chore(release): v3.41.2

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

.agents/skills/cpr-dev-guide/SKILL.md

@@ -5,6 +5,13 @@ description: Codex Proxy RS 开发、修复、排障、代码审查和文档修
 
 # 开发指南
 
+## 首要写作要求：言简意赅
+
+所有面向人的文字都按此要求编写和审查，包括界面、通知、后端错误、任务状态、命令行、日志、注释、文档和交付说明
+
+- 先写读者需要知道的事实或动作。删掉一句不影响理解、判断或操作，就删；标题、正文和通知不重复同一信息
+- 保留会改变决定的条件、权限、后果和恢复步骤。错误通知只说已知问题，有明确办法才补一句；后端返回的提示在后端改，前端不重复解释。上游原文、用户内容和诊断事实保持原样
+
 ## 先确定领域与必读规范
 
 按用户意图、受影响行为与对象初判，定位后按实际文件复核，不要求用户说出“前端”“后端”或技能名。**所有命中行共同构成本次必读规范，先读完再确定方案、修改或给出审查结论**；跨领域叠加，不能只选最像当前步骤的一行
@@ -27,7 +34,7 @@ description: Codex Proxy RS 开发、修复、排障、代码审查和文档修
 
 纯文档任务按文档分支执行；核实文中的合同与职责时读对应领域条款，不因提及代码路径或语言加载实现、构建与页面验收流程
 
-命中的流程引用完整读取，并落实其中指定的必读章节；长文档先用 `rg -n '^#{1,4} ' 文件` 定位，读取指定章节的完整内容。`#章节` 不会自动截取，“按需”仅用于未命中的领域和后续操作资料，不能省略必读规范；已有内容只在当前上下文可用且仍适用时复用，不循环重读技能
+首次命中的流程引用完整读取，并落实其中指定的必读章节；长文档先用 `rg -n '^#{1,4} ' 文件` 定位，分段读取指定章节，避免输出截断。`#章节` 不会自动截取，“按需”仅用于未命中的领域和后续操作资料，不能省略必读规范；读取记录与验证证据的复用按 [任务延续与收尾](../../../AGENTS.md#任务延续与收尾) 执行
 
 ## 参考仓库的优先级
 
@@ -38,8 +45,8 @@ description: Codex Proxy RS 开发、修复、排障、代码审查和文档修
 1. 遵守已提供的 [AGENTS.md](../../../AGENTS.md)，按其 CodeGraph 约定定位代码；确认工作区、任务范围与已有改动，找到事实归属、同类实现和调用链，补齐上表命中规范及[项目约定](../../../CONTRIBUTING.md#项目约定)对应条目后再修改
 2. 以最终差异重新匹配上表，补齐新增领域的规范并检查实际实现，再处理本次引入的职责越界、重复规则、冗余状态与无依据分支；删除或替换功能时一并清理失效的配置、类型、调用、测试与文档，已部署数据和公开合同仍遵守所属迁移及兼容规则；仅审查时报告，不自行修复
 3. 按最终行为执行[文档检查](references/documentation.md)，核对所属正文及相关概述、示例和引用，在本任务内完成必要同步；不以尚无文档差异跳过检查。内部重构等未改变文档所述事实时无需改文档；常规文档只写当前状态，普通开发不自动修改 `release/notes.md`
-4. 按变更范围执行[验证](../../../CONTRIBUTING.md#验证)及其停止条件，后端命令见[验证命令](../../../docs/architecture.md#验证命令)；沿用本轮有效证据与用户已确定的验收分工，区分通过、失败、跳过与未执行；提交时补读[提交约定](../../../CONTRIBUTING.md#项目约定)
-5. 交付实际结果与验证缺口；前端按[前端流程](references/frontend.md)核对最终差异和运行证据，后端按上表检查生命周期，不把构建通过当作行为验收
+4. 按变更范围执行[验证](../../../CONTRIBUTING.md#验证)及其停止条件，后端命令见[验证命令](../../../docs/architecture.md#验证命令)；复用仍适用的验证证据与用户已确定的验收分工，区分通过、失败、跳过与未执行；提交前确认已覆盖[提交约定](../../../CONTRIBUTING.md#项目约定)
+5. 交付前按[首要写作要求](#首要写作要求言简意赅)通读本次新增或修改的文字。交代实际结果与验证缺口；前端按[前端流程](references/frontend.md)核对运行证据，后端按上表检查生命周期，不把构建通过当作行为验收
 
 ## 测试维护
 

.agents/skills/cpr-github-pr/SKILL.md

@@ -15,6 +15,8 @@ description: 准备、创建、更新或审查 GitHub PR，含回复讨论与处
 
 本仓库目标分支为 `main`，其他仓库使用其可信基线规则与模板，PR 内修改的规则不能降低审查要求
 
+为本仓库拟写或更新 PR 标题时，完整标题使用英文，沿用提交信息的 Conventional Commits 格式，例如 `fix(store): preserve client key ledgers after deletion`
+
 涉及上游行为的判断按[问题与方案依据](../../../CONTRIBUTING.md#问题与方案依据)执行
 
 ## 按模式读取

.agents/skills/cpr-release/SKILL.md

@@ -18,7 +18,7 @@ description: Codex Proxy RS 的版本规划、发布说明、正式或预发行
 ## 必须保持的边界
 
 - Codex 兼容性变化按[问题与方案依据](../../../CONTRIBUTING.md#问题与方案依据)核对已有依据与验证范围，缺少依据列为发行风险，不以 CI 通过代替
-- `release/publish` 会提交、打 tag、推送并触发工作流，没有只读预演模式，不能用于探测或演练
+- `release/publish --check <version>` 只读检查发行准备条件；不带 `--check` 会提交、打 tag、推送并触发工作流，实际发布仍需相应授权
 - 同名版本、超时或中断先查本地与远端状态，不删已发布 tag、不移动 tag、不强推掩盖冲突
 - 预发行不得覆盖 GitHub Latest 或镜像 `latest`，完成后回读核对
 - `release/notes.md` 只承载当前发行的说明；常规文档修改另按开发入口执行[文档检查](../cpr-dev-guide/references/documentation.md)

.agents/skills/cpr-release/references/operations.md

@@ -31,7 +31,7 @@ release/publish "$release_version"
 ```
 
 该命令会创建上述版本提交与 annotated tag，原子推送分支和 tag，再从长期分支手动触发 `release.yml`。
-它没有只读预演模式；不能为了检查或演练而执行。发布工作流读取 tag 中的说明，修改 tag 之后的本地文件不会改变该次构建。
+只读预检使用 `release/publish --check "$release_version"`。发布工作流读取 tag 中的说明，修改 tag 之后的本地文件不会改变该次构建。
 
 只调整已发布页面的标题或正文时，编辑对应 GitHub Release 的 `name` 或 `body` 并回读核对；
 保持已有 tag、源码提交、附件和预发行状态，不重新执行发布入口。
@@ -43,6 +43,7 @@ release/publish "$release_version"
 - 提交和 tag 已推送但工作流未触发时，核对目标后使用脚本提示的 dispatch 命令补触发；
   工作流已存在则跟踪或恢复对应 run，避免重复发布。发现 tag 指向不同提交时报告冲突，不移动已发布 tag。
 - 跟踪与本次 tag 对应的 run ID，核对工作流解析的目标提交。触发工作流成功只表示已开始，不能当作发布完成。
+- 构建与打包中间产物保留 7 天，在有效期内可重跑失败任务；产物过期后重跑完整工作流，不移动原 tag。
 - 发布完成后核对 GitHub Release 的版本、正式版/预发行状态和中文变更正文；对照平台清单与工作流确认归档、校验和及镜像产物。
   工作流附加的安装说明和自动提交列表按其当前配置处理，不用它们替代手写的中文变更说明。
 - 返回版本、tag 对应提交、Release/工作流链接及实际结果。失败、仍在构建或缺失产物时明确说明，不能称为发布成功；

.agents/skills/cpr-release/references/preparation.md

@@ -26,6 +26,9 @@
 
 进入实际发行准备后，读取目标分支的 [release/publish](../../../../release/publish)、[工作流](../../../../.github/workflows/release.yml)与[平台清单](../../../../release/platforms.yaml)，按当前入口执行，不另写脚本或绕过检查
 
+发布说明准备好、其他代码已提交后，执行 `release/publish --check <version>`，检查版本、说明、工作区、远端分支与 tag、工具链和插件兼容窗口。
+预检不修改文件、Git 引用或远端状态；远端存在本地未知提交时先同步再检查。它不替代 CI、发行物验证或实际发布授权
+
 按[验证要求](../../../../CONTRIBUTING.md#验证)核对目标提交的证据，区分通过、失败、跳过与未执行
 数据库变更同时读取[迁移冻结规则](../../../../backend/migrations/README.md#冻结规则)：
 

.gitattributes

@@ -0,0 +1,3 @@
+# SQLx migration checksums are byte-sensitive; keep migration inputs portable across hosts.
+backend/migrations/*.sql text eol=lf
+backend/migrations/.frozen-sha256 text eol=lf

.github/ISSUE_TEMPLATE/api-bug-report.yml

@@ -139,7 +139,6 @@ body:
     id: expected-behavior
     attributes:
       label: 预期行为
-      description: 说明原本期望得到的结果。
     validations:
       required: true
 

.github/ISSUE_TEMPLATE/general-bug-report.yml

@@ -108,7 +108,6 @@ body:
     id: expected-behavior
     attributes:
       label: 预期行为
-      description: 说明原本期望得到的结果。
     validations:
       required: true
 

.github/actions/build-binary/action.yml

@@ -0,0 +1,76 @@
+name: Build binary
+description: Build a native release binary with shared dependency caching and timings
+inputs:
+  rust:
+    description: Pinned Rust toolchain
+    required: true
+  target:
+    description: Rust target triple
+    required: true
+  platform:
+    description: Release platform name, such as linux-amd64
+    required: true
+  binary:
+    description: Executable filename
+    default: codex-proxy-rs
+  rust-image:
+    description: Pinned Linux builder image; empty for native builds
+    default: ''
+runs:
+  using: composite
+  steps:
+    - name: Setup Rust
+      uses: dtolnay/rust-toolchain@683b588c487a69d01f6c6ddf40f036ff682cc2c8 # master
+      with:
+        toolchain: ${{ inputs.rust }}
+        targets: ${{ inputs.target }}
+
+    - name: Configure Windows runtime linkage
+      if: runner.os == 'Windows'
+      shell: bash
+      # 发行包静态链接 MSVC 运行库，解压运行时无需安装 VC++ Redistributable
+      run: echo 'RUSTFLAGS=-C target-feature=+crt-static' >> "$GITHUB_ENV"
+
+    - name: Cache Rust dependencies
+      uses: Swatinem/rust-cache@d1527c8f67ef9af357290475d4af4b0fab8f12e0 # v2.9.3
+      with:
+        workspaces: backend -> target
+        shared-key: release-${{ inputs.target }}-${{ inputs.rust-image }}
+        cache-bin: false
+        # 只缓存依赖，避免随版本变化的 workspace 产物挤占缓存
+        save-if: ${{ github.event_name != 'pull_request' }}
+
+    - name: Build binary
+      shell: bash
+      working-directory: backend
+      env:
+        BUILD_TARGET: ${{ inputs.target }}
+        BUILD_PLATFORM: ${{ inputs.platform }}
+        BUILD_BINARY: ${{ inputs.binary }}
+        RUST_IMAGE: ${{ inputs.rust-image }}
+      run: |
+        set -euo pipefail
+        if [ -n "$RUST_IMAGE" ]; then
+          mkdir -p "$HOME/.cargo"
+          docker run --rm --user "$(id -u):$(id -g)" \
+            -e CARGO_HOME=/cargo -e HOME=/tmp \
+            -e CPR_VERSION -e CPR_GIT_SHA -e CPR_BUILD_TIME -e CPR_BUILD_TYPE \
+            -v "$HOME/.cargo:/cargo" -v "$PWD/..:/workspace" \
+            -w /workspace/backend "$RUST_IMAGE" \
+            cargo build --release --locked --timings --target "$BUILD_TARGET" --bin codex-proxy-rs
+        else
+          cargo build --release --locked --timings --target "$BUILD_TARGET" --bin codex-proxy-rs
+        fi
+        "target/$BUILD_TARGET/release/$BUILD_BINARY" --help
+        "target/$BUILD_TARGET/release/$BUILD_BINARY" --version
+        mkdir -p "../dist/binaries/$BUILD_PLATFORM"
+        cp "target/$BUILD_TARGET/release/$BUILD_BINARY" "../dist/binaries/$BUILD_PLATFORM/$BUILD_BINARY"
+
+    - name: Upload build timings
+      if: always()
+      uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+      with:
+        name: build-timings-${{ inputs.platform }}
+        path: backend/target/cargo-timings/
+        if-no-files-found: ignore
+        retention-days: 7

.github/actions/build-frontend/action.yml

@@ -43,4 +43,4 @@ runs:
         name: frontend-dist
         path: frontend/dist
         if-no-files-found: error
-        retention-days: 1
+        retention-days: 7

.github/actions/cargo-cache/Dockerfile

@@ -1,24 +0,0 @@
-# syntax=docker/dockerfile:1.7@sha256:a57df69d0ea827fb7266491f2813635de6f17269be881f696fbfdf2d83dda33e
-
-FROM busybox:1.37.0-musl@sha256:5cec3fc171c87218698e85a52af7087de727372aae264a787b8112901a5b0092 AS restore
-ARG CACHE_STAMP
-RUN --mount=type=bind,target=/cache \
-    --mount=type=cache,target=/usr/local/cargo/registry \
-    --mount=type=cache,target=/usr/local/cargo/git \
-    --mount=type=cache,target=/app/backend/target \
-    test -n "$CACHE_STAMP" \
-    && tar -xzf /cache/registry.tar.gz -C /usr/local/cargo/registry \
-    && tar -xzf /cache/git.tar.gz -C /usr/local/cargo/git \
-    && tar -xzf /cache/target.tar.gz -C /app/backend/target
-
-FROM busybox:1.37.0-musl@sha256:5cec3fc171c87218698e85a52af7087de727372aae264a787b8112901a5b0092 AS snapshot
-ARG CACHE_STAMP
-# 直接压缩 mount 内容，构建层和 runner 只保存归档，避免多份展开的编译产物占满磁盘
-RUN --mount=type=cache,target=/usr/local/cargo/registry \
-    --mount=type=cache,target=/usr/local/cargo/git \
-    --mount=type=cache,target=/app/backend/target \
-    test -n "$CACHE_STAMP" \
-    && mkdir -p /cache \
-    && tar -czf /cache/registry.tar.gz -C /usr/local/cargo/registry . \
-    && tar -czf /cache/git.tar.gz -C /usr/local/cargo/git . \
-    && tar -czf /cache/target.tar.gz -C /app/backend/target .

.github/actions/cargo-cache/action.yml

@@ -1,31 +0,0 @@
-name: Cargo cache mounts
-description: Restore or export a validated Cargo snapshot for a BuildKit builder
-inputs:
-  operation:
-    description: Cache operation, restore or snapshot
-    required: true
-  builder:
-    description: Buildx builder name
-    required: true
-  path:
-    description: Cargo snapshot directory on the runner
-    required: true
-  architecture:
-    description: Cargo target directory architecture, amd64 or arm64
-    required: true
-outputs:
-  usable:
-    description: Whether the restored or exported snapshot contains Cargo dependencies
-    value: ${{ steps.cache.outputs.usable }}
-runs:
-  using: composite
-  steps:
-    - id: cache
-      shell: bash
-      env:
-        ACTION_PATH: ${{ github.action_path }}
-        OPERATION: ${{ inputs.operation }}
-        BUILDER: ${{ inputs.builder }}
-        CACHE_PATH: ${{ inputs.path }}
-        ARCHITECTURE: ${{ inputs.architecture }}
-      run: bash "$ACTION_PATH/cargo-cache.sh" "$OPERATION" "$BUILDER" "$CACHE_PATH" "$ARCHITECTURE"

.github/actions/cargo-cache/cargo-cache.sh

@@ -1,78 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-if [ "$#" -ne 4 ]; then
-  echo "usage: $0 restore|snapshot BUILDER DIRECTORY amd64|arm64" >&2
-  exit 2
-fi
-operation="$1"
-builder="$2"
-directory="$(realpath -m "$3")"
-architecture="$4"
-case "$operation" in restore|snapshot) ;; *) exit 2 ;; esac
-case "$architecture" in amd64|arm64) ;; *) exit 2 ;; esac
-dockerfile="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/Dockerfile"
-
-usable() {
-  # 流式检查归档中的非空依赖文件，校验时不在 runner 展开编译产物
-  python3 - "$1" "$architecture" <<'PY'
-import pathlib
-import re
-import sys
-import tarfile
-
-root = pathlib.Path(sys.argv[1])
-architecture = sys.argv[2]
-
-def contains(filename, pattern):
-    with tarfile.open(root / filename, mode="r|gz") as archive:
-        return any(
-            member.isfile() and member.size > 0
-            and re.fullmatch(pattern, member.name.removeprefix("./"))
-            for member in archive
-        )
-
-try:
-    valid = (
-        (root / "git.tar.gz").stat().st_size > 0
-        and contains("registry.tar.gz", r"cache/[^/]+/[^/]+\.crate")
-        and contains("target.tar.gz", rf"{architecture}/release/deps/[^/]+\.rlib")
-    )
-except (OSError, tarfile.TarError):
-    valid = False
-sys.exit(0 if valid else 1)
-PY
-}
-
-command=(docker buildx build --builder "$builder" --file "$dockerfile" --progress plain)
-# mount 的内容不参与层指纹，用时间戳重跑归档操作；--no-cache 会重置 cache mount
-command+=(--build-arg "CACHE_STAMP=$(date +%s%N)" --target "$operation")
-valid=false
-if [ "$operation" = restore ]; then
-  if usable "$directory"; then
-    "${command[@]}" --output type=cacheonly "$directory"
-    valid=true
-  else
-    echo "No usable Cargo snapshot; cached image layers may still be available"
-  fi
-else
-  # 导出只发送空上下文，新快照独立校验后替换旧目录，避免残留文件造成误判。
-  mkdir -p "$(dirname "$directory")"
-  temporary="$(mktemp -d "${directory}.XXXXXX")"
-  trap 'rm -rf "$temporary"' EXIT
-  mkdir "$temporary"/{context,snapshot}
-  # tar 流避开 local exporter 的逐文件同步阻塞，只接收 /cache 下的压缩归档
-  # 直接导出打包阶段，避免再创建一层归档副本
-  # https://github.com/moby/buildkit/issues/2950
-  "${command[@]}" --output type=tar,dest=- "$temporary/context" \
-    | tar -xf - -C "$temporary/snapshot" --strip-components=1 cache/
-  if usable "$temporary/snapshot"; then
-    rm -rf "$directory"
-    mv "$temporary/snapshot" "$directory"
-    valid=true
-  fi
-fi
-
-echo "Cargo snapshot for $architecture: usable=$valid"
-if [ "$valid" = true ]; then du -sh "$directory"; fi
-if [ -n "${GITHUB_OUTPUT:-}" ]; then printf 'usable=%s\n' "$valid" >> "$GITHUB_OUTPUT"; fi

.github/dependabot.yml

@@ -70,7 +70,6 @@ updates:
   - package-ecosystem: docker
     directories:
       - /deploy
-      - /.github/actions/cargo-cache
     labels: []
     schedule:
       interval: weekly

.github/scripts/release-checks-test.rb

@@ -0,0 +1,193 @@
+require 'fileutils'
+require 'json'
+require 'open3'
+require 'tmpdir'
+require_relative 'release-quality'
+
+# 使用临时 Git 仓库验证远端状态和只读边界，不访问真实 GitHub 或修改当前仓库
+ROOT = File.expand_path('../..', __dir__)
+
+def assert(condition, message)
+  raise message unless condition
+end
+
+def git(*arguments)
+  output, error, status = Open3.capture3('git', *arguments)
+  raise "git #{arguments.first}: #{error}" unless status.success?
+  output.strip
+end
+
+def commit(message)
+  git('add', '.')
+  git('commit', '-qm', message)
+end
+
+Dir.mktmpdir('release-checks-') do |directory|
+  remote = File.join(directory, 'remote.git')
+  system('git', 'init', '--bare', '-q', remote, exception: true)
+  checkout = File.join(directory, 'checkout')
+  FileUtils.mkdir_p(checkout)
+  Dir.chdir(checkout) do
+    git('init', '-q', '-b', 'main')
+    git('config', 'user.email', 'test@example.invalid')
+    git('config', 'user.name', 'Release test')
+    files = %w[
+      release/publish release/version.yaml release/notes.md release/platforms.yaml
+      .github/scripts/toolchains.rb .github/scripts/release-metadata.rb
+      backend/rust-toolchain.toml deploy/Dockerfile
+      backend/crates/gateway-plugin/runtime/plugin-api-lifecycle.rb
+      backend/crates/gateway-plugin/runtime/plugin-host-compatibility.json
+      backend/crates/gateway-plugin/runtime/plugin-api-deprecations.json
+    ]
+    files.each do |path|
+      FileUtils.mkdir_p(File.dirname(path))
+      FileUtils.cp(File.join(ROOT, path), path)
+    end
+    commit('initial source')
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'root commit should require full checks')
+    git('remote', 'add', 'origin', remote)
+    git('push', '-qu', 'origin', 'main')
+    File.write('release/notes.md', "# v99.0.0\n\nFixture notes\n")
+
+    bin = File.join(directory, 'bin')
+    FileUtils.mkdir_p(bin)
+    File.write(File.join(bin, 'gh'), <<~RUBY)
+      #!/usr/bin/env ruby
+      case ARGV
+      when ['auth', 'status'] then exit 0
+      when ['repo', 'view', #{remote.inspect}, '--json', 'nameWithOwner', '--jq', '.nameWithOwner']
+        puts 'owner/repo'
+      else
+        abort "unexpected gh mutation: \#{ARGV.inspect}"
+      end
+    RUBY
+    File.chmod(0o755, File.join(bin, 'gh'))
+    environment = { 'PATH' => "#{bin}:#{ENV.fetch('PATH')}" }
+    snapshot = lambda do
+      [git('show-ref'), git('status', '--porcelain'), File.binread('.git/index'),
+       files.to_h { |path| [path, File.binread(path)] },
+       git('ls-remote', 'origin'), File.exist?('.git/FETCH_HEAD')]
+    end
+    check = lambda do |success, message = nil|
+      before = snapshot.call
+      output, error, status = Open3.capture3(environment, 'bash', 'release/publish', '--check', '99.0.0')
+      assert(status.success? == success, "preflight outcome: #{output}#{error}")
+      assert("#{output}#{error}".include?(message), "missing error: #{message}; #{error}") if message
+      assert(snapshot.call == before, 'preflight modified files, refs, index, or FETCH_HEAD')
+    end
+    check.call(true, 'Preflight passed')
+    File.write('deploy/Dockerfile', File.read('deploy/Dockerfile') + "\n# fixture\n")
+    check.call(false, 'unstaged changes')
+    git('checkout', '--', 'deploy/Dockerfile')
+    git('tag', 'v99.0.0')
+    check.call(false, 'local tag already exists')
+    git('push', '-q', 'origin', 'refs/tags/v99.0.0')
+    git('tag', '-d', 'v99.0.0')
+    check.call(false, 'remote tag already exists')
+    git('push', '-q', 'origin', ':refs/tags/v99.0.0')
+
+    # 未履行的兼容窗口必须在只读预检中失败，不能等待提交版本后再发现
+    deprecations = 'backend/crates/gateway-plugin/runtime/plugin-api-deprecations.json'
+    previous = File.read(deprecations)
+    File.write(deprecations, JSON.generate([{
+      capability: 'removed-fixture', version: 1, replacement_version: 2, remaining_releases: 7
+    }]))
+    git('add', deprecations)
+    git('commit', '-qm', 'invalid lifecycle fixture')
+    check.call(false, 'replacement v2 must be available')
+    File.write(deprecations, previous)
+    commit('restore lifecycle and notes')
+    File.write('release/notes.md', "# v99.0.0\n\nUpdated fixture notes\n")
+
+    # 远端前进但没有本地对象时，提示同步而不隐式 fetch
+    other = File.join(directory, 'other')
+    git('clone', '-q', '-b', 'main', remote, other)
+    Dir.chdir(other) do
+      git('config', 'user.email', 'test@example.invalid')
+      git('config', 'user.name', 'Release test')
+      File.write('remote-only', 'change')
+      commit('remote advance')
+      git('push', '-q')
+    end
+    check.call(false, 'unseen commits')
+    git('fetch', '-q', 'origin')
+    check.call(false, 'diverged')
+    FileUtils.mv(remote, "#{remote}.hidden")
+    # 读取远端失败不能当作 tag 不存在，仍须保持本地不变
+    before = [git('show-ref'), git('status', '--porcelain'), File.binread('.git/index')]
+    _, error, status = Open3.capture3(environment, 'bash', 'release/publish', '--check', '99.0.0')
+    assert(!status.success? && error.include?('failed to read remote refs'), 'remote failure was ignored')
+    assert(before == [git('show-ref'), git('status', '--porcelain'), File.binread('.git/index')], 'remote failure changed local state')
+    FileUtils.mv("#{remote}.hidden", remote)
+
+    File.write('release/version.yaml', "version: \"99.0.0\"\n")
+    commit('release metadata')
+    parent = git('rev-parse', 'HEAD^')
+    run = { 'head_sha' => parent, 'conclusion' => 'success', 'head_repository' => { 'full_name' => 'owner/repo' }, 'id' => 42 }
+    job = { 'name' => 'quality / backend', 'conclusion' => 'success', 'html_url' => 'https://example.invalid/42' }
+    runs = [run]
+    jobs = [job]
+    original_capture = ReleaseQuality.method(:capture)
+    ReleaseQuality.define_singleton_method(:capture) do |*arguments|
+      if arguments.first == 'gh'
+        endpoint = arguments.find { |argument| argument.start_with?('repos/') }
+        if endpoint.include?('/workflows/ci.yml/runs?')
+          assert(endpoint.include?("event=push&branch=main&head_sha=#{parent}"), 'wrong CI evidence scope')
+          JSON.generate('workflow_runs' => runs)
+        else
+          assert(endpoint == 'repos/owner/repo/actions/runs/42/jobs?per_page=100', 'wrong run jobs')
+          jobs.map { |entry| JSON.generate(entry) }.join("\n")
+        end
+      else
+        original_capture.call(*arguments)
+      end
+    end
+    assert(ReleaseQuality.evidence('owner/repo') == job['html_url'], 'valid CI evidence not reused')
+    %w[skipped failure cancelled].each do |conclusion|
+      job['conclusion'] = conclusion
+      assert(ReleaseQuality.evidence('owner/repo').nil?, "reused #{conclusion} backend")
+    end
+    job['conclusion'] = 'success'
+    jobs = []
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused missing backend job')
+    jobs = [job]
+    run['conclusion'] = 'failure'
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused failed CI run')
+    run['conclusion'] = nil
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused unfinished CI run')
+    run['conclusion'] = 'success'
+    run['head_repository']['full_name'] = 'fork/repo'
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused foreign repository CI')
+    run['head_repository']['full_name'] = 'owner/repo'
+    runs = []
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused absent CI run')
+    runs = [run]
+    output, _, status = Open3.capture3(environment.merge('GITHUB_REPOSITORY' => 'owner/repo'), 'ruby', File.join(ROOT, '.github/scripts/release-quality.rb'))
+    assert(status.success? && output.strip == 'run_backend=true', 'API failure did not fall back to full checks')
+    File.write('backend/source.rs', '// changed source')
+    commit('source changed')
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'reused CI across source changes')
+    merge = git('commit-tree', 'HEAD^{tree}', '-p', 'HEAD', '-p', 'HEAD^', '-m', 'merge fixture')
+    git('update-ref', 'HEAD', merge)
+    assert(ReleaseQuality.evidence('owner/repo').nil?, 'merge commit should require full checks')
+
+    # 在同一个隔离仓库走实际提交与原子推送路径，dispatch 仍由本地替身接收
+    git('merge', '--no-edit', 'origin/main')
+    File.write('release/notes.md', "# v100.0.0\n\nPublish fixture notes\n")
+    dispatch = File.join(directory, 'dispatch.json')
+    mock = File.join(bin, 'gh')
+    File.write(mock, File.read(mock).sub("else\n", <<~RUBY))
+      when ['workflow', 'run', 'release.yml', '--repo', 'owner/repo', '--ref', 'main', '--raw-field', 'tag=v100.0.0']
+        File.write(#{dispatch.inspect}, ARGV.join(' '))
+      else
+    RUBY
+    output, error, status = Open3.capture3(environment, 'bash', 'release/publish', '100.0.0')
+    assert(status.success?, "publish failed: #{output}#{error}")
+    assert(File.exist?(dispatch), 'workflow was not dispatched')
+    assert(git('log', '-1', '--format=%s') == 'chore(release): v100.0.0', 'wrong release commit')
+    assert(git('status', '--porcelain').empty?, 'release left tracked changes')
+    assert(git('rev-parse', 'HEAD') == git('rev-parse', 'v100.0.0^{commit}'), 'tag differs from release commit')
+    assert(git('ls-remote', 'origin', 'refs/tags/v100.0.0').split.first == git('rev-parse', 'v100.0.0'), 'tag not pushed')
+  end
+end
+puts 'Release preflight and CI evidence checks passed'

.github/scripts/release-metadata.rb

@@ -82,6 +82,7 @@ module ReleaseMetadata
       'platform_matrix' => JSON.generate('include' => entries),
       'docker_matrix' => JSON.generate('include' => docker),
       'non_docker_matrix' => JSON.generate('include' => native),
+      'windows_matrix' => JSON.generate('include' => entries.select { |entry| entry['os'] == 'windows' }),
       'docker_platforms' => docker.map { |entry| entry['dockerPlatform'] }.join(','),
       'previous_tag' => previous,
       'prerelease' => prerelease?(value),

.github/scripts/release-quality.rb

@@ -0,0 +1,44 @@
+require 'json'
+require 'open3'
+
+# 仅复用同一源码的主分支 CI，缺少证据时完整检查发行提交
+module ReleaseQuality
+  def self.capture(*command)
+    output, error, status = Open3.capture3(*command)
+    raise "#{command.first} failed: #{error.strip}" unless status.success?
+    output
+  end
+
+  def self.evidence(repository)
+    parents = capture('git', 'rev-list', '--parents', '-n', '1', 'HEAD').split
+    return nil unless parents.length == 2
+    parent = parents.last
+    changes = capture('git', 'diff', '--name-only', '-z', parent, 'HEAD').split("\0")
+    return nil if changes.empty? || (changes - %w[release/version.yaml release/notes.md]).any?
+
+    # 按最新一次运行判断，失败或仍在执行时不回退到旧的成功记录
+    endpoint = "repos/#{repository}/actions/workflows/ci.yml/runs?event=push&branch=main&head_sha=#{parent}&per_page=1"
+    run = JSON.parse(capture('gh', 'api', endpoint)).fetch('workflow_runs').first
+    return nil unless run && run.fetch('head_sha') == parent && run.fetch('conclusion') == 'success'
+    return nil unless run.fetch('head_repository').fetch('full_name') == repository
+
+    rows = capture('gh', 'api', '--paginate', "repos/#{repository}/actions/runs/#{run.fetch('id')}/jobs?per_page=100", '--jq', '.jobs[] | @json')
+    job = rows.lines.map { |line| JSON.parse(line) }.find { |entry| entry.fetch('name') == 'quality / backend' }
+    return nil unless job && job.fetch('conclusion') == 'success'
+    job.fetch('html_url')
+  end
+end
+
+if $PROGRAM_NAME == __FILE__
+  begin
+    evidence = ReleaseQuality.evidence(ENV.fetch('GITHUB_REPOSITORY'))
+  rescue StandardError => error
+    warn "CI evidence unavailable; running full release checks: #{error.message}"
+    evidence = nil
+  end
+  puts "run_backend=#{evidence.nil?}"
+  if ENV['GITHUB_STEP_SUMMARY']
+    message = evidence ? "后端质量检查复用版本提交父提交的 [CI 结果](#{evidence})；仅版本与发布说明不同" : '未找到可复用的后端 CI 结果，完整检查发行提交'
+    File.open(ENV.fetch('GITHUB_STEP_SUMMARY'), 'a') { |file| file.puts(message) }
+  end
+end

.github/workflows/_container.yml

@@ -7,13 +7,58 @@ on:
         description: Exact commit SHA to build and validate
         required: true
         type: string
+      source_build:
+        description: Validate the complete Docker source build
+        type: boolean
+        default: true
 
 permissions:
   contents: read
   security-events: write
 
 jobs:
+  frontend:
+    if: ${{ !inputs.source_build }}
+    runs-on: ubuntu-26.04
+    timeout-minutes: 15
+    env:
+      CI: 'true'
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          ref: ${{ inputs.ref }}
+      - uses: ./.github/actions/build-frontend
+        with:
+          upload-artifact: 'true'
+
+  binary:
+    if: ${{ !inputs.source_build }}
+    runs-on: ubuntu-26.04
+    timeout-minutes: 45
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          ref: ${{ inputs.ref }}
+      - id: toolchains
+        run: ruby .github/scripts/toolchains.rb >> "$GITHUB_OUTPUT"
+      - uses: ./.github/actions/build-binary
+        with:
+          rust: ${{ steps.toolchains.outputs.rust }}
+          target: x86_64-unknown-linux-gnu
+          platform: linux-amd64
+          rust-image: ${{ steps.toolchains.outputs.rust_image }}
+        env:
+          CPR_GIT_SHA: ${{ inputs.ref }}
+      - uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+        with:
+          name: codex-proxy-rs-linux-amd64
+          path: dist/binaries/linux-amd64/
+          if-no-files-found: error
+          retention-days: 7
+
   container:
+    needs: [frontend, binary]
+    if: always() && !cancelled()
     runs-on: ubuntu-26.04
     timeout-minutes: 45
     env:
@@ -21,6 +66,14 @@ jobs:
       TRIVY_QUIET: 'true'
       TRIVY_SKIP_VERSION_CHECK: 'true'
     steps:
+      # 上游失败必须传递给已有的容器检查，不能让必需状态变成 skipped
+      - name: Require prebuilt inputs
+        if: ${{ !inputs.source_build }}
+        env:
+          FRONTEND_RESULT: ${{ needs.frontend.result }}
+          BINARY_RESULT: ${{ needs.binary.result }}
+        run: test "$FRONTEND_RESULT" = success && test "$BINARY_RESULT" = success
+
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
@@ -30,41 +83,51 @@ jobs:
         id: buildx
         uses: docker/setup-buildx-action@f87e5991a6d7451dcb8d9637bfbc97413f497069 # v4.4.1
 
-      - name: Restore Cargo snapshot
-        id: cargo-cache
-        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+      - name: Download frontend
+        if: ${{ !inputs.source_build }}
+        uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
         with:
-          path: ${{ runner.temp }}/container-cargo
-          # 同一平台和依赖复用快照，源码变化由 Cargo 指纹判定是否重编译
-          key: container-cargo-v4-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml', 'deploy/Dockerfile', '.github/actions/cargo-cache/Dockerfile') }}
-          restore-keys: |
-            container-cargo-v4-${{ runner.os }}-${{ runner.arch }}-
+          name: frontend-dist
+          path: dist/docker/web/dist
 
-      - name: Restore Cargo mounts to BuildKit
-        id: cargo-restore
-        uses: ./.github/actions/cargo-cache
+      - name: Download binary
+        if: ${{ !inputs.source_build }}
+        uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
         with:
-          operation: restore
-          builder: ${{ steps.buildx.outputs.name }}
-          path: ${{ runner.temp }}/container-cargo
-          architecture: amd64
+          name: codex-proxy-rs-linux-amd64
+          path: dist/docker-artifacts/codex-proxy-rs-linux-amd64
 
-      - name: Release restored Cargo snapshot
-        run: rm -rf "$RUNNER_TEMP/container-cargo"
+      - name: Prepare prebuilt image
+        if: ${{ !inputs.source_build }}
+        env:
+          MATRIX_OS: linux
+          MATRIX_ARCH: amd64
+          MATRIX_BINARY: codex-proxy-rs
+        run: |
+          ruby -r './.github/scripts/release-metadata' -e '
+            ReleaseMetadata.seal_manifest(
+              "version" => ReleaseMetadata.version(YAML.load_file("release/version.yaml").fetch("version")),
+              "git_sha" => ReleaseMetadata.git("rev-parse", "HEAD")
+            )'
+          ruby .github/scripts/package-release.rb image
 
       - name: Build runtime image
         uses: docker/build-push-action@c3c9e263c25d99ce0380d002d59b67737d91b0dc # v7.4.0
         with:
           context: .
           file: deploy/Dockerfile
-          target: runtime
+          target: ${{ inputs.source_build && 'runtime' || 'runtime-prebuilt' }}
+          build-args: |
+            CPR_PREBUILT_DIR=dist/docker
+            CPR_GIT_SHA=${{ inputs.ref }}
           load: true
           tags: ${{ env.CPR_IMAGE }}
           no-cache-filters: |
             runtime-base
             runtime
-          cache-from: type=gha,scope=runtime-ci
-          cache-to: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' && 'type=gha,mode=max,scope=runtime-ci' || '' }}
+            runtime-prebuilt
+          cache-from: type=gha,scope=runtime-${{ inputs.source_build && 'source' || 'prebuilt' }}
+          cache-to: ${{ (github.event_name == 'push' || github.event_name == 'schedule') && github.ref == 'refs/heads/main' && format('type=gha,mode=max,scope=runtime-{0}', inputs.source_build && 'source' || 'prebuilt') || '' }}
 
       - name: Verify runtime image
         uses: ./.github/actions/verify-container
@@ -72,23 +135,3 @@ jobs:
           image: ${{ env.CPR_IMAGE }}
           platform: linux/amd64
           artifact-name: container-diagnostics-${{ github.run_id }}-${{ github.run_attempt }}-amd64
-
-      # 构建层命中时 mount 仍可能为空，只有实际检查过内容的快照才允许保存。
-      - name: Export Cargo snapshot
-        if: >-
-          github.event_name == 'push' && github.ref == 'refs/heads/main' &&
-          (steps.cargo-cache.outputs.cache-hit != 'true' || steps.cargo-restore.outputs.usable != 'true')
-        id: cargo-snapshot
-        uses: ./.github/actions/cargo-cache
-        with:
-          operation: snapshot
-          builder: ${{ steps.buildx.outputs.name }}
-          path: ${{ runner.temp }}/container-cargo
-          architecture: amd64
-
-      - name: Save Cargo snapshot
-        if: steps.cargo-snapshot.outputs.usable == 'true' && steps.cargo-cache.outputs.cache-hit != 'true'
-        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-        with:
-          path: ${{ runner.temp }}/container-cargo
-          key: ${{ steps.cargo-cache.outputs.cache-primary-key }}

.github/workflows/_quality.yml

@@ -28,6 +28,7 @@ jobs:
     timeout-minutes: 30
     env:
       CARGO_TERM_COLOR: always
+      CARGO_PROFILE_DEV_DEBUG: '1'
       # 编译 AWS SDK 调试信息需要更大的 codegen 线程栈
       RUST_MIN_STACK: 16777216
       CPR_TEST_DATABASE_URL: postgres://codex_proxy:codex_proxy@127.0.0.1:5432/codex_proxy
@@ -111,7 +112,9 @@ jobs:
         uses: Swatinem/rust-cache@d1527c8f67ef9af357290475d4af4b0fab8f12e0 # v2.9.3
         with:
           workspaces: backend -> target
-          save-if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
+          shared-key: quality
+          cache-bin: false
+          save-if: ${{ github.event_name != 'pull_request' && github.ref == 'refs/heads/main' }}
 
       - name: Rust format
         working-directory: backend
@@ -122,7 +125,7 @@ jobs:
         run: cargo clippy --all-targets --all-features --locked -- -D warnings
 
       - name: Setup nextest
-        uses: taiki-e/install-action@68a389c788b2cd04016ce8c80ee23b80d2ab3d68 # v2.88.1
+        uses: taiki-e/install-action@682ce6c3c696a4cd5168a05f98e51aa02b877941 # v2.89.1
         with:
           tool: cargo-nextest@0.9.143
           fallback: none
@@ -131,7 +134,7 @@ jobs:
         working-directory: backend
         run: |
           cargo metadata --format-version 1 --locked > "$RUNNER_TEMP/nextest-cargo-metadata.json"
-          cargo nextest list --test main --locked --list-type binaries-only --message-format json \
+          cargo nextest list --test main --locked --timings --list-type binaries-only --message-format json \
             > "$RUNNER_TEMP/nextest-binaries.json"
 
       - name: Configure PostgreSQL and Redis test authentication
@@ -173,10 +176,22 @@ jobs:
       - name: Rust tests
         working-directory: backend
         run: |
-          cargo nextest run \
+          printf '[profile.ci.junit]\npath = "junit.xml"\n' > "$RUNNER_TEMP/nextest-ci.toml"
+          cargo nextest run --config-file "$RUNNER_TEMP/nextest-ci.toml" \
             --cargo-metadata "$RUNNER_TEMP/nextest-cargo-metadata.json" \
             --binaries-metadata "$RUNNER_TEMP/nextest-binaries.json" \
-            --test-threads 8 --no-tests fail
+            --test-threads 8 --no-tests fail --profile ci
+
+      - name: Upload test and build reports
+        if: always()
+        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+        with:
+          name: backend-quality-reports
+          path: |
+            backend/target/nextest/ci/junit.xml
+            backend/target/cargo-timings/
+          if-no-files-found: ignore
+          retention-days: 7
 
       - name: Store tests with Redis ACL authentication
         working-directory: backend
@@ -244,3 +259,6 @@ jobs:
           for script in .github/scripts/*.rb; do ruby -c "$script"; done
           ruby .github/scripts/toolchains.rb
           ruby -c backend/crates/gateway-plugin/runtime/plugin-api-lifecycle.rb
+
+      - name: Verify release preflight and CI evidence
+        run: ruby .github/scripts/release-checks-test.rb

.github/workflows/ci.yml

@@ -29,6 +29,7 @@ jobs:
       backend: ${{ steps.filter.outputs.backend }}
       frontend: ${{ steps.filter.outputs.frontend }}
       container: ${{ steps.filter.outputs.container }}
+      source_container: ${{ steps.filter.outputs.source_container }}
     steps:
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -67,10 +68,30 @@ jobs:
               - '.dockerignore'
               - 'release/version.yaml'
               - '.github/actions/verify-container/**'
-              - '.github/actions/cargo-cache/**'
+              - '.github/actions/build-binary/**'
+              - '.github/actions/build-frontend/**'
+              - '.github/scripts/toolchains.rb'
+              - '.github/scripts/package-release.rb'
+              - '.github/scripts/release-metadata.rb'
               - '.github/workflows/_container.yml'
               - '.github/workflows/ci.yml'
               - '!**/*.md'
+            source_container:
+              - 'deploy/Dockerfile'
+              - 'deploy/Dockerfile.dockerignore'
+              - '.dockerignore'
+              - 'backend/**/Cargo.toml'
+              - 'backend/Cargo.lock'
+              - 'backend/rust-toolchain.toml'
+              - 'backend/**/build.rs'
+              - 'backend/.cargo/**'
+              - 'frontend/package.json'
+              - 'frontend/pnpm-lock.yaml'
+              - 'frontend/pnpm-workspace.yaml'
+              - 'frontend/.npmrc'
+              - 'frontend/patches/**'
+              - '.github/workflows/_container.yml'
+              - '.github/workflows/ci.yml'
 
   quality:
     needs: changes
@@ -78,7 +99,8 @@ jobs:
     with:
       ref: ${{ github.event.pull_request.head.sha || github.sha }}
       run_backend: ${{ needs.changes.outputs.backend == 'true' }}
-      run_frontend: ${{ needs.changes.outputs.frontend == 'true' }}
+      # 预构建容器复用同一次前端检查产物，源码 Docker 构建仍独立验证
+      run_frontend: ${{ needs.changes.outputs.frontend == 'true' && (needs.changes.outputs.container != 'true' || needs.changes.outputs.source_container == 'true') }}
 
   container:
     needs: changes
@@ -89,3 +111,4 @@ jobs:
     uses: ./.github/workflows/_container.yml
     with:
       ref: ${{ github.event.pull_request.head.sha || github.sha }}
+      source_build: ${{ needs.changes.outputs.source_container == 'true' }}

.github/workflows/release.yml

@@ -23,6 +23,9 @@ jobs:
   release-info:
     runs-on: ubuntu-26.04
     timeout-minutes: 10
+    permissions:
+      contents: read
+      actions: read
     outputs:
       tag: ${{ steps.version.outputs.tag }}
       version: ${{ steps.version.outputs.version }}
@@ -32,12 +35,14 @@ jobs:
       platform_matrix: ${{ steps.version.outputs.platform_matrix }}
       docker_matrix: ${{ steps.version.outputs.docker_matrix }}
       non_docker_matrix: ${{ steps.version.outputs.non_docker_matrix }}
+      windows_matrix: ${{ steps.version.outputs.windows_matrix }}
       docker_platforms: ${{ steps.version.outputs.docker_platforms }}
       previous_tag: ${{ steps.version.outputs.previous_tag }}
       prerelease: ${{ steps.version.outputs.prerelease }}
       build_type: ${{ steps.version.outputs.build_type }}
       rust: ${{ steps.toolchains.outputs.rust }}
       rust_image: ${{ steps.toolchains.outputs.rust_image }}
+      run_backend: ${{ steps.quality.outputs.run_backend }}
 
     steps:
       - name: Checkout
@@ -56,21 +61,88 @@ jobs:
         id: toolchains
         run: ruby .github/scripts/toolchains.rb >> "$GITHUB_OUTPUT"
 
+      - name: Check reusable backend CI evidence
+        id: quality
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: ruby .github/scripts/release-quality.rb >> "$GITHUB_OUTPUT"
+
       - name: Upload sealed plugin assets
         uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
         with:
           name: plugin-release-assets
           path: dist/plugin-release-assets
           if-no-files-found: error
-          retention-days: 1
+          retention-days: 7
 
   quality:
     needs: [release-info]
     uses: ./.github/workflows/_quality.yml
     with:
       ref: ${{ needs.release-info.outputs.git_sha }}
+      run_backend: ${{ needs.release-info.outputs.run_backend == 'true' }}
       run_frontend: false
 
+  windows:
+    needs: release-info
+    name: windows-tests (${{ matrix.arch }})
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.release-info.outputs.windows_matrix) }}
+    runs-on: ${{ matrix.runner }}
+    timeout-minutes: 30
+    env:
+      RUST_MIN_STACK: '16777216'
+      RUSTFLAGS: '-C target-feature=+crt-static'
+      CARGO_PROFILE_DEV_DEBUG: '1'
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          ref: ${{ needs.release-info.outputs.git_sha }}
+      - uses: dtolnay/rust-toolchain@683b588c487a69d01f6c6ddf40f036ff682cc2c8 # master
+        with:
+          toolchain: ${{ needs.release-info.outputs.rust }}
+          targets: ${{ matrix.target }}
+      - uses: Swatinem/rust-cache@d1527c8f67ef9af357290475d4af4b0fab8f12e0 # v2.9.3
+        with:
+          workspaces: backend -> target
+          shared-key: platform-tests-${{ matrix.target }}
+          cache-bin: false
+          save-if: ${{ github.event_name != 'pull_request' }}
+      - name: Setup nextest
+        uses: taiki-e/install-action@682ce6c3c696a4cd5168a05f98e51aa02b877941 # v2.89.1
+        with:
+          tool: cargo-nextest@0.9.143
+          fallback: none
+      - name: Verify Windows platform behavior
+        shell: bash
+        working-directory: backend
+        env:
+          BUILD_TARGET: ${{ matrix.target }}
+        # 同一次构建统一两个 package 的依赖特性，保留原有平台用例和静态运行库
+        run: |
+          printf '[profile.ci.junit]\npath = "junit.xml"\n' > "$RUNNER_TEMP/nextest-ci.toml"
+          cargo nextest run --config-file "$RUNNER_TEMP/nextest-ci.toml" --locked --target "$BUILD_TARGET" \
+            -p gateway-admin -p gateway-host --test main --no-tests fail --profile ci \
+            -E '(package(=gateway-admin) & test(/^use_case::plugins::official::/)) | (package(=gateway-host) & test(/^system_update::/))'
+      - name: Upload test report
+        if: always()
+        uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
+        with:
+          name: windows-tests-${{ matrix.arch }}
+          path: backend/target/nextest/ci/junit.xml
+          if-no-files-found: ignore
+          retention-days: 7
+
+  security:
+    needs: release-info
+    uses: ./.github/workflows/security.yml
+    permissions:
+      contents: read
+      security-events: write
+    with:
+      ref: ${{ needs.release-info.outputs.git_sha }}
+
   frontend:
     needs: release-info
     runs-on: ubuntu-26.04
@@ -103,40 +175,15 @@ jobs:
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
-      - name: Cache Cargo
-        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-        with:
-          path: |
-            ~/.cargo/registry
-            ~/.cargo/git
-            backend/target
-          # 按目标、工具链和依赖保存，不为每个发行提交复制整个 target
-          key: cargo-v3-${{ runner.os }}-${{ matrix.target }}-${{ needs.release-info.outputs.rust_image }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
-          restore-keys: |
-            cargo-v3-${{ runner.os }}-${{ matrix.target }}-
-
       - name: Build binary
-        shell: bash
-        run: |
-          mkdir -p "$HOME/.cargo" "../dist/binaries/${{ matrix.os }}-${{ matrix.arch }}"
-          docker run --rm \
-            --platform "${{ matrix.dockerPlatform }}" \
-            --user "$(id -u):$(id -g)" \
-            -e CARGO_HOME=/cargo \
-            -e HOME=/tmp \
-            -e CPR_VERSION="${CPR_VERSION}" \
-            -e CPR_GIT_SHA="${CPR_GIT_SHA}" \
-            -e CPR_BUILD_TIME="${CPR_BUILD_TIME}" \
-            -e CPR_BUILD_TYPE="${CPR_BUILD_TYPE}" \
-            -v "$HOME/.cargo:/cargo" \
-            -v "$PWD/..:/workspace" \
-            -w /workspace/backend \
-            "${RUST_IMAGE}" \
-            cargo build --release --locked --target "${{ matrix.target }}" --bin codex-proxy-rs
-          cp "target/${{ matrix.target }}/release/${{ matrix.binary }}" "../dist/binaries/${{ matrix.os }}-${{ matrix.arch }}/${{ matrix.binary }}"
-        working-directory: backend
+        uses: ./.github/actions/build-binary
+        with:
+          rust: ${{ needs.release-info.outputs.rust }}
+          target: ${{ matrix.target }}
+          platform: ${{ matrix.os }}-${{ matrix.arch }}
+          binary: ${{ matrix.binary }}
+          rust-image: ${{ needs.release-info.outputs.rust_image }}
         env:
-          RUST_IMAGE: ${{ needs.release-info.outputs.rust_image }}
           CPR_VERSION: ${{ needs.release-info.outputs.version }}
           CPR_GIT_SHA: ${{ needs.release-info.outputs.git_sha }}
           CPR_BUILD_TIME: ${{ needs.release-info.outputs.build_time }}
@@ -148,7 +195,7 @@ jobs:
           name: codex-proxy-rs-${{ matrix.os }}-${{ matrix.arch }}
           path: dist/binaries/${{ matrix.os }}-${{ matrix.arch }}/
           if-no-files-found: error
-          retention-days: 1
+          retention-days: 7
 
   build-binary:
     name: build-binary (${{ matrix.os }}-${{ matrix.arch }})
@@ -165,30 +212,13 @@ jobs:
         with:
           ref: ${{ needs.release-info.outputs.git_sha }}
 
-      - name: Setup Rust
-        uses: dtolnay/rust-toolchain@683b588c487a69d01f6c6ddf40f036ff682cc2c8 # master
-        with:
-          toolchain: ${{ needs.release-info.outputs.rust }}
-          targets: ${{ matrix.target }}
-
-      - name: Cache Cargo
-        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-        with:
-          path: |
-            ~/.cargo/registry
-            ~/.cargo/git
-            backend/target
-          key: cargo-v3-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
-          restore-keys: |
-            cargo-v3-${{ runner.os }}-${{ matrix.target }}-
-
       - name: Build binary
-        shell: bash
-        run: |
-          cargo build --release --locked --target "${{ matrix.target }}" --bin codex-proxy-rs
-          mkdir -p "../dist/binaries/${{ matrix.os }}-${{ matrix.arch }}"
-          cp "target/${{ matrix.target }}/release/${{ matrix.binary }}" "../dist/binaries/${{ matrix.os }}-${{ matrix.arch }}/${{ matrix.binary }}"
-        working-directory: backend
+        uses: ./.github/actions/build-binary
+        with:
+          rust: ${{ needs.release-info.outputs.rust }}
+          target: ${{ matrix.target }}
+          platform: ${{ matrix.os }}-${{ matrix.arch }}
+          binary: ${{ matrix.binary }}
         env:
           CPR_VERSION: ${{ needs.release-info.outputs.version }}
           CPR_GIT_SHA: ${{ needs.release-info.outputs.git_sha }}
@@ -201,7 +231,7 @@ jobs:
           name: codex-proxy-rs-${{ matrix.os }}-${{ matrix.arch }}
           path: dist/binaries/${{ matrix.os }}-${{ matrix.arch }}/
           if-no-files-found: error
-          retention-days: 1
+          retention-days: 7
 
   package-assets:
     needs: [release-info, frontend, build-docker-binary, build-binary]
@@ -255,7 +285,7 @@ jobs:
           name: release-assets
           path: dist/release
           if-no-files-found: error
-          retention-days: 1
+          retention-days: 7
           # tar.gz 已压缩，Actions 只负责传递原始发行字节。
           compression-level: 0
 
@@ -367,14 +397,14 @@ jobs:
           name: image-digest-${{ matrix.os }}-${{ matrix.arch }}
           path: dist/digests/*.txt
           if-no-files-found: error
-          retention-days: 1
+          retention-days: 7
 
   publish:
     concurrency:
       group: release-publication
       queue: max
     # 产物准备可与测试重叠，版本标签和 GitHub Release 必须等全部质量与镜像验证通过
-    needs: [release-info, quality, package-assets, build-docker-image]
+    needs: [release-info, quality, windows, security, package-assets, build-docker-image]
     runs-on: ubuntu-26.04
     timeout-minutes: 20
     permissions:

.github/workflows/security.yml

@@ -1,6 +1,12 @@
 name: Security
 
 on:
+  workflow_call:
+    inputs:
+      ref:
+        description: Exact commit SHA to audit
+        required: true
+        type: string
   push:
     branches:
       - main
@@ -14,7 +20,7 @@ permissions:
   contents: read
 
 concurrency:
-  group: security-${{ github.event.pull_request.head.repo.full_name || github.repository }}-${{ github.head_ref || github.ref_name }}
+  group: security-${{ github.workflow }}-${{ inputs.ref || github.event.pull_request.head.repo.full_name || github.repository }}-${{ github.head_ref || github.ref_name }}
   cancel-in-progress: true
 
 jobs:
@@ -25,10 +31,10 @@ jobs:
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
+          ref: ${{ inputs.ref || github.event.pull_request.head.sha || github.sha }}
 
       - name: Install cargo-audit
-        uses: taiki-e/install-action@68a389c788b2cd04016ce8c80ee23b80d2ab3d68 # v2.88.1
+        uses: taiki-e/install-action@682ce6c3c696a4cd5168a05f98e51aa02b877941 # v2.89.1
         with:
           tool: cargo-audit@0.22.2
           fallback: none
@@ -44,7 +50,7 @@ jobs:
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha || github.sha }}
+          ref: ${{ inputs.ref || github.event.pull_request.head.sha || github.sha }}
 
       - name: Setup pnpm
         uses: pnpm/action-setup@ea17c68df8912ef543352723c149a84f56e3d413 # v6.1.0

AGENTS.md

@@ -12,9 +12,9 @@
 
 结合上下文识别“提交吧”“看看这个问题”等省略说法：普通 Git 提交不自动变成 PR，代码排查不自动变成 Issue；审查与发版准备不代表获准远程写入
 
-先完整读取命中技能的 `SKILL.md`，再读取其领域必读规范，之后按当前步骤补充实现、命令和示例。技能名称、描述或入口摘要不能代替正文与必读引用；引用中明确要求“先读”“必须读取”或“执行”的规范也要落实，其他资料按需读取
+首次命中技能时完整读取其 `SKILL.md`，再读取领域必读规范，之后按当前步骤补充实现、命令和示例。技能名称、描述或入口摘要不能代替首次读取的正文与必读引用；引用中明确要求“先读”“必须读取”或“执行”的规范也要落实，其他资料按需读取
 
-按用户意图、行为影响和实际文件共同匹配，跨领域叠加；确定方案或给出审查结论前完成对应领域必读，不能因改动小、路径未落在该模块或自认为熟悉而跳过。只复用当前上下文中已实际读取且仍适用的内容；输出截断、上下文压缩后缺失的必要内容须补读，范围或阶段变化时重新匹配
+按用户意图、行为影响和实际文件共同匹配，跨领域叠加；确定方案或给出审查结论前完成对应领域必读，不能因改动小、路径未落在该模块或自认为熟悉而跳过
 
 执行所选流程中的问题核实、自审、验证与交付要求，协作流程和审查标准见 [CONTRIBUTING.md](CONTRIBUTING.md)
 
@@ -23,6 +23,13 @@ Issue 和 PR 回复统一按 [GitHub 回复口吻](CONTRIBUTING.md#github-回复
 模块职责以 [系统架构](docs/architecture.md) 为准，界面约定以 [管理端主题](docs/theme.md) 为准；
 没有明确约定时保持与相邻实现一致，不把单次页面反馈扩展成全仓规则
 
+### 任务延续与收尾
+
+- 在任务上下文和压缩摘要中保留目标、授权、当前阶段、已读规范的路径与关键约束、验证命令与结果及对应代码状态、剩余事项
+- 同一任务可复用实际完成的读取与验证记录；仅在规范变更、进入未覆盖领域或具体决策缺少条款时补读对应内容。输出截断只补缺失部分，上下文压缩与阶段切换本身不触发重读或重验
+- 远端更新或合并冲突后，按实际变更及其依赖影响补充自审和验证，复用未受影响的证据
+- 实现、自审与必要验证完成后，按[验证停止条件](CONTRIBUTING.md#验证)停止扩围；完成已获授权的剩余交付步骤并确认结果后结束
+
 <!-- CODEGRAPH_START -->
 ## CodeGraph
 

CONTRIBUTING.md

@@ -232,6 +232,10 @@ git diff --check
 
 后端 CI 使用 nextest 执行 `main` 集成测试，默认 Redis 密码模式执行完整测试集，ACL 用户模式复用同一批构建产物执行 Store 的 Redis 测试；本地验证命令见 [架构文档](docs/architecture.md#验证命令)
 
+常规容器检查与发行构建共用二进制构建入口，并复用已检查的前端产物；Dockerfile、工具链、依赖或构建配置变化时执行完整源码镜像构建，定期安全检查也覆盖源码构建。两条路径均验证容器运行、安全扫描与关闭行为
+
+发行构建与质量检查并行，Windows 两种架构的插件与系统更新测试独立运行。仅当发行提交只修改版本与发布说明，且其父提交有本仓库主分支成功的后端 CI 时复用该结果；缺少证据则完整重跑。对外发布等待质量、Windows 测试、依赖审计和镜像验证全部成功，构建耗时与测试报告保留 7 天
+
 新增自动规则优先使用现有工具，要求依据明确、结果稳定、误报可控；无法可靠判定的设计与视觉问题保留审查判断，避免把具体源码写法锁成测试
 
 AI 自动审查需要在所用工具中单独启用。其支持的检查范围和优先级过滤以工具说明为准；即使能读取 `AGENTS.md`，也不能保证所有可维护性和视觉问题都会被报告。配置参考 [Codex GitHub 审查文档](https://learn.chatgpt.com/docs/third-party/github)

README.md

@@ -40,6 +40,8 @@
 
 以下命令适用于 Linux amd64/arm64，需要 Docker Engine、Docker Compose Plugin、curl 和 OpenSSL
 
+Windows x64 / ARM64 使用发行包部署，步骤见 [Windows 二进制部署](deploy/README.md#windows-二进制部署)
+
 已有部署请先看 [升级说明](deploy/README.md#镜像升级与源码构建)，不要覆盖原配置
 
 ### 一键安装
@@ -89,7 +91,7 @@ API Key 持有者可在登录页切换身份，查看自己的用量与额度，
 
 1. 在「账号」中添加账号，完成授权或导入
 2. 按需建立账号分组，再创建客户端密钥并选择可用分组，**不选分组表示可使用全部账号**
-3. 打开密钥的「使用密钥」，复制客户端配置
+3. [连接客户端](#客户端接入)
 
 ## 客户端接入
 

backend/Cargo.lock

@@ -286,9 +286,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-s3"
-version = "1.156.0"
+version = "1.157.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1072c9aa20159b9b417115342d38c4c53108fc98e5359fcb86b7d4575747eb59"
+checksum = "6ea9794c741520d8baec9462bcd0ad12164d4f5f78d008a8da9d6a0b7222caa8"
 dependencies = [
  "arc-swap",
  "aws-credential-types",
@@ -503,9 +503,9 @@ dependencies = [
 
 [[package]]
 name = "aws-smithy-schema"
-version = "1.1.0"
+version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bec8dae1015a6d959a5faf86fbdf77486cfe19e4ccb6ee009d8a46efc45028a4"
+checksum = "9543fc722ed4865ab29fb66bd7ed0bef7b029d265ba8c587144511e30006d431"
 dependencies = [
  "aws-smithy-runtime-api",
  "aws-smithy-types",
@@ -1081,9 +1081,9 @@ dependencies = [
 
 [[package]]
 name = "crc32fast"
-version = "1.5.3"
+version = "1.5.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ba106e844045ddc02c20768ac4b0b7cb45f2cc2ecbd833ac9f5dacb183c2055"
+checksum = "5f97d3416d5337d15c4b0d78c8c91df922ca143f57ec20e2d1c188333047ef04"
 dependencies = [
  "cfg-if",
 ]
@@ -2729,9 +2729,9 @@ dependencies = [
 
 [[package]]
 name = "mio"
-version = "1.2.1"
+version = "1.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02bd0af71c67b473010cbbc60715ee815645a4dc942899111f494b4b737d6fda"
+checksum = "1788edb87fdc09c7e26304471e2f5be8cdefb1b6930d6e3985fc02ff53bf86ee"
 dependencies = [
  "libc",
  "wasi",
@@ -3578,9 +3578,9 @@ dependencies = [
 
 [[package]]
 name = "redis"
-version = "1.8.0"
+version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7acd809e80afa754c63f586955699d8990efe1c4b6613183ee5f027a11fbc8b5"
+checksum = "db7f3d75b5a3301746bff39a767bf4c5c42506b08513527308b3875bfb64a031"
 dependencies = [
  "arc-swap",
  "arcstr",
@@ -5646,14 +5646,15 @@ dependencies = [
 
 [[package]]
 name = "zip"
-version = "9.1.3"
+version = "9.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1156b39d142a34b999c2310a50455e0cb3760bf7efad0122f796d813bee26ccb"
+checksum = "e408c6cc4699dd017d53dc080cd51c2cea2b5354af57a1479bd265ed42911487"
 dependencies = [
  "crc32fast",
  "flate2",
  "getrandom 0.4.3",
  "indexmap",
+ "libc",
  "memchr",
  "nix",
  "typed-path",

backend/apps/gateway/src/bootstrap/command.rs

@@ -146,6 +146,10 @@ async fn execute(
         providers.admin,
     );
     or_shutdown!(plugin_runtime, services.register_usage_data(&usage_data));
+    or_shutdown!(
+        plugin_runtime,
+        plugin_runtime.bind_usage_queries(&usage_data)
+    );
     let services = std::sync::Arc::new(services);
     or_shutdown!(plugin_runtime, plugin_runtime.bind_services(&services));
     let commands = or_shutdown!(plugin_runtime, plugin_runtime.prepare_command_line().await);

backend/apps/gateway/src/bootstrap/server.rs

@@ -160,6 +160,10 @@ pub async fn run() -> Result<(), BootstrapError> {
         plugin_runtime,
         plugin_runtime.bind_services(&admin.services().public_services())
     );
+    or_shutdown!(
+        plugin_runtime,
+        plugin_runtime.bind_usage_queries(&admin.services().usage_data())
+    );
 
     let mut plan = store.take_worker_contributions();
     plan.push(analytics_worker);

backend/apps/gateway/src/bootstrap/startup.rs

@@ -4,7 +4,7 @@ use std::{path::PathBuf, sync::Arc};
 
 use gateway_admin::ports::provider::ProviderAdminRegistry;
 use gateway_core::{engine::provider::ProviderRegistry, time::DeploymentTimeZone};
-use gateway_host::{ConfigError, HostBundle, HostConfig, outbound::HttpClient};
+use gateway_host::{HostBundle, HostConfig, outbound::HttpClient};
 use gateway_store::{StoreBundle, StoreConfig};
 
 use super::BootstrapError;
@@ -33,6 +33,8 @@ impl Environment {
         let timezone = host.timezone;
         let store = store.with_timezone(timezone);
         let plugin_cache = host.runtime_data_dir().join("plugins");
+        // 插件兼容检查只需本地运行版本，管理端版本查询还会等待远端发行服务
+        let version = host.system_update.version.clone();
         let host = match mode {
             Mode::Server => gateway_host::initialize(host).await?,
             Mode::Command | Mode::Help => gateway_host::initialize_command_line(host).await?,
@@ -44,12 +46,6 @@ impl Environment {
             Mode::Help => gateway_store::initialize_read_only(store).await?,
         };
         host.report_startup_ready("Store");
-        let version = host
-            .system_operations()
-            .version()
-            .await
-            .map_err(|_| ConfigError::InvalidField("host.version"))?
-            .version;
         let plugin_http = Arc::new(HttpClient::new()?);
         Ok(Self {
             host,

backend/apps/gateway/src/main.rs

@@ -1,7 +1,6 @@
 //! 网关命令行入口，选择启动模式并创建异步运行时
 
 use std::{
-    env,
     error::Error,
     io::{self, Write},
     process::ExitCode,
@@ -21,7 +20,7 @@ fn main() -> ExitCode {
 
 fn run() -> Result<ExitCode, Box<dyn Error + Send + Sync>> {
     ensure_rustls_provider();
-    let mut arguments = env::args_os().skip(1);
+    let mut arguments = gateway_host::system_update::startup_arguments()?;
     let command = arguments
         .next()
         .map(|value| {
@@ -92,7 +91,7 @@ fn runtime() -> Result<tokio::runtime::Runtime, io::Error> {
 
 fn reject_extra_arguments(mut arguments: impl Iterator) -> Result<(), io::Error> {
     if arguments.next().is_some() {
-        return Err(invalid_cli("unexpected extra command arguments"));
+        return Err(invalid_cli("too many arguments"));
     }
     Ok(())
 }

backend/apps/plugin-cli/README.md

@@ -15,7 +15,7 @@ cargo +1.99.1 install --locked --path backend/apps/plugin-cli --root /path/to/lo
 
 ## 打包
 
-先构建目标平台的插件二进制；插件提供管理页面时，还需构建页面静态资源。打包命令传入作者清单、二进制和所需的资源目录映射，通过 `cpr-plugin package --help` 查看完整参数：
+先构建目标平台的二进制；有管理页面时，也构建静态资源。全部参数见 `cpr-plugin package --help`
 
 ```bash
 cpr-plugin package \

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

@@ -197,6 +197,7 @@ async fn initialize_inner(
         auth,
         accounts: accounts.clone(),
         account_groups: Arc::new(DefaultAccountGroupService::new(
+            upstream_info.clone(),
             store.account_groups(),
             store.account_runtime(),
             snapshot.clone(),

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

@@ -7,6 +7,7 @@ use std::time::{Duration, SystemTime};
 use chrono::{DateTime, Utc};
 use futures::StreamExt as _;
 use gateway_core::account::{AccountErrorProtection, ProviderAccountId};
+use gateway_core::engine::probe::AccountProbeTarget;
 use gateway_core::routing::UpstreamModelId;
 use gateway_core::task::{
     ScheduledTask, WorkerContribution, WorkerCycleContext, WorkerId, WorkerKind,
@@ -161,7 +162,7 @@ impl FreezeRecoveryTask {
         let probe_succeeded = match self
             .deps
             .accounts
-            .test_connection(account.clone(), model)
+            .test_connection(AccountProbeTarget::FreezeRecovery(account.clone()), model)
             .await
         {
             Ok(events) => drain_probe(events).await,

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

@@ -288,8 +288,8 @@ impl AdminServices {
     }
 
     #[must_use]
-    pub fn usage_data(&self) -> &dyn UsageDataService {
-        self.usage_data.as_ref()
+    pub fn usage_data(&self) -> Arc<dyn UsageDataService> {
+        self.usage_data.clone()
     }
 
     #[must_use]

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

@@ -73,6 +73,7 @@ pub struct AccountGroupUsage {
 /// 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 inherited_version: Option<gateway_core::account::QuotaObservationVersion>,
     pub group_id: AccountGroupId,
     pub account_id: String,
     pub status: AccountStatusFacts,

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

@@ -219,7 +219,7 @@ pub struct AccountPageItem {
 pub struct AccountCapacity {
     /// 实时租约读取失败时为 `None`，不能当作空闲
     pub used_slots: Option<u64>,
-    /// 应用账号覆盖或全局默认值后的上限；`None` 表示不限
+    /// 应用账号覆盖或继承默认值后的普通并发上限；`None` 表示不限
     pub total_slots: Option<u64>,
 }
 

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

@@ -472,6 +472,90 @@ impl CostCoverage {
     }
 }
 
+/// 请求健康计数与服务成功率，调用方错误和取消不计入有效样本
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub struct RequestHealth {
+    pub success_requests: u64,
+    pub failed_requests: u64,
+    pub cancelled_requests: u64,
+    pub incomplete_requests: u64,
+    pub caller_error_requests: u64,
+}
+
+impl RequestHealth {
+    #[must_use]
+    pub fn from_counts(
+        success: u64,
+        failed: u64,
+        cancelled: u64,
+        incomplete: u64,
+        caller_error: u64,
+    ) -> Self {
+        Self {
+            success_requests: success,
+            failed_requests: failed.saturating_sub(caller_error),
+            cancelled_requests: cancelled,
+            incomplete_requests: incomplete,
+            caller_error_requests: caller_error,
+        }
+    }
+
+    pub(crate) fn from_metrics(metrics: &RequestMetrics) -> Self {
+        Self::from_counts(
+            metrics.success_count,
+            metrics.failure_count,
+            metrics.cancelled_count,
+            metrics.incomplete_count,
+            metrics.caller_error_count,
+        )
+    }
+
+    /// 账号与健康时间线使用百分数，洞察接口使用 0 到 1 的比例
+    #[must_use]
+    pub fn success_rate(self) -> Option<f64> {
+        self.success_ratio().map(|ratio| ratio * 100.0)
+    }
+
+    pub(crate) fn success_ratio(self) -> Option<f64> {
+        let total = self.eligible_requests();
+        (total > 0).then(|| self.success_requests as f64 / total as f64)
+    }
+
+    pub(crate) fn error_ratio(self) -> Option<f64> {
+        let total = self.eligible_requests();
+        (total > 0).then(|| self.non_success_requests() as f64 / total as f64)
+    }
+
+    // 未完成保留交付终态，但上游失败、超时和进程中断都不能视为服务成功
+    pub(crate) fn non_success_requests(self) -> u64 {
+        self.failed_requests
+            .saturating_add(self.incomplete_requests)
+    }
+
+    pub(crate) fn eligible_requests(self) -> u64 {
+        self.success_requests
+            .saturating_add(self.non_success_requests())
+    }
+
+    pub(crate) fn add_metrics(&mut self, metrics: &RequestMetrics) {
+        self.add_window(Self::from_metrics(metrics));
+    }
+
+    pub(crate) fn add_window(&mut self, other: Self) {
+        self.success_requests = self.success_requests.saturating_add(other.success_requests);
+        self.failed_requests = self.failed_requests.saturating_add(other.failed_requests);
+        self.cancelled_requests = self
+            .cancelled_requests
+            .saturating_add(other.cancelled_requests);
+        self.incomplete_requests = self
+            .incomplete_requests
+            .saturating_add(other.incomplete_requests);
+        self.caller_error_requests = self
+            .caller_error_requests
+            .saturating_add(other.caller_error_requests);
+    }
+}
+
 /// 请求级聚合指标
 #[derive(Debug, Clone, Default, PartialEq, Eq)]
 pub struct RequestMetrics {
@@ -622,7 +706,7 @@ pub struct AccountPoolMetrics {
 pub struct AccountModelUsage {
     pub model: String,
     pub request_count: u64,
-    pub success_count: u64,
+    pub health: RequestHealth,
     pub input_tokens: Option<u64>,
     pub output_tokens: Option<u64>,
     pub cached_input_tokens: Option<u64>,
@@ -635,7 +719,7 @@ pub struct AccountModelUsage {
     pub total_tokens: Option<u64>,
     pub cost_coverage: CostCoverage,
     pub costs: Vec<CurrencyCost>,
-    pub last_used_at: DateTime<Utc>,
+    pub last_used_at: Option<DateTime<Utc>>,
 }
 
 /// 账号在单小时窗口内的请求数
@@ -684,8 +768,10 @@ 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)]
+#[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DashboardRuntimeSlots {
+    /// 仅未设置本地覆盖的账号可能继承有效互联观测
+    pub inherited_versions: Vec<gateway_core::account::QuotaObservationVersion>,
     /// 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
@@ -724,6 +810,11 @@ pub struct UsageListRecord {
     pub outcome: RequestOutcome,
     pub error_code: Option<String>,
     pub error_message: Option<String>,
+    pub error_kind: Option<String>,
+    pub websocket_close_code: Option<u16>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub recovered: bool,
     pub client_status_code: Option<u16>,
     pub client_api_key_name: Option<String>,
     pub id: String,
@@ -739,6 +830,8 @@ pub struct UsageListRecord {
     /// 请求选号时冻结的账号套餐
     pub provider_account_plan_type: Option<String>,
     pub provider_account_plan_type_display: Option<String>,
+    /// 查询时的互联识别结果，缺少当前摘要时为未知
+    pub provider_account_upstream_peer: Option<bool>,
     pub provider_account_authentication_kind: Option<String>,
     pub upstream_model_id: Option<String>,
     pub upstream_transport: Option<String>,
@@ -780,6 +873,23 @@ pub struct UsageListRecord {
     pub started_at: DateTime<Utc>,
 }
 
+/// 受控请求详情中的上游错误字段，不参与错误分类或普通日志输出
+#[derive(Clone, PartialEq)]
+pub struct UsageUpstreamError {
+    pub code: Option<String>,
+    pub error_type: Option<String>,
+    pub message: Option<String>,
+    pub param: Option<String>,
+    pub close_reason: Option<String>,
+    pub last_event_type: Option<String>,
+}
+
+impl std::fmt::Debug for UsageUpstreamError {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter.write_str("UsageUpstreamError(<restricted>)")
+    }
+}
+
 /// 一次完整模型请求的公共观测记录
 #[derive(Debug, Clone, PartialEq)]
 pub struct UsageRecord {
@@ -818,6 +928,11 @@ pub struct UsageRecord {
     pub error_kind: Option<String>,
     pub provider_error_code: Option<String>,
     pub error_message: Option<String>,
+    pub upstream_error: Option<UsageUpstreamError>,
+    pub websocket_close_code: Option<u16>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub recovered: bool,
     pub retry_after_ms: Option<u64>,
     pub input_tokens: Option<u64>,
     pub output_tokens: Option<u64>,
@@ -976,7 +1091,9 @@ pub struct DiagnosticObservation {
     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 cancelled_count: u64,
+    pub incomplete_count: u64,
+    pub caller_error_count: u64,
     pub retry_count: u64,
     pub retried_request_count: u64,
     pub cost_coverage: CostCoverage,
@@ -1064,7 +1181,7 @@ pub struct TrendPoint {
     pub bucket_start: DateTime<Utc>,
     pub granularity: Granularity,
     pub metrics: RequestMetrics,
-    pub service_failure_count: u64,
+    pub error_count: u64,
     pub average_latency_ms: Option<u64>,
     pub average_first_token_latency_ms: Option<u64>,
     pub cached_token_rate: f64,
@@ -1082,7 +1199,7 @@ pub struct TrendSummary {
     pub output_tokens: u64,
     pub cached_input_tokens: u64,
     pub total_tokens: u64,
-    pub service_failure_count: u64,
+    pub error_count: u64,
     pub average_latency_ms: Option<u64>,
     pub max_latency_ms: Option<u64>,
     pub min_latency_ms: Option<u64>,
@@ -1246,7 +1363,7 @@ pub struct UsageInsightsHealthPoint {
     pub cancelled_requests: u64,
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
-    pub error_rate: f64,
+    pub error_rate: Option<f64>,
 }
 
 /// 洞察健康汇总；失败数已排除调用方错误
@@ -1258,7 +1375,7 @@ pub struct UsageInsightsHealth {
     pub cancelled_requests: u64,
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
-    pub success_rate: f64,
+    pub success_rate: Option<f64>,
     pub completion_rate: f64,
     pub points: Vec<UsageInsightsHealthPoint>,
 }
@@ -1439,11 +1556,13 @@ pub struct DiagnosticsItem {
     pub name: String,
     pub account_authentication_kind: Option<String>,
     pub account_plan_type: Option<String>,
+    /// 仅账号维度补充当前互联识别结果
+    pub account_upstream_peer: Option<bool>,
     pub account_plan_type_display: Option<String>,
     pub request_count: u64,
     pub success_count: u64,
     pub error_count: u64,
-    pub error_rate: f64,
+    pub error_rate: Option<f64>,
     pub request_share: f64,
     pub average_latency_ms: Option<u64>,
     pub latency_p95_ms: Option<u64>,

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

@@ -17,6 +17,7 @@ pub struct PeerLinkLimits {
 pub struct PeerLinkExport {
     pub observed_at: DateTime<Utc>,
     pub expires_at: DateTime<Utc>,
+    pub key_limits: gateway_core::policy::RateLimits,
     pub budget: ClientBudgetStatus,
     pub budget_access: ClientBudgetAccess,
     pub budget_observed_at: DateTime<Utc>,

backend/crates/gateway-admin/src/model/plugins/instances.rs

@@ -165,8 +165,9 @@ pub struct ConfigurePluginInstance {
     pub artifact_sha256: String,
     pub enabled: bool,
     pub configuration: serde_json::Value,
-    /// 缺省保留旧值；显式空对象清除全部 secret
-    pub secrets: Option<BTreeMap<String, SecretString>>,
+    /// 按字段更新，省略的字段保留，null 清除对应字段
+    #[serde(default)]
+    pub secrets: BTreeMap<String, Option<SecretString>>,
     pub bindings: Vec<PluginCapabilityBinding>,
 }
 

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

@@ -806,11 +806,12 @@ pub struct ProviderQuotaWindow {
     pub provider_data: Option<ProviderDocument>,
 }
 
-/// 账号用量统计周期，按周优先、月次之选择；短期限流窗口不参与统计面板
+/// 账号用量统计周期，完整周/月额度优先，随后使用 Provider 提供的本地滚动日统计
 #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
 pub enum AccountUsagePeriod {
     Weekly,
     Monthly,
+    Daily,
 }
 
 /// Provider 解释 quota 所需的公共请求事实
@@ -998,16 +999,27 @@ impl ProviderQuota {
         }
     }
 
-    /// 选择账号用量统计的周/月窗口，同时返回展示所需的周期事实
+    /// 选择账号用量统计窗口，同时返回展示所需的周期事实
     ///
-    /// 只使用边界完整、可归属到整个账号的窗口；周优先于月，同周期保持
-    /// Provider 投影顺序
-    /// 没有符合条件的窗口时不回退到短期或历史累计
+    /// 周/月额度使用边界完整、可归属到整个账号的窗口
+    /// 周优先于月，同周期保持 Provider 投影顺序
+    /// Provider 提供的无固定重置点的滚动日统计可独立展示
     #[must_use]
     pub fn usage_window(&self) -> Option<(&ProviderQuotaWindow, AccountUsagePeriod)> {
         self.usage_windows()
             .filter(|(window, _)| window.local_usage.is_some())
             .min_by_key(|(_, period)| *period)
+            .or_else(|| {
+                self.windows
+                    .iter()
+                    .find(|window| {
+                        window.local_usage_attribution == QuotaLocalUsageAttribution::AccountWide
+                            && window.window_seconds == Some(86_400)
+                            && window.reset_at.is_none()
+                            && window.local_usage.is_some()
+                    })
+                    .map(|window| (window, AccountUsagePeriod::Daily))
+            })
     }
 
     /// 互联账号按最长的 Key 消费周期统计本地用量，池内账号窗口不代表此 Key 的周期
@@ -1025,7 +1037,7 @@ impl ProviderQuota {
             .max_by_key(|window| window.window_seconds)
     }
 
-    /// 统计与预测共用窗口归属规则，避免把模型专属桶或短期限流当作账号容量
+    /// 周/月额度的归属规则，供额度周期统计与容量预测共用
     pub(crate) fn usage_windows(
         &self,
     ) -> impl Iterator<Item = (&ProviderQuotaWindow, AccountUsagePeriod)> {

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

@@ -62,14 +62,15 @@ pub fn account_quota_forecasts(
     now: DateTime<Utc>,
     samples: &[QuotaForecastSample],
 ) -> [AccountQuotaForecast; 2] {
-    [AccountUsagePeriod::Weekly, AccountUsagePeriod::Monthly].map(|period| {
+    [
+        (AccountUsagePeriod::Weekly, 7 * DAY_SECONDS),
+        (AccountUsagePeriod::Monthly, 30 * DAY_SECONDS),
+    ]
+    .map(|(period, target_seconds)| {
         let selected = quota_forecast_source_window(quota, period);
         let mut forecast = AccountQuotaForecast {
             period,
-            target_seconds: match period {
-                AccountUsagePeriod::Weekly => 7 * DAY_SECONDS,
-                AccountUsagePeriod::Monthly => 30 * DAY_SECONDS,
-            },
+            target_seconds,
             extrapolated: false,
             source: None,
             unavailable_reason: Some("缺少周/月额度窗口，请刷新账号额度"),

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

@@ -4,11 +4,14 @@ use chrono::{DateTime, Utc};
 
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ProviderUpstreamInfo {
+    /// 当前连接的互联识别结果，明确关闭共享或不支持协议时清除
     pub discovered: bool,
     pub observed_at: Option<DateTime<Utc>>,
     pub stale: bool,
     pub connection_revision: String,
     pub last_error: Option<String>,
+    pub max_concurrency: Option<u64>,
+    pub requests_per_minute: Option<u64>,
     pub pool: Option<UpstreamPool>,
 }
 

backend/crates/gateway-admin/src/model/usage_data/error.rs

@@ -10,6 +10,8 @@ pub enum UsageErrorKind {
     Conflict,
     CapacityExceeded,
     Unavailable,
+    Cancelled,
+    Timeout,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]

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

@@ -20,3 +20,6 @@ pub use actor::*;
 
 mod aggregate;
 pub use aggregate::*;
+
+mod read;
+pub use read::*;

backend/crates/gateway-admin/src/model/usage_data/read.rs

@@ -0,0 +1,162 @@
+//! 历史用量的窄事实、分组统计与调用内分批读取合同
+
+use super::{UsageCount, UsageMetric, UsageRecordData, UsageRecordFilter};
+use serde::{Deserialize, Serialize};
+use std::collections::BTreeMap;
+
+pub const USAGE_READ_MAX_BATCH_ROWS: u16 = 1024;
+pub const USAGE_READ_MAX_BATCH_BYTES: usize = 2 * 1024 * 1024;
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadFilter {
+    pub records: UsageRecordFilter,
+    pub routing_group_ref: Option<String>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct ScanUsageRecords {
+    pub filter: UsageReadFilter,
+    pub batch_size: Option<u16>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "snake_case")]
+pub enum UsageGrouping {
+    Model,
+    Key,
+    KeyModel,
+    RoutingGroup,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct QueryUsageStatistics {
+    pub filter: UsageReadFilter,
+    pub group_by: UsageGrouping,
+    pub batch_size: Option<u16>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case")]
+pub enum UsageReadQuery {
+    Records(ScanUsageRecords),
+    Statistics(QueryUsageStatistics),
+}
+
+impl UsageReadQuery {
+    pub fn filter(&self) -> &UsageReadFilter {
+        match self {
+            Self::Records(query) => &query.filter,
+            Self::Statistics(query) => &query.filter,
+        }
+    }
+
+    pub fn batch_size(&self) -> u16 {
+        match self {
+            Self::Records(query) => query.batch_size,
+            Self::Statistics(query) => query.batch_size,
+        }
+        .unwrap_or(USAGE_READ_MAX_BATCH_ROWS)
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageRecordFact {
+    pub id: String,
+    pub data: UsageRecordData,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub request_kind: Option<String>,
+    pub routing_scope: Option<String>,
+    pub routing_group_refs: Vec<String>,
+    pub recovered: bool,
+    /// 由宿主现行规则派生，原始审计中的恢复请求仍可读取
+    pub request_counted: bool,
+    /// 包含完整交付、预热排除及恢复关联规则
+    pub usage_counted: bool,
+}
+
+#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageStatisticsGroup {
+    pub client_key_ref: Option<String>,
+    pub model: Option<String>,
+    pub routing_group_ref: Option<String>,
+    pub unassigned_contribution: bool,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageStatisticsCost {
+    pub currency: String,
+    pub amount: String,
+    pub native_amount: Option<String>,
+    /// 外部修正允许负值，原生费用来源覆盖单独返回
+    pub contribution_amount: Option<String>,
+}
+
+#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageStatisticsCostCoverage {
+    pub provider_reported: UsageCount,
+    pub calculated: UsageCount,
+    pub unavailable: UsageCount,
+}
+
+#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageStatisticsMetrics {
+    /// 缺失的 Token 指标表示未知，计数指标始终返回
+    pub values: BTreeMap<UsageMetric, UsageCount>,
+    pub native_request_count: UsageCount,
+    pub contribution_count: UsageCount,
+    pub native_token_samples: BTreeMap<UsageMetric, UsageCount>,
+    /// 数量表示提供该指标的贡献记录数，不能用作请求覆盖率的分母
+    pub contribution_token_samples: BTreeMap<UsageMetric, UsageCount>,
+    pub cost_coverage: UsageStatisticsCostCoverage,
+    pub costs: Vec<UsageStatisticsCost>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageStatisticsRow {
+    /// null 表示全局总计，分组重叠不会重复计入该行
+    pub group: Option<UsageStatisticsGroup>,
+    pub metrics: UsageStatisticsMetrics,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(tag = "kind", content = "value", rename_all = "snake_case")]
+pub enum UsageReadItem {
+    Record(Box<UsageRecordFact>),
+    Statistics(Box<UsageStatisticsRow>),
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadAnalytics {
+    pub coverage_start_ms: Option<i64>,
+    pub coverage_end_ms: Option<i64>,
+    pub lag_seconds: u64,
+    pub state: String,
+    pub generation: u64,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadObservation {
+    pub generated_at_ms: i64,
+    pub analytics: Option<UsageReadAnalytics>,
+    pub total_groups: Option<UsageCount>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadBatch {
+    pub observation: UsageReadObservation,
+    pub items: Vec<UsageReadItem>,
+    pub complete: bool,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadOpened {
+    pub reader: Option<String>,
+    pub batch: UsageReadBatch,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct UsageReadHandle {
+    pub reader: String,
+}

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

@@ -38,6 +38,13 @@ pub trait PeerTransport: Send + Sync {
 /// 账号用例读取公共互联观测，显式刷新等待额度查询完成
 #[async_trait]
 pub trait PeerUpstreamService: gateway_core::account::UpstreamInfoSource {
+    /// 仅在指定持久观测与当前调度缓存一致时估算容量
+    fn observed_concurrency_limit(
+        &self,
+        version: &gateway_core::account::QuotaObservationVersion,
+        now: std::time::SystemTime,
+    ) -> Option<gateway_core::account::AccountConcurrencyLimit>;
+
     async fn account_changed(
         &self,
         id: &gateway_core::account::ProviderAccountId,

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

@@ -222,6 +222,15 @@ pub trait ProviderAdmin: Send + Sync {
         Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
     }
 
+    /// Key 可以继承当前全局画像；额外字段的合法性由对应 Provider 判定
+    fn preview_key_client_profile(
+        &self,
+        key: &gateway_core::account::OpaqueProviderData,
+        _global: Option<&gateway_core::account::OpaqueProviderData>,
+    ) -> Result<gateway_core::account::OpaqueProviderData, ProviderAdminError> {
+        self.preview_client_profile(key)
+    }
+
     /// 提供最终套餐展示名称；未覆盖时采用通用的大驼峰格式
     fn plan_type_display(&self, plan_type: &str) -> String {
         default_plan_type_display(plan_type)

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

@@ -2,6 +2,14 @@
 
 use crate::model::{auth::AdminAuditEvent, usage_data::*};
 use async_trait::async_trait;
+use gateway_core::lifecycle::CancellationToken;
+
+#[async_trait]
+pub trait UsageReadSession: Send {
+    async fn next_batch(&mut self) -> UsageDataResult<UsageReadBatch>;
+    fn is_finished(&self) -> bool;
+    async fn close(&mut self);
+}
 
 pub struct StoredUsageWrite {
     pub changes: Vec<(UsageRecordChange, AdminAuditEvent)>,
@@ -13,6 +21,11 @@ pub struct StoredAggregateWrite {
 
 #[async_trait]
 pub trait UsageDataStore: Send + Sync {
+    async fn open_read(
+        &self,
+        query: UsageReadQuery,
+        cancellation: CancellationToken,
+    ) -> UsageDataResult<Box<dyn UsageReadSession>>;
     async fn list_aggregates(
         &self,
         request: ListUsageAggregates,

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

@@ -60,6 +60,7 @@ pub trait AccountGroupService: Send + Sync {
 }
 
 pub(crate) struct DefaultAccountGroupService {
+    upstream_info: Option<Arc<dyn crate::ports::peer::PeerUpstreamService>>,
     store: Arc<dyn AccountGroupStore>,
     runtime: Arc<dyn AccountRuntimeStore>,
     snapshot: Arc<dyn SnapshotControl>,
@@ -68,11 +69,13 @@ pub(crate) struct DefaultAccountGroupService {
 impl DefaultAccountGroupService {
     #[must_use]
     pub(crate) fn new(
+        upstream_info: Option<Arc<dyn crate::ports::peer::PeerUpstreamService>>,
         store: Arc<dyn AccountGroupStore>,
         runtime: Arc<dyn AccountRuntimeStore>,
         snapshot: Arc<dyn SnapshotControl>,
     ) -> Self {
         Self {
+            upstream_info,
             store,
             runtime,
             snapshot,
@@ -105,7 +108,7 @@ impl DefaultAccountGroupService {
                 Default::default()
             }
         };
-        project_group_runtime(records, &members, &runtime);
+        project_group_runtime(records, &members, &runtime, self.upstream_info.as_deref());
         Ok(())
     }
 
@@ -215,6 +218,7 @@ fn project_group_runtime(
     records: &mut [AccountGroupRecord],
     members: &[AccountGroupMemberFact],
     runtime: &crate::model::accounts::AccountRuntimeSnapshot,
+    upstream: Option<&dyn crate::ports::peer::PeerUpstreamService>,
 ) {
     let now = SystemTime::now();
     let mut status_by_account = BTreeMap::new();
@@ -228,7 +232,14 @@ fn project_group_runtime(
             .or_insert_with(|| resolve_account_status(&status, now).status);
         slots_by_account
             .entry(member.account_id.as_str())
-            .or_insert(member.total_slots);
+            .or_insert_with(|| {
+                member
+                    .inherited_version
+                    .as_ref()
+                    .and_then(|version| upstream?.observed_concurrency_limit(version, now))
+                    .map(|limit| u64::from(limit.get()))
+                    .or(member.total_slots)
+            });
         accounts_by_group
             .entry(member.group_id.as_str())
             .or_default()

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

@@ -12,7 +12,7 @@ use chrono::{Duration, Utc};
 use futures::StreamExt as _;
 use gateway_core::{
     account::ProviderAccountId,
-    engine::probe::{AccountProbe, AccountProbeRequest},
+    engine::probe::{AccountProbe, AccountProbeRequest, AccountProbeTarget},
     routing::{ProviderKind, UpstreamModelId},
     runtime::SnapshotControl,
 };
@@ -178,7 +178,7 @@ pub trait AccountsService: Send + Sync {
 
     async fn test_connection(
         &self,
-        account_id: ProviderAccountId,
+        target: AccountProbeTarget,
         upstream_model: UpstreamModelId,
     ) -> Result<AccountConnectionTestEventStream, AdminError>;
 }
@@ -504,7 +504,11 @@ impl DefaultAccountsService {
             });
         Ok(AccountDirectoryItem {
             protection_rules: stored.protection_rules,
-            capacity: stored.capacity,
+            capacity: super::peer_link::upstream::account_capacity(
+                &stored.account,
+                stored.capacity,
+                &quota,
+            ),
             capabilities: provider
                 .account_capabilities(account_id, &stored.account.authentication_kind),
             plan_type_display: self.providers.resolve_account_plan(
@@ -618,7 +622,11 @@ impl AccountsService for DefaultAccountsService {
                         used_slots: in_flight
                             .as_ref()
                             .map(|counts| counts.get(&item.account.id).copied().unwrap_or(0)),
-                        ..item.capacity
+                        ..super::peer_link::upstream::account_capacity(
+                            &item.account,
+                            item.capacity,
+                            &quota,
+                        )
                     },
                     capabilities,
                     plan_type_display: providers.resolve_account_plan(
@@ -1123,10 +1131,10 @@ impl AccountsService for DefaultAccountsService {
 
     async fn test_connection(
         &self,
-        account_id: ProviderAccountId,
+        target: AccountProbeTarget,
         upstream_model: UpstreamModelId,
     ) -> Result<AccountConnectionTestEventStream, AdminError> {
-        let (stored, provider) = self.provider_for_account(&account_id).await?;
+        let (stored, provider) = self.provider_for_account(target.account_id()).await?;
         let account = stored.account;
         let model = upstream_model.as_str().to_owned();
         let operation = provider
@@ -1149,7 +1157,7 @@ impl AccountsService for DefaultAccountsService {
             let result = probe
                 .probe(
                     AccountProbeRequest {
-                        account_id,
+                        target,
                         provider_kind: account.provider_kind,
                         upstream_model,
                         operation,

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

@@ -162,7 +162,7 @@ impl BackupService for DefaultBackupService {
                 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(),
+                message: "备份存储配置不完整".to_owned(),
             });
         };
         let result = self
@@ -198,14 +198,10 @@ impl BackupService for DefaultBackupService {
             .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",
-            ));
+            return Err(AdminError::bad_request("请先补全并保存备份存储配置"));
         }
         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",
-            ));
+            return Err(AdminError::bad_request("请先通过备份存储连接测试"));
         }
         let prefix = settings.prefix.as_deref().unwrap_or_default();
         let seed = build_backup_seed(
@@ -241,9 +237,7 @@ impl BackupService for DefaultBackupService {
     ) -> 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",
-            ));
+            return Err(AdminError::conflict("只能下载已完成的备份"));
         }
         let settings = self
             .repository
@@ -280,9 +274,7 @@ impl BackupService for DefaultBackupService {
     ) -> 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",
-            ));
+            return Err(AdminError::conflict("只能删除已完成或失败的备份"));
         }
         let now = Utc::now();
         let deleting = self
@@ -290,7 +282,7 @@ impl BackupService for DefaultBackupService {
             .transition_to_deleting(backup_id, now, Some(context))
             .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"))?;
+            .ok_or_else(|| AdminError::conflict("备份状态已变更，请刷新列表"))?;
         Ok(deleting)
     }
 }

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

@@ -162,7 +162,7 @@ impl ClientKeyService for DefaultClientKeyService {
         for (provider, profile) in &command.request_profile_overrides {
             self.providers
                 .require(provider)
-                .and_then(|provider| provider.preview_client_profile(profile))
+                .and_then(|provider| provider.preview_key_client_profile(profile, None))
                 .map_err(|error| super::map_provider_error(error, "client profile"))?;
         }
         validate_peer_sharing(command.peer_sharing, &command.group_ids)?;
@@ -209,7 +209,7 @@ impl ClientKeyService for DefaultClientKeyService {
             if let Some(profile) = profile {
                 self.providers
                     .require(provider)
-                    .and_then(|provider| provider.preview_client_profile(profile))
+                    .and_then(|provider| provider.preview_key_client_profile(profile, None))
                     .map_err(|error| super::map_provider_error(error, "client profile"))?;
             }
         }

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

@@ -207,7 +207,7 @@ impl DefaultImportTasksService {
             }
             Err(_) => {
                 item.status = ImportItemStatus::Unknown;
-                item.message = Some("执行中断，请先核对账号列表再决定是否重新导入".to_owned());
+                item.message = Some("导入结果未知，重新导入前请核对账号列表".to_owned());
             }
         }
         entry.finish_if_done();

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

@@ -8,6 +8,7 @@ use std::{
 
 use async_trait::async_trait;
 use chrono::{DateTime, Duration, Utc};
+use futures::StreamExt as _;
 use gateway_core::{account::ProviderAccountId, routing::ProviderKind};
 
 use crate::{
@@ -18,8 +19,8 @@ use crate::{
             DashboardPeriodMetrics, DashboardQuery, DashboardResult, DecimalAmount,
             DiagnosticDimension, DiagnosticsItem, DiagnosticsResult, Granularity, HealthStatus,
             HealthTimeline, HealthTimelinePoint, OpsErrorPage, OpsErrorQuery, ProviderBillingInput,
-            RequestMetricPoint, RequestMetrics, TimeRange, Trend, TrendKind, TrendPoint,
-            TrendSummary, UsageBilling, UsageBillingProjection, UsageCacheEfficiency,
+            RequestHealth, RequestMetricPoint, RequestMetrics, TimeRange, Trend, TrendKind,
+            TrendPoint, TrendSummary, UsageBilling, UsageBillingProjection, UsageCacheEfficiency,
             UsageCalculatedBillingFact, UsageConcurrencyPoint, UsageCostComparison,
             UsageCostSummary, UsageDetail, UsageFilter, UsageInsight, UsageInsightData,
             UsageInsightMetric, UsageInsights, UsageInsightsCost, UsageInsightsCostPoint,
@@ -132,8 +133,9 @@ impl DefaultObservabilityService {
             self.settings.load_runtime_settings(),
         )
         .map_err(|error| map_store_error(error, "dashboard"))?;
-        let runtime_slots = observation.runtime_slots;
-        self.enrich_list_records(&mut observation.recent_requests);
+        let runtime_slots = observation.runtime_slots.as_ref();
+        self.enrich_list_records(&mut observation.recent_requests)
+            .await;
         self.enrich_dashboard_quotas(&mut observation.account_usage)
             .await;
         for account in &mut observation.account_usage {
@@ -178,11 +180,19 @@ impl DefaultObservabilityService {
             .providers
             .dashboard_wire_profiles(&settings.request_profiles);
         let max_concurrent_per_account = u64::from(settings.values.max_concurrent_per_account);
-        let (inherited_accounts, overridden_slots) = runtime_slots
-            .as_ref()
+        let (mut inherited_accounts, mut overridden_slots) = runtime_slots
             .map_or((observation.provider_accounts.normal, 0), |slots| {
                 (slots.inherited_accounts, slots.overridden_slots)
             });
+        if let (Some(peer), Some(slots)) = (&self.upstream_info, runtime_slots) {
+            let now = std::time::SystemTime::now();
+            for version in &slots.inherited_versions {
+                if let Some(limit) = peer.observed_concurrency_limit(version, now) {
+                    inherited_accounts -= 1;
+                    overridden_slots = overridden_slots.saturating_add(u64::from(limit.get()));
+                }
+            }
+        }
         let total_slots = (max_concurrent_per_account > 0 || inherited_accounts == 0).then(|| {
             inherited_accounts
                 .saturating_mul(max_concurrent_per_account)
@@ -259,7 +269,7 @@ impl ObservabilityService for DefaultObservabilityService {
             .list_usage_records(query)
             .await
             .map_err(|error| map_store_error(error, "usage records"))?;
-        self.enrich_list_records(&mut page.items);
+        self.enrich_list_records(&mut page.items).await;
         Ok(page)
     }
 
@@ -336,15 +346,29 @@ impl ObservabilityService for DefaultObservabilityService {
             .usage_diagnostics(range, filter, dimension, 100)
             .await
             .map_err(|error| map_store_error(error, "usage diagnostics"))?;
+        let peers = if dimension == DiagnosticDimension::Account {
+            self.current_upstream_peers(observation.items.iter().map(|item| item.key.as_str()))
+                .await
+        } else {
+            HashMap::new()
+        };
         let items = observation
             .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 health = RequestHealth::from_counts(
+                    item.success_count,
+                    item.failure_count,
+                    item.cancelled_count,
+                    item.incomplete_count,
+                    item.caller_error_count,
+                );
+                let non_completion_count =
+                    item.cancelled_count.saturating_add(item.incomplete_count);
+                let non_completion_rate = rate_or_zero(non_completion_count, item.request_count);
                 let retry_rate = rate_or_zero(item.retried_request_count, item.request_count);
                 DiagnosticsItem {
+                    account_upstream_peer: peers.get(&item.key).copied(),
                     key: item.key,
                     name: item.name,
                     account_authentication_kind: item.account_authentication_kind,
@@ -357,8 +381,8 @@ impl ObservabilityService for DefaultObservabilityService {
                     account_plan_type: item.account_plan_type,
                     request_count: item.request_count,
                     success_count: item.success_count,
-                    error_count: item.failure_count,
-                    error_rate,
+                    error_count: health.non_success_requests(),
+                    error_rate: health.error_ratio(),
                     request_share: rate_or_zero(
                         item.request_count,
                         observation.total_request_count,
@@ -366,7 +390,7 @@ impl ObservabilityService for DefaultObservabilityService {
                     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_count,
                     non_completion_rate,
                     retry_count: item.retry_count,
                     retry_rate,
@@ -557,9 +581,8 @@ fn build_usage_insights(
     }
 
     let requests = &overview.requests;
-    let health_window = HealthWindow::from_metrics(requests);
+    let health_window = RequestHealth::from_metrics(requests);
     let failed_requests = health_window.failed_requests;
-    let health_requests = health_window.eligible_requests();
     let health = UsageInsightsHealth {
         total_requests: requests.request_count,
         success_requests: requests.success_count,
@@ -567,7 +590,7 @@ fn build_usage_insights(
         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),
+        success_rate: health_window.success_ratio(),
         completion_rate: rate_or_zero(
             requests
                 .success_count
@@ -577,7 +600,7 @@ fn build_usage_insights(
         points: trend
             .iter()
             .map(|point| {
-                let health_window = HealthWindow::from_metrics(&point.metrics);
+                let health_window = RequestHealth::from_metrics(&point.metrics);
                 UsageInsightsHealthPoint {
                     total_requests: point.metrics.request_count,
                     bucket_start: point.bucket_start,
@@ -586,10 +609,7 @@ fn build_usage_insights(
                     cancelled_requests: point.metrics.cancelled_count,
                     incomplete_requests: point.metrics.incomplete_count,
                     caller_error_requests: point.metrics.caller_error_count,
-                    error_rate: rate_or_zero(
-                        health_window.non_success_requests(),
-                        health_window.eligible_requests(),
-                    ),
+                    error_rate: health_window.error_ratio(),
                 }
             })
             .collect(),
@@ -912,6 +932,29 @@ fn usd_cost(costs: &[CurrencyCost]) -> Option<DecimalAmount> {
 }
 
 impl DefaultObservabilityService {
+    async fn current_upstream_peers<'a>(
+        &self,
+        ids: impl Iterator<Item = &'a str>,
+    ) -> HashMap<String, bool> {
+        let Some(peer) = self.upstream_info.as_deref() else {
+            return HashMap::new();
+        };
+        let ids = ids
+            .map(str::to_owned)
+            .collect::<std::collections::BTreeSet<_>>();
+        // 同一页重复账号只读取一次摘要，单个账号不存在或读取失败不阻断历史记录
+        futures::stream::iter(ids)
+            .map(|id: String| async move {
+                let account_id = ProviderAccountId::new(id.clone()).ok()?;
+                let upstream = peer.read_summary(&account_id).await.ok()??.upstream?;
+                Some((id, upstream.discovered && upstream.observed_at.is_some()))
+            })
+            .buffer_unordered(8)
+            .filter_map(|value| async move { value })
+            .collect()
+            .await
+    }
+
     async fn enrich_dashboard_quotas(&self, accounts: &mut [DashboardAccountUsage]) {
         if accounts.is_empty() {
             return;
@@ -976,8 +1019,22 @@ impl DefaultObservabilityService {
 
     /// 补充当前套餐展示名称，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_records(&self, records: &mut [crate::model::observability::UsageListRecord]) {
+    async fn enrich_list_records(
+        &self,
+        records: &mut [crate::model::observability::UsageListRecord],
+    ) {
+        let peers = self
+            .current_upstream_peers(
+                records
+                    .iter()
+                    .filter_map(|record| record.provider_account_ref.as_deref()),
+            )
+            .await;
         for record in records {
+            record.provider_account_upstream_peer = record
+                .provider_account_ref
+                .as_ref()
+                .and_then(|id| peers.get(id).copied());
             record.provider_account_plan_type_display =
                 record.provider_kind.as_deref().and_then(|provider| {
                     self.providers
@@ -1071,7 +1128,7 @@ pub(super) fn health_timeline_at(
         .map(|index| {
             (
                 start + Duration::minutes(HEALTH_TIMELINE_SLOT_MINUTES * index),
-                HealthWindow::default(),
+                RequestHealth::default(),
             )
         })
         .collect::<Vec<_>>();
@@ -1097,7 +1154,7 @@ pub(super) fn health_timeline_at(
     let totals = buckets
         .iter()
         .filter(|(bucket_start, _)| *bucket_start <= current_slot)
-        .fold(HealthWindow::default(), |mut totals, (_, bucket)| {
+        .fold(RequestHealth::default(), |mut totals, (_, bucket)| {
             totals.add_window(*bucket);
             totals
         });
@@ -1161,11 +1218,9 @@ fn trend(
         }
     }
     let average_latency_ms = average(metrics.latency_sum_ms, metrics.latency_count);
-    let service_failure_count = service_failure_count(&metrics);
-    let success_rate = ratio(
-        metrics.success_count,
-        HealthWindow::from_metrics(&metrics).eligible_requests(),
-    );
+    let health = RequestHealth::from_metrics(&metrics);
+    let error_count = health.non_success_requests();
+    let success_rate = health.success_ratio();
     let cache_hit_request_rate = ratio(
         metrics.cache_hit_request_count,
         metrics.cache_eligible_request_count,
@@ -1194,7 +1249,7 @@ fn trend(
             output_tokens: metrics.output_tokens,
             cached_input_tokens: metrics.cached_input_tokens,
             total_tokens: metrics.total_tokens,
-            service_failure_count,
+            error_count,
             average_latency_ms,
             max_latency_ms: metrics.max_latency_ms,
             min_latency_ms: metrics.min_latency_ms,
@@ -1213,11 +1268,11 @@ fn trend(
 }
 
 fn trend_point(point: RequestMetricPoint) -> TrendPoint {
-    let service_failure_count = service_failure_count(&point.metrics);
+    let health = RequestHealth::from_metrics(&point.metrics);
     TrendPoint {
         bucket_start: point.bucket_start,
         granularity: point.granularity,
-        service_failure_count,
+        error_count: health.non_success_requests(),
         average_latency_ms: average(point.metrics.latency_sum_ms, point.metrics.latency_count),
         average_first_token_latency_ms: average(
             point.metrics.first_token_latency_sum_ms,
@@ -1231,10 +1286,7 @@ fn trend_point(point: RequestMetricPoint) -> TrendPoint {
             point.metrics.cache_hit_request_count,
             point.metrics.cache_eligible_request_count,
         ),
-        success_rate: ratio(
-            point.metrics.success_count,
-            HealthWindow::from_metrics(&point.metrics).eligible_requests(),
-        ),
+        success_rate: health.success_ratio(),
         metrics: point.metrics,
         cost_coverage: point.cost_coverage,
         costs: point.costs,
@@ -1318,57 +1370,7 @@ fn rate_or_zero(numerator: u64, denominator: u64) -> f64 {
     ratio(numerator, denominator).unwrap_or(0.0)
 }
 
-#[derive(Debug, Clone, Copy, Default)]
-struct HealthWindow {
-    success_requests: u64,
-    failed_requests: u64,
-    cancelled_requests: u64,
-    incomplete_requests: u64,
-    caller_error_requests: u64,
-}
-
-impl HealthWindow {
-    fn from_metrics(metrics: &RequestMetrics) -> Self {
-        Self {
-            success_requests: metrics.success_count,
-            failed_requests: service_failure_count(metrics),
-            cancelled_requests: metrics.cancelled_count,
-            incomplete_requests: metrics.incomplete_count,
-            caller_error_requests: metrics.caller_error_count,
-        }
-    }
-
-    // 未完成保留交付终态，但上游失败、超时和进程中断都不能视为服务成功
-    fn non_success_requests(self) -> u64 {
-        self.failed_requests
-            .saturating_add(self.incomplete_requests)
-    }
-
-    fn eligible_requests(self) -> u64 {
-        self.success_requests
-            .saturating_add(self.non_success_requests())
-    }
-
-    fn add_metrics(&mut self, metrics: &RequestMetrics) {
-        self.add_window(Self::from_metrics(metrics));
-    }
-
-    fn add_window(&mut self, other: Self) {
-        self.success_requests = self.success_requests.saturating_add(other.success_requests);
-        self.failed_requests = self.failed_requests.saturating_add(other.failed_requests);
-        self.cancelled_requests = self
-            .cancelled_requests
-            .saturating_add(other.cancelled_requests);
-        self.incomplete_requests = self
-            .incomplete_requests
-            .saturating_add(other.incomplete_requests);
-        self.caller_error_requests = self
-            .caller_error_requests
-            .saturating_add(other.caller_error_requests);
-    }
-}
-
-fn health_status(bucket: HealthWindow, is_future: bool) -> HealthStatus {
+fn health_status(bucket: RequestHealth, is_future: bool) -> HealthStatus {
     let eligible_requests = bucket.eligible_requests();
     if is_future {
         HealthStatus::Future
@@ -1389,14 +1391,6 @@ fn health_status(bucket: HealthWindow, is_future: bool) -> HealthStatus {
     }
 }
 
-fn health_reliability(bucket: HealthWindow) -> Option<f64> {
-    let eligible_requests = bucket.eligible_requests();
-    (eligible_requests > 0)
-        .then(|| bucket.success_requests as f64 / eligible_requests as f64 * 100.0)
-}
-
-fn service_failure_count(metrics: &RequestMetrics) -> u64 {
-    metrics
-        .failure_count
-        .saturating_sub(metrics.caller_error_count)
+fn health_reliability(bucket: RequestHealth) -> Option<f64> {
+    bucket.success_rate()
 }

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

@@ -117,6 +117,7 @@ impl PeerLinkService for DefaultPeerLinkService {
                 .budget
                 .limits
                 .access(key.budget.daily_used_usd, key.budget.weekly_used_usd),
+            key_limits: key.limits,
             budget: key.budget,
             budget_observed_at,
             pool: None,

backend/crates/gateway-admin/src/use_case/peer_link/upstream/cache.rs

@@ -56,7 +56,7 @@ impl PeerInfoService {
                             checked_at: now,
                             scheduling: None,
                             summary: None,
-                            unsupported: false,
+                            stored_failure: None,
                         },
                     ));
                 }
@@ -92,19 +92,19 @@ impl PeerInfoService {
                     (
                         connection.clone(),
                         cached.and_then(|cached| cached.summary.clone()),
-                        cached.is_some_and(|cached| cached.unsupported),
+                        cached.and_then(|cached| cached.stored_failure),
                     )
                 })
                 .collect::<Vec<_>>()
         };
         Ok(summaries
             .into_iter()
-            .map(|(connection, peer, unsupported)| {
+            .map(|(connection, peer, stored_failure)| {
                 let quota = Self::project_peer(
                     &connection,
                     peer.as_deref(),
-                    self.last_error(&connection)
-                        .or(unsupported.then_some(UpstreamInfoFailure::Unsupported)),
+                    stored_failure,
+                    self.last_error(&connection),
                     now,
                 );
                 (connection, quota)
@@ -135,8 +135,8 @@ impl PeerInfoService {
             checked_at: now,
             scheduling,
             summary,
-            unsupported: observation
-                .is_some_and(|value| snapshot::is_unsupported(&value.quota, connection)),
+            stored_failure: observation
+                .and_then(|value| snapshot::stored_failure(&value.quota, connection)),
         };
         let previous = self
             .observations
@@ -151,6 +151,9 @@ impl PeerInfoService {
             .read()
             .unwrap_or_else(std::sync::PoisonError::into_inner)
             .get(&connection.account_id)
-            .is_some_and(|cached| cached.connection == *connection && cached.unsupported)
+            .is_some_and(|cached| {
+                cached.connection == *connection
+                    && cached.stored_failure == Some(UpstreamInfoFailure::Unsupported)
+            })
     }
 }

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

@@ -25,6 +25,7 @@ use gateway_core::{
     error::StoreError,
     task::{WorkerContribution, WorkerDefinitionError},
 };
+pub(crate) use projection::account_capacity;
 use service::PeerInfoService;
 
 /// 组合根独立注册公共互联 Worker，不属于任何具体 Provider 的任务集合
@@ -62,6 +63,24 @@ pub fn initialize(
 
 #[async_trait::async_trait]
 impl PeerUpstreamService for PeerInfoService {
+    fn observed_concurrency_limit(
+        &self,
+        version: &gateway_core::account::QuotaObservationVersion,
+        now: std::time::SystemTime,
+    ) -> Option<gateway_core::account::AccountConcurrencyLimit> {
+        let observations = self
+            .observations
+            .read()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        let cached = observations.get(&version.account_id)?;
+        if cached.observed_at != Some(version.observed_at)
+            || cached.connection.credential_revision != version.credential_revision
+        {
+            return None;
+        }
+        cached.scheduling.as_ref()?.concurrency_limit(now)
+    }
+
     async fn account_changed(&self, id: &ProviderAccountId) -> Result<(), StoreError> {
         PeerInfoService::account_changed(self, id).await
     }

backend/crates/gateway-admin/src/use_case/peer_link/upstream/projection.rs

@@ -16,10 +16,31 @@ use gateway_protocol::peer::{PeerComponentStatus, PeerLink};
 
 use super::{PeerInfoService, quota, snapshot};
 
+pub(crate) fn account_capacity(
+    account: &crate::model::accounts::AccountRecord,
+    mut capacity: crate::model::accounts::AccountCapacity,
+    quota: &ProviderQuota,
+) -> crate::model::accounts::AccountCapacity {
+    if account.concurrency_limit.is_none()
+        && let Some(info) = &quota.upstream
+        && !info.stale
+        && info
+            .observed_at
+            .is_some_and(|at| snapshot::fresh_at(at.into(), SystemTime::now()))
+        && let Some(limit) = info
+            .max_concurrency
+            .and_then(gateway_core::account::AccountConcurrencyLimit::from_key_limit)
+    {
+        capacity.total_slots = Some(u64::from(limit.get()));
+    }
+    capacity
+}
+
 impl PeerInfoService {
     pub(super) fn project_peer(
         connection: &UpstreamConnection,
         peer: Option<&PeerLink>,
+        stored_failure: Option<UpstreamInfoFailure>,
         last_error: Option<UpstreamInfoFailure>,
         now: SystemTime,
     ) -> ProviderQuota {
@@ -29,12 +50,17 @@ impl PeerInfoService {
         let stale = peer.as_ref().is_none_or(|peer| {
             !snapshot::component_fresh(Some(&peer.observed_at), Some(&peer.expires_at), now)
         });
+        let limits = peer.and_then(|peer| peer.key_limits);
         let info = ProviderUpstreamInfo {
-            discovered: peer.is_some(),
+            discovered: peer.is_some() || stored_failure == Some(UpstreamInfoFailure::Unauthorized),
             observed_at,
             stale,
             connection_revision: connection.revision.clone(),
-            last_error: last_error.map(|error| error.as_str().to_owned()),
+            last_error: last_error
+                .or(stored_failure)
+                .map(|error| error.as_str().to_owned()),
+            max_concurrency: limits.and_then(|limits| limits.max_concurrency),
+            requests_per_minute: limits.and_then(|limits| limits.requests_per_minute),
             pool: peer
                 .as_ref()
                 .and_then(|peer| peer.pool.as_ref())

backend/crates/gateway-admin/src/use_case/peer_link/upstream/refresh.rs

@@ -105,8 +105,8 @@ impl PeerInfoService {
         {
             let error = state.last_error;
             drop(state);
-            if let Some(error) = error.filter(|error| *error != UpstreamInfoFailure::Unsupported) {
-                return Err(refresh_error(error));
+            if let Some(error) = error.and_then(refresh_error) {
+                return Err(error);
             }
             return self
                 .read_quota(id)
@@ -130,26 +130,39 @@ impl PeerInfoService {
         let failure = result.as_ref().err().copied();
         let delay = match failure {
             None => Duration::from_secs(240 + stable_jitter(id.as_str())),
-            Some(UpstreamInfoFailure::Unauthorized) => Duration::from_secs(1800),
+            Some(UpstreamInfoFailure::Unauthorized | UpstreamInfoFailure::SharingDisabled) => {
+                Duration::from_secs(1800)
+            }
             Some(_) => Duration::from_secs(30),
         }
         .max(retry_after.unwrap_or_default());
         state.next_attempt = Instant::now() + delay;
-        state.manual_after = Instant::now()
-            + (if failure.is_some_and(|error| error != UpstreamInfoFailure::Unsupported) {
-                delay
-            } else {
-                Duration::from_secs(15)
-            })
-            .max(retry_after.unwrap_or_default());
+        // 管理员修复授权后可主动复核，不继承自动重试的长退避，仍遵守上游限流
+        state.manual_after =
+            Instant::now() + Duration::from_secs(15).max(retry_after.unwrap_or_default());
         state.last_error = failure;
         let document = match result {
             Ok(document) => Some(document),
-            // 空观测清除已撤销内容，并用共有观察时间阻止更早请求重新写回
-            Err(UpstreamInfoFailure::Unauthorized) => {
-                Some(OpaqueProviderData::new(Default::default()))
-            }
             Err(UpstreamInfoFailure::Unsupported) => Some(snapshot::unsupported(&connection)),
+            Err(error @ UpstreamInfoFailure::SharingDisabled) => {
+                Some(snapshot::unavailable(&connection, error))
+            }
+            Err(error @ UpstreamInfoFailure::Unauthorized) => {
+                let discovered = self
+                    .read_summary(id)
+                    .await
+                    .map_err(store_error)?
+                    .and_then(|quota| quota.upstream)
+                    .is_some_and(|info| {
+                        info.connection_revision == connection.revision && info.discovered
+                    });
+                // 首次探测失败不能证明对方是互联节点；已确认的连接只留下无共享内容的识别记录
+                Some(if discovered {
+                    snapshot::unavailable(&connection, error)
+                } else {
+                    OpaqueProviderData::new(Default::default())
+                })
+            }
             Err(_) => None,
         };
         if let Some(document) = document {
@@ -190,8 +203,8 @@ impl PeerInfoService {
         }
         drop(state);
         // 不支持协议是正常发现结果，管理端保留分类，后台不重复报警
-        if let Some(error) = failure.filter(|error| *error != UpstreamInfoFailure::Unsupported) {
-            return Err(refresh_error(error));
+        if let Some(error) = failure.and_then(refresh_error) {
+            return Err(error);
         }
         self.read_quota(id)
             .await
@@ -206,12 +219,13 @@ fn stable_jitter(id: &str) -> u64 {
     }) % 60
 }
 
-fn refresh_error(error: UpstreamInfoFailure) -> ProviderAdminError {
-    ProviderAdminError::new(ProviderAdminErrorKind::BadGateway).with_public_message(match error {
+fn refresh_error(error: UpstreamInfoFailure) -> Option<ProviderAdminError> {
+    let message = match error {
         UpstreamInfoFailure::Unauthorized => "上游未授权读取互联信息",
-        UpstreamInfoFailure::Unsupported => "上游不支持互联信息查询",
+        UpstreamInfoFailure::Unsupported | UpstreamInfoFailure::SharingDisabled => return None,
         UpstreamInfoFailure::RateLimited => "上游互联查询已限流",
         UpstreamInfoFailure::InvalidResponse => "上游互联响应无效",
         UpstreamInfoFailure::Unavailable => "上游互联服务暂不可用",
-    })
+    };
+    Some(ProviderAdminError::new(ProviderAdminErrorKind::BadGateway).with_public_message(message))
 }

backend/crates/gateway-admin/src/use_case/peer_link/upstream/scheduling.rs

@@ -63,6 +63,7 @@ struct ModelObservation {
 
 pub(super) struct SchedulingObservation {
     validity: Validity,
+    concurrency_limit: Option<gateway_core::account::AccountConcurrencyLimit>,
     exhausted_budgets: Vec<Validity>,
     models: HashMap<String, Option<ModelObservation>>,
 }
@@ -166,43 +167,52 @@ impl SchedulingObservation {
         }
         Some(Self {
             validity,
+            concurrency_limit: peer
+                .key_limits
+                .and_then(|limits| limits.max_concurrency)
+                .and_then(gateway_core::account::AccountConcurrencyLimit::from_key_limit),
             exhausted_budgets,
             models,
         })
     }
 
     pub(super) fn fresh(&self, now: SystemTime) -> bool {
-        self.validity.fresh(now)
-            && now
-                .duration_since(self.validity.observed_at)
-                .unwrap_or_default()
-                <= snapshot::FRESH_FOR
+        self.validity.fresh(now) && snapshot::fresh_at(self.validity.observed_at, now)
     }
 
-    pub(super) fn signal(&self, model: &str, now: SystemTime) -> Option<UpstreamSchedulingSignal> {
+    pub(super) fn concurrency_limit(
+        &self,
+        now: SystemTime,
+    ) -> Option<gateway_core::account::AccountConcurrencyLimit> {
+        self.concurrency_limit.filter(|_| self.fresh(now))
+    }
+
+    pub(super) fn signal(
+        &self,
+        model: Option<&str>,
+        now: SystemTime,
+    ) -> Option<UpstreamSchedulingSignal> {
         if !self.fresh(now) {
             return None;
         }
-        if self
+        let budget_exhausted = self
             .exhausted_budgets
             .iter()
-            .any(|validity| validity.fresh(now))
-        {
-            return Some(UpstreamSchedulingSignal {
-                exhausted: true,
-                remaining_percent: None,
-            });
-        }
-        let model = self.models.get(model)?.as_ref()?;
-        if !model.validity.fresh(now) {
+            .any(|validity| validity.fresh(now));
+        let model = model
+            .and_then(|id| self.models.get(id)?.as_ref())
+            .filter(|model| model.validity.fresh(now));
+        if !budget_exhausted && model.is_none() && self.concurrency_limit.is_none() {
             return None;
         }
         Some(UpstreamSchedulingSignal {
-            exhausted: model.exhausted,
-            remaining_percent: model
-                .account
-                .as_ref()
-                .and_then(|account| account.remaining_percent(now)),
+            concurrency_limit: self.concurrency_limit,
+            exhausted: budget_exhausted || model.is_some_and(|model| model.exhausted),
+            remaining_percent: if budget_exhausted {
+                None
+            } else {
+                model.and_then(|model| model.account.as_ref()?.remaining_percent(now))
+            },
         })
     }
 }

backend/crates/gateway-admin/src/use_case/peer_link/upstream/service.rs

@@ -34,7 +34,7 @@ pub(super) struct CachedObservation {
     pub checked_at: SystemTime,
     pub scheduling: Option<Arc<SchedulingObservation>>,
     pub summary: Option<Arc<PeerLink>>,
-    pub unsupported: bool,
+    pub stored_failure: Option<UpstreamInfoFailure>,
 }
 
 pub(crate) struct PeerInfoService {
@@ -172,17 +172,17 @@ impl PeerInfoService {
         let peer = observation
             .as_ref()
             .and_then(|value| snapshot::decode(&value.quota));
-        let unsupported = observation
+        let stored_failure = observation
             .as_ref()
-            .is_some_and(|value| snapshot::is_unsupported(&value.quota, &connection));
+            .and_then(|value| snapshot::stored_failure(&value.quota, &connection));
         if self.current_connection(id).await?.as_ref() != Some(&connection) {
             return Ok(None);
         }
         Ok(Some(Self::project_peer(
             &connection,
             peer.as_ref(),
-            self.last_error(&connection)
-                .or(unsupported.then_some(UpstreamInfoFailure::Unsupported)),
+            stored_failure,
+            self.last_error(&connection),
             SystemTime::now(),
         )))
     }
@@ -285,7 +285,7 @@ impl UpstreamInfoSource for PeerInfoService {
     fn signal(
         &self,
         account: &ProviderAccount,
-        model: &str,
+        model: Option<&str>,
         now: SystemTime,
     ) -> Option<UpstreamSchedulingSignal> {
         if !account.enabled() {

backend/crates/gateway-admin/src/use_case/peer_link/upstream/snapshot.rs

@@ -28,17 +28,42 @@ pub(super) fn unsupported(connection: &UpstreamConnection) -> OpaqueProviderData
     ]))
 }
 
-pub(super) fn is_unsupported(data: &OpaqueProviderData, connection: &UpstreamConnection) -> bool {
+// 授权撤销或共享关闭后只保存连接与失败原因，丢弃全部共享数据
+pub(super) fn unavailable(
+    connection: &UpstreamConnection,
+    reason: UpstreamInfoFailure,
+) -> OpaqueProviderData {
+    OpaqueProviderData::new(serde_json::Map::from_iter([
+        ("object".into(), "cpr.peer.unavailable".into()),
+        ("schema_version".into(), 1.into()),
+        (
+            "connection_revision".into(),
+            connection.revision.clone().into(),
+        ),
+        ("reason".into(), reason.as_str().into()),
+    ]))
+}
+
+pub(super) fn stored_failure(
+    data: &OpaqueProviderData,
+    connection: &UpstreamConnection,
+) -> Option<UpstreamInfoFailure> {
     let fields = data.expose_to_provider();
-    fields.get("object").and_then(serde_json::Value::as_str) == Some("cpr.peer.unsupported")
-        && fields
-            .get("schema_version")
-            .and_then(serde_json::Value::as_u64)
-            == Some(1)
-        && fields
-            .get("connection_revision")
-            .and_then(serde_json::Value::as_str)
-            == Some(connection.revision.as_str())
+    if fields.get("schema_version")?.as_u64()? != 1
+        || fields.get("connection_revision")?.as_str()? != connection.revision
+    {
+        return None;
+    }
+    match fields.get("object")?.as_str()? {
+        "cpr.peer.unsupported" => Some(UpstreamInfoFailure::Unsupported),
+        "cpr.peer.unavailable" => match fields.get("reason")?.as_str()? {
+            "unauthorized" => Some(UpstreamInfoFailure::Unauthorized),
+            "sharing_disabled" => Some(UpstreamInfoFailure::SharingDisabled),
+            "unsupported" => Some(UpstreamInfoFailure::Unsupported),
+            _ => None,
+        },
+        _ => None,
+    }
 }
 
 pub(super) fn timestamp(value: &str) -> Option<SystemTime> {
@@ -54,10 +79,12 @@ pub(super) fn datetime(value: &str) -> Option<DateTime<Utc>> {
 }
 
 pub(super) fn fresh(observed: &str, now: SystemTime) -> bool {
-    timestamp(observed).is_some_and(|observed| {
-        observed <= now + Duration::from_secs(60)
-            && now.duration_since(observed).unwrap_or_default() <= FRESH_FOR
-    })
+    timestamp(observed).is_some_and(|observed| fresh_at(observed, now))
+}
+
+pub(super) fn fresh_at(observed: SystemTime, now: SystemTime) -> bool {
+    observed <= now + Duration::from_secs(60)
+        && now.duration_since(observed).unwrap_or_default() <= FRESH_FOR
 }
 
 pub(super) fn component_fresh(
@@ -127,6 +154,9 @@ pub(super) fn parse(
     }
     // 未授权能力不能借同名数据块越过逐层公开边界
     let disclosed = |capability| peer.capabilities.iter().any(|value| value == capability);
+    if !disclosed("key_limits") {
+        peer.key_limits = None;
+    }
     if !disclosed("key_usage") {
         peer.usage = None;
     }

backend/crates/gateway-admin/src/use_case/plugins/artifacts.rs

@@ -217,7 +217,7 @@ impl PluginsService {
                 artifact_sha256: metadata.sha256.clone(),
                 enabled: !configuration_required && compatible,
                 configuration: configuration.clone(),
-                secrets: None,
+                secrets: Default::default(),
                 bindings: bindings.clone(),
             };
             match self.configure_instance(None, input, context).await {

backend/crates/gateway-admin/src/use_case/plugins/instances/configuration.rs

@@ -28,17 +28,16 @@ pub(super) fn same_creation_request(
     existing: &PluginInstance,
     input: &ConfigurePluginInstance,
 ) -> bool {
-    let same_secrets = input
+    let mut requested_secrets = input
         .secrets
-        .as_ref()
-        .map_or(existing.secrets.is_empty(), |secrets| {
-            secrets.len() == existing.secrets.len()
-                && secrets.iter().all(|(key, value)| {
-                    existing
-                        .secrets
-                        .get(key)
-                        .is_some_and(|current| current.expose_secret() == value.expose_secret())
-                })
+        .iter()
+        .filter_map(|(key, value)| value.as_ref().map(|value| (key, value)));
+    let same_secrets = requested_secrets.clone().count() == existing.secrets.len()
+        && requested_secrets.all(|(key, value)| {
+            existing
+                .secrets
+                .get(key)
+                .is_some_and(|current| current.expose_secret() == value.expose_secret())
         });
     existing.name == input.name.trim()
         && existing.artifact_sha256 == input.artifact_sha256

backend/crates/gateway-admin/src/use_case/plugins/instances/mutations.rs

@@ -158,7 +158,6 @@ impl PluginsService {
         }
         let saved = if let Some(previous) = &existing
             && previous.artifact_sha256 != input.artifact_sha256
-            && input.secrets.is_none()
         {
             self.store
                 .load_version_configuration(&previous.id, &input.artifact_sha256)
@@ -167,6 +166,21 @@ impl PluginsService {
         } else {
             None
         };
+        let mut secrets = saved.map(|saved| saved.secrets).unwrap_or_else(|| {
+            existing
+                .as_ref()
+                .map_or_else(Default::default, |instance| instance.secrets.clone())
+        });
+        for (name, value) in input.secrets {
+            match value {
+                Some(value) => {
+                    secrets.insert(name, value);
+                }
+                None => {
+                    secrets.remove(&name);
+                }
+            }
+        }
         let instance = PluginInstance {
             id: existing.as_ref().map_or_else(
                 || {
@@ -182,14 +196,7 @@ impl PluginsService {
             enabled: input.enabled,
             trusted_process: true,
             configuration: input.configuration,
-            secrets: input
-                .secrets
-                .or_else(|| saved.map(|saved| saved.secrets))
-                .unwrap_or_else(|| {
-                    existing
-                        .as_ref()
-                        .map_or_else(Default::default, |instance| instance.secrets.clone())
-                }),
+            secrets,
             bindings: input.bindings,
             revision: candidate_revision,
         };

backend/crates/gateway-admin/src/use_case/plugins/official.rs

@@ -366,6 +366,7 @@ fn target_environment_matches(target: &str) -> bool {
     match target {
         "x86_64-unknown-linux-gnu" | "aarch64-unknown-linux-gnu" => cfg!(target_env = "gnu"),
         "aarch64-apple-darwin" => cfg!(target_os = "macos"),
+        "x86_64-pc-windows-msvc" | "aarch64-pc-windows-msvc" => cfg!(target_env = "msvc"),
         _ => false,
     }
 }
@@ -392,4 +393,18 @@ const SUPPORTED_PLATFORMS: &[Platform] = &[
         runtime_os: "macos",
         runtime_architecture: "aarch64",
     },
+    Platform {
+        release_os: "windows",
+        release_architecture: "amd64",
+        target: "x86_64-pc-windows-msvc",
+        runtime_os: "windows",
+        runtime_architecture: "x86_64",
+    },
+    Platform {
+        release_os: "windows",
+        release_architecture: "arm64",
+        target: "aarch64-pc-windows-msvc",
+        runtime_os: "windows",
+        runtime_architecture: "aarch64",
+    },
 ];

backend/crates/gateway-admin/src/use_case/plugins/versions.rs

@@ -69,7 +69,7 @@ impl PluginsService {
             artifact_sha256: input.artifact_sha256,
             enabled: existing.enabled,
             configuration: saved.configuration,
-            secrets: Some(saved.secrets),
+            secrets: Default::default(),
             bindings: saved.bindings,
         };
         // 沿用同一份快照的 CAS 和状态迁移流程，不能在检查目标后重新读取并覆盖并发配置
@@ -202,7 +202,7 @@ impl PluginsService {
             artifact_sha256: input.artifact_sha256,
             enabled: existing.enabled,
             configuration: configuration.configuration,
-            secrets: Some(configuration.secrets),
+            secrets: Default::default(),
             bindings: configuration.bindings,
         };
         // 同一次读取的 CAS 覆盖草稿计算、准备与提交，不能覆盖并发设置

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

@@ -361,9 +361,10 @@ impl ProxiesService for DefaultProxiesService {
         proxy: Option<&OutboundProxy>,
         detect_location: bool,
     ) -> Result<ProxyTestResult, AdminError> {
-        let _permit = self.test_slots.try_acquire().map_err(|_| {
-            AdminError::new(AdminErrorKind::RateLimited, "代理测试繁忙，请稍后重试")
-        })?;
+        let _permit = self
+            .test_slots
+            .try_acquire()
+            .map_err(|_| AdminError::new(AdminErrorKind::RateLimited, "代理测试已达并发上限"))?;
         Ok(self.probe.test(proxy, detect_location).await)
     }
 
@@ -374,9 +375,10 @@ impl ProxiesService for DefaultProxiesService {
         detect_location: bool,
         context: &MutationContext,
     ) -> Result<ProxyRecord, AdminError> {
-        let _permit = self.test_slots.try_acquire().map_err(|_| {
-            AdminError::new(AdminErrorKind::RateLimited, "代理测试繁忙，请稍后重试")
-        })?;
+        let _permit = self
+            .test_slots
+            .try_acquire()
+            .map_err(|_| AdminError::new(AdminErrorKind::RateLimited, "代理测试已达并发上限"))?;
         let record = self
             .store
             .get(id)

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

@@ -252,7 +252,7 @@ impl SettingsService for DefaultSettingsService {
                     .is_some_and(|models| models.contains_key(model))
             })
         {
-            return Err(AdminError::invalid("内置价目不能删除，仅支持人工覆盖"));
+            return Err(AdminError::invalid("内置价目只能覆盖，不能删除"));
         }
         let defaults = gateway_core::metering::merge_pricing(catalog.defaults, &catalog.synced);
         let defaults = defaults.get(&command.provider);
@@ -332,24 +332,35 @@ impl SettingsService for DefaultSettingsService {
         configuration: Option<&gateway_core::account::OpaqueProviderData>,
     ) -> Result<gateway_core::account::OpaqueProviderData, AdminError> {
         let profile_provider = self.profile_provider(provider)?;
-        let global;
-        let (configuration, source) = if let Some(configuration) = configuration {
-            (configuration, "override")
+        let independent = configuration.filter(|key| {
+            gateway_core::settings::request_profiles::inherited_fields(key).is_none()
+        });
+        let preview = if let Some(key) = independent {
+            profile_provider.preview_key_client_profile(key, None)
         } else {
-            global = self
+            let global = self
                 .load()
                 .await?
                 .client_profile(provider)
                 .cloned()
                 .or_else(|| profile_provider.default_client_profile())
                 .ok_or_else(|| AdminError::internal("通用客户端身份尚未初始化"))?;
-            (&global, "global")
-        };
-        let mut preview = profile_provider
-            .preview_client_profile(configuration)
-            .map_err(|error| super::map_provider_error(error, "client profile"))?
-            .into_inner();
-        preview.insert("source".to_owned(), serde_json::Value::from(source));
+            if let Some(key) = configuration {
+                profile_provider.preview_key_client_profile(key, Some(&global))
+            } else {
+                profile_provider.preview_client_profile(&global)
+            }
+        }
+        .map_err(|error| super::map_provider_error(error, "client profile"))?;
+        let mut preview = preview.into_inner();
+        preview.insert(
+            "source".to_owned(),
+            serde_json::Value::from(if independent.is_some() {
+                "override"
+            } else {
+                "global"
+            }),
+        );
         Ok(gateway_core::account::OpaqueProviderData::new(preview))
     }
 
@@ -419,7 +430,7 @@ impl SettingsService for DefaultSettingsService {
                     crate::ports::store::AdminStoreErrorKind::Conflict
                         | crate::ports::store::AdminStoreErrorKind::StaleRevision
                 ) {
-                    AdminError::conflict("运行设置已被其他调用修改，请重新读取并确认后提交")
+                    AdminError::conflict("运行设置已变更，请刷新核对后提交")
                 } else {
                     map_store_error(error, "runtime settings")
                 }

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

@@ -15,6 +15,11 @@ use std::sync::Arc;
 
 #[async_trait]
 pub trait UsageDataService: Send + Sync {
+    async fn open_read(
+        &self,
+        query: UsageReadQuery,
+        cancellation: gateway_core::lifecycle::CancellationToken,
+    ) -> UsageDataResult<Box<dyn UsageReadSession>>;
     async fn list_aggregates(
         &self,
         request: ListUsageAggregates,
@@ -58,6 +63,21 @@ impl DefaultUsageDataService {
 
 #[async_trait]
 impl UsageDataService for DefaultUsageDataService {
+    async fn open_read(
+        &self,
+        query: UsageReadQuery,
+        cancellation: gateway_core::lifecycle::CancellationToken,
+    ) -> UsageDataResult<Box<dyn UsageReadSession>> {
+        let filter = query.filter();
+        validation::query(&filter.records, None, None)?;
+        if let Some(group) = &filter.routing_group_ref {
+            validation::text(group, 128)?;
+        }
+        if !(1..=USAGE_READ_MAX_BATCH_ROWS).contains(&query.batch_size()) {
+            return Err(UsageDataError::invalid("读取批次条数应为 1 到 1024"));
+        }
+        self.store.open_read(query, cancellation).await
+    }
     async fn list_aggregates(
         &self,
         request: ListUsageAggregates,

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

@@ -7,7 +7,6 @@ use gateway_core::account::OpaqueProviderData;
 
 use gateway_admin::model::{
     PageSize, Revision,
-    accounts::AccountUsage,
     auth::LoginCommand,
     client_keys::ClientKeyPageSize,
     observability::{DecimalAmount, RequestOutcome, TimeRange},
@@ -146,57 +145,6 @@ fn representative_quota_should_prefer_account_wide_window_over_model_specific_wi
     assert_eq!(quota.representative_used_percent(), Some(5.0));
 }
 
-#[test]
-fn usage_window_should_not_use_daily_rolling_usage_for_weekly_statistics() {
-    let usage = AccountUsage {
-        account_id: "acct_xai".to_owned(),
-        request_count: 5,
-        success_count: 5,
-        input_tokens: Some(100),
-        output_tokens: Some(20),
-        cached_input_tokens: Some(80),
-        cache_write_input_tokens: Some(0),
-        reasoning_output_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 {
-        upstream: None,
-        credits: None,
-        plan_type: None,
-        observed_at: None,
-        refresh_token_expires_at: None,
-        windows: vec![ProviderQuotaWindow {
-            upstream: None,
-            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),
-            provider_data: None,
-        }],
-        limit_reached: false,
-        provider_data: None,
-    };
-
-    assert_eq!(quota.usage_window(), None);
-}
-
 #[test]
 fn exhausted_quota_should_project_full_usage_to_only_the_representative_window() {
     let mut quota = ProviderQuota {

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

@@ -65,6 +65,36 @@ fn usage_window_should_not_fallback_to_short_daily_or_incomplete_windows() {
     assert_eq!(quota.usage_window(), None);
 }
 
+#[test]
+fn usage_window_should_preserve_provider_rolling_daily_statistics() {
+    let mut rolling = usage_window("rolling-day", "shortTerm", 86_400);
+    rolling.reset_at = None;
+    rolling.used_percent = None;
+    let mut quota = usage_quota(vec![rolling.clone()]);
+    assert_eq!(
+        selected_usage_window(&quota),
+        Some(("rolling-day", AccountUsagePeriod::Daily))
+    );
+
+    quota.limit_reached = true;
+    quota.apply_limit_reached_display();
+    assert_eq!(
+        selected_usage_window(&quota),
+        Some(("rolling-day", AccountUsagePeriod::Daily))
+    );
+
+    quota
+        .windows
+        .push(usage_window("week", "shortTerm", 7 * 86_400));
+    assert_eq!(
+        selected_usage_window(&quota),
+        Some(("week", AccountUsagePeriod::Weekly))
+    );
+
+    rolling.local_usage_attribution = QuotaLocalUsageAttribution::Unavailable;
+    assert_eq!(usage_quota(vec![rolling]).usage_window(), None);
+}
+
 #[test]
 fn usage_window_should_preserve_provider_order_for_equal_periods() {
     let quota = usage_quota(vec![

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

@@ -162,7 +162,10 @@ fn source_selection_keeps_provider_order_with_the_maximum_window_count() {
 fn short_or_model_specific_windows_are_not_account_capacity() {
     let mut model = window("model", 7);
     model.local_usage_attribution = QuotaLocalUsageAttribution::Unavailable;
-    for item in forecast(&quota(vec![window("day", 1), model])) {
+    let mut rolling = window("rolling-day", 1);
+    rolling.reset_at = None;
+    rolling.used_percent = None;
+    for item in forecast(&quota(vec![window("day", 1), rolling, model])) {
         assert!(item.source.is_none());
         assert!(item.unavailable_reason.is_some());
         assert!(item.estimated_tokens.is_none());

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

@@ -373,6 +373,7 @@ fn group_record() -> AccountGroupRecord {
 
 fn member(account_id: &str, total_slots: u64) -> AccountGroupMemberFact {
     AccountGroupMemberFact {
+        inherited_version: None,
         group_id: group_id(),
         account_id: account_id.to_owned(),
         status: AccountStatusFacts {

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

@@ -2,6 +2,7 @@
 
 mod reset_credit_automation;
 
+use gateway_core::engine::probe::AccountProbeTarget;
 use std::{
     collections::BTreeMap,
     sync::{Arc, Mutex},
@@ -1335,7 +1336,9 @@ async fn connection_test_should_probe_unavailable_account() {
     let events = services
         .accounts()
         .test_connection(
-            ProviderAccountId::new("acct_test").expect("account ID"),
+            AccountProbeTarget::ConnectionTest(
+                ProviderAccountId::new("acct_test").expect("account ID"),
+            ),
             gateway_core::routing::UpstreamModelId::new("grok-4.5").expect("model"),
         )
         .await
@@ -1372,7 +1375,9 @@ async fn connection_test_rate_limited_probe_returns_provider_failure() {
     let events = services
         .accounts()
         .test_connection(
-            ProviderAccountId::new("acct_test").expect("account ID"),
+            AccountProbeTarget::ConnectionTest(
+                ProviderAccountId::new("acct_test").expect("account ID"),
+            ),
             gateway_core::routing::UpstreamModelId::new("grok-4.5").expect("model"),
         )
         .await
@@ -1405,7 +1410,9 @@ async fn connection_test_should_preserve_disabled_account_status() {
     let events = services
         .accounts()
         .test_connection(
-            ProviderAccountId::new("acct_test").expect("account ID"),
+            AccountProbeTarget::ConnectionTest(
+                ProviderAccountId::new("acct_test").expect("account ID"),
+            ),
             gateway_core::routing::UpstreamModelId::new("grok-4.5").expect("model"),
         )
         .await
@@ -2686,12 +2693,15 @@ async fn peer_account_usage_should_follow_budget_windows_without_borrowing_pool_
     for longest in [86_400, 604_800] {
         let provider = FakeProviderAdmin::new("openai", events());
         let mut account = account_record("openai");
+        account.concurrency_limit = None;
         account.authentication_kind = "api_key".to_owned();
         account.created_at = Utc::now() - TimeDelta::days(60);
         let store = FakeAccountStore::with_account(account, events());
         let reset_at = Utc::now() + TimeDelta::hours(1);
         let mut quota = empty_quota();
         quota.upstream = Some(ProviderUpstreamInfo {
+            max_concurrency: Some(7),
+            requests_per_minute: Some(60),
             discovered: true,
             observed_at: Some(Utc::now()),
             stale: false,
@@ -2762,6 +2772,8 @@ async fn peer_account_usage_should_follow_budget_windows_without_borrowing_pool_
             page.items[0].usage.as_ref().unwrap().total_tokens,
             Some(1_234)
         );
+        assert_eq!(page.items[0].capacity.total_slots, Some(7));
+        assert_eq!(page.items[0].account.concurrency_limit, None);
         let queries = store.quota_window_queries();
         assert_eq!(queries.len(), window_usage.len());
         for (query, expected) in queries.iter().zip(&window_usage) {

backend/crates/gateway-admin/tests/use_case/credentials/peer.rs

@@ -143,7 +143,7 @@ impl UpstreamInfoSource for PendingPeer {
     fn signal(
         &self,
         _: &ProviderAccount,
-        _: &str,
+        _: Option<&str>,
         _: std::time::SystemTime,
     ) -> Option<UpstreamSchedulingSignal> {
         None
@@ -152,6 +152,14 @@ impl UpstreamInfoSource for PendingPeer {
 
 #[async_trait]
 impl PeerUpstreamService for PendingPeer {
+    fn observed_concurrency_limit(
+        &self,
+        _: &gateway_core::account::QuotaObservationVersion,
+        _: std::time::SystemTime,
+    ) -> Option<gateway_core::account::AccountConcurrencyLimit> {
+        None
+    }
+
     async fn account_changed(&self, id: &ProviderAccountId) -> Result<(), StoreError> {
         self.changed.lock().unwrap().push(id.as_str().into());
         Ok(())

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

@@ -1,5 +1,6 @@
 //! 账号保护恢复编排：到期探测、快照参数与失败顺延
 
+use gateway_core::engine::probe::AccountProbeTarget;
 use std::collections::BTreeMap;
 use std::sync::{Arc, Mutex};
 
@@ -242,6 +243,10 @@ impl AccountProbe for FailingProbe {
         request: AccountProbeRequest,
         _: Option<Arc<gateway_core::routing::RuntimeSnapshot>>,
     ) -> futures::future::BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
+        assert!(matches!(
+            request.target,
+            AccountProbeTarget::FreezeRecovery(_)
+        ));
         assert_eq!(request.upstream_model.as_str(), "snapshot-model");
         Box::pin(async {
             Err(AccountProbeError::new(

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

@@ -364,21 +364,26 @@ async fn health_views_should_include_incomplete_and_keep_final_outcomes_separate
     let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
     let services = observability_services(store.clone()).await;
     let fixtures = [
-        (162, 0, 2, 0, 0, 98.780_487_804_878_05),
-        (297, 0, 2, 5, 0, 99.331_103_678_929_76),
-        (467, 1, 5, 0, 0, 98.731_501_057_082_45),
-        (95, 2, 3, 4, 1, 95.0),
-        (100, 0, 0, 0, 0, 100.0),
+        (162, 0, 2, 0, 0, 0, Some(98.780_487_804_878_05)),
+        (297, 0, 2, 5, 0, 0, Some(99.331_103_678_929_76)),
+        (467, 1, 5, 0, 0, 0, Some(98.731_501_057_082_45)),
+        (95, 2, 3, 4, 1, 7, Some(95.0)),
+        (100, 0, 0, 0, 0, 0, Some(100.0)),
+        (0, 0, 0, 0, 0, 0, None),
+        (0, 0, 0, 4, 3, 2, None),
+        (0, 1, 2, 0, 0, 0, Some(0.0)),
     ];
 
-    for (index, (success, failed, incomplete, cancelled, caller_error, expected_percent)) in
-        fixtures.into_iter().enumerate()
+    for (
+        index,
+        (success, failed, incomplete, cancelled, caller_error, running, expected_percent),
+    ) in fixtures.into_iter().enumerate()
     {
         let range = observation_range(
             now + Duration::seconds(i64::try_from(index).expect("fixture index fits i64") * 2),
         );
         let metrics = RequestMetrics {
-            request_count: success + failed + incomplete + cancelled + caller_error,
+            request_count: success + failed + incomplete + cancelled + caller_error + running,
             success_count: success,
             failure_count: failed + caller_error,
             incomplete_count: incomplete,
@@ -399,6 +404,27 @@ async fn health_views_should_include_incomplete_and_keep_final_outcomes_separate
             providers: Vec::new(),
         });
 
+        let mut item = diagnostic(
+            "model",
+            success + failed + incomplete + cancelled + caller_error + running,
+        );
+        item.success_count = success;
+        item.failure_count = failed + caller_error;
+        item.incomplete_count = incomplete;
+        item.cancelled_count = cancelled;
+        item.caller_error_count = caller_error;
+        store.replace_diagnostics(DiagnosticsObservation {
+            analytics: Default::default(),
+            total_request_count: item.request_count,
+            items: vec![item],
+        });
+        let diagnostics = services
+            .observability()
+            .diagnostics(range, UsageFilter::default(), DiagnosticDimension::Model)
+            .await
+            .unwrap();
+        assert_eq!(diagnostics.items[0].error_count, failed + incomplete);
+
         let dashboard = services
             .observability()
             .dashboard_summary(range, TrendKind::Usage)
@@ -410,23 +436,12 @@ async fn health_views_should_include_incomplete_and_keep_final_outcomes_separate
             .iter()
             .find(|point| point.bucket_start == current_slot)
             .expect("current health slot");
-        assert_eq!(point.status, HealthStatus::Stable);
+        assert_eq!(dashboard.trend.summary.error_count, failed + incomplete);
+        assert_eq!(dashboard.trend.points[0].error_count, failed + incomplete);
         assert_eq!(point.failed_requests, failed);
         assert_eq!(point.incomplete_requests, incomplete);
         assert_eq!(point.cancelled_requests, cancelled);
         assert_eq!(point.caller_error_requests, caller_error);
-        for reliability in [timeline.reliability_percent, point.reliability_percent] {
-            assert!((reliability.expect("health reliability") - expected_percent).abs() < 1e-10);
-        }
-        for success_rate in [
-            dashboard.trend.summary.success_rate,
-            dashboard.trend.points[0].success_rate,
-        ] {
-            assert!(
-                (success_rate.expect("trend success rate") * 100.0 - expected_percent).abs()
-                    < 1e-10
-            );
-        }
 
         let insights = services
             .observability()
@@ -435,11 +450,31 @@ async fn health_views_should_include_incomplete_and_keep_final_outcomes_separate
             .expect("usage insights");
         assert_eq!(insights.health.failed_requests, failed);
         assert_eq!(insights.health.incomplete_requests, incomplete);
-        assert!((insights.health.success_rate * 100.0 - expected_percent).abs() < 1e-10);
-        assert!(
-            (insights.health.points[0].error_rate * 100.0 - (100.0 - expected_percent)).abs()
-                < 1e-10
-        );
+        for actual in [
+            timeline.reliability_percent,
+            point.reliability_percent,
+            dashboard
+                .trend
+                .summary
+                .success_rate
+                .map(|rate| rate * 100.0),
+            dashboard.trend.points[0]
+                .success_rate
+                .map(|rate| rate * 100.0),
+            insights.health.success_rate.map(|rate| rate * 100.0),
+            insights.health.points[0]
+                .error_rate
+                .map(|rate| (1.0 - rate) * 100.0),
+            diagnostics.items[0]
+                .error_rate
+                .map(|rate| (1.0 - rate) * 100.0),
+        ] {
+            match (actual, expected_percent) {
+                (Some(actual), Some(expected)) => assert!((actual - expected).abs() < 1e-10),
+                (None, None) => {}
+                _ => panic!("unexpected rate: {actual:?}, expected {expected_percent:?}"),
+            }
+        }
     }
 }
 
@@ -448,6 +483,7 @@ 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 {
+        inherited_versions: Vec::new(),
         inherited_accounts: 2,
         overridden_slots: 5,
         used_slots: Some(2),
@@ -476,6 +512,7 @@ async fn dashboard_capacity_distinguishes_unlimited_inheritance_finite_overrides
         let now = Utc::now();
         let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
         store.replace_runtime_slots(Some(DashboardRuntimeSlots {
+            inherited_versions: Vec::new(),
             inherited_accounts,
             overridden_slots,
             used_slots: Some(2),
@@ -676,7 +713,7 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
 
     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.success_rate, Some(0.75));
     assert_eq!(insights.health.completion_rate, 1.0);
     assert_eq!(insights.granularity, Granularity::FifteenMinutes);
     assert_eq!(
@@ -831,7 +868,7 @@ async fn diagnostics_should_preserve_request_order_when_a_small_sample_fails() {
     assert_eq!(result.items[1].key, "single_failure");
     assert_eq!(result.items[0].error_count, 0);
     assert_eq!(result.items[1].error_count, 1);
-    assert_eq!(result.items[1].error_rate, 1.0);
+    assert_eq!(result.items[1].error_rate, Some(1.0));
 }
 
 #[tokio::test]
@@ -1212,7 +1249,7 @@ impl ObservabilityStore for FixtureObservabilityStore {
             range: query.range,
             totals: Default::default(),
             provider_accounts: AccountPoolMetrics::default(),
-            runtime_slots: *self.runtime_slots.lock().expect("runtime slots"),
+            runtime_slots: self.runtime_slots.lock().expect("runtime slots").clone(),
             trend: self.trend.lock().expect("trend").clone(),
             account_usage: self.account_usage.lock().expect("account usage").clone(),
             recent_requests: Vec::new(),
@@ -1479,8 +1516,14 @@ fn total_record(
     now: DateTime<Utc>,
 ) -> UsageListRecord {
     UsageListRecord {
+        provider_account_upstream_peer: None,
         error_code: None,
         error_message: None,
+        error_kind: None,
+        websocket_close_code: None,
+        continuation_unavailable_reason: None,
+        upstream_connection_exit_reason: None,
+        recovered: false,
         client_status_code: None,
         outcome: gateway_admin::model::observability::RequestOutcome::Succeeded,
         client_api_key_name: Some("Production".to_owned()),
@@ -1557,7 +1600,9 @@ 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,
+        cancelled_count: 0,
+        incomplete_count: 0,
+        caller_error_count: 0,
         retry_count: 0,
         retried_request_count: 0,
         account_provider_kind: None,

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

@@ -241,7 +241,7 @@ async fn discovery_uses_provider_capabilities_and_publishes_neutral_signals() {
         let reader = UpstreamInfoReader::default();
         assert!(
             reader
-                .signal(&initial_accounts[0], "model", SystemTime::now())
+                .signal(&initial_accounts[0], Some("model"), SystemTime::now())
                 .is_none()
         );
         let source = bundle.scheduling_source();
@@ -273,7 +273,11 @@ async fn discovery_uses_provider_capabilities_and_publishes_neutral_signals() {
         );
         for account in &initial_accounts[..2] {
             if Some(account.provider().as_str()) == failed_provider {
-                assert!(reader.signal(account, "model", SystemTime::now()).is_none());
+                assert!(
+                    reader
+                        .signal(account, Some("model"), SystemTime::now())
+                        .is_none()
+                );
                 continue;
             }
             let observed = bundle
@@ -288,21 +292,21 @@ async fn discovery_uses_provider_capabilities_and_publishes_neutral_signals() {
             );
             assert!(
                 reader
-                    .signal(account, "model", SystemTime::now())
+                    .signal(account, Some("model"), SystemTime::now())
                     .unwrap()
                     .exhausted
             );
         }
         assert!(
             reader
-                .signal(&initial_accounts[2], "model", SystemTime::now())
+                .signal(&initial_accounts[2], Some("model"), SystemTime::now())
                 .is_none()
         );
         drop(worker);
         drop(bundle);
         assert!(
             reader
-                .signal(&initial_accounts[0], "model", SystemTime::now())
+                .signal(&initial_accounts[0], Some("model"), SystemTime::now())
                 .is_none()
         );
     }
@@ -332,7 +336,7 @@ async fn account_edits_preserve_observation_and_refresh_budget_until_connection_
     assert!(
         bundle
             .scheduling_source()
-            .signal(&edited, "model", SystemTime::now())
+            .signal(&edited, Some("model"), SystemTime::now())
             .is_some()
     );
     let after = service.refresh_quota(edited.id()).await.unwrap();
@@ -347,7 +351,7 @@ async fn account_edits_preserve_observation_and_refresh_budget_until_connection_
     assert!(
         bundle
             .scheduling_source()
-            .signal(&reconnected, "model", SystemTime::now())
+            .signal(&reconnected, Some("model"), SystemTime::now())
             .is_none()
     );
     service.refresh_quota(reconnected.id()).await.unwrap();
@@ -392,7 +396,7 @@ impl PeerTransport for TestTransport {
             .push(account.id().as_str().to_owned());
         let now = Utc::now();
         Ok(serde_json::to_vec(&serde_json::json!({
-            "object":"cpr.peer", "schema_version":2,
+            "object":"cpr.peer", "schema_version":3,
             "observed_at":now.to_rfc3339(),
             "expires_at":(now + chrono::Duration::minutes(5)).to_rfc3339(),
             "capabilities":["key_usage"],

backend/crates/gateway-admin/tests/use_case/peer_link/upstream/refresh.rs

@@ -175,6 +175,191 @@ async fn uncertain_discovery_failures_retry_without_becoming_unsupported() {
     }
 }
 
+#[tokio::test(start_paused = true)]
+async fn known_peer_identity_changes_only_on_definitive_detection() {
+    for failure in [
+        UpstreamInfoFailure::Unauthorized,
+        UpstreamInfoFailure::Unsupported,
+        UpstreamInfoFailure::SharingDisabled,
+        UpstreamInfoFailure::Unavailable,
+        UpstreamInfoFailure::RateLimited,
+        UpstreamInfoFailure::InvalidResponse,
+    ] {
+        let (bundle, accounts, transport, id) = fixture(failure);
+        *transport.failure.lock().unwrap() = None;
+        let before = bundle.service().refresh_quota(&id).await.unwrap();
+        assert!(!before.windows.is_empty());
+        tokio::time::advance(Duration::from_secs(15)).await;
+        *transport.failure.lock().unwrap() = Some(failure.into());
+        let result = bundle.service().refresh_quota(&id).await;
+        let clears_identity = matches!(
+            failure,
+            UpstreamInfoFailure::Unsupported | UpstreamInfoFailure::SharingDisabled
+        );
+        assert_eq!(result.is_ok(), clears_identity);
+        let clears_data = clears_identity || failure == UpstreamInfoFailure::Unauthorized;
+        let quota = bundle.service().read_quota(&id).await.unwrap().unwrap();
+        let info = quota.upstream.as_ref().unwrap();
+        assert_eq!(info.discovered, !clears_identity);
+        assert_eq!(info.last_error.as_deref(), Some(failure.as_str()));
+        assert_eq!(quota.windows.is_empty(), clears_data);
+        assert_eq!(info.observed_at.is_none(), clears_data);
+        assert_eq!(
+            bundle
+                .service()
+                .read_summary(&id)
+                .await
+                .unwrap()
+                .unwrap()
+                .upstream,
+            quota.upstream
+        );
+        let account = accounts.accounts.lock().unwrap()[0].clone();
+        assert_eq!(
+            bundle
+                .scheduling_source()
+                .signal(&account, Some("model"), SystemTime::now())
+                .is_none(),
+            clears_data
+        );
+
+        if failure == UpstreamInfoFailure::Unsupported {
+            // 已运行 v3.40.0 的节点可能持有这种不支持记录，读取时应直接显示为普通 API Key
+            accounts.records.lock().unwrap().get_mut(&id).unwrap().quota =
+                serde_json::from_value(serde_json::json!({
+                    "object": "cpr.peer.unavailable",
+                    "schema_version": 1,
+                    "connection_revision": info.connection_revision,
+                    "reason": "unsupported",
+                }))
+                .unwrap();
+        }
+        drop(bundle);
+        let restarted = initialize(accounts, transport);
+        let restored = restarted.service().read_quota(&id).await.unwrap().unwrap();
+        assert_eq!(
+            restored.upstream.as_ref().unwrap().discovered,
+            !clears_identity
+        );
+        assert_eq!(restored.windows.is_empty(), clears_data);
+        if clears_data {
+            assert_eq!(
+                restored.upstream.as_ref().unwrap().last_error.as_deref(),
+                Some(failure.as_str())
+            );
+        }
+        assert_eq!(
+            restarted
+                .service()
+                .read_summary(&id)
+                .await
+                .unwrap()
+                .unwrap()
+                .upstream,
+            restored.upstream
+        );
+    }
+}
+
+#[tokio::test(start_paused = true)]
+async fn peer_detection_after_revocation_is_scoped_to_the_connection() {
+    for failure in [
+        UpstreamInfoFailure::Unauthorized,
+        UpstreamInfoFailure::Unsupported,
+    ] {
+        let (bundle, accounts, transport, id) = fixture(failure);
+        *transport.failure.lock().unwrap() = None;
+        bundle.service().refresh_quota(&id).await.unwrap();
+        tokio::time::advance(Duration::from_secs(15)).await;
+        *transport.failure.lock().unwrap() = Some(failure.into());
+        let _result = bundle.service().refresh_quota(&id).await;
+        let initial = accounts.accounts.lock().unwrap()[0].clone();
+        let edited = initial.clone().with_notes(Some("保留连接身份".into()));
+        *accounts.accounts.lock().unwrap() = vec![edited.clone()];
+        bundle.service().account_changed(&id).await.unwrap();
+        assert_eq!(
+            bundle
+                .service()
+                .read_summary(&id)
+                .await
+                .unwrap()
+                .unwrap()
+                .upstream
+                .unwrap()
+                .discovered,
+            failure == UpstreamInfoFailure::Unauthorized
+        );
+
+        // 地址和密钥修改推进凭据版本，出口变化则改变同一版本的连接身份
+        for replacement in [
+            edited.with_outbound_proxy(Some(
+                OutboundProxy::parse("http://other.invalid:8080").unwrap(),
+            )),
+            ProviderAccount::new(
+                id.clone(),
+                initial.provider().clone(),
+                "替换连接".into(),
+                None,
+                "peer_test".into(),
+                CredentialRevision::new(2).unwrap(),
+                None,
+            )
+            .with_account_facts(
+                true,
+                CredentialState::Ready,
+                QuotaState::unknown(),
+                None,
+                None,
+            ),
+        ] {
+            *accounts.accounts.lock().unwrap() = vec![replacement];
+            bundle.service().account_changed(&id).await.unwrap();
+            let detail = bundle.service().read_quota(&id).await.unwrap().unwrap();
+            assert!(!detail.upstream.as_ref().unwrap().discovered);
+            assert!(detail.upstream.as_ref().unwrap().last_error.is_none());
+            assert_eq!(
+                bundle
+                    .service()
+                    .read_summary(&id)
+                    .await
+                    .unwrap()
+                    .unwrap()
+                    .upstream,
+                detail.upstream
+            );
+        }
+    }
+}
+
+#[tokio::test(start_paused = true)]
+async fn manual_rediscovery_does_not_wait_for_authorization_backoff_but_respects_retry_after() {
+    for retry_after in [None, Some(Duration::from_secs(90))] {
+        let (mut bundle, _, transport, id) = fixture(UpstreamInfoFailure::Unauthorized);
+        *transport.failure.lock().unwrap() = None;
+        bundle.service().refresh_quota(&id).await.unwrap();
+        tokio::time::advance(Duration::from_secs(15)).await;
+        *transport.failure.lock().unwrap() = Some(PeerFetchFailure {
+            kind: UpstreamInfoFailure::Unauthorized,
+            retry_after,
+        });
+        assert!(bundle.service().refresh_quota(&id).await.is_err());
+        let worker = worker(&mut bundle);
+        *transport.failure.lock().unwrap() = None;
+        let delay = retry_after.unwrap_or(Duration::from_secs(15));
+        tokio::time::advance(delay - Duration::from_secs(1)).await;
+        assert!(bundle.service().refresh_quota(&id).await.is_err());
+        assert_eq!(transport.requests.load(Ordering::SeqCst), 2);
+        tokio::time::advance(Duration::from_secs(1)).await;
+        cycle(&worker).await;
+        assert_eq!(transport.requests.load(Ordering::SeqCst), 2);
+        let recovered = bundle.service().refresh_quota(&id).await.unwrap();
+        assert_eq!(transport.requests.load(Ordering::SeqCst), 3);
+        assert!(recovered.upstream.as_ref().unwrap().discovered);
+        assert!(recovered.upstream.as_ref().unwrap().last_error.is_none());
+        assert!(!recovered.windows.is_empty());
+    }
+}
+
 fn fixture(
     failure: UpstreamInfoFailure,
 ) -> (

backend/crates/gateway-admin/tests/use_case/plugins/instances/configuration.rs

@@ -0,0 +1,115 @@
+//! 实例敏感配置的逐字段更新、版本基准与提交隔离测试
+
+use super::*;
+use secrecy::ExposeSecret;
+
+fn secret_values(instance: &PluginInstance) -> serde_json::Value {
+    serde_json::Value::Object(
+        instance
+            .secrets
+            .iter()
+            .map(|(name, value)| (name.clone(), json!(value.expose_secret())))
+            .collect(),
+    )
+}
+
+#[tokio::test]
+async fn secret_changes_apply_to_current_or_target_version_configuration() {
+    for (target, saved_version) in [
+        (OLD_ARTIFACT, false),
+        (NEW_ARTIFACT, false),
+        (NEW_ARTIFACT, true),
+    ] {
+        let token = if saved_version {
+            "saved-token"
+        } else {
+            "current-token"
+        };
+        let untouched = if saved_version {
+            "saved-value"
+        } else {
+            "current-value"
+        };
+        for (changes, expected) in [
+            (json!({}), json!({"token":token,"untouched":untouched})),
+            (
+                json!({"adminKey":"new-key"}),
+                json!({"token":token,"untouched":untouched,"adminKey":"new-key"}),
+            ),
+            (
+                json!({"token":"new-token"}),
+                json!({"token":"new-token","untouched":untouched}),
+            ),
+            (json!({"token":null}), json!({"untouched":untouched})),
+            (
+                json!({"token":null,"adminKey":"new-key","absent":null}),
+                json!({"untouched":untouched,"adminKey":"new-key"}),
+            ),
+        ] {
+            let fixture = LifecycleFixture::new(MigrationBehavior::Succeed);
+            {
+                let mut data = fixture.data.lock().unwrap();
+                data.snapshot.instances[0].secrets = BTreeMap::from([
+                    ("token".into(), "current-token".into()),
+                    ("untouched".into(), "current-value".into()),
+                ]);
+                if saved_version {
+                    data.history.get_mut(NEW_ARTIFACT).unwrap().secrets = BTreeMap::from([
+                        ("token".into(), "saved-token".into()),
+                        ("untouched".into(), "saved-value".into()),
+                    ]);
+                } else {
+                    data.history.clear();
+                }
+            }
+            let before = fixture.snapshot();
+            let mut request = input();
+            request.artifact_sha256 = target.into();
+            request.expected_revision = Some(10);
+            request.secrets = serde_json::from_value(changes).unwrap();
+            let result = service(fixture.clone(), Arc::new(Published::default()))
+                .configure_instance(Some(&before.instances[0].id), request, &context())
+                .await
+                .unwrap();
+            assert_eq!(secret_values(&result.instance), expected);
+            assert_eq!(secret_values(&fixture.snapshot().instances[0]), expected);
+        }
+    }
+}
+
+#[tokio::test]
+async fn failed_secret_changes_leave_saved_values_unchanged() {
+    for failure in ["stale", "preparation", "size"] {
+        let fixture = LifecycleFixture::new(MigrationBehavior::Succeed);
+        fixture.data.lock().unwrap().snapshot.instances[0].secrets =
+            BTreeMap::from([("token".into(), "saved-token".into())]);
+        let before = fixture.snapshot();
+        let mut request = input();
+        request.artifact_sha256 = OLD_ARTIFACT.into();
+        request.expected_revision = Some(if failure == "stale" { 9 } else { 10 });
+        request.secrets = BTreeMap::from([
+            ("token".into(), None),
+            (
+                "adminKey".into(),
+                Some(
+                    if failure == "size" {
+                        "x".repeat(8193)
+                    } else {
+                        "new-key".into()
+                    }
+                    .into(),
+                ),
+            ),
+        ]);
+        fixture.data.lock().unwrap().fail_preparation = failure == "preparation";
+        let result = service(fixture.clone(), Arc::new(Published::default()))
+            .configure_instance(Some(&before.instances[0].id), request, &context())
+            .await;
+        assert!(result.is_err(), "{failure} must reject the update");
+        assert_eq!(
+            secret_values(&fixture.snapshot().instances[0]),
+            secret_values(&before.instances[0])
+        );
+        assert!(fixture.data.lock().unwrap().saves.is_empty());
+    }
+}

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

@@ -49,6 +49,7 @@ use serde_json::json;
 
 use super::TestPluginPorts;
 
+mod configuration;
 mod queries;
 
 const OLD_ARTIFACT: &str = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
@@ -759,7 +760,7 @@ fn input() -> ConfigurePluginInstance {
         artifact_sha256: NEW_ARTIFACT.into(),
         enabled: true,
         configuration: json!({}),
-        secrets: None,
+        secrets: Default::default(),
         bindings: vec![],
     }
 }
@@ -942,6 +943,8 @@ async fn configuration_retry_reuses_creation_id_and_rejects_changed_draft() {
         // 此用例验证创建重试，使用不需要私有状态迁移的固定版本
         value.artifact_sha256 = OLD_ARTIFACT.into();
         value.enabled = false;
+        value.secrets =
+            serde_json::from_value(json!({"token": "saved-token", "absent": null})).unwrap();
         value
     };
     let created = service
@@ -955,6 +958,12 @@ async fn configuration_retry_reuses_creation_id_and_rejects_changed_draft() {
     assert_eq!(created.instance.id, creation_id);
     assert_eq!(retried.instance.id, creation_id);
     assert_eq!(fixture.snapshot().instances.len(), 2);
+    use secrecy::ExposeSecret as _;
+    assert_eq!(
+        retried.instance.secrets["token"].expose_secret(),
+        "saved-token"
+    );
+    assert!(!retried.instance.secrets.contains_key("absent"));
     let before = fixture.snapshot().config_revision;
     let mut changed = request();
     changed.name = "changed draft".into();
@@ -965,6 +974,17 @@ async fn configuration_retry_reuses_creation_id_and_rejects_changed_draft() {
         .unwrap();
     assert_eq!(error.kind(), AdminErrorKind::Conflict);
     assert_eq!(fixture.snapshot().config_revision, before);
+    let mut changed = request();
+    changed
+        .secrets
+        .insert("token".into(), Some("different-token".into()));
+    let error = service
+        .configure_instance(None, changed, &context())
+        .await
+        .err()
+        .unwrap();
+    assert_eq!(error.kind(), AdminErrorKind::Conflict);
+    assert_eq!(fixture.snapshot().config_revision, before);
 }
 
 #[tokio::test]
@@ -1435,23 +1455,6 @@ async fn version_switch_preparation_failure_preserves_current_and_saved_settings
     );
 }
 
-#[tokio::test]
-async fn version_edit_preserves_the_target_versions_secrets_when_omitted() {
-    use secrecy::ExposeSecret as _;
-    let fixture = LifecycleFixture::new(MigrationBehavior::Succeed);
-    let before = fixture.snapshot();
-    let mut request = input();
-    request.secrets = None;
-    let result = service(fixture, Arc::new(Published::default()))
-        .configure_instance(Some(&before.instances[0].id), request, &context())
-        .await
-        .unwrap();
-    assert_eq!(
-        result.instance.secrets["token"].expose_secret(),
-        "old-version-secret"
-    );
-}
-
 #[tokio::test]
 async fn rollback_requires_a_saved_configuration_instead_of_reusing_incompatible_current_settings()
 {

backend/crates/gateway-admin/tests/use_case/plugins/official.rs

@@ -446,6 +446,8 @@ fn release_platform() -> (&'static str, &'static str, &'static str) {
         ("linux", "x86_64") => ("linux", "amd64", "x86_64-unknown-linux-gnu"),
         ("linux", "aarch64") => ("linux", "arm64", "aarch64-unknown-linux-gnu"),
         ("macos", "aarch64") => ("darwin", "arm64", "aarch64-apple-darwin"),
+        ("windows", "x86_64") => ("windows", "amd64", "x86_64-pc-windows-msvc"),
+        ("windows", "aarch64") => ("windows", "arm64", "aarch64-pc-windows-msvc"),
         platform => panic!("unsupported test platform: {platform:?}"),
     }
 }

backend/crates/gateway-admin/tests/use_case/plugins/usage_data.rs

@@ -3,6 +3,14 @@ use super::TestPluginPorts;
 use gateway_admin::{model::usage_data::*, ports::usage_data::*};
 #[async_trait::async_trait]
 impl UsageDataStore for TestPluginPorts {
+    async fn open_read(
+        &self,
+        _: UsageReadQuery,
+        _: gateway_core::lifecycle::CancellationToken,
+    ) -> UsageDataResult<Box<dyn UsageReadSession>> {
+        Err(UsageDataError::unavailable("test usage reader unavailable"))
+    }
+
     async fn get_record(&self, _: GetUsageRecord) -> UsageDataResult<UsageRecord> {
         unreachable!("unexpected usage call")
     }

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

@@ -64,6 +64,7 @@ fn sdk_wire_types_match_host_contracts() {
         "value.rs",
         "record.rs",
         "query.rs",
+        "read.rs",
         "aggregate.rs",
         "pricing.rs",
         "error.rs",

backend/crates/gateway-api/Cargo.toml

@@ -12,7 +12,7 @@ name = "main"
 path = "tests/main.rs"
 
 [dependencies]
-axum = { version = "0.8.9", default-features = false, features = ["json", "multipart", "query", "ws"] }
+axum = { version = "0.8.9", default-features = false, features = ["json", "matched-path", "multipart", "query", "ws"] }
 base64 = "0.23.0"
 bytes = "1.11.1"
 chrono = { version = "0.4.45", features = ["serde"] }

backend/crates/gateway-api/src/admin/accounts/handlers.rs

@@ -1,5 +1,7 @@
 //! 账号管理路由与 HTTP handler 编排
 
+use gateway_core::engine::probe::AccountProbeTarget;
+
 use crate::auth::SessionState;
 
 use super::*;
@@ -626,7 +628,10 @@ where
     let stream = state
         .admin_services()
         .accounts()
-        .test_connection(account_id, upstream_model)
+        .test_connection(
+            AccountProbeTarget::ConnectionTest(account_id),
+            upstream_model,
+        )
         .await
         .map_err(map_service_error)?
         .map(move |event| {

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

@@ -193,6 +193,7 @@ fn quota_forecast_view(
         period: match forecast.period {
             AccountUsagePeriod::Weekly => "weekly",
             AccountUsagePeriod::Monthly => "monthly",
+            AccountUsagePeriod::Daily => "daily",
         },
         target_days: forecast.target_seconds as f64 / 86_400.0,
         extrapolated: forecast.extrapolated,
@@ -389,6 +390,7 @@ pub(super) fn account_usage_view(
     };
     AccountUsageView {
         window_kind: match period {
+            Some(AccountUsagePeriod::Daily) => AccountUsageWindowKind::Daily,
             Some(AccountUsagePeriod::Weekly) => AccountUsageWindowKind::Weekly,
             Some(AccountUsagePeriod::Monthly) => AccountUsageWindowKind::Monthly,
             None => AccountUsageWindowKind::Quota,
@@ -453,20 +455,14 @@ pub(super) fn account_model_usage_view(
         .costs
         .iter()
         .find(|cost| cost.currency.eq_ignore_ascii_case("USD"));
+    let success_rate = usage.health.success_rate();
     ModelUsageView {
         model: usage.model,
         request_count: usage.request_count,
         request_count_display: format_number(usage.request_count),
-        success_rate: (usage.request_count > 0)
-            .then(|| usage.success_count as f64 * 100.0 / usage.request_count as f64),
-        success_rate_display: if usage.request_count == 0 {
-            "—".to_owned()
-        } else {
-            format!(
-                "{:.1}%",
-                usage.success_count as f64 * 100.0 / usage.request_count as f64
-            )
-        },
+        success_rate,
+        success_rate_display: success_rate
+            .map_or_else(|| "—".to_owned(), |rate| format!("{rate:.1}%")),
         input_tokens: usage.input_tokens,
         input_tokens_display: display_optional_tokens(usage.input_tokens),
         output_tokens: usage.output_tokens,
@@ -493,9 +489,11 @@ pub(super) fn account_model_usage_view(
         partial_cost_count: u64::from(cost_estimate_status == "partial"),
         unknown_cost_count: usage.cost_coverage.unavailable_count,
         costs: usage.costs.iter().map(account_currency_cost_view).collect(),
-        last_used_at: time.rfc3339(&usage.last_used_at),
-        last_used_at_full_display: Some(time.datetime(&usage.last_used_at)),
-        last_used_at_display: time.relative(usage.last_used_at, now),
+        last_used_at: usage.last_used_at.map(|value| time.rfc3339(&value)),
+        last_used_at_full_display: usage.last_used_at.map(|value| time.datetime(&value)),
+        last_used_at_display: usage
+            .last_used_at
+            .map_or_else(|| "—".to_owned(), |value| time.relative(value, now)),
     }
 }
 

backend/crates/gateway-api/src/admin/accounts/upstream_info.rs

@@ -14,6 +14,8 @@ pub struct AccountUpstreamInfoView {
     pub stale: bool,
     pub connection_revision: String,
     pub last_error: Option<String>,
+    pub max_concurrency: Option<u64>,
+    pub requests_per_minute: Option<u64>,
     pub pool: Option<UpstreamPoolView>,
 }
 
@@ -78,6 +80,8 @@ pub(crate) fn view(
         stale: info.stale,
         connection_revision: info.connection_revision,
         last_error: info.last_error,
+        max_concurrency: info.max_concurrency,
+        requests_per_minute: info.requests_per_minute,
         pool: info.pool.map(|pool| UpstreamPoolView {
             account_count: pool.account_count,
             states: UpstreamPoolStatesView {

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

@@ -515,7 +515,7 @@ pub struct ModelUsageView {
     pub partial_cost_count: u64,
     pub unknown_cost_count: u64,
     pub costs: Vec<CurrencyCostView>,
-    pub last_used_at: String,
+    pub last_used_at: Option<String>,
     pub last_used_at_display: String,
     pub last_used_at_full_display: Option<String>,
 }

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

@@ -260,6 +260,11 @@ pub(crate) fn usage_list_record_view(
     UsageListRecordView {
         error_code: record.error_code,
         error_message: record.error_message,
+        error_kind: record.error_kind,
+        websocket_close_code: record.websocket_close_code,
+        continuation_unavailable_reason: record.continuation_unavailable_reason,
+        upstream_connection_exit_reason: record.upstream_connection_exit_reason,
+        recovered: record.recovered,
         logical_outcome: record.outcome.as_str().to_owned(),
         client_api_key_name: record.client_api_key_name,
         id: record.id,
@@ -271,6 +276,7 @@ pub(crate) fn usage_list_record_view(
         account_notes: record.provider_account_notes,
         account_plan_type: record.provider_account_plan_type,
         account_plan_type_display: record.provider_account_plan_type_display,
+        account_upstream_peer: record.provider_account_upstream_peer,
         route: record.endpoint,
         model,
         requested_model: record.requested_model_id,
@@ -356,6 +362,23 @@ pub(crate) fn usage_record_view(
         .or_else(|| record.requested_model_id.clone());
     let metadata = provider_metadata_fields(record.provider_metadata_json.as_deref());
     UsageRecordView {
+        upstream_error: record
+            .upstream_error
+            .map(|error| super::wire::UsageUpstreamErrorView {
+                code: error.code,
+                error_type: error.error_type,
+                message: error.message,
+                param: error.param,
+                close_reason: error.close_reason,
+                last_event_type: error.last_event_type,
+            }),
+        retry_after_ms: record.retry_after_ms,
+        error_code: record.provider_error_code,
+        error_kind: record.error_kind,
+        websocket_close_code: record.websocket_close_code,
+        continuation_unavailable_reason: record.continuation_unavailable_reason,
+        upstream_connection_exit_reason: record.upstream_connection_exit_reason,
+        recovered: record.recovered,
         id: record.id.clone(),
         request_id: record.id,
         client_api_key_id: Some(record.client_api_key_ref),
@@ -678,8 +701,8 @@ pub(crate) fn trend_point_view(
         cached_input_tokens_value: point.metrics.cached_input_tokens,
         cache_hit_rate_value: point.cached_token_rate,
         tokens_value: point.metrics.total_tokens,
-        errors: format_compact_number(point.service_failure_count),
-        errors_value: point.service_failure_count,
+        errors: format_compact_number(point.error_count),
+        errors_value: point.error_count,
         latency_value: point.average_latency_ms,
         success_rate: success_rate_value
             .map_or_else(|| "—".to_owned(), |value| format!("{value:.1}%")),
@@ -742,7 +765,7 @@ pub(crate) fn trend_summary_view(
         TrendKind::Errors => vec![
             TrendSummaryView {
                 metric: TrendMetric::Errors,
-                value: format_compact_number(summary.service_failure_count),
+                value: format_compact_number(summary.error_count),
                 ratio: None,
             },
             TrendSummaryView {
@@ -1351,6 +1374,7 @@ pub(crate) fn diagnostics_view(
                 request_count: item.request_count,
                 account_plan_type: item.account_plan_type,
                 account_plan_type_display: item.account_plan_type_display,
+                account_upstream_peer: item.account_upstream_peer,
                 success_count: item.success_count,
                 error_count: item.error_count,
                 error_rate: item.error_rate,

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

@@ -88,6 +88,11 @@ pub struct ImageBillingView {
 pub struct UsageListRecordView {
     pub error_code: Option<String>,
     pub error_message: Option<String>,
+    pub error_kind: Option<String>,
+    pub websocket_close_code: Option<u16>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub recovered: bool,
     pub logical_outcome: String,
     pub client_api_key_name: Option<String>,
     pub id: String,
@@ -99,6 +104,7 @@ pub struct UsageListRecordView {
     pub account_notes: Option<String>,
     pub account_plan_type: Option<String>,
     pub account_plan_type_display: Option<String>,
+    pub account_upstream_peer: Option<bool>,
     pub route: String,
     pub model: Option<String>,
     pub requested_model: Option<String>,
@@ -121,10 +127,30 @@ pub struct UsageListRecordView {
     pub user_agent: Option<String>,
 }
 
+/// 受控详情中的原始上游错误字段
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageUpstreamErrorView {
+    pub code: Option<String>,
+    pub error_type: Option<String>,
+    pub message: Option<String>,
+    pub param: Option<String>,
+    pub close_reason: Option<String>,
+    pub last_event_type: Option<String>,
+}
+
 /// 单条逻辑请求详情展示
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageRecordView {
+    pub upstream_error: Option<UsageUpstreamErrorView>,
+    pub retry_after_ms: Option<u64>,
+    pub error_code: Option<String>,
+    pub error_kind: Option<String>,
+    pub websocket_close_code: Option<u16>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub recovered: bool,
     pub id: String,
     pub request_id: String,
     pub client_api_key_id: Option<String>,
@@ -630,7 +656,7 @@ pub struct OverviewHealthPointView {
     pub cancelled_requests: u64,
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
-    pub error_rate: f64,
+    pub error_rate: Option<f64>,
 }
 
 /// 洞察健康摘要
@@ -643,7 +669,7 @@ pub struct OverviewHealthView {
     pub cancelled_requests: u64,
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
-    pub success_rate: f64,
+    pub success_rate: Option<f64>,
     pub completion_rate: f64,
     pub request_change_rate: Option<f64>,
     pub success_rate_change: Option<f64>,
@@ -849,10 +875,11 @@ pub struct DiagnosticItemView {
     pub authentication_kind: Option<String>,
     pub account_plan_type: Option<String>,
     pub account_plan_type_display: Option<String>,
+    pub account_upstream_peer: Option<bool>,
     pub request_count: u64,
     pub success_count: u64,
     pub error_count: u64,
-    pub error_rate: f64,
+    pub error_rate: Option<f64>,
     pub request_share: f64,
     pub average_latency_ms: Option<u64>,
     pub latency_p95_ms: Option<u64>,

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

@@ -537,14 +537,10 @@ async fn probe<S>(
 where
     S: SessionState + Send + Sync,
 {
-    let proxy = request
-        .proxy_url
-        .0
-        .ok_or_else(|| AdminError::bad_request("代理 URL 不能为空"))?;
     let result = state
         .admin_services()
         .proxies()
-        .probe(Some(&proxy), request.detect_location)
+        .probe(request.proxy_url.0.as_ref(), request.detect_location)
         .await
         .map_err(map_error)?;
     Ok(AdminResponse::new(

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

@@ -9,6 +9,14 @@ use gateway_core::error::{GatewayError, GatewayErrorKind};
 use serde::Serialize;
 use serde_json::{Value, json};
 
+/// 认证边界提供的稳定拒绝原因，不携带认证输入
+#[derive(Clone)]
+pub(crate) struct AccessRejection(pub &'static str);
+
+/// 执行已交给 Core 观测，HTTP 入口只补充交付边界日志
+#[derive(Clone)]
+pub(crate) struct ExecutionObserved;
+
 /// OpenAI 风格的协议错误 JSON
 #[derive(Debug, Clone, PartialEq, Eq, Serialize)]
 pub struct ProtocolErrorBody {
@@ -107,6 +115,7 @@ pub fn gateway_error_response(error: &GatewayError) -> Response {
         error.client_error_code().unwrap_or(default_code),
     )
     .into_response();
+    response.extensions_mut().insert(error.clone());
     if let Some(delay) = error.retry_after()
         && let Ok(value) = HeaderValue::from_str(
             &delay

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

@@ -0,0 +1,218 @@
+//! 数据面 HTTP 入口诊断；执行前失败进入运维事件，不伪造模型请求或上游状态
+
+use std::{
+    pin::Pin,
+    sync::Arc,
+    task::{Context, Poll},
+};
+
+use axum::{
+    body::{Body, Bytes},
+    extract::{MatchedPath, Request, State},
+    http::StatusCode,
+    middleware::Next,
+    response::Response,
+};
+use gateway_core::diagnostics::{OperationalDiagnostics, OperationalFailure, TraceContext};
+use http_body::{Body as _, Frame, SizeHint};
+use serde_json::json;
+use tower_http::request_id::RequestId;
+
+use crate::client_error::{AccessRejection, ProtocolError, ProtocolErrorBody};
+
+pub(crate) async fn record_ingress(
+    State(diagnostics): State<Arc<dyn OperationalDiagnostics>>,
+    mut request: Request,
+    next: Next,
+) -> Response {
+    if request.uri().path() != "/v1" && !request.uri().path().starts_with("/v1/") {
+        return next.run(request).await;
+    }
+    let correlation_id = request
+        .extensions()
+        .get::<RequestId>()
+        .and_then(|id| id.header_value().to_str().ok())
+        .map(str::to_owned);
+    let endpoint = request
+        .extensions()
+        .get::<MatchedPath>()
+        .map(|path| path.as_str().to_owned());
+    let method = request.method().clone();
+    let dump = if tracing::enabled!(target: "request_dump", tracing::Level::INFO) {
+        let trace = TraceContext::new(correlation_id.as_deref().unwrap_or("ingress"));
+        trace.dump(
+            "ingress.request",
+            &serde_json::to_vec(&json!({
+                "method":method.as_str(), "uri":request.uri().to_string(),
+            }))
+            .unwrap_or_default(),
+        );
+        trace.headers(
+            "ingress.request.headers",
+            json!({}),
+            request
+                .headers()
+                .iter()
+                .map(|(name, value)| (name.as_str(), value.as_bytes())),
+        );
+        let body = std::mem::replace(request.body_mut(), Body::empty());
+        *request.body_mut() = Body::new(DumpBody::new(body, trace.clone(), "ingress.request.body"));
+        Some(trace)
+    } else {
+        None
+    };
+    let mut response = if endpoint.is_none() {
+        // 数据面未知路径不能落入 SPA fallback，否则会把协议错误伪装成 HTML 成功
+        crate::openai::error::protocol_error_response(
+            StatusCode::NOT_FOUND,
+            ProtocolErrorBody {
+                error: ProtocolError {
+                    kind: "invalid_request_error",
+                    code: "unknown_endpoint",
+                    message: "The requested API endpoint does not exist.".into(),
+                    param: None,
+                },
+            },
+        )
+    } else {
+        next.run(request).await
+    };
+    let protocol = response.extensions_mut().remove::<ProtocolErrorBody>();
+    let gateway = response
+        .extensions_mut()
+        .remove::<gateway_core::error::GatewayError>();
+    let access = response.extensions_mut().remove::<AccessRejection>();
+    let execution_observed = response
+        .extensions_mut()
+        .remove::<crate::client_error::ExecutionObserved>()
+        .is_some();
+    let status = response.status();
+    if status.is_client_error() || status.is_server_error() {
+        let code = access
+            .map(|error| error.0)
+            .or_else(|| protocol.as_ref().map(|body| body.error.code))
+            .or_else(|| gateway.as_ref().map(|error| error.kind().as_str()))
+            .unwrap_or(match status {
+                StatusCode::UNAUTHORIZED => "invalid_api_key",
+                StatusCode::METHOD_NOT_ALLOWED => "method_not_allowed",
+                StatusCode::NOT_FOUND => "not_found",
+                _ => "http_rejection",
+            });
+        // 未知参数名可由客户端任意构造，只保留 decoder 生成的已知参数路径
+        let parameter = protocol
+            .as_ref()
+            .filter(|body| body.error.code != "unknown_parameter")
+            .and_then(|body| body.error.param.as_deref())
+            .filter(|path| {
+                path.len() <= 256
+                    && path.bytes().all(|byte| {
+                        byte.is_ascii_alphanumeric() || matches!(byte, b'_' | b'.' | b'[' | b']')
+                    })
+            });
+        let endpoint = endpoint.as_deref().unwrap_or("/v1/<unmatched>");
+        let model_request_id = execution_observed
+            .then(|| {
+                response
+                    .headers()
+                    .get("x-gateway-request-id")
+                    .and_then(|id| id.to_str().ok())
+            })
+            .flatten();
+        tracing::info!(target: "request_trace", stage="ingress.rejected", status=status.as_u16(),
+            code, parameter, endpoint, model_request_id, method=method.as_str(), "Data-plane HTTP request rejected");
+        if !execution_observed {
+            let mut failure = OperationalFailure::new(
+                "api",
+                "http_ingress",
+                code,
+                json!({"method":method.as_str(), "endpoint":endpoint, "status":status.as_u16(),
+                    "code":code, "param":parameter})
+                .to_string(),
+            );
+            failure.correlation_id = correlation_id;
+            failure.details = gateway.as_ref().and_then(|error| error.error_details());
+            if diagnostics.record_failure(failure).await.is_err() {
+                tracing::warn!("HTTP ingress diagnostic could not be recorded");
+            }
+        }
+    }
+    if let Some(trace) = dump {
+        trace.dump(
+            "ingress.response",
+            &serde_json::to_vec(&json!({"status":status.as_u16()})).unwrap_or_default(),
+        );
+        trace.headers(
+            "ingress.response.headers",
+            json!({"status":status.as_u16()}),
+            response
+                .headers()
+                .iter()
+                .map(|(name, value)| (name.as_str(), value.as_bytes())),
+        );
+        let body = std::mem::replace(response.body_mut(), Body::empty());
+        *response.body_mut() = Body::new(DumpBody::new(body, trace, "ingress.response.body"));
+    }
+    response
+}
+
+struct DumpBody {
+    inner: Body,
+    trace: TraceContext,
+    stage: &'static str,
+    complete: bool,
+}
+
+impl DumpBody {
+    fn new(inner: Body, trace: TraceContext, stage: &'static str) -> Self {
+        let complete = inner.is_end_stream();
+        Self {
+            inner,
+            trace,
+            stage,
+            complete,
+        }
+    }
+}
+
+impl http_body::Body for DumpBody {
+    type Data = Bytes;
+    type Error = axum::Error;
+
+    fn poll_frame(
+        mut self: Pin<&mut Self>,
+        cx: &mut Context<'_>,
+    ) -> Poll<Option<Result<Frame<Bytes>, axum::Error>>> {
+        let result = Pin::new(&mut self.inner).poll_frame(cx);
+        if let Poll::Ready(Some(Ok(frame))) = &result
+            && let Some(bytes) = frame.data_ref()
+        {
+            self.trace.dump(self.stage, bytes);
+        }
+        if matches!(result, Poll::Ready(Some(Err(_)))) {
+            self.complete = false;
+        } else if matches!(result, Poll::Ready(None)) || self.inner.is_end_stream() {
+            self.complete = true;
+        }
+        result
+    }
+
+    fn is_end_stream(&self) -> bool {
+        self.inner.is_end_stream()
+    }
+    fn size_hint(&self) -> SizeHint {
+        self.inner.size_hint()
+    }
+}
+
+impl Drop for DumpBody {
+    fn drop(&mut self) {
+        // 不为诊断主动读取剩余正文；取消或未消费的请求必须明确标出转储不完整
+        self.trace.dump(
+            "ingress.body.finished",
+            &serde_json::to_vec(&json!({
+                "stage":self.stage, "complete":self.complete,
+            }))
+            .unwrap_or_default(),
+        );
+    }
+}

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

@@ -1,4 +1,4 @@
-//! `/healthz` 对 Core、Store 与 Host 关键 worker 健康事实的聚合
+//! 请求就绪检查与综合健康诊断
 
 use std::sync::{Arc, Mutex};
 use std::time::Duration;
@@ -67,22 +67,7 @@ impl HealthStatus {
                 ),
             })
             .collect();
-        // 逐个探针共享截止时间，保留已完成结果并指出具体超时组件
-        let deadline = tokio::time::Instant::now() + HEALTH_CHECK_TIMEOUT;
-        let checks = self.probes.iter().map(|probe| async move {
-            let (state, reason) = match tokio::time::timeout_at(deadline, probe.check()).await {
-                Ok(HealthState::Healthy) => return None,
-                Ok(HealthState::Degraded(reason)) => ("degraded", reason),
-                Ok(HealthState::Unhealthy(reason)) => ("unhealthy", reason),
-                Err(_) => ("timed_out", "health probe exceeded 2s deadline".to_owned()),
-            };
-            Some(HealthFailure {
-                component: format!("probe:{}", probe.name()),
-                state,
-                reason,
-            })
-        });
-        failures.extend(join_all(checks).await.into_iter().flatten());
+        failures.extend(probe_failures(self.probes.iter()).await);
         let healthy = failures.is_empty();
         let changed = {
             let mut previous = self
@@ -128,8 +113,42 @@ impl HealthStatus {
     }
 }
 
+async fn probe_failures<'a>(
+    probes: impl Iterator<Item = &'a Arc<dyn HealthProbe>>,
+) -> Vec<HealthFailure> {
+    // 探针并行共用截止时间，保留已完成结果并指出具体超时组件
+    let deadline = tokio::time::Instant::now() + HEALTH_CHECK_TIMEOUT;
+    let checks = probes.map(|probe| async move {
+        let (state, reason) = match tokio::time::timeout_at(deadline, probe.check()).await {
+            Ok(HealthState::Healthy) => return None,
+            Ok(HealthState::Degraded(reason)) => ("degraded", reason),
+            Ok(HealthState::Unhealthy(reason)) => ("unhealthy", reason),
+            Err(_) => ("timed_out", "health probe exceeded 2s deadline".to_owned()),
+        };
+        Some(HealthFailure {
+            component: format!("probe:{}", probe.name()),
+            state,
+            reason,
+        })
+    });
+    join_all(checks).await.into_iter().flatten().collect()
+}
+
+pub(crate) async fn readyz(State(state): State<ApiState>) -> StatusCode {
+    let required = state
+        .health()
+        .probes
+        .iter()
+        .filter(|probe| probe.required_for_readiness());
+    status_code(probe_failures(required).await.is_empty())
+}
+
 pub(crate) async fn healthz(State(state): State<ApiState>) -> StatusCode {
-    if state.health().healthy().await {
+    status_code(state.health().healthy().await)
+}
+
+fn status_code(healthy: bool) -> StatusCode {
+    if healthy {
         StatusCode::NO_CONTENT
     } else {
         StatusCode::SERVICE_UNAVAILABLE

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

@@ -30,6 +30,7 @@ use crate::openai::service::OpenAiService;
 pub mod admin;
 pub mod auth;
 mod client_error;
+mod diagnostics;
 mod health;
 mod key_usage;
 mod middleware;
@@ -216,6 +217,7 @@ pub fn initialize(
     };
     let index = config.asset_directory.join("index.html");
     let mut router = Router::new()
+        .route("/readyz", get(health::readyz))
         .route("/healthz", get(health::healthz))
         .merge(openai::router::router())
         .merge(provider::router())
@@ -279,6 +281,10 @@ pub fn initialize(
             headers_ms = latency.as_millis(), "HTTP response headers ready");
     });
     let router = router
+        .layer(axum::middleware::from_fn_with_state(
+            diagnostics.clone(),
+            diagnostics::record_ingress,
+        ))
         .layer(axum::middleware::from_fn_with_state(
             diagnostics,
             admin::diagnostics::record_failure,

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

@@ -128,7 +128,12 @@ fn client_authentication_request(
 }
 
 pub(crate) fn client_access_error_response(error: ClientAccessError) -> Response {
-    match error {
+    let code = match &error {
+        ClientAccessError::Authentication(error) => error.reason(),
+        ClientAccessError::Version(error) if error.current().is_some() => "client_version_too_old",
+        ClientAccessError::Version(_) => "client_version_unavailable",
+    };
+    let mut response = match error {
         ClientAccessError::Authentication(error) => {
             log_client_api_key_auth_failure(error);
             if error == ClientApiKeyAuthError::RuntimeUnavailable {
@@ -146,7 +151,11 @@ pub(crate) fn client_access_error_response(error: ClientAccessError) -> Response
             );
             client_version_rejection_response(&error).into_response()
         }
-    }
+    };
+    response
+        .extensions_mut()
+        .insert(crate::client_error::AccessRejection(code));
+    response
 }
 
 /// Desktop 优先于内嵌 CLI/Core；未知客户端及未提供应用版本的手机远程客户端返回 `None`

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

@@ -1,5 +1,7 @@
 //! 将 Chat 请求转换为 Responses 正文，协议选项留在 API，业务 JSON 与上游兼容规则保持原有归属
 
+use std::collections::HashSet;
+
 use serde_json::{Map, Value, json};
 
 use crate::openai::responses::RequestDecodeError;
@@ -27,18 +29,44 @@ pub(in crate::openai) fn convert_request(
         ("stream".into(), stream.into()),
         ("store".into(), false.into()),
     ]);
-    if let Some(value) = optional(&mut chat, "tools") {
-        body.insert("tools".into(), function_tools(value)?.into());
-    }
-    if let Some(value) = optional(&mut chat, "tool_choice") {
-        let choice = tool_choice(value, body.get("tools"))?;
-        body.insert("tool_choice".into(), choice);
+    if let Some(options) = optional(&mut chat, "web_search_options") {
+        let tool = web_search_tool(options)?;
+        // Chat 搜索要求先检索，不能用强制搜索覆盖调用方的函数工具或选择
+        if let Some(tools) = optional(&mut chat, "tools")
+            && !array(tools, "tools")?.is_empty()
+        {
+            return Err(RequestDecodeError::UnsupportedCombination {
+                field: "tools",
+                other: "web_search_options",
+            });
+        }
+        if let Some(choice) = optional(&mut chat, "tool_choice")
+            && choice != "auto"
+        {
+            return Err(RequestDecodeError::UnsupportedCombination {
+                field: "tool_choice",
+                other: "web_search_options",
+            });
+        }
+        body.insert("tools".into(), Value::Array(vec![tool]));
+        body.insert("tool_choice".into(), json!({"type": "web_search"}));
+    } else {
+        if let Some(value) = optional(&mut chat, "tools") {
+            body.insert("tools".into(), tools(value)?.into());
+        }
+        if let Some(value) = optional(&mut chat, "tool_choice") {
+            let choice = tool_choice(value, "tool_choice")?;
+            body.insert("tool_choice".into(), choice);
+        }
     }
     if let Some(value) = optional_bool(&mut chat, "parallel_tool_calls", "parallel_tool_calls")? {
         body.insert("parallel_tool_calls".into(), value.into());
     }
 
-    let mut text = Map::new();
+    let mut text = optional(&mut chat, "text")
+        .map(|value| object(value, "text"))
+        .transpose()?
+        .unwrap_or_default();
     if let Some(value) = optional(&mut chat, "response_format") {
         text.insert("format".into(), response_format(value)?);
     }
@@ -49,47 +77,81 @@ pub(in crate::openai) fn convert_request(
     if !text.is_empty() {
         body.insert("text".into(), text.into());
     }
+    let mut reasoning = optional(&mut chat, "reasoning")
+        .map(|value| object(value, "reasoning"))
+        .transpose()?
+        .unwrap_or_default();
     if let Some(value) = optional(&mut chat, "reasoning_effort") {
         string(&value, "reasoning_effort", false)?;
-        body.insert("reasoning".into(), json!({"effort": value}));
+        reasoning.insert("effort".into(), value);
     }
-    for field in ["max_tokens", "max_completion_tokens"] {
+    if !reasoning.is_empty() {
+        body.insert("reasoning".into(), reasoning.into());
+    }
+    for field in ["max_output_tokens", "max_tokens", "max_completion_tokens"] {
         if let Some(value) = optional(&mut chat, field) {
-            if !value.as_u64().is_some_and(|tokens| tokens > 0) {
-                return Err(invalid(field));
-            }
             // 新字段优先，具体上游是否接受长度控制仍由现有 Provider 决定
             body.insert("max_output_tokens".into(), value);
         }
     }
-    for (field, maximum) in [("temperature", 2.0), ("top_p", 1.0)] {
-        if let Some(value) = optional(&mut chat, field) {
-            if !value
-                .as_f64()
-                .is_some_and(|number| (0.0..=maximum).contains(&number))
-            {
-                return Err(invalid(field));
-            }
-            body.insert(field.into(), value);
-        }
-    }
+    // 同语义字段不在入口预判模型支持范围，交由既有 Provider 与上游校验
     for field in [
+        "temperature",
+        "top_p",
         "user",
         "safety_identifier",
         "service_tier",
         "prompt_cache_key",
         "prompt_cache_retention",
+        "metadata",
+        "prompt_cache_options",
+        "moderation",
+        "instructions",
+        "include",
+        "max_tool_calls",
+        "truncation",
+        "context_management",
     ] {
         if let Some(value) = optional(&mut chat, field) {
-            string(&value, field, true)?;
             body.insert(field.into(), value);
         }
     }
-    for field in ["metadata", "prompt_cache_options", "moderation"] {
-        if let Some(value) = optional(&mut chat, field) {
-            let object = object(value, field)?;
-            body.insert(field.into(), object.into());
+    if optional_bool(&mut chat, "logprobs", "logprobs")? == Some(true) {
+        let mut include = body
+            .remove("include")
+            .map(|value| array(value, "include"))
+            .transpose()?
+            .unwrap_or_default();
+        let logprobs = json!("message.output_text.logprobs");
+        if !include.contains(&logprobs) {
+            include.push(logprobs);
         }
+        body.insert("include".into(), include.into());
+        if let Some(value) = optional(&mut chat, "top_logprobs") {
+            body.insert("top_logprobs".into(), value);
+        }
+    }
+    let ignored = [
+        "stop",
+        "seed",
+        "frequency_penalty",
+        "presence_penalty",
+        "logit_bias",
+        "prediction",
+    ]
+    .into_iter()
+    .filter(|field| {
+        chat.get(*field).is_some_and(|value| {
+            !value.is_null()
+                && value.as_f64() != Some(0.0)
+                && !value.as_array().is_some_and(Vec::is_empty)
+                && !value.as_object().is_some_and(Map::is_empty)
+        })
+    })
+    .collect::<Vec<_>>();
+    if !ignored.is_empty() {
+        tracing::info!(target: "request_trace", stage="chat.compatibility", ignored_options=?ignored,
+            "Chat-only optional controls omitted from Responses request");
     }
     // 未识别的客户端顶层扩展不等于 Responses 参数，不进入上游正文
     Ok(ConvertedChatRequest {
@@ -102,27 +164,10 @@ fn validate_options(chat: &Map<String, Value>) -> Result<(), RequestDecodeError>
     for (field, value) in chat.iter().filter(|(_, value)| !value.is_null()) {
         let supported = match field.as_str() {
             "n" => value.as_u64() == Some(1),
-            "store" | "logprobs" => value == false,
-            "frequency_penalty" | "presence_penalty" => value.as_f64() == Some(0.0),
-            "top_logprobs" => value.as_u64() == Some(0),
-            "logit_bias" => value.as_object().is_some_and(Map::is_empty),
-            "functions" | "stop" => value.as_array().is_some_and(Vec::is_empty),
+            "store" | "background" => value == false,
+            "functions" => value.as_array().is_some_and(Vec::is_empty),
             "modalities" => value == &json!(["text"]),
-            "audio"
-            | "prediction"
-            | "seed"
-            | "function_call"
-            | "web_search_options"
-            | "reasoning_content"
-            | "input"
-            | "previous_response_id"
-            | "conversation"
-            | "instructions"
-            | "reasoning"
-            | "text"
-            | "include"
-            | "background"
-            | "max_output_tokens" => false,
+            "audio" | "function_call" | "input" | "previous_response_id" | "conversation" => false,
             _ => true,
         };
         if !supported {
@@ -132,6 +177,33 @@ fn validate_options(chat: &Map<String, Value>) -> Result<(), RequestDecodeError>
     Ok(())
 }
 
+fn web_search_tool(value: Value) -> Result<Value, RequestDecodeError> {
+    let mut options = object(value, "web_search_options")?;
+    let mut tool = json!({"type": "web_search"});
+    if let Some(size) = optional(&mut options, "search_context_size") {
+        string(&size, "web_search_options.search_context_size", false)?;
+        tool["search_context_size"] = size;
+    }
+    if let Some(location) = optional(&mut options, "user_location") {
+        let mut location = object(location, "web_search_options.user_location")?;
+        let path = "web_search_options.user_location.type";
+        if required_string(&mut location, "type", path, false)? != "approximate" {
+            return Err(unsupported(path));
+        }
+        let path = "web_search_options.user_location.approximate";
+        let mut approximate = object(required(&mut location, "approximate", path)?, path)?;
+        let mut flat = json!({"type": "approximate"});
+        for field in ["city", "country", "region", "timezone"] {
+            if let Some(value) = optional(&mut approximate, field) {
+                string(&value, &format!("{path}.{field}"), true)?;
+                flat[field] = value;
+            }
+        }
+        tool["user_location"] = flat;
+    }
+    Ok(tool)
+}
+
 fn stream_options(value: Option<Value>, stream: bool) -> Result<bool, RequestDecodeError> {
     let Some(value) = value else {
         return Ok(false);
@@ -166,6 +238,7 @@ fn messages(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
         });
     }
     let mut input = Vec::with_capacity(messages.len());
+    let mut custom_calls = HashSet::new();
     for (index, value) in messages.into_iter().enumerate() {
         let path = format!("messages[{index}]");
         let mut message = object(value, &path)?;
@@ -176,12 +249,13 @@ fn messages(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
         ) {
             return Err(unsupported(&format!("{path}.role")));
         }
-        if let Some(name) = optional(&mut message, "name")
-            && !string(&name, &format!("{path}.name"), true)?.is_empty()
-        {
-            return Err(unsupported(&format!("{path}.name")));
+        let name = optional(&mut message, "name").filter(|name| name != "");
+        if let Some(name) = &name {
+            let name_path = format!("{path}.name");
+            string(name, &name_path, true)?;
         }
-        for field in ["function_call", "reasoning_content", "reasoning", "audio"] {
+        // Chat 的显示名称和明文推理历史没有对应的 Responses 输入语义
+        for field in ["function_call", "audio"] {
             if optional(&mut message, field).is_some() {
                 return Err(unsupported(&format!("{path}.{field}")));
             }
@@ -209,9 +283,16 @@ fn messages(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
             } else {
                 content_parts(content, &role, &content_path, false)?.into()
             };
-            input.push(
-                json!({"type": "function_call_output", "call_id": call_id, "output": output}),
-            );
+            let kind = if custom_calls.contains(&call_id) {
+                "custom_tool_call_output"
+            } else {
+                "function_call_output"
+            };
+            let mut item = json!({"type": kind, "call_id": call_id, "output": output});
+            if let Some(name) = name {
+                item["name"] = name;
+            }
+            input.push(item);
             continue;
         }
 
@@ -245,7 +326,15 @@ fn messages(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
             }
             input.push(item);
         }
-        input.extend(calls);
+        for call in calls {
+            let id = string(&call["call_id"], &format!("{path}.tool_calls.id"), false)?.to_owned();
+            if call["type"] == "custom_tool_call" {
+                custom_calls.insert(id);
+            } else {
+                custom_calls.remove(&id);
+            }
+            input.push(call);
+        }
     }
     Ok(input)
 }
@@ -267,14 +356,23 @@ fn content_parts(
         let mut part = object(value, &path)?;
         let kind = required_string(&mut part, "type", &format!("{path}.type"), false)?;
         let mut converted = match kind.as_str() {
-            "text" => text_part(
+            "text" | "input_text" | "output_text" => text_part(
                 required_string(&mut part, "text", &format!("{path}.text"), true)?,
                 is_assistant,
             ),
-            "image_url" if role == "user" => image_part(
+            "image_url" if matches!(role, "user" | "tool") => image_part(
                 required(&mut part, "image_url", &format!("{path}.image_url"))?,
                 &format!("{path}.image_url"),
             )?,
+            "file" if matches!(role, "user" | "tool") => {
+                let file_path = format!("{path}.file");
+                file_part(required(&mut part, "file", &file_path)?, &file_path)?
+            }
+            "input_audio" if matches!(role, "user" | "tool") => audio_part(&mut part, &path)?,
+            "input_image" | "input_file" if matches!(role, "user" | "tool") => {
+                part.insert("type".into(), kind.into());
+                Value::Object(std::mem::take(&mut part))
+            }
             "refusal" if role == "assistant" => json!({
                 "type": "refusal",
                 "refusal": required_string(&mut part, "refusal", &format!("{path}.refusal"), true)?,
@@ -301,6 +399,34 @@ fn text_part(text: String, is_assistant: bool) -> Value {
     }
 }
 
+fn file_part(value: Value, path: &str) -> Result<Value, RequestDecodeError> {
+    let mut file = object(value, path)?;
+    if !["file_id", "file_url", "file_data"]
+        .iter()
+        .any(|field| file.get(*field).is_some_and(|value| !value.is_null()))
+    {
+        return Err(invalid(path));
+    }
+    // 文件可用性、格式和组合由接收文件的上游判断，网关不下载或重编码
+    file.insert("type".into(), "input_file".into());
+    Ok(file.into())
+}
+
+fn audio_part(part: &mut Map<String, Value>, path: &str) -> Result<Value, RequestDecodeError> {
+    if let Some(value) = optional(part, "input_audio") {
+        let path = format!("{path}.input_audio");
+        let mut audio = object(value, &path)?;
+        let data = required_string(&mut audio, "data", &format!("{path}.data"), false)?;
+        let format = required_string(&mut audio, "format", &format!("{path}.format"), false)?;
+        let mime = if format == "mp3" { "mpeg" } else { &format };
+        Ok(json!({"type":"input_audio", "audio_url":format!("data:audio/{mime};base64,{data}")}))
+    } else {
+        // Codex 使用 audio_url/file_id 引用，原生扩展保持其结构
+        part.insert("type".into(), "input_audio".into());
+        Ok(Value::Object(std::mem::take(part)))
+    }
+}
+
 fn image_part(value: Value, path: &str) -> Result<Value, RequestDecodeError> {
     let mut image = object(value, path)?;
     let url = required_string(&mut image, "url", &format!("{path}.url"), false)?;
@@ -324,104 +450,82 @@ fn image_part(value: Value, path: &str) -> Result<Value, RequestDecodeError> {
 }
 
 fn tool_calls(value: Value, path: &str) -> Result<Vec<Value>, RequestDecodeError> {
-    let calls = array(value, path)?;
-    let mut result = Vec::with_capacity(calls.len());
-    for (index, value) in calls.into_iter().enumerate() {
-        let path = format!("{path}[{index}]");
-        let mut call = object(value, &path)?;
-        let id = required_string(&mut call, "id", &format!("{path}.id"), false)?;
-        if required_string(&mut call, "type", &format!("{path}.type"), false)? != "function" {
-            return Err(unsupported(&format!("{path}.type")));
-        }
-        let function_path = format!("{path}.function");
-        let mut function = object(
-            required(&mut call, "function", &function_path)?,
-            &function_path,
-        )?;
-        let name = required_string(
-            &mut function,
-            "name",
-            &format!("{function_path}.name"),
-            false,
-        )?;
-        let arguments = required_string(
-            &mut function,
-            "arguments",
-            &format!("{function_path}.arguments"),
-            true,
-        )?;
-        result.push(
-            json!({"type": "function_call", "call_id": id, "name": name, "arguments": arguments}),
-        );
-    }
-    Ok(result)
+    array(value, path)?
+        .into_iter()
+        .enumerate()
+        .map(|(index, value)| {
+            let path = format!("{path}[{index}]");
+            let mut call = object(value, &path)?;
+            let id = required_string(&mut call, "id", &format!("{path}.id"), false)?;
+            let kind = required_string(&mut call, "type", &format!("{path}.type"), false)?;
+            let (output_type, data_field) = match kind.as_str() {
+                "function" => ("function_call", "arguments"),
+                "custom" => ("custom_tool_call", "input"),
+                _ => return Err(unsupported(&format!("{path}.type"))),
+            };
+            let nested_path = format!("{path}.{kind}");
+            let mut nested = object(required(&mut call, &kind, &nested_path)?, &nested_path)?;
+            let name = required_string(&mut nested, "name", &format!("{nested_path}.name"), false)?;
+            let data = required_string(
+                &mut nested,
+                data_field,
+                &format!("{nested_path}.{data_field}"),
+                true,
+            )?;
+            Ok(json!({"type":output_type, "call_id":id, "name":name, data_field:data}))
+        })
+        .collect()
 }
 
-fn function_tools(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
+fn tools(value: Value) -> Result<Vec<Value>, RequestDecodeError> {
     array(value, "tools")?
         .into_iter()
         .enumerate()
         .map(|(index, value)| {
             let path = format!("tools[{index}]");
             let mut tool = object(value, &path)?;
-            if required_string(&mut tool, "type", &format!("{path}.type"), false)? != "function" {
-                return Err(unsupported(&format!("{path}.type")));
+            let kind = required_string(&mut tool, "type", &format!("{path}.type"), false)?;
+            if matches!(kind.as_str(), "function" | "custom") {
+                if let Some(nested) = optional(&mut tool, &kind) {
+                    tool = object(nested, &format!("{path}.{kind}"))?;
+                }
+                if kind == "function" && tool.get("strict").is_none_or(Value::is_null) {
+                    // Chat 的缺省是宽松 schema，不能让 Responses 收紧参数合同
+                    tool.insert("strict".into(), false.into());
+                }
             }
-            let function_path = format!("{path}.function");
-            let mut function = object(
-                required(&mut tool, "function", &function_path)?,
-                &function_path,
-            )?;
-            let name = required_string(
-                &mut function,
-                "name",
-                &format!("{function_path}.name"),
-                false,
-            )?;
-            // Chat 的缺省是宽松函数 schema，不能让 Responses 的缺省收紧原始参数合同
-            let strict =
-                optional_bool(&mut function, "strict", &format!("{function_path}.strict"))?
-                    .unwrap_or(false);
-            let mut converted = json!({"type": "function", "name": name, "strict": strict});
-            if let Some(description) = optional(&mut function, "description") {
-                string(&description, &format!("{function_path}.description"), true)?;
-                converted["description"] = description;
-            }
-            if let Some(parameters) = optional(&mut function, "parameters") {
-                converted["parameters"] = parameters;
-            }
-            Ok(converted)
+            // hosted 工具采用原生 Responses 结构，支持范围由选中的 Provider 决定
+            tool.insert("type".into(), kind.into());
+            Ok(tool.into())
         })
         .collect()
 }
 
-fn tool_choice(value: Value, tools: Option<&Value>) -> Result<Value, RequestDecodeError> {
-    let tools = tools.and_then(Value::as_array);
-    if let Value::String(choice) = &value {
-        return match choice.as_str() {
-            "auto" | "none" => Ok(value),
-            "required" if tools.is_some_and(|tools| !tools.is_empty()) => Ok(value),
-            "required" => Err(invalid("tool_choice")),
-            _ => Err(unsupported("tool_choice")),
-        };
+fn tool_choice(value: Value, path: &str) -> Result<Value, RequestDecodeError> {
+    if value.is_string() {
+        return Ok(value);
     }
-    let mut choice = object(value, "tool_choice")?;
-    if required_string(&mut choice, "type", "tool_choice.type", false)? != "function" {
-        return Err(unsupported("tool_choice.type"));
+    let mut choice = object(value, path)?;
+    let kind = required_string(&mut choice, "type", &format!("{path}.type"), false)?;
+    if matches!(kind.as_str(), "function" | "custom") {
+        if let Some(nested) = optional(&mut choice, &kind) {
+            choice = object(nested, &format!("{path}.{kind}"))?;
+        }
+    } else if kind == "allowed_tools" {
+        if let Some(nested) = optional(&mut choice, "allowed_tools") {
+            choice = object(nested, &format!("{path}.allowed_tools"))?;
+        }
+        if let Some(value) = optional(&mut choice, "tools") {
+            let mapped = array(value, &format!("{path}.tools"))?
+                .into_iter()
+                .enumerate()
+                .map(|(index, value)| tool_choice(value, &format!("{path}.tools[{index}]")))
+                .collect::<Result<Vec<_>, _>>()?;
+            choice.insert("tools".into(), mapped.into());
+        }
     }
-    let mut function = object(
-        required(&mut choice, "function", "tool_choice.function")?,
-        "tool_choice.function",
-    )?;
-    let name = required_string(&mut function, "name", "tool_choice.function.name", false)?;
-    if !tools.is_some_and(|tools| {
-        tools
-            .iter()
-            .any(|tool| tool.get("name").and_then(Value::as_str) == Some(name.as_str()))
-    }) {
-        return Err(invalid("tool_choice.function.name"));
-    }
-    Ok(json!({"type": "function", "name": name}))
+    choice.insert("type".into(), kind.into());
+    Ok(choice.into())
 }
 
 fn response_format(value: Value) -> Result<Value, RequestDecodeError> {
@@ -460,7 +564,10 @@ fn response_format(value: Value) -> Result<Value, RequestDecodeError> {
             }
             Ok(converted)
         }
-        _ => Err(unsupported("response_format.type")),
+        _ => {
+            format.insert("type".into(), kind.into());
+            Ok(format.into())
+        }
     }
 }
 

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

@@ -7,6 +7,7 @@ use gateway_protocol::openai::events::{billable_usage_is_complete, extract_usage
 use gateway_protocol::openai::sse::encode_sse_event;
 use serde::Serialize;
 use serde_json::{Value, json};
+use sha2::{Digest as _, Sha256};
 
 use crate::client_error::{ProtocolError, ProtocolErrorBody};
 
@@ -46,26 +47,52 @@ pub(in crate::openai) fn project_response(
     let mut content = None;
     let mut refusal = None;
     let mut tools = Vec::new();
+    let mut annotations = Vec::new();
+    let mut content_chars = 0;
+    let mut reasoning = Vec::new();
+    let mut images = Vec::new();
+    let mut logprobs = None;
     for item in output {
         match required_str(item, "type")? {
             "message" => {
+                // 两侧索引都按消息中的字符计数，合并多条 assistant 消息时平移引用
                 for part in message_parts(item)? {
                     let (kind, text) = part_text(part)?;
                     let target = match kind {
-                        PartKind::Text => &mut content,
+                        PartKind::Text => {
+                            append_url_citations(part, content_chars, &mut annotations)?;
+                            if let Some(values) = part.get("logprobs").and_then(Value::as_array) {
+                                logprobs
+                                    .get_or_insert_with(Vec::new)
+                                    .extend(values.iter().cloned());
+                            }
+                            content_chars += text.chars().count() as u64;
+                            &mut content
+                        }
                         PartKind::Refusal => &mut refusal,
                     };
                     target.get_or_insert_with(String::new).push_str(text);
                 }
             }
-            "function_call" => {
-                let (id, name, arguments) = function_fields(item)?;
-                tools.push(json!({
-                    "id": id, "type": "function",
-                    "function": {"name": name, "arguments": arguments}
-                }));
+            "function_call" | "custom_tool_call" => {
+                let kind = ToolKind::from_item(item)?;
+                let (id, name, data) = tool_fields(item, kind)?;
+                tools.push(json!({"id":id, "type":kind.chat_type(),
+                    kind.chat_type():{"name":name, kind.data_field():data}}));
             }
-            "reasoning" => {}
+            "reasoning" => {
+                for (_, _, text) in reasoning_parts(item)? {
+                    if !text.is_empty() {
+                        reasoning.push(text);
+                    }
+                }
+            }
+            "image_generation_call" => {
+                if let Some(image) = image_payload(item)? {
+                    images.push(image);
+                }
+            }
+            kind if is_auxiliary_output(kind) => {}
             _ => return Err(invalid_response()),
         }
     }
@@ -74,10 +101,20 @@ pub(in crate::openai) fn project_response(
     if !tools.is_empty() {
         message["tool_calls"] = Value::Array(tools);
     }
+    if !annotations.is_empty() {
+        message["annotations"] = Value::Array(annotations);
+    }
+    if !reasoning.is_empty() {
+        message["reasoning_content"] = reasoning.join("\n\n").into();
+    }
+    if !images.is_empty() {
+        message["images"] = images.into();
+    }
+    let logprobs = logprobs.map(|content| json!({"content":content, "refusal":null}));
     serde_json::to_value(Envelope {
         identity,
         object: "chat.completion",
-        choices: json!([{"index": 0, "message": message, "finish_reason": finish_reason, "logprobs": null}]),
+        choices: json!([{"index": 0, "message": message, "finish_reason": finish_reason, "logprobs": logprobs}]),
         usage: chat_usage(response),
         metadata: response.get("metadata"),
         service_tier: response.get("service_tier"),
@@ -104,9 +141,47 @@ impl PartKind {
 struct Part {
     kind: PartKind,
     text: String,
+    logprobs: Vec<Value>,
+    annotations: BTreeMap<u64, Value>,
+    spans: Vec<TextSpan>,
+}
+
+struct TextSpan {
+    start: u64,
+    end: u64,
+    delivered_start: u64,
+}
+
+#[derive(Clone, Copy, PartialEq, Eq)]
+enum ToolKind {
+    Function,
+    Custom,
+}
+
+impl ToolKind {
+    fn from_item(item: &Value) -> Result<Self, ProtocolErrorBody> {
+        match required_str(item, "type")? {
+            "function_call" => Ok(Self::Function),
+            "custom_tool_call" => Ok(Self::Custom),
+            _ => Err(invalid_response()),
+        }
+    }
+    const fn chat_type(self) -> &'static str {
+        match self {
+            Self::Function => "function",
+            Self::Custom => "custom",
+        }
+    }
+    const fn data_field(self) -> &'static str {
+        match self {
+            Self::Function => "arguments",
+            Self::Custom => "input",
+        }
+    }
 }
 
 struct Tool {
+    kind: ToolKind,
     index: usize,
     call_id: String,
     name: String,
@@ -115,8 +190,13 @@ struct Tool {
 
 enum Output {
     Message(BTreeMap<u64, Part>),
-    Function(Tool),
-    Reasoning,
+    Tool(Tool),
+    Reasoning(BTreeMap<(bool, u64), String>),
+    Image {
+        index: usize,
+        fingerprint: Option<[u8; 32]>,
+    },
+    Auxiliary(String),
 }
 
 struct OutputItem {
@@ -137,6 +217,7 @@ pub(in crate::openai) struct ChatStreamEncoder {
     role_sent: bool,
     output: BTreeMap<u64, OutputItem>,
     terminal: Option<Terminal>,
+    content_chars: u64,
 }
 
 impl ChatStreamEncoder {
@@ -147,6 +228,7 @@ impl ChatStreamEncoder {
             role_sent: false,
             output: BTreeMap::new(),
             terminal: None,
+            content_chars: 0,
         }
     }
 
@@ -184,11 +266,7 @@ impl ChatStreamEncoder {
                     PartKind::Text
                 };
                 let delta = required_str(data, "delta")?;
-                let part = self.event_part(data, kind)?;
-                part.text.push_str(delta);
-                if !delta.is_empty() {
-                    frames.push(self.delta(json!({kind.field(): delta}))?);
-                }
+                self.text_event(data, kind, delta, false, data, &mut frames)?;
             }
             Some("response.output_text.done" | "response.refusal.done") => {
                 self.require_open()?;
@@ -197,22 +275,29 @@ impl ChatStreamEncoder {
                 } else {
                     (PartKind::Text, "text")
                 };
-                let text = required_str(data, field)?;
-                let part = self.event_part(data, kind)?;
-                let suffix = append_snapshot(&mut part.text, text)?;
-                if !suffix.is_empty() {
-                    frames.push(self.delta(json!({kind.field(): suffix}))?);
-                }
+                self.text_event(
+                    data,
+                    kind,
+                    required_str(data, field)?,
+                    true,
+                    data,
+                    &mut frames,
+                )?;
             }
             Some("response.content_part.added" | "response.content_part.done") => {
                 self.require_open()?;
                 let part = data.get("part").ok_or_else(invalid_response)?;
                 let (kind, text) = part_text(part)?;
-                let part = self.event_part(data, kind)?;
-                let suffix = append_snapshot(&mut part.text, text)?;
-                if !suffix.is_empty() {
-                    frames.push(self.delta(json!({kind.field(): suffix}))?);
-                }
+                self.text_event(data, kind, text, true, part, &mut frames)?;
+            }
+            Some("response.output_text.annotation.added") => {
+                self.require_open()?;
+                let part = self.event_part(data, PartKind::Text)?;
+                insert_annotation(
+                    part,
+                    required_index(data, "annotation_index")?,
+                    data.get("annotation").ok_or_else(invalid_response)?,
+                )?;
             }
             Some("response.output_item.added" | "response.output_item.done") => {
                 self.require_open()?;
@@ -224,27 +309,73 @@ impl ChatStreamEncoder {
                 )?;
             }
             Some(
-                "response.function_call_arguments.delta" | "response.function_call_arguments.done",
+                "response.function_call_arguments.delta"
+                | "response.function_call_arguments.done"
+                | "response.custom_tool_call_input.delta"
+                | "response.custom_tool_call_input.done",
             ) => {
                 self.require_open()?;
                 let index = required_index(data, "output_index")?;
                 let item = self.output.get_mut(&index).ok_or_else(invalid_response)?;
                 bind_id(item, optional_id(data, "item_id")?)?;
-                let Output::Function(tool) = &mut item.output else {
+                let Output::Tool(tool) = &mut item.output else {
                     return Err(invalid_response());
                 };
-                let delta = if event_type == Some("response.function_call_arguments.delta") {
+                let kind = tool.kind;
+                let custom_event = event_type
+                    .is_some_and(|event| event.starts_with("response.custom_tool_call_input."));
+                if custom_event != (kind == ToolKind::Custom) {
+                    return Err(invalid_response());
+                }
+                let delta = if event_type.is_some_and(|event| event.ends_with(".delta")) {
                     let delta = required_str(data, "delta")?;
                     tool.arguments.push_str(delta);
                     delta
                 } else {
-                    append_snapshot(&mut tool.arguments, required_str(data, "arguments")?)?
+                    append_snapshot(&mut tool.arguments, required_str(data, kind.data_field())?)?
                 };
                 let tool_index = tool.index;
                 if !delta.is_empty() {
-                    frames.push(self.delta(json!({"tool_calls": [{"index": tool_index, "function": {"arguments": delta}}]}))?);
+                    frames.push(self.delta(json!({"tool_calls": [{"index": tool_index, kind.chat_type(): {kind.data_field(): delta}}]}))?);
                 }
             }
+            Some(
+                "response.reasoning_summary_text.delta"
+                | "response.reasoning_summary_text.done"
+                | "response.reasoning_text.delta"
+                | "response.reasoning_text.done",
+            ) => {
+                self.require_open()?;
+                let summary =
+                    event_type.is_some_and(|event| event.starts_with("response.reasoning_summary"));
+                let snapshot = event_type.is_some_and(|event| event.ends_with(".done"));
+                self.reasoning_text(
+                    required_index(data, "output_index")?,
+                    optional_id(data, "item_id")?,
+                    (
+                        summary,
+                        required_index(
+                            data,
+                            if summary {
+                                "summary_index"
+                            } else {
+                                "content_index"
+                            },
+                        )?,
+                    ),
+                    required_str(data, if snapshot { "text" } else { "delta" })?,
+                    snapshot,
+                    &mut frames,
+                )?;
+            }
+            Some("response.image_generation_call.partial_image") => {
+                self.require_open()?;
+                self.item_snapshot(required_index(data, "output_index")?, &json!({
+                    "id": required_nonempty_str(data, "item_id")?, "type":"image_generation_call",
+                    "result": required_str(data, "partial_image_b64")?,
+                    "output_format": data.get("output_format").unwrap_or(&json!("png")),
+                }), false, &mut frames)?;
+            }
             Some("response.completed" | "response.incomplete") => {
                 self.require_open()?;
                 let response = data.get("response").ok_or_else(invalid_response)?;
@@ -263,6 +394,10 @@ impl ChatStreamEncoder {
                 } else if self.output.is_empty() {
                     return Err(invalid_response());
                 }
+                let annotations = self.stream_annotations()?;
+                if !annotations.is_empty() {
+                    frames.push(self.delta(json!({"annotations":annotations}))?);
+                }
                 let finish_reason = finish_reason(response, self.tool_count() > 0)?;
                 frames.push(self.chunk(
                     json!([{"index": 0, "delta": {}, "finish_reason": finish_reason, "logprobs": null}]),
@@ -298,7 +433,7 @@ impl ChatStreamEncoder {
             // 辅助事件可随上游演进；实际 output item 和 content part 仍逐项检查可表达性
             _ => {}
         }
-        // done-only 流也要提供完整 Chat 消息身份，辅助事件或私有推理不触发角色帧
+        // done-only 流也要提供完整 Chat 消息身份，不含可交付内容的辅助事件不触发角色帧
         if !self.role_sent && !frames.is_empty() && !self.has_wire_failure() {
             frames.insert(0, self.delta(json!({"role": "assistant"}))?);
             self.role_sent = true;
@@ -306,6 +441,106 @@ impl ChatStreamEncoder {
         Ok(frames)
     }
 
+    fn text_event(
+        &mut self,
+        data: &Value,
+        kind: PartKind,
+        text: &str,
+        snapshot: bool,
+        metadata: &Value,
+        frames: &mut Vec<Bytes>,
+    ) -> Result<(), ProtocolErrorBody> {
+        let mut content_chars = self.content_chars;
+        let part = self.event_part(data, kind)?;
+        let delta = if snapshot {
+            append_snapshot(&mut part.text, text)?
+        } else {
+            part.text.push_str(text);
+            text
+        };
+        record_text_span(part, &mut content_chars, delta);
+        merge_annotations(part, metadata)?;
+        let logprobs = append_logprobs(part, metadata, snapshot)?;
+        self.content_chars = content_chars;
+        if !delta.is_empty() {
+            frames.push(self.delta(json!({kind.field():delta}))?);
+        }
+        if !logprobs.is_empty() {
+            frames.push(logprobs_frame(
+                &self.identity,
+                self.include_usage,
+                kind,
+                logprobs,
+            )?);
+        }
+        Ok(())
+    }
+
+    fn stream_annotations(&self) -> Result<Vec<Value>, ProtocolErrorBody> {
+        let mut result = Vec::new();
+        for item in self.output.values() {
+            if let Output::Message(parts) = &item.output {
+                for part in parts.values() {
+                    let mut citations = Vec::new();
+                    append_url_citations(
+                        &json!({"annotations":part.annotations.values().collect::<Vec<_>>()}),
+                        0,
+                        &mut citations,
+                    )?;
+                    for mut citation in citations {
+                        for field in ["start_index", "end_index"] {
+                            let position = required_index(&citation["url_citation"], field)?;
+                            citation["url_citation"][field] =
+                                delivered_position(part, position, field == "end_index")?.into();
+                        }
+                        result.push(citation);
+                    }
+                }
+            }
+        }
+        Ok(result)
+    }
+
+    fn reasoning_text(
+        &mut self,
+        index: u64,
+        id: Option<&str>,
+        part: (bool, u64),
+        text: &str,
+        snapshot: bool,
+        frames: &mut Vec<Bytes>,
+    ) -> Result<(), ProtocolErrorBody> {
+        let has_text = self.output.values().any(|item| {
+            matches!(&item.output,
+            Output::Reasoning(parts) if parts.values().any(|text| !text.is_empty()))
+        });
+        let item = self.output.entry(index).or_insert_with(|| OutputItem {
+            id: None,
+            output: Output::Reasoning(BTreeMap::new()),
+        });
+        bind_id(item, id)?;
+        let Output::Reasoning(parts) = &mut item.output else {
+            return Err(invalid_response());
+        };
+        let previous = parts.entry(part).or_default();
+        let separator = previous.is_empty() && has_text;
+        let delta = if snapshot {
+            append_snapshot(previous, text)?
+        } else {
+            previous.push_str(text);
+            text
+        };
+        if !delta.is_empty() {
+            let delta = if separator {
+                format!("\n\n{delta}")
+            } else {
+                delta.to_owned()
+            };
+            frames.push(self.delta(json!({"reasoning_content":delta}))?);
+        }
+        Ok(())
+    }
+
     fn require_open(&self) -> Result<(), ProtocolErrorBody> {
         if self.terminal.is_some() {
             Err(invalid_response())
@@ -317,7 +552,7 @@ impl ChatStreamEncoder {
     fn tool_count(&self) -> usize {
         self.output
             .values()
-            .filter(|item| matches!(item.output, Output::Function(_)))
+            .filter(|item| matches!(item.output, Output::Tool(_)))
             .count()
     }
 
@@ -342,7 +577,7 @@ impl ChatStreamEncoder {
     ) -> Result<(), ProtocolErrorBody> {
         let id = optional_id(snapshot, "id")?;
         let kind = required_str(snapshot, "type")?;
-        let call_id = if kind == "function_call" {
+        let call_id = if matches!(kind, "function_call" | "custom_tool_call") {
             Some(required_nonempty_str(snapshot, "call_id")?)
         } else {
             None
@@ -356,12 +591,23 @@ impl ChatStreamEncoder {
         if !self.output.contains_key(&index) {
             let output = match kind {
                 "message" => Output::Message(BTreeMap::new()),
-                "reasoning" => Output::Reasoning,
-                "function_call" => {
-                    let (call_id, name, _) = function_fields(snapshot)?;
+                "reasoning" => Output::Reasoning(BTreeMap::new()),
+                "image_generation_call" => Output::Image {
+                    index: self
+                        .output
+                        .values()
+                        .filter(|item| matches!(item.output, Output::Image { .. }))
+                        .count(),
+                    fingerprint: None,
+                },
+                kind if is_auxiliary_output(kind) => Output::Auxiliary(kind.to_owned()),
+                "function_call" | "custom_tool_call" => {
+                    let kind = ToolKind::from_item(snapshot)?;
+                    let (call_id, name, _) = tool_fields(snapshot, kind)?;
                     let tool_index = self.tool_count();
-                    frames.push(self.delta(json!({"tool_calls": [{"index": tool_index, "id": call_id, "type": "function", "function": {"name": name, "arguments": ""}}]}))?);
-                    Output::Function(Tool {
+                    frames.push(self.delta(json!({"tool_calls": [{"index": tool_index, "id": call_id, "type": kind.chat_type(), kind.chat_type(): {"name": name, kind.data_field(): ""}}]}))?);
+                    Output::Tool(Tool {
+                        kind,
                         index: tool_index,
                         call_id: call_id.to_owned(),
                         name: name.to_owned(),
@@ -378,8 +624,20 @@ impl ChatStreamEncoder {
             (Output::Message(parts), "message") => {
                 for (index, part) in message_parts(snapshot)?.iter().enumerate() {
                     let (kind, text) = part_text(part)?;
+                    let snapshot = part;
                     let part = part_entry(parts, index as u64, kind)?;
                     let suffix = append_snapshot(&mut part.text, text)?;
+                    record_text_span(part, &mut self.content_chars, suffix);
+                    merge_annotations(part, snapshot)?;
+                    let logprobs = append_logprobs(part, snapshot, true)?;
+                    if !logprobs.is_empty() {
+                        frames.push(logprobs_frame(
+                            &self.identity,
+                            self.include_usage,
+                            kind,
+                            logprobs,
+                        )?);
+                    }
                     if !suffix.is_empty() {
                         frames.push(delta_frame(
                             &self.identity,
@@ -389,17 +647,41 @@ impl ChatStreamEncoder {
                     }
                 }
             }
-            (Output::Function(tool), "function_call") => {
-                let (id, name, arguments) = function_fields(snapshot)?;
+            (Output::Tool(tool), "function_call" | "custom_tool_call") => {
+                let kind = ToolKind::from_item(snapshot)?;
+                if kind != tool.kind {
+                    return Err(invalid_response());
+                }
+                let (id, name, arguments) = tool_fields(snapshot, kind)?;
                 if tool.call_id != id || tool.name != name {
                     return Err(invalid_response());
                 }
                 let suffix = append_snapshot(&mut tool.arguments, arguments)?;
                 if !suffix.is_empty() {
-                    frames.push(delta_frame(&self.identity, self.include_usage, json!({"tool_calls": [{"index": tool.index, "function": {"arguments": suffix}}]}))?);
+                    frames.push(delta_frame(&self.identity, self.include_usage, json!({"tool_calls": [{"index": tool.index, kind.chat_type(): {kind.data_field(): suffix}}]}))?);
                 }
             }
-            (Output::Reasoning, "reasoning") => {}
+            (Output::Reasoning(_), "reasoning") => {
+                for (summary, part_index, text) in reasoning_parts(snapshot)? {
+                    self.reasoning_text(index, id, (summary, part_index), text, true, frames)?;
+                }
+            }
+            (Output::Image { index, fingerprint }, "image_generation_call") => {
+                if let Some(mut image) = image_payload(snapshot)? {
+                    let hash: [u8; 32] =
+                        Sha256::digest(required_str(&image["image_url"], "url")?.as_bytes()).into();
+                    if *fingerprint != Some(hash) {
+                        *fingerprint = Some(hash);
+                        image["index"] = (*index).into();
+                        frames.push(delta_frame(
+                            &self.identity,
+                            self.include_usage,
+                            json!({"images":[image]}),
+                        )?);
+                    }
+                }
+            }
+            (Output::Auxiliary(previous), kind) if previous == kind => {}
             _ => return Err(invalid_response()),
         }
         Ok(())
@@ -413,7 +695,7 @@ impl ChatStreamEncoder {
         let mut found = None;
         for (&index, item) in &self.output {
             let same_id = id.is_some() && item.id.as_deref() == id;
-            let same_call = matches!(&item.output, Output::Function(tool) if call_id == Some(tool.call_id.as_str()));
+            let same_call = matches!(&item.output, Output::Tool(tool) if call_id == Some(tool.call_id.as_str()));
             if same_id || same_call {
                 if found.is_some_and(|previous| previous != index) {
                     return Err(invalid_response());
@@ -457,6 +739,9 @@ fn part_entry(
     let part = parts.entry(index).or_insert_with(|| Part {
         kind,
         text: String::new(),
+        logprobs: Vec::new(),
+        annotations: BTreeMap::new(),
+        spans: Vec::new(),
     });
     if part.kind != kind {
         return Err(invalid_response());
@@ -464,6 +749,68 @@ fn part_entry(
     Ok(part)
 }
 
+fn record_text_span(part: &mut Part, delivered: &mut u64, delta: &str) {
+    if part.kind != PartKind::Text || delta.is_empty() {
+        return;
+    }
+    let length = delta.chars().count() as u64;
+    let start = part.spans.last().map_or(0, |span| span.end);
+    if let Some(last) = part.spans.last_mut()
+        && last.delivered_start + last.end - last.start == *delivered
+    {
+        last.end += length;
+    } else {
+        part.spans.push(TextSpan {
+            start,
+            end: start + length,
+            delivered_start: *delivered,
+        });
+    }
+    *delivered += length;
+}
+
+fn delivered_position(part: &Part, position: u64, end: bool) -> Result<u64, ProtocolErrorBody> {
+    let matches = |span: &&TextSpan| {
+        if end && position > 0 {
+            span.start < position && position <= span.end
+        } else {
+            span.start <= position && position < span.end
+        }
+    };
+    let span = part
+        .spans
+        .iter()
+        .find(matches)
+        .or_else(|| part.spans.last().filter(|span| position == span.end))
+        .ok_or_else(invalid_response)?;
+    Ok(span.delivered_start + position - span.start)
+}
+
+fn merge_annotations(part: &mut Part, value: &Value) -> Result<(), ProtocolErrorBody> {
+    if let Some(values) = value.get("annotations").filter(|value| !value.is_null()) {
+        for (index, annotation) in values
+            .as_array()
+            .ok_or_else(invalid_response)?
+            .iter()
+            .enumerate()
+        {
+            insert_annotation(part, index as u64, annotation)?;
+        }
+    }
+    Ok(())
+}
+
+fn insert_annotation(part: &mut Part, index: u64, value: &Value) -> Result<(), ProtocolErrorBody> {
+    if let Some(previous) = part.annotations.get(&index) {
+        if previous != value {
+            return Err(invalid_response());
+        }
+    } else {
+        part.annotations.insert(index, value.clone());
+    }
+    Ok(())
+}
+
 fn bind_id(item: &mut OutputItem, id: Option<&str>) -> Result<(), ProtocolErrorBody> {
     if let Some(id) = id {
         if item.id.as_deref().is_some_and(|previous| previous != id) {
@@ -502,11 +849,136 @@ fn part_text(part: &Value) -> Result<(PartKind, &str), ProtocolErrorBody> {
     }
 }
 
-fn function_fields(item: &Value) -> Result<(&str, &str, &str), ProtocolErrorBody> {
+fn append_url_citations(
+    part: &Value,
+    message_offset: u64,
+    annotations: &mut Vec<Value>,
+) -> Result<(), ProtocolErrorBody> {
+    let Some(values) = part.get("annotations").filter(|value| !value.is_null()) else {
+        return Ok(());
+    };
+    for value in values.as_array().ok_or_else(invalid_response)? {
+        if value["type"] != "url_citation" {
+            continue;
+        }
+        let start = required_index(value, "start_index")?;
+        let end = required_index(value, "end_index")?;
+        if start > end {
+            return Err(invalid_response());
+        }
+        annotations.push(json!({"type": "url_citation", "url_citation": {
+            "url": required_str(value, "url")?,
+            "title": required_str(value, "title")?,
+            "start_index": message_offset.checked_add(start).ok_or_else(invalid_response)?,
+            "end_index": message_offset.checked_add(end).ok_or_else(invalid_response)?,
+        }}));
+    }
+    Ok(())
+}
+
+fn is_auxiliary_output(kind: &str) -> bool {
+    // 服务端工具记录和压缩密文不要求 Chat 客户端执行动作，也不投影为可读内容
+    matches!(
+        kind,
+        "web_search_call"
+            | "file_search_call"
+            | "code_interpreter_call"
+            | "mcp_call"
+            | "mcp_list_tools"
+            | "compaction"
+            | "compaction_summary"
+            | "context_compaction"
+    )
+}
+
+fn reasoning_parts(item: &Value) -> Result<Vec<(bool, u64, &str)>, ProtocolErrorBody> {
+    let mut result = Vec::new();
+    // 只交付上游明确公开的推理文本，不解读或暴露 encrypted_content
+    for (field, kind) in [("summary", "summary_text"), ("content", "reasoning_text")] {
+        if let Some(parts) = item.get(field).filter(|value| !value.is_null()) {
+            for (index, part) in parts
+                .as_array()
+                .ok_or_else(invalid_response)?
+                .iter()
+                .enumerate()
+            {
+                if part["type"] == kind {
+                    result.push((
+                        field == "summary",
+                        index as u64,
+                        required_str(part, "text")?,
+                    ));
+                }
+            }
+        }
+    }
+    Ok(result)
+}
+
+fn image_payload(item: &Value) -> Result<Option<Value>, ProtocolErrorBody> {
+    let Some(data) = item.get("result").filter(|value| !value.is_null()) else {
+        return Ok(None);
+    };
+    let data = data.as_str().ok_or_else(invalid_response)?;
+    if data.is_empty() {
+        return Ok(None);
+    }
+    let format = item
+        .get("output_format")
+        .and_then(Value::as_str)
+        .unwrap_or("png");
+    let mime = match format {
+        "png" => "image/png",
+        "jpeg" | "jpg" => "image/jpeg",
+        "webp" => "image/webp",
+        _ => return Err(invalid_response()),
+    };
+    Ok(Some(
+        json!({"type":"image_url", "image_url":{"url":format!("data:{mime};base64,{data}")}}),
+    ))
+}
+
+fn append_logprobs(
+    part: &mut Part,
+    value: &Value,
+    snapshot: bool,
+) -> Result<Vec<Value>, ProtocolErrorBody> {
+    let Some(values) = value.get("logprobs").filter(|value| !value.is_null()) else {
+        return Ok(Vec::new());
+    };
+    let values = values.as_array().ok_or_else(invalid_response)?;
+    let delta = if snapshot {
+        values
+            .strip_prefix(part.logprobs.as_slice())
+            .ok_or_else(invalid_response)?
+    } else {
+        values
+    };
+    let delta = delta.to_vec();
+    part.logprobs.extend(delta.iter().cloned());
+    Ok(delta)
+}
+
+fn logprobs_frame(
+    identity: &ChatIdentity,
+    include_usage: bool,
+    kind: PartKind,
+    values: Vec<Value>,
+) -> Result<Bytes, ProtocolErrorBody> {
+    chunk_frame(
+        identity,
+        json!([{"index":0, "delta":{}, "finish_reason":null,
+        "logprobs":{kind.field():values}}]),
+        include_usage.then_some(Value::Null),
+        None,
+    )
+}
+
+fn tool_fields(item: &Value, kind: ToolKind) -> Result<(&str, &str, &str), ProtocolErrorBody> {
     Ok((
         required_nonempty_str(item, "call_id")?,
         required_nonempty_str(item, "name")?,
-        required_str(item, "arguments")?,
+        required_str(item, kind.data_field())?,
     ))
 }
 
@@ -519,8 +991,10 @@ fn validate_output_identities(output: &[Value]) -> Result<(), ProtocolErrorBody>
         {
             return Err(invalid_response());
         }
-        if item.get("type").and_then(Value::as_str) == Some("function_call")
-            && !call_ids.insert(required_nonempty_str(item, "call_id")?)
+        if matches!(
+            item.get("type").and_then(Value::as_str),
+            Some("function_call" | "custom_tool_call")
+        ) && !call_ids.insert(required_nonempty_str(item, "call_id")?)
         {
             return Err(invalid_response());
         }
@@ -552,19 +1026,41 @@ fn chat_usage(response: &Value) -> Option<Value> {
         return None;
     }
     let mut result = json!({"prompt_tokens": usage.input_tokens, "completion_tokens": usage.output_tokens, "total_tokens": usage.total_tokens});
-    if response
-        .pointer("/usage/input_tokens_details/cached_tokens")
-        .is_some()
-    {
-        result["prompt_tokens_details"] = json!({"cached_tokens": usage.cached_input_tokens});
+    for (source, target) in [
+        ("input_tokens_details", "prompt_tokens_details"),
+        ("output_tokens_details", "completion_tokens_details"),
+    ] {
+        if let Some(details) = response
+            .get("usage")
+            .and_then(|usage| usage.get(source))
+            .filter(|value| value.is_object())
+        {
+            result[target] = details.clone();
+        }
     }
-    if response
-        .pointer("/usage/output_tokens_details/reasoning_tokens")
-        .and_then(Value::as_u64)
-        .is_some_and(|tokens| tokens <= usage.output_tokens)
+    if let Some(details) = result
+        .get_mut("prompt_tokens_details")
+        .and_then(Value::as_object_mut)
+        && details.contains_key("cached_tokens")
     {
-        result["completion_tokens_details"] =
-            json!({"reasoning_tokens": usage.reasoning_output_tokens});
+        details.insert("cached_tokens".into(), usage.cached_input_tokens.into());
+    }
+    if let Some(details) = result
+        .get_mut("completion_tokens_details")
+        .and_then(Value::as_object_mut)
+    {
+        if details
+            .get("reasoning_tokens")
+            .and_then(Value::as_u64)
+            .is_some_and(|tokens| tokens <= usage.output_tokens)
+        {
+            details.insert(
+                "reasoning_tokens".into(),
+                usage.reasoning_output_tokens.into(),
+            );
+        } else {
+            details.remove("reasoning_tokens");
+        }
     }
     Some(result)
 }