 拥有稳定值与 wire 映射。
+pub use gateway_core::engine::credential::RotationStrategy;
 
 /// 完整运行设置事实。
 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -39,7 +33,6 @@ pub struct RuntimeSettings {
 /// 原子替换运行设置的命令。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ReplaceRuntimeSettings {
-    pub expected_config_revision: Revision,
     pub model_mappings: ModelMappings,
     pub refresh_margin_seconds: u64,
     pub refresh_concurrency: u32,

backend/crates/gateway-admin/src/ports/backup.rs

@@ -0,0 +1,442 @@
+//! 备份控制面所需的持久化与基础设施能力。
+//!
+//! 端口方法只接受/返回领域类型与既有错误体系：`BackupRepository` 复用
+//! `AdminStoreError`；`DatabaseDumpPort` 与 `BackupObjectStorePort` 返回只携带稳定
+//! 错误码的 [`BackupError`]。`gateway-store` 实现全部端口；`gateway-admin` 拥有
+//! 状态机、Cron、保留策略与 BackupTask 算法。
+
+use std::path::PathBuf;
+use std::sync::Arc;
+use std::time::Duration;
+
+use async_trait::async_trait;
+use chrono::{DateTime, Utc};
+
+use crate::model::Revision;
+use crate::model::{
+    MutationContext,
+    backup::{
+        BackupError, BackupObjectMetadata, BackupRecord, BackupRecordListQuery, BackupRecordPage,
+        BackupRecordSeed, BackupSettings, BackupStatus, BackupStorageConfig, ConnectionTestResult,
+        UpdateBackupScheduleCommand, UpdateBackupStorageCommand,
+    },
+};
+use crate::ports::store::AdminStoreResult;
+
+/// Worker 状态迁移携带的字段更新；`None` 字段不写入。
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct StatusTransitionUpdate {
+    pub size_bytes: Option<u64>,
+    pub sha256: Option<String>,
+    pub error_code: Option<String>,
+    pub error_message: Option<String>,
+    pub completed_at: Option<DateTime<Utc>>,
+}
+
+/// 备份配置、任务与计划游标的 PostgreSQL 仓储端口。
+#[async_trait]
+pub trait BackupRepository: Send + Sync {
+    /// 读取完整设置（含 Secret）。
+    async fn load_settings(&self) -> AdminStoreResult<BackupSettings>;
+
+    /// 同事务更新 S3 存储配置、递增 revision、清空验证状态并写审计事件。
+    ///
+    /// 已有记录时禁止切换 endpoint/region/bucket/path-style（存储身份锁定）。
+    /// 返回更新后的设置与新的全局 `config_revision`。
+    async fn update_storage_settings(
+        &self,
+        command: UpdateBackupStorageCommand,
+        context: &MutationContext,
+    ) -> AdminStoreResult<(BackupSettings, Revision)>;
+
+    /// 同事务更新调度配置、推进计划游标并写审计事件。
+    async fn update_schedule_settings(
+        &self,
+        command: UpdateBackupScheduleCommand,
+        next_run_at: Option<DateTime<Utc>>,
+        context: &MutationContext,
+    ) -> AdminStoreResult<BackupSettings>;
+
+    /// CAS 记录探针成功；`storage_revision` 与当前配置不一致时丢弃结果（返回 `false`）。
+    async fn record_verification(
+        &self,
+        storage_revision: u64,
+        at: DateTime<Utc>,
+    ) -> AdminStoreResult<bool>;
+
+    /// 插入 queued 任务；存在活跃任务时返回 `backup.active_task_conflict`。
+    async fn insert_backup_record(&self, seed: BackupRecordSeed) -> AdminStoreResult<BackupRecord>;
+
+    /// 幂等插入 scheduled 任务；同一时间点或活跃冲突时返回 `false`（调用方推进游标即可）。
+    async fn insert_scheduled_record(&self, seed: BackupRecordSeed) -> AdminStoreResult<bool>;
+
+    /// 分页查询记录。
+    async fn list_backup_records(
+        &self,
+        query: BackupRecordListQuery,
+    ) -> AdminStoreResult<BackupRecordPage>;
+
+    /// 读取单条记录。
+    async fn load_backup_record(&self, id: &str) -> AdminStoreResult<Option<BackupRecord>>;
+
+    /// 读取中间状态记录（dumping/uploading），供启动恢复。
+    async fn list_intermediate_records(&self) -> AdminStoreResult<Vec<BackupRecord>>;
+
+    /// 读取等待完成墓碑的记录（status = deleting）。
+    async fn list_pending_deletions(&self, limit: u32) -> AdminStoreResult<Vec<BackupRecord>>;
+
+    /// 读取 `expires_at` 已到期且非活跃的记录（completed/failed），供保留清理。
+    async fn list_expired_records(&self, limit: u32) -> AdminStoreResult<Vec<BackupRecord>>;
+
+    /// 原子领取最旧的 queued 任务并迁移到 dumping；无任务返回 `None`。
+    async fn claim_next_queued(&self, now: DateTime<Utc>)
+    -> AdminStoreResult<Option<BackupRecord>>;
+
+    /// 条件迁移状态：要求当前状态一致；不匹配返回 `None`。
+    async fn transition_status(
+        &self,
+        id: &str,
+        from: BackupStatus,
+        to: BackupStatus,
+        update: StatusTransitionUpdate,
+        now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>>;
+
+    /// 迁移到删除流程（completed/failed → deleting）；供管理员与保留策略调用。
+    async fn transition_to_deleting(
+        &self,
+        id: &str,
+        now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>>;
+
+    /// 远端删除成功后硬删除记录行。
+    async fn delete_record(&self, id: &str) -> AdminStoreResult<()>;
+
+    /// 条件推进计划游标；仅当计划表达式和时区仍是 `expected_*` 时才写入，返回是否推进。
+    async fn advance_schedule_cursor(
+        &self,
+        next_run_at: DateTime<Utc>,
+        expected_cron: &str,
+        expected_timezone: &str,
+    ) -> AdminStoreResult<bool>;
+
+    /// 按完成时间倒序读取 completed 计划备份，供保留策略扫描（最多 `limit` 条）。
+    async fn list_scheduled_completed_desc(
+        &self,
+        limit: u32,
+    ) -> AdminStoreResult<Vec<BackupRecord>>;
+}
+
+/// `pg_dump` 导出与本地暂存端口。
+#[async_trait]
+pub trait DatabaseDumpPort: Send + Sync {
+    /// 创建归档；完成后原子落盘。取消时终止子进程并清理部分文件。
+    async fn dump(&self, request: DumpRequest) -> Result<DumpArtifact, BackupError>;
+
+    /// 检查暂存目录是否存在完整归档。
+    async fn inspect_staging(&self, backup_id: &str)
+    -> Result<Option<StagedArtifact>, BackupError>;
+
+    /// 清理暂存目录中该备份的全部文件。
+    async fn cleanup_staging(&self, backup_id: &str) -> Result<(), BackupError>;
+}
+
+/// 一次 `pg_dump` 请求。
+#[derive(Debug, Clone)]
+pub struct DumpRequest {
+    pub backup_id: String,
+    pub cancellation: gateway_core::engine::CancellationToken,
+}
+
+/// 已完成并落盘的归档事实。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct DumpArtifact {
+    pub path: PathBuf,
+    pub size_bytes: u64,
+    pub sha256: String,
+}
+
+/// 暂存目录中已存在的完整归档。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct StagedArtifact {
+    pub path: PathBuf,
+    pub size_bytes: u64,
+    pub sha256: String,
+}
+
+/// S3 兼容对象存储适配器端口。
+///
+/// 方法接受已经校验的存储配置；SDK client 的构造与缓存属于 adapter 实现细节。
+#[async_trait]
+pub trait BackupObjectStorePort: Send + Sync {
+    /// 对专用探针对象执行 Put/Head/Get/Delete。
+    async fn test_connection(
+        &self,
+        config: &BackupStorageConfig,
+    ) -> Result<ConnectionTestResult, BackupError>;
+
+    /// 分片流式上传本地归档；取消时中止 multipart 并返回 `backup.cancelled`。
+    async fn upload_file(
+        &self,
+        config: &BackupStorageConfig,
+        request: UploadObjectRequest,
+    ) -> Result<(), BackupError>;
+
+    /// 读取对象大小与 metadata；对象不存在返回 `Ok(None)`。
+    async fn head_object(
+        &self,
+        config: &BackupStorageConfig,
+        object_key: &str,
+    ) -> Result<Option<BackupObjectMetadata>, BackupError>;
+
+    /// 删除对象；对象不存在视为成功。
+    async fn delete_object(
+        &self,
+        config: &BackupStorageConfig,
+        object_key: &str,
+    ) -> Result<(), BackupError>;
+
+    /// 创建短时预签名下载 URL。
+    async fn presigned_download(
+        &self,
+        config: &BackupStorageConfig,
+        object_key: &str,
+        file_name: &str,
+        ttl: Duration,
+    ) -> Result<String, BackupError>;
+}
+
+/// 一次对象上传请求。
+#[derive(Debug, Clone)]
+pub struct UploadObjectRequest {
+    pub object_key: String,
+    pub source: PathBuf,
+    pub metadata: BackupObjectMetadata,
+    pub cancellation: gateway_core::engine::CancellationToken,
+}
+
+/// 备份控制面所需的全部 Store 能力集合。
+#[derive(Clone)]
+pub struct BackupStorePorts {
+    repository: Arc<dyn BackupRepository>,
+    dump: Arc<dyn DatabaseDumpPort>,
+    object_store: Arc<dyn BackupObjectStorePort>,
+}
+
+impl BackupStorePorts {
+    /// 组合备份端口。
+    #[must_use]
+    pub fn new(
+        repository: Arc<dyn BackupRepository>,
+        dump: Arc<dyn DatabaseDumpPort>,
+        object_store: Arc<dyn BackupObjectStorePort>,
+    ) -> Self {
+        Self {
+            repository,
+            dump,
+            object_store,
+        }
+    }
+
+    /// 备份任务/配置仓储。
+    #[must_use]
+    pub fn repository(&self) -> Arc<dyn BackupRepository> {
+        self.repository.clone()
+    }
+
+    /// `pg_dump` 导出与暂存。
+    #[must_use]
+    pub fn dump(&self) -> Arc<dyn DatabaseDumpPort> {
+        self.dump.clone()
+    }
+
+    /// S3/R2 对象存储适配器。
+    #[must_use]
+    pub fn object_store(&self) -> Arc<dyn BackupObjectStorePort> {
+        self.object_store.clone()
+    }
+
+    /// 测试与不可用路径使用的空实现；任何调用都返回不可用错误。
+    #[doc(hidden)]
+    #[must_use]
+    pub fn disabled() -> Self {
+        Self {
+            repository: Arc::new(UnavailableBackupRepository),
+            dump: Arc::new(UnavailableDumpPort),
+            object_store: Arc::new(UnavailableObjectStore),
+        }
+    }
+}
+
+struct UnavailableBackupRepository;
+
+#[async_trait]
+impl BackupRepository for UnavailableBackupRepository {
+    async fn load_settings(&self) -> AdminStoreResult<BackupSettings> {
+        Err(disabled_store())
+    }
+    async fn update_storage_settings(
+        &self,
+        _command: UpdateBackupStorageCommand,
+        _context: &MutationContext,
+    ) -> AdminStoreResult<(BackupSettings, Revision)> {
+        Err(disabled_store())
+    }
+    async fn update_schedule_settings(
+        &self,
+        _command: UpdateBackupScheduleCommand,
+        _next_run_at: Option<DateTime<Utc>>,
+        _context: &MutationContext,
+    ) -> AdminStoreResult<BackupSettings> {
+        Err(disabled_store())
+    }
+    async fn record_verification(
+        &self,
+        _storage_revision: u64,
+        _at: DateTime<Utc>,
+    ) -> AdminStoreResult<bool> {
+        Err(disabled_store())
+    }
+    async fn insert_backup_record(
+        &self,
+        _seed: BackupRecordSeed,
+    ) -> AdminStoreResult<BackupRecord> {
+        Err(disabled_store())
+    }
+    async fn insert_scheduled_record(&self, _seed: BackupRecordSeed) -> AdminStoreResult<bool> {
+        Err(disabled_store())
+    }
+    async fn list_backup_records(
+        &self,
+        _query: BackupRecordListQuery,
+    ) -> AdminStoreResult<BackupRecordPage> {
+        Err(disabled_store())
+    }
+    async fn load_backup_record(&self, _id: &str) -> AdminStoreResult<Option<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn list_intermediate_records(&self) -> AdminStoreResult<Vec<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn list_pending_deletions(&self, _limit: u32) -> AdminStoreResult<Vec<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn list_expired_records(&self, _limit: u32) -> AdminStoreResult<Vec<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn claim_next_queued(
+        &self,
+        _now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn transition_status(
+        &self,
+        _id: &str,
+        _from: BackupStatus,
+        _to: BackupStatus,
+        _update: StatusTransitionUpdate,
+        _now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn transition_to_deleting(
+        &self,
+        _id: &str,
+        _now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        Err(disabled_store())
+    }
+    async fn delete_record(&self, _id: &str) -> AdminStoreResult<()> {
+        Err(disabled_store())
+    }
+    async fn advance_schedule_cursor(
+        &self,
+        _next_run_at: DateTime<Utc>,
+        _expected_cron: &str,
+        _expected_timezone: &str,
+    ) -> AdminStoreResult<bool> {
+        Err(disabled_store())
+    }
+    async fn list_scheduled_completed_desc(
+        &self,
+        _limit: u32,
+    ) -> AdminStoreResult<Vec<BackupRecord>> {
+        Err(disabled_store())
+    }
+}
+
+struct UnavailableDumpPort;
+
+#[async_trait]
+impl DatabaseDumpPort for UnavailableDumpPort {
+    async fn dump(&self, _request: DumpRequest) -> Result<DumpArtifact, BackupError> {
+        Err(disabled_infra())
+    }
+    async fn inspect_staging(
+        &self,
+        _backup_id: &str,
+    ) -> Result<Option<StagedArtifact>, BackupError> {
+        Err(disabled_infra())
+    }
+    async fn cleanup_staging(&self, _backup_id: &str) -> Result<(), BackupError> {
+        Err(disabled_infra())
+    }
+}
+
+struct UnavailableObjectStore;
+
+#[async_trait]
+impl BackupObjectStorePort for UnavailableObjectStore {
+    async fn test_connection(
+        &self,
+        _config: &BackupStorageConfig,
+    ) -> Result<ConnectionTestResult, BackupError> {
+        Err(disabled_infra())
+    }
+    async fn upload_file(
+        &self,
+        _config: &BackupStorageConfig,
+        _request: UploadObjectRequest,
+    ) -> Result<(), BackupError> {
+        Err(disabled_infra())
+    }
+    async fn head_object(
+        &self,
+        _config: &BackupStorageConfig,
+        _object_key: &str,
+    ) -> Result<Option<BackupObjectMetadata>, BackupError> {
+        Err(disabled_infra())
+    }
+    async fn delete_object(
+        &self,
+        _config: &BackupStorageConfig,
+        _object_key: &str,
+    ) -> Result<(), BackupError> {
+        Err(disabled_infra())
+    }
+    async fn presigned_download(
+        &self,
+        _config: &BackupStorageConfig,
+        _object_key: &str,
+        _file_name: &str,
+        _ttl: std::time::Duration,
+    ) -> Result<String, BackupError> {
+        Err(disabled_infra())
+    }
+}
+
+fn disabled_store() -> crate::ports::store::AdminStoreError {
+    crate::ports::store::AdminStoreError::new(
+        crate::ports::store::AdminStoreErrorKind::Unavailable,
+        "backup",
+        "backup store is disabled in this configuration",
+    )
+}
+
+fn disabled_infra() -> BackupError {
+    BackupError::new(
+        crate::model::backup::code::STORE_UNAVAILABLE,
+        "backup infrastructure is disabled in this configuration".to_owned(),
+    )
+}

backend/crates/gateway-admin/src/ports/mod.rs

@@ -1,5 +1,6 @@
 //! 管理用例依赖的外部能力端口。
 
+pub mod backup;
 pub mod provider;
 pub mod store;
 pub mod system;

backend/crates/gateway-admin/src/ports/provider.rs

@@ -13,11 +13,12 @@ use crate::model::observability::{
     CalculatedBillingBreakdown, DashboardWireProfile, ProviderBillingInput,
 };
 use crate::model::provider_credentials::{
-    AuthorizationStarted, CompleteAuthorization, PendingAuthorizationMutation,
-    PrepareCredentialImport, PrepareCredentialRefresh, PrepareCredentialRotation,
-    PreparedAuthorizationCommit, PreparedCredentialImport, PreparedCredentialRotation,
-    ProviderExport, ProviderExportCredentialInput, ProviderModels, ProviderQuota,
-    ProviderQuotaRequest,
+    AuthorizationStarted, CompleteAuthorization, ConsumeProviderResetCredit,
+    PendingAuthorizationMutation, PrepareCredentialImport, PrepareCredentialRefresh,
+    PrepareCredentialRotation, PreparedAuthorizationCommit, PreparedCredentialImport,
+    PreparedCredentialRotation, ProviderExport, ProviderExportCredentialInput, ProviderModels,
+    ProviderProfileAvatar, ProviderProfileStatistics, ProviderQuota, ProviderQuotaRequest,
+    ProviderResetCreditResult, ProviderResetCredits,
 };
 
 /// Provider 管理失败的稳定分类。
@@ -27,27 +28,59 @@ pub enum ProviderAdminErrorKind {
     Unsupported,
     NotFound,
     Conflict,
+    /// Provider 已发起不可逆操作，但无法确认最终执行结果。
+    Ambiguous,
     Unavailable,
+    CredentialRefreshRequired,
+    BadGateway,
     Internal,
 }
 
-/// 不泄漏 OAuth material 与 Provider 响应体的管理错误。
-#[derive(Debug, Clone, PartialEq, Eq, thiserror::Error)]
+/// 不携带 OAuth 请求材料的管理错误。
+///
+/// `message` 是 Provider 局部诊断，可能包含原始上游正文；通用管理用例不得自动把它作为公开文案。
+/// 只有明确拥有原始诊断合同的调用方才能读取，`Debug` 始终只记录是否存在。
+#[derive(Clone, PartialEq, Eq, thiserror::Error)]
 #[error("provider admin operation failed: {kind:?}")]
 pub struct ProviderAdminError {
     kind: ProviderAdminErrorKind,
+    message: Option<String>,
+}
+
+impl std::fmt::Debug for ProviderAdminError {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter
+            .debug_struct("ProviderAdminError")
+            .field("kind", &self.kind)
+            .field("message", &self.message.as_ref().map(|_| "<redacted>"))
+            .finish()
+    }
 }
 
 impl ProviderAdminError {
     #[must_use]
     pub const fn new(kind: ProviderAdminErrorKind) -> Self {
-        Self { kind }
+        Self {
+            kind,
+            message: None,
+        }
+    }
+
+    #[must_use]
+    pub fn with_message(mut self, message: impl Into<String>) -> Self {
+        self.message = Some(message.into());
+        self
     }
 
     #[must_use]
     pub const fn kind(&self) -> ProviderAdminErrorKind {
         self.kind
     }
+
+    #[must_use]
+    pub fn message(&self) -> Option<&str> {
+        self.message.as_deref()
+    }
 }
 
 /// 一个具体 Provider 对管理控制面提供的解析、验证、上游交互与运行时资源回收能力。
@@ -64,6 +97,12 @@ pub trait ProviderAdmin: Send + Sync {
     /// 成功之后，不参与事务成败，也不得恢复或改写已经提交的账号状态。
     async fn account_unavailable(&self, account_id: &ProviderAccountId);
 
+    /// 账号资格事实已经由控制面提交，失效 Provider 持有的可重建派生状态。
+    ///
+    /// 该通知发生在 Store 事务成功之后、下一份 RuntimeSnapshot 编译之前；通知
+    /// 不参与已提交事务成败。没有账号派生状态的 Provider 可使用默认空实现。
+    async fn account_facts_changed(&self, _account_ids: &[ProviderAccountId]) {}
+
     /// 生成一次连接测试所需的 Provider-owned operation；Core 负责实际执行与落账。
     fn connection_test_operation(
         &self,
@@ -110,6 +149,38 @@ pub trait ProviderAdmin: Send + Sync {
         request: ProviderQuotaRequest,
     ) -> Result<ProviderQuota, ProviderAdminError>;
 
+    /// 查询 Provider 官方个人资料统计；不支持该能力的 Provider 使用默认拒绝。
+    async fn profile_statistics(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
+    /// 打开 Provider 官方头像字节流；不支持该能力的 Provider 使用默认拒绝。
+    async fn profile_avatar(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
+    /// 查询 Provider 主动额度重置卡；不支持该能力的 Provider 使用默认拒绝。
+    async fn reset_credits(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderResetCredits, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
+    /// 消费 Provider 主动额度重置卡；不支持该能力的 Provider 使用默认拒绝。
+    async fn consume_reset_credit(
+        &self,
+        _command: ConsumeProviderResetCredit,
+    ) -> Result<ProviderResetCreditResult, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
     async fn models(
         &self,
         account_id: &ProviderAccountId,

backend/crates/gateway-admin/src/ports/store.rs

@@ -7,11 +7,17 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
 
+use super::backup::BackupStorePorts;
 use crate::model::{
     MutationContext, Revision,
+    account_groups::{
+        AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+        DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+    },
     accounts::{
-        AccountListQuery, AccountPage, AccountRecord, AccountUsage, AccountUsageWindowQuery,
-        AccountUsageWindowResult, DeleteAccounts, SetAccountEnabled,
+        AccountListQuery, AccountPage, AccountPageItem, AccountRuntimeSnapshot,
+        AccountUpdateResult, AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult,
+        AccountsUpdateResult, BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
     },
     auth::{AdminAuditEvent, AdminSession},
     client_keys::{
@@ -80,9 +86,17 @@ pub type AdminStoreResult<T> = Result<T, AdminStoreError>;
 /// 账号目录与公共账号写操作。
 #[async_trait]
 pub trait AccountStore: Send + Sync {
-    async fn list_accounts(&self, query: AccountListQuery) -> AdminStoreResult<AccountPage>;
+    async fn list_accounts(
+        &self,
+        query: AccountListQuery,
+        runtime: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage>;
 
-    async fn load_account(&self, account_id: &str) -> AdminStoreResult<Option<AccountRecord>>;
+    async fn load_account(
+        &self,
+        account_id: &str,
+        runtime: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<Option<AccountPageItem>>;
 
     async fn load_account_usage(
         &self,
@@ -137,11 +151,23 @@ pub trait AccountStore: Send + Sync {
         context: &MutationContext,
     ) -> AdminStoreResult<CredentialMutationResult>;
 
-    async fn set_account_enabled(
+    async fn update_account(
         &self,
-        command: SetAccountEnabled,
+        command: UpdateAccount,
         context: &MutationContext,
-    ) -> AdminStoreResult<Revision>;
+    ) -> AdminStoreResult<AccountUpdateResult>;
+
+    async fn recover_account(
+        &self,
+        account_id: &gateway_core::engine::credential::ProviderAccountId,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountUpdateResult>;
+
+    async fn batch_update_accounts(
+        &self,
+        command: BatchUpdateAccounts,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountsUpdateResult>;
 
     async fn delete_accounts(
         &self,
@@ -156,7 +182,18 @@ pub trait AccountStore: Send + Sync {
     ) -> AdminStoreResult<()>;
 }
 
-/// 管理员密码、会话、登录限流和安全审计。
+/// 可丢失账号运行态的管理读端口；跨存储编排由 Admin application service 拥有。
+#[async_trait]
+pub trait AccountRuntimeStore: Send + Sync {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot>;
+
+    async fn account_runtime(
+        &self,
+        account_ids: &[String],
+    ) -> AdminStoreResult<AccountRuntimeSnapshot>;
+}
+
+/// 管理员密码、会话和安全审计。
 #[async_trait]
 pub trait AuthStore: Send + Sync {
     async fn load_password_hash(&self, admin_user_id: &str) -> AdminStoreResult<Option<String>>;
@@ -176,26 +213,10 @@ pub trait AuthStore: Send + Sync {
 
     async fn delete_session(&self, session_id: &str) -> AdminStoreResult<Option<AdminSession>>;
 
-    async fn login_source_is_throttled(
-        &self,
-        source: &str,
-        failure_limit: u32,
-        window_seconds: u64,
-    ) -> AdminStoreResult<bool>;
-
-    async fn record_login_failure(
-        &self,
-        source: &str,
-        failure_limit: u32,
-        window_seconds: u64,
-    ) -> AdminStoreResult<bool>;
-
-    async fn clear_login_failures(&self, source: &str) -> AdminStoreResult<()>;
-
     async fn append_audit_event(&self, event: AdminAuditEvent) -> AdminStoreResult<()>;
 }
 
-/// Client API Key 管理及其 revision CAS 写入。
+/// Client API Key 管理写入。
 #[async_trait]
 pub trait ClientKeyStore: Send + Sync {
     async fn list_client_keys(&self, query: ClientKeyListQuery) -> AdminStoreResult<ClientKeyPage>;
@@ -230,10 +251,53 @@ pub trait ClientKeyStore: Send + Sync {
     ) -> AdminStoreResult<Revision>;
 }
 
+/// Provider-neutral account group management transactions.
+#[async_trait]
+pub trait AccountGroupStore: Send + Sync {
+    async fn list_account_groups(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupPage>;
+
+    async fn load_account_group_members(
+        &self,
+        group_ids: &[gateway_core::routing::AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>>;
+
+    async fn create_account_group(
+        &self,
+        command: NewAccountGroup,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation>;
+
+    async fn update_account_group(
+        &self,
+        command: UpdateAccountGroup,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation>;
+
+    async fn set_account_group_enabled(
+        &self,
+        command: SetAccountGroupEnabled,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation>;
+
+    async fn delete_account_group(
+        &self,
+        command: DeleteAccountGroup,
+        context: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation>;
+}
+
 /// 用量、趋势、诊断与运维错误的只读能力。
 #[async_trait]
 pub trait ObservabilityStore: Send + Sync {
-    async fn dashboard_summary(&self, range: TimeRange) -> AdminStoreResult<DashboardObservation>;
+    /// 返回历史统计区间和指定观测时刻下的实时账号状态。
+    async fn dashboard_summary(
+        &self,
+        range: TimeRange,
+        observed_at: DateTime<Utc>,
+    ) -> AdminStoreResult<DashboardObservation>;
 
     /// 返回 Dashboard 可选的实时槽位事实。
     ///
@@ -281,7 +345,7 @@ pub trait ObservabilityStore: Send + Sync {
     async fn list_ops_errors(&self, query: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage>;
 }
 
-/// Runtime settings 与管理员 API Key 的 revision CAS 写入。
+/// Runtime settings 与管理员 API Key 写入。
 #[async_trait]
 pub trait SettingsStore: Send + Sync {
     async fn load_runtime_settings(&self) -> AdminStoreResult<RuntimeSettings>;
@@ -296,38 +360,61 @@ pub trait SettingsStore: Send + Sync {
 
     async fn replace_admin_api_key(
         &self,
-        expected_config_revision: Revision,
         key: AdminApiKey,
         context: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation>;
 
     async fn delete_admin_api_key(
         &self,
-        expected_config_revision: Revision,
         context: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation>;
 }
 
+/// 账号目录、运行态与分组所需的 Store 能力集合。
+#[derive(Clone)]
+pub struct AdminAccountStorePorts {
+    accounts: Arc<dyn AccountStore>,
+    runtime: Arc<dyn AccountRuntimeStore>,
+    groups: Arc<dyn AccountGroupStore>,
+}
+
+impl AdminAccountStorePorts {
+    #[must_use]
+    pub fn new(
+        accounts: Arc<dyn AccountStore>,
+        runtime: Arc<dyn AccountRuntimeStore>,
+        groups: Arc<dyn AccountGroupStore>,
+    ) -> Self {
+        Self {
+            accounts,
+            runtime,
+            groups,
+        }
+    }
+}
+
 /// 管理用例所需能力的封闭集合。
 ///
 /// 字段保持私有，每个 getter 只交出一种明确能力。该类型不提供通用拆包入口。
 #[derive(Clone)]
 pub struct AdminStorePorts {
-    accounts: Arc<dyn AccountStore>,
+    accounts: AdminAccountStorePorts,
     auth: Arc<dyn AuthStore>,
     client_keys: Arc<dyn ClientKeyStore>,
     observability: Arc<dyn ObservabilityStore>,
     settings: Arc<dyn SettingsStore>,
+    backup: BackupStorePorts,
 }
 
 impl AdminStorePorts {
     #[must_use]
     pub fn new(
-        accounts: Arc<dyn AccountStore>,
+        accounts: AdminAccountStorePorts,
         auth: Arc<dyn AuthStore>,
         client_keys: Arc<dyn ClientKeyStore>,
         observability: Arc<dyn ObservabilityStore>,
         settings: Arc<dyn SettingsStore>,
+        backup: BackupStorePorts,
     ) -> Self {
         Self {
             accounts,
@@ -335,12 +422,23 @@ impl AdminStorePorts {
             client_keys,
             observability,
             settings,
+            backup,
         }
     }
 
     #[must_use]
     pub fn accounts(&self) -> Arc<dyn AccountStore> {
-        self.accounts.clone()
+        self.accounts.accounts.clone()
+    }
+
+    #[must_use]
+    pub fn account_runtime(&self) -> Arc<dyn AccountRuntimeStore> {
+        self.accounts.runtime.clone()
+    }
+
+    #[must_use]
+    pub fn account_groups(&self) -> Arc<dyn AccountGroupStore> {
+        self.accounts.groups.clone()
     }
 
     #[must_use]
@@ -362,4 +460,9 @@ impl AdminStorePorts {
     pub fn settings(&self) -> Arc<dyn SettingsStore> {
         self.settings.clone()
     }
+
+    #[must_use]
+    pub fn backup(&self) -> BackupStorePorts {
+        self.backup.clone()
+    }
 }

backend/crates/gateway-admin/src/use_case/account_groups.rs

@@ -0,0 +1,241 @@
+//! Account group management use cases.
+
+use std::{
+    collections::{BTreeMap, BTreeSet},
+    sync::Arc,
+    time::SystemTime,
+};
+
+use async_trait::async_trait;
+use gateway_core::{
+    engine::credential::{AccountStatus, resolve_account_status},
+    routing::{AccountGroupId, snapshot::SnapshotControl},
+};
+use uuid::Uuid;
+
+use crate::{
+    model::{
+        AdminError, MutationContext,
+        account_groups::{
+            AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupListQuery,
+            AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage, AccountGroupRecord,
+            CreateAccountGroup, DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled,
+            UpdateAccountGroup,
+        },
+    },
+    ports::store::{AccountGroupStore, AccountRuntimeStore},
+};
+
+use super::{map_store_error, publish_committed};
+
+/// API-facing account group management service.
+#[async_trait]
+pub trait AccountGroupService: Send + Sync {
+    async fn list(&self, query: AccountGroupListQuery) -> Result<AccountGroupPage, AdminError>;
+    async fn create(
+        &self,
+        context: &MutationContext,
+        command: CreateAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError>;
+    async fn update(
+        &self,
+        context: &MutationContext,
+        command: UpdateAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError>;
+    async fn set_enabled(
+        &self,
+        context: &MutationContext,
+        command: SetAccountGroupEnabled,
+    ) -> Result<AccountGroupMutation, AdminError>;
+    async fn delete(
+        &self,
+        context: &MutationContext,
+        command: DeleteAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError>;
+}
+
+pub(crate) struct DefaultAccountGroupService {
+    store: Arc<dyn AccountGroupStore>,
+    runtime: Arc<dyn AccountRuntimeStore>,
+    snapshot: Arc<dyn SnapshotControl>,
+}
+
+impl DefaultAccountGroupService {
+    #[must_use]
+    pub(crate) fn new(
+        store: Arc<dyn AccountGroupStore>,
+        runtime: Arc<dyn AccountRuntimeStore>,
+        snapshot: Arc<dyn SnapshotControl>,
+    ) -> Self {
+        Self {
+            store,
+            runtime,
+            snapshot,
+        }
+    }
+
+    async fn enrich_records(&self, records: &mut [AccountGroupRecord]) -> Result<(), AdminError> {
+        if records.is_empty() {
+            return Ok(());
+        }
+        let group_ids = records
+            .iter()
+            .map(|record| record.id.clone())
+            .collect::<Vec<_>>();
+        let members = self
+            .store
+            .load_account_group_members(&group_ids)
+            .await
+            .map_err(|error| map_store_error(error, "account group members"))?;
+        let account_ids = members
+            .iter()
+            .map(|member| member.account_id.clone())
+            .collect::<BTreeSet<_>>()
+            .into_iter()
+            .collect::<Vec<_>>();
+        let runtime = match self.runtime.account_runtime(&account_ids).await {
+            Ok(runtime) => runtime,
+            Err(error) => {
+                tracing::warn!(error = %error, "account group runtime projection is unavailable");
+                Default::default()
+            }
+        };
+        project_group_runtime(records, &members, &runtime);
+        Ok(())
+    }
+
+    async fn publish(
+        &self,
+        result: Result<AccountGroupMutation, crate::ports::store::AdminStoreError>,
+    ) -> Result<AccountGroupMutation, AdminError> {
+        let mut result = result.map_err(|error| map_store_error(error, "account group"))?;
+        if let Some(record) = result.record.as_mut() {
+            self.enrich_records(std::slice::from_mut(record)).await?;
+        }
+        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        Ok(result)
+    }
+}
+
+#[async_trait]
+impl AccountGroupService for DefaultAccountGroupService {
+    async fn list(&self, query: AccountGroupListQuery) -> Result<AccountGroupPage, AdminError> {
+        let mut page = self
+            .store
+            .list_account_groups(query)
+            .await
+            .map_err(|error| map_store_error(error, "account group"))?;
+        self.enrich_records(&mut page.items).await?;
+        Ok(page)
+    }
+
+    async fn create(
+        &self,
+        context: &MutationContext,
+        command: CreateAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError> {
+        let id = AccountGroupId::new(format!("grp_{}", Uuid::now_v7().simple()))
+            .map_err(|_| AdminError::internal("创建账号组 ID 失败"))?;
+        self.publish(
+            self.store
+                .create_account_group(
+                    NewAccountGroup {
+                        id,
+                        name: command.name,
+                        description: command.description,
+                        color: command.color,
+                    },
+                    context,
+                )
+                .await,
+        )
+        .await
+    }
+
+    async fn update(
+        &self,
+        context: &MutationContext,
+        command: UpdateAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError> {
+        self.publish(self.store.update_account_group(command, context).await)
+            .await
+    }
+
+    async fn set_enabled(
+        &self,
+        context: &MutationContext,
+        command: SetAccountGroupEnabled,
+    ) -> Result<AccountGroupMutation, AdminError> {
+        self.publish(self.store.set_account_group_enabled(command, context).await)
+            .await
+    }
+
+    async fn delete(
+        &self,
+        context: &MutationContext,
+        command: DeleteAccountGroup,
+    ) -> Result<AccountGroupMutation, AdminError> {
+        self.publish(self.store.delete_account_group(command, context).await)
+            .await
+    }
+}
+
+fn project_group_runtime(
+    records: &mut [AccountGroupRecord],
+    members: &[AccountGroupMemberFact],
+    runtime: &crate::model::accounts::AccountRuntimeSnapshot,
+) {
+    let now = SystemTime::now();
+    let mut status_by_account = BTreeMap::new();
+    let mut slots_by_account = BTreeMap::new();
+    let mut accounts_by_group = BTreeMap::<&str, Vec<&str>>::new();
+    for member in members {
+        let mut status = member.status.clone();
+        status.rate_limited_until = runtime
+            .rate_limited_until
+            .get(&member.account_id)
+            .copied()
+            .map(Into::into);
+        status_by_account
+            .entry(member.account_id.as_str())
+            .or_insert_with(|| resolve_account_status(&status, now).status);
+        slots_by_account
+            .entry(member.account_id.as_str())
+            .or_insert(member.total_slots);
+        accounts_by_group
+            .entry(member.group_id.as_str())
+            .or_default()
+            .push(member.account_id.as_str());
+    }
+    for record in records {
+        let account_ids = accounts_by_group
+            .get(record.id.as_str())
+            .map_or(&[][..], Vec::as_slice);
+        let available_ids = account_ids
+            .iter()
+            .copied()
+            .filter(|account_id| status_by_account.get(account_id) == Some(&AccountStatus::Normal))
+            .collect::<Vec<_>>();
+        let total = u64::try_from(account_ids.len()).unwrap_or(u64::MAX);
+        let available = u64::try_from(available_ids.len()).unwrap_or(u64::MAX);
+        record.account_summary = AccountGroupAccountSummary {
+            available,
+            limited: total.saturating_sub(available),
+            total,
+        };
+        record.capacity = AccountGroupCapacity {
+            used_slots: if available_ids.is_empty() {
+                Some(0)
+            } else {
+                runtime.in_flight.as_ref().map(|in_flight| {
+                    available_ids.iter().fold(0_u64, |sum, account_id| {
+                        sum.saturating_add(in_flight.get(*account_id).copied().unwrap_or(0))
+                    })
+                })
+            },
+            total_slots: available_ids.iter().fold(0_u64, |sum, account_id| {
+                sum.saturating_add(slots_by_account.get(*account_id).copied().unwrap_or(0))
+            }),
+        };
+    }
+}

backend/crates/gateway-admin/src/use_case/accounts.rs

@@ -10,27 +10,29 @@ use gateway_core::{
         credential::ProviderAccountId,
         probe::{AccountProbe, AccountProbeRequest},
     },
-    error::GatewayErrorKind,
     routing::{ProviderKind, UpstreamModelId, snapshot::SnapshotControl},
 };
 
 use crate::{
     model::{
-        AdminError, MutationContext, Revision,
+        AdminError, MutationContext,
         accounts::{
             AccountConnectionTestEvent, AccountConnectionTestEventStream, AccountListQuery,
-            AccountRecord, AccountStatus, AccountUsageWindowQuery,
+            AccountPageItem, AccountUpdateResult, AccountUsageWindowQuery, AccountsUpdateResult,
+            BatchUpdateAccounts, UpdateAccount,
         },
         observability::TimeRange,
         provider_credentials::{
             AccountDirectoryItem, AccountDirectoryPage, AccountExportBundle, AccountRefreshResult,
-            PrepareCredentialRefresh, ProviderModels, ProviderQuota, ProviderQuotaRequest,
-            ProviderQuotaWindow,
+            ConsumeProviderResetCredit, PrepareCredentialRefresh, ProviderModels,
+            ProviderProfileAvatar, ProviderProfileStatistics, ProviderQuota, ProviderQuotaRequest,
+            ProviderQuotaWindow, ProviderResetCreditResult, ProviderResetCredits,
+            QuotaLocalUsageAttribution,
         },
     },
     ports::{
         provider::ProviderAdminRegistry,
-        store::{AccountStore, SettingsStore},
+        store::{AccountRuntimeStore, AccountStore},
     },
 };
 
@@ -55,16 +57,63 @@ pub trait AccountsService: Send + Sync {
     async fn refresh(
         &self,
         context: &MutationContext,
-        expected_config_revision: Revision,
         account_id: ProviderAccountId,
     ) -> Result<AccountRefreshResult, AdminError>;
 
+    async fn recover(
+        &self,
+        context: &MutationContext,
+        account_id: ProviderAccountId,
+    ) -> Result<AccountRefreshResult, AdminError>;
+
+    async fn update(
+        &self,
+        context: &MutationContext,
+        command: UpdateAccount,
+    ) -> Result<AccountUpdateResult, AdminError>;
+
+    async fn batch_update(
+        &self,
+        context: &MutationContext,
+        command: BatchUpdateAccounts,
+    ) -> Result<AccountsUpdateResult, AdminError>;
+
     async fn quota(
         &self,
         account_id: &ProviderAccountId,
         refresh: bool,
     ) -> Result<AccountDirectoryItem, AdminError>;
 
+    async fn profile_statistics(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持账号统计"))
+    }
+
+    async fn profile_avatar(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持账号头像"))
+    }
+
+    async fn reset_credits(
+        &self,
+        _context: &MutationContext,
+        _account_id: ProviderAccountId,
+    ) -> Result<ProviderResetCredits, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持重置额度"))
+    }
+
+    async fn consume_reset_credit(
+        &self,
+        _context: &MutationContext,
+        _command: ConsumeProviderResetCredit,
+    ) -> Result<ProviderResetCreditResult, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持重置额度"))
+    }
+
     async fn models(
         &self,
         account_id: &ProviderAccountId,
@@ -80,39 +129,59 @@ pub trait AccountsService: Send + Sync {
 
 pub(crate) struct DefaultAccountsService {
     accounts: Arc<dyn AccountStore>,
-    settings: Arc<dyn SettingsStore>,
+    account_runtime: Arc<dyn AccountRuntimeStore>,
     providers: ProviderAdminRegistry,
     snapshot: Arc<dyn SnapshotControl>,
     probe: Arc<dyn AccountProbe>,
+    reset_credit_locks:
+        Arc<futures::lock::Mutex<BTreeMap<ProviderAccountId, Arc<futures::lock::Mutex<()>>>>>,
 }
 
 impl DefaultAccountsService {
     #[must_use]
-    pub(crate) const fn new(
+    pub(crate) fn new(
         accounts: Arc<dyn AccountStore>,
-        settings: Arc<dyn SettingsStore>,
+        account_runtime: Arc<dyn AccountRuntimeStore>,
         providers: ProviderAdminRegistry,
         snapshot: Arc<dyn SnapshotControl>,
         probe: Arc<dyn AccountProbe>,
     ) -> Self {
         Self {
             accounts,
-            settings,
+            account_runtime,
             providers,
             snapshot,
             probe,
+            reset_credit_locks: Arc::new(futures::lock::Mutex::new(BTreeMap::new())),
         }
     }
 
+    async fn reset_credit_lock(
+        &self,
+        account_id: &ProviderAccountId,
+    ) -> Arc<futures::lock::Mutex<()>> {
+        let mut locks = self.reset_credit_locks.lock().await;
+        Arc::clone(
+            locks
+                .entry(account_id.clone())
+                .or_insert_with(|| Arc::new(futures::lock::Mutex::new(()))),
+        )
+    }
+
     async fn load_account(
         &self,
         account_id: &ProviderAccountId,
-    ) -> Result<AccountRecord, AdminError> {
+    ) -> Result<AccountPageItem, AdminError> {
+        let runtime = self
+            .account_runtime
+            .account_runtime(&[account_id.as_str().to_owned()])
+            .await
+            .map_err(|error| map_store_error(error, "account runtime"))?;
         self.accounts
-            .load_account(account_id.as_str())
+            .load_account(account_id.as_str(), runtime)
             .await
             .map_err(|error| map_store_error(error, "provider account"))?
-            .ok_or_else(|| AdminError::not_found("Provider account was not found"))
+            .ok_or_else(|| AdminError::not_found("Provider 账号不存在"))
     }
 
     async fn provider_for_account(
@@ -120,32 +189,32 @@ impl DefaultAccountsService {
         account_id: &ProviderAccountId,
     ) -> Result<
         (
-            AccountRecord,
+            AccountPageItem,
             Arc<dyn crate::ports::provider::ProviderAdmin>,
         ),
         AdminError,
     > {
-        let account = self.load_account(account_id).await?;
+        let item = self.load_account(account_id).await?;
         let provider = self
             .providers
-            .require(&account.provider_kind)
+            .require(&item.account.provider_kind)
             .map_err(|error| map_provider_error(error, "provider account"))?;
-        Ok((account, provider))
+        Ok((item, provider))
     }
 
     async fn attach_quota_local_usage(
         &self,
-        accounts: &[AccountRecord],
+        accounts: &[AccountPageItem],
         quotas: &mut [ProviderQuota],
     ) -> Result<(), AdminError> {
         let windows = accounts
             .iter()
             .zip(quotas.iter())
-            .flat_map(|(account, quota)| {
+            .flat_map(|(item, quota)| {
                 quota
                     .windows
                     .iter()
-                    .filter_map(|window| quota_usage_window(&account.id, window))
+                    .filter_map(|window| quota_usage_window(&item.account.id, window))
             })
             .collect::<Vec<_>>();
         if windows.is_empty() {
@@ -159,10 +228,12 @@ impl DefaultAccountsService {
             .into_iter()
             .map(|result| ((result.account_id, result.key), result.usage))
             .collect::<BTreeMap<_, _>>();
-        for (account, quota) in accounts.iter().zip(quotas) {
+        for (item, quota) in accounts.iter().zip(quotas) {
             for window in &mut quota.windows {
-                if window.local_usage.is_none() {
-                    let key = (account.id.clone(), window.key.clone());
+                if window.local_usage.is_none()
+                    && window.local_usage_attribution == QuotaLocalUsageAttribution::AccountWide
+                {
+                    let key = (item.account.id.clone(), window.key.clone());
                     if let Some(usage) = usage_by_window.get(&key) {
                         window.local_usage = Some(usage.clone());
                     }
@@ -177,33 +248,19 @@ impl DefaultAccountsService {
         account_id: &ProviderAccountId,
         refresh_quota: bool,
     ) -> Result<AccountDirectoryItem, AdminError> {
-        let (account, provider) = self.provider_for_account(account_id).await?;
-        let settings = self
-            .settings
-            .load_runtime_settings()
-            .await
-            .map_err(|error| map_store_error(error, "runtime settings"))?;
+        let (stored, provider) = self.provider_for_account(account_id).await?;
+        let account = &stored.account;
         let now = Utc::now();
-        let retained_range = retained_usage_range(now, settings.usage_retention_days);
         let rolling_range = TimeRange {
             start: now - Duration::hours(24),
             end: now,
         };
         let ids = vec![account.id.clone()];
-        let (usage, rolling_usage) = futures::try_join!(
-            async {
-                self.accounts
-                    .load_account_usage(retained_range, &ids)
-                    .await
-                    .map_err(|error| map_store_error(error, "account usage"))
-            },
-            async {
-                self.accounts
-                    .load_account_usage(rolling_range, &ids)
-                    .await
-                    .map_err(|error| map_store_error(error, "rolling account usage"))
-            },
-        )?;
+        let rolling_usage = self
+            .accounts
+            .load_account_usage(rolling_range, &ids)
+            .await
+            .map_err(|error| map_store_error(error, "rolling account usage"))?;
         let rolling_usage = rolling_usage.into_iter().next();
         let mut quota = provider
             .quota(ProviderQuotaRequest {
@@ -214,14 +271,15 @@ impl DefaultAccountsService {
             .await
             .map_err(|error| map_provider_error(error, "provider quota"))?;
         self.attach_quota_local_usage(
-            std::slice::from_ref(&account),
+            std::slice::from_ref(&stored),
             std::slice::from_mut(&mut quota),
         )
         .await?;
+        let usage = quota.representative_window_usage().cloned();
         Ok(AccountDirectoryItem {
-            status: account_status(&account, now),
-            usage: usage.into_iter().next(),
-            account,
+            projection: stored.projection,
+            usage,
+            account: stored.account,
             quota,
         })
     }
@@ -230,13 +288,17 @@ impl DefaultAccountsService {
 #[async_trait]
 impl AccountsService for DefaultAccountsService {
     async fn list(&self, query: AccountListQuery) -> Result<AccountDirectoryPage, AdminError> {
-        let (page, settings) = futures::try_join!(
-            self.accounts.list_accounts(query),
-            self.settings.load_runtime_settings(),
-        )
-        .map_err(|error| map_store_error(error, "account directory"))?;
+        let runtime = self
+            .account_runtime
+            .active_rate_limits()
+            .await
+            .map_err(|error| map_store_error(error, "account runtime"))?;
+        let page = self
+            .accounts
+            .list_accounts(query, runtime)
+            .await
+            .map_err(|error| map_store_error(error, "account directory"))?;
         let now = Utc::now();
-        let retained_range = retained_usage_range(now, settings.usage_retention_days);
         let rolling_range = TimeRange {
             start: now - Duration::hours(24),
             end: now,
@@ -244,36 +306,52 @@ impl AccountsService for DefaultAccountsService {
         let ids = page
             .items
             .iter()
-            .map(|account| account.id.clone())
+            .map(|item| item.account.id.clone())
             .collect::<Vec<_>>();
-        let (usage, rolling_usage) = futures::try_join!(
-            self.accounts.load_account_usage(retained_range, &ids),
-            self.accounts.load_account_usage(rolling_range, &ids),
-        )
-        .map_err(|error| map_store_error(error, "account usage"))?;
-        let usage = usage
-            .into_iter()
-            .map(|usage| (usage.account_id.clone(), usage))
-            .collect::<BTreeMap<_, _>>();
+        let rolling_usage = self
+            .accounts
+            .load_account_usage(rolling_range, &ids)
+            .await
+            .map_err(|error| map_store_error(error, "rolling account usage"))?;
         let rolling_usage = rolling_usage
             .into_iter()
             .map(|usage| (usage.account_id.clone(), usage))
             .collect::<BTreeMap<_, _>>();
-        let mut quotas = futures::future::join_all(page.items.iter().map(|account| async {
+        let mut quotas = futures::future::join_all(page.items.iter().map(|item| async {
+            let account = &item.account;
             let account_id = ProviderAccountId::new(account.id.clone())
-                .map_err(|_| AdminError::invalid("Invalid provider account ID"))?;
-            let provider = self
-                .providers
-                .require(&account.provider_kind)
-                .map_err(|error| map_provider_error(error, "provider quota"))?;
-            provider
+                .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
+            // 单个账号的 quota 投影失败（Provider 未注册或 quota 读取失败）不拖垮整页：
+            // 该账号降级为空额度投影，其余账号与页面状态照常返回。
+            let provider = match self.providers.require(&account.provider_kind) {
+                Ok(provider) => provider,
+                Err(error) => {
+                    tracing::warn!(
+                        account_id = %account.id,
+                        error = %error,
+                        "account directory provider is not registered; showing empty quota"
+                    );
+                    return Ok(empty_quota());
+                }
+            };
+            match provider
                 .quota(ProviderQuotaRequest {
                     account_id,
                     refresh: false,
                     rolling_usage: rolling_usage.get(&account.id).cloned(),
                 })
                 .await
-                .map_err(|error| map_provider_error(error, "provider quota"))
+            {
+                Ok(quota) => Ok(quota),
+                Err(error) => {
+                    tracing::warn!(
+                        account_id = %account.id,
+                        error = %error,
+                        "account directory quota projection failed; showing empty quota"
+                    );
+                    Ok(empty_quota())
+                }
+            }
         }))
         .await
         .into_iter()
@@ -284,11 +362,14 @@ impl AccountsService for DefaultAccountsService {
             .items
             .into_iter()
             .zip(quotas)
-            .map(|(account, quota)| AccountDirectoryItem {
-                status: account_status(&account, now),
-                usage: usage.get(&account.id).cloned(),
-                account,
-                quota,
+            .map(|(item, quota)| {
+                let usage = quota.representative_window_usage().cloned();
+                AccountDirectoryItem {
+                    usage,
+                    account: item.account,
+                    projection: item.projection,
+                    quota,
+                }
             })
             .collect();
         Ok(AccountDirectoryPage {
@@ -305,16 +386,14 @@ impl AccountsService for DefaultAccountsService {
         account_ids: Vec<ProviderAccountId>,
     ) -> Result<AccountExportBundle, AdminError> {
         if account_ids.is_empty() || account_ids.len() > 200 {
-            return Err(AdminError::invalid(
-                "Account export requires between 1 and 200 accounts",
-            ));
+            return Err(AdminError::invalid("账号导出数量必须在 1 到 200 之间"));
         }
         let exported_ids = account_ids.clone();
         let mut grouped = BTreeMap::<ProviderKind, Vec<ProviderAccountId>>::new();
         for account_id in account_ids {
             let account = self.load_account(&account_id).await?;
             grouped
-                .entry(account.provider_kind)
+                .entry(account.account.provider_kind)
                 .or_default()
                 .push(account_id);
         }
@@ -322,7 +401,7 @@ impl AccountsService for DefaultAccountsService {
             let unique = ids.iter().collect::<std::collections::BTreeSet<_>>();
             unique.len() != ids.len()
         }) {
-            return Err(AdminError::invalid("Account export contains duplicate IDs"));
+            return Err(AdminError::invalid("账号导出列表包含重复 ID"));
         }
         let mut documents = Vec::with_capacity(grouped.len());
         for (provider_kind, ids) in grouped {
@@ -355,10 +434,10 @@ impl AccountsService for DefaultAccountsService {
     async fn refresh(
         &self,
         context: &MutationContext,
-        expected_config_revision: Revision,
         account_id: ProviderAccountId,
     ) -> Result<AccountRefreshResult, AdminError> {
-        let (account, provider) = self.provider_for_account(&account_id).await?;
+        let (stored, provider) = self.provider_for_account(&account_id).await?;
+        let account = stored.account;
         let prepared = provider
             .prepare_refresh(PrepareCredentialRefresh {
                 account: account.clone(),
@@ -368,12 +447,14 @@ impl AccountsService for DefaultAccountsService {
         validate_prepared_rotation(&account, &prepared, "provider credential refresh")?;
         let result = commit_credential_refresh(
             self.accounts.as_ref(),
-            expected_config_revision,
             prepared,
             context,
             "provider credential refresh",
         )
         .await?;
+        provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
         let account = self.load_directory_item(&result.account_id, false).await?;
         Ok(AccountRefreshResult {
@@ -382,6 +463,98 @@ impl AccountsService for DefaultAccountsService {
         })
     }
 
+    async fn recover(
+        &self,
+        context: &MutationContext,
+        account_id: ProviderAccountId,
+    ) -> Result<AccountRefreshResult, AdminError> {
+        let (_, provider) = self.provider_for_account(&account_id).await?;
+        let result = self
+            .accounts
+            .recover_account(&account_id, context)
+            .await
+            .map_err(|error| map_store_error(error, "provider account recovery"))?;
+        provider
+            .account_facts_changed(std::slice::from_ref(&account_id))
+            .await;
+        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        let account = self.load_directory_item(&account_id, false).await?;
+        Ok(AccountRefreshResult {
+            config_revision: result.config_revision,
+            account,
+        })
+    }
+
+    async fn update(
+        &self,
+        context: &MutationContext,
+        command: UpdateAccount,
+    ) -> Result<AccountUpdateResult, AdminError> {
+        let account_id = ProviderAccountId::new(command.account_id.clone())
+            .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
+        let (_, provider) = self.provider_for_account(&account_id).await?;
+        let enabled = command.enabled;
+        let result = self
+            .accounts
+            .update_account(command, context)
+            .await
+            .map_err(|error| map_store_error(error, "provider account"))?;
+        if !enabled {
+            provider.account_unavailable(&account_id).await;
+        }
+        provider
+            .account_facts_changed(std::slice::from_ref(&account_id))
+            .await;
+        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        Ok(result)
+    }
+
+    async fn batch_update(
+        &self,
+        context: &MutationContext,
+        command: BatchUpdateAccounts,
+    ) -> Result<AccountsUpdateResult, AdminError> {
+        let account_ids = command
+            .account_ids
+            .iter()
+            .map(|id| {
+                ProviderAccountId::new(id.clone())
+                    .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))
+            })
+            .collect::<Result<Vec<_>, _>>()?;
+        let mut providers = BTreeMap::<
+            ProviderKind,
+            (
+                Arc<dyn crate::ports::provider::ProviderAdmin>,
+                Vec<ProviderAccountId>,
+            ),
+        >::new();
+        for account_id in &account_ids {
+            let (item, provider) = self.provider_for_account(account_id).await?;
+            providers
+                .entry(item.account.provider_kind)
+                .or_insert_with(|| (provider, Vec::new()))
+                .1
+                .push(account_id.clone());
+        }
+        let enabled = command.enabled;
+        let result = self
+            .accounts
+            .batch_update_accounts(command, context)
+            .await
+            .map_err(|error| map_store_error(error, "provider accounts"))?;
+        for (provider, provider_ids) in providers.values() {
+            if !enabled {
+                for account_id in provider_ids {
+                    provider.account_unavailable(account_id).await;
+                }
+            }
+            provider.account_facts_changed(provider_ids).await;
+        }
+        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        Ok(result)
+    }
+
     async fn quota(
         &self,
         account_id: &ProviderAccountId,
@@ -390,6 +563,79 @@ impl AccountsService for DefaultAccountsService {
         self.load_directory_item(account_id, refresh).await
     }
 
+    async fn profile_statistics(
+        &self,
+        account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, AdminError> {
+        let (_, provider) = self.provider_for_account(account_id).await?;
+        provider
+            .profile_statistics(account_id)
+            .await
+            .map_err(|error| map_provider_error(error, "provider profile statistics"))
+    }
+
+    async fn profile_avatar(
+        &self,
+        account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, AdminError> {
+        let (_, provider) = self.provider_for_account(account_id).await?;
+        provider
+            .profile_avatar(account_id)
+            .await
+            .map_err(|error| map_provider_error(error, "provider profile avatar"))
+    }
+
+    async fn reset_credits(
+        &self,
+        context: &MutationContext,
+        account_id: ProviderAccountId,
+    ) -> Result<ProviderResetCredits, AdminError> {
+        let (_, provider) = self.provider_for_account(&account_id).await?;
+        match provider.reset_credits(&account_id).await {
+            Ok(credits) => Ok(credits),
+            Err(error)
+                if error.kind()
+                    == crate::ports::provider::ProviderAdminErrorKind::CredentialRefreshRequired =>
+            {
+                self.refresh(context, account_id.clone()).await?;
+                let (_, provider) = self.provider_for_account(&account_id).await?;
+                provider
+                    .reset_credits(&account_id)
+                    .await
+                    .map_err(map_reset_credits_error_after_refresh)
+            }
+            Err(error) => Err(map_provider_error(error, "provider reset credits")),
+        }
+    }
+
+    async fn consume_reset_credit(
+        &self,
+        context: &MutationContext,
+        command: ConsumeProviderResetCredit,
+    ) -> Result<ProviderResetCreditResult, AdminError> {
+        let account_id = command.account_id.clone();
+        // 覆盖 credential refresh + 同键重试的完整账号级临界区，避免 401 两次调用
+        // 之间插入另一笔不可逆消费。
+        let lock = self.reset_credit_lock(&account_id).await;
+        let _guard = lock.lock().await;
+        let (_, provider) = self.provider_for_account(&account_id).await?;
+        match provider.consume_reset_credit(command.clone()).await {
+            Ok(result) => Ok(result),
+            Err(error)
+                if error.kind()
+                    == crate::ports::provider::ProviderAdminErrorKind::CredentialRefreshRequired =>
+            {
+                self.refresh(context, account_id.clone()).await?;
+                let (_, provider) = self.provider_for_account(&account_id).await?;
+                provider
+                    .consume_reset_credit(command)
+                    .await
+                    .map_err(map_reset_credits_error_after_refresh)
+            }
+            Err(error) => Err(map_provider_error(error, "provider reset-credit consume")),
+        }
+    }
+
     async fn models(
         &self,
         account_id: &ProviderAccountId,
@@ -407,8 +653,8 @@ impl AccountsService for DefaultAccountsService {
         account_id: ProviderAccountId,
         upstream_model: UpstreamModelId,
     ) -> Result<AccountConnectionTestEventStream, AdminError> {
-        let (account, provider) = self.provider_for_account(&account_id).await?;
-        let initial_status = account_status(&account, Utc::now());
+        let (stored, provider) = self.provider_for_account(&account_id).await?;
+        let account = stored.account;
         let model = upstream_model.as_str().to_owned();
         let operation = provider
             .connection_test_operation(&upstream_model, CONNECTION_TEST_INPUT)
@@ -425,8 +671,6 @@ impl AccountsService for DefaultAccountsService {
             },
         ];
         let probe = Arc::clone(&self.probe);
-        let accounts = Arc::clone(&self.accounts);
-        let stored_account_id = account.id.clone();
         let terminal = futures::stream::once(async move {
             let result = probe
                 .probe(AccountProbeRequest {
@@ -436,32 +680,38 @@ impl AccountsService for DefaultAccountsService {
                     operation,
                 })
                 .await;
-            let status = accounts
-                .load_account(&stored_account_id)
-                .await
-                .ok()
-                .flatten()
-                .map_or(initial_status, |account| {
-                    account_status(&account, Utc::now())
-                });
             match result {
                 Ok(result) => result
                     .text
                     .into_iter()
                     .map(|text| AccountConnectionTestEvent::Content { text })
-                    .chain(std::iter::once(AccountConnectionTestEvent::Completed {
-                        account_status: status,
-                    }))
+                    .chain(std::iter::once(AccountConnectionTestEvent::Completed))
                     .collect(),
-                Err(error) => vec![AccountConnectionTestEvent::Failed {
-                    message: match error.kind() {
-                        GatewayErrorKind::InvalidRequest
-                        | GatewayErrorKind::Unsupported
-                        | GatewayErrorKind::ModelNotFound => error.safe_message().to_owned(),
-                        _ => "Provider connection test failed".to_owned(),
-                    },
-                    account_status: status,
-                }],
+                Err(error) => {
+                    let upstream_status = error
+                        .upstream_response()
+                        .map(gateway_core::engine::probe::AccountProbeUpstreamResponse::status);
+                    let upstream_content_type = error
+                        .upstream_response()
+                        .and_then(|response| response.content_type())
+                        .and_then(|value| std::str::from_utf8(value).ok())
+                        .map(ToOwned::to_owned);
+                    let upstream_body = error
+                        .upstream_response()
+                        .map(|response| String::from_utf8_lossy(response.body()).into_owned());
+                    let message = error.client_message().to_owned();
+                    vec![AccountConnectionTestEvent::Failed {
+                        source: error.source(),
+                        gateway_error_code: error.kind(),
+                        send_state: error.send_state(),
+                        message,
+                        provider_error_code: error.client_error_code().map(ToOwned::to_owned),
+                        provider_error_type: error.client_error_type().map(ToOwned::to_owned),
+                        upstream_status,
+                        upstream_content_type,
+                        upstream_body,
+                    }]
+                }
             }
         })
         .flat_map(futures::stream::iter);
@@ -469,33 +719,23 @@ impl AccountsService for DefaultAccountsService {
     }
 }
 
-fn account_status(account: &AccountRecord, now: chrono::DateTime<Utc>) -> AccountStatus {
-    if !account.enabled {
-        AccountStatus::Disabled
-    } else {
-        match account.availability {
-            crate::model::accounts::AccountAvailability::Banned => AccountStatus::Banned,
-            crate::model::accounts::AccountAvailability::QuotaExhausted => {
-                AccountStatus::QuotaExhausted
-            }
-            crate::model::accounts::AccountAvailability::Expired => AccountStatus::Expired,
-            _ if account
-                .access_token_expires_at
-                .is_some_and(|expires_at| expires_at <= now) =>
-            {
-                AccountStatus::Expired
-            }
-            crate::model::accounts::AccountAvailability::Ready => AccountStatus::Active,
-            _ => AccountStatus::Attention,
-        }
+fn map_reset_credits_error_after_refresh(
+    error: crate::ports::provider::ProviderAdminError,
+) -> AdminError {
+    if error.kind() == crate::ports::provider::ProviderAdminErrorKind::CredentialRefreshRequired {
+        return AdminError::bad_gateway("上游服务拒绝了刷新后的凭据");
     }
+    map_provider_error(error, "provider reset credits")
 }
 
-fn retained_usage_range(now: chrono::DateTime<Utc>, retention_days: u32) -> TimeRange {
-    // 账号留存投影是内部查询，不受外部观测接口 366 天上限约束。
-    TimeRange {
-        start: now - Duration::days(i64::from(retention_days)),
-        end: now,
+/// 账号目录中单个账号 quota 读取失败时使用的空额度投影。
+fn empty_quota() -> ProviderQuota {
+    ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: Vec::new(),
+        limit_reached: false,
+        provider_data: None,
     }
 }
 
@@ -503,7 +743,9 @@ fn quota_usage_window(
     account_id: &str,
     window: &ProviderQuotaWindow,
 ) -> Option<AccountUsageWindowQuery> {
-    if window.local_usage.is_some() {
+    if window.local_usage.is_some()
+        || window.local_usage_attribution != QuotaLocalUsageAttribution::AccountWide
+    {
         return None;
     }
     let reset_at = window.reset_at?;

backend/crates/gateway-admin/src/use_case/auth.rs

@@ -2,7 +2,7 @@
 
 use std::sync::Arc;
 
-use argon2::{Argon2, PasswordHash, PasswordHasher, PasswordVerifier, password_hash::SaltString};
+use argon2::{Argon2, PasswordHash, PasswordHasher, PasswordVerifier};
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use chrono::{Duration, Utc};
@@ -22,9 +22,6 @@ use crate::{
 
 use super::map_store_error;
 
-const LOGIN_FAILURE_LIMIT: u32 = 5;
-const LOGIN_FAILURE_WINDOW_SECONDS: u64 = 15 * 60;
-
 /// API 鉴权与管理员登录消费的统一服务。
 #[async_trait]
 pub trait AuthService: Send + Sync {
@@ -39,6 +36,10 @@ pub trait AuthService: Send + Sync {
     async fn logout(&self, session_id: &str) -> Result<(), AdminError>;
 }
 
+/// 会话有效期上限(366 天);超出的配置按上限截断,保证 TTL 构造与
+/// `Utc::now() + session_ttl` 永不越界。
+const MAX_SESSION_TTL_MINUTES: i64 = 366 * 24 * 60;
+
 /// 单管理员认证策略的最终实现。
 pub(crate) struct DefaultAuthService {
     default_admin_user_id: String,
@@ -54,8 +55,8 @@ impl DefaultAuthService {
         store: Arc<dyn AuthStore>,
     ) -> Self {
         let minutes = i64::try_from(session_ttl_minutes)
-            .unwrap_or(i64::MAX)
-            .max(1);
+            .unwrap_or(MAX_SESSION_TTL_MINUTES)
+            .clamp(1, MAX_SESSION_TTL_MINUTES);
         Self {
             default_admin_user_id: default_admin_user_id.into(),
             session_ttl: Duration::minutes(minutes),
@@ -63,19 +64,6 @@ impl DefaultAuthService {
         }
     }
 
-    async fn record_failed_login(&self, source: &str) -> Result<LoginError, LoginError> {
-        let throttled = self
-            .store
-            .record_login_failure(source, LOGIN_FAILURE_LIMIT, LOGIN_FAILURE_WINDOW_SECONDS)
-            .await
-            .map_err(|_| LoginError::Unavailable)?;
-        Ok(if throttled {
-            LoginError::Throttled
-        } else {
-            LoginError::InvalidCredentials
-        })
-    }
-
     fn auth_audit(&self, action: &str, occurred_at: chrono::DateTime<Utc>) -> AdminAuditEvent {
         AdminAuditEvent {
             id: format!("audit_{}", Uuid::now_v7().simple()),
@@ -137,22 +125,13 @@ impl AuthService for DefaultAuthService {
     }
 
     async fn login(&self, command: LoginCommand) -> Result<LoginResult, LoginError> {
-        let source = normalized_login_source(&command.source);
-        if self
-            .store
-            .login_source_is_throttled(source, LOGIN_FAILURE_LIMIT, LOGIN_FAILURE_WINDOW_SECONDS)
-            .await
-            .map_err(|_| LoginError::Unavailable)?
-        {
-            return Err(LoginError::Throttled);
-        }
         if command
             .username
             .as_deref()
             .unwrap_or(&self.default_admin_user_id)
             != self.default_admin_user_id
         {
-            return Err(self.record_failed_login(source).await?);
+            return Err(LoginError::InvalidCredentials);
         }
         let hash = self
             .store
@@ -161,13 +140,9 @@ impl AuthService for DefaultAuthService {
             .map_err(|_| LoginError::Unavailable)?
             .ok_or(LoginError::InvalidCredentials)?;
         if !verify_admin_password(&command.password, &hash).map_err(|_| LoginError::Unavailable)? {
-            return Err(self.record_failed_login(source).await?);
+            return Err(LoginError::InvalidCredentials);
         }
 
-        self.store
-            .clear_login_failures(source)
-            .await
-            .map_err(|_| LoginError::Unavailable)?;
         let session_id = random_session_token();
         let expires_at = Utc::now() + self.session_ttl;
         self.store
@@ -220,16 +195,15 @@ impl AuthService for DefaultAuthService {
 }
 
 fn hash_admin_password(password: &str) -> Result<String, AdminError> {
-    let salt = SaltString::generate(&mut OsRng);
     Argon2::default()
-        .hash_password(password.as_bytes(), &salt)
+        .hash_password(password.as_bytes())
         .map(|hash| hash.to_string())
-        .map_err(|_| AdminError::internal("Failed to hash administrator password"))
+        .map_err(|_| AdminError::internal("管理员密码哈希失败"))
 }
 
 fn verify_admin_password(password: &str, encoded: &str) -> Result<bool, AdminError> {
     let hash = PasswordHash::new(encoded)
-        .map_err(|_| AdminError::internal("Stored administrator password hash is invalid"))?;
+        .map_err(|_| AdminError::internal("已保存的管理员密码哈希不合法"))?;
     Ok(Argon2::default()
         .verify_password(password.as_bytes(), &hash)
         .is_ok())
@@ -246,8 +220,3 @@ fn valid_admin_api_key_shape(value: &str) -> bool {
         && value.starts_with("admin-")
         && value[6..].bytes().all(|byte| byte.is_ascii_hexdigit())
 }
-
-fn normalized_login_source(source: &str) -> &str {
-    let source = source.trim();
-    if source.is_empty() { "unknown" } else { source }
-}

backend/crates/gateway-admin/src/use_case/backup.rs

@@ -0,0 +1,435 @@
+//! 备份配置、手动创建、下载与删除用例。
+
+use std::sync::Arc;
+use std::time::Duration;
+
+use async_trait::async_trait;
+use chrono::{DateTime, Utc};
+use gateway_core::routing::snapshot::SnapshotControl;
+use secrecy::ExposeSecret as _;
+use uuid::Uuid;
+
+use crate::model::{
+    AdminError, AdminErrorKind, MutationContext,
+    auth::{AdminAuditEvent, AuditActorKind},
+    backup::{
+        BackupError, BackupRecord, BackupRecordListQuery, BackupRecordPage, BackupSettings,
+        BackupStatus, BackupStorageConfig, BackupTriggerKind, ConnectionTestResult,
+        DownloadUrlResult, UpdateBackupScheduleCommand, UpdateBackupStorageCommand,
+        build_backup_seed, code,
+    },
+};
+use crate::ports::{
+    backup::{BackupObjectStorePort, BackupRepository},
+    store::AuthStore,
+};
+
+use super::map_store_error;
+
+/// 默认下载地址有效期。
+const DOWNLOAD_TTL: Duration = Duration::from_secs(5 * 60);
+
+/// API 消费的备份管理服务。
+#[async_trait]
+pub trait BackupService: Send + Sync {
+    async fn load_settings(&self) -> Result<BackupSettings, AdminError>;
+
+    async fn update_storage(
+        &self,
+        context: &MutationContext,
+        command: UpdateBackupStorageCommand,
+    ) -> Result<BackupSettings, AdminError>;
+
+    async fn update_schedule(
+        &self,
+        context: &MutationContext,
+        command: UpdateBackupScheduleCommand,
+    ) -> Result<BackupSettings, AdminError>;
+
+    async fn test_connection(
+        &self,
+        context: &MutationContext,
+    ) -> Result<ConnectionTestResult, AdminError>;
+
+    async fn create_backup(
+        &self,
+        context: &MutationContext,
+        expires_at: Option<DateTime<Utc>>,
+    ) -> Result<BackupRecord, AdminError>;
+
+    async fn list_records(
+        &self,
+        query: BackupRecordListQuery,
+    ) -> Result<BackupRecordPage, AdminError>;
+
+    async fn download_url(
+        &self,
+        context: &MutationContext,
+        backup_id: &str,
+    ) -> Result<DownloadUrlResult, AdminError>;
+
+    async fn delete_backup(
+        &self,
+        context: &MutationContext,
+        backup_id: &str,
+    ) -> Result<BackupRecord, AdminError>;
+}
+
+pub(crate) struct DefaultBackupService {
+    repository: Arc<dyn BackupRepository>,
+    object_store: Arc<dyn BackupObjectStorePort>,
+    auth: Arc<dyn AuthStore>,
+    snapshot: Arc<dyn SnapshotControl>,
+}
+
+impl DefaultBackupService {
+    #[must_use]
+    pub(crate) fn new(
+        repository: Arc<dyn BackupRepository>,
+        object_store: Arc<dyn BackupObjectStorePort>,
+        auth: Arc<dyn AuthStore>,
+        snapshot: Arc<dyn SnapshotControl>,
+    ) -> Self {
+        Self {
+            repository,
+            object_store,
+            auth,
+            snapshot,
+        }
+    }
+}
+
+#[async_trait]
+impl BackupService for DefaultBackupService {
+    async fn load_settings(&self) -> Result<BackupSettings, AdminError> {
+        self.repository
+            .load_settings()
+            .await
+            .map_err(|error| map_store_error(error, "backup settings"))
+    }
+
+    async fn update_storage(
+        &self,
+        context: &MutationContext,
+        command: UpdateBackupStorageCommand,
+    ) -> Result<BackupSettings, AdminError> {
+        validate_storage(&command)?;
+        let (settings, revision) = self
+            .repository
+            .update_storage_settings(command, context)
+            .await
+            .map_err(|error| map_store_error(error, "backup storage"))?;
+        super::publish_committed(self.snapshot.as_ref(), revision).await?;
+        Ok(settings)
+    }
+
+    async fn update_schedule(
+        &self,
+        context: &MutationContext,
+        command: UpdateBackupScheduleCommand,
+    ) -> Result<BackupSettings, AdminError> {
+        validate_schedule(&command)?;
+        let next_run_at = if command.schedule_enabled {
+            Some(
+                crate::backup::policy::BackupSchedule::parse(
+                    &command.cron_expression,
+                    &command.schedule_timezone,
+                )
+                .map_err(map_backup_error)?
+                .next_after(Utc::now())
+                .ok_or_else(|| AdminError::bad_request("无法从计划推导下次执行时间"))?,
+            )
+        } else {
+            None
+        };
+        self.repository
+            .update_schedule_settings(command, next_run_at, context)
+            .await
+            .map_err(|error| map_store_error(error, "backup schedule"))
+    }
+
+    async fn test_connection(
+        &self,
+        context: &MutationContext,
+    ) -> Result<ConnectionTestResult, AdminError> {
+        let settings = self
+            .repository
+            .load_settings()
+            .await
+            .map_err(|error| map_store_error(error, "backup settings"))?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Ok(ConnectionTestResult {
+                ok: false,
+                stage: "putObject",
+                code: Some(code::INVALID_CONFIG),
+                message: "备份存储配置不完整，无法执行连接测试".to_owned(),
+            });
+        };
+        let result = self
+            .object_store
+            .test_connection(&config)
+            .await
+            .map_err(map_backup_error)?;
+        if result.ok {
+            let _ = self
+                .repository
+                .record_verification(config.storage_revision, Utc::now())
+                .await
+                .map_err(|error| map_store_error(error, "backup settings"))?;
+        }
+        self.append_audit(
+            context,
+            "backup.s3_connection_tested",
+            "backup_settings",
+            vec![],
+        )
+        .await?;
+        Ok(result)
+    }
+
+    async fn create_backup(
+        &self,
+        context: &MutationContext,
+        expires_at: Option<DateTime<Utc>>,
+    ) -> Result<BackupRecord, AdminError> {
+        let settings = self
+            .repository
+            .load_settings()
+            .await
+            .map_err(|error| map_store_error(error, "backup settings"))?;
+        if !settings.storage_configured() {
+            return Err(AdminError::bad_request(
+                "备份存储配置不完整，请先保存存储配置",
+            ));
+        }
+        if !settings.storage_verified() {
+            return Err(AdminError::bad_request(
+                "备份存储尚未通过连接测试，请先测试存储配置",
+            ));
+        }
+        let prefix = settings.prefix.as_deref().unwrap_or_default();
+        let seed = build_backup_seed(
+            BackupTriggerKind::Manual,
+            None,
+            prefix,
+            Utc::now(),
+            expires_at,
+        )
+        .map_err(map_backup_error)?;
+        let record = self
+            .repository
+            .insert_backup_record(seed)
+            .await
+            .map_err(|error| map_store_error(error, "backup record"))?;
+        self.append_audit(context, "backup.created", "backup", vec![record.id.clone()])
+            .await?;
+        Ok(record)
+    }
+
+    async fn list_records(
+        &self,
+        query: BackupRecordListQuery,
+    ) -> Result<BackupRecordPage, AdminError> {
+        self.repository
+            .list_backup_records(query)
+            .await
+            .map_err(|error| map_store_error(error, "backup records"))
+    }
+
+    async fn download_url(
+        &self,
+        context: &MutationContext,
+        backup_id: &str,
+    ) -> Result<DownloadUrlResult, AdminError> {
+        let record = self.require_record(backup_id).await?;
+        if record.status != BackupStatus::Completed {
+            return Err(AdminError::conflict(
+                "只有 completed 的备份才能创建下载地址",
+            ));
+        }
+        let settings = self
+            .repository
+            .load_settings()
+            .await
+            .map_err(|error| map_store_error(error, "backup settings"))?;
+        let Some(config) = BackupStorageConfig::from_settings(&settings) else {
+            return Err(AdminError::bad_request("备份存储配置不完整"));
+        };
+        let file_name = crate::model::backup::build_download_file_name(backup_id);
+        let url = self
+            .object_store
+            .presigned_download(&config, &record.object_key, &file_name, DOWNLOAD_TTL)
+            .await
+            .map_err(map_backup_error)?;
+        self.append_audit(
+            context,
+            "backup.download_url_created",
+            "backup",
+            vec![backup_id.to_owned()],
+        )
+        .await?;
+        Ok(DownloadUrlResult {
+            url,
+            file_name,
+            expires_in: DOWNLOAD_TTL,
+        })
+    }
+
+    async fn delete_backup(
+        &self,
+        context: &MutationContext,
+        backup_id: &str,
+    ) -> Result<BackupRecord, AdminError> {
+        let record = self.require_record(backup_id).await?;
+        if !record.status.can_be_deleted() {
+            return Err(AdminError::conflict(
+                "只有 completed 或 failed 的备份才能删除",
+            ));
+        }
+        let now = Utc::now();
+        let deleting = self
+            .repository
+            .transition_to_deleting(backup_id, now)
+            .await
+            .map_err(|error| map_store_error(error, "backup record"))?
+            .ok_or_else(|| AdminError::conflict("备份记录已进入删除流程"))?;
+        self.append_audit(
+            context,
+            "backup.delete_requested",
+            "backup",
+            vec![backup_id.to_owned()],
+        )
+        .await?;
+        Ok(deleting)
+    }
+}
+
+impl DefaultBackupService {
+    async fn require_record(&self, backup_id: &str) -> Result<BackupRecord, AdminError> {
+        self.repository
+            .load_backup_record(backup_id)
+            .await
+            .map_err(|error| map_store_error(error, "backup record"))?
+            .ok_or_else(|| AdminError::not_found("备份记录不存在"))
+    }
+
+    async fn append_audit(
+        &self,
+        context: &MutationContext,
+        action: &str,
+        entity_ref: &str,
+        changed_fields: Vec<String>,
+    ) -> Result<(), AdminError> {
+        let actor_kind = match context.actor {
+            crate::model::MutationActor::AdminSession { .. } => AuditActorKind::AdminSession,
+            crate::model::MutationActor::AdminApiKey => AuditActorKind::AdminApiKey,
+            crate::model::MutationActor::System => AuditActorKind::System,
+        };
+        let actor_ref = match &context.actor {
+            crate::model::MutationActor::AdminSession { admin_user_id } => admin_user_id.clone(),
+            crate::model::MutationActor::AdminApiKey => "admin_api_key".to_owned(),
+            crate::model::MutationActor::System => "system".to_owned(),
+        };
+        let actor_admin_user_id = match &context.actor {
+            crate::model::MutationActor::AdminSession { admin_user_id } => {
+                Some(admin_user_id.clone())
+            }
+            _ => None,
+        };
+        let event = AdminAuditEvent {
+            id: format!("audit_{}", Uuid::now_v7().simple()),
+            actor_kind,
+            actor_admin_user_id,
+            actor_ref,
+            request_id: Some(context.request_id.clone()),
+            action: action.to_owned(),
+            entity_kind: "backup".to_owned(),
+            entity_ref: entity_ref.to_owned(),
+            config_revision: None,
+            changed_fields,
+            occurred_at: Utc::now(),
+        };
+        self.auth
+            .append_audit_event(event)
+            .await
+            .map_err(|error| map_store_error(error, "backup audit"))
+    }
+}
+
+/// 校验存储配置；空串视为非法，Secret 缺省表示保留旧值。
+fn validate_storage(command: &UpdateBackupStorageCommand) -> Result<(), AdminError> {
+    validate_endpoint(&command.endpoint)?;
+    validate_nonempty("region", &command.region)?;
+    validate_nonempty("bucket", &command.bucket)?;
+    validate_nonempty("accessKeyId", &command.access_key_id)?;
+    if let Some(secret) = command.secret_access_key.as_ref() {
+        let value = secret.expose_secret();
+        if value.is_empty() {
+            return Err(AdminError::bad_request(
+                "secretAccessKey 不能为空字符串；缺省表示保留旧值",
+            ));
+        }
+        validate_length("secretAccessKey", value, 512)?;
+    }
+    crate::model::backup::normalize_prefix(&command.prefix).map_err(map_backup_error)?;
+    Ok(())
+}
+
+fn validate_endpoint(value: &str) -> Result<(), AdminError> {
+    if value.is_empty() {
+        return Err(AdminError::bad_request("endpoint 不能为空"));
+    }
+    if !value.starts_with("https://") {
+        return Err(AdminError::bad_request(
+            "endpoint 必须使用 HTTPS；仅测试或显式开发配置允许 HTTP",
+        ));
+    }
+    if value.contains('@') || value.bytes().any(|byte| byte.is_ascii_control()) {
+        return Err(AdminError::bad_request("endpoint 格式非法"));
+    }
+    validate_length("endpoint", value, 2048)
+}
+
+fn validate_nonempty(field: &str, value: &str) -> Result<(), AdminError> {
+    if value.is_empty() {
+        return Err(AdminError::bad_request(format!("{field} 不能为空")));
+    }
+    validate_length(field, value, 255)
+}
+
+fn validate_length(field: &str, value: &str, max: usize) -> Result<(), AdminError> {
+    if value.len() > max || value.bytes().any(|byte| byte.is_ascii_control()) {
+        return Err(AdminError::bad_request(format!(
+            "{field} 超出长度或包含非法字符"
+        )));
+    }
+    Ok(())
+}
+
+/// 校验调度配置并解析 Cron 与时区。
+fn validate_schedule(command: &UpdateBackupScheduleCommand) -> Result<(), AdminError> {
+    if command.cron_expression.trim().is_empty() {
+        return Err(AdminError::bad_request("cronExpression 不能为空"));
+    }
+    crate::backup::policy::BackupSchedule::parse(
+        &command.cron_expression,
+        &command.schedule_timezone,
+    )
+    .map_err(map_backup_error)?;
+    Ok(())
+}
+
+/// 备份基础设施错误到既有 `AdminErrorKind` 的唯一边界映射。
+fn map_backup_error(error: BackupError) -> AdminError {
+    match error.code() {
+        code::INVALID_CONFIG | code::INVALID_CRON | code::INVALID_TIMEZONE => {
+            AdminError::bad_request(error.message().to_owned())
+        }
+        code::RECORD_NOT_FOUND => AdminError::not_found(error.message().to_owned()),
+        code::ACTIVE_TASK_CONFLICT | code::STATE_CONFLICT | code::STORAGE_IDENTITY_LOCKED => {
+            AdminError::conflict(error.message().to_owned())
+        }
+        code::STORE_UNAVAILABLE => AdminError::new(AdminErrorKind::Unavailable, "备份服务暂不可用"),
+        _ => AdminError::bad_gateway("备份服务请求失败"),
+    }
+}

backend/crates/gateway-admin/src/use_case/client_keys.rs

@@ -77,7 +77,7 @@ impl ClientKeyService for DefaultClientKeyService {
             .reveal_client_key(id)
             .await
             .map_err(|error| map_store_error(error, "client API key"))?
-            .ok_or_else(|| AdminError::not_found("Client API key was not found"))
+            .ok_or_else(|| AdminError::not_found("Client API Key 不存在"))
     }
 
     async fn create(
@@ -86,7 +86,7 @@ impl ClientKeyService for DefaultClientKeyService {
         command: CreateClientKey,
     ) -> Result<CreatedClientKey, AdminError> {
         let id = ClientApiKeyId::new(format!("key_{}", Uuid::now_v7().simple()))
-            .map_err(|_| AdminError::internal("Failed to create Client API key ID"))?;
+            .map_err(|_| AdminError::internal("创建 Client API Key ID 失败"))?;
         let mut bytes = [0_u8; 32];
         OsRng.fill_bytes(&mut bytes);
         let plaintext = format!("sk_{}", URL_SAFE_NO_PAD.encode(bytes));
@@ -94,11 +94,10 @@ impl ClientKeyService for DefaultClientKeyService {
             .store
             .create_client_key(
                 NewClientKey {
-                    expected_config_revision: command.expected_config_revision,
                     id,
                     name: command.name,
                     label: command.label,
-                    provider_kind: command.provider_kind,
+                    group_ids: command.group_ids,
                     limits: command.limits,
                     plaintext: plaintext.clone(),
                 },
@@ -177,7 +176,7 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
     };
     if cursor.sort != query.sort {
         return Err(AdminError::invalid(
-            "Client API key cursor sort does not match the query",
+            "Client API Key 游标排序与查询条件不一致",
         ));
     }
     let matches = matches!(
@@ -199,6 +198,6 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
     if matches {
         Ok(())
     } else {
-        Err(AdminError::invalid("Invalid Client API key cursor"))
+        Err(AdminError::invalid("Client API Key 游标不合法"))
     }
 }

backend/crates/gateway-admin/src/use_case/mod.rs

@@ -1,7 +1,9 @@
 //! 管理控制面的用例实现。
 
+pub mod account_groups;
 pub mod accounts;
 pub mod auth;
+pub mod backup;
 pub mod client_keys;
 pub mod observability;
 pub mod openai;
@@ -12,11 +14,11 @@ pub mod xai;
 use crate::{
     model::{
         AdminError, AdminErrorKind, MutationContext,
-        accounts::{DeleteAccounts, SetAccountEnabled},
+        accounts::DeleteAccounts,
         provider_credentials::{
             AuthorizationMutationTarget, CredentialDeletion, CredentialDeletionResult,
-            CredentialDetails, CredentialMutation, CredentialMutationResult,
-            CredentialRotationCommit, PendingAuthorizationMutation, PreparedAuthorizationCommit,
+            CredentialDetails, CredentialMutationResult, CredentialRotationCommit,
+            PendingAuthorizationMutation, PreparedAuthorizationCommit,
             PreparedAuthorizationCredential, PreparedCredentialImport, PreparedCredentialRotation,
             StartAuthorization,
         },
@@ -40,7 +42,15 @@ fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError
         }
         AdminStoreErrorKind::Unavailable => AdminErrorKind::Unavailable,
     };
-    AdminError::new(kind, format!("{resource} operation failed"))
+    tracing::warn!(resource, error_kind = ?error.kind(), "admin store operation failed");
+    let message = match kind {
+        AdminErrorKind::Invalid => "请求参数不合法",
+        AdminErrorKind::NotFound => "请求的资源不存在",
+        AdminErrorKind::Conflict => "当前资源状态冲突，请刷新后重试",
+        AdminErrorKind::Unavailable => "依赖服务暂不可用",
+        _ => "服务内部错误",
+    };
+    AdminError::new(kind, message)
 }
 
 fn map_provider_error(
@@ -54,10 +64,24 @@ fn map_provider_error(
         ProviderAdminErrorKind::Unsupported => AdminErrorKind::Invalid,
         ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
         ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
+        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
         ProviderAdminErrorKind::Unavailable => AdminErrorKind::Unavailable,
+        ProviderAdminErrorKind::CredentialRefreshRequired => AdminErrorKind::Unavailable,
+        ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
         ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
     };
-    AdminError::new(kind, format!("{resource} operation failed"))
+    tracing::warn!(resource, error_kind = ?error.kind(), "admin provider operation failed");
+    let message = match kind {
+        AdminErrorKind::Invalid => "Provider 请求不合法",
+        AdminErrorKind::NotFound => "Provider 资源不存在",
+        AdminErrorKind::Conflict => "Provider 资源状态冲突，请刷新后重试",
+        AdminErrorKind::BadGateway => "上游服务请求失败",
+        AdminErrorKind::UpstreamResultUnknown => "上游执行结果未知，请刷新状态后再决定是否重试",
+        AdminErrorKind::Unavailable => "Provider 服务暂不可用",
+        AdminErrorKind::Internal => "服务内部错误",
+        _ => "Provider 操作失败",
+    };
+    AdminError::new(kind, message)
 }
 
 async fn publish_committed(
@@ -65,7 +89,7 @@ async fn publish_committed(
     revision: crate::model::Revision,
 ) -> Result<(), AdminError> {
     let revision = ConfigRevision::new(revision.get())
-        .map_err(|_| AdminError::internal("Committed configuration revision is invalid"))?;
+        .map_err(|_| AdminError::internal("已提交的配置版本不合法"))?;
     snapshot.publish_committed(revision).await;
     Ok(())
 }
@@ -80,7 +104,7 @@ async fn required_credential(
         .credential_details(provider_kind, account_id)
         .await
         .map_err(|error| map_store_error(error, resource))?
-        .ok_or_else(|| AdminError::not_found(format!("{resource} was not found")))
+        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
 }
 
 async fn pending_authorization(
@@ -90,17 +114,10 @@ async fn pending_authorization(
     resource: &'static str,
 ) -> Result<PendingAuthorizationMutation, AdminError> {
     let target = match &command.reauthorization {
-        Some(target) => {
-            let details =
-                required_credential(accounts, provider_kind, &target.account_id, resource).await?;
-            if details.credential.credential_revision != target.credential_revision {
-                return Err(AdminError::conflict(format!(
-                    "{resource} reauthorization target is stale"
-                )));
-            }
+        Some(account_id) => {
+            required_credential(accounts, provider_kind, account_id, resource).await?;
             AuthorizationMutationTarget::Reauthorize {
-                account_id: target.account_id.clone(),
-                expected_credential_revision: target.credential_revision,
+                account_id: account_id.clone(),
             }
         }
         None => AuthorizationMutationTarget::Create {
@@ -108,7 +125,6 @@ async fn pending_authorization(
         },
     };
     Ok(PendingAuthorizationMutation::new(
-        command.expected_config_revision,
         provider_kind.clone(),
         target,
         crate::model::provider_credentials::AuthorizationOwnerBinding::from_context(
@@ -120,7 +136,7 @@ async fn pending_authorization(
 fn validate_prepared_import(
     provider_kind: &ProviderKind,
     prepared: &PreparedCredentialImport,
-    resource: &'static str,
+    _resource: &'static str,
 ) -> Result<(), AdminError> {
     if prepared.provider_kind != *provider_kind
         || prepared
@@ -128,9 +144,7 @@ fn validate_prepared_import(
             .iter()
             .any(|credential| credential.provider_kind != *provider_kind)
     {
-        return Err(AdminError::conflict(format!(
-            "{resource} prepared facts do not match the requested Provider scope"
-        )));
+        return Err(AdminError::conflict("Provider 准备结果与请求范围不一致"));
     }
     Ok(())
 }
@@ -138,32 +152,36 @@ fn validate_prepared_import(
 fn validate_prepared_rotation(
     account: &crate::model::accounts::AccountRecord,
     prepared: &PreparedCredentialRotation,
-    resource: &'static str,
+    _resource: &'static str,
 ) -> Result<(), AdminError> {
     let facts = prepared.facts();
     if facts.account_id.as_str() != account.id.as_str()
         || facts.provider_kind != account.provider_kind
-        || facts.expected_credential_revision != account.credential_revision
     {
-        return Err(AdminError::conflict(format!(
-            "{resource} prepared facts do not match the current credential"
-        )));
+        return Err(AdminError::conflict("Provider 准备结果与当前凭据不一致"));
     }
     Ok(())
 }
 
-fn validate_authorization_commit(
+async fn validate_authorization_commit(
     provider_kind: &ProviderKind,
     context: &MutationContext,
-    prepared: &PreparedAuthorizationCommit,
+    prepared: PreparedAuthorizationCommit,
     resource: &'static str,
-) -> Result<(), AdminError> {
+) -> Result<PreparedAuthorizationCommit, AdminError> {
     if prepared.pending.provider_kind() != provider_kind
         || !prepared.pending.owner_binding().matches_context(context)
     {
-        return Err(AdminError::conflict(format!(
-            "{resource} pending authorization binding is invalid"
-        )));
+        let validation_error = AdminError::conflict("OAuth 授权绑定已失效，请重新发起授权");
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
     }
     let matches_target = match (prepared.pending.target(), &prepared.credential) {
         (
@@ -171,25 +189,27 @@ fn validate_authorization_commit(
             PreparedAuthorizationCredential::Create(credential),
         ) => credential.provider_kind == *provider_kind,
         (
-            AuthorizationMutationTarget::Reauthorize {
-                account_id,
-                expected_credential_revision,
-            },
+            AuthorizationMutationTarget::Reauthorize { account_id },
             PreparedAuthorizationCredential::Reauthorize(credential),
         ) => {
             let facts = credential.facts();
-            facts.provider_kind == *provider_kind
-                && facts.account_id == *account_id
-                && facts.expected_credential_revision == *expected_credential_revision
+            facts.provider_kind == *provider_kind && facts.account_id == *account_id
         }
         _ => false,
     };
     if !matches_target {
-        return Err(AdminError::conflict(format!(
-            "{resource} prepared credential does not match its pending target"
-        )));
+        let validation_error = AdminError::conflict("OAuth 凭据与待提交目标不一致");
+        if let Err(error) = prepared.abort().await {
+            tracing::warn!(
+                resource,
+                settlement_error = %error,
+                "OAuth authorization claim release failed after preparation validation"
+            );
+            return Err(error);
+        }
+        return Err(validation_error);
     }
-    Ok(())
+    Ok(prepared)
 }
 
 async fn commit_authorization(
@@ -198,16 +218,34 @@ async fn commit_authorization(
     context: &MutationContext,
     resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
-    let (command, guard) = prepared.into_commit();
+    let crate::model::provider_credentials::AuthorizationCommitSettlement {
+        command,
+        credential_guard,
+        authorization_guard,
+    } = prepared.into_commit();
     match accounts.commit_authorization(command, context).await {
         Ok(result) => {
-            if let Some(guard) = guard {
+            if let Some(guard) = credential_guard {
                 guard.finish();
             }
+            if let Some(guard) = authorization_guard {
+                guard.commit().await?;
+            }
             Ok(result)
         }
         Err(error) => {
-            drop(guard);
+            drop(credential_guard);
+            if let Some(guard) = authorization_guard
+                && let Err(settlement_error) = guard.abort().await
+            {
+                tracing::warn!(
+                    resource,
+                    store_error = %error,
+                    settlement_error = %settlement_error,
+                    "OAuth authorization claim release failed after Store commit failure"
+                );
+                return Err(settlement_error);
+            }
             Err(map_store_error(error, resource))
         }
     }
@@ -215,20 +253,13 @@ async fn commit_authorization(
 
 async fn commit_credential_rotation(
     accounts: &dyn AccountStore,
-    expected_config_revision: crate::model::Revision,
     prepared: PreparedCredentialRotation,
     context: &MutationContext,
     resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
     let (facts, guard) = prepared.into_parts();
     match accounts
-        .commit_credential_rotation(
-            CredentialRotationCommit {
-                expected_config_revision,
-                prepared: facts,
-            },
-            context,
-        )
+        .commit_credential_rotation(CredentialRotationCommit { prepared: facts }, context)
         .await
     {
         Ok(result) => {
@@ -244,20 +275,13 @@ async fn commit_credential_rotation(
 
 async fn commit_credential_refresh(
     accounts: &dyn AccountStore,
-    expected_config_revision: crate::model::Revision,
     prepared: PreparedCredentialRotation,
     context: &MutationContext,
     resource: &'static str,
 ) -> Result<CredentialMutationResult, AdminError> {
     let (facts, guard) = prepared.into_parts();
     match accounts
-        .commit_credential_refresh(
-            CredentialRotationCommit {
-                expected_config_revision,
-                prepared: facts,
-            },
-            context,
-        )
+        .commit_credential_refresh(CredentialRotationCommit { prepared: facts }, context)
         .await
     {
         Ok(result) => {
@@ -271,42 +295,6 @@ async fn commit_credential_refresh(
     }
 }
 
-async fn set_credential_enabled(
-    accounts: &dyn AccountStore,
-    provider: &dyn ProviderAdmin,
-    command: CredentialMutation,
-    enabled: bool,
-    resource: &'static str,
-) -> Result<CredentialMutationResult, AdminError> {
-    required_credential(
-        accounts,
-        provider.provider_kind(),
-        &command.account_id,
-        resource,
-    )
-    .await?;
-    let account_id = command.account_id;
-    let revision = accounts
-        .set_account_enabled(
-            SetAccountEnabled {
-                expected_config_revision: command.expected_config_revision,
-                account_id: account_id.as_str().to_owned(),
-                enabled,
-            },
-            &command.context,
-        )
-        .await
-        .map_err(|error| map_store_error(error, resource))?;
-    if !enabled {
-        provider.account_unavailable(&account_id).await;
-    }
-    Ok(CredentialMutationResult {
-        config_revision: revision,
-        account_id,
-        credential_revision: None,
-    })
-}
-
 async fn delete_credentials(
     accounts: &dyn AccountStore,
     provider: &dyn ProviderAdmin,
@@ -320,7 +308,6 @@ async fn delete_credentials(
     let revision = accounts
         .delete_accounts(
             DeleteAccounts {
-                expected_config_revision: command.expected_config_revision,
                 account_ids: account_ids
                     .iter()
                     .map(|account_id| account_id.as_str().to_owned())
@@ -333,6 +320,7 @@ async fn delete_credentials(
     for account_id in &account_ids {
         provider.account_unavailable(account_id).await;
     }
+    provider.account_facts_changed(&account_ids).await;
     Ok(CredentialDeletionResult {
         config_revision: revision,
         account_ids,

backend/crates/gateway-admin/src/use_case/observability.rs

@@ -1,8 +1,10 @@
 //! 观测查询、趋势、费用覆盖与健康阈值规则。
 
 use std::{
-    collections::{BTreeMap, btree_map::Entry},
+    collections::{BTreeMap, HashMap, btree_map::Entry},
+    str::FromStr,
     sync::Arc,
+    time::{Duration as StdDuration, Instant},
 };
 
 use async_trait::async_trait;
@@ -21,7 +23,7 @@ use crate::{
             UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageInsights, UsageInsightsCost,
             UsageInsightsCostPoint, UsageInsightsHealth, UsageInsightsHealthPoint,
             UsageInsightsPerformance, UsageInsightsPerformancePoint, UsageOverview, UsagePage,
-            UsageQuery, UsageSummary,
+            UsageQuery, UsageSummary, china_day_start,
         },
         provider_credentials::ProviderQuotaRequest,
     },
@@ -38,7 +40,58 @@ const HEALTH_TIMELINE_SLOTS: i64 = 24 * 4;
 const HEALTH_TIMELINE_MIN_SAMPLE_SIZE: u64 = 10;
 const HEALTH_TIMELINE_UNAVAILABLE_FAILURE_THRESHOLD: u64 = 3;
 const HEALTH_TIMELINE_STABLE_RELIABILITY: f64 = 99.0;
-const CHINA_OFFSET_SECONDS: i64 = 8 * 60 * 60;
+const DASHBOARD_QUERY_BUCKET_SECONDS: i64 = 2;
+const DASHBOARD_QUERY_CACHE_RETENTION: StdDuration = StdDuration::from_secs(2);
+
+#[derive(Clone, Copy, PartialEq, Eq, Hash)]
+struct DashboardQueryKey {
+    start: DateTime<Utc>,
+    end_bucket: i64,
+}
+
+impl DashboardQueryKey {
+    fn new(range: TimeRange) -> Self {
+        Self {
+            start: range.start,
+            end_bucket: range
+                .end
+                .timestamp()
+                .div_euclid(DASHBOARD_QUERY_BUCKET_SECONDS),
+        }
+    }
+}
+
+struct DashboardQueryEntry {
+    created_at: Instant,
+    result: Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>>,
+}
+
+#[derive(Default)]
+struct DashboardQueryCache {
+    entries: tokio::sync::Mutex<HashMap<DashboardQueryKey, DashboardQueryEntry>>,
+}
+
+impl DashboardQueryCache {
+    async fn result_cell(
+        &self,
+        key: DashboardQueryKey,
+    ) -> Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>> {
+        let now = Instant::now();
+        let mut entries = self.entries.lock().await;
+        entries.retain(|_, entry| {
+            now.duration_since(entry.created_at) < DASHBOARD_QUERY_CACHE_RETENTION
+        });
+        Arc::clone(
+            &entries
+                .entry(key)
+                .or_insert_with(|| DashboardQueryEntry {
+                    created_at: now,
+                    result: Arc::new(tokio::sync::OnceCell::new()),
+                })
+                .result,
+        )
+    }
+}
 
 /// API 消费的观测控制面服务。
 #[async_trait]
@@ -75,6 +128,7 @@ pub(crate) struct DefaultObservabilityService {
     store: Arc<dyn ObservabilityStore>,
     settings: Arc<dyn SettingsStore>,
     providers: ProviderAdminRegistry,
+    dashboard_queries: DashboardQueryCache,
 }
 
 impl DefaultObservabilityService {
@@ -88,24 +142,22 @@ impl DefaultObservabilityService {
             store,
             settings,
             providers,
+            dashboard_queries: DashboardQueryCache::default(),
         }
     }
-}
 
-#[async_trait]
-impl ObservabilityService for DefaultObservabilityService {
-    async fn dashboard_summary(
+    async fn load_dashboard_summary(
         &self,
         range: TimeRange,
-        kind: TrendKind,
     ) -> Result<DashboardResult, AdminError> {
+        let observed_at = Utc::now();
         let (mut observation, settings, runtime_slots) = futures::try_join!(
-            self.store.dashboard_summary(range),
+            self.store.dashboard_summary(range, observed_at),
             self.settings.load_runtime_settings(),
-            self.store.dashboard_runtime_slots(range.end),
+            self.store.dashboard_runtime_slots(observed_at),
         )
         .map_err(|error| map_store_error(error, "dashboard"))?;
-        self.enrich_billing(&mut observation.recent_requests)?;
+        self.enrich_list_billing(&mut observation.recent_requests);
         self.enrich_dashboard_quotas(&mut observation.account_usage)
             .await;
         let today_start = china_day_start(observation.range.end);
@@ -113,30 +165,40 @@ impl ObservabilityService for DefaultObservabilityService {
         let today =
             dashboard_period_metrics(&observation.trend, today_start, observation.range.end);
         let yesterday = dashboard_period_metrics(&observation.trend, yesterday_start, today_start);
-        let total_billing_usd = observation
-            .attempts
-            .costs
-            .iter()
-            .find(|cost| cost.currency == "USD")
-            .map(|cost| cost.amount.clone());
+        let total_billing_usd = observation.totals.billing_usd.clone();
         let total_cached_token_rate = rate_or_zero(
-            observation.requests.cached_tokens,
-            observation.requests.input_tokens,
+            observation.totals.cached_tokens,
+            observation.totals.input_tokens,
         );
-        let average_first_token_latency_ms = average(
-            observation.requests.first_token_latency_sum_ms,
-            observation.requests.first_token_latency_count,
-        );
-        let trend = trend(kind, observation.trend.clone())?;
+        let (first_token_latency_sum_ms, first_token_latency_count) = observation
+            .trend
+            .iter()
+            .fold((0_u64, 0_u64), |(sum, count), point| {
+                (
+                    sum.saturating_add(point.metrics.first_token_latency_sum_ms),
+                    count.saturating_add(point.metrics.first_token_latency_count),
+                )
+            });
+        let average_first_token_latency_ms =
+            average(first_token_latency_sum_ms, first_token_latency_count);
+        let trend = trend(TrendKind::Usage, observation.trend.clone())?;
         let health_timeline = health_timeline_at(&observation.trend, Utc::now());
         let wire_profiles = self.providers.dashboard_wire_profiles();
         let max_concurrent_per_account = u64::from(settings.max_concurrent_per_account);
-        let active_accounts = runtime_slots
-            .as_ref()
-            .map_or(observation.provider_accounts.active, |slots| {
-                slots.active_accounts
-            });
-        let total_slots = active_accounts.saturating_mul(max_concurrent_per_account);
+        let total_slots = runtime_slots.as_ref().map_or_else(
+            || {
+                observation
+                    .provider_accounts
+                    .normal
+                    .saturating_mul(max_concurrent_per_account)
+            },
+            |slots| {
+                slots
+                    .inherited_accounts
+                    .saturating_mul(max_concurrent_per_account)
+                    .saturating_add(slots.overridden_slots)
+            },
+        );
         let used_slots = runtime_slots.and_then(|slots| slots.used_slots);
         Ok(DashboardResult {
             capacity: DashboardCapacity {
@@ -157,6 +219,26 @@ impl ObservabilityService for DefaultObservabilityService {
             wire_profiles,
         })
     }
+}
+
+#[async_trait]
+impl ObservabilityService for DefaultObservabilityService {
+    async fn dashboard_summary(
+        &self,
+        range: TimeRange,
+        kind: TrendKind,
+    ) -> Result<DashboardResult, AdminError> {
+        let cell = self
+            .dashboard_queries
+            .result_cell(DashboardQueryKey::new(range))
+            .await;
+        let mut result = cell
+            .get_or_init(|| self.load_dashboard_summary(range))
+            .await
+            .clone()?;
+        result.trend = trend(kind, result.observation.trend.clone())?;
+        Ok(result)
+    }
 
     async fn dashboard_trend(
         &self,
@@ -177,20 +259,20 @@ impl ObservabilityService for DefaultObservabilityService {
             .list_usage_records(query)
             .await
             .map_err(|error| map_store_error(error, "usage records"))?;
-        self.enrich_billing(&mut page.items)?;
+        self.enrich_list_billing(&mut page.items);
         Ok(page)
     }
 
     async fn usage_record_detail(&self, request_id: &str) -> Result<UsageDetail, AdminError> {
         if request_id.trim().is_empty() {
-            return Err(AdminError::invalid("Usage record ID is required"));
+            return Err(AdminError::invalid("用量记录 ID 不能为空"));
         }
         let mut detail = self
             .store
             .usage_record_detail(request_id)
             .await
             .map_err(|error| map_store_error(error, "usage record"))?;
-        self.enrich_billing(std::slice::from_mut(&mut detail.request))?;
+        self.enrich_detail_billing(std::slice::from_mut(&mut detail.request));
         Ok(detail)
     }
 
@@ -243,24 +325,50 @@ impl ObservabilityService for DefaultObservabilityService {
         let total_requests = items.iter().fold(0_u64, |total, item| {
             total.saturating_add(item.request_count)
         });
-        Ok(DiagnosticsResult {
-            dimension,
-            items: items
-                .into_iter()
-                .map(|item| DiagnosticsItem {
+        let mut items = items
+            .into_iter()
+            .map(|item| {
+                let error_rate = rate_or_zero(item.failure_count, item.request_count);
+                let non_completion_rate =
+                    rate_or_zero(item.non_completion_count, item.request_count);
+                let retry_rate = rate_or_zero(item.retry_count, item.request_count);
+                let impact_score = diagnostic_impact_score(
+                    item.request_count,
+                    total_requests,
+                    error_rate,
+                    non_completion_rate,
+                    retry_rate,
+                    item.first_token_p95_ms,
+                );
+                DiagnosticsItem {
+                    key: item.key,
                     name: item.name,
                     request_count: item.request_count,
-                    success_count: item.request_count.saturating_sub(item.failure_count),
+                    success_count: item.success_count,
                     error_count: item.failure_count,
-                    error_rate: rate_or_zero(item.failure_count, item.request_count),
+                    error_rate,
                     request_share: rate_or_zero(item.request_count, total_requests),
                     average_latency_ms: item.average_latency_ms,
+                    latency_p95_ms: item.latency_p95_ms,
+                    first_token_p95_ms: item.first_token_p95_ms,
+                    non_completion_count: item.non_completion_count,
+                    non_completion_rate,
+                    retry_count: item.retry_count,
+                    retry_rate,
+                    impact_score,
                     estimated_cost: usd_cost(&item.costs),
                     attempt_count: item.attempt_count,
                     total_tokens: item.total_tokens,
-                })
-                .collect(),
-        })
+                }
+            })
+            .collect::<Vec<_>>();
+        items.sort_by(|left, right| {
+            right
+                .impact_score
+                .total_cmp(&left.impact_score)
+                .then_with(|| right.request_count.cmp(&left.request_count))
+        });
+        Ok(DiagnosticsResult { dimension, items })
     }
 
     async fn ops_errors(&self, query: OpsErrorQuery) -> Result<OpsErrorPage, AdminError> {
@@ -274,35 +382,40 @@ impl ObservabilityService for DefaultObservabilityService {
 fn build_usage_insights(
     overview: UsageOverview,
     trend: Vec<RequestMetricPoint>,
-    standard_costs: UsageStandardCosts,
+    standard_costs: UsageCostScenarios,
 ) -> Result<UsageInsights, AdminError> {
     let granularity = trend.first().map_or(
         crate::model::observability::Granularity::FifteenMinutes,
         |point| point.granularity,
     );
     if trend.iter().any(|point| point.granularity != granularity) {
-        return Err(AdminError::internal(
-            "Usage insight trend contains mixed granularities",
-        ));
+        return Err(AdminError::internal("用量洞察趋势包含不一致的时间粒度"));
     }
 
     let requests = &overview.requests;
     let failed_requests = service_failure_count(requests);
     let health_requests = requests.success_count.saturating_add(failed_requests);
     let health = UsageInsightsHealth {
-        total_requests: health_requests,
+        total_requests: requests.request_count,
         success_requests: requests.success_count,
         failed_requests,
         cancelled_requests: requests.cancelled_count,
         incomplete_requests: requests.incomplete_count,
         caller_error_requests: requests.caller_error_count,
         success_rate: rate_or_zero(requests.success_count, health_requests),
+        completion_rate: rate_or_zero(
+            requests
+                .success_count
+                .saturating_add(requests.failure_count),
+            requests.request_count,
+        ),
         points: trend
             .iter()
             .map(|point| {
                 let failed_requests = service_failure_count(&point.metrics);
                 let health_requests = point.metrics.success_count.saturating_add(failed_requests);
                 UsageInsightsHealthPoint {
+                    total_requests: point.metrics.request_count,
                     bucket_start: point.bucket_start,
                     success_requests: point.metrics.success_count,
                     failed_requests,
@@ -322,27 +435,74 @@ fn build_usage_insights(
             requests.first_token_latency_count,
             requests.request_count,
         ),
+        admission_decision_percentiles: requests.admission_decision_percentiles,
+        account_selection_wait_percentiles: requests.account_selection_wait_percentiles,
+        admission_decision_coverage: rate_or_zero(
+            requests.admission_decision_count,
+            requests.request_count,
+        ),
+        account_selection_wait_coverage: rate_or_zero(
+            requests.account_selection_wait_count,
+            requests.request_count,
+        ),
+        output_throughput_p10: requests.output_throughput_p10,
+        output_throughput_p50: requests.output_throughput_p50,
+        output_throughput_p90: requests.output_throughput_p90,
+        capacity_utilization_avg_basis_points: requests.capacity_utilization_avg_basis_points,
+        capacity_utilization_p95_basis_points: requests.capacity_utilization_p95_basis_points,
+        capacity_coverage: rate_or_zero(requests.capacity_sample_count, requests.request_count),
         points: trend
             .iter()
             .map(|point| UsageInsightsPerformancePoint {
                 bucket_start: point.bucket_start,
                 latency_percentiles: point.metrics.latency_percentiles,
                 first_token_latency_percentiles: point.metrics.first_token_latency_percentiles,
+                admission_decision_percentiles: point.metrics.admission_decision_percentiles,
+                account_selection_wait_percentiles: point
+                    .metrics
+                    .account_selection_wait_percentiles,
+                output_throughput_p10: point.metrics.output_throughput_p10,
+                output_throughput_p50: point.metrics.output_throughput_p50,
+                output_throughput_p90: point.metrics.output_throughput_p90,
+                capacity_utilization_avg_basis_points: point
+                    .metrics
+                    .capacity_utilization_avg_basis_points,
+                capacity_utilization_p95_basis_points: point
+                    .metrics
+                    .capacity_utilization_p95_basis_points,
             })
             .collect(),
     };
     let estimated_cost = usd_cost(&overview.attempts.costs);
-    let UsageStandardCosts {
-        total: standard_cost,
-        by_bucket: standard_costs_by_bucket,
+    let UsageCostScenarios {
+        standard:
+            ScenarioCosts {
+                total: standard_cost,
+                by_bucket: standard_costs_by_bucket,
+            },
+        no_cache:
+            ScenarioCosts {
+                total: no_cache_cost,
+                by_bucket: no_cache_costs_by_bucket,
+            },
     } = standard_costs;
+    let cache_savings = amount_difference(no_cache_cost.as_ref(), estimated_cost.as_ref());
+    let tier_premium = amount_difference(estimated_cost.as_ref(), standard_cost.as_ref());
+    let cost_per_request = estimated_cost
+        .as_ref()
+        .and_then(|cost| cost.checked_div_u64(requests.request_count));
+    let cost_per_successful_request = estimated_cost
+        .as_ref()
+        .and_then(|cost| cost.checked_div_u64(requests.success_count));
     let cost = UsageInsightsCost {
-        cost_per_request: estimated_cost
-            .as_ref()
-            .and_then(|cost| cost.checked_div_u64(requests.request_count)),
+        cost_per_request,
         estimated_cost,
         standard_cost,
+        no_cache_cost,
+        cache_savings,
+        tier_premium,
         tokens_per_request: rate_or_zero(requests.total_tokens, requests.request_count),
+        cost_per_successful_request,
         cached_token_rate: rate_or_zero(requests.cached_tokens, requests.input_tokens),
         cache_hit_request_rate: ratio(
             requests.cache_hit_request_count,
@@ -362,6 +522,11 @@ fn build_usage_insights(
                 total_tokens: point.metrics.total_tokens,
                 estimated_cost: usd_cost(&point.costs),
                 standard_cost: standard_costs_by_bucket.get(&point.bucket_start).cloned(),
+                no_cache_cost: no_cache_costs_by_bucket.get(&point.bucket_start).cloned(),
+                cache_savings: amount_difference(
+                    no_cache_costs_by_bucket.get(&point.bucket_start),
+                    usd_cost(&point.costs).as_ref(),
+                ),
                 cached_token_rate: rate_or_zero(
                     point.metrics.cached_tokens,
                     point.metrics.input_tokens,
@@ -386,12 +551,12 @@ fn build_usage_insights(
 }
 
 #[derive(Debug, Default)]
-struct UsageStandardCosts {
+struct ScenarioCosts {
     total: Option<DecimalAmount>,
     by_bucket: BTreeMap<DateTime<Utc>, DecimalAmount>,
 }
 
-impl UsageStandardCosts {
+impl ScenarioCosts {
     fn add(
         &mut self,
         bucket_start: DateTime<Utc>,
@@ -400,14 +565,15 @@ impl UsageStandardCosts {
         self.total = Some(match self.total.take() {
             Some(current) => current
                 .checked_add(&amount)
-                .ok_or_else(|| AdminError::internal("Usage standard cost exceeds decimal range"))?,
+                .ok_or_else(|| AdminError::internal("用量标准成本超出数值范围"))?,
             None => amount.clone(),
         });
         match self.by_bucket.entry(bucket_start) {
             Entry::Occupied(mut entry) => {
-                let sum = entry.get().checked_add(&amount).ok_or_else(|| {
-                    AdminError::internal("Usage standard cost exceeds decimal range")
-                })?;
+                let sum = entry
+                    .get()
+                    .checked_add(&amount)
+                    .ok_or_else(|| AdminError::internal("用量标准成本超出数值范围"))?;
                 entry.insert(sum);
             }
             Entry::Vacant(entry) => {
@@ -418,22 +584,29 @@ impl UsageStandardCosts {
     }
 }
 
+#[derive(Debug, Default)]
+struct UsageCostScenarios {
+    standard: ScenarioCosts,
+    no_cache: ScenarioCosts,
+}
+
 fn recover_standard_costs(
     providers: &ProviderAdminRegistry,
     facts: Vec<UsageCalculatedBillingFact>,
-) -> Result<UsageStandardCosts, AdminError> {
-    let mut standard_costs = UsageStandardCosts::default();
+) -> Result<UsageCostScenarios, AdminError> {
+    let mut scenarios = UsageCostScenarios::default();
     for fact in facts {
-        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind) else {
+        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind.clone()) else {
             continue;
         };
         let input = ProviderBillingInput {
-            upstream_model_id: fact.upstream_model_id,
+            upstream_model_id: fact.upstream_model_id.clone(),
+            service_tier: fact.service_tier.clone(),
             input_tokens: fact.input_tokens,
             output_tokens: fact.output_tokens,
             cached_tokens: fact.cached_tokens,
             cache_write_tokens: fact.cache_write_tokens,
-            total: fact.total,
+            total: fact.total.clone(),
         };
         let breakdown = match providers.calculated_billing(&provider_kind, &input) {
             Ok(breakdown) => breakdown,
@@ -450,9 +623,80 @@ fn recover_standard_costs(
         {
             continue;
         }
-        standard_costs.add(fact.bucket_start, breakdown.standard_amount.amount)?;
+        scenarios
+            .standard
+            .add(fact.bucket_start, breakdown.standard_amount.amount.clone())?;
+        if let Some(no_cache_cost) = no_cache_cost(&fact, &breakdown) {
+            scenarios.no_cache.add(fact.bucket_start, no_cache_cost)?;
+        }
     }
-    Ok(standard_costs)
+    Ok(scenarios)
+}
+
+fn no_cache_cost(
+    fact: &UsageCalculatedBillingFact,
+    breakdown: &crate::model::observability::CalculatedBillingBreakdown,
+) -> Option<DecimalAmount> {
+    let input_tokens = fact.input_tokens?;
+    let cached_tokens = fact.cached_tokens.unwrap_or_default().min(input_tokens);
+    let cache_write_tokens = fact
+        .cache_write_tokens
+        .unwrap_or_default()
+        .min(input_tokens.saturating_sub(cached_tokens));
+    let input_rate = decimal(&breakdown.input_price_per_million.amount)?;
+    let replaced_input_amount = input_rate
+        .scaled()
+        .checked_mul(u128::from(cached_tokens.saturating_add(cache_write_tokens)))?
+        .checked_div(1_000_000)?;
+    let total = decimal(&breakdown.total_amount.amount)?
+        .scaled()
+        .checked_sub(decimal(&breakdown.cache_read_amount.amount)?.scaled())?
+        .checked_sub(decimal(&breakdown.cache_write_amount.amount)?.scaled())?
+        .checked_add(replaced_input_amount)?;
+    DecimalAmount::from_str(
+        &gateway_core::accounting::Decimal::from_scaled(total)
+            .ok()?
+            .canonical(),
+    )
+    .ok()
+}
+
+fn amount_difference(
+    larger: Option<&DecimalAmount>,
+    smaller: Option<&DecimalAmount>,
+) -> Option<DecimalAmount> {
+    let difference = decimal(larger?)?
+        .scaled()
+        .checked_sub(decimal(smaller?)?.scaled())?;
+    DecimalAmount::from_str(
+        &gateway_core::accounting::Decimal::from_scaled(difference)
+            .ok()?
+            .canonical(),
+    )
+    .ok()
+}
+
+fn decimal(value: &DecimalAmount) -> Option<gateway_core::accounting::Decimal> {
+    value.as_str().parse().ok()
+}
+
+fn diagnostic_impact_score(
+    request_count: u64,
+    total_requests: u64,
+    error_rate: f64,
+    non_completion_rate: f64,
+    retry_rate: f64,
+    first_token_p95_ms: Option<u64>,
+) -> f64 {
+    let request_share = rate_or_zero(request_count, total_requests);
+    let slow_score = first_token_p95_ms
+        .map_or(0.0, |value| value as f64 / 30_000.0)
+        .min(1.0);
+    error_rate * 0.35
+        + non_completion_rate * 0.25
+        + retry_rate.min(1.0) * 0.20
+        + request_share * 0.10
+        + slow_score * 0.10
 }
 
 fn usd_cost(costs: &[CurrencyCost]) -> Option<DecimalAmount> {
@@ -487,20 +731,18 @@ impl DefaultObservabilityService {
         });
         let quota_used = futures::future::join_all(quota_reads).await;
         for (account, used_percent) in accounts.iter_mut().zip(quota_used) {
-            account.quota_used_percent = used_percent
-                .or_else(|| (account.availability == "quota_exhausted").then_some(100.0));
+            account.quota_used_percent = used_percent;
         }
     }
 
-    fn enrich_billing(
-        &self,
-        records: &mut [crate::model::observability::UsageRecord],
-    ) -> Result<(), AdminError> {
+    /// 逐条尽力把可校验的总额升级为完整分解；单条脏数据（非法 Provider kind、
+    /// 不支持的来源或费用规则失败）只保留该条已存的总额，不影响整页返回。
+    fn enrich_list_billing(&self, records: &mut [crate::model::observability::UsageListRecord]) {
         for record in records {
             let Some(UsageBilling::Total { source, total }) = record.billing.as_ref() else {
                 continue;
             };
-            if source != "calculated" {
+            if !matches!(source.as_str(), "calculated" | "provider_reported") {
                 continue;
             }
             let (Some(provider), Some(upstream_model_id)) = (
@@ -509,25 +751,54 @@ impl DefaultObservabilityService {
             ) else {
                 continue;
             };
-            let provider_kind = ProviderKind::new(provider.to_owned())
-                .map_err(|_| AdminError::internal("Stored Provider kind is invalid"))?;
+            let Ok(provider_kind) = ProviderKind::new(provider.to_owned()) else {
+                continue;
+            };
             let input = ProviderBillingInput {
                 upstream_model_id: upstream_model_id.clone(),
+                service_tier: record.service_tier.clone(),
                 input_tokens: record.input_tokens,
                 output_tokens: record.output_tokens,
                 cached_tokens: record.cached_tokens,
                 cache_write_tokens: record.cache_write_tokens,
                 total: total.clone(),
             };
-            if let Some(breakdown) = self
-                .providers
-                .calculated_billing(&provider_kind, &input)
-                .map_err(|error| map_provider_error(error, "usage billing"))?
-            {
+            if let Ok(Some(breakdown)) = self.providers.calculated_billing(&provider_kind, &input) {
+                record.billing = Some(UsageBilling::Calculated(Box::new(breakdown)));
+            }
+        }
+    }
+
+    fn enrich_detail_billing(&self, records: &mut [crate::model::observability::UsageRecord]) {
+        for record in records {
+            let Some(UsageBilling::Total { source, total }) = record.billing.as_ref() else {
+                continue;
+            };
+            if !matches!(source.as_str(), "calculated" | "provider_reported") {
+                continue;
+            }
+            let (Some(provider), Some(upstream_model_id)) = (
+                record.provider_kind.as_deref(),
+                record.upstream_model_id.as_ref(),
+            ) else {
+                continue;
+            };
+            let Ok(provider_kind) = ProviderKind::new(provider.to_owned()) else {
+                continue;
+            };
+            let input = ProviderBillingInput {
+                upstream_model_id: upstream_model_id.clone(),
+                service_tier: record.service_tier.clone(),
+                input_tokens: record.input_tokens,
+                output_tokens: record.output_tokens,
+                cached_tokens: record.cached_tokens,
+                cache_write_tokens: record.cache_write_tokens,
+                total: total.clone(),
+            };
+            if let Ok(Some(breakdown)) = self.providers.calculated_billing(&provider_kind, &input) {
                 record.billing = Some(UsageBilling::Calculated(Box::new(breakdown)));
             }
         }
-        Ok(())
     }
 }
 
@@ -611,9 +882,9 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
             .saturating_add(point.cost_coverage.not_billable_count);
         for cost in &point.costs {
             if let Some(amount) = costs.get_mut(&cost.currency) {
-                *amount = amount.checked_add(&cost.amount).ok_or_else(|| {
-                    AdminError::internal("Cost aggregation exceeded numeric bounds")
-                })?;
+                *amount = amount
+                    .checked_add(&cost.amount)
+                    .ok_or_else(|| AdminError::internal("成本聚合结果超出数值范围"))?;
             } else {
                 costs.insert(cost.currency.clone(), cost.amount.clone());
             }
@@ -629,6 +900,20 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
         metrics.cache_hit_request_count,
         metrics.cache_eligible_request_count,
     );
+    let peak_first_token_p95_ms = points
+        .iter()
+        .filter_map(|point| point.metrics.first_token_latency_percentiles.p95_ms)
+        .map(|value| value.as_f64())
+        .reduce(f64::max);
+    let peak_latency_p95_ms = points
+        .iter()
+        .filter_map(|point| point.metrics.latency_percentiles.p95_ms)
+        .map(|value| value.as_f64())
+        .reduce(f64::max);
+    let minimum_output_throughput_p50 = points
+        .iter()
+        .filter_map(|point| point.metrics.output_throughput_p50)
+        .min();
     Ok(Trend {
         kind,
         points: points.into_iter().map(trend_point).collect(),
@@ -642,6 +927,9 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
             average_latency_ms,
             max_latency_ms: metrics.max_latency_ms,
             min_latency_ms: metrics.min_latency_ms,
+            peak_first_token_p95_ms,
+            peak_latency_p95_ms,
+            minimum_output_throughput_p50,
             success_rate,
             cache_hit_request_rate,
             costs: costs
@@ -833,11 +1121,6 @@ fn service_failure_count(metrics: &RequestMetrics) -> u64 {
         .saturating_sub(metrics.caller_error_count)
 }
 
-fn china_day_start(value: DateTime<Utc>) -> DateTime<Utc> {
-    let elapsed = (value.timestamp() + CHINA_OFFSET_SECONDS).rem_euclid(24 * 60 * 60);
-    value - Duration::seconds(elapsed) - Duration::nanoseconds(i64::from(value.nanosecond()))
-}
-
 fn quarter_hour_start(value: DateTime<Utc>) -> DateTime<Utc> {
     let elapsed = value
         .timestamp()

backend/crates/gateway-admin/src/use_case/openai.rs

@@ -11,9 +11,9 @@ use crate::{
         provider_credentials::{
             AuthorizationStarted, CompleteAuthorization, CredentialDeletion,
             CredentialDeletionResult, CredentialDetails, CredentialImportCommit,
-            CredentialImportResult, CredentialListQuery, CredentialMutation,
-            CredentialMutationResult, CredentialPage, ImportCredentials, PrepareCredentialImport,
-            PrepareCredentialRotation, ProviderQuotaRequest, RotateCredential, StartAuthorization,
+            CredentialImportResult, CredentialListQuery, CredentialMutationResult, CredentialPage,
+            ImportCredentials, PrepareCredentialImport, PrepareCredentialRotation,
+            ProviderQuotaRequest, RotateCredential, StartAuthorization,
         },
     },
     ports::{provider::ProviderAdmin, store::AccountStore},
@@ -22,8 +22,7 @@ use crate::{
 use super::{
     commit_authorization, commit_credential_rotation, delete_credentials, map_provider_error,
     map_store_error, pending_authorization, publish_committed, required_credential,
-    set_credential_enabled, validate_authorization_commit, validate_prepared_import,
-    validate_prepared_rotation,
+    validate_authorization_commit, validate_prepared_import, validate_prepared_rotation,
 };
 
 /// OpenAI 固定管理路由消费的服务。
@@ -50,14 +49,6 @@ pub trait OpenAiService: Send + Sync {
         &self,
         command: RotateCredential,
     ) -> Result<CredentialMutationResult, AdminError>;
-    async fn enable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError>;
-    async fn disable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError>;
     async fn delete(
         &self,
         command: CredentialDeletion,
@@ -83,6 +74,31 @@ impl DefaultOpenAiService {
             snapshot,
         }
     }
+
+    fn observe_initial_quotas(&self, account_ids: &[ProviderAccountId], request_id: &str) {
+        let provider = Arc::clone(&self.provider);
+        let account_ids = account_ids.to_vec();
+        let request_id = request_id.to_owned();
+        tokio::spawn(async move {
+            for account_id in account_ids {
+                if let Err(error) = provider
+                    .quota(ProviderQuotaRequest {
+                        account_id: account_id.clone(),
+                        refresh: true,
+                        rolling_usage: None,
+                    })
+                    .await
+                {
+                    tracing::warn!(
+                        request_id,
+                        account_id = %account_id.as_str(),
+                        quota_error = ?error.kind(),
+                        "OpenAI initial quota observation failed"
+                    );
+                }
+            }
+        });
+    }
 }
 
 #[async_trait]
@@ -112,7 +128,6 @@ impl OpenAiService for DefaultOpenAiService {
         command: ImportCredentials,
     ) -> Result<CredentialImportResult, AdminError> {
         let context = command.context;
-        let expected_config_revision = command.expected_config_revision;
         let prepared = self
             .provider
             .prepare_import(PrepareCredentialImport {
@@ -127,27 +142,15 @@ impl OpenAiService for DefaultOpenAiService {
         )?;
         let result = self
             .accounts
-            .commit_credential_import(
-                CredentialImportCommit {
-                    expected_config_revision,
-                    prepared,
-                },
-                &context,
-            )
+            .commit_credential_import(CredentialImportCommit { prepared }, &context)
             .await
             .map_err(|error| map_store_error(error, "OpenAI credential import"))?;
+        self.provider
+            .account_facts_changed(&result.credential_ids)
+            .await;
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        // 导入已经提交，额度属于可重建观察事实；单个账号查询失败由周期任务重试。
-        for account_id in &result.credential_ids {
-            let _ = self
-                .provider
-                .quota(ProviderQuotaRequest {
-                    account_id: account_id.clone(),
-                    refresh: true,
-                    rolling_usage: None,
-                })
-                .await;
-        }
+        // 导入完成后立即做一次观察；失败不回滚已经提交的 credential。
+        self.observe_initial_quotas(&result.credential_ids, &context.request_id);
         Ok(result)
     }
 
@@ -178,12 +181,13 @@ impl OpenAiService for DefaultOpenAiService {
             .complete_authorization(command)
             .await
             .map_err(|error| map_provider_error(error, "OpenAI authorization"))?;
-        validate_authorization_commit(
+        let prepared = validate_authorization_commit(
             self.provider.provider_kind(),
             &context,
-            &prepared,
+            prepared,
             "OpenAI authorization",
-        )?;
+        )
+        .await?;
         let result = commit_authorization(
             self.accounts.as_ref(),
             prepared,
@@ -191,7 +195,14 @@ impl OpenAiService for DefaultOpenAiService {
             "OpenAI authorization",
         )
         .await?;
+        self.provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
+        self.observe_initial_quotas(
+            std::slice::from_ref(&result.account_id),
+            &context.request_id,
+        );
         Ok(result)
     }
 
@@ -200,7 +211,6 @@ impl OpenAiService for DefaultOpenAiService {
         command: RotateCredential,
     ) -> Result<CredentialMutationResult, AdminError> {
         let context = command.mutation.context;
-        let expected_config_revision = command.mutation.expected_config_revision;
         let account_id = command.mutation.account_id;
         let details = required_credential(
             self.accounts.as_ref(),
@@ -209,17 +219,11 @@ impl OpenAiService for DefaultOpenAiService {
             "OpenAI credential rotation",
         )
         .await?;
-        if details.credential.credential_revision != command.expected_credential_revision {
-            return Err(AdminError::conflict(
-                "OpenAI credential rotation revision is stale",
-            ));
-        }
         let account = details.credential;
         let prepared = self
             .provider
             .prepare_rotation(PrepareCredentialRotation {
                 account: account.clone(),
-                expected_credential_revision: command.expected_credential_revision,
                 provider_material: command.provider_material,
             })
             .await
@@ -227,44 +231,14 @@ impl OpenAiService for DefaultOpenAiService {
         validate_prepared_rotation(&account, &prepared, "OpenAI credential rotation")?;
         let result = commit_credential_rotation(
             self.accounts.as_ref(),
-            expected_config_revision,
             prepared,
             &context,
             "OpenAI credential rotation",
         )
         .await?;
-        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        Ok(result)
-    }
-
-    async fn enable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError> {
-        let result = set_credential_enabled(
-            self.accounts.as_ref(),
-            self.provider.as_ref(),
-            command,
-            true,
-            "OpenAI credential",
-        )
-        .await?;
-        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        Ok(result)
-    }
-
-    async fn disable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError> {
-        let result = set_credential_enabled(
-            self.accounts.as_ref(),
-            self.provider.as_ref(),
-            command,
-            false,
-            "OpenAI credential",
-        )
-        .await?;
+        self.provider
+            .account_facts_changed(std::slice::from_ref(&result.account_id))
+            .await;
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
         Ok(result)
     }

backend/crates/gateway-admin/src/use_case/settings.rs

@@ -86,13 +86,12 @@ impl SettingsService for DefaultSettingsService {
         &self,
         context: &MutationContext,
     ) -> Result<RegeneratedAdminApiKey, AdminError> {
-        let settings = self.load().await?;
         let mut bytes = [0_u8; 32];
         OsRng.fill_bytes(&mut bytes);
         let key = AdminApiKey::new(format!("admin-{}", hex::encode(bytes)));
         let mutation = self
             .store
-            .replace_admin_api_key(settings.config_revision, key.clone(), context)
+            .replace_admin_api_key(key.clone(), context)
             .await
             .map_err(|error| map_store_error(error, "administrator API key"))?;
         publish_committed(self.snapshot.as_ref(), mutation.config_revision).await?;
@@ -103,10 +102,9 @@ impl SettingsService for DefaultSettingsService {
         &self,
         context: &MutationContext,
     ) -> Result<AdminApiKeyMutation, AdminError> {
-        let settings = self.load().await?;
         let mutation = self
             .store
-            .delete_admin_api_key(settings.config_revision, context)
+            .delete_admin_api_key(context)
             .await
             .map_err(|error| map_store_error(error, "administrator API key"))?;
         publish_committed(self.snapshot.as_ref(), mutation.config_revision).await?;
@@ -125,6 +123,6 @@ fn validate_settings(command: &ReplaceRuntimeSettings) -> Result<(), AdminError>
     if valid {
         Ok(())
     } else {
-        Err(AdminError::invalid("Runtime settings violate constraints"))
+        Err(AdminError::invalid("运行时设置不满足约束"))
     }
 }

backend/crates/gateway-admin/src/use_case/system.rs

@@ -94,5 +94,12 @@ fn map_system_error(error: SystemOperationError) -> AdminError {
         SystemOperationErrorKind::Upstream => AdminErrorKind::BadGateway,
         SystemOperationErrorKind::Internal => AdminErrorKind::Internal,
     };
-    AdminError::new(kind, error.message())
+    let message = match kind {
+        AdminErrorKind::Invalid => "系统操作请求不合法",
+        AdminErrorKind::Conflict => "系统当前状态不允许执行该操作",
+        AdminErrorKind::BadGateway => "系统更新服务请求失败",
+        AdminErrorKind::Internal => "系统操作失败",
+        _ => "系统操作失败",
+    };
+    AdminError::new(kind, message)
 }

backend/crates/gateway-admin/src/use_case/xai.rs

@@ -11,8 +11,8 @@ use crate::{
         provider_credentials::{
             AuthorizationStarted, CompleteAuthorization, CredentialDeletion,
             CredentialDeletionResult, CredentialImportCommit, CredentialImportResult,
-            CredentialListQuery, CredentialMutation, CredentialMutationResult, CredentialPage,
-            ImportCredentials, PrepareCredentialImport, ProviderQuotaRequest, StartAuthorization,
+            CredentialListQuery, CredentialMutationResult, CredentialPage, ImportCredentials,
+            PrepareCredentialImport, ProviderQuotaRequest, StartAuthorization,
         },
     },
     ports::{provider::ProviderAdmin, store::AccountStore},
@@ -20,8 +20,8 @@ use crate::{
 
 use super::{
     commit_authorization, delete_credentials, map_provider_error, map_store_error,
-    pending_authorization, publish_committed, set_credential_enabled,
-    validate_authorization_commit, validate_prepared_import,
+    pending_authorization, publish_committed, validate_authorization_commit,
+    validate_prepared_import,
 };
 
 /// xAI 固定管理路由消费的服务。
@@ -40,14 +40,6 @@ pub trait XaiService: Send + Sync {
         &self,
         command: CompleteAuthorization,
     ) -> Result<CredentialMutationResult, AdminError>;
-    async fn enable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError>;
-    async fn disable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError>;
     async fn delete(
         &self,
         command: CredentialDeletion,
@@ -89,7 +81,6 @@ impl XaiService for DefaultXaiService {
         command: ImportCredentials,
     ) -> Result<CredentialImportResult, AdminError> {
         let context = command.context;
-        let expected_config_revision = command.expected_config_revision;
         let prepared = self
             .provider
             .prepare_import(PrepareCredentialImport {
@@ -104,13 +95,7 @@ impl XaiService for DefaultXaiService {
         )?;
         let result = self
             .accounts
-            .commit_credential_import(
-                CredentialImportCommit {
-                    expected_config_revision,
-                    prepared,
-                },
-                &context,
-            )
+            .commit_credential_import(CredentialImportCommit { prepared }, &context)
             .await
             .map_err(|error| map_store_error(error, "xAI credential import"))?;
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
@@ -155,12 +140,13 @@ impl XaiService for DefaultXaiService {
             .complete_authorization(command)
             .await
             .map_err(|error| map_provider_error(error, "xAI authorization"))?;
-        validate_authorization_commit(
+        let prepared = validate_authorization_commit(
             self.provider.provider_kind(),
             &context,
-            &prepared,
+            prepared,
             "xAI authorization",
-        )?;
+        )
+        .await?;
         let result = commit_authorization(
             self.accounts.as_ref(),
             prepared,
@@ -172,38 +158,6 @@ impl XaiService for DefaultXaiService {
         Ok(result)
     }
 
-    async fn enable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError> {
-        let result = set_credential_enabled(
-            self.accounts.as_ref(),
-            self.provider.as_ref(),
-            command,
-            true,
-            "xAI credential",
-        )
-        .await?;
-        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        Ok(result)
-    }
-
-    async fn disable(
-        &self,
-        command: CredentialMutation,
-    ) -> Result<CredentialMutationResult, AdminError> {
-        let result = set_credential_enabled(
-            self.accounts.as_ref(),
-            self.provider.as_ref(),
-            command,
-            false,
-            "xAI credential",
-        )
-        .await?;
-        publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
-        Ok(result)
-    }
-
     async fn delete(
         &self,
         command: CredentialDeletion,

backend/crates/gateway-admin/tests/backup/mod.rs

@@ -0,0 +1,5 @@
+//! 备份模块测试：镜像 src/backup/ 的 policy 与 task。
+
+mod policy;
+pub mod support;
+mod task;

backend/crates/gateway-admin/tests/backup/policy.rs

@@ -0,0 +1,171 @@
+//! 备份调度与保留策略（backup/policy.rs）的纯逻辑测试。
+
+use chrono::{Duration, TimeZone as _, Utc};
+
+use gateway_admin::{
+    backup::policy::{BackupSchedule, RetentionReason, decide_retention},
+    model::backup::{BackupRecord, BackupStatus, BackupTriggerKind},
+};
+
+fn record(
+    id: &str,
+    trigger: BackupTriggerKind,
+    status: BackupStatus,
+    created_at: chrono::DateTime<Utc>,
+    completed_at: Option<chrono::DateTime<Utc>>,
+) -> BackupRecord {
+    BackupRecord {
+        id: id.to_owned(),
+        trigger_kind: trigger,
+        status,
+        scheduled_at: if trigger == BackupTriggerKind::Scheduled {
+            Some(created_at)
+        } else {
+            None
+        },
+        object_key: format!("k/{id}"),
+        size_bytes: Some(1),
+        sha256: Some("a".repeat(64)),
+        attempt_count: 0,
+        error_code: None,
+        error_message: None,
+        started_at: Some(created_at),
+        completed_at,
+        expires_at: None,
+        created_at,
+        updated_at: created_at,
+    }
+}
+
+#[test]
+fn parse_rejects_bad_cron_and_timezone() {
+    assert!(BackupSchedule::parse("61 * * * *", "Asia/Shanghai").is_err());
+    assert!(BackupSchedule::parse("0 2 * * *", "Not/AZone").is_err());
+    assert!(BackupSchedule::parse("0 2 * * *", "Asia/Shanghai").is_ok());
+}
+
+#[test]
+fn next_after_is_strictly_later() {
+    let schedule = BackupSchedule::parse("0 2 * * *", "Asia/Shanghai").unwrap();
+    let at = Utc.with_ymd_and_hms(2026, 8, 1, 18, 0, 0).unwrap();
+    let next = schedule.next_after(at).unwrap();
+    assert_eq!(next, Utc.with_ymd_and_hms(2026, 8, 2, 18, 0, 0).unwrap());
+}
+
+#[test]
+fn last_firing_is_at_or_before() {
+    let schedule = BackupSchedule::parse("0 2 * * *", "Asia/Shanghai").unwrap();
+    // 北京时间 02:00 = 前一日 18:00 UTC。
+    let before = Utc.with_ymd_and_hms(2026, 8, 1, 17, 59, 0).unwrap();
+    assert_eq!(
+        schedule.last_firing_at_or_before(before).unwrap(),
+        Utc.with_ymd_and_hms(2026, 7, 31, 18, 0, 0).unwrap()
+    );
+    let exact = Utc.with_ymd_and_hms(2026, 8, 1, 18, 0, 0).unwrap();
+    assert_eq!(schedule.last_firing_at_or_before(exact).unwrap(), exact);
+    let after = Utc.with_ymd_and_hms(2026, 8, 1, 19, 0, 0).unwrap();
+    assert_eq!(schedule.last_firing_at_or_before(after).unwrap(), exact);
+}
+
+#[test]
+fn dst_spring_forward_skips_missing_hour() {
+    let schedule = BackupSchedule::parse("30 2 * * *", "America/New_York").unwrap();
+    let at = Utc.with_ymd_and_hms(2026, 3, 8, 6, 29, 0).unwrap(); // 01:29 EST
+    let next = schedule.next_after(at).unwrap();
+    assert_eq!(next, Utc.with_ymd_and_hms(2026, 3, 9, 6, 30, 0).unwrap());
+    let at_after_spring = Utc.with_ymd_and_hms(2026, 3, 8, 10, 0, 0).unwrap(); // 06:00 EDT
+    let last = schedule.last_firing_at_or_before(at_after_spring).unwrap();
+    assert_eq!(last, Utc.with_ymd_and_hms(2026, 3, 7, 7, 30, 0).unwrap());
+}
+
+#[test]
+fn retention_count_keeps_newest_n() {
+    let now = Utc::now();
+    let base = now - Duration::days(10);
+    let records = vec![
+        record(
+            "newest",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            base + Duration::days(2),
+            Some(base + Duration::days(2)),
+        ),
+        record(
+            "middle",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            base + Duration::days(1),
+            Some(base + Duration::days(1)),
+        ),
+        record(
+            "oldest",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            base,
+            Some(base),
+        ),
+    ];
+    let decisions = decide_retention(0, 2, now, &records);
+    let ids: Vec<_> = decisions.iter().map(|d| d.record_id.as_str()).collect();
+    assert_eq!(ids, vec!["oldest"]);
+    assert_eq!(decisions[0].reason, RetentionReason::Count);
+}
+
+#[test]
+fn retention_days_deletes_old_scheduled_but_keeps_newest() {
+    let now = Utc::now();
+    let records = vec![
+        record(
+            "recent",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            now - Duration::days(1),
+            Some(now - Duration::days(1)),
+        ),
+        record(
+            "ancient",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            now - Duration::days(40),
+            Some(now - Duration::days(40)),
+        ),
+    ];
+    let decisions = decide_retention(30, 0, now, &records);
+    let ids: Vec<_> = decisions.iter().map(|d| d.record_id.as_str()).collect();
+    assert_eq!(ids, vec!["ancient"]);
+}
+
+#[test]
+fn newest_scheduled_never_auto_deleted_even_when_ancient() {
+    let now = Utc::now();
+    let records = vec![record(
+        "sole",
+        BackupTriggerKind::Scheduled,
+        BackupStatus::Completed,
+        now - Duration::days(400),
+        Some(now - Duration::days(400)),
+    )];
+    assert!(decide_retention(30, 1, now, &records).is_empty());
+}
+
+#[test]
+fn disabled_thresholds_delete_nothing() {
+    let now = Utc::now();
+    let records = vec![
+        record(
+            "newest",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            now - Duration::days(2),
+            Some(now - Duration::days(2)),
+        ),
+        record(
+            "old",
+            BackupTriggerKind::Scheduled,
+            BackupStatus::Completed,
+            now - Duration::days(90),
+            Some(now - Duration::days(90)),
+        ),
+    ];
+    assert!(decide_retention(0, 0, now, &records).is_empty());
+}

backend/crates/gateway-admin/tests/backup/support.rs

@@ -0,0 +1,664 @@
+//! 备份测试共享 fixture：内存 fake 端口与辅助函数。
+//!
+//! 用内存 fake 端口驱动编排层，不依赖 MinIO/真实 S3。
+//! s3.rs / pg_dump.rs 是 SDK 薄适配器，协议正确性交给 aws-sdk / pg_dump 保证。
+//! 供 backup::task 与 use_case::backup 的测试复用。
+
+use std::sync::Mutex;
+
+use async_trait::async_trait;
+use chrono::{DateTime, Utc};
+use gateway_admin::{
+    model::{
+        MutationActor, MutationContext, Revision,
+        auth::AdminAuditEvent,
+        backup::{
+            BackupError, BackupObjectMetadata, BackupRecord, BackupRecordListQuery,
+            BackupRecordPage, BackupRecordSeed, BackupSettings, BackupStatus, BackupStorageConfig,
+            BackupTriggerKind, ConnectionTestResult, UpdateBackupScheduleCommand,
+            UpdateBackupStorageCommand,
+        },
+    },
+    ports::{
+        backup::{
+            BackupObjectStorePort, BackupRepository, DatabaseDumpPort, DumpArtifact, DumpRequest,
+            StagedArtifact, StatusTransitionUpdate, UploadObjectRequest,
+        },
+        store::{AdminStoreError, AdminStoreErrorKind, AdminStoreResult, AuthStore},
+    },
+};
+use secrecy::SecretString;
+use sha2::{Digest as _, Sha256};
+use tempfile::TempDir;
+
+/// 假归档内容；dump 与上传校验共用同一字节与校验值。
+pub(crate) const DUMP_CONTENT: &[u8] = b"custom-format-archive-bytes-0123456789";
+
+/// 计算一段内容的 SHA-256 十六进制。
+pub(crate) fn sha256_hex(content: &[u8]) -> String {
+    hex::encode(Sha256::digest(content))
+}
+
+/// 返回 32 位十六进制的合法备份记录 id。
+pub(crate) fn backup_id(suffix: &str) -> String {
+    format!("backup_{}", sha256_hex(suffix.as_bytes()))
+}
+
+/// 已配置且已通过连接测试的设置快照。
+pub(crate) fn configured_settings() -> BackupSettings {
+    let now = Utc::now();
+    BackupSettings {
+        storage_revision: 1,
+        endpoint: Some("https://s3.example.com".to_owned()),
+        region: Some("auto".to_owned()),
+        bucket: Some("backup-bucket".to_owned()),
+        access_key_id: Some("ak".to_owned()),
+        secret_access_key: Some(SecretString::from("sk-value")),
+        prefix: Some("codex".to_owned()),
+        force_path_style: false,
+        schedule_enabled: false,
+        cron_expression: None,
+        schedule_timezone: None,
+        retention_days: 0,
+        retention_count: 0,
+        next_run_at: None,
+        last_verified_at: Some(now),
+        updated_at: now,
+    }
+}
+
+/// 从 seed 构造 queued 记录。
+pub(crate) fn queued_record(seed: &BackupRecordSeed) -> BackupRecord {
+    let now = Utc::now();
+    BackupRecord {
+        id: seed.id.clone(),
+        trigger_kind: seed.trigger_kind,
+        status: BackupStatus::Queued,
+        scheduled_at: seed.scheduled_at,
+        object_key: seed.object_key.clone(),
+        size_bytes: None,
+        sha256: None,
+        attempt_count: 0,
+        error_code: None,
+        error_message: None,
+        started_at: None,
+        completed_at: None,
+        expires_at: seed.expires_at,
+        created_at: now,
+        updated_at: now,
+    }
+}
+
+/// 内存版备份仓储。
+pub(crate) struct FakeBackupRepository {
+    settings: Mutex<BackupSettings>,
+    records: Mutex<Vec<BackupRecord>>,
+}
+
+impl FakeBackupRepository {
+    pub(crate) fn new(settings: BackupSettings) -> Self {
+        Self {
+            settings: Mutex::new(settings),
+            records: Mutex::new(Vec::new()),
+        }
+    }
+
+    /// 测试辅助：读取当前全部记录。
+    pub(crate) fn all_records(&self) -> Vec<BackupRecord> {
+        self.records.lock().expect("records").clone()
+    }
+
+    /// 测试辅助：强制把一条记录标记为指定时间完成的 completed。
+    pub(crate) fn set_completed(&self, id: &str, completed_at: DateTime<Utc>) {
+        let mut records = self.records.lock().expect("records");
+        if let Some(record) = records.iter_mut().find(|record| record.id == id) {
+            record.status = BackupStatus::Completed;
+            record.completed_at = Some(completed_at);
+            record.updated_at = Utc::now();
+        }
+    }
+
+    /// 测试辅助：强制把一条记录迁移到指定状态。
+    pub(crate) fn force_status(&self, id: &str, status: BackupStatus) {
+        let mut records = self.records.lock().expect("records");
+        if let Some(record) = records.iter_mut().find(|record| record.id == id) {
+            record.status = status;
+            if matches!(status, BackupStatus::Completed | BackupStatus::Failed) {
+                record.completed_at = Some(Utc::now());
+            }
+            record.updated_at = Utc::now();
+        }
+    }
+}
+
+#[async_trait]
+impl BackupRepository for FakeBackupRepository {
+    async fn load_settings(&self) -> AdminStoreResult<BackupSettings> {
+        Ok(self.settings.lock().expect("settings").clone())
+    }
+
+    async fn update_storage_settings(
+        &self,
+        command: UpdateBackupStorageCommand,
+        _context: &MutationContext,
+    ) -> AdminStoreResult<(BackupSettings, Revision)> {
+        let mut settings = self.settings.lock().expect("settings");
+        settings.storage_revision += 1;
+        settings.endpoint = Some(command.endpoint);
+        settings.region = Some(command.region);
+        settings.bucket = Some(command.bucket);
+        settings.access_key_id = Some(command.access_key_id);
+        if let Some(secret) = command.secret_access_key {
+            settings.secret_access_key = Some(secret);
+        }
+        settings.prefix = Some(command.prefix);
+        settings.force_path_style = command.force_path_style;
+        settings.last_verified_at = None;
+        settings.updated_at = Utc::now();
+        let revision = Revision::new(settings.storage_revision).map_err(|_| {
+            AdminStoreError::new(AdminStoreErrorKind::Invalid, "backup", "zero revision")
+        })?;
+        Ok((settings.clone(), revision))
+    }
+
+    async fn update_schedule_settings(
+        &self,
+        command: UpdateBackupScheduleCommand,
+        next_run_at: Option<DateTime<Utc>>,
+        _context: &MutationContext,
+    ) -> AdminStoreResult<BackupSettings> {
+        let mut settings = self.settings.lock().expect("settings");
+        settings.schedule_enabled = command.schedule_enabled;
+        settings.cron_expression = Some(command.cron_expression);
+        settings.schedule_timezone = Some(command.schedule_timezone);
+        settings.retention_days = command.retention_days;
+        settings.retention_count = command.retention_count;
+        settings.next_run_at = next_run_at;
+        settings.updated_at = Utc::now();
+        Ok(settings.clone())
+    }
+
+    async fn record_verification(
+        &self,
+        storage_revision: u64,
+        at: DateTime<Utc>,
+    ) -> AdminStoreResult<bool> {
+        let mut settings = self.settings.lock().expect("settings");
+        if settings.storage_revision != storage_revision {
+            return Ok(false);
+        }
+        settings.last_verified_at = Some(at);
+        Ok(true)
+    }
+
+    async fn insert_backup_record(&self, seed: BackupRecordSeed) -> AdminStoreResult<BackupRecord> {
+        let mut records = self.records.lock().expect("records");
+        if records.iter().any(|record| record.status.is_active()) {
+            return Err(AdminStoreError::new(
+                AdminStoreErrorKind::Conflict,
+                "backup record",
+                "an active backup task already exists",
+            ));
+        }
+        let record = queued_record(&seed);
+        records.push(record.clone());
+        Ok(record)
+    }
+
+    async fn insert_scheduled_record(&self, seed: BackupRecordSeed) -> AdminStoreResult<bool> {
+        let mut records = self.records.lock().expect("records");
+        if records.iter().any(|record| record.status.is_active())
+            || records.iter().any(|record| {
+                record.trigger_kind == BackupTriggerKind::Scheduled
+                    && record.scheduled_at == seed.scheduled_at
+            })
+        {
+            return Ok(false);
+        }
+        records.push(queued_record(&seed));
+        Ok(true)
+    }
+
+    async fn list_backup_records(
+        &self,
+        query: BackupRecordListQuery,
+    ) -> AdminStoreResult<BackupRecordPage> {
+        let records = self.records.lock().expect("records");
+        let mut items = records
+            .iter()
+            .filter(|record| {
+                query.status.is_none_or(|status| record.status == status)
+                    && query
+                        .trigger
+                        .is_none_or(|trigger| record.trigger_kind == trigger)
+            })
+            .cloned()
+            .collect::<Vec<_>>();
+        items.sort_by(|a, b| {
+            b.created_at
+                .cmp(&a.created_at)
+                .then_with(|| b.id.cmp(&a.id))
+        });
+        let total = items.len() as u64;
+        let offset =
+            (u64::from(query.page.saturating_sub(1)) * u64::from(query.page_size.get())) as usize;
+        let limit = usize::from(query.page_size.get());
+        items = items.into_iter().skip(offset).take(limit).collect();
+        Ok(BackupRecordPage {
+            items,
+            total,
+            page: query.page,
+            page_size: query.page_size,
+        })
+    }
+
+    async fn load_backup_record(&self, id: &str) -> AdminStoreResult<Option<BackupRecord>> {
+        Ok(self
+            .records
+            .lock()
+            .expect("records")
+            .iter()
+            .find(|record| record.id == id)
+            .cloned())
+    }
+
+    async fn list_intermediate_records(&self) -> AdminStoreResult<Vec<BackupRecord>> {
+        Ok(self
+            .records
+            .lock()
+            .expect("records")
+            .iter()
+            .filter(|record| {
+                matches!(
+                    record.status,
+                    BackupStatus::Dumping | BackupStatus::Uploading
+                )
+            })
+            .cloned()
+            .collect())
+    }
+
+    async fn list_pending_deletions(&self, _limit: u32) -> AdminStoreResult<Vec<BackupRecord>> {
+        Ok(self
+            .records
+            .lock()
+            .expect("records")
+            .iter()
+            .filter(|record| record.status == BackupStatus::Deleting)
+            .cloned()
+            .collect())
+    }
+
+    async fn list_expired_records(&self, _limit: u32) -> AdminStoreResult<Vec<BackupRecord>> {
+        let now = Utc::now();
+        Ok(self
+            .records
+            .lock()
+            .expect("records")
+            .iter()
+            .filter(|record| {
+                record
+                    .expires_at
+                    .is_some_and(|expires_at| expires_at <= now)
+                    && matches!(
+                        record.status,
+                        BackupStatus::Completed | BackupStatus::Failed
+                    )
+            })
+            .cloned()
+            .collect())
+    }
+
+    async fn claim_next_queued(
+        &self,
+        now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        let mut records = self.records.lock().expect("records");
+        let Some(record) = records
+            .iter_mut()
+            .find(|record| record.status == BackupStatus::Queued)
+        else {
+            return Ok(None);
+        };
+        record.status = BackupStatus::Dumping;
+        record.started_at = Some(now);
+        record.attempt_count += 1;
+        record.updated_at = now;
+        Ok(Some(record.clone()))
+    }
+
+    async fn transition_status(
+        &self,
+        id: &str,
+        from: BackupStatus,
+        to: BackupStatus,
+        update: StatusTransitionUpdate,
+        now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        let mut records = self.records.lock().expect("records");
+        let Some(record) = records
+            .iter_mut()
+            .find(|record| record.id == id && record.status == from)
+        else {
+            return Ok(None);
+        };
+        record.status = to;
+        if let Some(size) = update.size_bytes {
+            record.size_bytes = Some(size);
+        }
+        if let Some(sha256) = update.sha256 {
+            record.sha256 = Some(sha256);
+        }
+        if let Some(code) = update.error_code {
+            record.error_code = Some(code);
+        }
+        if let Some(message) = update.error_message {
+            record.error_message = Some(message);
+        }
+        record.completed_at = update.completed_at.or_else(|| {
+            matches!(to, BackupStatus::Completed | BackupStatus::Failed).then_some(now)
+        });
+        record.updated_at = now;
+        Ok(Some(record.clone()))
+    }
+
+    async fn transition_to_deleting(
+        &self,
+        id: &str,
+        now: DateTime<Utc>,
+    ) -> AdminStoreResult<Option<BackupRecord>> {
+        let mut records = self.records.lock().expect("records");
+        let Some(record) = records
+            .iter_mut()
+            .find(|record| record.id == id && record.status.can_be_deleted())
+        else {
+            return Ok(None);
+        };
+        record.status = BackupStatus::Deleting;
+        record.updated_at = now;
+        Ok(Some(record.clone()))
+    }
+
+    async fn delete_record(&self, id: &str) -> AdminStoreResult<()> {
+        let mut records = self.records.lock().expect("records");
+        records.retain(|record| record.id != id);
+        Ok(())
+    }
+
+    async fn advance_schedule_cursor(
+        &self,
+        next_run_at: DateTime<Utc>,
+        _expected_cron: &str,
+        _expected_timezone: &str,
+    ) -> AdminStoreResult<bool> {
+        let mut settings = self.settings.lock().expect("settings");
+        settings.next_run_at = Some(next_run_at);
+        Ok(true)
+    }
+
+    async fn list_scheduled_completed_desc(
+        &self,
+        _limit: u32,
+    ) -> AdminStoreResult<Vec<BackupRecord>> {
+        let mut records = self
+            .records
+            .lock()
+            .expect("records")
+            .iter()
+            .filter(|record| {
+                record.trigger_kind == BackupTriggerKind::Scheduled
+                    && record.status == BackupStatus::Completed
+            })
+            .cloned()
+            .collect::<Vec<_>>();
+        records.sort_by(|a, b| {
+            b.completed_at
+                .cmp(&a.completed_at)
+                .then_with(|| b.id.cmp(&a.id))
+        });
+        Ok(records)
+    }
+}
+
+/// 假 `pg_dump` 端口：把固定内容写入临时文件作为归档；可注入失败。
+pub(crate) struct FakeDumpPort {
+    dir: TempDir,
+    fail_dump: bool,
+}
+
+impl FakeDumpPort {
+    pub(crate) fn new() -> Self {
+        Self {
+            dir: tempfile::tempdir().expect("temp dir"),
+            fail_dump: false,
+        }
+    }
+
+    /// 让下一次 `dump` 返回 `backup.pg_dump_failed`。
+    pub(crate) fn fail_next_dump(mut self) -> Self {
+        self.fail_dump = true;
+        self
+    }
+
+    fn artifact(&self, backup_id: &str) -> DumpArtifact {
+        let path = self.dir.path().join(format!("{backup_id}.dump"));
+        std::fs::write(&path, DUMP_CONTENT).expect("write artifact");
+        DumpArtifact {
+            path,
+            size_bytes: DUMP_CONTENT.len() as u64,
+            sha256: sha256_hex(DUMP_CONTENT),
+        }
+    }
+}
+
+#[async_trait]
+impl DatabaseDumpPort for FakeDumpPort {
+    async fn dump(
+        &self,
+        request: DumpRequest,
+    ) -> Result<DumpArtifact, gateway_admin::model::backup::BackupError> {
+        if self.fail_dump {
+            return Err(gateway_admin::model::backup::BackupError::new(
+                gateway_admin::model::backup::code::PG_DUMP_FAILED,
+                "pg_dump failed".to_owned(),
+            ));
+        }
+        if request.cancellation.is_cancelled() {
+            return Err(gateway_admin::model::backup::BackupError::new(
+                gateway_admin::model::backup::code::CANCELLED,
+                "cancelled".to_owned(),
+            ));
+        }
+        Ok(self.artifact(&request.backup_id))
+    }
+
+    async fn inspect_staging(
+        &self,
+        backup_id: &str,
+    ) -> Result<Option<StagedArtifact>, gateway_admin::model::backup::BackupError> {
+        let path = self.dir.path().join(format!("{backup_id}.dump"));
+        if !path.exists() {
+            return Ok(None);
+        }
+        Ok(Some(StagedArtifact {
+            path,
+            size_bytes: DUMP_CONTENT.len() as u64,
+            sha256: sha256_hex(DUMP_CONTENT),
+        }))
+    }
+
+    async fn cleanup_staging(
+        &self,
+        _backup_id: &str,
+    ) -> Result<(), gateway_admin::model::backup::BackupError> {
+        Ok(())
+    }
+}
+
+/// 内存版对象存储：把上传内容按 key 保存并支持 Head/Delete/预签名。
+pub(crate) struct FakeObjectStore {
+    pub(crate) objects: Mutex<std::collections::HashMap<String, Vec<u8>>>,
+    upload_error: Option<BackupError>,
+}
+
+impl FakeObjectStore {
+    pub(crate) fn new() -> Self {
+        Self {
+            objects: Mutex::new(std::collections::HashMap::new()),
+            upload_error: None,
+        }
+    }
+
+    /// 让上传返回指定的脱敏 S3 错误。
+    pub(crate) fn fail_upload(mut self, code: &'static str, message: impl Into<String>) -> Self {
+        self.upload_error = Some(BackupError::new(code, message.into()));
+        self
+    }
+
+    pub(crate) fn object(&self, key: &str) -> Option<Vec<u8>> {
+        self.objects.lock().expect("objects").get(key).cloned()
+    }
+}
+
+#[async_trait]
+impl BackupObjectStorePort for FakeObjectStore {
+    async fn test_connection(
+        &self,
+        _config: &BackupStorageConfig,
+    ) -> Result<ConnectionTestResult, gateway_admin::model::backup::BackupError> {
+        Ok(ConnectionTestResult {
+            ok: true,
+            stage: "deleteObject",
+            code: None,
+            message: "连接测试成功".to_owned(),
+        })
+    }
+
+    async fn upload_file(
+        &self,
+        _config: &BackupStorageConfig,
+        request: UploadObjectRequest,
+    ) -> Result<(), gateway_admin::model::backup::BackupError> {
+        if let Some(error) = &self.upload_error {
+            return Err(error.clone());
+        }
+        let content = std::fs::read(&request.source).map_err(|_| {
+            gateway_admin::model::backup::BackupError::new(
+                gateway_admin::model::backup::code::S3_UPLOAD_FAILED,
+                "read source".to_owned(),
+            )
+        })?;
+        self.objects
+            .lock()
+            .expect("objects")
+            .insert(request.object_key, content);
+        Ok(())
+    }
+
+    async fn head_object(
+        &self,
+        _config: &BackupStorageConfig,
+        object_key: &str,
+    ) -> Result<Option<BackupObjectMetadata>, gateway_admin::model::backup::BackupError> {
+        let Some(content) = self.object(object_key) else {
+            return Ok(None);
+        };
+        Ok(Some(BackupObjectMetadata::new(
+            "backup-test".to_owned(),
+            sha256_hex(&content),
+            Utc::now(),
+            content.len() as u64,
+        )))
+    }
+
+    async fn delete_object(
+        &self,
+        _config: &BackupStorageConfig,
+        object_key: &str,
+    ) -> Result<(), gateway_admin::model::backup::BackupError> {
+        self.objects.lock().expect("objects").remove(object_key);
+        Ok(())
+    }
+
+    async fn presigned_download(
+        &self,
+        _config: &BackupStorageConfig,
+        object_key: &str,
+        _file_name: &str,
+        _ttl: std::time::Duration,
+    ) -> Result<String, gateway_admin::model::backup::BackupError> {
+        Ok(format!("https://presigned.example.com/{object_key}"))
+    }
+}
+
+/// 记录审计事件的假 AuthStore。
+pub(crate) struct FakeAuthStore {
+    audit: Mutex<Vec<AdminAuditEvent>>,
+}
+
+impl FakeAuthStore {
+    pub(crate) fn new() -> Self {
+        Self {
+            audit: Mutex::new(Vec::new()),
+        }
+    }
+
+    pub(crate) fn audit_actions(&self) -> Vec<String> {
+        self.audit
+            .lock()
+            .expect("audit")
+            .iter()
+            .map(|event| event.action.clone())
+            .collect()
+    }
+}
+
+#[async_trait]
+impl AuthStore for FakeAuthStore {
+    async fn load_password_hash(&self, _admin_user_id: &str) -> AdminStoreResult<Option<String>> {
+        Ok(None)
+    }
+    async fn create_password_hash_if_absent(
+        &self,
+        _admin_user_id: &str,
+        _password_hash: &str,
+    ) -> AdminStoreResult<bool> {
+        Ok(true)
+    }
+    async fn load_admin_api_key(
+        &self,
+    ) -> AdminStoreResult<Option<gateway_admin::model::settings::AdminApiKey>> {
+        Ok(None)
+    }
+    async fn load_session(
+        &self,
+        _session_id: &str,
+    ) -> AdminStoreResult<Option<gateway_admin::model::auth::AdminSession>> {
+        Ok(None)
+    }
+    async fn store_session(
+        &self,
+        _session_id: &str,
+        _session: &gateway_admin::model::auth::AdminSession,
+    ) -> AdminStoreResult<()> {
+        Ok(())
+    }
+    async fn delete_session(
+        &self,
+        _session_id: &str,
+    ) -> AdminStoreResult<Option<gateway_admin::model::auth::AdminSession>> {
+        Ok(None)
+    }
+    async fn append_audit_event(&self, event: AdminAuditEvent) -> AdminStoreResult<()> {
+        self.audit.lock().expect("audit").push(event);
+        Ok(())
+    }
+}
+
+/// 系统发起者上下文。
+pub(crate) fn system_context() -> MutationContext {
+    MutationContext {
+        actor: MutationActor::System,
+        request_id: "backup-runtime-test".to_owned(),
+    }
+}

backend/crates/gateway-admin/tests/backup/task.rs

@@ -0,0 +1,237 @@
+//! BackupTask 执行链测试：驱动内存 fake 端口跑完整 dump/upload/verify/retention 流程。
+
+use std::sync::Arc;
+
+use chrono::{Duration, Utc};
+use gateway_admin::{
+    backup::task::BackupTask,
+    model::backup::{
+        BackupRecordSeed, BackupStatus, BackupTriggerKind, UpdateBackupScheduleCommand, code,
+    },
+    ports::backup::{BackupRepository, DatabaseDumpPort, DumpRequest},
+};
+use gateway_core::engine::CancellationToken;
+
+use super::support::{
+    DUMP_CONTENT, FakeBackupRepository, FakeDumpPort, FakeObjectStore, backup_id,
+    configured_settings, sha256_hex, system_context,
+};
+
+#[tokio::test]
+async fn backup_task_runs_full_dump_upload_verify_pipeline() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store = Arc::new(FakeObjectStore::new());
+
+    let seed = BackupRecordSeed {
+        id: backup_id("manual"),
+        trigger_kind: BackupTriggerKind::Manual,
+        scheduled_at: None,
+        object_key: "codex/2026/08/01/manual.dump".to_owned(),
+        expires_at: None,
+    };
+    repository
+        .insert_backup_record(seed.clone())
+        .await
+        .expect("insert queued");
+
+    let task = BackupTask::new(repository.clone(), dump.clone(), object_store.clone());
+    task.run_cycle(&CancellationToken::new())
+        .await
+        .expect("run cycle");
+
+    let records = repository.all_records();
+    assert_eq!(records.len(), 1);
+    let finished = &records[0];
+    assert_eq!(finished.status, BackupStatus::Completed);
+    assert_eq!(finished.size_bytes, Some(DUMP_CONTENT.len() as u64));
+    assert_eq!(
+        finished.sha256.as_deref(),
+        Some(sha256_hex(DUMP_CONTENT).as_str())
+    );
+
+    // 对象已上传且内容与本地归档一致。
+    let stored = object_store
+        .object(&seed.object_key)
+        .expect("uploaded object exists");
+    assert_eq!(stored.as_slice(), DUMP_CONTENT);
+}
+
+#[tokio::test]
+async fn backup_task_marks_failed_when_dump_port_fails() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new().fail_next_dump());
+    let object_store = Arc::new(FakeObjectStore::new());
+
+    let seed = BackupRecordSeed {
+        id: backup_id("fail"),
+        trigger_kind: BackupTriggerKind::Manual,
+        scheduled_at: None,
+        object_key: "codex/2026/08/01/fail.dump".to_owned(),
+        expires_at: None,
+    };
+    repository
+        .insert_backup_record(seed.clone())
+        .await
+        .expect("insert queued");
+
+    let task = BackupTask::new(repository.clone(), dump.clone(), object_store.clone());
+    task.run_cycle(&CancellationToken::new())
+        .await
+        .expect("run cycle");
+
+    let records = repository.all_records();
+    let failed = &records[0];
+    assert_eq!(failed.status, BackupStatus::Failed);
+    assert_eq!(failed.error_code.as_deref(), Some("backup.pg_dump_failed"));
+    assert!(failed.completed_at.is_some());
+    // 归档未上传，对象不存在。
+    assert!(object_store.object(&seed.object_key).is_none());
+}
+
+#[tokio::test]
+async fn backup_task_marks_failed_with_the_upload_error() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store =
+        Arc::new(FakeObjectStore::new().fail_upload(code::S3_UPLOAD_FAILED, "对象存储拒绝上传"));
+    let seed = BackupRecordSeed {
+        id: backup_id("upload-failure"),
+        trigger_kind: BackupTriggerKind::Manual,
+        scheduled_at: None,
+        object_key: "codex/2026/08/01/upload-failure.dump".to_owned(),
+        expires_at: None,
+    };
+    repository
+        .insert_backup_record(seed.clone())
+        .await
+        .expect("insert queued");
+
+    let task = BackupTask::new(repository.clone(), dump, object_store);
+    task.run_cycle(&CancellationToken::new())
+        .await
+        .expect("run cycle");
+
+    let records = repository.all_records();
+    let failed = &records[0];
+    assert_eq!(failed.status, BackupStatus::Failed);
+    assert_eq!(failed.error_code.as_deref(), Some(code::S3_UPLOAD_FAILED));
+    assert_eq!(
+        failed.error_message.as_deref(),
+        Some("上传到对象存储失败：对象存储拒绝上传")
+    );
+}
+
+#[tokio::test]
+async fn backup_task_recovery_marks_failed_with_the_upload_error() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store =
+        Arc::new(FakeObjectStore::new().fail_upload(code::S3_UPLOAD_FAILED, "对象存储拒绝上传"));
+    let seed = BackupRecordSeed {
+        id: backup_id("recovered-upload-failure"),
+        trigger_kind: BackupTriggerKind::Manual,
+        scheduled_at: None,
+        object_key: "codex/2026/08/01/recovered-upload-failure.dump".to_owned(),
+        expires_at: None,
+    };
+    repository
+        .insert_backup_record(seed.clone())
+        .await
+        .expect("insert queued");
+    let cancellation = CancellationToken::new();
+    dump.dump(DumpRequest {
+        backup_id: seed.id.clone(),
+        cancellation: cancellation.clone(),
+    })
+    .await
+    .expect("stage dump");
+    repository.force_status(&seed.id, BackupStatus::Dumping);
+
+    let task = BackupTask::new(repository.clone(), dump, object_store);
+    task.run_cycle(&cancellation).await.expect("run cycle");
+
+    let records = repository.all_records();
+    let failed = &records[0];
+    assert_eq!(failed.status, BackupStatus::Failed);
+    assert_eq!(failed.error_code.as_deref(), Some(code::S3_UPLOAD_FAILED));
+    assert_eq!(
+        failed.error_message.as_deref(),
+        Some("上传到对象存储失败：对象存储拒绝上传")
+    );
+}
+
+#[tokio::test]
+async fn retention_cleans_expired_scheduled_backups() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store = Arc::new(FakeObjectStore::new());
+
+    // 造一条旧 completed 计划备份（超过 retention_days）与一条新备份。
+    let old_seed = BackupRecordSeed {
+        id: backup_id("old"),
+        trigger_kind: BackupTriggerKind::Scheduled,
+        scheduled_at: Some(Utc::now() - Duration::days(40)),
+        object_key: "codex/2026/06/01/old.dump".to_owned(),
+        expires_at: None,
+    };
+    let new_seed = BackupRecordSeed {
+        id: backup_id("new"),
+        trigger_kind: BackupTriggerKind::Scheduled,
+        scheduled_at: Some(Utc::now() - Duration::days(1)),
+        object_key: "codex/2026/07/01/new.dump".to_owned(),
+        expires_at: None,
+    };
+    repository
+        .insert_scheduled_record(old_seed.clone())
+        .await
+        .expect("insert old");
+    // 旧备份 40 天前完成（释放活跃名额），再插入新备份。
+    let now = Utc::now();
+    repository.set_completed(&backup_id("old"), now - Duration::days(40));
+    repository
+        .insert_scheduled_record(new_seed.clone())
+        .await
+        .expect("insert new");
+    // 新备份 1 天前完成。
+    repository.set_completed(&backup_id("new"), now - Duration::days(1));
+    // 两个对象都已上传。
+    object_store
+        .objects
+        .lock()
+        .expect("objects")
+        .insert(old_seed.object_key.clone(), DUMP_CONTENT.to_vec());
+    object_store
+        .objects
+        .lock()
+        .expect("objects")
+        .insert(new_seed.object_key.clone(), DUMP_CONTENT.to_vec());
+
+    // 设置 retention_days = 30。
+    repository
+        .update_schedule_settings(
+            UpdateBackupScheduleCommand {
+                schedule_enabled: false,
+                cron_expression: "0 2 * * *".to_owned(),
+                schedule_timezone: "Asia/Shanghai".to_owned(),
+                retention_days: 30,
+                retention_count: 0,
+            },
+            None,
+            &system_context(),
+        )
+        .await
+        .expect("set retention");
+
+    let task = BackupTask::new(repository.clone(), dump.clone(), object_store.clone());
+    task.run_cycle(&CancellationToken::new())
+        .await
+        .expect("run cycle");
+
+    // 旧备份被硬删除，对象被删除；新备份保留。
+    let records = repository.all_records();
+    let ids: Vec<_> = records.iter().map(|record| record.id.as_str()).collect();
+    assert_eq!(ids, vec![backup_id("new").as_str()]);
+    assert!(object_store.object(&old_seed.object_key).is_none());
+    assert!(object_store.object(&new_seed.object_key).is_some());
+}

backend/crates/gateway-admin/tests/main.rs

@@ -6,17 +6,21 @@ use gateway_core::engine::credential::OpaqueProviderData;
 use gateway_admin::{
     model::{
         PageSize, Revision,
+        accounts::AccountUsage,
         auth::LoginCommand,
         client_keys::ClientKeyPageSize,
         observability::{DecimalAmount, RequestOutcome, TimeRange},
         provider_credentials::{
             CredentialCommitGuard, ProviderDocument, ProviderQuota, ProviderQuotaWindow,
+            QuotaLocalUsageAttribution,
         },
         settings::AdminApiKey,
     },
     ports::store::{AccountStore, AuthStore, ClientKeyStore, ObservabilityStore, SettingsStore},
 };
 
+mod backup;
+mod model;
 mod use_case;
 
 #[test]
@@ -87,7 +91,6 @@ fn login_command_debug_should_redact_password() {
     let command = LoginCommand {
         username: None,
         password: "secret-password".to_owned(),
-        source: "127.0.0.1".to_owned(),
     };
     assert!(!format!("{command:?}").contains("secret-password"));
 }
@@ -126,12 +129,122 @@ fn representative_quota_should_prefer_short_window_and_highest_usage() {
             quota_window("shortTerm", Some(18_000), Some(30.0)),
             quota_window("shortTerm", Some(14_400), Some(45.0)),
         ],
+        limit_reached: false,
         provider_data: None,
     };
 
     assert_eq!(quota.representative_used_percent(), Some(45.0));
 }
 
+#[test]
+fn representative_quota_should_prefer_account_wide_window_over_model_specific_window() {
+    let mut model_specific = quota_window("shortTerm", Some(18_000), Some(64.0));
+    model_specific.local_usage_attribution = QuotaLocalUsageAttribution::Unavailable;
+    let quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: vec![
+            model_specific,
+            quota_window("shortTerm", Some(604_800), Some(5.0)),
+        ],
+        limit_reached: false,
+        provider_data: None,
+    };
+
+    assert_eq!(quota.representative_used_percent(), Some(5.0));
+}
+
+#[test]
+fn representative_window_usage_should_accept_account_wide_rolling_window_without_reset() {
+    let usage = AccountUsage {
+        account_id: "acct_xai".to_owned(),
+        request_count: 5,
+        success_count: 5,
+        input_tokens: Some(100),
+        output_tokens: Some(20),
+        cached_tokens: Some(80),
+        cache_write_tokens: Some(0),
+        reasoning_tokens: Some(0),
+        image_input_tokens: Some(0),
+        image_output_tokens: Some(0),
+        image_request_count: 0,
+        image_request_failed_count: 0,
+        total_tokens: Some(120),
+        cost_coverage: Default::default(),
+        costs: Vec::new(),
+        last_used_at: Some(Utc::now()),
+        request_buckets: Vec::new(),
+        models: Vec::new(),
+    };
+    let quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: vec![ProviderQuotaWindow {
+            key: "free-rolling-24h".to_owned(),
+            group: "shortTerm".to_owned(),
+            label: "日限额".to_owned(),
+            limit_id: None,
+            limit_name: None,
+            role: None,
+            local_usage_attribution: QuotaLocalUsageAttribution::AccountWide,
+            window_seconds: Some(86_400),
+            used_percent: None,
+            reset_at: None,
+            limit_reached: false,
+            local_usage: Some(usage.clone()),
+            provider_data: None,
+        }],
+        limit_reached: false,
+        provider_data: None,
+    };
+
+    assert_eq!(quota.representative_window_usage(), Some(&usage));
+}
+
+#[test]
+fn exhausted_quota_should_project_full_usage_to_only_the_representative_window() {
+    let mut quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: vec![
+            quota_window("monthly", Some(2_592_000), Some(99.0)),
+            quota_window("shortTerm", Some(604_800), Some(80.0)),
+            quota_window("shortTerm", Some(18_000), Some(30.0)),
+            quota_window("shortTerm", Some(14_400), Some(95.0)),
+        ],
+        limit_reached: true,
+        provider_data: None,
+    };
+
+    assert_eq!(quota.representative_used_percent(), Some(100.0));
+    quota.apply_limit_reached_display();
+
+    assert_eq!(quota.windows[0].used_percent, Some(99.0));
+    assert_eq!(quota.windows[1].used_percent, Some(80.0));
+    assert_eq!(quota.windows[2].used_percent, Some(30.0));
+    assert_eq!(quota.windows[3].used_percent, Some(100.0));
+    assert!(quota.windows[3].limit_reached);
+}
+
+#[test]
+fn exhausted_quota_should_preserve_the_provider_identified_reached_window() {
+    let mut reached = quota_window("monthly", Some(2_592_000), Some(98.0));
+    reached.limit_reached = true;
+    let mut quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: vec![reached, quota_window("shortTerm", Some(18_000), Some(95.0))],
+        limit_reached: true,
+        provider_data: None,
+    };
+
+    quota.apply_limit_reached_display();
+
+    assert_eq!(quota.windows[0].used_percent, Some(100.0));
+    assert_eq!(quota.windows[1].used_percent, Some(95.0));
+    assert!(!quota.windows[1].limit_reached);
+}
+
 fn quota_window(
     group: &str,
     window_seconds: Option<u64>,
@@ -141,10 +254,14 @@ fn quota_window(
         key: group.to_owned(),
         group: group.to_owned(),
         label: group.to_owned(),
-        source: None,
+        limit_id: None,
+        limit_name: None,
+        role: None,
+        local_usage_attribution: QuotaLocalUsageAttribution::AccountWide,
         window_seconds,
         used_percent,
         reset_at: None,
+        limit_reached: false,
         local_usage: None,
         provider_data: None,
     }

backend/crates/gateway-admin/tests/model/backup.rs

@@ -0,0 +1,104 @@
+//! 备份领域模型（model/backup.rs）的纯逻辑测试。
+
+use chrono::{TimeZone as _, Utc};
+use secrecy::SecretString;
+
+use gateway_admin::model::backup::{
+    BackupSettings, BackupStatus, BackupStorageConfig, BackupTriggerKind, build_object_key,
+};
+
+#[test]
+fn status_machine_rejects_invalid_transitions() {
+    assert!(BackupStatus::Queued.allows_transition_to(BackupStatus::Dumping));
+    assert!(BackupStatus::Dumping.allows_transition_to(BackupStatus::Uploading));
+    assert!(BackupStatus::Uploading.allows_transition_to(BackupStatus::Completed));
+    assert!(BackupStatus::Completed.allows_transition_to(BackupStatus::Deleting));
+    assert!(!BackupStatus::Queued.allows_transition_to(BackupStatus::Completed));
+    assert!(!BackupStatus::Completed.allows_transition_to(BackupStatus::Dumping));
+    assert!(!BackupStatus::Deleting.allows_transition_to(BackupStatus::Failed));
+    assert!(!BackupStatus::Deleting.allows_transition_to(BackupStatus::Completed));
+}
+
+#[test]
+fn status_classification() {
+    assert!(BackupStatus::Queued.is_active());
+    assert!(BackupStatus::Uploading.is_active());
+    assert!(!BackupStatus::Completed.is_active());
+    assert!(BackupStatus::Completed.can_be_deleted());
+    assert!(BackupStatus::Failed.can_be_deleted());
+    assert!(!BackupStatus::Queued.can_be_deleted());
+}
+
+#[test]
+fn object_key_shape() {
+    let at = Utc.with_ymd_and_hms(2026, 8, 1, 12, 30, 0).unwrap();
+    let key = build_object_key("production/backups", "backup_abc", at).unwrap();
+    assert_eq!(
+        key,
+        "production/backups/2026/08/01/codex-proxy-rs_20260801_123000_abc.dump"
+    );
+}
+
+#[test]
+fn object_key_rejects_dangerous_prefixes() {
+    let at = Utc::now();
+    assert!(build_object_key("/leading", "backup_x", at).is_err());
+    assert!(build_object_key("a/../b", "backup_x", at).is_err());
+    assert!(build_object_key("a\\b", "backup_x", at).is_err());
+    assert!(build_object_key("a\u{0001}b", "backup_x", at).is_err());
+    assert!(build_object_key("", "backup_x", at).is_err());
+    assert!(build_object_key("trailing//", "backup_x", at).is_ok());
+}
+
+#[test]
+fn trigger_and_status_roundtrip() {
+    for status in [
+        BackupStatus::Queued,
+        BackupStatus::Dumping,
+        BackupStatus::Uploading,
+        BackupStatus::Completed,
+        BackupStatus::Failed,
+        BackupStatus::Deleting,
+    ] {
+        assert_eq!(BackupStatus::parse(status.as_str()), Some(status));
+    }
+    assert_eq!(
+        BackupTriggerKind::parse("manual"),
+        Some(BackupTriggerKind::Manual)
+    );
+    assert_eq!(
+        BackupTriggerKind::parse("scheduled"),
+        Some(BackupTriggerKind::Scheduled)
+    );
+    assert_eq!(BackupTriggerKind::parse("unknown"), None);
+    assert_eq!(BackupStatus::parse("skipped"), None);
+    assert_eq!(BackupStatus::parse("deleted"), None);
+    assert_eq!(BackupStatus::parse("unknown"), None);
+}
+
+#[test]
+fn config_from_settings_redacts_secret_in_debug() {
+    let mut settings = BackupSettings {
+        storage_revision: 3,
+        endpoint: Some("https://example.com".to_owned()),
+        region: Some("auto".to_owned()),
+        bucket: Some("b".to_owned()),
+        access_key_id: Some("ak".to_owned()),
+        secret_access_key: Some(SecretString::from("sk-secret")),
+        prefix: Some("p".to_owned()),
+        force_path_style: false,
+        schedule_enabled: false,
+        cron_expression: None,
+        schedule_timezone: None,
+        retention_days: 0,
+        retention_count: 0,
+        next_run_at: None,
+        last_verified_at: None,
+        updated_at: Utc::now(),
+    };
+    assert!(!format!("{:?}", settings).contains("sk-secret"));
+    let config = BackupStorageConfig::from_settings(&settings).unwrap();
+    assert!(!format!("{config:?}").contains("sk-secret"));
+    settings.endpoint = None;
+    assert!(BackupStorageConfig::from_settings(&settings).is_none());
+}

backend/crates/gateway-admin/tests/model/mod.rs

@@ -0,0 +1,3 @@
+//! 模型模块测试：镜像 src/model/ 中带逻辑的模块。
+
+mod backup;

backend/crates/gateway-admin/tests/use_case/account_groups.rs

@@ -0,0 +1,236 @@
+use std::{
+    collections::BTreeMap,
+    str::FromStr as _,
+    sync::{Arc, Mutex},
+};
+
+use async_trait::async_trait;
+use chrono::{Duration, Utc};
+use gateway_admin::{
+    model::{
+        MutationContext, PageSize, Revision,
+        account_groups::{
+            AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupColor,
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+            AccountGroupRecord, AccountGroupUsage, DeleteAccountGroup, NewAccountGroup,
+            SetAccountGroupEnabled, UpdateAccountGroup,
+        },
+        accounts::AccountRuntimeSnapshot,
+        observability::DecimalAmount,
+    },
+    ports::store::{
+        AccountGroupStore, AccountRuntimeStore, AdminStoreError, AdminStoreErrorKind,
+        AdminStoreResult,
+    },
+};
+use gateway_core::{
+    engine::credential::{AccountStatusFacts, CredentialState, QuotaState},
+    routing::AccountGroupId,
+};
+
+use super::AdminHarness;
+
+const GROUP_ID: &str = "grp_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
+
+#[tokio::test]
+async fn group_query_service_enriches_only_current_page_members_with_runtime_facts() {
+    let groups = Arc::new(FakeGroupStore::default());
+    let runtime = Arc::new(FakeRuntimeStore::default());
+    let service = AdminHarness::new()
+        .account_groups(groups.clone())
+        .account_runtime(runtime.clone())
+        .build()
+        .await;
+
+    let page = service
+        .account_groups()
+        .list(AccountGroupListQuery {
+            page: 1,
+            page_size: PageSize::new(20).expect("page size"),
+            search: None,
+            enabled: None,
+        })
+        .await
+        .expect("list projected account groups");
+
+    assert_eq!(
+        groups
+            .requested_groups
+            .lock()
+            .expect("requested groups")
+            .as_slice(),
+        [GROUP_ID]
+    );
+    assert_eq!(
+        runtime
+            .requested_accounts
+            .lock()
+            .expect("requested accounts")
+            .as_slice(),
+        ["acct_available", "acct_limited"]
+    );
+    let group = &page.items[0];
+    assert_eq!(
+        group.account_summary,
+        AccountGroupAccountSummary {
+            available: 1,
+            limited: 1,
+            total: 2,
+        }
+    );
+    assert_eq!(
+        group.capacity,
+        AccountGroupCapacity {
+            used_slots: Some(2),
+            total_slots: 4,
+        }
+    );
+}
+
+#[derive(Default)]
+struct FakeGroupStore {
+    requested_groups: Mutex<Vec<String>>,
+}
+
+#[async_trait]
+impl AccountGroupStore for FakeGroupStore {
+    async fn list_account_groups(
+        &self,
+        query: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupPage> {
+        Ok(AccountGroupPage {
+            config_revision: Revision::new(1).expect("revision"),
+            items: vec![group_record()],
+            total: 1,
+            page: query.page,
+            page_size: query.page_size.get(),
+        })
+    }
+
+    async fn load_account_group_members(
+        &self,
+        group_ids: &[AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>> {
+        *self.requested_groups.lock().expect("requested groups") = group_ids
+            .iter()
+            .map(|group_id| group_id.as_str().to_owned())
+            .collect();
+        Ok(vec![member("acct_available", 4), member("acct_limited", 3)])
+    }
+
+    async fn create_account_group(
+        &self,
+        _: NewAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unused())
+    }
+
+    async fn update_account_group(
+        &self,
+        _: UpdateAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unused())
+    }
+
+    async fn set_account_group_enabled(
+        &self,
+        _: SetAccountGroupEnabled,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unused())
+    }
+
+    async fn delete_account_group(
+        &self,
+        _: DeleteAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unused())
+    }
+}
+
+#[derive(Default)]
+struct FakeRuntimeStore {
+    requested_accounts: Mutex<Vec<String>>,
+}
+
+#[async_trait]
+impl AccountRuntimeStore for FakeRuntimeStore {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot::default())
+    }
+
+    async fn account_runtime(
+        &self,
+        account_ids: &[String],
+    ) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        *self.requested_accounts.lock().expect("requested accounts") = account_ids.to_vec();
+        Ok(AccountRuntimeSnapshot {
+            rate_limited_until: BTreeMap::from([(
+                "acct_limited".to_owned(),
+                Utc::now() + Duration::minutes(5),
+            )]),
+            in_flight: Some(BTreeMap::from([("acct_available".to_owned(), 2)])),
+        })
+    }
+}
+
+fn group_record() -> AccountGroupRecord {
+    let now = Utc::now();
+    AccountGroupRecord {
+        id: group_id(),
+        name: "Primary".to_owned(),
+        description: None,
+        color: AccountGroupColor::parse("#2563EBFF").expect("color"),
+        enabled: true,
+        member_count: 2,
+        provider_counts: BTreeMap::from([("openai".to_owned(), 2)]),
+        client_key_count: 1,
+        account_summary: AccountGroupAccountSummary {
+            available: 0,
+            limited: 0,
+            total: 0,
+        },
+        capacity: AccountGroupCapacity {
+            used_slots: None,
+            total_slots: 0,
+        },
+        usage: AccountGroupUsage {
+            today_usd: DecimalAmount::from_str("1").expect("today usage"),
+            retained_total_usd: DecimalAmount::from_str("3").expect("retained usage"),
+        },
+        created_at: now,
+        updated_at: now,
+    }
+}
+
+fn member(account_id: &str, total_slots: u64) -> AccountGroupMemberFact {
+    AccountGroupMemberFact {
+        group_id: group_id(),
+        account_id: account_id.to_owned(),
+        status: AccountStatusFacts {
+            enabled: true,
+            credential_state: CredentialState::Ready,
+            access_token_expires_at: None,
+            quota: QuotaState::default(),
+            rate_limited_until: None,
+            last_error_reason: None,
+            last_error_message: None,
+        },
+        total_slots,
+    }
+}
+
+fn group_id() -> AccountGroupId {
+    AccountGroupId::new(GROUP_ID).expect("group ID")
+}
+
+fn unused() -> AdminStoreError {
+    AdminStoreError::new(
+        AdminStoreErrorKind::Unavailable,
+        "account group",
+        "unused test operation",
+    )
+}

backend/crates/gateway-admin/tests/use_case/auth.rs

@@ -1,6 +1,7 @@
 use std::{collections::BTreeMap, sync::Mutex};
 
 use async_trait::async_trait;
+use chrono::{TimeDelta, Utc};
 
 use gateway_admin::{
     model::{
@@ -15,7 +16,6 @@ struct MemoryAuthStore {
     password_hash: Mutex<Option<String>>,
     sessions: Mutex<BTreeMap<String, AdminSession>>,
     audits: Mutex<Vec<AdminAuditEvent>>,
-    failures: Mutex<u32>,
 }
 
 #[async_trait]
@@ -66,31 +66,6 @@ impl AuthStore for MemoryAuthStore {
         Ok(self.sessions.lock().expect("sessions").remove(session_id))
     }
 
-    async fn login_source_is_throttled(
-        &self,
-        _: &str,
-        failure_limit: u32,
-        _: u64,
-    ) -> AdminStoreResult<bool> {
-        Ok(*self.failures.lock().expect("failures") >= failure_limit)
-    }
-
-    async fn record_login_failure(
-        &self,
-        _: &str,
-        failure_limit: u32,
-        _: u64,
-    ) -> AdminStoreResult<bool> {
-        let mut failures = self.failures.lock().expect("failures");
-        *failures += 1;
-        Ok(*failures >= failure_limit)
-    }
-
-    async fn clear_login_failures(&self, _: &str) -> AdminStoreResult<()> {
-        *self.failures.lock().expect("failures") = 0;
-        Ok(())
-    }
-
     async fn append_audit_event(&self, event: AdminAuditEvent) -> AdminStoreResult<()> {
         self.audits.lock().expect("audits").push(event);
         Ok(())
@@ -107,7 +82,6 @@ async fn successful_login_should_create_expiring_session_and_audit() {
         .login(LoginCommand {
             username: Some("admin".to_owned()),
             password: "strong-test-password".to_owned(),
-            source: "127.0.0.1".to_owned(),
         })
         .await
         .expect("login");
@@ -142,9 +116,38 @@ async fn repeated_default_initialization_should_not_replace_password() {
             .login(LoginCommand {
                 username: Some("admin".to_owned()),
                 password: "first-strong-password".to_owned(),
-                source: "127.0.0.1".to_owned(),
             })
             .await
             .is_ok()
     );
 }
+
+#[tokio::test]
+async fn login_with_huge_session_ttl_should_clamp_expiry_instead_of_panicking() {
+    let store = std::sync::Arc::new(MemoryAuthStore::default());
+    let services = super::AdminHarness::new()
+        .auth(store.clone())
+        .session_ttl_minutes(i64::MAX as u64)
+        .build()
+        .await;
+
+    let before = Utc::now();
+    let result = services
+        .auth()
+        .login(LoginCommand {
+            username: Some("admin".to_owned()),
+            password: "strong-test-password".to_owned(),
+        })
+        .await
+        .expect("login with huge session TTL");
+
+    assert!(result.expires_at > before);
+    assert!(result.expires_at <= before + TimeDelta::days(366) + TimeDelta::minutes(1));
+    assert!(
+        services
+            .auth()
+            .validate_session(Some(&result.session_id))
+            .await
+            .expect("validate")
+    );
+}

backend/crates/gateway-admin/tests/use_case/backup.rs

@@ -0,0 +1,104 @@
+//! BackupService 用例测试：通过 AdminHarness 注入 fake 备份端口构造真实服务。
+
+use std::sync::Arc;
+
+use gateway_admin::model::backup::BackupStatus;
+use gateway_admin::ports::backup::BackupStorePorts;
+
+use crate::backup::support::{
+    FakeAuthStore, FakeBackupRepository, FakeDumpPort, FakeObjectStore, configured_settings,
+    system_context,
+};
+
+use super::AdminHarness;
+
+#[tokio::test]
+async fn backup_service_creates_downloads_and_deletes_with_audit() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store = Arc::new(FakeObjectStore::new());
+    let auth = Arc::new(FakeAuthStore::new());
+
+    let services = AdminHarness::new()
+        .auth(auth.clone())
+        .backup(BackupStorePorts::new(
+            repository.clone(),
+            dump,
+            object_store,
+        ))
+        .build()
+        .await;
+
+    // 创建手动备份 → queued + 审计。
+    let created = services
+        .backups()
+        .create_backup(&system_context(), None)
+        .await
+        .expect("create backup");
+    assert_eq!(created.status, BackupStatus::Queued);
+    assert!(created.object_key.starts_with("codex/"));
+    assert!(
+        auth.audit_actions()
+            .iter()
+            .any(|action| action == "backup.created")
+    );
+
+    // 下载地址要求 completed 记录。
+    repository.force_status(&created.id, BackupStatus::Completed);
+    let download = services
+        .backups()
+        .download_url(&system_context(), &created.id)
+        .await
+        .expect("download url");
+    assert!(download.url.starts_with("https://presigned.example.com/"));
+    assert!(
+        auth.audit_actions()
+            .iter()
+            .any(|action| action == "backup.download_url_created")
+    );
+
+    // 删除 → deleting + 审计。
+    let deleting = services
+        .backups()
+        .delete_backup(&system_context(), &created.id)
+        .await
+        .expect("delete backup");
+    assert_eq!(deleting.status, BackupStatus::Deleting);
+    assert!(
+        auth.audit_actions()
+            .iter()
+            .any(|action| action == "backup.delete_requested")
+    );
+}
+
+#[tokio::test]
+async fn backup_service_rejects_download_of_non_completed_record() {
+    let repository = Arc::new(FakeBackupRepository::new(configured_settings()));
+    let dump = Arc::new(FakeDumpPort::new());
+    let object_store = Arc::new(FakeObjectStore::new());
+    let auth = Arc::new(FakeAuthStore::new());
+
+    let services = AdminHarness::new()
+        .auth(auth.clone())
+        .backup(BackupStorePorts::new(
+            repository.clone(),
+            dump,
+            object_store,
+        ))
+        .build()
+        .await;
+
+    let created = services
+        .backups()
+        .create_backup(&system_context(), None)
+        .await
+        .expect("create backup");
+
+    // queued 记录不能创建下载地址。
+    let error = services
+        .backups()
+        .download_url(&system_context(), &created.id)
+        .await
+        .expect_err("non-completed record must be rejected");
+    assert_eq!(error.kind(), gateway_admin::model::AdminErrorKind::Conflict);
+}

backend/crates/gateway-admin/tests/use_case/mod.rs

@@ -1,5 +1,7 @@
+mod account_groups;
 mod accounts;
 mod auth;
+mod backup;
 mod client_keys;
 mod observability;
 mod openai;
@@ -13,14 +15,20 @@ use std::{
 };
 
 use async_trait::async_trait;
+use chrono::{DateTime, Utc};
 use futures::future::BoxFuture;
 use gateway_admin::{
     AdminConfig, AdminServices, InitialAdminPassword,
     model::{
         MutationContext, Revision,
+        account_groups::{
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+            DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+        },
         accounts::{
-            AccountListQuery, AccountPage, AccountRecord, AccountUsage, AccountUsageWindowQuery,
-            AccountUsageWindowResult, DeleteAccounts, SetAccountEnabled,
+            AccountListQuery, AccountPage, AccountRuntimeSnapshot, AccountUpdateResult,
+            AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
+            BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
         },
         auth::{AdminAuditEvent, AdminSession},
         client_keys::{
@@ -46,10 +54,12 @@ use gateway_admin::{
         system::{SystemOperationAccepted, SystemUpdateDetail, SystemUpdateStatus, SystemVersion},
     },
     ports::{
+        backup::BackupStorePorts,
         provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind},
         store::{
-            AccountStore, AdminStoreError, AdminStoreErrorKind, AdminStorePorts, AdminStoreResult,
-            AuthStore, ClientKeyStore, ObservabilityStore, SettingsStore,
+            AccountGroupStore, AccountRuntimeStore, AccountStore, AdminAccountStorePorts,
+            AdminStoreError, AdminStoreErrorKind, AdminStorePorts, AdminStoreResult, AuthStore,
+            ClientKeyStore, ObservabilityStore, SettingsStore,
         },
         system::{
             SystemOperationError, SystemOperationErrorKind, SystemOperations,
@@ -60,7 +70,7 @@ use gateway_admin::{
 use gateway_core::{
     engine::{
         credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeRequest, AccountProbeResult},
+        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
     },
     error::{GatewayError, GatewayErrorKind},
     policy::ClientApiKeyId,
@@ -69,11 +79,15 @@ use gateway_core::{
 
 pub(super) struct AdminHarness {
     default_password: String,
+    session_ttl_minutes: u64,
     accounts: Arc<dyn AccountStore>,
+    account_runtime: Arc<dyn AccountRuntimeStore>,
+    account_groups: Arc<dyn AccountGroupStore>,
     auth: Arc<dyn AuthStore>,
     client_keys: Arc<dyn ClientKeyStore>,
     observability: Arc<dyn ObservabilityStore>,
     settings: Arc<dyn SettingsStore>,
+    backup: BackupStorePorts,
     providers: Vec<Arc<dyn ProviderAdmin>>,
     probe: Arc<dyn AccountProbe>,
     system: Arc<dyn SystemOperations>,
@@ -84,11 +98,15 @@ impl AdminHarness {
         let unavailable = Arc::new(UnavailableStore);
         Self {
             default_password: "strong-test-password".to_owned(),
+            session_ttl_minutes: 60,
             accounts: unavailable.clone(),
+            account_runtime: unavailable.clone(),
+            account_groups: Arc::new(UnavailableAccountGroupStore),
             auth: Arc::new(BootstrapAuthStore::default()),
             client_keys: unavailable.clone(),
             observability: unavailable.clone(),
             settings: unavailable,
+            backup: BackupStorePorts::disabled(),
             providers: vec![
                 Arc::new(UnavailableProvider::new("openai")),
                 Arc::new(UnavailableProvider::new("xai")),
@@ -103,11 +121,26 @@ impl AdminHarness {
         self
     }
 
+    pub(super) fn session_ttl_minutes(mut self, minutes: u64) -> Self {
+        self.session_ttl_minutes = minutes;
+        self
+    }
+
     pub(super) fn accounts(mut self, store: Arc<dyn AccountStore>) -> Self {
         self.accounts = store;
         self
     }
 
+    pub(super) fn account_runtime(mut self, store: Arc<dyn AccountRuntimeStore>) -> Self {
+        self.account_runtime = store;
+        self
+    }
+
+    pub(super) fn account_groups(mut self, store: Arc<dyn AccountGroupStore>) -> Self {
+        self.account_groups = store;
+        self
+    }
+
     pub(super) fn auth(mut self, store: Arc<dyn AuthStore>) -> Self {
         self.auth = store;
         self
@@ -128,6 +161,11 @@ impl AdminHarness {
         self
     }
 
+    pub(super) fn backup(mut self, backup: BackupStorePorts) -> Self {
+        self.backup = backup;
+        self
+    }
+
     pub(super) fn provider(mut self, provider: Arc<dyn ProviderAdmin>) -> Self {
         self.providers
             .retain(|registered| registered.provider_kind() != provider.provider_kind());
@@ -148,16 +186,21 @@ impl AdminHarness {
     pub(super) async fn build(self) -> AdminServices {
         gateway_admin::initialize(
             AdminConfig {
-                session_ttl_minutes: 60,
+                session_ttl_minutes: self.session_ttl_minutes,
                 default_username: "admin".to_owned(),
                 default_password: InitialAdminPassword::new(self.default_password),
             },
             AdminStorePorts::new(
-                self.accounts,
+                AdminAccountStorePorts::new(
+                    self.accounts,
+                    self.account_runtime,
+                    self.account_groups,
+                ),
                 self.auth,
                 self.client_keys,
                 self.observability,
                 self.settings,
+                self.backup,
             ),
             self.providers,
             Arc::new(NoopSnapshot),
@@ -210,18 +253,6 @@ impl AuthStore for BootstrapAuthStore {
         Err(unavailable("admin session"))
     }
 
-    async fn login_source_is_throttled(&self, _: &str, _: u32, _: u64) -> AdminStoreResult<bool> {
-        Ok(false)
-    }
-
-    async fn record_login_failure(&self, _: &str, _: u32, _: u64) -> AdminStoreResult<bool> {
-        Err(unavailable("login failure"))
-    }
-
-    async fn clear_login_failures(&self, _: &str) -> AdminStoreResult<()> {
-        Ok(())
-    }
-
     async fn append_audit_event(&self, _: AdminAuditEvent) -> AdminStoreResult<()> {
         Ok(())
     }
@@ -229,13 +260,72 @@ impl AuthStore for BootstrapAuthStore {
 
 struct UnavailableStore;
 
+struct UnavailableAccountGroupStore;
+
+#[async_trait]
+impl AccountGroupStore for UnavailableAccountGroupStore {
+    async fn list_account_groups(
+        &self,
+        _: AccountGroupListQuery,
+    ) -> AdminStoreResult<AccountGroupPage> {
+        Err(unavailable("account groups"))
+    }
+
+    async fn load_account_group_members(
+        &self,
+        _: &[gateway_core::routing::AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>> {
+        Err(unavailable("account group members"))
+    }
+
+    async fn create_account_group(
+        &self,
+        _: NewAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unavailable("account group create"))
+    }
+
+    async fn update_account_group(
+        &self,
+        _: UpdateAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unavailable("account group update"))
+    }
+
+    async fn set_account_group_enabled(
+        &self,
+        _: SetAccountGroupEnabled,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unavailable("account group state"))
+    }
+
+    async fn delete_account_group(
+        &self,
+        _: DeleteAccountGroup,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountGroupMutation> {
+        Err(unavailable("account group delete"))
+    }
+}
+
 #[async_trait]
 impl AccountStore for UnavailableStore {
-    async fn list_accounts(&self, _: AccountListQuery) -> AdminStoreResult<AccountPage> {
+    async fn list_accounts(
+        &self,
+        _: AccountListQuery,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage> {
         Err(unavailable("accounts"))
     }
 
-    async fn load_account(&self, _: &str) -> AdminStoreResult<Option<AccountRecord>> {
+    async fn load_account(
+        &self,
+        _: &str,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<Option<gateway_admin::model::accounts::AccountPageItem>> {
         Err(unavailable("account"))
     }
 
@@ -310,14 +400,30 @@ impl AccountStore for UnavailableStore {
         Err(unavailable("credential refresh"))
     }
 
-    async fn set_account_enabled(
+    async fn update_account(
         &self,
-        _: SetAccountEnabled,
+        _: UpdateAccount,
         _: &MutationContext,
-    ) -> AdminStoreResult<Revision> {
+    ) -> AdminStoreResult<AccountUpdateResult> {
         Err(unavailable("account enabled"))
     }
 
+    async fn recover_account(
+        &self,
+        _: &ProviderAccountId,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountUpdateResult> {
+        Err(unavailable("account recovery"))
+    }
+
+    async fn batch_update_accounts(
+        &self,
+        _: BatchUpdateAccounts,
+        _: &MutationContext,
+    ) -> AdminStoreResult<AccountsUpdateResult> {
+        Err(unavailable("account batch update"))
+    }
+
     async fn delete_accounts(
         &self,
         _: DeleteAccounts,
@@ -335,6 +441,17 @@ impl AccountStore for UnavailableStore {
     }
 }
 
+#[async_trait]
+impl AccountRuntimeStore for UnavailableStore {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot::default())
+    }
+
+    async fn account_runtime(&self, _: &[String]) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot::default())
+    }
+}
+
 #[async_trait]
 impl ClientKeyStore for UnavailableStore {
     async fn list_client_keys(&self, _: ClientKeyListQuery) -> AdminStoreResult<ClientKeyPage> {
@@ -383,7 +500,11 @@ impl ClientKeyStore for UnavailableStore {
 
 #[async_trait]
 impl ObservabilityStore for UnavailableStore {
-    async fn dashboard_summary(&self, _: TimeRange) -> AdminStoreResult<DashboardObservation> {
+    async fn dashboard_summary(
+        &self,
+        _: TimeRange,
+        _: DateTime<Utc>,
+    ) -> AdminStoreResult<DashboardObservation> {
         Err(unavailable("dashboard"))
     }
 
@@ -454,7 +575,6 @@ impl SettingsStore for UnavailableStore {
 
     async fn replace_admin_api_key(
         &self,
-        _: Revision,
         _: AdminApiKey,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -463,7 +583,6 @@ impl SettingsStore for UnavailableStore {
 
     async fn delete_admin_api_key(
         &self,
-        _: Revision,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
         Err(unavailable("admin API key"))
@@ -654,12 +773,13 @@ impl AccountProbe for UnavailableProbe {
     fn probe(
         &self,
         _: AccountProbeRequest,
-    ) -> BoxFuture<'_, Result<AccountProbeResult, GatewayError>> {
+    ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
         Box::pin(async {
             Err(GatewayError::new(
                 GatewayErrorKind::Internal,
                 "test account probe is unavailable",
-            ))
+            )
+            .into())
         })
     }
 }

backend/crates/gateway-admin/tests/use_case/observability.rs

@@ -1,6 +1,10 @@
 use std::{
     str::FromStr as _,
-    sync::{Arc, Mutex},
+    sync::{
+        Arc, Mutex,
+        atomic::{AtomicUsize, Ordering},
+    },
+    time::Duration as StdDuration,
 };
 
 use async_trait::async_trait;
@@ -9,13 +13,14 @@ use chrono::{DateTime, Duration, Timelike as _, Utc};
 use gateway_admin::{
     AdminServices,
     model::{
-        MutationContext, Revision,
+        MutationContext, PageSize, Revision,
         observability::{
             AccountPoolMetrics, AttemptMetrics, CostCoverage, CurrencyCost, DashboardObservation,
             DashboardRuntimeSlots, DiagnosticDimension, DiagnosticObservation, Granularity,
-            HealthStatus, OpsErrorPage, OpsErrorQuery, RequestMetricPoint, RequestMetrics,
-            TimeRange, TrendKind, UsageCalculatedBillingFact, UsageDetail, UsageFilter,
-            UsageOverview, UsagePage, UsageQuery,
+            HealthStatus, LatencyPercentiles, OpsErrorPage, OpsErrorQuery, PercentileMilliseconds,
+            RequestMetricPoint, RequestMetrics, TimeRange, TrendKind, UsageBilling,
+            UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageListRecord, UsageOverview,
+            UsagePage, UsageQuery, china_day_start,
         },
         settings::{
             AdminApiKey, AdminApiKeyMutation, ReplaceRuntimeSettings, RotationStrategy,
@@ -103,6 +108,40 @@ async fn health_timeline_should_keep_exactly_china_day_quarter_hour_slots() {
     }));
 }
 
+#[tokio::test]
+async fn dashboard_summary_should_derive_first_token_average_from_trend() {
+    let now = Utc::now();
+    let current_slot = quarter_hour_start(now);
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    store.replace_trend(vec![
+        health_metric_point(
+            current_slot - Duration::minutes(15),
+            RequestMetrics {
+                first_token_latency_sum_ms: 120,
+                first_token_latency_count: 2,
+                ..RequestMetrics::default()
+            },
+        ),
+        health_metric_point(
+            current_slot,
+            RequestMetrics {
+                first_token_latency_sum_ms: 180,
+                first_token_latency_count: 1,
+                ..RequestMetrics::default()
+            },
+        ),
+    ]);
+    let services = observability_services(store).await;
+
+    let summary = services
+        .observability()
+        .dashboard_summary(observation_range(now), TrendKind::Usage)
+        .await
+        .expect("dashboard summary");
+
+    assert_eq!(summary.average_first_token_latency_ms, Some(100));
+}
+
 #[tokio::test]
 async fn health_timeline_should_match_legacy_status_precedence_and_thresholds() {
     let now = Utc::now();
@@ -158,11 +197,15 @@ async fn health_timeline_should_match_legacy_status_precedence_and_thresholds()
         ),
     ];
 
-    for (metrics, expected_status, expected_reliability) in fixtures {
+    for (index, (metrics, expected_status, expected_reliability)) in
+        fixtures.into_iter().enumerate()
+    {
         store.replace_trend(vec![health_metric_point(current_slot, metrics)]);
+        let range_end =
+            now + Duration::seconds(i64::try_from(index).expect("fixture index fits i64") * 2);
         let timeline = services
             .observability()
-            .dashboard_summary(observation_range(now), TrendKind::Usage)
+            .dashboard_summary(observation_range(range_end), TrendKind::Usage)
             .await
             .expect("dashboard summary")
             .health_timeline;
@@ -181,7 +224,8 @@ async fn dashboard_summary_should_project_rebuildable_runtime_slots() {
     let now = Utc::now();
     let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
     store.replace_runtime_slots(Some(DashboardRuntimeSlots {
-        active_accounts: 3,
+        inherited_accounts: 2,
+        overridden_slots: 5,
         used_slots: Some(2),
     }));
     let services = observability_services(store).await;
@@ -193,9 +237,75 @@ async fn dashboard_summary_should_project_rebuildable_runtime_slots() {
         .expect("dashboard summary")
         .capacity;
 
-    assert_eq!(capacity.total_slots, 3);
+    assert_eq!(capacity.total_slots, 7);
     assert_eq!(capacity.used_slots, Some(2));
-    assert_eq!(capacity.available_slots, Some(1));
+    assert_eq!(capacity.available_slots, Some(5));
+}
+
+#[tokio::test]
+async fn dashboard_summary_should_share_one_current_observation_time_across_runtime_facts() {
+    let historical_end = Utc::now() - Duration::hours(1);
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(
+        historical_end,
+    )));
+    let services = observability_services(store.clone()).await;
+
+    services
+        .observability()
+        .dashboard_summary(observation_range(historical_end), TrendKind::Usage)
+        .await
+        .expect("dashboard summary");
+
+    let (summary_observed_at, slots_observed_at) = store.observed_times();
+    assert_eq!(summary_observed_at, slots_observed_at);
+    assert!(summary_observed_at.is_some_and(|value| value > historical_end));
+}
+
+#[tokio::test]
+async fn dashboard_summary_should_coalesce_concurrent_requests_in_one_short_window() {
+    let end_bucket = Utc::now().timestamp().div_euclid(2) * 2;
+    let first_end = DateTime::from_timestamp(end_bucket, 100_000_000).expect("first end");
+    let second_end = DateTime::from_timestamp(end_bucket, 900_000_000).expect("second end");
+    let first_range = TimeRange::new(china_day_start(first_end), first_end).expect("first range");
+    let second_range =
+        TimeRange::new(china_day_start(second_end), second_end).expect("second range");
+    let store = Arc::new(FixtureObservabilityStore::new(first_range));
+    store.set_dashboard_delay(StdDuration::from_millis(20));
+    let services = observability_services(store.clone()).await;
+    let observability = services.observability();
+
+    let (first, second) = tokio::join!(
+        observability.dashboard_summary(first_range, TrendKind::Usage),
+        observability.dashboard_summary(second_range, TrendKind::Errors),
+    );
+
+    first.expect("first dashboard summary");
+    second.expect("second dashboard summary");
+    assert_eq!(store.dashboard_summary_calls(), 1);
+}
+
+#[tokio::test]
+async fn dashboard_summary_should_reload_after_the_short_window_changes() {
+    let end_bucket = Utc::now().timestamp().div_euclid(2) * 2;
+    let first_end = DateTime::from_timestamp(end_bucket, 100_000_000).expect("first end");
+    let second_end = first_end + Duration::seconds(2);
+    let first_range = TimeRange::new(china_day_start(first_end), first_end).expect("first range");
+    let second_range =
+        TimeRange::new(china_day_start(second_end), second_end).expect("second range");
+    let store = Arc::new(FixtureObservabilityStore::new(first_range));
+    let services = observability_services(store.clone()).await;
+    let observability = services.observability();
+
+    observability
+        .dashboard_summary(first_range, TrendKind::Usage)
+        .await
+        .expect("first dashboard summary");
+    observability
+        .dashboard_summary(second_range, TrendKind::Usage)
+        .await
+        .expect("second dashboard summary");
+
+    assert_eq!(store.dashboard_summary_calls(), 2);
 }
 
 #[tokio::test]
@@ -212,6 +322,24 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
         output_tokens: 200,
         total_tokens: 1_000,
         latency_count: 5,
+        admission_decision_count: 10,
+        admission_decision_percentiles: LatencyPercentiles {
+            p50_ms: Some(PercentileMilliseconds::new(2.0).expect("admission P50")),
+            p95_ms: Some(PercentileMilliseconds::new(5.0).expect("admission P95")),
+            p99_ms: Some(PercentileMilliseconds::new(8.0).expect("admission P99")),
+        },
+        account_selection_wait_count: 8,
+        account_selection_wait_percentiles: LatencyPercentiles {
+            p50_ms: Some(PercentileMilliseconds::new(10.0).expect("selection P50")),
+            p95_ms: Some(PercentileMilliseconds::new(40.0).expect("selection P95")),
+            p99_ms: Some(PercentileMilliseconds::new(70.0).expect("selection P99")),
+        },
+        output_throughput_p10: Some(40),
+        output_throughput_p50: Some(50),
+        output_throughput_p90: Some(60),
+        capacity_sample_count: 8,
+        capacity_utilization_avg_basis_points: Some(6_500),
+        capacity_utilization_p95_basis_points: Some(8_000),
         ..RequestMetrics::default()
     };
     store.replace_overview(UsageOverview {
@@ -247,6 +375,7 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
         bucket_start: quarter_hour_start(now),
         provider_kind: "openai".to_owned(),
         upstream_model_id: "gpt-5.5".to_owned(),
+        service_tier: None,
         input_tokens: Some(800),
         output_tokens: Some(200),
         cached_tokens: Some(0),
@@ -271,10 +400,16 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
         .await
         .expect("usage diagnostics");
 
-    assert_eq!(insights.health.total_requests, 8);
+    assert_eq!(insights.health.total_requests, 10);
     assert_eq!(insights.health.failed_requests, 2);
+    assert_eq!(insights.health.success_rate, 0.75);
+    assert_eq!(insights.health.completion_rate, 1.0);
     assert_eq!(insights.granularity, Granularity::FifteenMinutes);
     assert_eq!(insights.performance.latency_coverage, 0.5);
+    assert_eq!(insights.performance.admission_decision_coverage, 1.0);
+    assert_eq!(insights.performance.account_selection_wait_coverage, 0.8);
+    assert_eq!(insights.performance.capacity_coverage, 0.8);
+    assert_eq!(insights.performance.output_throughput_p50, Some(50));
     assert_eq!(insights.cost.tokens_per_request, 100.0);
     assert_eq!(
         insights
@@ -314,8 +449,92 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
             .map(gateway_admin::model::observability::DecimalAmount::as_str),
         Some("1")
     );
+    assert_eq!(
+        insights
+            .cost
+            .no_cache_cost
+            .as_ref()
+            .map(gateway_admin::model::observability::DecimalAmount::as_str),
+        Some("1.25")
+    );
+    assert_eq!(
+        insights
+            .cost
+            .tier_premium
+            .as_ref()
+            .map(gateway_admin::model::observability::DecimalAmount::as_str),
+        Some("0.25")
+    );
     assert_eq!(diagnostics.items[0].request_share, 0.75);
     assert_eq!(diagnostics.items[1].request_share, 0.25);
+    assert!((diagnostics.items[0].impact_score - 0.075).abs() < 1e-9);
+}
+
+#[tokio::test]
+async fn usage_records_should_tolerate_records_that_fail_billing_enrichment() {
+    let now = Utc::now();
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    let invalid_kind = "x".repeat(65);
+    store.replace_usage_records(vec![
+        total_record(
+            "request_invalid_kind",
+            Some(&invalid_kind),
+            "calculated",
+            now,
+        ),
+        total_record(
+            "request_unregistered_kind",
+            Some("anthropic"),
+            "calculated",
+            now,
+        ),
+        total_record("request_enriched", Some("openai"), "calculated", now),
+    ]);
+    let services = observability_services_with_calculated_billing(store).await;
+
+    let page = services
+        .observability()
+        .usage_records(usage_query(now))
+        .await
+        .expect("one bad record must not fail the whole usage list");
+
+    assert_eq!(page.items.len(), 3);
+    assert!(
+        matches!(page.items[0].billing, Some(UsageBilling::Total { .. })),
+        "invalid Provider kind keeps the stored total"
+    );
+    assert!(
+        matches!(page.items[1].billing, Some(UsageBilling::Total { .. })),
+        "unregistered Provider kind keeps the stored total"
+    );
+    assert!(
+        matches!(page.items[2].billing, Some(UsageBilling::Calculated(_))),
+        "healthy record is still enriched"
+    );
+}
+
+#[tokio::test]
+async fn usage_records_should_enrich_provider_reported_totals_when_pricing_matches() {
+    let now = Utc::now();
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    store.replace_usage_records(vec![total_record(
+        "request_provider_reported",
+        Some("openai"),
+        "provider_reported",
+        now,
+    )]);
+    let services = observability_services_with_calculated_billing(store).await;
+
+    let page = services
+        .observability()
+        .usage_records(usage_query(now))
+        .await
+        .expect("usage records");
+
+    assert!(matches!(
+        page.items[0].billing,
+        Some(UsageBilling::Calculated(_))
+    ));
 }
 
 struct FixtureObservabilityStore {
@@ -324,6 +543,11 @@ struct FixtureObservabilityStore {
     calculated_billing_facts: Mutex<Vec<UsageCalculatedBillingFact>>,
     diagnostics: Mutex<Vec<DiagnosticObservation>>,
     runtime_slots: Mutex<Option<DashboardRuntimeSlots>>,
+    summary_observed_at: Mutex<Option<DateTime<Utc>>>,
+    slots_observed_at: Mutex<Option<DateTime<Utc>>>,
+    usage_records: Mutex<Vec<UsageListRecord>>,
+    dashboard_delay: Mutex<StdDuration>,
+    dashboard_summary_calls: AtomicUsize,
 }
 
 impl FixtureObservabilityStore {
@@ -339,9 +563,22 @@ impl FixtureObservabilityStore {
             calculated_billing_facts: Mutex::new(Vec::new()),
             diagnostics: Mutex::new(Vec::new()),
             runtime_slots: Mutex::new(None),
+            summary_observed_at: Mutex::new(None),
+            slots_observed_at: Mutex::new(None),
+            usage_records: Mutex::new(Vec::new()),
+            dashboard_delay: Mutex::new(StdDuration::ZERO),
+            dashboard_summary_calls: AtomicUsize::new(0),
         }
     }
 
+    fn set_dashboard_delay(&self, delay: StdDuration) {
+        *self.dashboard_delay.lock().expect("dashboard delay") = delay;
+    }
+
+    fn dashboard_summary_calls(&self) -> usize {
+        self.dashboard_summary_calls.load(Ordering::Relaxed)
+    }
+
     fn replace_trend(&self, trend: Vec<RequestMetricPoint>) {
         *self.trend.lock().expect("trend") = trend;
     }
@@ -364,15 +601,41 @@ impl FixtureObservabilityStore {
     fn replace_runtime_slots(&self, runtime_slots: Option<DashboardRuntimeSlots>) {
         *self.runtime_slots.lock().expect("runtime slots") = runtime_slots;
     }
+
+    fn observed_times(&self) -> (Option<DateTime<Utc>>, Option<DateTime<Utc>>) {
+        (
+            *self
+                .summary_observed_at
+                .lock()
+                .expect("summary observed at"),
+            *self.slots_observed_at.lock().expect("slots observed at"),
+        )
+    }
+
+    fn replace_usage_records(&self, records: Vec<UsageListRecord>) {
+        *self.usage_records.lock().expect("usage records") = records;
+    }
 }
 
 #[async_trait]
 impl ObservabilityStore for FixtureObservabilityStore {
-    async fn dashboard_summary(&self, range: TimeRange) -> AdminStoreResult<DashboardObservation> {
+    async fn dashboard_summary(
+        &self,
+        range: TimeRange,
+        observed_at: DateTime<Utc>,
+    ) -> AdminStoreResult<DashboardObservation> {
+        self.dashboard_summary_calls.fetch_add(1, Ordering::Relaxed);
+        *self
+            .summary_observed_at
+            .lock()
+            .expect("summary observed at") = Some(observed_at);
+        let dashboard_delay = *self.dashboard_delay.lock().expect("dashboard delay");
+        if !dashboard_delay.is_zero() {
+            tokio::time::sleep(dashboard_delay).await;
+        }
         Ok(DashboardObservation {
             range,
-            requests: RequestMetrics::default(),
-            attempts: AttemptMetrics::default(),
+            totals: Default::default(),
             provider_accounts: AccountPoolMetrics::default(),
             trend: self.trend.lock().expect("trend").clone(),
             account_usage: Vec::new(),
@@ -382,8 +645,9 @@ impl ObservabilityStore for FixtureObservabilityStore {
 
     async fn dashboard_runtime_slots(
         &self,
-        _: DateTime<Utc>,
+        observed_at: DateTime<Utc>,
     ) -> AdminStoreResult<Option<DashboardRuntimeSlots>> {
+        *self.slots_observed_at.lock().expect("slots observed at") = Some(observed_at);
         Ok(*self.runtime_slots.lock().expect("runtime slots"))
     }
 
@@ -411,8 +675,15 @@ impl ObservabilityStore for FixtureObservabilityStore {
             .clone())
     }
 
-    async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {
-        Err(super::unavailable("usage records"))
+    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
+        let items = self.usage_records.lock().expect("usage records").clone();
+        let total = u64::try_from(items.len()).unwrap_or(u64::MAX);
+        Ok(UsagePage {
+            items,
+            current_page: query.current_page,
+            page_size: query.page_size.get(),
+            total,
+        })
     }
 
     async fn usage_record_detail(&self, _: &str) -> AdminStoreResult<UsageDetail> {
@@ -471,7 +742,6 @@ impl SettingsStore for FixtureSettingsStore {
 
     async fn replace_admin_api_key(
         &self,
-        _: Revision,
         _: AdminApiKey,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -480,7 +750,6 @@ impl SettingsStore for FixtureSettingsStore {
 
     async fn delete_admin_api_key(
         &self,
-        _: Revision,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
         Err(super::unavailable("admin API key"))
@@ -511,6 +780,76 @@ fn observation_range(end: DateTime<Utc>) -> TimeRange {
     TimeRange::new(end - Duration::hours(24), end).expect("observation range")
 }
 
+fn usage_query(now: DateTime<Utc>) -> UsageQuery {
+    UsageQuery {
+        range: observation_range(now),
+        filter: UsageFilter::default(),
+        current_page: 1,
+        page_size: PageSize::new(50).expect("page size"),
+    }
+}
+
+fn total_record(
+    id: &str,
+    provider_kind: Option<&str>,
+    source: &str,
+    now: DateTime<Utc>,
+) -> UsageListRecord {
+    UsageListRecord {
+        id: id.to_owned(),
+        endpoint: "/v1/responses".to_owned(),
+        client_transport: "http_sse".to_owned(),
+        requested_model_id: Some("gpt-5.5".to_owned()),
+        provider_kind: provider_kind.map(str::to_owned),
+        provider_account_ref: None,
+        provider_account_name: None,
+        provider_account_email: None,
+        provider_account_authentication_kind: None,
+        upstream_model_id: Some("gpt-5.5".to_owned()),
+        upstream_transport: None,
+        service_tier: None,
+        input_tokens: Some(800),
+        output_tokens: Some(200),
+        cached_tokens: Some(0),
+        cache_write_tokens: Some(0),
+        reasoning_tokens: Some(0),
+        image_input_tokens: None,
+        image_output_tokens: None,
+        total_tokens: Some(1_000),
+        cost_source: source.to_owned(),
+        cost_amount: None,
+        cost_currency: None,
+        billing: Some(UsageBilling::Total {
+            source: source.to_owned(),
+            total: CurrencyCost {
+                currency: "USD".to_owned(),
+                amount: gateway_admin::model::observability::DecimalAmount::from_str("1.25")
+                    .expect("billing total"),
+            },
+        }),
+        transport_decision_wait_ms: None,
+        connect_ms: None,
+        headers_ms: None,
+        first_event_ms: None,
+        first_reasoning_ms: None,
+        first_text_ms: None,
+        first_token_ms: None,
+        provider_processing_ms: None,
+        latency_ms: Some(100),
+        admission_decision_ms: None,
+        account_selection_wait_ms: None,
+        capacity_used_slots: None,
+        capacity_total_slots: None,
+        client_ip: None,
+        user_agent: None,
+        reasoning_effort: None,
+        reasoning_preset: None,
+        subagent_kind: None,
+        compact: false,
+        started_at: now,
+    }
+}
+
 fn health_metric_point(bucket_start: DateTime<Utc>, metrics: RequestMetrics) -> RequestMetricPoint {
     RequestMetricPoint {
         bucket_start,
@@ -523,6 +862,10 @@ fn health_metric_point(bucket_start: DateTime<Utc>, metrics: RequestMetrics) ->
 
 fn diagnostic(name: &str, request_count: u64) -> DiagnosticObservation {
     DiagnosticObservation {
+        first_token_p95_ms: None,
+        non_completion_count: 0,
+        retry_count: 0,
+        key: name.to_owned(),
         name: name.to_owned(),
         request_count,
         success_count: request_count,
@@ -530,16 +873,12 @@ fn diagnostic(name: &str, request_count: u64) -> DiagnosticObservation {
         attempt_count: request_count,
         total_tokens: request_count.saturating_mul(100),
         average_latency_ms: Some(100),
+        latency_p95_ms: Some(200),
         cost_coverage: CostCoverage::default(),
         costs: Vec::new(),
     }
 }
 
-fn china_day_start(value: DateTime<Utc>) -> DateTime<Utc> {
-    let elapsed = (value.timestamp() + 8 * 60 * 60).rem_euclid(24 * 60 * 60);
-    value - Duration::seconds(elapsed) - Duration::nanoseconds(i64::from(value.nanosecond()))
-}
-
 fn quarter_hour_start(value: DateTime<Utc>) -> DateTime<Utc> {
     let elapsed = value.timestamp().rem_euclid(15 * 60);
     value - Duration::seconds(elapsed) - Duration::nanoseconds(i64::from(value.nanosecond()))

backend/crates/gateway-admin/tests/use_case/openai.rs

@@ -5,8 +5,8 @@ use gateway_core::engine::credential::ProviderAccountId;
 use gateway_admin::{
     AdminServices,
     model::provider_credentials::{
-        AuthorizationMutationTarget, CompleteAuthorization, CredentialDeletion, CredentialMutation,
-        ImportCredentials, ProviderQuotaRequest, ReauthorizationTarget, StartAuthorization,
+        AuthorizationMutationTarget, CompleteAuthorization, CredentialDeletion, ImportCredentials,
+        ProviderQuotaRequest, StartAuthorization,
     },
     ports::provider::ProviderAdminErrorKind,
 };
@@ -15,50 +15,6 @@ use super::accounts::{
     FakeAccountStore, FakeProviderAdmin, context, document, events, recorded, revision,
 };
 
-#[tokio::test]
-async fn openai_enable_should_use_scoped_store_without_provider_mutation() {
-    let events = events();
-    let provider = FakeProviderAdmin::new("openai", events.clone());
-    let store = FakeAccountStore::new("openai", events.clone());
-    let services = service(provider, store.clone()).await;
-
-    services
-        .openai()
-        .enable(mutation("acct_test"))
-        .await
-        .expect("enable credential");
-
-    assert_eq!(
-        recorded(&events),
-        ["store.credential_details", "store.set_enabled"]
-    );
-    assert_eq!(store.audit_requests(), ["request-openai"]);
-}
-
-#[tokio::test]
-async fn openai_disable_should_commit_then_release_provider_resources() {
-    let events = events();
-    let provider = FakeProviderAdmin::new("openai", events.clone());
-    let store = FakeAccountStore::new("openai", events.clone());
-    let services = service(provider, store.clone()).await;
-
-    services
-        .openai()
-        .disable(mutation("acct_test"))
-        .await
-        .expect("disable credential");
-
-    assert_eq!(
-        recorded(&events),
-        [
-            "store.credential_details",
-            "store.set_enabled",
-            "provider.account_unavailable",
-        ]
-    );
-    assert_eq!(store.audit_requests(), ["request-openai"]);
-}
-
 #[tokio::test]
 async fn openai_delete_should_commit_then_release_provider_resources() {
     let events = events();
@@ -78,31 +34,12 @@ async fn openai_delete_should_commit_then_release_provider_resources() {
             "store.credential_details",
             "store.delete",
             "provider.account_unavailable",
+            "provider.account_facts_changed",
         ]
     );
     assert_eq!(store.audit_requests(), ["request-openai"]);
 }
 
-#[tokio::test]
-async fn openai_disable_store_failure_should_not_release_provider_resources() {
-    let events = events();
-    let provider = FakeProviderAdmin::new("openai", events.clone());
-    let store = FakeAccountStore::new("openai", events.clone());
-    store.fail_next_commit();
-    let services = service(provider, store).await;
-
-    services
-        .openai()
-        .disable(mutation("acct_test"))
-        .await
-        .expect_err("failed Store transaction");
-
-    assert_eq!(
-        recorded(&events),
-        ["store.credential_details", "store.set_enabled"]
-    );
-}
-
 #[tokio::test]
 async fn openai_import_should_prepare_before_atomic_store_commit() {
     let events = events();
@@ -114,17 +51,19 @@ async fn openai_import_should_prepare_before_atomic_store_commit() {
         .openai()
         .import_document(ImportCredentials {
             context: context("import-openai"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
         .expect("import credential");
 
+    await_quota_requests(&provider, 1).await;
+
     assert_eq!(
         recorded(&events),
         [
             "provider.prepare_import",
             "store.commit_import",
+            "provider.account_facts_changed",
             "provider.quota",
         ]
     );
@@ -151,12 +90,13 @@ async fn openai_import_should_refresh_quota_for_every_imported_account() {
         .openai()
         .import_document(ImportCredentials {
             context: context("import-openai-batch"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
         .expect("import credentials");
 
+    await_quota_requests(&provider, 2).await;
+
     assert_eq!(
         result.credential_ids,
         [
@@ -193,12 +133,13 @@ async fn openai_import_should_remain_successful_when_quota_refresh_fails() {
         .openai()
         .import_document(ImportCredentials {
             context: context("import-openai-quota-failure"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
         .expect("committed import remains successful");
 
+    await_quota_requests(&provider, 1).await;
+
     assert_eq!(
         result.credential_ids,
         [ProviderAccountId::new("acct_prepared").expect("account ID")]
@@ -206,6 +147,141 @@ async fn openai_import_should_remain_successful_when_quota_refresh_fails() {
     assert_eq!(provider.quota_requests().len(), 1);
 }
 
+#[tokio::test]
+async fn openai_authorization_create_should_observe_initial_quota() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    let store = FakeAccountStore::new("openai", events.clone());
+    let services = service(provider.clone(), store.clone()).await;
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-start-openai-create"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    services
+        .openai()
+        .complete_authorization(CompleteAuthorization {
+            context: context("oauth-start-openai-create"),
+            flow_id: "flow-test".to_owned(),
+            callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+        })
+        .await
+        .expect("complete authorization");
+
+    await_quota_requests(&provider, 1).await;
+
+    assert_eq!(
+        recorded(&events),
+        [
+            "provider.start_authorization",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "provider.account_facts_changed",
+            "provider.quota",
+        ]
+    );
+    assert_eq!(
+        provider.quota_requests(),
+        [ProviderQuotaRequest {
+            account_id: ProviderAccountId::new("acct_prepared").expect("account ID"),
+            refresh: true,
+            rolling_usage: None,
+        }]
+    );
+    assert_eq!(store.audit_requests(), ["oauth-start-openai-create"]);
+}
+
+#[tokio::test]
+async fn openai_authorization_create_should_remain_successful_when_initial_quota_fails() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    provider.fail_next_quota(ProviderAdminErrorKind::Unavailable);
+    let store = FakeAccountStore::new("openai", events);
+    let services = service(provider.clone(), store).await;
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-start-openai-quota-failure"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    let result = services
+        .openai()
+        .complete_authorization(CompleteAuthorization {
+            context: context("oauth-start-openai-quota-failure"),
+            flow_id: "flow-test".to_owned(),
+            callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+        })
+        .await
+        .expect("quota observation must not fail authorization");
+
+    await_quota_requests(&provider, 1).await;
+
+    assert_eq!(result.account_id.as_str(), "acct_prepared");
+    assert_eq!(provider.quota_requests().len(), 1);
+}
+
+#[tokio::test]
+async fn openai_authorization_store_failure_should_release_claim_for_retry() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    provider.retry_authorization_after_abort();
+    let store = FakeAccountStore::new("openai", events.clone());
+    store.fail_next_commit();
+    let services = service(provider.clone(), store).await;
+    let command = || CompleteAuthorization {
+        context: context("oauth-store-retry"),
+        flow_id: "flow-test".to_owned(),
+        callback_url: "http://localhost/callback?code=test&state=test".to_owned(),
+    };
+
+    services
+        .openai()
+        .start_authorization(StartAuthorization {
+            context: context("oauth-store-retry"),
+            name: "new OpenAI credential".to_owned(),
+            reauthorization: None,
+        })
+        .await
+        .expect("start authorization");
+    services
+        .openai()
+        .complete_authorization(command())
+        .await
+        .expect_err("Store commit must fail");
+    services
+        .openai()
+        .complete_authorization(command())
+        .await
+        .expect("released claim must permit retry");
+
+    await_quota_requests(&provider, 1).await;
+
+    assert_eq!(
+        recorded(&events),
+        [
+            "provider.start_authorization",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "authorization_guard.abort",
+            "provider.complete_authorization",
+            "store.commit_authorization",
+            "authorization_guard.commit",
+            "provider.account_facts_changed",
+            "provider.quota",
+        ]
+    );
+    assert!(provider.pending().is_none());
+}
+
 #[tokio::test]
 async fn openai_import_provider_error_should_not_touch_store_transaction() {
     let events = events();
@@ -218,7 +294,6 @@ async fn openai_import_provider_error_should_not_touch_store_transaction() {
         .openai()
         .import_document(ImportCredentials {
             context: context("import-openai-error"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
@@ -228,7 +303,7 @@ async fn openai_import_provider_error_should_not_touch_store_transaction() {
 }
 
 #[tokio::test]
-async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_through_commit() {
+async fn openai_reauthorization_should_commit_after_credential_revision_advances() {
     let events = events();
     let provider = FakeProviderAdmin::new("openai", events.clone());
     let store = FakeAccountStore::new("openai", events.clone());
@@ -237,18 +312,13 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
         .openai()
         .start_authorization(StartAuthorization {
             context: context("oauth-start-openai"),
-            expected_config_revision: revision(7),
             name: "reauthorize".to_owned(),
-            reauthorization: Some(ReauthorizationTarget {
-                account_id: ProviderAccountId::new("acct_test").expect("account ID"),
-                credential_revision: revision(1),
-            }),
+            reauthorization: Some(ProviderAccountId::new("acct_test").expect("account ID")),
         })
         .await
         .expect("start reauthorization");
 
     let pending = provider.pending().expect("pending envelope");
-    assert_eq!(pending.expected_config_revision(), revision(7));
     assert_eq!(pending.provider_kind().as_str(), "openai");
     assert_eq!(
         pending.owner_binding().started_request_id(),
@@ -256,15 +326,14 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
     );
     assert!(matches!(
         pending.target(),
-        AuthorizationMutationTarget::Reauthorize {
-            account_id,
-            expected_credential_revision,
-        } if account_id.as_str() == "acct_test"
-            && *expected_credential_revision == revision(1)
+        AuthorizationMutationTarget::Reauthorize { account_id }
+            if account_id.as_str() == "acct_test"
     ));
     assert!(!format!("{pending:?}").contains("admin-test"));
 
-    services
+    provider.set_current_credential_revision(revision(2));
+
+    let result = services
         .openai()
         .complete_authorization(CompleteAuthorization {
             context: context("oauth-complete-openai"),
@@ -274,6 +343,10 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
         .await
         .expect("complete reauthorization");
 
+    await_quota_requests(&provider, 1).await;
+
+    assert_eq!(result.credential_revision, Some(revision(3)));
+
     assert_eq!(
         recorded(&events),
         [
@@ -282,9 +355,11 @@ async fn openai_reauthorization_should_restore_pending_envelope_and_hold_guard_t
             "provider.complete_authorization",
             "store.commit_authorization",
             "guard.finish",
+            "provider.account_facts_changed",
+            "provider.quota",
         ]
     );
-    assert_eq!(store.authorization_revision(), Some(revision(7)));
+    assert_eq!(provider.quota_requests().len(), 1);
     assert_eq!(store.audit_requests(), ["oauth-complete-openai"]);
 }
 
@@ -296,18 +371,19 @@ async fn service(provider: Arc<FakeProviderAdmin>, store: Arc<FakeAccountStore>)
         .await
 }
 
-fn mutation(account_id: &str) -> CredentialMutation {
-    CredentialMutation {
-        context: context("request-openai"),
-        expected_config_revision: revision(1),
-        account_id: ProviderAccountId::new(account_id).expect("account ID"),
+async fn await_quota_requests(provider: &FakeProviderAdmin, expected: usize) {
+    for _ in 0..100 {
+        if provider.quota_requests().len() == expected {
+            return;
+        }
+        tokio::task::yield_now().await;
     }
+    assert_eq!(provider.quota_requests().len(), expected);
 }
 
 fn deletion(account_id: &str) -> CredentialDeletion {
     CredentialDeletion {
         context: context("request-openai"),
-        expected_config_revision: revision(1),
         account_ids: vec![ProviderAccountId::new(account_id).expect("account ID")],
     }
 }

backend/crates/gateway-admin/tests/use_case/settings.rs

@@ -2,7 +2,7 @@ use async_trait::async_trait;
 
 use gateway_admin::{
     model::{
-        AdminErrorKind, MutationContext, Revision,
+        AdminErrorKind, MutationContext,
         settings::{
             AdminApiKey, AdminApiKeyMutation, ReplaceRuntimeSettings, RotationStrategy,
             RuntimeSettings,
@@ -33,7 +33,6 @@ impl SettingsStore for UnusedSettingsStore {
 
     async fn replace_admin_api_key(
         &self,
-        _: Revision,
         _: AdminApiKey,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
@@ -42,7 +41,6 @@ impl SettingsStore for UnusedSettingsStore {
 
     async fn delete_admin_api_key(
         &self,
-        _: Revision,
         _: &MutationContext,
     ) -> AdminStoreResult<AdminApiKeyMutation> {
         Err(unused())
@@ -63,7 +61,6 @@ async fn settings_should_reject_zero_refresh_margin_before_store_call() {
                 request_id: "request-settings".to_owned(),
             },
             ReplaceRuntimeSettings {
-                expected_config_revision: Revision::new(1).expect("revision"),
                 model_mappings: Default::default(),
                 refresh_margin_seconds: 0,
                 refresh_concurrency: 1,

backend/crates/gateway-admin/tests/use_case/xai.rs

@@ -4,37 +4,11 @@ use gateway_core::engine::credential::ProviderAccountId;
 
 use gateway_admin::{
     AdminServices,
-    model::provider_credentials::{CredentialMutation, ImportCredentials, ProviderQuotaRequest},
+    model::provider_credentials::{ImportCredentials, ProviderQuotaRequest},
     ports::provider::ProviderAdminErrorKind,
 };
 
-use super::accounts::{
-    FakeAccountStore, FakeProviderAdmin, context, document, events, recorded, revision,
-};
-
-#[tokio::test]
-async fn xai_disable_should_commit_then_notify_the_stateless_provider() {
-    let events = events();
-    let provider = FakeProviderAdmin::new("xai", events.clone());
-    let store = FakeAccountStore::new("xai", events.clone());
-    let services = service(provider.clone(), store.clone()).await;
-
-    services
-        .xai()
-        .disable(mutation("acct_test"))
-        .await
-        .expect("disable credential");
-
-    assert_eq!(
-        recorded(&events),
-        [
-            "store.credential_details",
-            "store.set_enabled",
-            "provider.account_unavailable",
-        ]
-    );
-    assert_eq!(store.audit_requests(), ["request-xai"]);
-}
+use super::accounts::{FakeAccountStore, FakeProviderAdmin, context, document, events, recorded};
 
 #[tokio::test]
 async fn xai_import_should_prepare_before_atomic_store_commit() {
@@ -47,7 +21,6 @@ async fn xai_import_should_prepare_before_atomic_store_commit() {
         .xai()
         .import_document(ImportCredentials {
             context: context("import-xai"),
-            expected_config_revision: revision(3),
             document: document(),
         })
         .await
@@ -84,7 +57,6 @@ async fn xai_import_should_refresh_quota_for_every_imported_account() {
         .xai()
         .import_document(ImportCredentials {
             context: context("import-xai-batch"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
@@ -119,7 +91,6 @@ async fn xai_import_should_remain_successful_when_quota_refresh_fails() {
         .xai()
         .import_document(ImportCredentials {
             context: context("import-xai-quota-failure"),
-            expected_config_revision: revision(1),
             document: document(),
         })
         .await
@@ -136,11 +107,3 @@ async fn service(provider: Arc<FakeProviderAdmin>, store: Arc<FakeAccountStore>)
         .build()
         .await
 }
-
-fn mutation(account_id: &str) -> CredentialMutation {
-    CredentialMutation {
-        context: context("request-xai"),
-        expected_config_revision: revision(1),
-        account_id: ProviderAccountId::new(account_id).expect("account ID"),
-    }
-}

backend/crates/gateway-api/Cargo.toml

@@ -13,17 +13,18 @@ path = "tests/main.rs"
 
 [dependencies]
 axum = { version = "0.8.9", default-features = false, features = ["json", "query", "ws"] }
-base64 = "0.22.1"
+base64 = "0.23.0"
 bytes = "1.11.1"
 chrono = { version = "0.4.45", features = ["serde"] }
 futures = "0.3.32"
 gateway-admin = { path = "../gateway-admin" }
 gateway-core = { path = "../gateway-core" }
 gateway-protocol = { path = "../gateway-protocol" }
+secrecy = "0.10"
 serde = { version = "1.0.228", features = ["derive"] }
-serde_json = { version = "1.0.150", features = ["preserve_order"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 thiserror = "2.0.18"
-tokio = { version = "1.52.3", default-features = false, features = ["macros", "time"] }
+tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt", "sync", "time"] }
 tower-http = { version = "0.7.0", features = ["cors", "fs", "request-id", "timeout", "trace"] }
 tracing = "0.1.44"
 url = "2.5.8"
@@ -31,7 +32,9 @@ uuid = { version = "1.23.3", features = ["v7"] }
 
 [dev-dependencies]
 async-trait = "0.1.89"
-tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }
+axum = { version = "0.8.9", default-features = false, features = ["http1", "tokio"] }
+tokio = { version = "1.52.3", default-features = false, features = ["macros", "net", "rt-multi-thread", "test-util"] }
+tokio-tungstenite = "0.29.0"
 tower = { version = "0.5.3", features = ["util"] }
 
 [lints]

backend/crates/gateway-api/src/admin/account_groups.rs

@@ -0,0 +1,416 @@
+//! Account group HTTP wire and fixed routes.
+
+use std::collections::BTreeMap;
+
+use axum::{
+    Router,
+    extract::State,
+    http::StatusCode,
+    response::IntoResponse,
+    routing::{get, post},
+};
+use chrono::{DateTime, Utc};
+use gateway_admin::model::{
+    PageSize,
+    account_groups::{
+        AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupColor, AccountGroupListQuery,
+        AccountGroupMutation, AccountGroupPage, AccountGroupRecord, AccountGroupUsage,
+        CreateAccountGroup, DeleteAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+    },
+};
+use gateway_core::routing::AccountGroupId;
+use serde::{Deserialize, Serialize};
+
+use super::{
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    PageMeta, WireValidationError, wire::map_admin_service_error,
+};
+
+const DEFAULT_PAGE_SIZE: u32 = 50;
+const MAX_PAGE_SIZE: u32 = 200;
+
+#[derive(Debug, Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+struct ListAccountGroupsQuery {
+    page: Option<u32>,
+    page_size: Option<u32>,
+    search: Option<String>,
+    enabled: Option<bool>,
+}
+
+impl ListAccountGroupsQuery {
+    fn into_command(self) -> Result<AccountGroupListQuery, WireValidationError> {
+        let page = self.page.unwrap_or(1);
+        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+        if page == 0 || page_size == 0 || page_size > MAX_PAGE_SIZE {
+            return Err(WireValidationError::new("page"));
+        }
+        let search = self
+            .search
+            .map(|value| value.trim().to_owned())
+            .filter(|value| !value.is_empty());
+        if search
+            .as_deref()
+            .is_some_and(|value| value.len() > 256 || value.chars().any(char::is_control))
+        {
+            return Err(WireValidationError::new("search"));
+        }
+        Ok(AccountGroupListQuery {
+            page,
+            page_size: PageSize::new(
+                u16::try_from(page_size).map_err(|_| WireValidationError::new("pageSize"))?,
+            )
+            .map_err(|_| WireValidationError::new("pageSize"))?,
+            search,
+            enabled: self.enabled,
+        })
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+struct CreateAccountGroupRequest {
+    name: String,
+    description: Option<String>,
+    color: String,
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+struct UpdateAccountGroupRequest {
+    id: String,
+    name: String,
+    description: Option<String>,
+    color: String,
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+struct AccountGroupIdRequest {
+    id: String,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupView {
+    id: String,
+    name: String,
+    description: Option<String>,
+    color: String,
+    enabled: bool,
+    member_count: u64,
+    provider_counts: BTreeMap<String, u64>,
+    client_key_count: u64,
+    account_summary: AccountGroupAccountSummaryView,
+    capacity: AccountGroupCapacityView,
+    usage: AccountGroupUsageView,
+    created_at: DateTime<Utc>,
+    updated_at: DateTime<Utc>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupAccountSummaryView {
+    available: u64,
+    limited: u64,
+    total: u64,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupCapacityView {
+    used_slots: Option<u64>,
+    total_slots: u64,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupUsageView {
+    today_usd: String,
+    retained_total_usd: String,
+}
+
+impl From<AccountGroupRecord> for AccountGroupView {
+    fn from(record: AccountGroupRecord) -> Self {
+        Self {
+            id: record.id.to_string(),
+            name: record.name,
+            description: record.description,
+            color: record.color.as_str().to_owned(),
+            enabled: record.enabled,
+            member_count: record.member_count,
+            provider_counts: record.provider_counts,
+            client_key_count: record.client_key_count,
+            account_summary: account_summary_view(record.account_summary),
+            capacity: capacity_view(record.capacity),
+            usage: usage_view(record.usage),
+            created_at: record.created_at,
+            updated_at: record.updated_at,
+        }
+    }
+}
+
+fn account_summary_view(summary: AccountGroupAccountSummary) -> AccountGroupAccountSummaryView {
+    AccountGroupAccountSummaryView {
+        available: summary.available,
+        limited: summary.limited,
+        total: summary.total,
+    }
+}
+
+fn capacity_view(capacity: AccountGroupCapacity) -> AccountGroupCapacityView {
+    AccountGroupCapacityView {
+        used_slots: capacity.used_slots,
+        total_slots: capacity.total_slots,
+    }
+}
+
+fn usage_view(usage: AccountGroupUsage) -> AccountGroupUsageView {
+    AccountGroupUsageView {
+        today_usd: usage.today_usd.to_string(),
+        retained_total_usd: usage.retained_total_usd.to_string(),
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupPageData {
+    items: Vec<AccountGroupView>,
+    page: PageMeta,
+    config_revision: u64,
+}
+
+impl From<AccountGroupPage> for AccountGroupPageData {
+    fn from(page: AccountGroupPage) -> Self {
+        let total_pages = if page.total == 0 {
+            0
+        } else {
+            page.total.div_ceil(u64::from(page.page_size))
+        };
+        Self {
+            items: page.items.into_iter().map(Into::into).collect(),
+            page: PageMeta::new(
+                page.page,
+                u32::from(page.page_size),
+                page.total,
+                u32::try_from(total_pages).unwrap_or(u32::MAX),
+            ),
+            config_revision: page.config_revision.get(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct AccountGroupMutationData {
+    id: String,
+    record: Option<AccountGroupView>,
+    config_revision: u64,
+}
+
+impl From<AccountGroupMutation> for AccountGroupMutationData {
+    fn from(mutation: AccountGroupMutation) -> Self {
+        Self {
+            id: mutation.id.to_string(),
+            record: mutation.record.map(Into::into),
+            config_revision: mutation.config_revision.get(),
+        }
+    }
+}
+
+/// Construct all fixed account-group management routes.
+pub fn router<S>() -> Router<S>
+where
+    S: AdminSessionState + Clone + Send + Sync + 'static,
+{
+    Router::new()
+        .route("/api/admin/account-groups", get(list::<S>))
+        .route("/api/admin/account-groups/create", post(create::<S>))
+        .route("/api/admin/account-groups/update", post(update::<S>))
+        .route("/api/admin/account-groups/enable", post(enable::<S>))
+        .route("/api/admin/account-groups/disable", post(disable::<S>))
+        .route("/api/admin/account-groups/delete", post(delete::<S>))
+}
+
+async fn list<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ListAccountGroupsQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let result = state
+        .admin_services()
+        .account_groups()
+        .list(query.into_command().map_err(map_wire_error)?)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountGroupPageData::from(result)),
+    ))
+}
+
+async fn create<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<CreateAccountGroupRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    validate_group_fields(&request.name, request.description.as_deref())?;
+    mutation_response(
+        StatusCode::CREATED,
+        state
+            .admin_services()
+            .account_groups()
+            .create(
+                &auth.context().mutation_context(),
+                CreateAccountGroup {
+                    name: request.name,
+                    description: request.description,
+                    color: group_color(&request.color)?,
+                },
+            )
+            .await,
+    )
+}
+
+async fn update<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<UpdateAccountGroupRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    validate_group_fields(&request.name, request.description.as_deref())?;
+    mutation_response(
+        StatusCode::OK,
+        state
+            .admin_services()
+            .account_groups()
+            .update(
+                &auth.context().mutation_context(),
+                UpdateAccountGroup {
+                    id: group_id(request.id)?,
+                    name: request.name,
+                    description: request.description,
+                    color: group_color(&request.color)?,
+                },
+            )
+            .await,
+    )
+}
+
+async fn enable<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    set_enabled(auth, state, request, true).await
+}
+
+async fn disable<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    set_enabled(auth, state, request, false).await
+}
+
+async fn set_enabled<S>(
+    auth: AdminAuth,
+    state: S,
+    request: AccountGroupIdRequest,
+    enabled: bool,
+) -> Result<AdminResponse<AdminEnvelope<AccountGroupMutationData>>, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    mutation_response(
+        StatusCode::OK,
+        state
+            .admin_services()
+            .account_groups()
+            .set_enabled(
+                &auth.context().mutation_context(),
+                SetAccountGroupEnabled {
+                    id: group_id(request.id)?,
+                    enabled,
+                },
+            )
+            .await,
+    )
+}
+
+async fn delete<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    mutation_response(
+        StatusCode::OK,
+        state
+            .admin_services()
+            .account_groups()
+            .delete(
+                &auth.context().mutation_context(),
+                DeleteAccountGroup {
+                    id: group_id(request.id)?,
+                },
+            )
+            .await,
+    )
+}
+
+fn mutation_response(
+    status: StatusCode,
+    result: Result<AccountGroupMutation, gateway_admin::model::AdminError>,
+) -> Result<AdminResponse<AdminEnvelope<AccountGroupMutationData>>, AdminError> {
+    let result = result.map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        status,
+        AdminEnvelope::ok(AccountGroupMutationData::from(result)),
+    ))
+}
+
+fn group_id(value: String) -> Result<AccountGroupId, AdminError> {
+    AccountGroupId::new(value).map_err(|_| AdminError::bad_request("账号组 ID 不合法"))
+}
+
+fn group_color(value: &str) -> Result<AccountGroupColor, AdminError> {
+    AccountGroupColor::parse(value).ok_or_else(|| AdminError::bad_request("账号组颜色不合法"))
+}
+
+fn validate_group_fields(name: &str, description: Option<&str>) -> Result<(), AdminError> {
+    if name.trim() != name
+        || name.is_empty()
+        || name.chars().count() > 100
+        || name.chars().any(char::is_control)
+        || description
+            .is_some_and(|value| value.len() > 4096 || value.chars().any(char::is_control))
+    {
+        return Err(AdminError::bad_request("账号组请求不合法"));
+    }
+    Ok(())
+}
+
+fn map_wire_error(_: WireValidationError) -> AdminError {
+    AdminError::bad_request("账号组查询参数不合法")
+}
+
+fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
+    map_admin_service_error(error)
+}

backend/crates/gateway-api/src/admin/auth.rs

@@ -3,7 +3,7 @@
 use std::fmt;
 
 use axum::{
-    Extension, Json, Router,
+    Router,
     extract::{FromRequestParts, State},
     http::{HeaderMap, HeaderValue, StatusCode, header::SET_COOKIE, request::Parts},
     response::{IntoResponse, Response},
@@ -14,8 +14,9 @@ use gateway_admin::{
     model::auth::{AdminPrincipal, AdminRequestContext, LoginCommand, LoginError},
 };
 use serde::{Deserialize, Serialize};
+use tower_http::request_id::RequestId;
 
-use super::{AdminEnvelope, AdminError, AdminResponse};
+use super::{AdminEnvelope, AdminError, AdminJson, AdminResponse};
 
 const REQUEST_ID_HEADER: &str = "x-request-id";
 const ADMIN_SESSION_COOKIE: &str = "cpr_admin_session";
@@ -36,11 +37,6 @@ impl AdminAuth {
     pub const fn context(&self) -> &AdminRequestContext {
         &self.context
     }
-
-    #[must_use]
-    pub fn into_context(self) -> AdminRequestContext {
-        self.context
-    }
 }
 
 impl<S> FromRequestParts<S> for AdminAuth
@@ -51,22 +47,31 @@ where
 
     async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
         let principal = require_admin_auth(state, &parts.headers).await?;
-        let request_id = parts
-            .headers
-            .get(REQUEST_ID_HEADER)
-            .and_then(|value| value.to_str().ok())
-            .map(str::trim)
-            .filter(|value| !value.is_empty())
-            .ok_or_else(|| AdminError::internal("Missing admin request context"))?;
+        let request_id = admin_request_id(parts).ok_or_else(AdminError::internal)?;
         Ok(Self {
             context: AdminRequestContext {
                 principal,
-                request_id: request_id.to_owned(),
+                request_id,
             },
         })
     }
 }
 
+/// request-id 层按配置的 header 名注入，同时写入与名字无关的扩展；
+/// 优先读扩展，使自定义 header 名不会让管理请求失去请求上下文。
+/// header 回退覆盖未装配该层的调用方。
+fn admin_request_id(parts: &Parts) -> Option<String> {
+    parts
+        .extensions
+        .get::<RequestId>()
+        .map(RequestId::header_value)
+        .or_else(|| parts.headers.get(REQUEST_ID_HEADER))
+        .and_then(|value| value.to_str().ok())
+        .map(str::trim)
+        .filter(|value| !value.is_empty())
+        .map(ToOwned::to_owned)
+}
+
 pub async fn require_admin_session<S>(state: &S, headers: &HeaderMap) -> Result<String, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -79,7 +84,7 @@ where
     {
         Ok(Some(admin_user_id)) => Ok(admin_user_id),
         Ok(None) => Err(AdminError::admin_session_required()),
-        Err(_) => Err(AdminError::internal("Failed to validate admin session")),
+        Err(_) => Err(AdminError::internal()),
     }
 }
 
@@ -96,7 +101,7 @@ where
         {
             Ok(true) => Ok(AdminPrincipal::ApiKey),
             Ok(false) => Err(AdminError::invalid_admin_api_key()),
-            Err(_) => Err(AdminError::internal("Failed to validate admin API key")),
+            Err(_) => Err(AdminError::internal()),
         };
     }
 
@@ -185,22 +190,6 @@ impl Default for AdminLogoutData {
     }
 }
 
-/// 请求上下文解析出的客户端登录来源。
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct AdminLoginSource(String);
-
-impl AdminLoginSource {
-    #[must_use]
-    pub fn new(value: impl Into<String>) -> Self {
-        Self(value.into())
-    }
-
-    #[must_use]
-    pub fn as_str(&self) -> &str {
-        &self.0
-    }
-}
-
 /// 构造固定 GET/POST 管理员认证路由。
 pub fn router<S>() -> Router<S>
 where
@@ -214,24 +203,16 @@ where
 
 async fn login<S>(
     State(state): State<S>,
-    source: Option<Extension<AdminLoginSource>>,
-    Json(payload): Json<AdminLoginRequest>,
+    AdminJson(payload): AdminJson<AdminLoginRequest>,
 ) -> Result<Response, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let source = source
-        .as_ref()
-        .map_or("unknown", |Extension(source)| source.as_str());
     let (username, password) = payload.into_parts();
     let session = state
         .admin_services()
         .auth()
-        .login(LoginCommand {
-            username,
-            password,
-            source: source.to_owned(),
-        })
+        .login(LoginCommand { username, password })
         .await
         .map_err(map_login_error)?;
     let mut response = AdminResponse::new(
@@ -245,8 +226,7 @@ where
     );
     response.headers_mut().insert(
         SET_COOKIE,
-        HeaderValue::from_str(&cookie)
-            .map_err(|_| AdminError::internal("Failed to create admin session cookie"))?,
+        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
     );
     Ok(response)
 }
@@ -263,7 +243,7 @@ where
         .auth()
         .validate_session(admin_session_cookie(&headers).as_deref())
         .await
-        .map_err(|_| AdminError::internal("Failed to validate admin session"))?;
+        .map_err(|_| AdminError::internal())?;
     Ok(AdminResponse::new(
         StatusCode::OK,
         AdminEnvelope::ok(AdminSessionStatusData::new(authenticated)),
@@ -283,8 +263,7 @@ where
     let cookie = format!("{ADMIN_SESSION_COOKIE}=; {ADMIN_SESSION_COOKIE_ATTRS}; Max-Age=0");
     response.headers_mut().insert(
         SET_COOKIE,
-        HeaderValue::from_str(&cookie)
-            .map_err(|_| AdminError::internal("Failed to clear admin session cookie"))?,
+        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
     );
     Ok(response)
 }
@@ -300,7 +279,6 @@ fn admin_session_cookie(headers: &HeaderMap) -> Option<String> {
 fn map_login_error(error: LoginError) -> AdminError {
     match error {
         LoginError::InvalidCredentials => AdminError::invalid_admin_credentials(),
-        LoginError::Throttled => AdminError::too_many_login_attempts(),
-        LoginError::Unavailable => AdminError::internal("Failed to create admin session"),
+        LoginError::Unavailable => AdminError::internal(),
     }
 }

backend/crates/gateway-api/src/admin/backups.rs

@@ -0,0 +1,459 @@
+//! 备份设置、计划、手动创建、记录、下载与删除路由。
+//!
+//! 路径统一位于 `/api/admin/settings/backups/*`，内部由独立 `BackupService` 承担业务。
+
+use axum::{
+    Router,
+    extract::State,
+    http::StatusCode,
+    response::IntoResponse,
+    routing::{get, post},
+};
+use chrono::{DateTime, Utc};
+use gateway_admin::model::backup::{
+    BackupRecord, BackupSettings, BackupStatus, BackupTriggerKind, ConnectionTestResult,
+    UpdateBackupScheduleCommand, UpdateBackupStorageCommand,
+};
+use secrecy::{ExposeSecret as _, SecretString};
+use serde::{Deserialize, Serialize};
+
+use super::{
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminPageData, AdminQuery, AdminResponse,
+    AdminSessionState, PageMeta, wire::map_admin_service_error,
+};
+
+/// 备份设置视图；`secretAccessKey` 返回已保存的明文凭据，由前端掩码显示。
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct BackupSettingsView {
+    pub storage_revision: u64,
+    pub endpoint: Option<String>,
+    pub region: Option<String>,
+    pub bucket: Option<String>,
+    pub access_key_id: Option<String>,
+    pub secret_access_key: Option<String>,
+    pub prefix: Option<String>,
+    pub force_path_style: bool,
+    pub verified: bool,
+    pub schedule_enabled: bool,
+    pub cron_expression: Option<String>,
+    pub schedule_timezone: Option<String>,
+    pub retention_days: u32,
+    pub retention_count: u32,
+    pub next_run_at: Option<DateTime<Utc>>,
+    pub last_verified_at: Option<DateTime<Utc>>,
+    pub updated_at: DateTime<Utc>,
+}
+
+impl From<BackupSettings> for BackupSettingsView {
+    fn from(settings: BackupSettings) -> Self {
+        let verified = settings.storage_verified();
+        Self {
+            storage_revision: settings.storage_revision,
+            endpoint: settings.endpoint,
+            region: settings.region,
+            bucket: settings.bucket,
+            access_key_id: settings.access_key_id,
+            secret_access_key: settings
+                .secret_access_key
+                .map(|secret| secret.expose_secret().to_owned()),
+            prefix: settings.prefix,
+            force_path_style: settings.force_path_style,
+            verified,
+            schedule_enabled: settings.schedule_enabled,
+            cron_expression: settings.cron_expression,
+            schedule_timezone: settings.schedule_timezone,
+            retention_days: settings.retention_days,
+            retention_count: settings.retention_count,
+            next_run_at: settings.next_run_at,
+            last_verified_at: settings.last_verified_at,
+            updated_at: settings.updated_at,
+        }
+    }
+}
+
+/// 更新 S3 存储配置请求；`secretAccessKey` 缺省表示保留旧值。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct UpdateBackupStorageRequest {
+    pub endpoint: String,
+    pub region: String,
+    pub bucket: String,
+    pub access_key_id: String,
+    #[serde(default)]
+    pub secret_access_key: Option<String>,
+    pub prefix: String,
+    pub force_path_style: bool,
+}
+
+/// 更新调度配置请求。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct UpdateBackupScheduleRequest {
+    pub schedule_enabled: bool,
+    pub cron_expression: String,
+    pub schedule_timezone: String,
+    pub retention_days: u32,
+    pub retention_count: u32,
+}
+
+/// 备份记录 wire 视图。
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct BackupRecordView {
+    pub id: String,
+    pub trigger_kind: String,
+    pub status: String,
+    pub scheduled_at: Option<DateTime<Utc>>,
+    pub object_key: String,
+    pub size_bytes: Option<u64>,
+    pub sha256: Option<String>,
+    pub attempt_count: u32,
+    pub error_code: Option<String>,
+    pub error_message: Option<String>,
+    pub started_at: Option<DateTime<Utc>>,
+    pub completed_at: Option<DateTime<Utc>>,
+    pub expires_at: Option<DateTime<Utc>>,
+    pub created_at: DateTime<Utc>,
+    pub updated_at: DateTime<Utc>,
+}
+
+impl From<BackupRecord> for BackupRecordView {
+    fn from(record: BackupRecord) -> Self {
+        Self {
+            id: record.id,
+            trigger_kind: record.trigger_kind.to_string(),
+            status: record.status.to_string(),
+            scheduled_at: record.scheduled_at,
+            object_key: record.object_key,
+            size_bytes: record.size_bytes,
+            sha256: record.sha256,
+            attempt_count: record.attempt_count,
+            error_code: record.error_code,
+            error_message: record.error_message,
+            started_at: record.started_at,
+            completed_at: record.completed_at,
+            expires_at: record.expires_at,
+            created_at: record.created_at,
+            updated_at: record.updated_at,
+        }
+    }
+}
+
+/// 记录列表查询参数。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub struct BackupRecordsQuery {
+    pub page: Option<u32>,
+    pub page_size: Option<u16>,
+    pub status: Option<String>,
+    pub trigger: Option<String>,
+}
+
+/// 下载地址请求。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct BackupIdRequest {
+    pub backup_id: String,
+}
+
+/// 下载地址响应。
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DownloadUrlView {
+    pub url: String,
+    pub file_name: String,
+    pub expires_in_seconds: u64,
+}
+
+impl From<gateway_admin::model::backup::DownloadUrlResult> for DownloadUrlView {
+    fn from(result: gateway_admin::model::backup::DownloadUrlResult) -> Self {
+        Self {
+            url: result.url,
+            file_name: result.file_name,
+            expires_in_seconds: result.expires_in.as_secs(),
+        }
+    }
+}
+
+/// 连接测试响应。
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ConnectionTestView {
+    pub ok: bool,
+    pub stage: String,
+    pub code: Option<String>,
+    pub message: String,
+}
+
+impl From<ConnectionTestResult> for ConnectionTestView {
+    fn from(result: ConnectionTestResult) -> Self {
+        Self {
+            ok: result.ok,
+            stage: result.stage.to_owned(),
+            code: result.code.map(str::to_owned),
+            message: result.message,
+        }
+    }
+}
+
+/// 构造固定 GET/POST 备份路由。
+pub fn router<S>() -> Router<S>
+where
+    S: AdminSessionState + Clone + Send + Sync + 'static,
+{
+    Router::new()
+        .route("/api/admin/settings/backups", get(backup_settings::<S>))
+        .route(
+            "/api/admin/settings/backups/storage/update",
+            post(update_backup_storage::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/storage/test",
+            post(test_backup_storage::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/schedule/update",
+            post(update_backup_schedule::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/records",
+            get(backup_records::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/create",
+            post(create_backup::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/download-url",
+            post(download_backup_url::<S>),
+        )
+        .route(
+            "/api/admin/settings/backups/delete",
+            post(delete_backup::<S>),
+        )
+}
+
+async fn backup_settings<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let settings = state
+        .admin_services()
+        .backups()
+        .load_settings()
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BackupSettingsView::from(settings)),
+    ))
+}
+
+async fn update_backup_storage<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<UpdateBackupStorageRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = UpdateBackupStorageCommand {
+        endpoint: request.endpoint,
+        region: request.region,
+        bucket: request.bucket,
+        access_key_id: request.access_key_id,
+        secret_access_key: request.secret_access_key.map(SecretString::from),
+        prefix: request.prefix,
+        force_path_style: request.force_path_style,
+    };
+    let settings = state
+        .admin_services()
+        .backups()
+        .update_storage(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BackupSettingsView::from(settings)),
+    ))
+}
+
+async fn test_backup_storage<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let result = state
+        .admin_services()
+        .backups()
+        .test_connection(&auth.context().mutation_context())
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(ConnectionTestView::from(result)),
+    ))
+}
+
+async fn update_backup_schedule<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<UpdateBackupScheduleRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = UpdateBackupScheduleCommand {
+        schedule_enabled: request.schedule_enabled,
+        cron_expression: request.cron_expression,
+        schedule_timezone: request.schedule_timezone,
+        retention_days: request.retention_days,
+        retention_count: request.retention_count,
+    };
+    let settings = state
+        .admin_services()
+        .backups()
+        .update_schedule(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BackupSettingsView::from(settings)),
+    ))
+}
+
+async fn backup_records<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<BackupRecordsQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let page_size = gateway_admin::model::PageSize::new(query.page_size.unwrap_or(20))
+        .map_err(|_| AdminError::bad_request("pageSize 不合法"))?;
+    let page = query.page.unwrap_or(1);
+    if page == 0 {
+        return Err(AdminError::bad_request("page 不合法"));
+    }
+    let status = match query.status.as_deref() {
+        None => None,
+        Some(value) => BackupStatus::parse(value)
+            .map(Some)
+            .ok_or_else(|| AdminError::bad_request("status 不合法"))?,
+    };
+    let trigger = match query.trigger.as_deref() {
+        None => None,
+        Some(value) => BackupTriggerKind::parse(value)
+            .map(Some)
+            .ok_or_else(|| AdminError::bad_request("trigger 不合法"))?,
+    };
+    let domain_query = gateway_admin::model::backup::BackupRecordListQuery {
+        page,
+        page_size,
+        status,
+        trigger,
+    };
+    let page_result = state
+        .admin_services()
+        .backups()
+        .list_records(domain_query)
+        .await
+        .map_err(map_service_error)?;
+    let meta = PageMeta::new(
+        page_result.page,
+        u32::from(page_result.page_size.get()),
+        page_result.total,
+        page_result.total_pages(),
+    );
+    let items: Vec<BackupRecordView> = page_result
+        .items
+        .into_iter()
+        .map(BackupRecordView::from)
+        .collect();
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AdminPageData::new(items, meta)),
+    ))
+}
+
+async fn create_backup<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    body: Option<AdminJson<CreateBackupRequest>>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let expires_at = body
+        .and_then(|body| body.0.expires_in_days)
+        .filter(|&days| days > 0)
+        .map(|days| Utc::now() + chrono::Duration::days(i64::from(days)));
+    let record = state
+        .admin_services()
+        .backups()
+        .create_backup(&auth.context().mutation_context(), expires_at)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::ACCEPTED,
+        AdminEnvelope::ok(BackupRecordView::from(record)),
+    ))
+}
+
+/// 创建备份请求；`expiresInDays` 为 0 或缺省表示不设置过期时间。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct CreateBackupRequest {
+    pub expires_in_days: Option<u32>,
+}
+
+async fn download_backup_url<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<BackupIdRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let result = state
+        .admin_services()
+        .backups()
+        .download_url(&auth.context().mutation_context(), &request.backup_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(DownloadUrlView::from(result)),
+    ))
+}
+
+async fn delete_backup<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<BackupIdRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let record = state
+        .admin_services()
+        .backups()
+        .delete_backup(&auth.context().mutation_context(), &request.backup_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BackupRecordView::from(record)),
+    ))
+}
+
+fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
+    map_admin_service_error(error)
+}

backend/crates/gateway-api/src/admin/client_keys.rs

@@ -4,32 +4,29 @@ use std::fmt;
 
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use chrono::{DateTime, Utc};
-use gateway_admin::model::{
-    Revision,
-    client_keys::{
-        ClientKeyCursor, ClientKeyCursorValue as DomainCursorValue, ClientKeyListQuery,
-        ClientKeyMutation, ClientKeyPage, ClientKeyPageSize, ClientKeyRecord, ClientKeySecret,
-        ClientKeySort as DomainSort, ClientKeySortField as DomainSortField, CreateClientKey,
-        CreatedClientKey, DeleteClientKey, SetClientKeyEnabled, SortDirection, UpdateClientKey,
-    },
+use gateway_admin::model::client_keys::{
+    ClientKeyCursor, ClientKeyCursorValue as DomainCursorValue, ClientKeyListQuery,
+    ClientKeyMutation, ClientKeyPage, ClientKeyPageSize, ClientKeyRecord, ClientKeySecret,
+    ClientKeySort as DomainSort, ClientKeySortField as DomainSortField, CreateClientKey,
+    CreatedClientKey, DeleteClientKey, SetClientKeyEnabled, SortDirection, UpdateClientKey,
 };
 use gateway_core::{
     policy::{ClientApiKeyId, RateLimits},
-    routing::ProviderKind,
+    routing::AccountGroupId,
 };
 use serde::{Deserialize, Serialize};
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::{HeaderValue, StatusCode, header::CACHE_CONTROL},
     response::{IntoResponse, Response},
     routing::{get, post},
 };
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, WireValidationError,
-    wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    WireValidationError, wire::map_admin_service_error,
 };
 
 const MAX_CURSOR_BYTES: usize = 512;
@@ -138,10 +135,9 @@ impl ClientKeySort {
 #[derive(Debug, Clone, PartialEq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct CreateClientKeyRequest {
-    expected_config_revision: u64,
     name: String,
     label: Option<String>,
-    provider_kind: String,
+    group_ids: Vec<String>,
     max_concurrency: u64,
     requests_per_minute: u64,
 }
@@ -149,18 +145,15 @@ pub struct CreateClientKeyRequest {
 impl CreateClientKeyRequest {
     /// 校验 wire 边界并直接构造管理用例命令。
     pub fn into_command(self) -> Result<CreateClientKey, WireValidationError> {
-        validate_revision(self.expected_config_revision)?;
         validate_required_text(&self.name, "name")?;
         validate_optional_text(self.label.as_deref(), "label")?;
-        validate_provider_kind(&self.provider_kind)?;
+        let group_ids = validate_group_ids(self.group_ids)?;
         validate_limit(self.max_concurrency, "maxConcurrency")?;
         validate_limit(self.requests_per_minute, "requestsPerMinute")?;
         Ok(CreateClientKey {
-            expected_config_revision: revision(self.expected_config_revision)?,
             name: self.name,
             label: self.label,
-            provider_kind: ProviderKind::new(self.provider_kind)
-                .map_err(|_| WireValidationError::new("providerKind"))?,
+            group_ids,
             limits: RateLimits {
                 max_concurrency: self.max_concurrency,
                 requests_per_minute: self.requests_per_minute,
@@ -174,10 +167,9 @@ impl CreateClientKeyRequest {
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UpdateClientKeyRequest {
     id: String,
-    expected_config_revision: u64,
     name: String,
     label: Option<String>,
-    provider_kind: String,
+    group_ids: Vec<String>,
     max_concurrency: u64,
     requests_per_minute: u64,
 }
@@ -186,19 +178,16 @@ impl UpdateClientKeyRequest {
     /// 校验 wire 边界并直接构造管理用例命令。
     pub fn into_command(self) -> Result<UpdateClientKey, WireValidationError> {
         validate_required_text(&self.id, "id")?;
-        validate_revision(self.expected_config_revision)?;
         validate_required_text(&self.name, "name")?;
         validate_optional_text(self.label.as_deref(), "label")?;
-        validate_provider_kind(&self.provider_kind)?;
+        let group_ids = validate_group_ids(self.group_ids)?;
         validate_limit(self.max_concurrency, "maxConcurrency")?;
         validate_limit(self.requests_per_minute, "requestsPerMinute")?;
         Ok(UpdateClientKey {
-            expected_config_revision: revision(self.expected_config_revision)?,
             id: client_key_id(self.id, "clientKeyMutationNotFound")?,
             name: self.name,
             label: self.label,
-            provider_kind: ProviderKind::new(self.provider_kind)
-                .map_err(|_| WireValidationError::new("providerKind"))?,
+            group_ids,
             limits: RateLimits {
                 max_concurrency: self.max_concurrency,
                 requests_per_minute: self.requests_per_minute,
@@ -207,12 +196,11 @@ impl UpdateClientKeyRequest {
     }
 }
 
-/// 只携带 ID 与配置 revision 的 Client Key mutation 请求。
+/// 只携带 ID 的 Client Key mutation 请求。
 #[derive(Debug, Clone, PartialEq, Eq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
-pub struct ClientKeyRevisionRequest {
+pub struct ClientKeyMutationRequest {
     id: String,
-    expected_config_revision: u64,
 }
 
 /// 读取一次完整 Key 的 ID query。
@@ -233,20 +221,15 @@ impl ClientKeyIdQuery {
     }
 }
 
-impl ClientKeyRevisionRequest {
-    /// 校验请求并取出 ID 与 revision。
-    pub fn into_parts(self) -> Result<(String, u64), WireValidationError> {
+impl ClientKeyMutationRequest {
+    /// 校验请求并取出 ID。
+    pub fn into_id(self) -> Result<String, WireValidationError> {
         validate_required_text(&self.id, "id")?;
-        validate_revision(self.expected_config_revision)?;
-        Ok((self.id, self.expected_config_revision))
+        Ok(self.id)
     }
 
-    fn into_command_parts(self) -> Result<(ClientApiKeyId, Revision), WireValidationError> {
-        let (id, expected_config_revision) = self.into_parts()?;
-        Ok((
-            client_key_id(id, "clientKeyMutationNotFound")?,
-            revision(expected_config_revision)?,
-        ))
+    fn into_domain_id(self) -> Result<ClientApiKeyId, WireValidationError> {
+        client_key_id(self.into_id()?, "clientKeyMutationNotFound")
     }
 }
 
@@ -257,7 +240,9 @@ pub struct ClientKeyView {
     id: String,
     name: String,
     label: Option<String>,
-    provider_kind: String,
+    routing_scope: &'static str,
+    groups: Vec<ClientKeyGroupView>,
+    provider_kinds: Vec<String>,
     prefix: String,
     enabled: bool,
     max_concurrency: u64,
@@ -267,13 +252,42 @@ pub struct ClientKeyView {
     last_used_at: Option<DateTime<Utc>>,
 }
 
+#[derive(Debug, Clone, PartialEq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ClientKeyGroupView {
+    id: String,
+    name: String,
+    color: String,
+    enabled: bool,
+}
+
 impl From<ClientKeyRecord> for ClientKeyView {
     fn from(record: ClientKeyRecord) -> Self {
+        let routing_scope = if record.groups.is_empty() {
+            "all"
+        } else {
+            "groups"
+        };
         Self {
             id: record.id.to_string(),
             name: record.name,
             label: record.label,
-            provider_kind: record.provider_kind.to_string(),
+            routing_scope,
+            groups: record
+                .groups
+                .into_iter()
+                .map(|group| ClientKeyGroupView {
+                    id: group.id.to_string(),
+                    name: group.name,
+                    color: group.color.as_str().to_owned(),
+                    enabled: group.enabled,
+                })
+                .collect(),
+            provider_kinds: record
+                .provider_kinds
+                .into_iter()
+                .map(|provider| provider.to_string())
+                .collect(),
             prefix: record.prefix,
             enabled: record.enabled,
             max_concurrency: record.limits.max_concurrency,
@@ -289,7 +303,6 @@ impl From<ClientKeyRecord> for ClientKeyView {
 #[derive(Debug, Clone, PartialEq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct ClientKeyListData {
-    config_revision: u64,
     items: Vec<ClientKeyView>,
     next_cursor: Option<String>,
     total: u64,
@@ -298,14 +311,8 @@ pub struct ClientKeyListData {
 impl ClientKeyListData {
     /// 构造 Client Key 列表响应。
     #[must_use]
-    pub fn new(
-        config_revision: u64,
-        items: Vec<ClientKeyView>,
-        next_cursor: Option<String>,
-        total: u64,
-    ) -> Self {
+    pub fn new(items: Vec<ClientKeyView>, next_cursor: Option<String>, total: u64) -> Self {
         Self {
-            config_revision,
             items,
             next_cursor,
             total,
@@ -325,7 +332,6 @@ impl TryFrom<ClientKeyPage> for ClientKeyListData {
             .map(encode_client_key_cursor)
             .transpose()?;
         Ok(Self::new(
-            page.config_revision.get(),
             page.items.into_iter().map(Into::into).collect(),
             next_cursor,
             page.total,
@@ -337,7 +343,6 @@ impl TryFrom<ClientKeyPage> for ClientKeyListData {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct CreatedClientKeyData {
-    config_revision: u64,
     id: String,
     prefix: String,
     plaintext_key: String,
@@ -346,9 +351,8 @@ pub struct CreatedClientKeyData {
 impl CreatedClientKeyData {
     /// 构造一次性创建响应。
     #[must_use]
-    pub fn new(config_revision: u64, id: String, prefix: String, plaintext_key: String) -> Self {
+    pub fn new(id: String, prefix: String, plaintext_key: String) -> Self {
         Self {
-            config_revision,
             id,
             prefix,
             plaintext_key,
@@ -359,7 +363,6 @@ impl CreatedClientKeyData {
 impl From<CreatedClientKey> for CreatedClientKeyData {
     fn from(created: CreatedClientKey) -> Self {
         Self::new(
-            created.config_revision.get(),
             created.secret.record.id.to_string(),
             created.secret.record.prefix.clone(),
             created.secret.expose_for_response().to_owned(),
@@ -371,7 +374,6 @@ impl fmt::Debug for CreatedClientKeyData {
     fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
         formatter
             .debug_struct("CreatedClientKeyData")
-            .field("config_revision", &self.config_revision)
             .field("id", &self.id)
             .field("prefix", &self.prefix)
             .field("plaintext_key", &"[REDACTED]")
@@ -417,24 +419,20 @@ impl fmt::Debug for RevealedClientKeyData {
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct MutatedClientKeyData {
-    config_revision: u64,
     id: String,
 }
 
 impl MutatedClientKeyData {
     /// 构造 mutation 响应。
     #[must_use]
-    pub fn new(config_revision: u64, id: String) -> Self {
-        Self {
-            config_revision,
-            id,
-        }
+    pub fn new(id: String) -> Self {
+        Self { id }
     }
 }
 
 impl From<ClientKeyMutation> for MutatedClientKeyData {
     fn from(mutation: ClientKeyMutation) -> Self {
-        Self::new(mutation.config_revision.get(), mutation.id.to_string())
+        Self::new(mutation.id.to_string())
     }
 }
 
@@ -582,18 +580,6 @@ fn wire_cursor(cursor: ClientKeyCursor) -> Result<ClientKeyCursorData, WireValid
     Ok(cursor)
 }
 
-fn validate_revision(value: u64) -> Result<(), WireValidationError> {
-    if value == 0 {
-        return Err(WireValidationError::new("expectedConfigRevision"));
-    }
-    Ok(())
-}
-
-fn revision(value: u64) -> Result<Revision, WireValidationError> {
-    validate_revision(value)?;
-    Revision::new(value).map_err(|_| WireValidationError::new("expectedConfigRevision"))
-}
-
 fn client_key_id(
     value: String,
     field: &'static str,
@@ -615,21 +601,20 @@ fn validate_required_text(value: &str, field: &'static str) -> Result<(), WireVa
     Ok(())
 }
 
-fn validate_provider_kind(value: &str) -> Result<(), WireValidationError> {
-    let valid = !value.is_empty()
-        && value.len() <= 64
-        && value.bytes().enumerate().all(|(index, byte)| {
-            byte.is_ascii_lowercase()
-                || byte.is_ascii_digit()
-                || (byte == b'-' && index > 0 && index + 1 < value.len())
-        })
-        && !value.starts_with('-')
-        && !value.ends_with('-');
-    if valid {
-        Ok(())
-    } else {
-        Err(WireValidationError::new("providerKind"))
+fn validate_group_ids(values: Vec<String>) -> Result<Vec<AccountGroupId>, WireValidationError> {
+    if values.len() > 1000
+        || values
+            .iter()
+            .collect::<std::collections::BTreeSet<_>>()
+            .len()
+            != values.len()
+    {
+        return Err(WireValidationError::new("groupIds"));
     }
+    values
+        .into_iter()
+        .map(|value| AccountGroupId::new(value).map_err(|_| WireValidationError::new("groupIds")))
+        .collect()
 }
 
 fn validate_optional_text(
@@ -684,7 +669,7 @@ where
 async fn list_client_keys<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<ListClientKeysQuery>,
+    AdminQuery(query): AdminQuery<ListClientKeysQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -695,15 +680,14 @@ where
         .list(query.into_command().map_err(map_wire_error)?)
         .await
         .map_err(map_service_error)?;
-    let data = ClientKeyListData::try_from(result)
-        .map_err(|_| AdminError::internal("Failed to encode client key cursor"))?;
+    let data = ClientKeyListData::try_from(result).map_err(|_| AdminError::internal())?;
     Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
 }
 
 async fn create_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<CreateClientKeyRequest>,
+    AdminJson(payload): AdminJson<CreateClientKeyRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -724,7 +708,7 @@ where
 async fn reveal_client_key<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<ClientKeyIdQuery>,
+    AdminQuery(query): AdminQuery<ClientKeyIdQuery>,
 ) -> Result<Response, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -750,7 +734,7 @@ where
 async fn update_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<UpdateClientKeyRequest>,
+    AdminJson(payload): AdminJson<UpdateClientKeyRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -768,23 +752,19 @@ where
 async fn disable_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
     mutation_response(
         state
             .admin_services()
             .client_keys()
             .set_enabled(
                 &auth.context().mutation_context(),
-                SetClientKeyEnabled {
-                    expected_config_revision,
-                    id,
-                    enabled: false,
-                },
+                SetClientKeyEnabled { id, enabled: false },
             )
             .await,
     )
@@ -793,23 +773,19 @@ where
 async fn enable_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
     mutation_response(
         state
             .admin_services()
             .client_keys()
             .set_enabled(
                 &auth.context().mutation_context(),
-                SetClientKeyEnabled {
-                    expected_config_revision,
-                    id,
-                    enabled: true,
-                },
+                SetClientKeyEnabled { id, enabled: true },
             )
             .await,
     )
@@ -818,23 +794,17 @@ where
 async fn delete_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyRevisionRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let (id, expected_config_revision) = payload.into_command_parts().map_err(map_wire_error)?;
+    let id = payload.into_domain_id().map_err(map_wire_error)?;
     mutation_response(
         state
             .admin_services()
             .client_keys()
-            .delete(
-                &auth.context().mutation_context(),
-                DeleteClientKey {
-                    expected_config_revision,
-                    id,
-                },
-            )
+            .delete(&auth.context().mutation_context(), DeleteClientKey { id })
             .await,
     )
 }
@@ -851,16 +821,14 @@ fn mutation_response(
 
 fn map_wire_error(error: WireValidationError) -> AdminError {
     match error.field() {
-        "cursor" => AdminError::bad_request("Invalid client key cursor"),
-        "clientKeyRevealNotFound" => AdminError::not_found("Client API key was not found"),
-        "clientKeyMutationNotFound" => AdminError::not_found("client API key was not found"),
-        "expectedConfigRevision" => {
-            AdminError::bad_request("expectedConfigRevision must be positive")
+        "cursor" => AdminError::bad_request("Client API Key 游标不合法"),
+        "clientKeyRevealNotFound" | "clientKeyMutationNotFound" => {
+            AdminError::not_found("Client API Key 不存在")
         }
-        _ => AdminError::bad_request("Invalid client API key request"),
+        _ => AdminError::bad_request("Client API Key 请求不合法"),
     }
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Configuration repository unavailable")
+    map_admin_service_error(error)
 }

backend/crates/gateway-api/src/admin/extract.rs

@@ -0,0 +1,87 @@
+//! 管理端 JSON 与 Query extractor 的稳定 rejection 映射。
+
+use axum::{
+    Json,
+    extract::{
+        FromRequest, FromRequestParts, OptionalFromRequest, Query, Request,
+        rejection::{JsonRejection, QueryRejection},
+    },
+    http::{StatusCode, request::Parts},
+};
+use serde::de::DeserializeOwned;
+
+use super::AdminError;
+
+/// 将 Axum JSON rejection 收口为管理端错误信封。
+pub struct AdminJson<T>(pub T);
+
+impl<T, S> FromRequest<S> for AdminJson<T>
+where
+    T: DeserializeOwned,
+    S: Send + Sync,
+{
+    type Rejection = AdminError;
+
+    async fn from_request(request: Request, state: &S) -> Result<Self, Self::Rejection> {
+        <Json<T> as FromRequest<S>>::from_request(request, state)
+            .await
+            .map(|Json(value)| Self(value))
+            .map_err(map_json_rejection)
+    }
+}
+
+impl<T, S> OptionalFromRequest<S> for AdminJson<T>
+where
+    T: DeserializeOwned,
+    S: Send + Sync,
+{
+    type Rejection = AdminError;
+
+    async fn from_request(request: Request, state: &S) -> Result<Option<Self>, Self::Rejection> {
+        <Json<T> as OptionalFromRequest<S>>::from_request(request, state)
+            .await
+            .map(|value| value.map(|Json(value)| Self(value)))
+            .map_err(map_json_rejection)
+    }
+}
+
+/// 将 Axum Query rejection 收口为管理端错误信封。
+pub struct AdminQuery<T>(pub T);
+
+impl<T, S> FromRequestParts<S> for AdminQuery<T>
+where
+    T: DeserializeOwned,
+    S: Send + Sync,
+{
+    type Rejection = AdminError;
+
+    async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
+        Query::<T>::from_request_parts(parts, state)
+            .await
+            .map(|Query(value)| Self(value))
+            .map_err(map_query_rejection)
+    }
+}
+
+fn map_json_rejection(rejection: JsonRejection) -> AdminError {
+    let status = rejection.status();
+    match rejection {
+        JsonRejection::JsonSyntaxError(_) => AdminError::malformed_json(),
+        JsonRejection::JsonDataError(_) => {
+            AdminError::invalid_request(StatusCode::UNPROCESSABLE_ENTITY, "请求字段不合法")
+        }
+        JsonRejection::MissingJsonContentType(_) => AdminError::invalid_request(
+            StatusCode::UNSUPPORTED_MEDIA_TYPE,
+            "请求必须使用 application/json",
+        ),
+        JsonRejection::BytesRejection(_) if status == StatusCode::PAYLOAD_TOO_LARGE => {
+            AdminError::invalid_request(status, "请求体过大")
+        }
+        JsonRejection::BytesRejection(_) => AdminError::internal(),
+        _ => AdminError::invalid_request(status, "请求体不合法"),
+    }
+}
+
+fn map_query_rejection(_: QueryRejection) -> AdminError {
+    AdminError::bad_request("请求参数不合法")
+}

backend/crates/gateway-api/src/admin/mod.rs

@@ -5,17 +5,23 @@ use axum::{
     http::{HeaderValue, header},
     middleware,
     response::Response,
+    routing::any,
 };
 
+pub mod account_groups;
 pub mod accounts;
 pub mod auth;
+pub mod backups;
 pub mod client_keys;
+mod extract;
 pub mod observability;
+pub mod presenter;
 pub mod settings;
 pub mod system;
 pub mod wire;
 
 pub use auth::{AdminAuth, AdminSessionState};
+pub use extract::{AdminJson, AdminQuery};
 pub use wire::{
     ADMIN_OK_CODE, ADMIN_OK_MESSAGE, AdminEnvelope, AdminError, AdminErrorBody, AdminErrorCode,
     AdminPageData, AdminResponse, PageMeta, WireValidationError,
@@ -27,18 +33,32 @@ where
     S: AdminSessionState + Clone + Send + Sync + 'static,
 {
     Router::new()
+        .merge(account_groups::router::<S>())
         .merge(accounts::router::<S>())
         .merge(auth::router::<S>())
+        .merge(backups::router::<S>())
         .merge(client_keys::router::<S>())
         .merge(observability::router::<S>())
         .merge(settings::router::<S>())
         .merge(system::router::<S>())
+        .method_not_allowed_fallback(method_not_allowed)
+        .route("/api/admin", any(admin_not_found))
+        .route("/api/admin/{*path}", any(admin_not_found))
         .layer(middleware::map_response(no_store))
 }
 
+async fn method_not_allowed() -> AdminError {
+    AdminError::method_not_allowed()
+}
+
+async fn admin_not_found() -> AdminError {
+    AdminError::admin_route_not_found()
+}
+
 async fn no_store(mut response: Response) -> Response {
     response
         .headers_mut()
-        .insert(header::CACHE_CONTROL, HeaderValue::from_static("no-store"));
+        .entry(header::CACHE_CONTROL)
+        .or_insert(HeaderValue::from_static("no-store"));
     response
 }

backend/crates/gateway-api/src/admin/observability/mod.rs

@@ -0,0 +1,25 @@
+//! Dashboard、用量与诊断查询的 wire 映射和固定路由。
+
+use std::collections::BTreeMap;
+
+use axum::{Router, extract::State, http::StatusCode, response::IntoResponse, routing::get};
+use chrono::{DateTime, Duration, Utc};
+use gateway_admin::model::{PageSize as DomainPageSize, observability as domain};
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+use super::presenter::{format_compact_number, format_decimal_currency, format_number};
+use super::{
+    AdminAuth, AdminEnvelope, AdminError, AdminQuery, AdminResponse, AdminSessionState,
+    WireValidationError, wire::map_admin_service_error,
+};
+
+mod presenter;
+mod query;
+mod routes;
+mod wire;
+
+pub(crate) use presenter::*;
+pub use query::*;
+pub use routes::*;
+pub use wire::*;

backend/crates/gateway-api/src/admin/observability/query.rs

@@ -0,0 +1,374 @@
+//! 查询 wire 类型、校验与领域命令映射。
+
+use super::*;
+
+/// 观测列表默认页大小。
+pub const DEFAULT_PAGE_SIZE: u16 = 50;
+/// 观测列表允许的最大页大小。
+pub const MAX_PAGE_SIZE: u16 = 100;
+
+/// Dashboard 查询参数。
+#[derive(Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct DashboardQuery {
+    pub kind: Option<String>,
+    pub start_time: Option<String>,
+    pub end_time: Option<String>,
+}
+
+impl DashboardQuery {
+    /// 解析 dashboard 趋势类型。
+    pub fn trend_kind(&self) -> Result<TrendKind, WireValidationError> {
+        TrendKind::parse(self.kind.as_deref())
+    }
+}
+
+/// 逻辑请求列表、汇总和洞察查询参数。
+#[derive(Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct UsageQuery {
+    pub current_page: Option<u32>,
+    pub page_size: Option<u16>,
+    pub kind: Option<String>,
+    pub outcome: Option<String>,
+    pub client_api_key_id: Option<String>,
+    pub provider: Option<String>,
+    pub request_id: Option<String>,
+    pub account_id: Option<String>,
+    pub route: Option<String>,
+    pub model: Option<String>,
+    pub status_code: Option<i64>,
+    pub transport: Option<String>,
+    pub attempt_index: Option<i64>,
+    pub response_id: Option<String>,
+    pub upstream_request_id: Option<String>,
+    pub search: Option<String>,
+    pub start_time: Option<String>,
+    pub end_time: Option<String>,
+}
+
+impl UsageQuery {
+    /// 校验 Element Plus 风格的页码分页字段。
+    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
+        let current_page = self.current_page.unwrap_or(1);
+        if current_page == 0 {
+            return Err(WireValidationError::new("currentPage"));
+        }
+        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+        if page_size == 0 || page_size > MAX_PAGE_SIZE {
+            return Err(WireValidationError::new("pageSize"));
+        }
+        Ok((current_page, page_size))
+    }
+}
+
+/// 详情查询参数。
+#[derive(Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct DetailQuery {
+    pub id: String,
+}
+
+impl DetailQuery {
+    /// 校验详情 ID，错误不回显输入值。
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_text(&self.id, "id")
+    }
+}
+
+/// 诊断聚合查询参数。
+#[derive(Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct DiagnosticsQuery {
+    pub dimension: Option<String>,
+    pub start_time: Option<String>,
+    pub end_time: Option<String>,
+    pub provider: Option<String>,
+    pub model: Option<String>,
+    pub status_code: Option<i64>,
+    pub search: Option<String>,
+}
+
+impl DiagnosticsQuery {
+    /// 解析诊断维度。
+    pub fn dimension(&self) -> Result<DiagnosticDimension, WireValidationError> {
+        DiagnosticDimension::parse(self.dimension.as_deref())
+    }
+}
+
+/// 运维错误查询参数。
+#[derive(Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct OpsQuery {
+    pub current_page: Option<u32>,
+    pub page_size: Option<u16>,
+    pub kind: Option<String>,
+    pub client_api_key_id: Option<String>,
+    pub provider: Option<String>,
+    pub request_id: Option<String>,
+    pub account_id: Option<String>,
+    pub route: Option<String>,
+    pub model: Option<String>,
+    pub status_code: Option<i64>,
+    pub client_status_code: Option<i64>,
+    pub upstream_status_code: Option<i64>,
+    pub transport: Option<String>,
+    pub attempt_index: Option<i64>,
+    pub failure_class: Option<String>,
+    pub response_id: Option<String>,
+    pub upstream_request_id: Option<String>,
+    pub search: Option<String>,
+    pub start_time: Option<String>,
+    pub end_time: Option<String>,
+}
+
+impl OpsQuery {
+    /// 校验 Element Plus 风格的页码分页字段。
+    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
+        let current_page = self.current_page.unwrap_or(1);
+        if current_page == 0 {
+            return Err(WireValidationError::new("currentPage"));
+        }
+        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+        if page_size == 0 || page_size > MAX_PAGE_SIZE {
+            return Err(WireValidationError::new("pageSize"));
+        }
+        Ok((current_page, page_size))
+    }
+}
+
+/// Dashboard 趋势类型。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize)]
+#[serde(rename_all = "lowercase")]
+pub enum TrendKind {
+    Usage,
+    Latency,
+    Errors,
+}
+
+impl TrendKind {
+    /// 从 query 值解析趋势类型。
+    pub fn parse(value: Option<&str>) -> Result<Self, WireValidationError> {
+        match trimmed(value) {
+            None | Some("usage") => Ok(Self::Usage),
+            Some("latency") => Ok(Self::Latency),
+            Some("errors") => Ok(Self::Errors),
+            Some(_) => Err(WireValidationError::new("kind")),
+        }
+    }
+}
+
+/// 诊断聚合维度。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum DiagnosticDimension {
+    Model,
+    Account,
+    ApiKey,
+    Provider,
+    Transport,
+    Failure,
+    Status,
+}
+
+impl DiagnosticDimension {
+    /// 从 query 值解析诊断维度。
+    pub fn parse(value: Option<&str>) -> Result<Self, WireValidationError> {
+        match trimmed(value) {
+            None | Some("model") => Ok(Self::Model),
+            Some("account") => Ok(Self::Account),
+            Some("apiKey" | "api_key") => Ok(Self::ApiKey),
+            Some("provider") => Ok(Self::Provider),
+            Some("transport") => Ok(Self::Transport),
+            Some("failureClass" | "failure_class") => Ok(Self::Failure),
+            Some("status") => Ok(Self::Status),
+            Some(_) => Err(WireValidationError::new("dimension")),
+        }
+    }
+
+    /// 返回终态响应中的稳定维度名称。
+    #[must_use]
+    pub const fn display_name(self) -> &'static str {
+        match self {
+            Self::Model => "model",
+            Self::Account => "account",
+            Self::ApiKey => "apiKey",
+            Self::Provider => "provider",
+            Self::Transport => "transport",
+            Self::Failure => "failureClass",
+            Self::Status => "status",
+        }
+    }
+}
+
+/// 解析 RFC3339 时间；错误不回显原始值。
+pub fn parse_datetime(value: Option<&str>) -> Result<Option<DateTime<Utc>>, WireValidationError> {
+    let Some(value) = trimmed(value) else {
+        return Ok(None);
+    };
+    DateTime::parse_from_rfc3339(value)
+        .map(|value| Some(value.with_timezone(&Utc)))
+        .map_err(|_| WireValidationError::new("timeRange"))
+}
+
+/// 解析 HTTP 状态码。
+pub fn parse_status(value: Option<i64>) -> Result<Option<u16>, WireValidationError> {
+    value
+        .map(|value| {
+            u16::try_from(value)
+                .ok()
+                .filter(|value| (100..=599).contains(value))
+                .ok_or_else(|| WireValidationError::new("statusCode"))
+        })
+        .transpose()
+}
+
+/// 解析尝试序号。
+pub fn parse_attempt_index(value: Option<i64>) -> Result<Option<u32>, WireValidationError> {
+    value
+        .map(|value| {
+            u32::try_from(value)
+                .ok()
+                .filter(|value| *value > 0 && *value <= i32::MAX as u32)
+                .ok_or_else(|| WireValidationError::new("attemptIndex"))
+        })
+        .transpose()
+}
+
+pub(crate) fn require_text(value: &str, field: &'static str) -> Result<(), WireValidationError> {
+    if value.trim().is_empty() {
+        Err(WireValidationError::new(field))
+    } else {
+        Ok(())
+    }
+}
+
+pub(crate) fn trimmed(value: Option<&str>) -> Option<&str> {
+    value.map(str::trim).filter(|value| !value.is_empty())
+}
+
+pub(crate) fn domain_trend_kind(kind: TrendKind) -> domain::TrendKind {
+    match kind {
+        TrendKind::Usage => domain::TrendKind::Usage,
+        TrendKind::Latency => domain::TrendKind::Latency,
+        TrendKind::Errors => domain::TrendKind::Errors,
+    }
+}
+
+pub(crate) fn domain_diagnostic_dimension(
+    dimension: DiagnosticDimension,
+) -> domain::DiagnosticDimension {
+    match dimension {
+        DiagnosticDimension::Model => domain::DiagnosticDimension::Model,
+        DiagnosticDimension::Account => domain::DiagnosticDimension::Account,
+        DiagnosticDimension::ApiKey => domain::DiagnosticDimension::ApiKey,
+        DiagnosticDimension::Provider => domain::DiagnosticDimension::Provider,
+        DiagnosticDimension::Transport => domain::DiagnosticDimension::Transport,
+        DiagnosticDimension::Failure => domain::DiagnosticDimension::Failure,
+        DiagnosticDimension::Status => domain::DiagnosticDimension::Status,
+    }
+}
+
+pub(crate) fn request_outcome(
+    value: Option<String>,
+) -> Result<Option<domain::RequestOutcome>, WireValidationError> {
+    non_empty(value)
+        .map(|value| {
+            domain::RequestOutcome::new(value).map_err(|_| WireValidationError::new("outcome"))
+        })
+        .transpose()
+}
+
+pub(crate) fn usage_range(
+    start: Option<&str>,
+    end: Option<&str>,
+) -> Result<domain::TimeRange, WireValidationError> {
+    let end = parse_datetime(end)?.unwrap_or_else(Utc::now);
+    let start = parse_datetime(start)?.unwrap_or(end - Duration::days(7));
+    domain::TimeRange::new(start, end).map_err(|_| WireValidationError::new("timeRange"))
+}
+
+pub(crate) fn dashboard_today_range(
+    start: Option<&str>,
+    end: Option<&str>,
+) -> Result<domain::TimeRange, WireValidationError> {
+    let end = parse_datetime(end)?.unwrap_or_else(Utc::now);
+    let start = parse_datetime(start)?.unwrap_or_else(|| domain::china_day_start(end));
+    domain::TimeRange::new(start, end).map_err(|_| WireValidationError::new("timeRange"))
+}
+
+pub(crate) fn usage_filter(query: &UsageQuery) -> Result<domain::UsageFilter, WireValidationError> {
+    let outcome = query.outcome.clone().or_else(|| {
+        non_empty(query.kind.clone()).filter(|value| {
+            matches!(
+                value.as_str(),
+                "running" | "succeeded" | "failed" | "cancelled" | "incomplete"
+            )
+        })
+    });
+    Ok(domain::UsageFilter {
+        client_api_key_ref: non_empty(query.client_api_key_id.clone()),
+        request_id: non_empty(query.request_id.clone()),
+        provider_account_ref: non_empty(query.account_id.clone()),
+        operation: non_empty(query.route.clone()),
+        provider_kind: non_empty(query.provider.clone()),
+        model: non_empty(query.model.clone()),
+        outcome: request_outcome(outcome)?,
+        status_code: parse_status(query.status_code)?,
+        transport: non_empty(query.transport.clone()),
+        attempt_index: parse_attempt_index(query.attempt_index)?,
+        response_id: non_empty(query.response_id.clone()),
+        upstream_request_id: non_empty(query.upstream_request_id.clone()),
+        search: non_empty(query.search.clone()),
+    })
+}
+
+pub(crate) fn usage_command(query: &UsageQuery) -> Result<domain::UsageQuery, WireValidationError> {
+    let (current_page, page_size) = query.validate_pagination()?;
+    let page_size_value =
+        DomainPageSize::new(page_size).map_err(|_| WireValidationError::new("pageSize"))?;
+    Ok(domain::UsageQuery {
+        range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
+        filter: usage_filter(query)?,
+        current_page,
+        page_size: page_size_value,
+    })
+}
+
+pub(crate) fn ops_command(query: &OpsQuery) -> Result<domain::OpsErrorQuery, WireValidationError> {
+    let (current_page, page_size) = query.validate_pagination()?;
+    let page_size_value =
+        DomainPageSize::new(page_size).map_err(|_| WireValidationError::new("pageSize"))?;
+    let status_code = parse_status(
+        query
+            .upstream_status_code
+            .or(query.client_status_code)
+            .or(query.status_code),
+    )?;
+    Ok(domain::OpsErrorQuery {
+        range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
+        filter: domain::OpsErrorFilter {
+            client_api_key_ref: non_empty(query.client_api_key_id.clone()),
+            request_id: non_empty(query.request_id.clone()),
+            provider_kind: non_empty(query.provider.clone()),
+            provider_account_ref: non_empty(query.account_id.clone()),
+            operation: non_empty(query.kind.clone()),
+            endpoint: non_empty(query.route.clone()),
+            model: non_empty(query.model.clone()),
+            transport: non_empty(query.transport.clone()),
+            attempt_index: parse_attempt_index(query.attempt_index)?,
+            response_id: non_empty(query.response_id.clone()),
+            upstream_request_id: non_empty(query.upstream_request_id.clone()),
+            failure_kind: non_empty(query.failure_class.clone()),
+            status_code,
+            search: non_empty(query.search.clone()),
+        },
+        current_page,
+        page_size: page_size_value,
+    })
+}
+
+pub(crate) fn non_empty(value: Option<String>) -> Option<String> {
+    value
+        .map(|value| value.trim().to_owned())
+        .filter(|value| !value.is_empty())
+}

backend/crates/gateway-api/src/admin/observability/routes.rs

@@ -0,0 +1,212 @@
+//! 固定 `/api/admin` 观测路由与 handler。
+
+use super::*;
+
+pub fn router<S>() -> Router<S>
+where
+    S: AdminSessionState + Clone + Send + Sync + 'static,
+{
+    Router::new()
+        .route("/api/admin/dashboard/summary", get(dashboard_summary::<S>))
+        .route("/api/admin/dashboard/trend", get(dashboard_trend::<S>))
+        .route("/api/admin/usage/records", get(usage_records::<S>))
+        .route(
+            "/api/admin/usage/records/detail",
+            get(usage_record_detail::<S>),
+        )
+        .route(
+            "/api/admin/usage/records/summary",
+            get(usage_records_summary::<S>),
+        )
+        .route(
+            "/api/admin/usage/insights/overview",
+            get(usage_insights_overview::<S>),
+        )
+        .route(
+            "/api/admin/usage/insights/diagnostics",
+            get(usage_insights_diagnostics::<S>),
+        )
+        .route("/api/admin/operations/errors", get(ops_errors::<S>))
+}
+
+pub(crate) async fn dashboard_summary<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<DashboardQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let kind = query.trend_kind().map_err(map_wire_error)?;
+    // 概览默认按中国时区当日统计，与单独趋势接口保持同一口径。
+    let range = dashboard_today_range(query.start_time.as_deref(), query.end_time.as_deref())
+        .map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .dashboard_summary(range, domain_trend_kind(kind))
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(dashboard_view(result, kind)),
+    ))
+}
+
+pub(crate) async fn dashboard_trend<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<DashboardQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let kind = query.trend_kind().map_err(map_wire_error)?;
+    let range = dashboard_today_range(query.start_time.as_deref(), query.end_time.as_deref())
+        .map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .dashboard_trend(range, domain_trend_kind(kind))
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(trend_view(result, kind)),
+    ))
+}
+
+pub(crate) async fn usage_records<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = usage_command(&query).map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .usage_records(command)
+        .await
+        .map_err(map_service_error)?;
+    let data = usage_page_view(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+pub(crate) async fn usage_record_detail<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<DetailQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    query.validate().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .usage_record_detail(query.id.trim())
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(usage_detail_view(result)),
+    ))
+}
+
+pub(crate) async fn usage_records_summary<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let range = usage_range(query.start_time.as_deref(), query.end_time.as_deref())
+        .map_err(map_wire_error)?;
+    let filter = usage_filter(&query).map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .usage_summary(range, filter)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(usage_summary_view(result)),
+    ))
+}
+
+pub(crate) async fn usage_insights_overview<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let range = usage_range(query.start_time.as_deref(), query.end_time.as_deref())
+        .map_err(map_wire_error)?;
+    let filter = usage_filter(&query).map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .usage_insights(range, filter)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(usage_insights_view(result)),
+    ))
+}
+
+pub(crate) async fn usage_insights_diagnostics<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<DiagnosticsQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let dimension = query.dimension().map_err(map_wire_error)?;
+    let range = usage_range(query.start_time.as_deref(), query.end_time.as_deref())
+        .map_err(map_wire_error)?;
+    let filter = domain::UsageFilter {
+        provider_kind: non_empty(query.provider),
+        model: non_empty(query.model),
+        status_code: parse_status(query.status_code).map_err(map_wire_error)?,
+        search: non_empty(query.search),
+        ..domain::UsageFilter::default()
+    };
+    let result = state
+        .admin_services()
+        .observability()
+        .diagnostics(range, filter, domain_diagnostic_dimension(dimension))
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(diagnostics_view(result, dimension)),
+    ))
+}
+
+pub(crate) async fn ops_errors<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<OpsQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = ops_command(&query).map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .observability()
+        .ops_errors(command)
+        .await
+        .map_err(map_service_error)?;
+    let data = ops_page_view(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}

backend/crates/gateway-api/src/admin/observability/wire.rs

@@ -0,0 +1,805 @@
+//! 响应 DTO 与固定 wire 形状。
+
+use super::*;
+
+/// 观测列表响应数据。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct PageData<T> {
+    pub items: Vec<T>,
+    pub current_page: u32,
+    pub page_size: u16,
+    pub total: u64,
+}
+
+/// Token 详情展示。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TokenDetailsView {
+    pub input_tokens: Option<u64>,
+    pub output_tokens: Option<u64>,
+    pub cached_tokens: Option<u64>,
+    pub cache_write_tokens: Option<u64>,
+    pub reasoning_tokens: Option<u64>,
+    pub image_input_tokens: Option<u64>,
+    pub image_output_tokens: Option<u64>,
+    pub total_tokens: Option<u64>,
+    pub input_tokens_display: String,
+    pub output_tokens_display: String,
+    pub cached_tokens_display: String,
+    pub cache_write_tokens_display: String,
+    pub reasoning_tokens_display: String,
+    pub image_input_tokens_display: String,
+    pub image_output_tokens_display: String,
+    pub total_tokens_display: String,
+}
+
+/// 按货币展示的成本。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct CostView {
+    pub currency: String,
+    pub estimated_amount: String,
+}
+
+/// 成本覆盖状态计数。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct CostCoverageView {
+    pub known: u64,
+    pub partial: u64,
+    pub unknown: u64,
+    pub not_billable: u64,
+}
+
+/// Provider 受控价格规则生成的单次请求费用明细展示。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct BillingView {
+    pub input_amount_display: String,
+    pub output_amount_display: String,
+    pub cache_read_amount_display: String,
+    pub cache_write_amount_display: String,
+    pub standard_amount_display: String,
+    pub total_amount_display: String,
+    pub input_price_display: String,
+    pub output_price_display: String,
+    pub cache_read_price_display: String,
+    pub cache_write_price_display: String,
+    pub service_tier_display: String,
+    pub multiplier_display: String,
+}
+
+/// 使用记录表格的窄展示。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageListRecordView {
+    pub id: String,
+    pub provider: Option<String>,
+    pub authentication_kind: Option<String>,
+    pub account_id: Option<String>,
+    pub account_email: Option<String>,
+    pub account_name: Option<String>,
+    pub route: String,
+    pub model: Option<String>,
+    pub requested_model: Option<String>,
+    pub upstream_model: Option<String>,
+    pub service_tier: Option<String>,
+    pub client_transport: String,
+    pub upstream_transport: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: bool,
+    pub token_details: TokenDetailsView,
+    pub billing: Option<BillingView>,
+    pub latency_details: UsageLatencyDetailsView,
+    pub first_token_latency_ms: Option<u64>,
+    pub latency_ms: Option<u64>,
+    pub created_at: DateTime<Utc>,
+    pub created_at_display: String,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+}
+
+/// 单条逻辑请求详情展示。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageRecordView {
+    pub id: String,
+    pub request_id: String,
+    pub client_api_key_id: Option<String>,
+    pub routing_scope: String,
+    pub routing_group_refs: Vec<String>,
+    pub routing_group_names_snapshot: Vec<String>,
+    pub kind: String,
+    pub provider: Option<String>,
+    pub authentication_kind: Option<String>,
+    pub account_id: Option<String>,
+    pub account_email: Option<String>,
+    pub account_name: Option<String>,
+    pub route: String,
+    pub model: Option<String>,
+    pub requested_model: Option<String>,
+    pub upstream_model: Option<String>,
+    pub service_tier: Option<String>,
+    pub status_code: Option<i64>,
+    pub client_transport: String,
+    pub upstream_transport: Option<String>,
+    pub protocol: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub http_version: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub client_status_code: Option<i64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_status_code: Option<i64>,
+    pub websocket_pool: Option<WebSocketPoolMetadataView>,
+    pub image_generation_requested: bool,
+    pub image_generation_succeeded: Option<bool>,
+    pub latency_details: UsageLatencyDetailsView,
+    pub attempt_index: Option<i64>,
+    pub attempt_count: u64,
+    pub response_id: Option<String>,
+    pub upstream_request_id: Option<String>,
+    pub latency_ms: Option<u64>,
+    pub first_token_ms: Option<u64>,
+    pub input_tokens: Option<u64>,
+    pub output_tokens: Option<u64>,
+    pub cached_tokens: Option<u64>,
+    pub cache_write_tokens: Option<u64>,
+    pub reasoning_tokens: Option<u64>,
+    pub image_input_tokens: Option<u64>,
+    pub image_output_tokens: Option<u64>,
+    pub message: String,
+    /// Provider 安全观测；Core 字段由顶层字段提供，不再复制进 metadata。
+    pub metadata: BTreeMap<String, Value>,
+    pub created_at: DateTime<Utc>,
+    pub created_at_display: String,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub compact: Option<bool>,
+    pub request_kind: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub token_details: TokenDetailsView,
+    pub billing: Option<BillingView>,
+    pub costs: Vec<CostView>,
+    pub cost_coverage: CostCoverageView,
+    pub first_token_latency_ms: Option<u64>,
+    pub first_token_latency_ms_display: String,
+    pub latency_ms_display: String,
+    pub logical_outcome: String,
+}
+
+/// WebSocket 池决策的稳定形状；与 Provider 选择逻辑无关。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct WebSocketPoolMetadataView {
+    pub kind: String,
+}
+
+/// 逻辑请求在上游和输出阶段测得的时延事实。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageLatencyDetailsView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub admission_decision_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub account_selection_wait_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub capacity_used_slots: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub capacity_total_slots: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub transport_decision_wait_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub ws_connect_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub upstream_headers_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub first_event_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub first_reasoning_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub first_text_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub first_token_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub openai_processing_ms: Option<u64>,
+}
+
+/// 单次上游尝试展示。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageAttemptView {
+    pub id: String,
+    pub attempt_index: u32,
+    pub trigger: String,
+    pub provider: String,
+    pub model: Option<String>,
+    pub transport: String,
+    pub send_state: String,
+    pub outcome: String,
+    pub downstream_committed: bool,
+    pub status_code: Option<u16>,
+    pub provider_error_code: Option<String>,
+    pub failure_class: Option<String>,
+    pub cost_estimate_status: String,
+    pub estimated_cost_amount: Option<String>,
+    pub estimated_cost_currency: Option<String>,
+    pub input_tokens: Option<u64>,
+    pub output_tokens: Option<u64>,
+    pub cached_tokens: Option<u64>,
+    pub total_tokens: Option<u64>,
+    pub first_token_ms: Option<u64>,
+    pub latency_ms: Option<u64>,
+    pub credential_name: Option<String>,
+    pub account_id: Option<String>,
+    pub account_name: Option<String>,
+    pub account_email: Option<String>,
+    pub authentication_kind: Option<String>,
+    pub started_at: DateTime<Utc>,
+    pub completed_at: Option<DateTime<Utc>>,
+}
+
+/// 逻辑请求详情与其尝试列表。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageRecordDetailView {
+    #[serde(flatten)]
+    pub request: UsageRecordView,
+    pub attempts: Vec<UsageAttemptView>,
+    /// 尝试列表是否完整；best-effort 下恒为 false。
+    pub attempts_complete: bool,
+}
+
+/// Dashboard 趋势数据。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TrendData {
+    pub kind: TrendKind,
+    pub points: Vec<TrendPointView>,
+    pub summary: Vec<TrendSummaryView>,
+}
+
+/// Dashboard 单个趋势桶。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct TrendPointView {
+    pub time: String,
+    pub bucket: DateTime<Utc>,
+    pub label: String,
+    pub requests: String,
+    pub requests_value: u64,
+    pub input_tokens: String,
+    pub input_tokens_value: u64,
+    pub output_tokens: String,
+    pub output_tokens_value: u64,
+    pub cached_tokens: String,
+    pub cached_tokens_value: u64,
+    pub cache_hit_rate_value: f64,
+    pub tokens_value: u64,
+    pub errors: String,
+    pub errors_value: u64,
+    pub latency: String,
+    pub latency_value: Option<u64>,
+    pub max_latency: String,
+    pub max_latency_value: Option<u64>,
+    pub min_latency: String,
+    pub min_latency_value: Option<u64>,
+    pub success_rate: String,
+    pub success_rate_value: Option<f64>,
+    pub first_token_p50_ms: Option<f64>,
+    pub first_token_p95_ms: Option<f64>,
+    pub latency_p95_ms: Option<f64>,
+    pub output_throughput_p50: Option<u64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub capacity_utilization: Option<f64>,
+}
+
+/// Dashboard 趋势摘要。
+#[derive(Debug, Serialize)]
+pub struct TrendSummaryView {
+    pub label: String,
+    pub value: String,
+    pub ratio: Option<String>,
+}
+
+/// Dashboard 卡片集合。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardCardsView {
+    pub credentials: DashboardCredentialsCardView,
+    pub traffic: DashboardTrafficCardView,
+    pub tokens: DashboardTokensCardView,
+    pub cache: DashboardCacheCardView,
+}
+
+/// Dashboard 上游凭据卡片。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardCredentialsCardView {
+    pub total: String,
+    pub total_value: u64,
+    pub available: String,
+    pub available_value: u64,
+    pub unavailable: String,
+    pub unavailable_value: u64,
+}
+
+/// Dashboard 流量卡片。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardTrafficCardView {
+    pub today_requests: String,
+    pub today_requests_value: u64,
+    pub yesterday_requests_value: u64,
+    pub total_requests: String,
+}
+
+/// Dashboard token 卡片。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardTokensCardView {
+    pub today_tokens: String,
+    pub today_tokens_value: u64,
+    pub yesterday_tokens_value: u64,
+    pub total_tokens: String,
+    pub total_billing_amount_usd: String,
+}
+
+/// Dashboard 缓存卡片。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardCacheCardView {
+    pub today_hit_rate: String,
+    pub today_hit_rate_value: Option<f64>,
+    pub yesterday_hit_rate_value: Option<f64>,
+    pub total_hit_rate: String,
+    pub total_cached_tokens: String,
+    pub average_first_token_latency_ms: String,
+}
+
+/// 旧 Dashboard 账号概览卡片所需的 Provider 安全投影。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardAccountUsageView {
+    pub id: String,
+    pub provider: String,
+    pub authentication_kind: String,
+    pub email: String,
+    pub plan_type: Option<String>,
+    pub tokens: String,
+    pub request_count: u64,
+    pub request_buckets: Vec<DashboardAccountRequestBucketView>,
+    pub quota_used_percent: Option<f64>,
+    pub last_used: String,
+}
+
+/// Dashboard 账号单小时请求数。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardAccountRequestBucketView {
+    pub bucket_start: DateTime<Utc>,
+    pub request_count: u64,
+}
+
+/// Provider 账号池的持久事实汇总。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardPoolSummaryView {
+    pub total: u64,
+    pub normal: u64,
+    pub quota_exhausted: u64,
+    pub rate_limited: u64,
+    pub disabled: u64,
+    pub error: u64,
+}
+
+/// 同 target 账号调度容量；Redis 未提供聚合事实时运行中槽位保持空值。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardCapacityInfoView {
+    pub max_concurrent_per_account: u64,
+    pub total_slots: u64,
+    pub used_slots: Option<u64>,
+    pub available_slots: Option<u64>,
+}
+
+/// 逻辑请求指标展示。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct RequestMetricsView {
+    pub request_count: u64,
+    pub success_count: u64,
+    pub failure_count: u64,
+    pub cancelled_count: u64,
+    pub incomplete_count: u64,
+    pub caller_error_count: u64,
+    pub input_tokens: u64,
+    pub output_tokens: u64,
+    pub cached_tokens: u64,
+    pub cache_write_tokens: u64,
+    pub reasoning_tokens: u64,
+    pub total_tokens: u64,
+}
+
+/// 上游尝试指标展示。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AttemptMetricsView {
+    pub attempt_count: u64,
+    pub success_count: u64,
+    pub failure_count: u64,
+    pub cancelled_count: u64,
+    pub incomplete_count: u64,
+    pub rate_limited_count: u64,
+    pub auth_failure_count: u64,
+    pub provider5xx_count: u64,
+    pub cost_coverage: CostCoverageView,
+    pub costs: Vec<CostView>,
+}
+
+/// 健康时间线单点。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct HealthTimelinePointView {
+    pub time: String,
+    pub status: String,
+    pub reliability_display: String,
+    pub success_requests: u64,
+    pub failed_requests: u64,
+    pub cancelled_requests: u64,
+    pub incomplete_requests: u64,
+    pub caller_error_requests: u64,
+}
+
+/// Dashboard 健康时间线。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct HealthTimelineView {
+    pub title: String,
+    pub description: String,
+    pub reliability_display: String,
+    pub status: String,
+    pub success_requests: u64,
+    pub failed_requests: u64,
+    pub cancelled_requests: u64,
+    pub incomplete_requests: u64,
+    pub caller_error_requests: u64,
+    pub points: Vec<HealthTimelinePointView>,
+}
+
+/// Dashboard 展示的实际 Provider 上游请求身份。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardWireProfileView {
+    pub provider: String,
+    pub product: String,
+    pub version: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub build: Option<String>,
+    pub target: DashboardWireTargetView,
+    pub user_agent: String,
+    pub attributes: Vec<DashboardWireAttributeView>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub verified_at: Option<DateTime<Utc>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub release: Option<DashboardDesktopReleaseView>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardWireAttributeView {
+    pub label: String,
+    pub value: String,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardWireTargetView {
+    pub os_type: String,
+    pub os_version: String,
+    pub arch: String,
+    pub terminal: String,
+}
+
+/// 发布检查与启动画像分离；未检查时使用明确的 `unchecked` 状态。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardDesktopReleaseView {
+    pub status: DashboardDesktopReleaseStatusView,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub checked_at: Option<DateTime<Utc>>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub latest_version: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub latest_build: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub error: Option<String>,
+}
+
+/// Dashboard 发布检查的稳定 wire 状态。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "snake_case")]
+pub enum DashboardDesktopReleaseStatusView {
+    Unchecked,
+    Aligned,
+    ReviewRequired,
+    CheckFailed,
+}
+
+impl From<domain::DesktopReleaseStatus> for DashboardDesktopReleaseStatusView {
+    fn from(status: domain::DesktopReleaseStatus) -> Self {
+        match status {
+            domain::DesktopReleaseStatus::Unchecked => Self::Unchecked,
+            domain::DesktopReleaseStatus::Current => Self::Aligned,
+            domain::DesktopReleaseStatus::UpdateAvailable => Self::ReviewRequired,
+            domain::DesktopReleaseStatus::Failed => Self::CheckFailed,
+        }
+    }
+}
+
+/// Dashboard 汇总响应数据。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DashboardDataView {
+    pub cards: DashboardCardsView,
+    pub trend: TrendData,
+    pub health_timeline: HealthTimelineView,
+    pub wire_profiles: Vec<DashboardWireProfileView>,
+    pub account_usage: Vec<DashboardAccountUsageView>,
+    pub usage_records: Vec<UsageListRecordView>,
+    pub pool_summary: DashboardPoolSummaryView,
+    pub capacity_info: DashboardCapacityInfoView,
+    pub rotation_strategy: String,
+}
+
+/// 用量汇总响应数据。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageSummaryView {
+    pub total_requests: String,
+    pub input_tokens: String,
+    pub output_tokens: String,
+    pub cached_tokens: String,
+    pub cache_write_tokens: String,
+    pub total_tokens: String,
+    pub average_latency_ms: String,
+    pub logical_requests: RequestMetricsView,
+    pub attempts: AttemptMetricsView,
+}
+
+/// 洞察健康趋势点。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewHealthPointView {
+    pub bucket: DateTime<Utc>,
+    pub label: String,
+    pub total_requests: u64,
+    pub success_requests: u64,
+    pub failed_requests: u64,
+    pub cancelled_requests: u64,
+    pub incomplete_requests: u64,
+    pub caller_error_requests: u64,
+    pub error_rate: f64,
+}
+
+/// 洞察健康摘要。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewHealthView {
+    pub total_requests: u64,
+    pub success_requests: u64,
+    pub failed_requests: u64,
+    pub cancelled_requests: u64,
+    pub incomplete_requests: u64,
+    pub caller_error_requests: u64,
+    pub success_rate: f64,
+    pub completion_rate: f64,
+    pub request_change_rate: Option<f64>,
+    pub success_rate_change: Option<f64>,
+    pub points: Vec<OverviewHealthPointView>,
+}
+
+/// 洞察性能趋势点。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewPerformancePointView {
+    pub bucket: DateTime<Utc>,
+    pub label: String,
+    pub latency_p50_ms: Option<f64>,
+    pub latency_p95_ms: Option<f64>,
+    pub latency_p99_ms: Option<f64>,
+    pub first_token_p50_ms: Option<f64>,
+    pub first_token_p95_ms: Option<f64>,
+    pub first_token_p99_ms: Option<f64>,
+    pub admission_decision_p50_ms: Option<f64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p50_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization: Option<f64>,
+    pub capacity_utilization_p95: Option<f64>,
+}
+
+/// 洞察性能摘要。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewPerformanceView {
+    pub latency_p50_ms: Option<f64>,
+    pub latency_p95_ms: Option<f64>,
+    pub latency_p99_ms: Option<f64>,
+    pub first_token_p50_ms: Option<f64>,
+    pub first_token_p95_ms: Option<f64>,
+    pub first_token_p99_ms: Option<f64>,
+    pub admission_decision_p50_ms: Option<f64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p50_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization: Option<f64>,
+    pub capacity_utilization_p95: Option<f64>,
+    pub latency_coverage: f64,
+    pub first_token_coverage: f64,
+    pub admission_decision_coverage: f64,
+    pub account_selection_wait_coverage: f64,
+    pub capacity_coverage: f64,
+    pub points: Vec<OverviewPerformancePointView>,
+}
+
+/// 洞察成本趋势点。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewCostPointView {
+    pub bucket: DateTime<Utc>,
+    pub label: String,
+    pub input_tokens: u64,
+    pub output_tokens: u64,
+    pub cached_tokens: u64,
+    pub total_tokens: u64,
+    pub estimated_cost: Option<String>,
+    pub standard_cost: Option<String>,
+    pub no_cache_cost: Option<String>,
+    pub cache_savings: Option<String>,
+    pub cached_token_rate: f64,
+    pub cache_hit_request_rate: Option<f64>,
+}
+
+/// 洞察成本摘要。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OverviewCostView {
+    pub estimated_cost: Option<String>,
+    pub standard_cost: Option<String>,
+    pub no_cache_cost: Option<String>,
+    pub cache_savings: Option<String>,
+    pub tier_premium: Option<String>,
+    pub cost_per_request: Option<String>,
+    pub cost_per_successful_request: Option<String>,
+    pub tokens_per_request: f64,
+    pub cached_token_rate: f64,
+    pub cache_hit_request_rate: Option<f64>,
+    pub input_tokens: u64,
+    pub output_tokens: u64,
+    pub cached_tokens: u64,
+    pub total_tokens: u64,
+    pub points: Vec<OverviewCostPointView>,
+    pub costs: Vec<CostView>,
+    pub coverage: CostCoverageView,
+}
+
+/// Provider 维度洞察摘要。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ProviderOverviewView {
+    pub provider: String,
+    pub request_count: u64,
+    pub attempt_count: u64,
+    pub failure_count: u64,
+    pub total_tokens: u64,
+}
+
+/// 用量洞察总响应。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageInsightsOverviewView {
+    pub granularity: String,
+    pub health: OverviewHealthView,
+    pub performance: OverviewPerformanceView,
+    pub cost: OverviewCostView,
+    pub attempts: AttemptMetricsView,
+    pub providers: Vec<ProviderOverviewView>,
+}
+
+/// 诊断聚合项目。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DiagnosticItemView {
+    pub key: String,
+    pub name: String,
+    pub request_count: u64,
+    pub success_count: u64,
+    pub error_count: u64,
+    pub error_rate: f64,
+    pub request_share: f64,
+    pub average_latency_ms: Option<u64>,
+    pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub non_completion_rate: f64,
+    pub retry_count: u64,
+    pub retry_rate: f64,
+    pub impact_score: f64,
+    pub estimated_cost: Option<String>,
+    pub attempt_count: u64,
+    pub total_tokens: u64,
+}
+
+/// 诊断聚合响应。
+#[derive(Debug, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct DiagnosticsView {
+    pub dimension: String,
+    pub items: Vec<DiagnosticItemView>,
+}
+
+/// 运维错误项目。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OpsErrorView {
+    pub id: String,
+    pub request_id: Option<String>,
+    pub client_api_key_id: Option<String>,
+    pub kind: String,
+    pub operation: String,
+    pub protocol: Option<String>,
+    pub client_transport: Option<String>,
+    pub provider: Option<String>,
+    pub authentication_kind: Option<String>,
+    pub account_id: Option<String>,
+    pub account_name: Option<String>,
+    pub account_email: Option<String>,
+    pub route: String,
+    pub model: Option<String>,
+    pub requested_model: Option<String>,
+    pub upstream_model: Option<String>,
+    pub service_tier: Option<String>,
+    pub client_status_code: Option<i64>,
+    pub upstream_status_code: Option<i64>,
+    pub transport: Option<String>,
+    pub attempt_index: Option<u32>,
+    pub failure_class: String,
+    pub provider_error_code: Option<String>,
+    pub occurrence_count: u32,
+    pub response_id: Option<String>,
+    pub upstream_request_id: Option<String>,
+    pub latency_ms: Option<u64>,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub request_kind: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: Option<bool>,
+    pub message: String,
+    pub metadata: OpsErrorMetadataView,
+    pub created_at: DateTime<Utc>,
+    pub created_at_display: String,
+}
+
+/// 运维错误安全元数据；只保留可查询的标识，不回显秘密材料。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct OpsErrorMetadataView {
+    pub source: String,
+    pub component: String,
+    pub attempt_id: Option<String>,
+    pub account_label: Option<String>,
+}

backend/crates/gateway-api/src/admin/presenter.rs

@@ -0,0 +1,71 @@
+//! Admin API 的展示层辅助：数值格式化。
+//!
+//! 当前 wire 仍保留 display 字段；统一由本模块提供，避免 accounts/observability
+//! 各自维护格式化规则。
+
+use gateway_core::accounting::Decimal;
+
+/// 千分位格式化。
+#[must_use]
+pub fn format_number(value: u64) -> String {
+    let text = value.to_string();
+    let mut output = String::with_capacity(text.len() + text.len() / 3);
+    for (index, character) in text.chars().rev().enumerate() {
+        if index > 0 && index % 3 == 0 {
+            output.push(',');
+        }
+        output.push(character);
+    }
+    output.chars().rev().collect()
+}
+
+/// 紧凑格式化：≥1000 时用 K/M/B/T/P 后缀，否则千分位。
+#[must_use]
+pub fn format_compact_number(value: u64) -> String {
+    if value < 1_000 {
+        return format_number(value);
+    }
+    for (suffix, threshold) in [
+        ("P", 1_000_000_000_000_000_u64),
+        ("T", 1_000_000_000_000_u64),
+        ("B", 1_000_000_000_u64),
+        ("M", 1_000_000_u64),
+        ("K", 1_000_u64),
+    ] {
+        if value >= threshold {
+            let scaled = value as f64 / threshold as f64;
+            return format!("{scaled:.1}{suffix}").replace(".0", "");
+        }
+    }
+    format_number(value)
+}
+
+/// 货币展示格式化。USD 常规金额保留两位，小于 1 美元时最多保留四位。
+#[must_use]
+pub fn format_decimal_currency(amount: &str, currency: &str) -> String {
+    if currency != "USD" {
+        return format!("{currency} {amount}");
+    }
+
+    const DECIMAL_SCALE: u128 = 10_000_000_000;
+    let scaled = amount.parse::<Decimal>().unwrap_or_default().scaled();
+    let precision = if scaled != 0 && scaled < DECIMAL_SCALE {
+        4_u32
+    } else {
+        2_u32
+    };
+    let rounding_unit = 10_u128.pow(10 - precision);
+    let rounded = (scaled + rounding_unit / 2) / rounding_unit;
+    let display_scale = 10_u128.pow(precision);
+    let whole = rounded / display_scale;
+    let fraction = rounded % display_scale;
+    let mut display = format!("{whole}.{fraction:0width$}", width = precision as usize);
+    while display.ends_with('0')
+        && display
+            .split_once('.')
+            .is_some_and(|(_, fraction)| fraction.len() > 2)
+    {
+        display.pop();
+    }
+    format!("${display}")
+}

backend/crates/gateway-api/src/admin/settings.rs

@@ -3,26 +3,22 @@
 use std::{collections::BTreeMap, fmt};
 
 use axum::{
-    Json, Router,
+    Router,
     extract::State,
     http::StatusCode,
     response::IntoResponse,
     routing::{get, post},
 };
 use chrono::{DateTime, Utc};
-use gateway_admin::model::{
-    Revision,
-    settings::{
-        ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy,
-        RuntimeSettings,
-    },
+use gateway_admin::model::settings::{
+    ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy, RuntimeSettings,
 };
 use gateway_core::routing::{PublicModelId, UpstreamModelId};
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, WireValidationError,
-    wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminResponse, AdminSessionState,
+    WireValidationError, wire::map_admin_service_error,
 };
 
 /// 客户端模型到上游模型的全局精确映射。
@@ -32,7 +28,6 @@ pub type ModelMappings = BTreeMap<String, String>;
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct RuntimeSettingsView {
-    pub config_revision: u64,
     pub model_mappings: ModelMappings,
     pub refresh_margin_seconds: u64,
     pub refresh_concurrency: u64,
@@ -49,7 +44,6 @@ pub struct RuntimeSettingsView {
 #[derive(Debug, Clone, PartialEq, Eq, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UpdateRuntimeSettingsRequest {
-    pub expected_config_revision: u64,
     pub model_mappings: ModelMappings,
     pub refresh_margin_seconds: u64,
     pub refresh_concurrency: u64,
@@ -64,9 +58,6 @@ pub struct UpdateRuntimeSettingsRequest {
 impl UpdateRuntimeSettingsRequest {
     /// 校验公共运行参数。
     pub fn validate(&self) -> Result<(), WireValidationError> {
-        if self.expected_config_revision == 0 {
-            return Err(WireValidationError::new("expectedConfigRevision"));
-        }
         validate_model_mappings(&self.model_mappings)?;
         for (value, field) in [
             (self.refresh_margin_seconds, "refreshMarginSeconds"),
@@ -81,10 +72,7 @@ impl UpdateRuntimeSettingsRequest {
         if i64::try_from(self.request_interval_ms).is_err() {
             return Err(WireValidationError::new("requestIntervalMs"));
         }
-        if !matches!(
-            self.rotation_strategy.as_str(),
-            "smart" | "quota_reset_priority" | "round_robin" | "sticky"
-        ) {
+        if RotationStrategy::parse(&self.rotation_strategy).is_none() {
             return Err(WireValidationError::new("rotationStrategy"));
         }
         Ok(())
@@ -93,8 +81,6 @@ impl UpdateRuntimeSettingsRequest {
     fn into_command(self) -> Result<ReplaceRuntimeSettings, WireValidationError> {
         self.validate()?;
         Ok(ReplaceRuntimeSettings {
-            expected_config_revision: Revision::new(self.expected_config_revision)
-                .map_err(|_| WireValidationError::new("settingsRevisionOverflow"))?,
             model_mappings: domain_model_mappings(self.model_mappings)?,
             refresh_margin_seconds: self.refresh_margin_seconds,
             refresh_concurrency: u32::try_from(self.refresh_concurrency)
@@ -102,7 +88,7 @@ impl UpdateRuntimeSettingsRequest {
             max_concurrent_per_account: u32::try_from(self.max_concurrent_per_account)
                 .map_err(|_| WireValidationError::new("settingsMaxConcurrencyOverflow"))?,
             request_interval_ms: self.request_interval_ms,
-            rotation_strategy: parse_rotation_strategy(&self.rotation_strategy)
+            rotation_strategy: RotationStrategy::parse(&self.rotation_strategy)
                 .ok_or_else(|| WireValidationError::new("rotationStrategy"))?,
             usage_retention_days: u32::try_from(self.usage_retention_days)
                 .map_err(|_| WireValidationError::new("settingsUsageRetentionOverflow"))?,
@@ -117,13 +103,12 @@ impl UpdateRuntimeSettingsRequest {
 impl From<RuntimeSettings> for RuntimeSettingsView {
     fn from(settings: RuntimeSettings) -> Self {
         Self {
-            config_revision: settings.config_revision.get(),
             model_mappings: wire_model_mappings(settings.model_mappings),
             refresh_margin_seconds: settings.refresh_margin_seconds,
             refresh_concurrency: u64::from(settings.refresh_concurrency),
             max_concurrent_per_account: u64::from(settings.max_concurrent_per_account),
             request_interval_ms: settings.request_interval_ms,
-            rotation_strategy: rotation_strategy_name(settings.rotation_strategy).to_owned(),
+            rotation_strategy: settings.rotation_strategy.as_str().to_owned(),
             usage_retention_days: u64::from(settings.usage_retention_days),
             ops_event_retention_days: u64::from(settings.ops_event_retention_days),
             audit_retention_days: u64::from(settings.audit_retention_days),
@@ -212,7 +197,7 @@ where
 async fn update_settings<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<UpdateRuntimeSettingsRequest>,
+    AdminJson(request): AdminJson<UpdateRuntimeSettingsRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -331,25 +316,6 @@ fn wire_model_mappings(mappings: DomainModelMappings) -> ModelMappings {
         .collect()
 }
 
-fn parse_rotation_strategy(value: &str) -> Option<RotationStrategy> {
-    match value {
-        "smart" => Some(RotationStrategy::Smart),
-        "quota_reset_priority" => Some(RotationStrategy::QuotaResetPriority),
-        "round_robin" => Some(RotationStrategy::RoundRobin),
-        "sticky" => Some(RotationStrategy::Sticky),
-        _ => None,
-    }
-}
-
-const fn rotation_strategy_name(strategy: RotationStrategy) -> &'static str {
-    match strategy {
-        RotationStrategy::Smart => "smart",
-        RotationStrategy::QuotaResetPriority => "quota_reset_priority",
-        RotationStrategy::RoundRobin => "round_robin",
-        RotationStrategy::Sticky => "sticky",
-    }
-}
-
 fn valid_model_name(value: &str, max_len: usize) -> bool {
     !value.is_empty()
         && value.len() <= max_len
@@ -358,17 +324,16 @@ fn valid_model_name(value: &str, max_len: usize) -> bool {
 
 fn map_wire_error(error: WireValidationError) -> AdminError {
     let message = match error.field() {
-        "settingsRevisionOverflow" => "expectedConfigRevision must be positive".to_owned(),
-        "settingsRefreshConcurrencyOverflow" => "Invalid refreshConcurrency".to_owned(),
-        "settingsMaxConcurrencyOverflow" => "Invalid maxConcurrentPerAccount".to_owned(),
-        "settingsUsageRetentionOverflow" => "Invalid usageRetentionDays".to_owned(),
-        "settingsOpsRetentionOverflow" => "Invalid opsEventRetentionDays".to_owned(),
-        "settingsAuditRetentionOverflow" => "Invalid auditRetentionDays".to_owned(),
-        field => format!("Invalid field: {field}"),
+        "settingsRefreshConcurrencyOverflow" => "refreshConcurrency 不合法".to_owned(),
+        "settingsMaxConcurrencyOverflow" => "maxConcurrentPerAccount 不合法".to_owned(),
+        "settingsUsageRetentionOverflow" => "usageRetentionDays 不合法".to_owned(),
+        "settingsOpsRetentionOverflow" => "opsEventRetentionDays 不合法".to_owned(),
+        "settingsAuditRetentionOverflow" => "auditRetentionDays 不合法".to_owned(),
+        field => format!("{field} 字段不合法"),
     };
     AdminError::bad_request(message)
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Settings repository unavailable")
+    map_admin_service_error(error)
 }

backend/crates/gateway-api/src/admin/system.rs

@@ -5,8 +5,8 @@
 use std::convert::Infallible;
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::StatusCode,
     response::{
         IntoResponse,
@@ -23,7 +23,7 @@ use gateway_admin::model::system::{
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
     wire::map_admin_service_error,
 };
 
@@ -201,11 +201,13 @@ struct RestartAcceptedView {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 struct SystemUpdateEventView {
+    id: String,
     operation_id: Option<String>,
     level: &'static str,
     step: Option<String>,
     message: String,
     terminal: bool,
+    progress_percent: Option<u8>,
     at: String,
 }
 
@@ -249,7 +251,7 @@ where
 async fn update_detail<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<UpdateDetailQuery>,
+    AdminQuery(query): AdminQuery<UpdateDetailQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -288,7 +290,7 @@ where
 async fn perform_update<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    payload: Option<Json<UpdateRequest>>,
+    payload: Option<AdminJson<UpdateRequest>>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -296,7 +298,7 @@ where
     let result = state
         .admin_services()
         .system()
-        .perform_update(payload.map(|Json(value)| value.into_target_version()))
+        .perform_update(payload.map(|AdminJson(value)| value.into_target_version()))
         .await
         .map_err(map_system_error)?;
     let SystemOperationAccepted::Update {
@@ -307,7 +309,7 @@ where
         target_version,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system update result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -359,7 +361,7 @@ where
         need_restart,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system rollback result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -389,7 +391,7 @@ where
         message,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system restart result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -403,11 +405,13 @@ where
 impl From<SystemUpdateEvent> for SystemUpdateEventView {
     fn from(event: SystemUpdateEvent) -> Self {
         Self {
+            id: event.id,
             operation_id: event.operation_id,
             level: update_event_level_name(event.level),
             step: event.step,
             message: event.message,
             terminal: event.terminal,
+            progress_percent: event.progress_percent,
             at: event.occurred_at.to_rfc3339(),
         }
     }
@@ -416,11 +420,13 @@ impl From<SystemUpdateEvent> for SystemUpdateEventView {
 impl SystemUpdateEventView {
     fn into_json(self) -> serde_json::Value {
         serde_json::json!({
+            "id": self.id,
             "operationId": self.operation_id,
             "level": self.level,
             "step": self.step,
             "message": self.message,
             "terminal": self.terminal,
+            "progressPercent": self.progress_percent,
             "at": self.at,
         })
     }
@@ -471,5 +477,5 @@ const fn update_event_level_name(level: SystemUpdateEventLevel) -> &'static str
 }
 
 fn map_system_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "System operation unavailable")
+    map_admin_service_error(error)
 }

backend/crates/gateway-api/src/admin/wire.rs

@@ -116,6 +116,8 @@ impl AdminErrorCode {
     pub const USAGE_RECORD_ACCOUNTS: Self = Self(50002);
     /// 上游网关失败。
     pub const BAD_GATEWAY: Self = Self(50201);
+    /// 不可逆上游操作的执行结果未知。
+    pub const UPSTREAM_RESULT_UNKNOWN: Self = Self(50202);
     /// 依赖的服务暂不可用。
     pub const SERVICE_UNAVAILABLE: Self = Self(50301);
 
@@ -165,6 +167,89 @@ pub struct AdminError {
     body: AdminErrorBody,
 }
 
+#[derive(Debug, Clone, Copy)]
+struct AdminErrorSpec {
+    status: StatusCode,
+    code: AdminErrorCode,
+    message: &'static str,
+}
+
+impl AdminErrorSpec {
+    const fn new(status: StatusCode, code: AdminErrorCode, message: &'static str) -> Self {
+        Self {
+            status,
+            code,
+            message,
+        }
+    }
+}
+
+const MALFORMED_JSON: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::BAD_REQUEST,
+    AdminErrorCode::MALFORMED_JSON,
+    "请求体不是合法 JSON",
+);
+const BAD_REQUEST: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::BAD_REQUEST,
+    AdminErrorCode::BAD_REQUEST,
+    "请求参数不合法",
+);
+const INVALID_TIME_RANGE: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::BAD_REQUEST,
+    AdminErrorCode::INVALID_TIME_RANGE,
+    "时间范围不合法",
+);
+const SESSION_REQUIRED: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::UNAUTHORIZED,
+    AdminErrorCode::SESSION_REQUIRED,
+    "需要管理员登录",
+);
+const INVALID_CREDENTIALS: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::UNAUTHORIZED,
+    AdminErrorCode::INVALID_CREDENTIALS,
+    "管理员用户名或密码错误",
+);
+const INVALID_API_KEY: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::UNAUTHORIZED,
+    AdminErrorCode::INVALID_API_KEY,
+    "管理 API Key 无效",
+);
+const ADMIN_ROUTE_NOT_FOUND: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::NOT_FOUND,
+    AdminErrorCode::NOT_FOUND,
+    "管理接口不存在",
+);
+const METHOD_NOT_ALLOWED: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::METHOD_NOT_ALLOWED,
+    AdminErrorCode::BAD_REQUEST,
+    "请求方法不受支持",
+);
+const TOO_MANY_LOGIN_ATTEMPTS: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::TOO_MANY_REQUESTS,
+    AdminErrorCode::TOO_MANY_LOGIN_ATTEMPTS,
+    "登录尝试过多，请稍后重试",
+);
+const INTERNAL: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::INTERNAL_SERVER_ERROR,
+    AdminErrorCode::INTERNAL,
+    "服务内部错误",
+);
+const BAD_GATEWAY: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::BAD_GATEWAY,
+    AdminErrorCode::BAD_GATEWAY,
+    "上游服务请求失败",
+);
+const UPSTREAM_RESULT_UNKNOWN: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::BAD_GATEWAY,
+    AdminErrorCode::UPSTREAM_RESULT_UNKNOWN,
+    "上游执行结果未知，请刷新状态后再决定是否重试",
+);
+const SERVICE_UNAVAILABLE: AdminErrorSpec = AdminErrorSpec::new(
+    StatusCode::SERVICE_UNAVAILABLE,
+    AdminErrorCode::SERVICE_UNAVAILABLE,
+    "依赖服务暂不可用",
+);
+
 impl AdminError {
     fn new(status: StatusCode, code: AdminErrorCode, message: impl Into<String>) -> Self {
         Self {
@@ -173,44 +258,48 @@ impl AdminError {
         }
     }
 
+    fn from_spec(spec: AdminErrorSpec) -> Self {
+        Self::new(spec.status, spec.code, spec.message)
+    }
+
+    pub fn malformed_json() -> Self {
+        Self::from_spec(MALFORMED_JSON)
+    }
+
+    pub fn invalid_request(status: StatusCode, message: &'static str) -> Self {
+        Self::new(status, BAD_REQUEST.code, message)
+    }
+
+    pub fn invalid_time_range() -> Self {
+        Self::from_spec(INVALID_TIME_RANGE)
+    }
+
+    pub fn admin_route_not_found() -> Self {
+        Self::from_spec(ADMIN_ROUTE_NOT_FOUND)
+    }
+
+    pub fn method_not_allowed() -> Self {
+        Self::from_spec(METHOD_NOT_ALLOWED)
+    }
+
     pub fn bad_request(message: impl Into<String>) -> Self {
-        Self::new(
-            StatusCode::BAD_REQUEST,
-            AdminErrorCode::BAD_REQUEST,
-            message,
-        )
+        Self::new(BAD_REQUEST.status, BAD_REQUEST.code, message)
     }
 
     pub fn admin_session_required() -> Self {
-        Self::new(
-            StatusCode::UNAUTHORIZED,
-            AdminErrorCode::SESSION_REQUIRED,
-            "Admin session required",
-        )
+        Self::from_spec(SESSION_REQUIRED)
     }
 
     pub fn invalid_admin_credentials() -> Self {
-        Self::new(
-            StatusCode::UNAUTHORIZED,
-            AdminErrorCode::INVALID_CREDENTIALS,
-            "Invalid admin credentials",
-        )
+        Self::from_spec(INVALID_CREDENTIALS)
     }
 
     pub fn invalid_admin_api_key() -> Self {
-        Self::new(
-            StatusCode::UNAUTHORIZED,
-            AdminErrorCode::INVALID_API_KEY,
-            "Invalid admin API key",
-        )
+        Self::from_spec(INVALID_API_KEY)
     }
 
     pub fn too_many_login_attempts() -> Self {
-        Self::new(
-            StatusCode::TOO_MANY_REQUESTS,
-            AdminErrorCode::TOO_MANY_LOGIN_ATTEMPTS,
-            "Too many admin login attempts",
-        )
+        Self::from_spec(TOO_MANY_LOGIN_ATTEMPTS)
     }
 
     pub fn conflict(message: impl Into<String>) -> Self {
@@ -221,47 +310,37 @@ impl AdminError {
         Self::new(StatusCode::NOT_FOUND, AdminErrorCode::NOT_FOUND, message)
     }
 
-    pub fn internal(message: impl Into<String>) -> Self {
-        Self::new(
-            StatusCode::INTERNAL_SERVER_ERROR,
-            AdminErrorCode::INTERNAL,
-            message,
-        )
+    pub fn internal() -> Self {
+        Self::from_spec(INTERNAL)
     }
 
-    pub fn bad_gateway(message: impl Into<String>) -> Self {
-        Self::new(
-            StatusCode::BAD_GATEWAY,
-            AdminErrorCode::BAD_GATEWAY,
-            message,
-        )
+    pub fn bad_gateway() -> Self {
+        Self::from_spec(BAD_GATEWAY)
     }
 
-    pub fn service_unavailable(message: impl Into<String>) -> Self {
-        Self::new(
-            StatusCode::SERVICE_UNAVAILABLE,
-            AdminErrorCode::SERVICE_UNAVAILABLE,
-            message,
-        )
+    pub fn upstream_result_unknown() -> Self {
+        Self::from_spec(UPSTREAM_RESULT_UNKNOWN)
+    }
+
+    pub fn service_unavailable() -> Self {
+        Self::from_spec(SERVICE_UNAVAILABLE)
     }
 }
 
 /// 把管理用例的稳定错误分类映射到既有 HTTP 错误 contract。
-pub(crate) fn map_admin_service_error(
-    error: gateway_admin::model::AdminError,
-    unavailable_message: &'static str,
-) -> AdminError {
+pub(crate) fn map_admin_service_error(error: gateway_admin::model::AdminError) -> AdminError {
     use gateway_admin::model::AdminErrorKind;
 
     match error.kind() {
-        AdminErrorKind::Invalid => AdminError::bad_request(error.to_string()),
+        AdminErrorKind::Invalid => AdminError::bad_request(error.message()),
         AdminErrorKind::Unauthorized => AdminError::admin_session_required(),
-        AdminErrorKind::NotFound => AdminError::not_found(error.to_string()),
-        AdminErrorKind::Conflict => AdminError::conflict(error.to_string()),
+        AdminErrorKind::NotFound => AdminError::not_found(error.message()),
+        AdminErrorKind::Conflict => AdminError::conflict(error.message()),
         AdminErrorKind::RateLimited => AdminError::too_many_login_attempts(),
-        AdminErrorKind::BadGateway => AdminError::bad_gateway(error.to_string()),
-        AdminErrorKind::Unavailable => AdminError::service_unavailable(unavailable_message),
-        AdminErrorKind::Internal => AdminError::internal(error.to_string()),
+        AdminErrorKind::BadGateway => AdminError::bad_gateway(),
+        AdminErrorKind::UpstreamResultUnknown => AdminError::upstream_result_unknown(),
+        AdminErrorKind::Unavailable => AdminError::service_unavailable(),
+        AdminErrorKind::Internal => AdminError::internal(),
     }
 }
 

backend/crates/gateway-api/src/health.rs

@@ -1,4 +1,4 @@
-//! `/healthz` 对 Core、Store 与 Host worker 健康事实的聚合。
+//! `/healthz` 对 Core、Store 与 Host 关键 worker 健康事实的聚合。
 
 use std::sync::Arc;
 use std::time::Duration;
@@ -6,8 +6,10 @@ use std::time::Duration;
 use axum::{extract::State, http::StatusCode};
 use futures::future::join_all;
 use gateway_core::health::{
-    HealthProbe, HealthState, WorkerHealthSnapshot, WorkerHealthSource, WorkerRuntimeState,
+    HealthProbe, HealthState, WorkerHealthKey, WorkerHealthSnapshot, WorkerHealthSource,
+    WorkerRuntimeState,
 };
+use gateway_core::task::WorkerKind;
 
 use crate::ApiState;
 
@@ -32,7 +34,13 @@ impl HealthStatus {
     }
 
     pub(crate) async fn healthy(&self) -> bool {
-        if !self.workers.snapshot().iter().all(worker_is_healthy) {
+        if !self
+            .workers
+            .snapshot()
+            .iter()
+            .filter(|worker| worker_affects_healthz(worker))
+            .all(worker_is_healthy)
+        {
             return false;
         }
         let checks = self.probes.iter().map(|probe| probe.check());
@@ -54,6 +62,16 @@ pub(crate) async fn healthz(State(state): State<ApiState>) -> StatusCode {
     }
 }
 
+fn worker_affects_healthz(worker: &WorkerHealthSnapshot) -> bool {
+    let WorkerHealthKey::Task(id) = &worker.key else {
+        return false;
+    };
+    !matches!(
+        id.kind(),
+        WorkerKind::OAuthRefresh | WorkerKind::QuotaCatalogHealth
+    )
+}
+
 fn worker_is_healthy(worker: &WorkerHealthSnapshot) -> bool {
     match worker.state {
         WorkerRuntimeState::Disabled | WorkerRuntimeState::Standby => true,

backend/crates/gateway-api/src/lib.rs

@@ -9,14 +9,14 @@ use std::sync::Arc;
 use std::time::Duration;
 
 use axum::Router;
-use axum::http::{HeaderName, HeaderValue, Method, StatusCode};
+use axum::http::{HeaderName, HeaderValue, Method, Request, StatusCode};
 use axum::routing::get;
 use gateway_admin::AdminServices;
 use gateway_core::engine::execution::ExecutionService;
 use gateway_core::health::{HealthProbe, WorkerHealthSource};
 use gateway_core::lifecycle::ConnectionLifecycle;
 use serde::Deserialize;
-use tower_http::cors::{Any, CorsLayer};
+use tower_http::cors::CorsLayer;
 use tower_http::request_id::{MakeRequestUuid, PropagateRequestIdLayer, SetRequestIdLayer};
 use tower_http::services::{ServeDir, ServeFile};
 use tower_http::timeout::TimeoutLayer;
@@ -146,11 +146,17 @@ pub fn initialize(
                     .map_err(|_| ApiError::Config(ApiConfigError::InvalidCorsOrigin))
             })
             .collect::<Result<Vec<_>, _>>()?;
+        // credentials 模式禁止通配 allow_headers；显式列出鉴权与内容协商头。
         router = router.layer(
             CorsLayer::new()
                 .allow_origin(origins)
                 .allow_methods([Method::GET, Method::POST])
-                .allow_headers(Any)
+                .allow_headers([
+                    axum::http::header::AUTHORIZATION,
+                    axum::http::header::CONTENT_TYPE,
+                    HeaderName::from_static("x-api-key"),
+                    request_id_header.clone(),
+                ])
                 .allow_credentials(true),
         );
     }
@@ -160,10 +166,32 @@ pub fn initialize(
             Duration::from_secs(seconds),
         ));
     }
+    // Trace 必须在 SetRequestId 内侧，span 才能捕获本服务生成的 request_id；
+    // 默认 DEBUG span 会被 info 日志过滤器丢弃，这里显式用 info_span。
+    let trace_layer = TraceLayer::new_for_http().make_span_with({
+        let request_id_header = request_id_header.clone();
+        move |request: &Request<_>| {
+            let request_id = request
+                .headers()
+                .get(&request_id_header)
+                .and_then(|value| value.to_str().ok())
+                .unwrap_or_default();
+            tracing::info_span!(
+                "request",
+                request_id = %request_id,
+                method = %request.method().as_str(),
+                uri = %request
+                    .uri()
+                    .path_and_query()
+                    .map(axum::http::uri::PathAndQuery::as_str)
+                    .unwrap_or_default(),
+            )
+        }
+    });
     let router = router
         .layer(PropagateRequestIdLayer::new(request_id_header.clone()))
+        .layer(trace_layer)
         .layer(SetRequestIdLayer::new(request_id_header, MakeRequestUuid))
-        .layer(TraceLayer::new_for_http())
         .with_state(state);
     Ok(ApiBundle { router })
 }

backend/crates/gateway-api/src/openai/error.rs

@@ -2,12 +2,13 @@
 
 use axum::{
     Json,
-    http::StatusCode,
+    body::Body,
+    http::{HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
     response::{IntoResponse, Response},
 };
 use gateway_core::{
-    engine::{EngineError, UpstreamSendState},
-    error::{GatewayError, GatewayErrorKind, ProviderErrorKind},
+    engine::EngineError,
+    error::{GatewayError, GatewayErrorKind},
 };
 use serde_json::{Value, json};
 
@@ -71,15 +72,6 @@ pub fn model_not_found_response() -> (StatusCode, Json<Value>) {
 #[must_use]
 pub fn gateway_error_from_engine(error: &EngineError) -> GatewayError {
     match error {
-        EngineError::Provider(error)
-            if error.kind() == ProviderErrorKind::Unavailable
-                && error.send_state() == UpstreamSendState::NotSent =>
-        {
-            GatewayError::new(
-                GatewayErrorKind::NoAvailableProvider,
-                "no upstream provider is currently available for this request",
-            )
-        }
         EngineError::Provider(error) => GatewayError::from_provider(error),
         EngineError::Cancelled => {
             GatewayError::new(GatewayErrorKind::Cancelled, "request was cancelled")
@@ -97,7 +89,9 @@ pub fn gateway_error_from_engine(error: &EngineError) -> GatewayError {
         | EngineError::ProviderMetadataMismatch
         | EngineError::ContinuationPinMismatch
         | EngineError::RequiredAccountMismatch
+        | EngineError::AccountOutsideClientScope
         | EngineError::DownstreamCommitRequired
+        | EngineError::NoActiveAttempt
         | EngineError::InvalidDeliveryState => {
             GatewayError::new(GatewayErrorKind::Internal, "gateway execution failed")
         }
@@ -116,6 +110,33 @@ pub fn gateway_error_response(error: &GatewayError) -> Response {
     .into_response()
 }
 
+/// 在下游尚未提交时优先交付 Provider 的原始 HTTP 失败响应。
+pub fn engine_error_response(error: &EngineError) -> Response {
+    if let EngineError::Provider(error) = error
+        && let Some(upstream) = error.client_visible_upstream_response()
+        && let Ok(status) = StatusCode::from_u16(upstream.status())
+    {
+        let mut response = Response::new(Body::from(upstream.body().clone()));
+        *response.status_mut() = status;
+        if let Some(content_type) = upstream.content_type()
+            && let Ok(content_type) = HeaderValue::from_bytes(content_type)
+        {
+            response.headers_mut().insert(CONTENT_TYPE, content_type);
+        }
+        for header in upstream.headers() {
+            let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+                continue;
+            };
+            let Ok(value) = HeaderValue::from_bytes(header.value()) else {
+                continue;
+            };
+            response.headers_mut().append(name, value);
+        }
+        return response;
+    }
+    gateway_error_response(&gateway_error_from_engine(error))
+}
+
 /// Gateway 错误稳定映射，供 HTTP、SSE 和 WebSocket 共用。
 #[must_use]
 pub const fn gateway_error_contract(
@@ -152,6 +173,16 @@ pub const fn gateway_error_contract(
             "server_error",
             "no_available_provider",
         ),
+        GatewayErrorKind::AccountCapacityUnavailable => (
+            StatusCode::SERVICE_UNAVAILABLE,
+            "server_error",
+            "account_capacity_unavailable",
+        ),
+        GatewayErrorKind::ProviderInfrastructureUnavailable => (
+            StatusCode::SERVICE_UNAVAILABLE,
+            "server_error",
+            "provider_infrastructure_unavailable",
+        ),
         GatewayErrorKind::RateLimited => (
             StatusCode::TOO_MANY_REQUESTS,
             "rate_limit_error",

backend/crates/gateway-api/src/openai/images/http.rs

@@ -0,0 +1,233 @@
+//! Codex Images 非流式 HTTP adapter。
+
+use std::net::SocketAddr;
+
+use axum::{
+    body::{Body, Bytes},
+    extract::{Extension, State, connect_info::ConnectInfo},
+    http::{HeaderMap, HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
+    response::{IntoResponse, Response},
+};
+use gateway_core::engine::execution::StartedExecution;
+use gateway_core::error::{GatewayError, GatewayErrorKind};
+use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
+use gateway_core::operation::{ImageRequest, ImageRequestKind, Operation, RawJsonPayload};
+use serde_json::{Map, Value};
+
+use crate::ApiState;
+use crate::openai::{
+    auth::{authenticate_client, authentication_error_response},
+    error::{engine_error_response, gateway_error_response, protocol_error_response},
+    responses::{PendingExecution, ProtocolError, ProtocolErrorBody, request_client_context},
+};
+
+const OPENAI_PROTOCOL: &str = "openai";
+const IMAGE_TURN_ID_CONTEXT_KEY: &str = "image_turn_id";
+
+/// `POST /v1/images/generations`。
+pub(crate) async fn image_generations(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    handle_image_request(
+        state,
+        connect_info,
+        headers,
+        body,
+        ImageRequestKind::Generation,
+        "/v1/images/generations",
+    )
+    .await
+}
+
+/// `POST /v1/images/edits`。
+pub(crate) async fn image_edits(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    handle_image_request(
+        state,
+        connect_info,
+        headers,
+        body,
+        ImageRequestKind::Edit,
+        "/v1/images/edits",
+    )
+    .await
+}
+
+async fn handle_image_request(
+    state: ApiState,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    body: Bytes,
+    kind: ImageRequestKind,
+    endpoint: &'static str,
+) -> Response {
+    let service = state.openai();
+    let client = match authenticate_client(service, &headers) {
+        Ok(client) => client,
+        Err(error) => return authentication_error_response(error),
+    };
+    let (client_ip, user_agent) = request_client_context(
+        &headers,
+        connect_info.map(|Extension(ConnectInfo(address))| address),
+    );
+    let operation = match image_operation(body, &headers, kind) {
+        Ok(operation) => operation,
+        Err(error) => return gateway_error_response(&error),
+    };
+    let started = match service
+        .start_image(client, operation, client_ip, user_agent, endpoint)
+        .await
+    {
+        Ok(started) => started,
+        Err(error) => return gateway_error_response(&error),
+    };
+    collect_image_response(started).await
+}
+
+fn image_operation(
+    body: Bytes,
+    headers: &HeaderMap,
+    kind: ImageRequestKind,
+) -> Result<Operation, GatewayError> {
+    let mut context = Map::new();
+    if let Some(turn_id) = headers
+        .get("x-codex-image-turn-id")
+        .and_then(|value| value.to_str().ok())
+    {
+        context.insert(
+            IMAGE_TURN_ID_CONTEXT_KEY.to_owned(),
+            Value::String(turn_id.to_owned()),
+        );
+    }
+    let payload = RawJsonPayload::new(OPENAI_PROTOCOL, body)
+        .map_err(|_| {
+            GatewayError::new(
+                GatewayErrorKind::Internal,
+                "OpenAI protocol identifier is invalid",
+            )
+        })?
+        .with_context(context);
+    Ok(Operation::GenerateImage(ImageRequest::from_raw_json(
+        kind, payload,
+    )))
+}
+
+async fn collect_image_response(started: StartedExecution) -> Response {
+    let mut execution = PendingExecution::new(started.session);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    let events = match session.collect_uncommitted().await {
+        Ok(events) => events,
+        Err(error) => {
+            let response = engine_error_response(&error);
+            return execution.record_response_status(response).await;
+        }
+    };
+    let body = match raw_json_body(events) {
+        Some(body) => body,
+        None => {
+            let response = invalid_upstream_response();
+            let response = execution.record_response_status(response).await;
+            execution.cancel_and_finalize().await;
+            return response;
+        }
+    };
+    let status = session
+        .response_status_code()
+        .and_then(|status| StatusCode::from_u16(status).ok())
+        .filter(StatusCode::is_success)
+        .unwrap_or(StatusCode::OK);
+    let response_headers = session.response_headers().to_vec();
+    let response = json_body_response(body, status, &response_headers);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    if let Err(error) = session.commit_downstream(Some(status.as_u16())).await {
+        execution.cancel_and_finalize().await;
+        let response = engine_error_response(&error);
+        return execution.record_response_status(response).await;
+    }
+    if !session.is_finalized() {
+        execution.cancel_and_finalize().await;
+        return invalid_upstream_response();
+    }
+    execution.disarm();
+    response
+}
+
+fn raw_json_body(events: Vec<ProviderEvent>) -> Option<Bytes> {
+    let mut body = None;
+    for event in events {
+        let (_, wire) = event.into_parts();
+        let Some(wire) = wire.filter(|wire| wire.protocol() == "openai") else {
+            continue;
+        };
+        let Some(raw) = wire.into_raw_json_body() else {
+            continue;
+        };
+        if body.replace(raw).is_some() {
+            return None;
+        }
+    }
+    body
+}
+
+fn json_body_response(
+    body: Bytes,
+    status: StatusCode,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let mut response = Response::new(Body::from(body));
+    *response.status_mut() = status;
+    response
+        .headers_mut()
+        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
+    apply_response_headers(response, response_headers)
+}
+
+fn apply_response_headers(
+    mut response: Response,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let connection_options =
+        crate::openai::responses::response_connection_options(response_headers);
+    for header in response_headers {
+        if !crate::openai::responses::response_header_is_forwardable(
+            header.name(),
+            &connection_options,
+        ) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
+            continue;
+        };
+        response.headers_mut().append(name, value);
+    }
+    response
+}
+
+fn invalid_upstream_response() -> Response {
+    protocol_error_response(
+        StatusCode::BAD_GATEWAY,
+        ProtocolErrorBody {
+            error: ProtocolError {
+                kind: "server_error",
+                code: "invalid_upstream_response",
+                message: "The gateway could not forward the upstream image response.".to_owned(),
+                param: None,
+            },
+        },
+    )
+    .into_response()
+}

backend/crates/gateway-api/src/openai/images/mod.rs

@@ -0,0 +1,5 @@
+//! OpenAI/Codex Images JSON 透明 adapter。
+
+mod http;
+
+pub(crate) use http::{image_edits, image_generations};

backend/crates/gateway-api/src/openai/mod.rs

@@ -2,6 +2,7 @@
 
 pub mod auth;
 pub mod error;
+pub mod images;
 pub mod models;
 pub mod responses;
 pub mod router;

backend/crates/gateway-api/src/openai/models.rs

@@ -2,11 +2,12 @@
 
 use axum::{
     Json,
-    extract::{Path, State},
+    extract::{Path, Query, State},
     http::{HeaderMap, StatusCode},
     response::{IntoResponse, Response},
 };
-use gateway_core::routing::PublicModelId;
+use gateway_core::routing::{PublicModelId, PublicModelProfile};
+use serde::Deserialize;
 use serde_json::{Value, json};
 
 use crate::ApiState;
@@ -17,20 +18,50 @@ use super::{
 };
 
 const MODEL_CREATED_TIMESTAMP: i64 = 1_700_000_000;
+const CODEX_BASE_INSTRUCTIONS: &str = "You are Codex, a coding agent. Follow the user's instructions and use the available tools to complete software engineering tasks. Inspect relevant files before editing, preserve unrelated changes, and verify the result.";
 
-/// `GET /v1/models`。
-pub(crate) async fn models(State(state): State<ApiState>, headers: HeaderMap) -> Response {
+#[derive(Debug, Deserialize)]
+pub(crate) struct ModelsQuery {
+    client_version: Option<String>,
+}
+
+/// `GET /v1/models`。Codex 携带 `client_version` 时返回其专用目录合同。
+pub(crate) async fn models(
+    State(state): State<ApiState>,
+    Query(query): Query<ModelsQuery>,
+    headers: HeaderMap,
+) -> Response {
     let service = state.openai();
     let client = match authenticate_client(service, &headers) {
         Ok(client) => client,
         Err(error) => return authentication_error_response(error),
     };
+
+    if query
+        .client_version
+        .as_deref()
+        .is_some_and(|version| !version.trim().is_empty())
+    {
+        let models = service
+            .public_model_profiles(&client)
+            .iter()
+            .enumerate()
+            .map(|(index, profile)| codex_model_json(profile, index))
+            .collect::<Vec<_>>();
+        return (
+            StatusCode::OK,
+            Json(json!({
+                "models": models,
+            })),
+        )
+            .into_response();
+    }
+
     let data = service
         .public_models(&client)
         .into_iter()
         .map(|model| openai_model_json(&model))
         .collect::<Vec<_>>();
-
     (
         StatusCode::OK,
         Json(json!({
@@ -134,3 +165,92 @@ fn catalog_model_json(id: &str) -> Value {
         "source": "gateway",
     })
 }
+
+fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
+    let id = profile.model().as_str();
+    let presentation = profile.presentation();
+    let reasoning_levels = presentation
+        .supported_reasoning_efforts()
+        .iter()
+        .map(|effort| {
+            json!({
+                "effort": effort,
+                "description": reasoning_effort_description(effort),
+            })
+        })
+        .collect::<Vec<_>>();
+    let reasoning_supported = presentation
+        .supported_reasoning_efforts()
+        .iter()
+        .any(|effort| effort != "none");
+    let context_window = presentation.context_window_tokens();
+    let input_modalities = if presentation.image_input() {
+        vec!["text", "image"]
+    } else {
+        vec!["text"]
+    };
+    let additional_speed_tiers = presentation
+        .service_tiers()
+        .iter()
+        .filter_map(|tier| tier.speed_tier())
+        .collect::<Vec<_>>();
+    let service_tiers = presentation
+        .service_tiers()
+        .iter()
+        .map(|tier| {
+            json!({
+                "id": tier.id(),
+                "name": tier.name(),
+                "description": tier.description(),
+            })
+        })
+        .collect::<Vec<_>>();
+
+    json!({
+        "slug": id,
+        "display_name": presentation.display_name().unwrap_or(id),
+        "description": presentation.description(),
+        "default_reasoning_level": presentation.default_reasoning_effort(),
+        "supported_reasoning_levels": reasoning_levels,
+        "shell_type": "shell_command",
+        "visibility": if presentation.hidden() { "hide" } else { "list" },
+        "supported_in_api": true,
+        "priority": index.saturating_add(1),
+        "additional_speed_tiers": additional_speed_tiers,
+        "service_tiers": service_tiers,
+        "availability_nux": Value::Null,
+        "upgrade": Value::Null,
+        "base_instructions": CODEX_BASE_INSTRUCTIONS,
+        "model_messages": Value::Null,
+        "include_skills_usage_instructions": false,
+        "supports_reasoning_summary_parameter": reasoning_supported,
+        "default_reasoning_summary": "auto",
+        "support_verbosity": presentation.verbosity(),
+        "default_verbosity": Value::Null,
+        "apply_patch_tool_type": presentation.agent_tools().then_some("freeform"),
+        "web_search_tool_type": "text",
+        "truncation_policy": { "mode": "tokens", "limit": 10_000 },
+        "supports_parallel_tool_calls": presentation.parallel_tool_calls(),
+        "supports_image_detail_original": presentation.image_detail_original(),
+        "context_window": context_window,
+        "max_context_window": context_window,
+        "effective_context_window_percent": 95,
+        "experimental_supported_tools": [],
+        "input_modalities": input_modalities,
+        "supports_search_tool": presentation.search_tool(),
+        "use_responses_lite": false,
+    })
+}
+
+fn reasoning_effort_description(effort: &str) -> &'static str {
+    match effort {
+        "none" => "No reasoning",
+        "minimal" => "Minimal reasoning",
+        "low" => "Fast responses with lighter reasoning",
+        "medium" => "Balances speed and reasoning depth for everyday tasks",
+        "high" => "Greater reasoning depth for complex problems",
+        "xhigh" => "Extra high reasoning depth for complex problems",
+        "max" => "Maximum reasoning depth for the hardest problems",
+        _ => "Provider-supported reasoning level",
+    }
+}

backend/crates/gateway-api/src/openai/responses/error.rs

@@ -152,9 +152,6 @@ pub enum ResponseEncodeError {
     /// 协议原生流缺少可返回的终态 response object。
     #[error("responses wire stream has no terminal response")]
     MissingWireTerminal,
-    /// 协议原生事件携带了不一致的响应身份。
-    #[error("responses wire stream changed its response identity")]
-    WireIdentityChanged,
     /// 终态 response object 无法序列化为完整 HTTP JSON 响应。
     #[error("responses wire terminal serialization failed")]
     Serialization,
@@ -167,7 +164,7 @@ impl ResponseEncodeError {
         ProtocolErrorBody {
             error: ProtocolError {
                 kind: "server_error",
-                code: "invalid_canonical_response",
+                code: "invalid_upstream_response",
                 message: "The gateway could not forward the upstream response.".to_owned(),
                 param: None,
             },

backend/crates/gateway-api/src/openai/responses/http.rs

@@ -8,7 +8,7 @@ use axum::{
     body::{Body, Bytes},
     extract::{Extension, State, connect_info::ConnectInfo},
     http::{
-        HeaderMap, HeaderValue, StatusCode,
+        HeaderMap, HeaderName, HeaderValue, StatusCode,
         header::{CACHE_CONTROL, CONTENT_TYPE, USER_AGENT},
     },
     response::{IntoResponse, Response},
@@ -25,8 +25,8 @@ use crate::ApiState;
 use crate::openai::{
     auth::{authenticate_client, authentication_error_response},
     error::{
-        gateway_error_contract, gateway_error_from_engine, gateway_error_response,
-        protocol_error_response, runtime_unavailable_response,
+        engine_error_response, gateway_error_contract, gateway_error_from_engine,
+        gateway_error_response, protocol_error_response, runtime_unavailable_response,
     },
 };
 
@@ -123,7 +123,7 @@ async fn handle_responses(
 }
 
 /// 从 socket 与标准转发头提取旧 Usage 页面使用的诊断事实。
-pub(super) fn request_client_context(
+pub(in crate::openai) fn request_client_context(
     headers: &HeaderMap,
     peer_address: Option<SocketAddr>,
 ) -> (Option<IpAddr>, Option<String>) {
@@ -180,7 +180,7 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
     let events = match session.collect_uncommitted().await {
         Ok(events) => events,
         Err(error) => {
-            let response = gateway_error_response(&gateway_error_from_engine(&error));
+            let response = engine_error_response(&error);
             return execution.record_response_status(response).await;
         }
     };
@@ -206,7 +206,7 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
         .await
     {
         execution.cancel_and_finalize().await;
-        let response = gateway_error_response(&gateway_error_from_engine(&error));
+        let response = engine_error_response(&error);
         return execution.record_response_status(response).await;
     }
     if !session.is_finalized() {
@@ -237,9 +237,7 @@ fn encode_collected_events(
 ) -> Result<Vec<u8>, BufferedResponseEncodeError> {
     let mut encoder = OpenAiResponsesEncoder::new();
     for event in events {
-        encoder
-            .push_sse(event)
-            .map_err(BufferedResponseEncodeError::Canonical)?;
+        encoder.push_sse(event);
     }
     let response = encoder
         .finish()
@@ -253,23 +251,25 @@ fn json_body_response(encoded: Vec<u8>, response_headers: &[ProviderResponseHead
     response
         .headers_mut()
         .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
-    apply_safe_response_headers(response, response_headers)
+    apply_response_headers(response, response_headers)
 }
 
-fn apply_safe_response_headers(
+fn apply_response_headers(
     mut response: Response,
     response_headers: &[ProviderResponseHeader],
 ) -> Response {
+    let connection_options = super::response_connection_options(response_headers);
     for header in response_headers {
-        let Some(name) = super::safe_response_header_name(header.name()) else {
+        if !super::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
             continue;
         };
-        let Ok(value) = HeaderValue::from_str(header.value().as_str()) else {
+        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
             continue;
         };
-        response
-            .headers_mut()
-            .insert(axum::http::header::HeaderName::from_static(name), value);
+        response.headers_mut().append(name, value);
     }
     response
 }
@@ -295,7 +295,7 @@ pub async fn stream_execution_response(
             return response;
         }
         Err(error) => {
-            let response = gateway_error_response(&gateway_error_from_engine(&error));
+            let response = engine_error_response(&error);
             return execution.record_response_status(response).await;
         }
     };
@@ -310,18 +310,7 @@ pub async fn stream_execution_response(
     let mut encoder = OpenAiResponsesEncoder::new();
     let mut frames = Vec::new();
     for event in &first_events {
-        match encoder.push_sse(event) {
-            Ok(encoded) => frames.extend(encoded),
-            Err(error) => {
-                let response = protocol_error_response(
-                    StatusCode::INTERNAL_SERVER_ERROR,
-                    error.protocol_body(),
-                );
-                let response = execution.record_response_status(response).await;
-                execution.cancel_and_finalize().await;
-                return response;
-            }
-        }
+        frames.extend(encoder.push_sse(event));
     }
     if frames.is_empty() {
         let response = internal_gateway_response("gateway commit batch encoded no output");
@@ -338,7 +327,7 @@ pub async fn stream_execution_response(
         .await
     {
         execution.cancel_and_finalize().await;
-        let response = gateway_error_response(&gateway_error_from_engine(&error));
+        let response = engine_error_response(&error);
         return execution.record_response_status(response).await;
     }
     let Some(session) = execution.into_session() else {
@@ -371,29 +360,31 @@ fn event_stream_response(body: Body, response_headers: &[ProviderResponseHeader]
     response
         .headers_mut()
         .insert(CACHE_CONTROL, HeaderValue::from_static("no-cache"));
-    apply_safe_response_headers(response, response_headers)
+    apply_response_headers(response, response_headers)
 }
 
 fn internal_gateway_response(message: &'static str) -> Response {
     gateway_error_response(&GatewayError::new(GatewayErrorKind::Internal, message))
 }
 
-pub(super) struct PendingExecution {
+pub(in crate::openai) struct PendingExecution {
     session: Option<Box<dyn ExecutionSession>>,
 }
 
 impl PendingExecution {
-    pub(super) fn new(session: Box<dyn ExecutionSession>) -> Self {
+    pub(in crate::openai) fn new(session: Box<dyn ExecutionSession>) -> Self {
         Self {
             session: Some(session),
         }
     }
 
-    pub(super) fn session_mut(&mut self) -> Option<&mut (dyn ExecutionSession + 'static)> {
+    pub(in crate::openai) fn session_mut(
+        &mut self,
+    ) -> Option<&mut (dyn ExecutionSession + 'static)> {
         self.session.as_deref_mut()
     }
 
-    async fn cancel_and_finalize(&mut self) {
+    pub(in crate::openai) async fn cancel_and_finalize(&mut self) {
         if let Some(session) = self.session.as_mut() {
             session.cancel();
             if !session.is_finalized() {
@@ -402,21 +393,19 @@ impl PendingExecution {
         }
     }
 
-    async fn record_response_status(&mut self, response: Response) -> Response {
-        let Some(session) = self.session.as_mut() else {
-            return internal_gateway_response("gateway response session is unavailable");
-        };
-        if session
-            .record_client_status(response.status().as_u16())
-            .await
-            .is_err()
-        {
-            return internal_gateway_response("gateway client status could not be persisted");
+    pub(in crate::openai) async fn record_response_status(
+        &mut self,
+        response: Response,
+    ) -> Response {
+        if let Some(session) = self.session.as_mut() {
+            let _ = session
+                .record_client_status(response.status().as_u16())
+                .await;
         }
         response
     }
 
-    pub(super) fn disarm(&mut self) {
+    pub(in crate::openai) fn disarm(&mut self) {
         self.session = None;
     }
 
@@ -499,10 +488,16 @@ impl ResponsesStreamState {
                     .session
                     .as_ref()
                     .is_some_and(|session| session.is_finalized());
-                self.finish_with_gateway_error(GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended without a terminal event",
-                ));
+                if self.execution_terminal {
+                    self.pending
+                        .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
+                    self.output_finished = true;
+                } else {
+                    self.finish_with_gateway_error(GatewayError::new(
+                        GatewayErrorKind::Internal,
+                        "gateway response ended without finalizing the execution",
+                    ));
+                }
             }
             Err(error) => {
                 self.execution_terminal = self
@@ -521,18 +516,11 @@ impl ResponsesStreamState {
     }
 
     async fn push_event(&mut self, event: ProviderEvent) {
-        match self.encoder.push_sse(&event) {
-            Ok(frames) => {
-                if self.encoder.is_completed() {
-                    self.finish_completed(frames).await;
-                } else {
-                    self.pending.extend(frames);
-                }
-            }
-            Err(error) => {
-                self.cancel_execution().await;
-                self.finish_with_encode_error(error);
-            }
+        let frames = self.encoder.push_sse(&event);
+        if self.encoder.is_completed() {
+            self.finish_completed(frames).await;
+        } else {
+            self.pending.extend(frames);
         }
     }
 
@@ -607,20 +595,6 @@ impl ResponsesStreamState {
             .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
         self.output_finished = true;
     }
-
-    fn finish_with_encode_error(&mut self, error: ResponseEncodeError) {
-        let protocol = error.protocol_body().error;
-        self.pending
-            .push_back(Bytes::from(response_failed_sse_event_with_id(
-                self.encoder.response_id(),
-                protocol.kind,
-                protocol.code,
-                &protocol.message,
-            )));
-        self.pending
-            .push_back(Bytes::from_static(DONE_SSE_FRAME.as_bytes()));
-        self.output_finished = true;
-    }
 }
 
 impl Drop for ResponsesStreamState {

backend/crates/gateway-api/src/openai/responses/mod.rs

@@ -6,7 +6,8 @@ mod request;
 mod response;
 mod websocket;
 
-pub use error::{ProtocolErrorBody, RequestDecodeError, ResponseEncodeError};
+pub use error::{ProtocolError, ProtocolErrorBody, RequestDecodeError, ResponseEncodeError};
+pub(super) use http::{PendingExecution, request_client_context};
 pub use http::{collect_execution_response, stream_execution_response};
 pub(crate) use http::{responses, review_responses};
 pub use request::{
@@ -17,13 +18,62 @@ pub use response::OpenAiResponsesEncoder;
 pub(crate) use websocket::responses_websocket;
 pub use websocket::{ResponseCreateFrameError, decode_response_create_with_context};
 
-pub(super) fn safe_response_header_name(name: &str) -> Option<&'static str> {
-    match name {
-        "x-request-id" => Some("x-request-id"),
-        "openai-model" => Some("openai-model"),
-        "x-models-etag" => Some("x-models-etag"),
-        "x-reasoning-included" => Some("x-reasoning-included"),
-        "openai-processing-ms" => Some("openai-processing-ms"),
-        _ => None,
+use gateway_core::event::ProviderResponseHeader;
+
+pub(super) fn response_connection_options(headers: &[ProviderResponseHeader]) -> Vec<String> {
+    headers
+        .iter()
+        .filter(|header| header.name().trim().eq_ignore_ascii_case("connection"))
+        .filter_map(|header| std::str::from_utf8(header.value()).ok())
+        .flat_map(|value| value.split(','))
+        .map(str::trim)
+        .filter(|name| !name.is_empty())
+        .map(str::to_ascii_lowercase)
+        .collect()
+}
+
+pub(super) fn response_header_is_forwardable(name: &str, connection_options: &[String]) -> bool {
+    let name = name.trim().to_ascii_lowercase();
+    if connection_options
+        .iter()
+        .any(|option| option.eq_ignore_ascii_case(&name))
+        || name.starts_with("sec-websocket-")
+    {
+        return false;
     }
+
+    !matches!(
+        name.as_str(),
+        "connection"
+            | "keep-alive"
+            | "proxy-connection"
+            | "te"
+            | "trailer"
+            | "transfer-encoding"
+            | "upgrade"
+            | "content-length"
+            | "content-type"
+            | "content-encoding"
+            | "authorization"
+            | "x-api-key"
+            | "www-authenticate"
+            | "authentication-info"
+            | "proxy-authenticate"
+            | "proxy-authorization"
+            | "proxy-authentication-info"
+            | "cookie"
+            | "cookie2"
+            | "set-cookie"
+            | "set-cookie2"
+            | "chatgpt-account-id"
+            | "chatgpt-organization-id"
+            | "chatgpt-org-id"
+            | "chatgpt-project-id"
+            | "openai-organization"
+            | "openai-project"
+            | "x-openai-organization"
+            | "x-openai-project"
+            | "x-codex-installation-id"
+            | "x-codex-turn-metadata"
+    )
 }

backend/crates/gateway-api/src/openai/responses/request.rs

@@ -3,6 +3,7 @@
 use std::{fmt, net::IpAddr};
 
 use axum::http::HeaderMap;
+use base64::{Engine as _, engine::general_purpose::STANDARD};
 use gateway_core::operation::{GenerateRequest, Operation, ProtocolPayload, ProviderSessionState};
 use gateway_protocol::openai::{
     X_OPENAI_INTERNAL_CODEX_RESPONSES_LITE_HEADER, X_OPENAI_MEMGEN_REQUEST_HEADER,
@@ -14,6 +15,7 @@ use super::error::RequestDecodeError;
 const OPENAI_PROTOCOL: &str = "openai";
 const REVIEW_SUBAGENT: &str = "review";
 const OPENAI_SUBAGENT_KEY: &str = "x-openai-subagent";
+const PASSTHROUGH_HEADERS_CONTEXT_KEY: &str = "opaque_request_headers";
 
 #[derive(Clone, Default)]
 pub struct OpenAiRequestHeaders {
@@ -34,6 +36,7 @@ pub struct OpenAiRequestHeaders {
     responses_lite: Option<String>,
     memgen_request: Option<String>,
     subagent: Option<String>,
+    passthrough_headers: Vec<Value>,
 }
 
 impl OpenAiRequestHeaders {
@@ -57,12 +60,8 @@ impl OpenAiRequestHeaders {
             turn_id: header_string(headers, "x-codex-turn-id"),
             responses_lite: header_string(headers, X_OPENAI_INTERNAL_CODEX_RESPONSES_LITE_HEADER),
             memgen_request: header_string(headers, X_OPENAI_MEMGEN_REQUEST_HEADER),
-            subagent: header_string(headers, OPENAI_SUBAGENT_KEY).filter(|value| {
-                matches!(
-                    value.as_str(),
-                    "review" | "compact" | "memory_consolidation" | "collab_spawn"
-                )
-            }),
+            subagent: header_string(headers, OPENAI_SUBAGENT_KEY),
+            passthrough_headers: passthrough_headers(headers),
         }
     }
 
@@ -108,6 +107,12 @@ impl OpenAiRequestHeaders {
         insert_protocol_context(&mut context, "turn_id", self.turn_id.as_ref());
         insert_protocol_context(&mut context, "responses_lite", self.responses_lite.as_ref());
         insert_protocol_context(&mut context, "memgen_request", self.memgen_request.as_ref());
+        if !self.passthrough_headers.is_empty() {
+            context.insert(
+                PASSTHROUGH_HEADERS_CONTEXT_KEY.to_owned(),
+                Value::Array(self.passthrough_headers.clone()),
+            );
+        }
         if let Some(use_websocket) = use_websocket {
             context.insert("use_websocket".to_owned(), Value::Bool(use_websocket));
         }
@@ -131,12 +136,6 @@ pub enum ContinuationIntent {
 }
 
 impl ContinuationIntent {
-    /// 返回是否请求了对话延续。
-    #[must_use]
-    pub const fn is_continuation(&self) -> bool {
-        matches!(self, Self::PreviousResponseId(_))
-    }
-
     /// 返回待 history owner 解析的 response ID。
     #[must_use]
     pub fn previous_response_id(&self) -> Option<&str> {
@@ -160,7 +159,6 @@ impl fmt::Debug for ContinuationIntent {
 #[derive(Clone, PartialEq, Eq)]
 pub struct ResponsesRequestMetadata {
     requested_model: String,
-    public_model: String,
     stream: bool,
     store: bool,
     continuation: ContinuationIntent,
@@ -175,12 +173,6 @@ impl ResponsesRequestMetadata {
         &self.requested_model
     }
 
-    /// 返回协议层公开模型候选。
-    #[must_use]
-    pub fn public_model(&self) -> &str {
-        &self.public_model
-    }
-
     /// 返回客户端是否请求 SSE。
     #[must_use]
     pub const fn stream(&self) -> bool {
@@ -217,7 +209,6 @@ impl fmt::Debug for ResponsesRequestMetadata {
         formatter
             .debug_struct("ResponsesRequestMetadata")
             .field("requested_model", &self.requested_model)
-            .field("public_model", &self.public_model)
             .field("stream", &self.stream)
             .field("store", &self.store)
             .field("continuation", &self.continuation)
@@ -310,16 +301,26 @@ pub(super) fn decode_request_inner(
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
     let value =
         serde_json::from_slice::<Value>(body).map_err(|_| RequestDecodeError::MalformedJson)?;
-    let Value::Object(mut object) = value else {
+    let Value::Object(object) = value else {
         return Err(RequestDecodeError::ExpectedObject);
     };
-    // `use_websocket` 只影响本地 transport。无论值是否可识别，都不得进入上游 body。
-    let use_websocket = object
-        .remove("use_websocket")
-        .and_then(|value| value.as_bool());
+    decode_request_object(object, review, request_headers)
+}
 
-    let model = required_non_empty_string(&object, "model", "model")?.trim();
-    if model.is_empty() {
+/// 解码已解析的顶层 object；WebSocket 帧解码复用此内核，避免序列化往返。
+pub(super) fn decode_request_object(
+    mut object: Map<String, Value>,
+    review: bool,
+    request_headers: &OpenAiRequestHeaders,
+) -> Result<DecodedResponsesRequest, RequestDecodeError> {
+    // 仅消费已识别的本地 transport 开关；未知同名值保留给未来上游协议。
+    let use_websocket = object.get("use_websocket").and_then(Value::as_bool);
+    if use_websocket.is_some() {
+        object.remove("use_websocket");
+    }
+
+    let model = required_non_empty_string(&object, "model", "model")?;
+    if model.trim().is_empty() {
         return Err(RequestDecodeError::EmptyField {
             field: "model".to_owned(),
         });
@@ -336,7 +337,6 @@ pub(super) fn decode_request_inner(
     let continuation = object
         .get("previous_response_id")
         .and_then(Value::as_str)
-        .filter(|response_id| !response_id.is_empty())
         .map(|response_id| ContinuationIntent::PreviousResponseId(response_id.to_owned()))
         .unwrap_or(ContinuationIntent::None);
 
@@ -352,8 +352,7 @@ pub(super) fn decode_request_inner(
     Ok(DecodedResponsesRequest {
         operation,
         metadata: ResponsesRequestMetadata {
-            requested_model: model.clone(),
-            public_model: model,
+            requested_model: model,
             stream,
             store,
             continuation,
@@ -367,26 +366,107 @@ fn inject_subagent_metadata(body: &mut Map<String, Value>, subagent: &str) {
     let metadata = body
         .entry("client_metadata".to_owned())
         .or_insert_with(|| Value::Object(Map::new()));
-    if !metadata.is_object() {
-        *metadata = Value::Object(Map::new());
-    }
-    if let Some(metadata) = metadata.as_object_mut() {
-        metadata.insert(
-            OPENAI_SUBAGENT_KEY.to_owned(),
-            Value::String(subagent.to_owned()),
-        );
-    }
+    let Some(metadata) = metadata.as_object_mut() else {
+        return;
+    };
+    metadata.insert(
+        OPENAI_SUBAGENT_KEY.to_owned(),
+        Value::String(subagent.to_owned()),
+    );
 }
 
 fn header_string(headers: &HeaderMap, name: &str) -> Option<String> {
     headers
         .get(name)
         .and_then(|value| value.to_str().ok())
-        .map(str::trim)
-        .filter(|value| !value.is_empty())
         .map(ToOwned::to_owned)
 }
 
+fn passthrough_headers(headers: &HeaderMap) -> Vec<Value> {
+    let connection_headers = headers
+        .get_all("connection")
+        .iter()
+        .filter_map(|value| value.to_str().ok())
+        .flat_map(|value| value.split(','))
+        .map(str::trim)
+        .filter(|name| !name.is_empty())
+        .map(str::to_ascii_lowercase)
+        .collect::<Vec<_>>();
+
+    headers
+        .iter()
+        .filter(|(name, _)| passthrough_header_name(name.as_str(), &connection_headers))
+        .map(|(name, value)| {
+            Value::Array(vec![
+                Value::String(name.as_str().to_owned()),
+                Value::String(STANDARD.encode(value.as_bytes())),
+            ])
+        })
+        .collect()
+}
+
+fn passthrough_header_name(name: &str, connection_headers: &[String]) -> bool {
+    if connection_headers
+        .iter()
+        .any(|connection_header| connection_header.eq_ignore_ascii_case(name))
+        || name.starts_with("sec-websocket-")
+        || name.starts_with("x-grok-")
+        || name.starts_with("x-xai-")
+    {
+        return false;
+    }
+
+    !matches!(
+        name,
+        // 逐跳头、上游 authority 和重序列化后的实体长度由 transport 重建。
+        "connection"
+            | "keep-alive"
+            | "proxy-connection"
+            | "proxy-authenticate"
+            | "proxy-authorization"
+            | "te"
+            | "trailer"
+            | "transfer-encoding"
+            | "upgrade"
+            | "host"
+            | "content-length"
+            // 下游连接诊断事实只用于本地观测，不能伪装成 OpenAI 请求事实。
+            | "forwarded"
+            | "x-forwarded-for"
+            | "x-forwarded-host"
+            | "x-forwarded-proto"
+            | "x-forwarded-port"
+            | "x-real-ip"
+            | "true-client-ip"
+            | "cf-connecting-ip"
+            | "x-request-id"
+            // 下游鉴权和账号 cookie 绝不能成为上游账号身份。
+            | "authorization"
+            | "x-api-key"
+            | "cookie"
+            | "cookie2"
+            | "chatgpt-account-id"
+            | "chatgpt-organization-id"
+            | "chatgpt-org-id"
+            | "chatgpt-project-id"
+            | "openai-organization"
+            | "openai-project"
+            | "x-openai-organization"
+            | "x-openai-project"
+            // installation ID 始终由当前 lease 重建。
+            | "x-codex-installation-id"
+            // 上游指纹必须由运行时画像统一生成，客户端 originator/User-Agent
+            // 不能透传覆盖，避免不同下游客户端暴露不一致的设备指纹。
+            | "originator"
+            | "user-agent"
+            // 设备 attestation/integrity 头只能由官方客户端或网关自身生成，
+            // 客户端注入的 x-oai-attestation / X-OAI-IS 不得透传上游。
+            | "x-oai-attestation"
+            | "x-oai-is"
+            | "x-oai-is-update"
+    )
+}
+
 fn required_non_empty_string<'a>(
     object: &'a Map<String, Value>,
     key: &str,

backend/crates/gateway-api/src/openai/responses/response.rs

@@ -11,15 +11,14 @@ const OPENAI_PROTOCOL: &str = "openai";
 
 /// OpenAI Responses wire 的转发器。
 ///
-/// OpenAI Provider 与 xAI adapter 都必须交付 OpenAI wire。这里仅保留同一
-/// 响应的身份和终态校验，不再从 canonical facts 重建客户端 JSON；因此
-/// OpenAI 上游的未知字段、字段顺序和事件语义不会被 API 层二次解释。
+/// OpenAI Provider 与 xAI adapter 都必须交付 OpenAI wire。wire 是客户端交付
+/// 与终态判断的事实来源；canonical facts 只在 wire 暂未携带 ID 时提供旁路观测，
+/// 不得反过来拒绝或改写上游事件。
 #[derive(Debug, Default)]
 pub struct OpenAiResponsesEncoder {
     response_id: Option<String>,
     wire_terminal: Option<Value>,
     wire_failure: bool,
-    canonical_completed: bool,
 }
 
 impl OpenAiResponsesEncoder {
@@ -30,53 +29,41 @@ impl OpenAiResponsesEncoder {
             response_id: None,
             wire_terminal: None,
             wire_failure: false,
-            canonical_completed: false,
         }
     }
 
     /// 消费一个 Provider event，并返回 SSE frames。
-    ///
-    /// # Errors
-    ///
-    /// 同一响应身份变化时返回错误。
-    pub fn push_sse(&mut self, event: &ProviderEvent) -> Result<Vec<Bytes>, ResponseEncodeError> {
-        self.observe_identity(event)?;
+    pub fn push_sse(&mut self, event: &ProviderEvent) -> Vec<Bytes> {
+        self.observe_canonical_identity(event);
         let Some(wire) = openai_wire(event) else {
-            return Ok(Vec::new());
+            return Vec::new();
         };
-        self.observe_wire_terminal(wire);
+        self.observe_wire(wire);
         if let Some(raw_sse_frame) = wire.raw_sse_frame() {
-            return Ok(vec![raw_sse_frame.clone()]);
+            return vec![raw_sse_frame.clone()];
         }
-        Ok(vec![Bytes::from(encode_sse_event_with_metadata(
+        vec![Bytes::from(encode_sse_event_with_metadata(
             wire.event_type().unwrap_or_default(),
             &wire.data().to_string(),
             wire.sse_id(),
             wire.sse_retry(),
-        ))])
+        ))]
     }
 
     /// 消费一个 Provider event，并返回 WebSocket JSON messages。
-    ///
-    /// # Errors
-    ///
-    /// 同一响应身份变化时返回错误。
-    pub fn push_websocket(
-        &mut self,
-        event: &ProviderEvent,
-    ) -> Result<Vec<String>, ResponseEncodeError> {
-        self.observe_identity(event)?;
+    pub fn push_websocket(&mut self, event: &ProviderEvent) -> Vec<String> {
+        self.observe_canonical_identity(event);
         let Some(wire) = openai_wire(event).filter(|wire| wire.has_json_data()) else {
-            return Ok(Vec::new());
+            return Vec::new();
         };
-        self.observe_wire_terminal(wire);
-        Ok(vec![wire.data().to_string()])
+        self.observe_wire(wire);
+        vec![wire.data().to_string()]
     }
 
-    /// 返回是否已经看到同一响应的 canonical 与 wire 终态。
+    /// 返回是否已经看到客户端可见的 wire 终态。
     #[must_use]
     pub fn is_completed(&self) -> bool {
-        self.wire_terminal.is_some() && self.canonical_completed
+        self.wire_terminal.is_some()
     }
 
     /// 返回是否已把 Provider 原生失败 event 交付给客户端。
@@ -95,39 +82,31 @@ impl OpenAiResponsesEncoder {
     ///
     /// # Errors
     ///
-    /// 缺少 wire 或 canonical 终态时返回错误。
+    /// 缺少可转换为非流式响应的 wire 终态时返回错误。
     pub fn finish(self) -> Result<Value, ResponseEncodeError> {
-        if self.canonical_completed {
-            self.wire_terminal
-                .ok_or(ResponseEncodeError::MissingWireTerminal)
-        } else {
-            Err(ResponseEncodeError::MissingWireTerminal)
-        }
+        self.wire_terminal
+            .ok_or(ResponseEncodeError::MissingWireTerminal)
     }
 
-    fn observe_identity(&mut self, event: &ProviderEvent) -> Result<(), ResponseEncodeError> {
+    fn observe_canonical_identity(&mut self, event: &ProviderEvent) {
         for fact in event.canonical_facts() {
             let metadata = match fact {
-                GatewayEvent::Started(metadata) => metadata,
-                GatewayEvent::Completed(metadata) => {
-                    self.canonical_completed = true;
-                    metadata
-                }
+                GatewayEvent::Started(metadata) | GatewayEvent::Completed(metadata) => metadata,
                 _ => continue,
             };
-            if self
-                .response_id
-                .as_deref()
-                .is_some_and(|current| current != metadata.response_id())
-            {
-                return Err(ResponseEncodeError::WireIdentityChanged);
-            }
             self.response_id = Some(metadata.response_id().to_owned());
         }
-        Ok(())
     }
 
-    fn observe_wire_terminal(&mut self, wire: &ProtocolWireEvent) {
+    fn observe_wire(&mut self, wire: &ProtocolWireEvent) {
+        if let Some(response_id) = wire
+            .data()
+            .pointer("/response/id")
+            .or_else(|| wire.data().get("response_id"))
+            .and_then(Value::as_str)
+        {
+            self.response_id = Some(response_id.to_owned());
+        }
         let effective_type = wire
             .event_type()
             .or_else(|| wire.data().get("type").and_then(Value::as_str));

backend/crates/gateway-api/src/openai/responses/websocket.rs

@@ -1,722 +0,0 @@
-//! OpenAI Responses WebSocket adapter。
-
-use std::net::{IpAddr, SocketAddr};
-use std::sync::Arc;
-
-use axum::{
-    extract::{
-        Extension, State,
-        connect_info::ConnectInfo,
-        ws::{CloseFrame, Message, WebSocket, WebSocketUpgrade, close_code},
-    },
-    http::{HeaderMap, StatusCode},
-    response::{IntoResponse, Response},
-};
-use futures::StreamExt;
-use gateway_core::engine::execution::{AuthenticatedClient, ClientTransport, StartedExecution};
-use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
-use gateway_core::error::{GatewayError, GatewayErrorKind};
-use gateway_core::event::ProviderResponseHeader;
-use gateway_core::lifecycle::{ConnectionGuard, ConnectionLifecycle};
-use gateway_core::operation::ProviderSessionState;
-use serde_json::{Map, Value, json};
-use thiserror::Error;
-
-use crate::{
-    ApiState,
-    openai::{
-        auth::{authenticate_client, authentication_error_response},
-        error::{gateway_error_contract, gateway_error_from_engine, runtime_unavailable_response},
-        router::MAX_CLIENT_REQUEST_BODY_BYTES,
-        service::OpenAiService,
-    },
-};
-
-use super::{
-    DecodedResponsesRequest, OpenAiResponsesEncoder, ProtocolErrorBody, RequestDecodeError,
-    http::{PendingExecution, request_client_context},
-    request::OpenAiRequestHeaders,
-};
-
-const ACTIVE_RESPONSE_VIOLATION: &str = "Only one response.create may be active per connection";
-const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
-
-/// 将已认证的 `GET /v1/responses` 升级为 Responses WebSocket。
-pub(crate) async fn responses_websocket(
-    State(state): State<ApiState>,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    websocket: WebSocketUpgrade,
-) -> Response {
-    let service = state.openai().clone();
-    let client = match authenticate_client(&service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let (client_ip, user_agent) = request_client_context(
-        &headers,
-        connect_info.map(|Extension(ConnectInfo(address))| address),
-    );
-    ResponsesWebSocketAdapter::new(service).upgrade_with_client_context(
-        websocket,
-        client,
-        client_ip,
-        user_agent,
-        OpenAiRequestHeaders::from_headers(&headers),
-    )
-}
-
-/// 已鉴权 Responses WebSocket 升级边界。
-#[derive(Clone)]
-pub(crate) struct ResponsesWebSocketAdapter {
-    service: OpenAiService,
-}
-
-impl ResponsesWebSocketAdapter {
-    /// 绑定应用提供的唯一 OpenAI 客户端服务端口。
-    #[must_use]
-    pub const fn new(service: OpenAiService) -> Self {
-        Self { service }
-    }
-
-    fn upgrade_with_client_context(
-        &self,
-        websocket: WebSocketUpgrade,
-        client: AuthenticatedClient,
-        client_ip: Option<IpAddr>,
-        user_agent: Option<String>,
-        request_headers: OpenAiRequestHeaders,
-    ) -> Response {
-        let connection_guard = match self.service.try_register_connection() {
-            Ok(guard) => guard,
-            Err(_) => return runtime_unavailable_response().into_response(),
-        };
-        let session = ResponsesWebSocketSession {
-            service: self.service.clone(),
-            client,
-            connection_id: self.service.next_request_id().replacen("req_", "ws_", 1),
-            client_ip,
-            user_agent,
-            request_headers,
-            lifecycle: self.service.lifecycle(),
-            _connection_guard: connection_guard,
-        };
-        websocket
-            .max_message_size(MAX_CLIENT_REQUEST_BODY_BYTES)
-            .max_frame_size(MAX_CLIENT_REQUEST_BODY_BYTES)
-            .on_upgrade(move |socket| async move {
-                serve_responses_websocket(socket, session).await;
-            })
-    }
-}
-
-struct ResponsesWebSocketSession {
-    service: OpenAiService,
-    client: AuthenticatedClient,
-    connection_id: String,
-    client_ip: Option<IpAddr>,
-    user_agent: Option<String>,
-    request_headers: OpenAiRequestHeaders,
-    lifecycle: Arc<dyn ConnectionLifecycle>,
-    _connection_guard: Box<dyn ConnectionGuard>,
-}
-
-async fn serve_responses_websocket(mut socket: WebSocket, session: ResponsesWebSocketSession) {
-    tracing::info!(
-        websocket_connection_id = %session.connection_id,
-        "Responses WebSocket connected"
-    );
-    let mut request_count = 0_u64;
-    let mut replay = ConnectionReplaySnapshot::default();
-
-    let cancellation = session.lifecycle.cancellation();
-    loop {
-        let message = tokio::select! {
-            () = cancellation.cancelled() => break,
-            message = socket.next() => message,
-        };
-        let Some(message) = message else {
-            break;
-        };
-        let payload = match message {
-            Ok(Message::Text(payload)) => payload,
-            Ok(Message::Ping(_) | Message::Pong(_)) => continue,
-            Ok(Message::Close(_)) => break,
-            Ok(Message::Binary(_)) => {
-                close_for_protocol_violation(&mut socket, TEXT_FRAMES_ONLY).await;
-                break;
-            }
-            Err(error) => {
-                tracing::info!(
-                    websocket_connection_id = %session.connection_id,
-                    error = %error,
-                    "Responses WebSocket receive failed"
-                );
-                break;
-            }
-        };
-        request_count = request_count.saturating_add(1);
-        let correlation_id = session.service.next_request_id();
-        let decoded =
-            match decode_response_create_with_context(payload.as_str(), &session.request_headers) {
-                Ok(decoded) => {
-                    decoded.with_client_context(session.client_ip, session.user_agent.clone())
-                }
-                Err(error) => {
-                    tracing::info!(
-                        websocket_connection_id = %session.connection_id,
-                        request_id = %correlation_id,
-                        error = %error,
-                        "Responses WebSocket request rejected"
-                    );
-                    if send_protocol_error(
-                        &mut socket,
-                        StatusCode::BAD_REQUEST,
-                        error.protocol_body(),
-                        &correlation_id,
-                    )
-                    .await
-                        == ForwardOutcome::Disconnect
-                    {
-                        break;
-                    }
-                    continue;
-                }
-            };
-        let decoded = replay.prepare(decoded);
-        let started = match session
-            .service
-            .start_response(
-                session.client.clone(),
-                decoded,
-                ClientTransport::WebSocket,
-                "/v1/responses",
-            )
-            .await
-        {
-            Ok(started) => started,
-            Err(error) => {
-                if send_gateway_error(&mut socket, &error, &correlation_id).await
-                    == ForwardOutcome::Disconnect
-                {
-                    break;
-                }
-                continue;
-            }
-        };
-
-        if forward_execution(&mut socket, started, &mut replay).await == ForwardOutcome::Disconnect
-        {
-            break;
-        }
-    }
-
-    tracing::info!(
-        websocket_connection_id = %session.connection_id,
-        request_count,
-        "Responses WebSocket disconnected"
-    );
-}
-
-#[derive(Clone, Copy, PartialEq, Eq)]
-enum ForwardOutcome {
-    Continue,
-    Disconnect,
-}
-
-#[derive(Default)]
-struct ConnectionReplaySnapshot {
-    last_response_id: Option<String>,
-    provider_state: Option<ProviderSessionState>,
-}
-
-impl ConnectionReplaySnapshot {
-    fn prepare(&self, request: DecodedResponsesRequest) -> DecodedResponsesRequest {
-        match (
-            request.metadata().continuation().previous_response_id(),
-            self.last_response_id.as_deref(),
-            self.provider_state.as_ref(),
-        ) {
-            (Some(previous), Some(last), Some(state)) if previous == last => {
-                request.with_provider_session_state(state.clone())
-            }
-            _ => request,
-        }
-    }
-
-    fn commit(&mut self, response_id: String, provider_state: Option<ProviderSessionState>) {
-        self.last_response_id = Some(response_id);
-        self.provider_state = provider_state;
-    }
-}
-
-async fn forward_execution(
-    socket: &mut WebSocket,
-    started: StartedExecution,
-    replay: &mut ConnectionReplaySnapshot,
-) -> ForwardOutcome {
-    let request_id = started.request_id.to_string();
-    let streaming = started.stream;
-    let mut execution = PendingExecution::new(started.session);
-    if !streaming {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "WebSocket execution was not initialized as a stream",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let first = loop {
-        match next_active_input(socket, &mut execution).await {
-            ActiveInput::Event(Ok(Some(event))) => break event,
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended before its first event",
-                );
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Control => continue,
-            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return ForwardOutcome::Disconnect;
-            }
-        }
-    };
-    let requirement = first.commit_requirement();
-    let mut first = first.into_provider_events();
-    if requirement != CommitRequirement::CommitBeforeDelivery {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway first event did not require commit",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let mut encoder = OpenAiResponsesEncoder::new();
-    let mut provider_state = None;
-    let mut first_messages = Vec::new();
-    for event in &mut first {
-        if let Some(update) = event.take_session_update() {
-            provider_state = Some(update);
-        }
-        match encoder.push_websocket(event) {
-            Ok(messages) => first_messages.extend(messages),
-            Err(error) => {
-                return send_protocol_error(
-                    socket,
-                    StatusCode::INTERNAL_SERVER_ERROR,
-                    error.protocol_body(),
-                    &request_id,
-                )
-                .await;
-            }
-        }
-    }
-    if first_messages.is_empty() {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway commit batch encoded no output",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let Some(response_session) = execution.session_mut() else {
-        return ForwardOutcome::Disconnect;
-    };
-    let response_headers = response_session.response_headers().to_vec();
-    if let Err(error) = response_session.commit_downstream(None).await {
-        let error = gateway_error_from_engine(&error);
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    if encoder.is_completed() {
-        if let Err(outcome) = confirm_completed_execution(socket, &mut execution, &request_id).await
-        {
-            return outcome;
-        }
-        if let Err(error) = commit_connection_replay(replay, &encoder, provider_state.take()) {
-            return send_gateway_error(socket, &error, &request_id).await;
-        }
-        if !send_text(
-            socket,
-            response_metadata_event(&request_id, &response_headers),
-        )
-        .await
-            || !send_messages(socket, first_messages).await
-        {
-            return ForwardOutcome::Disconnect;
-        }
-        execution.disarm();
-        return ForwardOutcome::Continue;
-    }
-    if !send_text(
-        socket,
-        response_metadata_event(&request_id, &response_headers),
-    )
-    .await
-        || !send_messages(socket, first_messages).await
-    {
-        return ForwardOutcome::Disconnect;
-    }
-
-    loop {
-        match next_active_input(socket, &mut execution).await {
-            ActiveInput::Event(Ok(Some(delivery))) => {
-                let requirement = delivery.commit_requirement();
-                let mut events = delivery.into_provider_events();
-                if requirement != CommitRequirement::AlreadyCommitted {
-                    let error = GatewayError::new(
-                        GatewayErrorKind::Internal,
-                        "gateway requested another downstream commit",
-                    );
-                    return send_gateway_error(socket, &error, &request_id).await;
-                }
-                let mut messages = Vec::new();
-                for event in &mut events {
-                    if let Some(update) = event.take_session_update() {
-                        provider_state = Some(update);
-                    }
-                    match encoder.push_websocket(event) {
-                        Ok(encoded) => messages.extend(encoded),
-                        Err(error) => {
-                            return send_protocol_error(
-                                socket,
-                                StatusCode::INTERNAL_SERVER_ERROR,
-                                error.protocol_body(),
-                                &request_id,
-                            )
-                            .await;
-                        }
-                    }
-                }
-                if encoder.is_completed() {
-                    if let Err(outcome) =
-                        confirm_completed_execution(socket, &mut execution, &request_id).await
-                    {
-                        return outcome;
-                    }
-                    if let Err(error) =
-                        commit_connection_replay(replay, &encoder, provider_state.take())
-                    {
-                        return send_gateway_error(socket, &error, &request_id).await;
-                    }
-                    if !send_messages(socket, messages).await {
-                        return ForwardOutcome::Disconnect;
-                    }
-                    execution.disarm();
-                    return ForwardOutcome::Continue;
-                }
-                if !send_messages(socket, messages).await {
-                    return ForwardOutcome::Disconnect;
-                }
-            }
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended without a terminal event",
-                );
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Event(Err(error)) => {
-                if encoder.has_wire_failure() {
-                    execution.disarm();
-                    return ForwardOutcome::Continue;
-                }
-                let error = gateway_error_from_engine(&error);
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Control => {}
-            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return ForwardOutcome::Disconnect;
-            }
-        }
-    }
-}
-
-fn commit_connection_replay(
-    replay: &mut ConnectionReplaySnapshot,
-    encoder: &OpenAiResponsesEncoder,
-    provider_state: Option<ProviderSessionState>,
-) -> Result<(), GatewayError> {
-    let response_id = encoder.response_id().ok_or_else(|| {
-        GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway completed a response without an identity",
-        )
-    })?;
-    replay.commit(response_id.to_owned(), provider_state);
-    Ok(())
-}
-
-async fn confirm_completed_execution(
-    socket: &mut WebSocket,
-    execution: &mut PendingExecution,
-    request_id: &str,
-) -> Result<(), ForwardOutcome> {
-    loop {
-        match next_active_input(socket, execution).await {
-            ActiveInput::Event(Ok(None))
-                if execution
-                    .session_mut()
-                    .is_some_and(|session| session.is_finalized()) =>
-            {
-                return Ok(());
-            }
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response was not finalized after its terminal event",
-                );
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Event(Ok(Some(_))) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response continued after its terminal event",
-                );
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Control => {}
-            ActiveInput::Disconnect => return Err(ForwardOutcome::Disconnect),
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return Err(ForwardOutcome::Disconnect);
-            }
-        }
-    }
-}
-
-enum ActiveInput {
-    Event(Result<Option<CoordinatedEvent>, EngineError>),
-    Control,
-    Disconnect,
-    ProtocolViolation,
-}
-
-async fn next_active_input(
-    socket: &mut WebSocket,
-    execution: &mut PendingExecution,
-) -> ActiveInput {
-    let Some(session) = execution.session_mut() else {
-        return ActiveInput::Disconnect;
-    };
-    tokio::select! {
-        event = session.next_event() => ActiveInput::Event(event),
-        message = socket.next() => match message {
-            Some(Ok(Message::Ping(_) | Message::Pong(_))) => ActiveInput::Control,
-            Some(Ok(Message::Close(_))) | None | Some(Err(_)) => ActiveInput::Disconnect,
-            Some(Ok(Message::Text(_) | Message::Binary(_))) => ActiveInput::ProtocolViolation,
-        },
-    }
-}
-
-/// 使用连接级请求头和 Provider 上下文解码官方 `response.create` 文本帧。
-///
-/// 缺省 `stream` 等价于 WebSocket 固有的流式语义；显式 `false` 会被拒绝。
-///
-/// # Errors
-///
-/// 帧不是合法 JSON object、消息类型错误、显式关闭 stream，或 Responses 请求
-/// 无法映射到 canonical operation 时返回不包含正文内容的稳定错误。
-pub fn decode_response_create_with_context(
-    payload: &str,
-    request_headers: &OpenAiRequestHeaders,
-) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
-    decode_response_create_inner(payload, request_headers)
-}
-
-fn decode_response_create_inner(
-    payload: &str,
-    request_headers: &OpenAiRequestHeaders,
-) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
-    let Value::Object(mut body) = serde_json::from_str::<Value>(payload)
-        .map_err(|_| ResponseCreateFrameError::InvalidJson)?
-    else {
-        return Err(ResponseCreateFrameError::ExpectedObject);
-    };
-    match body.remove("type") {
-        Some(Value::String(message_type)) if message_type == "response.create" => {}
-        _ => return Err(ResponseCreateFrameError::UnsupportedType),
-    }
-    if matches!(body.get("stream"), Some(value) if value.as_bool() != Some(true)) {
-        return Err(ResponseCreateFrameError::StreamingRequired);
-    }
-    let encoded = serde_json::to_vec(&Value::Object(body))
-        .map_err(|_| ResponseCreateFrameError::InvalidJson)?;
-    super::request::decode_request_inner(&encoded, false, request_headers)
-        .map_err(ResponseCreateFrameError::Request)
-}
-
-/// `response.create` 帧的稳定安全错误。
-#[derive(Debug, Clone, PartialEq, Eq, Error)]
-pub enum ResponseCreateFrameError {
-    /// 文本不是合法 JSON。
-    #[error("response.create frame must be valid JSON")]
-    InvalidJson,
-    /// 顶层不是 object。
-    #[error("response.create frame must be a JSON object")]
-    ExpectedObject,
-    /// `type` 缺失或不是 `response.create`。
-    #[error("unsupported Responses WebSocket message type")]
-    UnsupportedType,
-    /// WebSocket 请求显式声明 `stream=false`。
-    #[error("Responses WebSocket requests require stream=true")]
-    StreamingRequired,
-    /// 内层 Responses 请求无法映射到 canonical operation。
-    #[error(transparent)]
-    Request(RequestDecodeError),
-}
-
-impl ResponseCreateFrameError {
-    fn protocol_body(&self) -> ProtocolErrorBody {
-        match self {
-            Self::Request(error) => error.protocol_body(),
-            Self::InvalidJson => RequestDecodeError::MalformedJson.protocol_body(),
-            Self::ExpectedObject => RequestDecodeError::ExpectedObject.protocol_body(),
-            Self::UnsupportedType => RequestDecodeError::InvalidValue {
-                field: "type".to_owned(),
-            }
-            .protocol_body(),
-            Self::StreamingRequired => RequestDecodeError::InvalidValue {
-                field: "stream".to_owned(),
-            }
-            .protocol_body(),
-        }
-    }
-}
-
-fn response_metadata_event(
-    request_id: &str,
-    response_headers: &[ProviderResponseHeader],
-) -> String {
-    let mut headers = response_headers
-        .iter()
-        .filter_map(|header| {
-            super::safe_response_header_name(header.name()).map(|name| {
-                (
-                    name.to_owned(),
-                    Value::String(header.value().as_str().to_owned()),
-                )
-            })
-        })
-        .collect::<Map<String, Value>>();
-    headers.insert(
-        "x-request-id".to_owned(),
-        Value::String(request_id.to_owned()),
-    );
-    json!({
-        "type": "response.metadata",
-        "headers": headers,
-    })
-    .to_string()
-}
-
-async fn send_gateway_error(
-    socket: &mut WebSocket,
-    error: &GatewayError,
-    request_id: &str,
-) -> ForwardOutcome {
-    let (status, default_type, default_code) = gateway_error_contract(error.kind());
-    if send_error_event(
-        socket,
-        status,
-        error.client_error_type().unwrap_or(default_type),
-        error.client_error_code().unwrap_or(default_code),
-        error.client_message(),
-        None,
-        request_id,
-    )
-    .await
-    {
-        ForwardOutcome::Continue
-    } else {
-        ForwardOutcome::Disconnect
-    }
-}
-
-async fn send_protocol_error(
-    socket: &mut WebSocket,
-    status: StatusCode,
-    body: ProtocolErrorBody,
-    request_id: &str,
-) -> ForwardOutcome {
-    let error = body.error;
-    if send_error_event(
-        socket,
-        status,
-        error.kind,
-        error.code,
-        &error.message,
-        error.param.as_deref(),
-        request_id,
-    )
-    .await
-    {
-        ForwardOutcome::Continue
-    } else {
-        ForwardOutcome::Disconnect
-    }
-}
-
-async fn send_error_event(
-    socket: &mut WebSocket,
-    status: StatusCode,
-    error_type: &str,
-    code: &str,
-    message: &str,
-    param: Option<&str>,
-    request_id: &str,
-) -> bool {
-    let mut error = Map::new();
-    error.insert("type".to_owned(), Value::String(error_type.to_owned()));
-    error.insert("code".to_owned(), Value::String(code.to_owned()));
-    error.insert("message".to_owned(), Value::String(message.to_owned()));
-    if let Some(param) = param {
-        error.insert("param".to_owned(), Value::String(param.to_owned()));
-    }
-    send_text(
-        socket,
-        json!({
-            "type": "error",
-            "status": status.as_u16(),
-            "error": error,
-            "request_id": request_id,
-        })
-        .to_string(),
-    )
-    .await
-}
-
-async fn send_messages(socket: &mut WebSocket, messages: Vec<String>) -> bool {
-    for message in messages {
-        if !send_text(socket, message).await {
-            return false;
-        }
-    }
-    true
-}
-
-async fn send_text(socket: &mut WebSocket, payload: String) -> bool {
-    if let Err(error) = socket.send(Message::Text(payload.into())).await {
-        tracing::info!(error = %error, "Responses WebSocket send failed");
-        return false;
-    }
-    true
-}
-
-async fn close_for_protocol_violation(socket: &mut WebSocket, reason: &'static str) {
-    let _ = socket
-        .send(Message::Close(Some(CloseFrame {
-            code: close_code::POLICY,
-            reason: reason.into(),
-        })))
-        .await;
-}

backend/crates/gateway-api/src/openai/responses/websocket/connection.rs

@@ -0,0 +1,550 @@
+//! 下游客户端 WebSocket 的单 owner pump 与有界收发边界。
+
+use std::{
+    fmt,
+    sync::{
+        Arc,
+        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+    },
+    time::Duration,
+};
+
+use axum::extract::ws::{CloseFrame, Message, WebSocket, close_code};
+use futures::{Sink, SinkExt, Stream, StreamExt};
+use gateway_core::engine::CancellationToken;
+use thiserror::Error;
+use tokio::{
+    sync::{mpsc, oneshot},
+    task::JoinHandle,
+    time::{Instant, timeout},
+};
+
+const OUTBOUND_COMMAND_BUFFER: usize = 32;
+const INBOUND_EVENT_BUFFER: usize = 32;
+const DOWNSTREAM_WRITE_TIMEOUT: Duration = Duration::from_secs(5 * 60);
+const CONNECTION_MAX_AGE: Duration = Duration::from_secs(60 * 60);
+
+#[derive(Clone, Copy)]
+pub(super) struct ConnectionConfig {
+    pub(super) write_timeout: Duration,
+    pub(super) max_age: Duration,
+}
+
+impl ConnectionConfig {
+    pub(super) const PRODUCTION: Self = Self {
+        write_timeout: DOWNSTREAM_WRITE_TIMEOUT,
+        max_age: CONNECTION_MAX_AGE,
+    };
+}
+
+/// 业务层可观察的客户端输入；Ping/Pong 始终由 pump 消费。
+pub(super) enum ConnectionEvent {
+    Text(String),
+    Binary,
+    Expired,
+    Exited(PumpExitReason),
+}
+
+/// 下游写入阶段；名称刻意使用 write，而不是暗示客户端已消费的 delivery。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(super) enum FramePhase {
+    Metadata,
+    First,
+    Data,
+    Terminal,
+    FirstAndTerminal,
+    Error,
+    ConnectionLimit,
+    Close,
+}
+
+impl FramePhase {
+    const fn as_str(self) -> &'static str {
+        match self {
+            Self::Metadata => "metadata",
+            Self::First => "first",
+            Self::Data => "data",
+            Self::Terminal => "terminal",
+            Self::FirstAndTerminal => "first_and_terminal",
+            Self::Error => "error",
+            Self::ConnectionLimit => "connection_limit",
+            Self::Close => "close",
+        }
+    }
+
+    const fn is_milestone(self) -> bool {
+        matches!(
+            self,
+            Self::First
+                | Self::Terminal
+                | Self::FirstAndTerminal
+                | Self::Error
+                | Self::ConnectionLimit
+                | Self::Close
+        )
+    }
+}
+
+#[derive(Clone)]
+pub(super) struct WriteContext {
+    request_id: Option<Arc<str>>,
+    phase: FramePhase,
+}
+
+impl WriteContext {
+    pub(super) fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
+        Self {
+            request_id: Some(Arc::clone(request_id)),
+            phase,
+        }
+    }
+
+    pub(super) const fn connection(phase: FramePhase) -> Self {
+        Self {
+            request_id: None,
+            phase,
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(super) enum PumpExitReason {
+    ClientClose,
+    PeerEof,
+    ReadError,
+    WriteError,
+    WriteTimeout,
+    LifecycleShutdown,
+    ConnectionMaxAge,
+    CoordinatorDropped,
+    InboundOverload,
+    ServerClose,
+    PumpStopped,
+}
+
+impl PumpExitReason {
+    pub(super) const fn as_str(self) -> &'static str {
+        match self {
+            Self::ClientClose => "client_close",
+            Self::PeerEof => "peer_eof",
+            Self::ReadError => "read_error",
+            Self::WriteError => "write_error",
+            Self::WriteTimeout => "write_timeout",
+            Self::LifecycleShutdown => "lifecycle_shutdown",
+            Self::ConnectionMaxAge => "connection_max_age",
+            Self::CoordinatorDropped => "coordinator_dropped",
+            Self::InboundOverload => "inbound_overload",
+            Self::ServerClose => "server_close",
+            Self::PumpStopped => "pump_stopped",
+        }
+    }
+}
+
+#[derive(Debug, Error)]
+pub(super) enum ConnectionWriteError {
+    #[error("downstream WebSocket pump is closed")]
+    Closed,
+    #[error("downstream WebSocket write timed out after {timeout:?}")]
+    Timeout { timeout: Duration },
+    #[error("downstream WebSocket transport write failed: {message}")]
+    Transport { message: String },
+}
+
+struct ConnectionCommand {
+    message: Message,
+    context: WriteContext,
+    acknowledged: oneshot::Sender<Result<(), ConnectionWriteError>>,
+}
+
+#[derive(Default)]
+struct ConnectionStats {
+    command_queue_high_water: AtomicUsize,
+    command_backpressure_count: AtomicU64,
+    ping_received_count: AtomicU64,
+    pong_written_count: AtomicU64,
+}
+
+impl ConnectionStats {
+    fn observe_command_queue(&self, sender: &mpsc::Sender<ConnectionCommand>) {
+        let queued = OUTBOUND_COMMAND_BUFFER
+            .saturating_sub(sender.capacity())
+            .saturating_add(1)
+            .min(OUTBOUND_COMMAND_BUFFER);
+        self.command_queue_high_water
+            .fetch_max(queued, Ordering::Relaxed);
+        if sender.capacity() == 0 {
+            self.command_backpressure_count
+                .fetch_add(1, Ordering::Relaxed);
+        }
+    }
+}
+
+pub(super) struct ResponsesWebSocketConnection {
+    connection_id: Arc<str>,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    commands: Option<mpsc::Sender<ConnectionCommand>>,
+    incoming: mpsc::Receiver<ConnectionEvent>,
+    pump_task: Option<JoinHandle<()>>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+    exit_reason: Option<PumpExitReason>,
+}
+
+impl ResponsesWebSocketConnection {
+    pub(super) fn new(
+        socket: WebSocket,
+        connection_id: String,
+        cancellation: CancellationToken,
+    ) -> Self {
+        spawn_connection(
+            socket,
+            Arc::<str>::from(connection_id),
+            cancellation,
+            ConnectionConfig::PRODUCTION,
+        )
+    }
+
+    pub(super) fn id(&self) -> &str {
+        &self.connection_id
+    }
+
+    pub(super) fn is_expired(&self) -> bool {
+        self.expired.load(Ordering::Acquire)
+    }
+
+    pub(super) fn age(&self) -> Duration {
+        self.opened_at.elapsed()
+    }
+
+    pub(super) async fn next_event(&mut self) -> Option<ConnectionEvent> {
+        let event = self.incoming.recv().await;
+        if let Some(ConnectionEvent::Exited(reason)) = event.as_ref() {
+            self.exit_reason.get_or_insert(*reason);
+        } else if event.is_none() {
+            self.exit_reason.get_or_insert(PumpExitReason::PumpStopped);
+        }
+        event
+    }
+
+    pub(super) async fn send_text(
+        &mut self,
+        payload: String,
+        context: WriteContext,
+    ) -> Result<(), ConnectionWriteError> {
+        self.send(Message::Text(payload.into()), context).await
+    }
+
+    pub(super) async fn close_policy(
+        &mut self,
+        reason: &'static str,
+        request_id: Option<&Arc<str>>,
+    ) {
+        let context = request_id.map_or_else(
+            || WriteContext::connection(FramePhase::Close),
+            |request_id| WriteContext::request(request_id, FramePhase::Close),
+        );
+        self.close(
+            CloseFrame {
+                code: close_code::POLICY,
+                reason: reason.into(),
+            },
+            context,
+            PumpExitReason::ServerClose,
+        )
+        .await;
+    }
+
+    pub(super) async fn close_for_connection_limit(&mut self, reason: &'static str) {
+        self.close(
+            CloseFrame {
+                code: close_code::NORMAL,
+                reason: reason.into(),
+            },
+            WriteContext::connection(FramePhase::Close),
+            PumpExitReason::ConnectionMaxAge,
+        )
+        .await;
+    }
+
+    async fn close(
+        &mut self,
+        frame: CloseFrame,
+        context: WriteContext,
+        exit_reason: PumpExitReason,
+    ) {
+        if self
+            .send(Message::Close(Some(frame)), context)
+            .await
+            .is_ok()
+        {
+            self.exit_reason.get_or_insert(exit_reason);
+        }
+    }
+
+    async fn send(
+        &mut self,
+        message: Message,
+        context: WriteContext,
+    ) -> Result<(), ConnectionWriteError> {
+        let Some(commands) = self.commands.as_ref().cloned() else {
+            return Err(ConnectionWriteError::Closed);
+        };
+        self.stats.observe_command_queue(&commands);
+        let (acknowledged, acknowledgement) = oneshot::channel();
+        let started_at = Instant::now();
+        let request_id = context.request_id.clone();
+        let phase = context.phase;
+        let command = ConnectionCommand {
+            message,
+            context,
+            acknowledged,
+        };
+        let write = async move {
+            commands
+                .send(command)
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?;
+            acknowledgement
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?
+        };
+        let result = match timeout(self.config.write_timeout, write).await {
+            Ok(result) => result,
+            Err(_) => Err(ConnectionWriteError::Timeout {
+                timeout: self.config.write_timeout,
+            }),
+        };
+        let duration = started_at.elapsed();
+        match &result {
+            Ok(()) if phase.is_milestone() => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                "Responses WebSocket frame write succeeded"
+            ),
+            Ok(()) => tracing::debug!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                "Responses WebSocket frame write succeeded"
+            ),
+            Err(error) => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                error = %error,
+                "Responses WebSocket frame write failed"
+            ),
+        }
+        if let Err(error) = &result {
+            let reason = match error {
+                ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
+                ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
+                ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
+            };
+            self.terminate(reason);
+        }
+        result
+    }
+
+    fn terminate(&mut self, reason: PumpExitReason) {
+        self.exit_reason.get_or_insert(reason);
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+
+    pub(super) fn log_summary(&self, request_count: u64) {
+        tracing::info!(
+            websocket_connection_id = %self.connection_id,
+            request_count,
+            connection_age_ms = self.age().as_millis(),
+            pump_exit_reason = self
+                .exit_reason
+                .map_or("unknown", PumpExitReason::as_str),
+            command_queue_high_water = self
+                .stats
+                .command_queue_high_water
+                .load(Ordering::Relaxed),
+            command_backpressure_count = self
+                .stats
+                .command_backpressure_count
+                .load(Ordering::Relaxed),
+            ping_received_count = self.stats.ping_received_count.load(Ordering::Relaxed),
+            pong_written_count = self.stats.pong_written_count.load(Ordering::Relaxed),
+            "Responses WebSocket disconnected"
+        );
+    }
+}
+
+impl Drop for ResponsesWebSocketConnection {
+    fn drop(&mut self) {
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+}
+
+pub(super) fn spawn_connection<S, E>(
+    socket: S,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    config: ConnectionConfig,
+) -> ResponsesWebSocketConnection
+where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
+    E: fmt::Display + Send + 'static,
+{
+    let opened_at = Instant::now();
+    let expired = Arc::new(AtomicBool::new(false));
+    let stats = Arc::new(ConnectionStats::default());
+    let (command_tx, command_rx) = mpsc::channel(OUTBOUND_COMMAND_BUFFER);
+    let (incoming_tx, incoming_rx) = mpsc::channel(INBOUND_EVENT_BUFFER);
+    let pump_task = tokio::spawn(run_pump(
+        socket,
+        command_rx,
+        incoming_tx,
+        Arc::clone(&connection_id),
+        cancellation,
+        opened_at,
+        Arc::clone(&expired),
+        Arc::clone(&stats),
+        config,
+    ));
+    ResponsesWebSocketConnection {
+        connection_id,
+        opened_at,
+        expired,
+        commands: Some(command_tx),
+        incoming: incoming_rx,
+        pump_task: Some(pump_task),
+        stats,
+        config,
+        exit_reason: None,
+    }
+}
+
+#[expect(clippy::too_many_arguments)]
+async fn run_pump<S, E>(
+    mut socket: S,
+    mut commands: mpsc::Receiver<ConnectionCommand>,
+    incoming: mpsc::Sender<ConnectionEvent>,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+) where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin,
+    E: fmt::Display,
+{
+    let deadline = tokio::time::sleep_until(opened_at + config.max_age);
+    tokio::pin!(deadline);
+    let mut deadline_elapsed = false;
+    let reason = loop {
+        tokio::select! {
+            biased;
+            () = cancellation.cancelled() => break PumpExitReason::LifecycleShutdown,
+            () = &mut deadline, if !deadline_elapsed => {
+                deadline_elapsed = true;
+                expired.store(true, Ordering::Release);
+                if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Expired) {
+                    break reason;
+                }
+            }
+            command = commands.recv() => {
+                let Some(command) = command else {
+                    break PumpExitReason::CoordinatorDropped;
+                };
+                let ConnectionCommand {
+                    message,
+                    context,
+                    acknowledged,
+                } = command;
+                let closing = matches!(message, Message::Close(_));
+                let result = socket.send(message).await.map_err(|error| {
+                    let message = error.to_string();
+                    tracing::debug!(
+                        websocket_connection_id = %connection_id,
+                        request_id = context.request_id.as_deref().unwrap_or(""),
+                        frame_phase = context.phase.as_str(),
+                        error = %message,
+                        "Responses WebSocket pump transport write failed"
+                    );
+                    ConnectionWriteError::Transport { message }
+                });
+                let failed = result.is_err();
+                let _ = acknowledged.send(result);
+                if failed {
+                    break PumpExitReason::WriteError;
+                }
+                if closing {
+                    break PumpExitReason::ServerClose;
+                }
+            }
+            message = socket.next() => match message {
+                Some(Ok(Message::Text(payload))) => {
+                    if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Text(payload.to_string())) {
+                        break reason;
+                    }
+                }
+                Some(Ok(Message::Binary(_))) => {
+                    if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Binary) {
+                        break reason;
+                    }
+                }
+                Some(Ok(Message::Ping(payload))) => {
+                    stats.ping_received_count.fetch_add(1, Ordering::Relaxed);
+                    match timeout(config.write_timeout, socket.send(Message::Pong(payload))).await {
+                        Ok(Ok(())) => {
+                            stats.pong_written_count.fetch_add(1, Ordering::Relaxed);
+                        }
+                        Ok(Err(error)) => {
+                            tracing::info!(
+                                websocket_connection_id = %connection_id,
+                                error = %error,
+                                "Responses WebSocket Pong write failed"
+                            );
+                            break PumpExitReason::WriteError;
+                        }
+                        Err(_) => break PumpExitReason::WriteTimeout,
+                    }
+                }
+                Some(Ok(Message::Pong(_))) => {}
+                Some(Ok(Message::Close(_))) => break PumpExitReason::ClientClose,
+                Some(Err(error)) => {
+                    tracing::info!(
+                        websocket_connection_id = %connection_id,
+                        error = %error,
+                        "Responses WebSocket receive failed"
+                    );
+                    break PumpExitReason::ReadError;
+                }
+                None => break PumpExitReason::PeerEof,
+            },
+        }
+    };
+    let _ = incoming.try_send(ConnectionEvent::Exited(reason));
+    tracing::debug!(
+        websocket_connection_id = %connection_id,
+        pump_exit_reason = reason.as_str(),
+        "Responses WebSocket pump exited"
+    );
+}
+
+fn emit_incoming(
+    incoming: &mpsc::Sender<ConnectionEvent>,
+    event: ConnectionEvent,
+) -> Result<(), PumpExitReason> {
+    incoming.try_send(event).map_err(|error| match error {
+        mpsc::error::TrySendError::Full(_) => PumpExitReason::InboundOverload,
+        mpsc::error::TrySendError::Closed(_) => PumpExitReason::CoordinatorDropped,
+    })
+}

backend/crates/gateway-api/src/openai/responses/websocket/forward.rs

@@ -0,0 +1,482 @@
+//! 已启动 Responses execution 到客户端 WebSocket wire event 的串行转发。
+
+use std::sync::Arc;
+
+use axum::http::StatusCode;
+use gateway_core::engine::execution::StartedExecution;
+use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
+use gateway_core::error::{GatewayError, GatewayErrorKind};
+use gateway_core::operation::ProviderSessionState;
+use tokio::time::Instant;
+
+use crate::openai::error::{gateway_error_contract, gateway_error_from_engine};
+
+use super::{
+    super::{DecodedResponsesRequest, OpenAiResponsesEncoder, PendingExecution, ProtocolErrorBody},
+    connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext},
+    protocol::{error_event, response_metadata_event},
+};
+
+const ACTIVE_RESPONSE_VIOLATION: &str = "Only one response.create may be active per connection";
+
+#[derive(Clone, Copy, PartialEq, Eq)]
+pub(super) enum ForwardOutcome {
+    Continue,
+    Disconnect,
+}
+
+#[derive(Default)]
+pub(super) struct ConnectionReplaySnapshot {
+    last_response_id: Option<String>,
+    provider_state: Option<ProviderSessionState>,
+}
+
+impl ConnectionReplaySnapshot {
+    pub(super) fn prepare(&self, request: DecodedResponsesRequest) -> DecodedResponsesRequest {
+        match (
+            request.metadata().continuation().previous_response_id(),
+            self.last_response_id.as_deref(),
+            self.provider_state.as_ref(),
+        ) {
+            (Some(previous), Some(last), Some(state)) if previous == last => {
+                request.with_provider_session_state(state.clone())
+            }
+            _ => request,
+        }
+    }
+
+    fn commit(&mut self, response_id: String, provider_state: Option<ProviderSessionState>) {
+        self.last_response_id = Some(response_id);
+        self.provider_state = provider_state;
+    }
+}
+
+pub(super) async fn forward_execution(
+    connection: &mut ResponsesWebSocketConnection,
+    started: StartedExecution,
+    replay: &mut ConnectionReplaySnapshot,
+) -> ForwardOutcome {
+    let request_id = Arc::<str>::from(started.request_id.to_string());
+    let streaming = started.stream;
+    let mut execution = PendingExecution::new(started.session);
+    if !streaming {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "WebSocket execution was not initialized as a stream",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let first = loop {
+        match next_active_input(connection, &mut execution).await {
+            ActiveInput::Event(Ok(Some(event))) => break event,
+            ActiveInput::Event(Ok(None)) => {
+                let error = GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "gateway response ended before its first event",
+                );
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Event(Err(error)) => {
+                let error = gateway_error_from_engine(&error);
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Control => continue,
+            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
+            ActiveInput::ProtocolViolation => {
+                connection
+                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(&request_id))
+                    .await;
+                return ForwardOutcome::Disconnect;
+            }
+        }
+    };
+    let requirement = first.commit_requirement();
+    let mut first = first.into_provider_events();
+    if requirement != CommitRequirement::CommitBeforeDelivery {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "gateway first event did not require commit",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let mut encoder = OpenAiResponsesEncoder::new();
+    let mut provider_state = None;
+    let mut first_messages = Vec::new();
+    for event in &mut first {
+        if let Some(update) = event.take_session_update() {
+            provider_state = Some(update);
+        }
+        first_messages.extend(encoder.push_websocket(event));
+    }
+    if first_messages.is_empty() {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "gateway commit batch encoded no output",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let Some(response_session) = execution.session_mut() else {
+        return ForwardOutcome::Disconnect;
+    };
+    let response_headers = response_session.response_headers().to_vec();
+    if let Err(error) = response_session.commit_downstream(None).await {
+        let error = gateway_error_from_engine(&error);
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let mut first_frame_written = false;
+    if encoder.is_completed() {
+        if let Err(outcome) =
+            confirm_completed_execution(connection, &mut execution, &request_id).await
+        {
+            return outcome;
+        }
+        let provider_terminal_at = Instant::now();
+        commit_connection_replay(replay, &encoder, provider_state.take());
+        let writes_succeeded = send_metadata(
+            connection,
+            &request_id,
+            response_metadata_event(&request_id, &response_headers),
+        )
+        .await
+            && send_messages(
+                connection,
+                first_messages,
+                &request_id,
+                &mut first_frame_written,
+                true,
+            )
+            .await;
+        if !writes_succeeded {
+            log_terminal_write_failure(connection, &request_id, provider_terminal_at.elapsed());
+            return ForwardOutcome::Disconnect;
+        }
+        log_terminal_write_success(connection, &request_id, provider_terminal_at.elapsed());
+        execution.disarm();
+        return ForwardOutcome::Continue;
+    }
+    if !send_metadata(
+        connection,
+        &request_id,
+        response_metadata_event(&request_id, &response_headers),
+    )
+    .await
+        || !send_messages(
+            connection,
+            first_messages,
+            &request_id,
+            &mut first_frame_written,
+            encoder.has_wire_failure(),
+        )
+        .await
+    {
+        return ForwardOutcome::Disconnect;
+    }
+
+    loop {
+        match next_active_input(connection, &mut execution).await {
+            ActiveInput::Event(Ok(Some(delivery))) => {
+                let requirement = delivery.commit_requirement();
+                let mut events = delivery.into_provider_events();
+                if requirement != CommitRequirement::AlreadyCommitted {
+                    let error = GatewayError::new(
+                        GatewayErrorKind::Internal,
+                        "gateway requested another downstream commit",
+                    );
+                    return send_gateway_error(connection, &error, &request_id).await;
+                }
+                let mut messages = Vec::new();
+                for event in &mut events {
+                    if let Some(update) = event.take_session_update() {
+                        provider_state = Some(update);
+                    }
+                    messages.extend(encoder.push_websocket(event));
+                }
+                if encoder.is_completed() {
+                    if let Err(outcome) =
+                        confirm_completed_execution(connection, &mut execution, &request_id).await
+                    {
+                        return outcome;
+                    }
+                    let provider_terminal_at = Instant::now();
+                    commit_connection_replay(replay, &encoder, provider_state.take());
+                    if !send_messages(
+                        connection,
+                        messages,
+                        &request_id,
+                        &mut first_frame_written,
+                        true,
+                    )
+                    .await
+                    {
+                        log_terminal_write_failure(
+                            connection,
+                            &request_id,
+                            provider_terminal_at.elapsed(),
+                        );
+                        return ForwardOutcome::Disconnect;
+                    }
+                    log_terminal_write_success(
+                        connection,
+                        &request_id,
+                        provider_terminal_at.elapsed(),
+                    );
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let terminal_batch = encoder.has_wire_failure();
+                if !send_messages(
+                    connection,
+                    messages,
+                    &request_id,
+                    &mut first_frame_written,
+                    terminal_batch,
+                )
+                .await
+                {
+                    return ForwardOutcome::Disconnect;
+                }
+            }
+            ActiveInput::Event(Ok(None)) => {
+                if execution
+                    .session_mut()
+                    .is_some_and(|session| session.is_finalized())
+                {
+                    commit_connection_replay(replay, &encoder, provider_state.take());
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let error = GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "gateway response ended without finalizing the execution",
+                );
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Event(Err(error)) => {
+                if encoder.has_wire_failure() {
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let error = gateway_error_from_engine(&error);
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Control => {}
+            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
+            ActiveInput::ProtocolViolation => {
+                connection
+                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(&request_id))
+                    .await;
+                return ForwardOutcome::Disconnect;
+            }
+        }
+    }
+}
+
+fn commit_connection_replay(
+    replay: &mut ConnectionReplaySnapshot,
+    encoder: &OpenAiResponsesEncoder,
+    provider_state: Option<ProviderSessionState>,
+) {
+    if let Some(response_id) = encoder.response_id() {
+        replay.commit(response_id.to_owned(), provider_state);
+    }
+}
+
+async fn confirm_completed_execution(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+    request_id: &Arc<str>,
+) -> Result<(), ForwardOutcome> {
+    loop {
+        match next_active_input(connection, execution).await {
+            ActiveInput::Event(Ok(None))
+                if execution
+                    .session_mut()
+                    .is_some_and(|session| session.is_finalized()) =>
+            {
+                return Ok(());
+            }
+            ActiveInput::Event(Ok(None)) => {
+                let error = GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "gateway response was not finalized after its terminal event",
+                );
+                return Err(send_gateway_error(connection, &error, request_id).await);
+            }
+            ActiveInput::Event(Ok(Some(_))) => {
+                let error = GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "gateway response continued after its terminal event",
+                );
+                return Err(send_gateway_error(connection, &error, request_id).await);
+            }
+            ActiveInput::Event(Err(error)) => {
+                let error = gateway_error_from_engine(&error);
+                return Err(send_gateway_error(connection, &error, request_id).await);
+            }
+            ActiveInput::Control => {}
+            ActiveInput::Disconnect => return Err(ForwardOutcome::Disconnect),
+            ActiveInput::ProtocolViolation => {
+                connection
+                    .close_policy(ACTIVE_RESPONSE_VIOLATION, Some(request_id))
+                    .await;
+                return Err(ForwardOutcome::Disconnect);
+            }
+        }
+    }
+}
+
+enum ActiveInput {
+    Event(Result<Option<CoordinatedEvent>, EngineError>),
+    Control,
+    Disconnect,
+    ProtocolViolation,
+}
+
+async fn next_active_input(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+) -> ActiveInput {
+    let Some(session) = execution.session_mut() else {
+        return ActiveInput::Disconnect;
+    };
+    tokio::select! {
+        event = session.next_event() => ActiveInput::Event(event),
+        message = connection.next_event() => match message {
+            Some(ConnectionEvent::Expired) => ActiveInput::Control,
+            Some(ConnectionEvent::Text(_) | ConnectionEvent::Binary) => {
+                ActiveInput::ProtocolViolation
+            }
+            Some(ConnectionEvent::Exited(_)) | None => ActiveInput::Disconnect,
+        },
+    }
+}
+
+pub(super) async fn send_gateway_error(
+    connection: &mut ResponsesWebSocketConnection,
+    error: &GatewayError,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let (status, default_type, default_code) = gateway_error_contract(error.kind());
+    send_error(
+        connection,
+        status,
+        error.client_error_type().unwrap_or(default_type),
+        error.client_error_code().unwrap_or(default_code),
+        error.client_message(),
+        None,
+        request_id,
+    )
+    .await
+}
+
+pub(super) async fn send_protocol_error(
+    connection: &mut ResponsesWebSocketConnection,
+    status: StatusCode,
+    body: ProtocolErrorBody,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let error = body.error;
+    send_error(
+        connection,
+        status,
+        error.kind,
+        error.code,
+        &error.message,
+        error.param.as_deref(),
+        request_id,
+    )
+    .await
+}
+
+async fn send_error(
+    connection: &mut ResponsesWebSocketConnection,
+    status: StatusCode,
+    error_type: &str,
+    code: &str,
+    message: &str,
+    param: Option<&str>,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    if connection
+        .send_text(
+            error_event(status, error_type, code, message, param, Some(request_id)),
+            WriteContext::request(request_id, FramePhase::Error),
+        )
+        .await
+        .is_ok()
+    {
+        ForwardOutcome::Continue
+    } else {
+        ForwardOutcome::Disconnect
+    }
+}
+
+async fn send_metadata(
+    connection: &mut ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    message: String,
+) -> bool {
+    connection
+        .send_text(
+            message,
+            WriteContext::request(request_id, FramePhase::Metadata),
+        )
+        .await
+        .is_ok()
+}
+
+async fn send_messages(
+    connection: &mut ResponsesWebSocketConnection,
+    messages: Vec<String>,
+    request_id: &Arc<str>,
+    first_frame_written: &mut bool,
+    terminal_batch: bool,
+) -> bool {
+    let message_count = messages.len();
+    for (index, message) in messages.into_iter().enumerate() {
+        let is_terminal = terminal_batch && index + 1 == message_count;
+        let phase = match (*first_frame_written, is_terminal) {
+            (false, true) => FramePhase::FirstAndTerminal,
+            (false, false) => FramePhase::First,
+            (true, true) => FramePhase::Terminal,
+            (true, false) => FramePhase::Data,
+        };
+        if connection
+            .send_text(message, WriteContext::request(request_id, phase))
+            .await
+            .is_err()
+        {
+            return false;
+        }
+        *first_frame_written = true;
+    }
+    true
+}
+
+fn log_terminal_write_success(
+    connection: &ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    provider_terminal_to_write: std::time::Duration,
+) {
+    tracing::info!(
+        websocket_connection_id = connection.id(),
+        request_id = %request_id,
+        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
+        terminal_frame_written = true,
+        "Provider execution terminal was written to the WebSocket transport"
+    );
+}
+
+fn log_terminal_write_failure(
+    connection: &ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    provider_terminal_to_write: std::time::Duration,
+) {
+    tracing::info!(
+        websocket_connection_id = connection.id(),
+        request_id = %request_id,
+        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
+        provider_succeeded_but_terminal_write_failed = true,
+        "Provider execution succeeded before the terminal WebSocket frame write failed"
+    );
+}

backend/crates/gateway-api/src/openai/responses/websocket/mod.rs

@@ -0,0 +1,248 @@
+//! OpenAI Responses WebSocket 的升级、连接与串行 session 编排。
+
+mod connection;
+mod forward;
+mod protocol;
+
+use std::{
+    net::{IpAddr, SocketAddr},
+    sync::Arc,
+};
+
+use axum::{
+    extract::{
+        Extension, State,
+        connect_info::ConnectInfo,
+        ws::{WebSocket, WebSocketUpgrade},
+    },
+    http::{HeaderMap, StatusCode},
+    response::{IntoResponse, Response},
+};
+use gateway_core::{
+    engine::execution::{AuthenticatedClient, ClientTransport},
+    lifecycle::{ConnectionGuard, ConnectionLifecycle},
+};
+
+use crate::{
+    ApiState,
+    openai::{
+        auth::{authenticate_client, authentication_error_response},
+        error::runtime_unavailable_response,
+        service::OpenAiService,
+    },
+};
+
+use super::{http::request_client_context, request::OpenAiRequestHeaders};
+use connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext};
+use forward::{
+    ConnectionReplaySnapshot, ForwardOutcome, forward_execution, send_gateway_error,
+    send_protocol_error,
+};
+use protocol::connection_limit_event;
+pub use protocol::{ResponseCreateFrameError, decode_response_create_with_context};
+
+const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
+const CONNECTION_LIMIT_CLOSE_REASON: &str = "Responses websocket connection limit reached";
+
+/// 将已认证的 `GET /v1/responses` 升级为 Responses WebSocket。
+pub(crate) async fn responses_websocket(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    websocket: WebSocketUpgrade,
+) -> Response {
+    let service = state.openai().clone();
+    let client = match authenticate_client(&service, &headers) {
+        Ok(client) => client,
+        Err(error) => return authentication_error_response(error),
+    };
+    let (client_ip, user_agent) = request_client_context(
+        &headers,
+        connect_info.map(|Extension(ConnectInfo(address))| address),
+    );
+    ResponsesWebSocketAdapter::new(service).upgrade_with_client_context(
+        websocket,
+        client,
+        client_ip,
+        user_agent,
+        OpenAiRequestHeaders::from_headers(&headers),
+    )
+}
+
+/// 已鉴权 Responses WebSocket 升级边界。
+#[derive(Clone)]
+pub(crate) struct ResponsesWebSocketAdapter {
+    service: OpenAiService,
+}
+
+impl ResponsesWebSocketAdapter {
+    /// 绑定应用提供的唯一 OpenAI 客户端服务端口。
+    #[must_use]
+    pub const fn new(service: OpenAiService) -> Self {
+        Self { service }
+    }
+
+    fn upgrade_with_client_context(
+        &self,
+        websocket: WebSocketUpgrade,
+        client: AuthenticatedClient,
+        client_ip: Option<IpAddr>,
+        user_agent: Option<String>,
+        request_headers: OpenAiRequestHeaders,
+    ) -> Response {
+        let connection_guard = match self.service.try_register_connection() {
+            Ok(guard) => guard,
+            Err(_) => return runtime_unavailable_response().into_response(),
+        };
+        let session = ResponsesWebSocketSession {
+            service: self.service.clone(),
+            client,
+            connection_id: self.service.next_request_id().replacen("req_", "ws_", 1),
+            client_ip,
+            user_agent,
+            request_headers,
+            lifecycle: self.service.lifecycle(),
+            connection_guard,
+        };
+        websocket
+            // 覆盖 axum/tungstenite 的私有 64 MiB message 与 16 MiB frame 默认值。
+            // Responses JSON 的协议可接受性由上游决定，代理不另设 wire 长度上限。
+            .max_message_size(usize::MAX)
+            .max_frame_size(usize::MAX)
+            .on_upgrade(move |socket| async move {
+                serve_responses_websocket(socket, session).await;
+            })
+    }
+}
+
+struct ResponsesWebSocketSession {
+    service: OpenAiService,
+    client: AuthenticatedClient,
+    connection_id: String,
+    client_ip: Option<IpAddr>,
+    user_agent: Option<String>,
+    request_headers: OpenAiRequestHeaders,
+    lifecycle: Arc<dyn ConnectionLifecycle>,
+    connection_guard: Box<dyn ConnectionGuard>,
+}
+
+async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocketSession) {
+    let ResponsesWebSocketSession {
+        service,
+        client,
+        connection_id,
+        client_ip,
+        user_agent,
+        request_headers,
+        lifecycle,
+        connection_guard,
+    } = session;
+    tracing::info!(
+        websocket_connection_id = %connection_id,
+        "Responses WebSocket connected"
+    );
+    let _connection_guard = connection_guard;
+    let cancellation = lifecycle.cancellation();
+    let mut connection = ResponsesWebSocketConnection::new(socket, connection_id, cancellation);
+    let mut request_count = 0_u64;
+    let mut replay = ConnectionReplaySnapshot::default();
+
+    loop {
+        let Some(event) = connection.next_event().await else {
+            break;
+        };
+        let payload = match event {
+            ConnectionEvent::Text(payload) => payload,
+            ConnectionEvent::Binary => {
+                connection.close_policy(TEXT_FRAMES_ONLY, None).await;
+                break;
+            }
+            ConnectionEvent::Expired => {
+                expire_connection(&mut connection).await;
+                break;
+            }
+            ConnectionEvent::Exited(_) => break,
+        };
+        if connection.is_expired() {
+            expire_connection(&mut connection).await;
+            break;
+        }
+        request_count = request_count.saturating_add(1);
+        let correlation_id = Arc::<str>::from(service.next_request_id());
+        let decoded = match decode_response_create_with_context(&payload, &request_headers) {
+            Ok(decoded) => decoded.with_client_context(client_ip, user_agent.clone()),
+            Err(error) => {
+                tracing::info!(
+                    websocket_connection_id = connection.id(),
+                    request_id = %correlation_id,
+                    error = %error,
+                    "Responses WebSocket request rejected"
+                );
+                if send_protocol_error(
+                    &mut connection,
+                    StatusCode::BAD_REQUEST,
+                    error.protocol_body(),
+                    &correlation_id,
+                )
+                .await
+                    == ForwardOutcome::Disconnect
+                {
+                    break;
+                }
+                continue;
+            }
+        };
+        let decoded = replay.prepare(decoded);
+        // deadline 与 Text 可能同时就绪；在任何上游执行开始前再次封住该竞争窗口。
+        if connection.is_expired() {
+            expire_connection(&mut connection).await;
+            break;
+        }
+        let started = match service
+            .start_response(
+                client.clone(),
+                decoded,
+                ClientTransport::WebSocket,
+                "/v1/responses",
+            )
+            .await
+        {
+            Ok(started) => started,
+            Err(error) => {
+                if send_gateway_error(&mut connection, &error, &correlation_id).await
+                    == ForwardOutcome::Disconnect
+                {
+                    break;
+                }
+                continue;
+            }
+        };
+
+        if forward_execution(&mut connection, started, &mut replay).await
+            == ForwardOutcome::Disconnect
+        {
+            break;
+        }
+        if connection.is_expired() {
+            expire_connection(&mut connection).await;
+            break;
+        }
+    }
+
+    connection.log_summary(request_count);
+}
+
+async fn expire_connection(connection: &mut ResponsesWebSocketConnection) {
+    if connection
+        .send_text(
+            connection_limit_event(),
+            WriteContext::connection(FramePhase::ConnectionLimit),
+        )
+        .await
+        .is_ok()
+    {
+        connection
+            .close_for_connection_limit(CONNECTION_LIMIT_CLOSE_REASON)
+            .await;
+    }
+}

backend/crates/gateway-api/src/openai/responses/websocket/protocol.rs

@@ -0,0 +1,151 @@
+//! Responses WebSocket 入站请求与下行事件的纯协议映射。
+
+use axum::http::{HeaderName, StatusCode};
+use gateway_core::event::ProviderResponseHeader;
+use serde_json::{Map, Value, json};
+use thiserror::Error;
+
+use super::super::{
+    DecodedResponsesRequest, ProtocolErrorBody, RequestDecodeError, request::OpenAiRequestHeaders,
+};
+
+/// 使用连接级请求头和 Provider 上下文解码官方 `response.create` 文本帧。
+///
+/// 缺省 `stream` 等价于 WebSocket 固有的流式语义；显式 `false` 会被拒绝。
+///
+/// # Errors
+///
+/// 帧不是合法 JSON object、消息类型错误、显式关闭 stream，或 Responses 请求
+/// 无法映射到 canonical operation 时返回不包含正文内容的稳定错误。
+pub fn decode_response_create_with_context(
+    payload: &str,
+    request_headers: &OpenAiRequestHeaders,
+) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
+    decode_response_create_inner(payload, request_headers)
+}
+
+fn decode_response_create_inner(
+    payload: &str,
+    request_headers: &OpenAiRequestHeaders,
+) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
+    let Value::Object(mut body) = serde_json::from_str::<Value>(payload)
+        .map_err(|_| ResponseCreateFrameError::InvalidJson)?
+    else {
+        return Err(ResponseCreateFrameError::ExpectedObject);
+    };
+    match body.remove("type") {
+        Some(Value::String(message_type)) if message_type == "response.create" => {}
+        _ => return Err(ResponseCreateFrameError::UnsupportedType),
+    }
+    if matches!(body.get("stream"), Some(value) if value.as_bool() != Some(true)) {
+        return Err(ResponseCreateFrameError::StreamingRequired);
+    }
+    super::super::request::decode_request_object(body, false, request_headers)
+        .map_err(ResponseCreateFrameError::Request)
+}
+
+/// `response.create` 帧的稳定安全错误。
+#[derive(Debug, Clone, PartialEq, Eq, Error)]
+pub enum ResponseCreateFrameError {
+    /// 文本不是合法 JSON。
+    #[error("response.create frame must be valid JSON")]
+    InvalidJson,
+    /// 顶层不是 object。
+    #[error("response.create frame must be a JSON object")]
+    ExpectedObject,
+    /// `type` 缺失或不是 `response.create`。
+    #[error("unsupported Responses WebSocket message type")]
+    UnsupportedType,
+    /// WebSocket 请求显式声明 `stream=false`。
+    #[error("Responses WebSocket requests require stream=true")]
+    StreamingRequired,
+    /// 内层 Responses 请求无法映射到 canonical operation。
+    #[error(transparent)]
+    Request(RequestDecodeError),
+}
+
+impl ResponseCreateFrameError {
+    pub(super) fn protocol_body(&self) -> ProtocolErrorBody {
+        match self {
+            Self::Request(error) => error.protocol_body(),
+            Self::InvalidJson => RequestDecodeError::MalformedJson.protocol_body(),
+            Self::ExpectedObject => RequestDecodeError::ExpectedObject.protocol_body(),
+            Self::UnsupportedType => RequestDecodeError::InvalidValue {
+                field: "type".to_owned(),
+            }
+            .protocol_body(),
+            Self::StreamingRequired => RequestDecodeError::InvalidValue {
+                field: "stream".to_owned(),
+            }
+            .protocol_body(),
+        }
+    }
+}
+
+pub(super) fn response_metadata_event(
+    request_id: &str,
+    response_headers: &[ProviderResponseHeader],
+) -> String {
+    let connection_options = super::super::response_connection_options(response_headers);
+    let mut headers = Map::new();
+    for header in response_headers {
+        if !super::super::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = std::str::from_utf8(header.value()) else {
+            continue;
+        };
+        // 官方 response.metadata 使用 string map，无法表达同名多值；后值保持既有覆盖语义。
+        headers.insert(name.as_str().to_owned(), Value::String(value.to_owned()));
+    }
+    headers
+        .entry("x-request-id".to_owned())
+        .or_insert_with(|| Value::String(request_id.to_owned()));
+    json!({
+        "type": "response.metadata",
+        "headers": headers,
+    })
+    .to_string()
+}
+
+pub(super) fn error_event(
+    status: StatusCode,
+    error_type: &str,
+    code: &str,
+    message: &str,
+    param: Option<&str>,
+    request_id: Option<&str>,
+) -> String {
+    let mut error = Map::new();
+    error.insert("type".to_owned(), Value::String(error_type.to_owned()));
+    error.insert("code".to_owned(), Value::String(code.to_owned()));
+    error.insert("message".to_owned(), Value::String(message.to_owned()));
+    if let Some(param) = param {
+        error.insert("param".to_owned(), Value::String(param.to_owned()));
+    }
+    let mut event = Map::new();
+    event.insert("type".to_owned(), Value::String("error".to_owned()));
+    event.insert("status".to_owned(), Value::Number(status.as_u16().into()));
+    event.insert("error".to_owned(), Value::Object(error));
+    if let Some(request_id) = request_id {
+        event.insert(
+            "request_id".to_owned(),
+            Value::String(request_id.to_owned()),
+        );
+    }
+    Value::Object(event).to_string()
+}
+
+pub(super) fn connection_limit_event() -> String {
+    error_event(
+        StatusCode::BAD_REQUEST,
+        "invalid_request_error",
+        "websocket_connection_limit_reached",
+        "Responses websocket connection limit reached (60 minutes). Create a new websocket connection to continue.",
+        None,
+        None,
+    )
+}

backend/crates/gateway-api/src/openai/router.rs

@@ -7,18 +7,18 @@ use axum::{
 };
 
 use super::{
+    images::{image_edits, image_generations},
     models::{model_catalog, model_detail, model_info, models},
     responses::{responses, responses_websocket, review_responses},
 };
 
 use crate::ApiState;
 
-/// OpenAI 请求正文上限。
-pub const MAX_CLIENT_REQUEST_BODY_BYTES: usize = 16 * 1024 * 1024;
-
 /// 构造 OpenAI 客户端协议路由。
 pub(crate) fn router() -> Router<ApiState> {
     Router::new()
+        .route("/v1/images/generations", post(image_generations))
+        .route("/v1/images/edits", post(image_edits))
         .route("/v1/responses", get(responses_websocket).post(responses))
         .route("/v1/responses/review", post(review_responses))
         .route("/v1/models", get(models))
@@ -26,5 +26,7 @@ pub(crate) fn router() -> Router<ApiState> {
         .route("/v1/models/{model_id}/info", get(model_info))
         // 官方 OpenAI 模型详情合同使用 path ID；它不属于 Admin API 约束。
         .route("/v1/models/{model_id}", get(model_detail))
-        .layer(DefaultBodyLimit::max(MAX_CLIENT_REQUEST_BODY_BYTES))
+        // OpenAI 数据面正文属于客户端/上游协议；代理不能用私有大小上限提前拒绝
+        // 上游本可接受的未来 payload。
+        .layer(DefaultBodyLimit::disable())
 }

backend/crates/gateway-api/src/openai/service.rs

@@ -1,15 +1,16 @@
 //! OpenAI wire adapter 到 Core 执行用例的唯一映射。
 
+use std::net::IpAddr;
 use std::sync::Arc;
 
 use gateway_core::engine::continuation::PreviousResponseId;
 use gateway_core::engine::execution::{
     AuthenticatedClient, ClientAuthenticationError, ClientTransport, ExecutionRequestMetadata,
-    ExecutionService, StartExecution, StartedExecution,
+    ExecutionService, StartExecution, StartProviderExecution, StartedExecution,
 };
 use gateway_core::error::{GatewayError, GatewayErrorKind};
 use gateway_core::lifecycle::{ConnectionDraining, ConnectionGuard, ConnectionLifecycle};
-use gateway_core::routing::PublicModelId;
+use gateway_core::routing::{PublicModelId, PublicModelProfile};
 use uuid::Uuid;
 
 use super::auth::ClientApiKeyAuthError;
@@ -51,6 +52,13 @@ impl OpenAiService {
             .collect()
     }
 
+    pub(crate) fn public_model_profiles(
+        &self,
+        client: &AuthenticatedClient,
+    ) -> Vec<PublicModelProfile> {
+        self.execution.public_model_profiles(client)
+    }
+
     pub(crate) fn contains_public_model(
         &self,
         client: &AuthenticatedClient,
@@ -67,23 +75,17 @@ impl OpenAiService {
         endpoint: &'static str,
     ) -> Result<StartedExecution, GatewayError> {
         let (operation, metadata) = request.into_parts();
-        let public_model = PublicModelId::from_client_wire(metadata.public_model().to_owned())
+        let public_model = PublicModelId::from_client_wire(metadata.requested_model().to_owned())
             .map_err(|_| {
-                GatewayError::new(
-                    GatewayErrorKind::ModelNotFound,
-                    "requested model was not found",
-                )
-            })?;
-        if !self.execution.contains_public_model(&client, &public_model) {
-            return Err(GatewayError::new(
+            GatewayError::new(
                 GatewayErrorKind::ModelNotFound,
                 "requested model was not found",
-            ));
-        }
+            )
+        })?;
         let previous_response_id = match metadata.continuation() {
             ContinuationIntent::None => None,
             ContinuationIntent::PreviousResponseId(value) => {
-                PreviousResponseId::new(value.clone()).ok()
+                Some(PreviousResponseId::new(value.clone()))
             }
         };
         self.execution
@@ -104,6 +106,38 @@ impl OpenAiService {
             .await
     }
 
+    pub(crate) async fn start_image(
+        &self,
+        client: AuthenticatedClient,
+        operation: gateway_core::operation::Operation,
+        client_ip: Option<IpAddr>,
+        user_agent: Option<String>,
+        endpoint: &'static str,
+    ) -> Result<StartedExecution, GatewayError> {
+        let provider = gateway_core::routing::ProviderKind::new("openai").map_err(|_| {
+            GatewayError::new(
+                GatewayErrorKind::Internal,
+                "OpenAI provider identifier is invalid",
+            )
+        })?;
+        self.execution
+            .start_provider_endpoint(StartProviderExecution {
+                client,
+                provider,
+                operation,
+                metadata: ExecutionRequestMetadata {
+                    protocol: "openai".to_owned(),
+                    endpoint: endpoint.to_owned(),
+                    transport: ClientTransport::HttpJson,
+                    stream: false,
+                    client_ip,
+                    user_agent,
+                    previous_response_id: None,
+                },
+            })
+            .await
+    }
+
     pub(crate) fn try_register_connection(
         &self,
     ) -> Result<Box<dyn ConnectionGuard>, ConnectionDraining> {

backend/crates/gateway-api/tests/admin/account_groups.rs

@@ -0,0 +1,274 @@
+use axum::{
+    Router,
+    body::{Body, to_bytes},
+    http::{Method, Request, StatusCode, header},
+};
+use gateway_api::admin::account_groups;
+use serde_json::{Value, json};
+use tower::ServiceExt as _;
+
+use super::{AdminTestFixture, AdminTestState, PRIMARY_GROUP_ID};
+
+const SESSION_COOKIE: &str = "cpr_admin_session=valid-session";
+
+#[tokio::test]
+async fn list_route_should_keep_camel_case_group_and_page_wire() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::GET,
+        "/api/admin/account-groups?page=1&pageSize=1&search=alpha&enabled=true",
+        None,
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::OK);
+    let value = response_json(response).await;
+    assert_eq!(value["data"]["page"]["page"], 1);
+    assert_eq!(value["data"]["page"]["pageSize"], 1);
+    assert_eq!(value["data"]["page"]["total"], 1);
+    assert_eq!(value["data"]["page"]["totalPages"], 1);
+    assert_eq!(value["data"]["configRevision"], 7);
+    assert_eq!(value["data"]["items"][0]["id"], PRIMARY_GROUP_ID);
+    assert_eq!(value["data"]["items"][0]["memberCount"], 2);
+    assert_eq!(value["data"]["items"][0]["providerCounts"]["openai"], 1);
+    assert_eq!(value["data"]["items"][0]["clientKeyCount"], 2);
+    assert_eq!(value["data"]["items"][0]["accountSummary"]["available"], 1);
+    assert_eq!(value["data"]["items"][0]["accountSummary"]["limited"], 1);
+    assert_eq!(value["data"]["items"][0]["accountSummary"]["total"], 2);
+    assert_eq!(value["data"]["items"][0]["capacity"]["usedSlots"], 0);
+    assert_eq!(value["data"]["items"][0]["capacity"]["totalSlots"], 1);
+    assert_eq!(value["data"]["items"][0]["usage"]["todayUsd"], "1.25");
+    assert_eq!(
+        value["data"]["items"][0]["usage"]["retainedTotalUsd"],
+        "5.5"
+    );
+    assert!(value["data"]["items"][0].get("member_count").is_none());
+}
+
+#[tokio::test]
+async fn create_route_should_create_an_empty_group() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/create",
+        Some(json!({
+            "name": "Gamma routing",
+            "description": "New traffic pool",
+            "color": "#a855f780"
+        })),
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::CREATED);
+    let value = response_json(response).await;
+    assert!(
+        value["data"]["id"]
+            .as_str()
+            .is_some_and(|id| id.starts_with("grp_") && id.len() == 36)
+    );
+    assert_eq!(value["data"]["record"]["name"], "Gamma routing");
+    assert_eq!(value["data"]["record"]["memberCount"], 0);
+    assert_eq!(value["data"]["record"]["color"], "#A855F780");
+    assert_eq!(value["data"]["configRevision"], 8);
+}
+
+#[tokio::test]
+async fn update_route_should_replace_group_fields() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/update",
+        Some(json!({
+            "id": PRIMARY_GROUP_ID,
+            "name": "Renamed routing",
+            "description": null,
+            "color": "#F43F5ECC"
+        })),
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::OK);
+    let value = response_json(response).await;
+    assert_eq!(value["data"]["record"]["name"], "Renamed routing");
+    assert!(value["data"]["record"]["description"].is_null());
+    assert_eq!(value["data"]["record"]["color"], "#F43F5ECC");
+}
+
+#[tokio::test]
+async fn enable_and_disable_routes_should_set_explicit_group_state() {
+    let fixture = authenticated_fixture().await;
+    let disabled = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/disable",
+        Some(json!({ "id": PRIMARY_GROUP_ID })),
+        true,
+    )
+    .await;
+    let enabled = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/enable",
+        Some(json!({ "id": PRIMARY_GROUP_ID })),
+        true,
+    )
+    .await;
+
+    assert_eq!(disabled.status(), StatusCode::OK);
+    assert!(
+        !response_json(disabled).await["data"]["record"]["enabled"]
+            .as_bool()
+            .expect("disabled flag")
+    );
+    assert_eq!(enabled.status(), StatusCode::OK);
+    assert!(
+        response_json(enabled).await["data"]["record"]["enabled"]
+            .as_bool()
+            .expect("enabled flag")
+    );
+}
+
+#[tokio::test]
+async fn delete_route_should_return_deleted_id_without_a_live_record() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/delete",
+        Some(json!({ "id": PRIMARY_GROUP_ID })),
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::OK);
+    let value = response_json(response).await;
+    assert_eq!(value["data"]["id"], PRIMARY_GROUP_ID);
+    assert!(value["data"]["record"].is_null());
+}
+
+#[tokio::test]
+async fn list_route_should_reject_unknown_and_invalid_pagination_fields() {
+    let fixture = authenticated_fixture().await;
+    for uri in [
+        "/api/admin/account-groups?other=true",
+        "/api/admin/account-groups?page=0",
+        "/api/admin/account-groups?pageSize=0",
+        "/api/admin/account-groups?pageSize=201",
+    ] {
+        let response = request(router(&fixture), Method::GET, uri, None, true).await;
+        assert_eq!(response.status(), StatusCode::BAD_REQUEST, "{uri}");
+    }
+}
+
+#[tokio::test]
+async fn mutation_route_should_reject_unknown_json_fields() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/create",
+        Some(json!({
+            "name": "Unknown field",
+            "description": null,
+            "color": "#2563EBFF",
+            "providerKind": "openai"
+        })),
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::UNPROCESSABLE_ENTITY);
+}
+
+#[tokio::test]
+async fn create_route_should_reject_six_digit_color_without_alpha() {
+    let fixture = authenticated_fixture().await;
+    let response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/create",
+        Some(json!({
+            "name": "Opaque legacy color",
+            "description": null,
+            "color": "#2563EB"
+        })),
+        true,
+    )
+    .await;
+
+    assert_eq!(response.status(), StatusCode::BAD_REQUEST);
+}
+
+#[tokio::test]
+async fn account_group_routes_should_require_admin_authentication() {
+    let fixture = AdminTestFixture::new().await;
+    let get_response = request(
+        router(&fixture),
+        Method::GET,
+        "/api/admin/account-groups",
+        None,
+        false,
+    )
+    .await;
+    let post_response = request(
+        router(&fixture),
+        Method::POST,
+        "/api/admin/account-groups/create",
+        Some(json!({ "name": "Unauthorized", "description": null, "color": "#2563EBFF" })),
+        false,
+    )
+    .await;
+
+    assert_eq!(get_response.status(), StatusCode::UNAUTHORIZED);
+    assert_eq!(post_response.status(), StatusCode::UNAUTHORIZED);
+}
+
+async fn authenticated_fixture() -> AdminTestFixture {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    fixture
+}
+
+fn router(fixture: &AdminTestFixture) -> Router {
+    account_groups::router::<AdminTestState>().with_state(fixture.state())
+}
+
+async fn request(
+    router: Router,
+    method: Method,
+    uri: &str,
+    body: Option<Value>,
+    authenticated: bool,
+) -> axum::response::Response {
+    let mut builder = Request::builder()
+        .method(method)
+        .uri(uri)
+        .header("x-request-id", "req_account_groups");
+    if authenticated {
+        builder = builder.header(header::COOKIE, SESSION_COOKIE);
+    }
+    let body = match body {
+        Some(value) => {
+            builder = builder.header(header::CONTENT_TYPE, "application/json");
+            Body::from(serde_json::to_vec(&value).expect("serialize request body"))
+        }
+        None => Body::empty(),
+    };
+    router
+        .oneshot(builder.body(body).expect("account group request"))
+        .await
+        .expect("account group response")
+}
+
+async fn response_json(response: axum::response::Response) -> Value {
+    let body = to_bytes(response.into_body(), 64 * 1024)
+        .await
+        .expect("account group response body");
+    serde_json::from_slice(&body).expect("account group response JSON")
+}

backend/crates/gateway-api/tests/admin/accounts.rs

@@ -10,7 +10,7 @@ mod query {
             "pageSize": 20,
             "provider": "xai",
             "search": "  operator  ",
-            "status": "active",
+            "status": "normal",
             "sortBy": "lastUsedAt",
             "sortDirection": "desc"
         }))
@@ -23,7 +23,7 @@ mod query {
             Some(ref provider) if provider.as_str() == "xai"
         ));
         assert_eq!(query.search.as_deref(), Some("operator"));
-        assert_eq!(query.status, Some(AccountStatus::Active));
+        assert_eq!(query.status, Some(AccountStatus::Normal));
         assert_eq!(
             query.sort.expect("sort").field,
             AccountSortField::LastUsedAt
@@ -34,6 +34,19 @@ mod query {
         );
     }
 
+    #[test]
+    fn account_query_should_parse_rate_limited_status() {
+        let query: ListQuery = serde_json::from_value(json!({
+            "status": "rate_limited"
+        }))
+        .expect("deserialize account query");
+
+        assert_eq!(
+            query.validate().expect("validate account query").status,
+            Some(AccountStatus::RateLimited)
+        );
+    }
+
     #[test]
     fn account_query_should_reject_unbounded_page_size() {
         let query: ListQuery =
@@ -57,8 +70,272 @@ mod query {
     }
 }
 
+mod profile_statistics {
+    use chrono::NaiveDate;
+    use gateway_admin::model::provider_credentials::{
+        ProviderProfileActivityInsights, ProviderProfileDailyUsage, ProviderProfileInvocation,
+        ProviderProfileStatistics, ProviderProfileStatisticsSummary,
+    };
+    use gateway_api::admin::accounts::{AccountProfileAvatarQuery, AccountProfileStatisticsData};
+    use serde_json::json;
+
+    #[test]
+    fn profile_statistics_response_preserves_nullable_official_fields() {
+        let response = AccountProfileStatisticsData::from(ProviderProfileStatistics {
+            display_name: Some("Ada".to_owned()),
+            username: Some("ada".to_owned()),
+            image_url: Some("https://example.test/avatar.png".to_owned()),
+            has_stats_error: false,
+            summary: ProviderProfileStatisticsSummary {
+                total_text_tokens: Some(409_500_000),
+                peak_tokens: Some(267_000_000),
+                longest_task_duration_ms: Some(51_900_000),
+                current_streak_days: Some(16),
+                longest_streak_days: Some(32),
+            },
+            daily_usage: Some(vec![ProviderProfileDailyUsage {
+                date: NaiveDate::from_ymd_opt(2026, 8, 25).expect("usage date"),
+                tokens: 42,
+            }]),
+            activity_insights: ProviderProfileActivityInsights {
+                fast_mode_percent: Some(0.0),
+                reasoning_effort: Some("high".to_owned()),
+                reasoning_effort_percent: Some(48.0),
+                skills_explored: Some(8),
+                total_skills_used: Some(61),
+                total_threads: Some(2_391),
+                invocations: Some(vec![ProviderProfileInvocation {
+                    invocation_type: "plugin".to_owned(),
+                    plugin_id: Some("plugin_1".to_owned()),
+                    plugin_name: Some("example".to_owned()),
+                    skill_id: None,
+                    skill_name: None,
+                    usage_count: Some(29),
+                }]),
+            },
+        });
+        let value = serde_json::to_value(response).expect("serialize profile statistics");
+
+        assert_eq!(value["displayName"], "Ada");
+        assert_eq!(value["summary"]["totalTextTokens"], 409_500_000);
+        assert_eq!(
+            value["dailyUsage"][0],
+            json!({"date": "2026-08-25", "tokens": 42})
+        );
+        assert_eq!(
+            value["activityInsights"]["invocations"][0]["type"],
+            "plugin"
+        );
+        assert_eq!(
+            value["activityInsights"]["invocations"][0]["usageCount"],
+            29
+        );
+        assert!(value.get("cycle").is_none());
+        assert!(value.get("models").is_none());
+        assert!(value.get("estimatedCost").is_none());
+    }
+
+    #[test]
+    fn profile_avatar_query_accepts_only_bounded_cache_versions() {
+        let valid: AccountProfileAvatarQuery = serde_json::from_value(json!({
+            "accountId": "acct_openai",
+            "version": "k9m2z1"
+        }))
+        .expect("decode avatar query");
+        valid.validate().expect("validate avatar query");
+
+        for version in ["", "contains-dash", "x23456789012345678901234567890123"] {
+            let query: AccountProfileAvatarQuery = serde_json::from_value(json!({
+                "accountId": "acct_openai",
+                "version": version
+            }))
+            .expect("decode invalid avatar query");
+            assert_eq!(
+                query.validate().expect_err("reject version").field(),
+                "version"
+            );
+        }
+        assert!(
+            serde_json::from_value::<AccountProfileAvatarQuery>(json!({
+                "accountId": "acct_openai",
+                "sourceUrl": "https://example.test/avatar"
+            }))
+            .is_err()
+        );
+    }
+}
+
+mod profile_avatar {
+    use axum::body::to_bytes;
+    use bytes::Bytes;
+    use futures::stream;
+    use gateway_admin::model::provider_credentials::ProviderProfileAvatar;
+    use gateway_api::admin::accounts::profile_avatar_response;
+
+    #[tokio::test]
+    async fn profile_avatar_response_preserves_stream_metadata_and_private_cache() {
+        let response = profile_avatar_response(ProviderProfileAvatar {
+            content_type: Some("image/svg+xml".to_owned()),
+            content_length: Some(6),
+            etag: Some("\"v1\"".to_owned()),
+            body: Box::pin(stream::iter([Ok(Bytes::from_static(b"avatar"))])),
+        });
+
+        assert_eq!(response.status(), 200);
+        assert_eq!(response.headers()["content-type"], "image/svg+xml");
+        assert_eq!(response.headers()["content-length"], "6");
+        assert_eq!(response.headers()["etag"], "\"v1\"");
+        assert_eq!(response.headers()["cache-control"], "private, max-age=3600");
+        assert_eq!(response.headers()["x-content-type-options"], "nosniff");
+        assert_eq!(
+            response.headers()["cross-origin-resource-policy"],
+            "same-origin"
+        );
+        assert_eq!(
+            response.headers()["content-security-policy"],
+            "sandbox; default-src 'none'"
+        );
+        assert_eq!(
+            to_bytes(response.into_body(), 16)
+                .await
+                .expect("avatar response body"),
+            Bytes::from_static(b"avatar")
+        );
+    }
+}
+
+mod batch_update {
+    use gateway_api::admin::accounts::{BatchUpdateAccountsRequest, UpdateAccountRequest};
+    use serde_json::json;
+
+    #[test]
+    fn batch_update_should_accept_complete_atomic_payload() {
+        let request: BatchUpdateAccountsRequest = serde_json::from_value(json!({
+            "accountIds": ["acct_openai", "acct_xai"],
+            "enabled": false,
+            "concurrencyLimit": null,
+            "weight": 1,
+            "groupIds": ["grp_00000000000000000000000000000001"]
+        }))
+        .expect("deserialize batch update");
+
+        request.validate().expect("validate batch update");
+    }
+
+    #[test]
+    fn batch_update_should_reject_duplicate_or_invalid_account_ids() {
+        for account_ids in [
+            json!(["acct_same", "acct_same"]),
+            json!(["not-an-account"]),
+            json!([]),
+        ] {
+            let request: BatchUpdateAccountsRequest = serde_json::from_value(json!({
+                "accountIds": account_ids,
+                "enabled": true,
+                "concurrencyLimit": 8,
+                "weight": 100,
+                "groupIds": []
+            }))
+            .expect("deserialize invalid batch update");
+            assert_eq!(
+                request.validate().expect_err("reject account IDs").field(),
+                "accountIds"
+            );
+        }
+    }
+
+    #[test]
+    fn batch_update_should_require_enabled_and_reject_unknown_fields() {
+        assert!(
+            serde_json::from_value::<BatchUpdateAccountsRequest>(json!({
+            "accountIds": ["acct_test"],
+            "concurrencyLimit": null,
+            "weight": 1,
+            "groupIds": []
+            }))
+            .is_err()
+        );
+        assert!(
+            serde_json::from_value::<BatchUpdateAccountsRequest>(json!({
+                "accountIds": ["acct_test"],
+                "enabled": true,
+                "concurrencyLimit": null,
+                "weight": 1,
+                "groupIds": [],
+                "legacy": true
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn batch_update_should_reject_invalid_scheduling_bounds_and_missing_fields() {
+        for (concurrency_limit, weight, field) in [
+            (json!(0), json!(1), "concurrencyLimit"),
+            (json!(4294967296_u64), json!(1), "concurrencyLimit"),
+            (json!(null), json!(0), "weight"),
+            (json!(null), json!(101), "weight"),
+        ] {
+            let request: BatchUpdateAccountsRequest = serde_json::from_value(json!({
+                "accountIds": ["acct_test"],
+                "enabled": true,
+                "concurrencyLimit": concurrency_limit,
+                "weight": weight,
+                "groupIds": []
+            }))
+            .expect("deserialize invalid scheduling");
+            assert_eq!(
+                request.validate().expect_err("reject scheduling").field(),
+                field
+            );
+        }
+        assert!(
+            serde_json::from_value::<BatchUpdateAccountsRequest>(json!({
+                "accountIds": ["acct_test"],
+                "enabled": true,
+                "weight": 1,
+                "groupIds": []
+            }))
+            .is_err()
+        );
+        assert!(
+            serde_json::from_value::<BatchUpdateAccountsRequest>(json!({
+                "accountIds": ["acct_test"],
+                "enabled": true,
+                "concurrencyLimit": null,
+                "groupIds": []
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn single_update_should_require_the_same_complete_scheduling_contract() {
+        let request: UpdateAccountRequest = serde_json::from_value(json!({
+            "accountId": "acct_test",
+            "enabled": true,
+            "concurrencyLimit": 4294967295_u64,
+            "weight": 100,
+            "groupIds": []
+        }))
+        .expect("deserialize single update");
+        request.validate().expect("validate single update");
+
+        assert!(
+            serde_json::from_value::<UpdateAccountRequest>(json!({
+                "accountId": "acct_test",
+                "enabled": true,
+                "weight": 1,
+                "groupIds": []
+            }))
+            .is_err()
+        );
+    }
+}
+
 mod response {
     use gateway_api::admin::accounts::AccountUsageView;
+    use gateway_api::admin::presenter::format_decimal_currency;
 
     #[test]
     fn account_usage_view_should_keep_unobserved_numbers_null() {
@@ -99,20 +376,39 @@ mod response {
         assert!(value["totalTokens"].is_null());
         assert_eq!(value["createdTokensDisplay"], "-");
     }
+
+    #[test]
+    fn account_usage_currency_should_limit_usd_to_four_fraction_digits() {
+        assert_eq!(format_decimal_currency("0.1204956", "USD"), "$0.1205");
+        assert_eq!(format_decimal_currency("0.99996", "USD"), "$1.00");
+        assert_eq!(format_decimal_currency("0.0300", "USD"), "$0.03");
+        assert_eq!(format_decimal_currency("12.3456", "USD"), "$12.35");
+        assert_eq!(format_decimal_currency("0.1204956", "CNY"), "CNY 0.1204956");
+    }
 }
 
 mod actions {
+    use base64::Engine as _;
     use gateway_admin::model::{
         Revision,
-        accounts::{AccountConnectionTestEvent as DomainConnectionTestEvent, AccountStatus},
-        provider_credentials::{CredentialDeletionResult, CredentialImportResult},
+        accounts::AccountConnectionTestEvent as DomainConnectionTestEvent,
+        provider_credentials::{
+            CredentialDeletionResult, CredentialImportResult, CredentialMutationResult,
+        },
     };
     use gateway_api::admin::accounts::{
         AccountActionRequest, AccountConnectionTestEvent, AccountDeletionData,
         AccountDeletionRequest, AccountExportData, AccountExportQuery, AccountIdQuery,
-        AccountImportData, AccountImportRequest, AccountRefreshRequest, AccountTestQuery,
+        AccountImportData, AccountImportRequest, AccountMutationData, AccountRefreshRequest,
+        AccountResetCreditConsumeRequest, AccountTestQuery, CompleteAccountAuthorizationRequest,
+        RotateAccountRequest, StartAccountAuthorizationRequest,
+    };
+    use gateway_core::{
+        engine::{
+            UpstreamSendState, credential::ProviderAccountId, probe::AccountProbeErrorSource,
+        },
+        error::GatewayErrorKind,
     };
-    use gateway_core::engine::credential::ProviderAccountId;
     use serde_json::json;
 
     #[test]
@@ -147,7 +443,7 @@ mod actions {
     }
 
     #[test]
-    fn account_actions_should_require_frozen_account_ids_and_revision() {
+    fn account_actions_should_require_frozen_account_ids_and_reject_unknown_revision() {
         let id: AccountIdQuery =
             serde_json::from_value(json!({ "accountId": "acct_1" })).expect("decode ID query");
         assert!(id.validate().is_ok());
@@ -155,13 +451,107 @@ mod actions {
             serde_json::from_value(json!({ "accountId": "legacy-id" })).expect("decode action");
         assert_eq!(action.validate().unwrap_err().field(), "accountId");
         let refresh: AccountRefreshRequest = serde_json::from_value(json!({
-            "accountId": "acct_1",
-            "expectedConfigRevision": 0
+            "accountId": "acct_1"
         }))
         .expect("decode refresh");
+        assert!(refresh.validate().is_ok());
+        assert!(
+            serde_json::from_value::<AccountRefreshRequest>(json!({
+                "accountId": "acct_1",
+                "expectedConfigRevision": 0
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn reset_credit_consume_should_require_canonical_v4_idempotency_key() {
+        let valid: AccountResetCreditConsumeRequest = serde_json::from_value(json!({
+            "accountId": "acct_1",
+            "creditId": "credit_1",
+            "redeemRequestId": "8fbf302d-11df-4bd5-82e4-08e4b3df7874"
+        }))
+        .expect("decode reset-credit consume");
+        valid.validate().expect("validate reset-credit consume");
+
+        for (redeem_request_id, field) in [
+            ("019c0000-0000-7000-8000-000000000000", "redeemRequestId"),
+            ("8FBF302D-11DF-4BD5-82E4-08E4B3DF7874", "redeemRequestId"),
+            ("invalid", "redeemRequestId"),
+        ] {
+            let request: AccountResetCreditConsumeRequest = serde_json::from_value(json!({
+                "accountId": "acct_1",
+                "redeemRequestId": redeem_request_id
+            }))
+            .expect("decode invalid reset-credit consume");
+            assert_eq!(request.validate().expect_err("reject UUID").field(), field);
+        }
+
+        let invalid_credit: AccountResetCreditConsumeRequest = serde_json::from_value(json!({
+            "accountId": "acct_1",
+            "creditId": " ",
+            "redeemRequestId": "8fbf302d-11df-4bd5-82e4-08e4b3df7874"
+        }))
+        .expect("decode invalid credit");
         assert_eq!(
-            refresh.validate().unwrap_err().field(),
-            "expectedConfigRevision"
+            invalid_credit
+                .validate()
+                .expect_err("reject credit")
+                .field(),
+            "creditId"
+        );
+    }
+
+    #[test]
+    fn credential_recovery_requests_should_not_accept_client_revision_fences() {
+        let authorization: StartAccountAuthorizationRequest = serde_json::from_value(json!({
+            "provider": "openai",
+            "name": "reauthorize",
+            "accountId": "acct_1"
+        }))
+        .expect("decode reauthorization");
+        assert!(authorization.validate().is_ok());
+        assert!(
+            serde_json::from_value::<StartAccountAuthorizationRequest>(json!({
+                "provider": "openai",
+                "name": "reauthorize",
+                "accountId": "acct_1",
+                "expectedCredentialRevision": 1
+            }))
+            .is_err()
+        );
+
+        let rotation: RotateAccountRequest = serde_json::from_value(json!({
+            "provider": "openai",
+            "accountId": "acct_1",
+            "accessToken": "header.payload.signature",
+            "refreshToken": "refresh-token",
+            "idToken": "id-header.id-payload.id-signature"
+        }))
+        .expect("decode rotation");
+        assert!(rotation.validate().is_ok());
+        assert!(
+            serde_json::from_value::<RotateAccountRequest>(json!({
+                "provider": "openai",
+                "accountId": "acct_1",
+                "expectedCredentialRevision": 1,
+                "accessToken": "header.payload.signature"
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn credential_mutation_response_should_not_expose_internal_revision() {
+        let response = AccountMutationData::from(CredentialMutationResult {
+            config_revision: Revision::new(8).expect("config revision"),
+            account_id: ProviderAccountId::new("acct_1").expect("account ID"),
+            credential_revision: Some(Revision::new(9).expect("credential revision")),
+        });
+
+        assert_eq!(
+            serde_json::to_value(response).expect("serialize credential mutation"),
+            json!({ "accountId": "acct_1" })
         );
     }
 
@@ -169,7 +559,6 @@ mod actions {
     fn account_import_should_use_provider_and_opaque_data_fields() {
         let valid: AccountImportRequest = serde_json::from_value(json!({
             "provider": "openai",
-            "expectedConfigRevision": 7,
             "data": {
                 "providerOwnedUnknownField": {"nested": [1, 2, 3]},
                 "accounts": [{"credentials": {"access_token": "provider-validates-this"}}]
@@ -180,7 +569,6 @@ mod actions {
 
         let invalid: AccountImportRequest = serde_json::from_value(json!({
             "provider": "xai",
-            "expectedConfigRevision": 7,
             "data": []
         }))
         .expect("decode invalid account import");
@@ -188,27 +576,61 @@ mod actions {
         assert!(
             serde_json::from_value::<AccountImportRequest>(json!({
                 "provider": "openai",
-                "expectedConfigRevision": 7,
                 "document": {}
             }))
             .is_err()
         );
+        assert!(
+            serde_json::from_value::<AccountImportRequest>(json!({
+                "provider": "openai",
+                "expectedConfigRevision": 7,
+                "data": {}
+            }))
+            .is_err()
+        );
+        assert!(
+            serde_json::from_value::<AccountImportRequest>(json!({
+                "provider": "openai",
+                "data": {},
+                "groupIds": []
+            }))
+            .is_err()
+        );
+    }
+
+    #[test]
+    fn oauth_complete_should_not_accept_group_assignment() {
+        let flow_id = base64::engine::general_purpose::URL_SAFE_NO_PAD.encode([7_u8; 32]);
+        let request: CompleteAccountAuthorizationRequest = serde_json::from_value(json!({
+            "provider": "openai",
+            "flowId": flow_id,
+            "callbackUrl": "http://localhost/callback?code=ok"
+        }))
+        .expect("decode OAuth completion");
+        assert!(request.validate().is_ok());
+        assert!(
+            serde_json::from_value::<CompleteAccountAuthorizationRequest>(json!({
+                "provider": "xai",
+                "flowId": "flow_test",
+                "callbackUrl": "http://localhost/callback?code=ok",
+                "groupIds": []
+            }))
+            .is_err()
+        );
     }
 
     #[test]
     fn account_deletion_should_validate_one_provider_batch_and_emit_account_ids() {
         let request: AccountDeletionRequest = serde_json::from_value(json!({
             "provider": "xai",
-            "accountIds": ["acct_1", "acct_2"],
-            "expectedConfigRevision": 8
+            "accountIds": ["acct_1", "acct_2"]
         }))
         .expect("decode account deletion");
         assert!(request.validate().is_ok());
 
         let duplicate: AccountDeletionRequest = serde_json::from_value(json!({
             "provider": "xai",
-            "accountIds": ["acct_1", "acct_1"],
-            "expectedConfigRevision": 8
+            "accountIds": ["acct_1", "acct_1"]
         }))
         .expect("decode duplicate account deletion");
         assert_eq!(duplicate.validate().unwrap_err().field(), "accountIds");
@@ -223,7 +645,6 @@ mod actions {
         assert_eq!(
             serde_json::to_value(response).expect("serialize account deletion"),
             json!({
-                "configRevision": 9,
                 "deletedCount": 2,
                 "accountIds": ["acct_1", "acct_2"]
             })
@@ -232,14 +653,13 @@ mod actions {
 
     #[test]
     fn account_import_response_should_emit_account_ids() {
-        let response = AccountImportData::from(CredentialImportResult {
+        let response = AccountImportData::from_result(CredentialImportResult {
             config_revision: Revision::new(8).expect("revision"),
             credential_ids: vec![ProviderAccountId::new("acct_imported").expect("account ID")],
         });
         assert_eq!(
             serde_json::to_value(response).expect("serialize account import"),
             json!({
-                "configRevision": 8,
                 "importedCount": 1,
                 "accountIds": ["acct_imported"]
             })
@@ -271,12 +691,17 @@ mod actions {
             DomainConnectionTestEvent::Content {
                 text: "OK".to_owned(),
             },
-            DomainConnectionTestEvent::Completed {
-                account_status: AccountStatus::Active,
-            },
+            DomainConnectionTestEvent::Completed {},
             DomainConnectionTestEvent::Failed {
+                source: AccountProbeErrorSource::Upstream,
+                gateway_error_code: GatewayErrorKind::RateLimited,
+                send_state: Some(UpstreamSendState::Sent),
                 message: "upstream unavailable".to_owned(),
-                account_status: AccountStatus::Active,
+                provider_error_code: Some("usage_exhausted".to_owned()),
+                provider_error_type: Some("invalid_request_error".to_owned()),
+                upstream_status: Some(429),
+                upstream_content_type: Some("application/json".to_owned()),
+                upstream_body: Some(r#"{"error":{"type":"usage_limit_reached"}}"#.to_owned()),
             },
         ]
         .map(|event| AccountConnectionTestEvent::from(event).data);
@@ -301,8 +726,19 @@ mod actions {
                     }
                 }),
                 json!({ "type": "content", "text": "OK" }),
-                json!({ "type": "test_complete", "success": true, "accountStatus": "active" }),
-                json!({ "type": "error", "error": "upstream unavailable", "accountStatus": "active" }),
+                json!({ "type": "test_complete", "success": true }),
+                json!({
+                    "type": "error",
+                    "source": "upstream",
+                    "gatewayErrorCode": "rate_limited",
+                    "sendState": "sent",
+                    "error": "upstream unavailable",
+                    "providerErrorCode": "usage_exhausted",
+                    "providerErrorType": "invalid_request_error",
+                    "upstreamStatus": 429,
+                    "upstreamContentType": "application/json",
+                    "upstreamBody": r#"{"error":{"type":"usage_limit_reached"}}"#
+                }),
             ]
         );
     }

backend/crates/gateway-api/tests/admin/auth.rs

@@ -51,7 +51,6 @@ async fn default_auth_service_should_initialize_login_validate_and_logout() {
     let service = fixture.services.auth();
     let session = service
         .login(LoginCommand {
-            source: "127.0.0.1".to_owned(),
             username: Some("admin_1".to_owned()),
             password: "strong-admin-password".to_owned(),
         })
@@ -84,42 +83,6 @@ async fn default_auth_service_should_initialize_login_validate_and_logout() {
     assert_eq!(fixture.auth.audit_count(), 2);
 }
 
-#[tokio::test]
-async fn default_auth_service_should_throttle_repeated_invalid_identity() {
-    let fixture = AdminTestFixture::new().await;
-    for attempt in 1..=5 {
-        let error = fixture
-            .services
-            .auth()
-            .login(LoginCommand {
-                source: "shared-source".to_owned(),
-                username: Some("wrong-user".to_owned()),
-                password: "wrong-password".to_owned(),
-            })
-            .await
-            .expect_err("invalid login");
-        if attempt < 5 {
-            assert_eq!(error, LoginError::InvalidCredentials);
-        } else {
-            assert_eq!(error, LoginError::Throttled);
-        }
-    }
-    assert_eq!(
-        fixture
-            .services
-            .auth()
-            .login(LoginCommand {
-                source: "shared-source".to_owned(),
-                username: None,
-                password: "anything".to_owned(),
-            })
-            .await
-            .expect_err("source remains throttled"),
-        LoginError::Throttled
-    );
-    assert_eq!(fixture.auth.session_count(), 0);
-}
-
 #[tokio::test]
 async fn default_auth_service_should_verify_only_full_plaintext_admin_key() {
     let fixture = AdminTestFixture::new().await;
@@ -162,7 +125,6 @@ async fn audit_failure_should_revoke_new_session_before_returning_it() {
             .services
             .auth()
             .login(LoginCommand {
-                source: "source".to_owned(),
                 username: None,
                 password: "strong-admin-password".to_owned(),
             })