chore: bump version to 3.3.30

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

.github/actions/verify-container/action.yml

@@ -0,0 +1,242 @@
+name: Verify container
+description: Scan and validate a built image with the deployment Compose configuration
+inputs:
+  image:
+    description: Local image tag or immutable registry digest to validate
+    required: true
+  platform:
+    description: Native runner image platform
+    required: true
+  artifact-name:
+    description: Unique diagnostics artifact name within the workflow run
+    required: true
+runs:
+  using: composite
+  steps:
+    - name: Define isolated runtime values
+      shell: bash
+      env:
+        IMAGE: ${{ inputs.image }}
+      run: |
+        set -euo pipefail
+        admin_password="$(openssl rand -hex 24)"
+        postgres_password="$(openssl rand -hex 24)"
+        redis_password="$(openssl rand -hex 24)"
+        echo "::add-mask::$admin_password"
+        echo "::add-mask::$postgres_password"
+        echo "::add-mask::$redis_password"
+        {
+          echo "CPR_IMAGE=$IMAGE"
+          echo "COMPOSE_PROJECT_NAME=cpr-check-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${RUNNER_ARCH,,}"
+          echo "DIAGNOSTICS_DIR=$RUNNER_TEMP/codex-proxy-rs-diagnostics"
+          echo "CI_ADMIN_PASSWORD=$admin_password"
+          echo "CI_POSTGRES_PASSWORD=$postgres_password"
+          echo "CI_REDIS_PASSWORD=$redis_password"
+        } >> "$GITHUB_ENV"
+
+    - name: Scan container image
+      uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
+      env:
+        TRIVY_PLATFORM: ${{ inputs.platform }}
+        TRIVY_QUIET: 'true'
+        TRIVY_SKIP_VERSION_CHECK: 'true'
+      with:
+        image-ref: ${{ inputs.image }}
+        version: v0.72.0
+        format: json
+        output: trivy-results.json
+        severity: HIGH,CRITICAL
+        vuln-type: os,library
+        scanners: vuln
+        ignore-unfixed: true
+        exit-code: '0'
+
+    - name: Generate Trivy SARIF
+      shell: bash
+      run: trivy convert --format sarif --output trivy-results.sarif trivy-results.json
+
+    - name: Upload Trivy SARIF
+      if: >-
+        ${{ always() && hashFiles('trivy-results.sarif') != '' &&
+            (github.event_name != 'pull_request' ||
+             github.event.pull_request.head.repo.full_name == github.repository) }}
+      uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4.37.9
+      with:
+        sarif_file: trivy-results.sarif
+        category: runtime-container-${{ inputs.platform }}
+
+    - name: Enforce Trivy vulnerability gate
+      shell: bash
+      run: trivy convert --format table --severity HIGH,CRITICAL --exit-code 1 trivy-results.json
+
+    - name: Prepare isolated runtime
+      shell: bash
+      run: |
+        set -euo pipefail
+        umask 0077
+        # Bind roots hand off ownership to the image-specific database users.
+        # Sticky directories keep that initialization compatible with user-namespaced runners.
+        install -d -m 1777 .runtime/postgres .runtime/redis
+        mkdir -p "$DIAGNOSTICS_DIR"
+        sudo install -d -m 0770 -o "$(id -u)" -g 10001 \
+          .runtime/data .runtime/logs
+        ruby <<'RUBY'
+        path = "deploy/config.example.yaml"
+        content = File.read(path)
+        replacements = {
+          "password: &postgres_password ''" => "password: &postgres_password '#{ENV.fetch("CI_POSTGRES_PASSWORD")}'",
+          "password: &redis_password ''" => "password: &redis_password '#{ENV.fetch("CI_REDIS_PASSWORD")}'",
+          "default_password: ''" => "default_password: '#{ENV.fetch("CI_ADMIN_PASSWORD")}'",
+        }
+        replacements.each do |placeholder, configured|
+          raise "missing config placeholder: #{placeholder}" unless content.sub!(placeholder, configured)
+        end
+        File.write("deploy/config.yaml", content)
+        RUBY
+        sudo chown "$(id -u):10001" deploy/config.yaml
+        chmod 0640 deploy/config.yaml
+
+    - name: Validate Docker Compose
+      shell: bash
+      run: |
+        set -euo pipefail
+        docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml config --quiet
+
+    - name: Configure Redis host memory overcommit
+      shell: bash
+      run: |
+        set -euo pipefail
+        sudo sysctl -w vm.overcommit_memory=1
+        test "$(sysctl -n vm.overcommit_memory)" = 1
+
+    - name: Verify PostgreSQL and Redis volume persistence
+      shell: bash
+      run: |
+        set -euo pipefail
+        compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml)
+        "${compose[@]}" up -d --no-build --wait postgres redis
+        test "$("${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
+          psql -At -U codex_proxy -d codex_proxy -c "SHOW TimeZone;" | tr -d '\r')" = Asia/Shanghai
+        "${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
+          psql -v ON_ERROR_STOP=1 -U codex_proxy -d codex_proxy -c \
+          "CREATE TABLE cpr_ci_persistence_probe (value text PRIMARY KEY); INSERT INTO cpr_ci_persistence_probe VALUES ('persisted');"
+        "${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
+          redis-cli SET cpr:ci:persistence-probe persisted
+        "${compose[@]}" up -d --no-build --wait --force-recreate postgres redis
+        test "$("${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
+          psql -At -U codex_proxy -d codex_proxy -c \
+          "SELECT value FROM cpr_ci_persistence_probe;")" = persisted
+        test "$("${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
+          redis-cli --raw GET cpr:ci:persistence-probe | tr -d '\r')" = persisted
+        "${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
+          psql -v ON_ERROR_STOP=1 -U codex_proxy -d codex_proxy -c \
+          "DROP TABLE cpr_ci_persistence_probe;"
+        "${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
+          redis-cli DEL cpr:ci:persistence-probe
+
+    - name: Start and verify application
+      shell: bash
+      run: |
+        set -euo pipefail
+        compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml)
+        "${compose[@]}" up -d --no-build --wait codex-proxy-rs
+        status="$(curl --silent --show-error --output /dev/null --write-out '%{http_code}' \
+          "http://127.0.0.1:8080/healthz")"
+        test "$status" = 204
+        test "$("${compose[@]}" exec -T codex-proxy-rs id -u | tr -d '\r')" = 10001
+        test "$("${compose[@]}" exec -T codex-proxy-rs id -g | tr -d '\r')" = 10001
+        test "$("${compose[@]}" exec -T codex-proxy-rs date +%z | tr -d '\r')" = +0800
+        test "$("${compose[@]}" exec -T codex-proxy-rs cat /etc/timezone | tr -d '\r')" = Asia/Shanghai
+        "${compose[@]}" exec -T codex-proxy-rs sh -c \
+          'touch /app/.runtime/data/.ci-write /app/.runtime/logs/.ci-write && rm /app/.runtime/data/.ci-write /app/.runtime/logs/.ci-write'
+
+    - name: Verify clean logs and graceful shutdown
+      shell: bash
+      run: |
+        set -euo pipefail
+        compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml)
+        "${compose[@]}" stop --timeout 30 codex-proxy-rs
+        container_id="$("${compose[@]}" ps -a -q codex-proxy-rs)"
+        test -n "$container_id"
+        test "$(docker inspect --format '{{.State.ExitCode}}' "$container_id")" = 0
+        "${compose[@]}" logs --no-color --timestamps codex-proxy-rs \
+          > "$DIAGNOSTICS_DIR/application.log"
+        "${compose[@]}" logs --no-color --timestamps postgres \
+          > "$DIAGNOSTICS_DIR/postgres.log"
+        "${compose[@]}" logs --no-color --timestamps redis \
+          > "$DIAGNOSTICS_DIR/redis.log"
+        if grep --extended-regexp --ignore-case \
+          '"level"[[:space:]]*:[[:space:]]*"(warn|error|fatal|panic)"|(^|[^[:alnum:]_])panic([^[:alnum:]_]|$)' \
+          "$DIAGNOSTICS_DIR/application.log" \
+          || grep --extended-regexp --ignore-case \
+            '(^|[[:space:]])(warning|error|fatal|panic):' \
+            "$DIAGNOSTICS_DIR/postgres.log" \
+          || grep --extended-regexp --ignore-case \
+            '[0-9]+:[A-Z][[:space:]].*[[:space:]]#[[:space:]]|(^|[|[:space:]])(warning|error|fatal|panic)(:|[[:space:]])' \
+            "$DIAGNOSTICS_DIR/redis.log"; then
+          echo "container logs contain a warning or error severity" >&2
+          exit 1
+        fi
+
+    - name: Collect container diagnostics
+      if: always()
+      shell: bash
+      run: |
+        set +e
+        mkdir -p "$DIAGNOSTICS_DIR"
+        raw_dir="$(mktemp -d)"
+        compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml)
+        "${compose[@]}" config > "$raw_dir/compose-config.yaml" 2>&1
+        "${compose[@]}" ps -a > "$raw_dir/compose-ps.txt" 2>&1
+        "${compose[@]}" logs --no-color --timestamps > "$raw_dir/compose.log" 2>&1
+        mapfile -t container_ids < <("${compose[@]}" ps -a -q)
+        if [ "${#container_ids[@]}" -gt 0 ]; then
+          docker inspect "${container_ids[@]}" > "$raw_dir/docker-inspect.json" 2>&1
+        fi
+        RAW_DIR="$raw_dir" OUTPUT_DIR="$DIAGNOSTICS_DIR" ruby <<'RUBY'
+        raw_dir = ENV.fetch("RAW_DIR")
+        output_dir = ENV.fetch("OUTPUT_DIR")
+        secrets = [
+          ENV.fetch("CI_ADMIN_PASSWORD"),
+          ENV.fetch("CI_POSTGRES_PASSWORD"),
+          ENV.fetch("CI_REDIS_PASSWORD"),
+        ]
+        encoded_secrets = secrets.map do |secret|
+          secret.encode("UTF-8").bytes.map do |byte|
+            character = byte.chr
+            character.match?(/[A-Za-z0-9]/) ? character : format("%%%02X", byte)
+          end.join
+        end
+
+        Dir.children(raw_dir).each do |name|
+          content = File.binread(File.join(raw_dir, name))
+          (secrets + encoded_secrets).each do |secret|
+            content = content.gsub(secret, "<redacted>")
+          end
+          File.binwrite(File.join(output_dir, name), content)
+        end
+        RUBY
+        rm -rf "$raw_dir"
+        cp trivy-results.json trivy-results.sarif "$DIAGNOSTICS_DIR/" 2>/dev/null || true
+
+    - name: Upload container diagnostics
+      if: always()
+      uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+      with:
+        name: ${{ inputs.artifact-name }}
+        path: ${{ runner.temp }}/codex-proxy-rs-diagnostics
+        if-no-files-found: warn
+        retention-days: 7
+
+    - name: Remove isolated runtime
+      if: always()
+      shell: bash
+      run: |
+        docker compose --project-name "$COMPOSE_PROJECT_NAME" \
+          -f deploy/compose.yaml down --remove-orphans || true
+        sudo rm -rf "$GITHUB_WORKSPACE/.runtime" "$GITHUB_WORKSPACE/deploy/config.yaml"

.github/workflows/_container.yml

@@ -17,35 +17,43 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 45
     env:
-      COMPOSE_PROJECT_NAME: cpr-ci-${{ github.run_id }}-${{ github.run_attempt }}
       CPR_IMAGE: codex-proxy-rs:ci-${{ inputs.ref }}
       TRIVY_QUIET: 'true'
       TRIVY_SKIP_VERSION_CHECK: 'true'
     steps:
-      - name: Define isolated runtime values
-        shell: bash
-        run: |
-          set -euo pipefail
-          admin_password="$(openssl rand -hex 24)"
-          postgres_password="$(openssl rand -hex 24)"
-          redis_password="$(openssl rand -hex 24)"
-          echo "::add-mask::$admin_password"
-          echo "::add-mask::$postgres_password"
-          echo "::add-mask::$redis_password"
-          {
-            echo "DIAGNOSTICS_DIR=$RUNNER_TEMP/codex-proxy-rs-diagnostics"
-            echo "CI_ADMIN_PASSWORD=$admin_password"
-            echo "CI_POSTGRES_PASSWORD=$postgres_password"
-            echo "CI_REDIS_PASSWORD=$redis_password"
-          } >> "$GITHUB_ENV"
-
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
         with:
           ref: ${{ inputs.ref }}
 
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        id: buildx
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
+
+      - name: Cache Cargo mounts
+        id: cargo-cache
+        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: ${{ runner.temp }}/container-cargo
+          key: container-cargo-v1-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles('backend/Cargo.lock', 'backend/**/Cargo.toml', 'deploy/Dockerfile') }}-${{ inputs.ref }}
+          restore-keys: |
+            container-cargo-v1-${{ runner.os }}-${{ runner.arch }}-${{ hashFiles('backend/Cargo.lock', 'backend/**/Cargo.toml', 'deploy/Dockerfile') }}-
+            container-cargo-v1-${{ runner.os }}-${{ runner.arch }}-
+
+      # The GHA layer exporter does not persist RUN --mount=type=cache contents.
+      # Extraction runs before actions/cache saves its directories in post steps.
+      - name: Restore Cargo mounts to BuildKit
+        uses: reproducible-containers/buildkit-cache-dance@5422eac04292c961a382e0f584ea0f03ad9da723 # v3.4.0
+        with:
+          builder: ${{ steps.buildx.outputs.name }}
+          scratch-dir: ${{ runner.temp }}/container-cache-dance
+          cache-map: |
+            {
+              "${{ runner.temp }}/container-cargo/registry": "/usr/local/cargo/registry",
+              "${{ runner.temp }}/container-cargo/git": "/usr/local/cargo/git",
+              "${{ runner.temp }}/container-cargo/target": "/app/backend/target"
+            }
+          skip-extraction: ${{ steps.cargo-cache.outputs.cache-hit }}
 
       - name: Build runtime image
         uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
@@ -61,209 +69,9 @@ jobs:
           cache-from: type=gha,scope=runtime-ci
           cache-to: type=gha,mode=max,scope=runtime-ci
 
-      - name: Generate Trivy SARIF
-        uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
+      - name: Verify runtime image
+        uses: ./.github/actions/verify-container
         with:
-          image-ref: ${{ env.CPR_IMAGE }}
-          version: v0.72.0
-          format: sarif
-          output: trivy-results.sarif
-          severity: HIGH,CRITICAL
-          vuln-type: os,library
-          scanners: vuln
-          ignore-unfixed: true
-          exit-code: '0'
-
-      - name: Upload Trivy SARIF
-        if: >-
-          ${{ hashFiles('trivy-results.sarif') != '' &&
-              (github.event_name != 'pull_request' ||
-               github.event.pull_request.head.repo.full_name == github.repository) }}
-        uses: github/codeql-action/upload-sarif@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd # v4.37.7
-        with:
-          sarif_file: trivy-results.sarif
-          category: runtime-container
-
-      - name: Enforce Trivy vulnerability gate
-        uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
-        with:
-          image-ref: ${{ env.CPR_IMAGE }}
-          version: v0.72.0
-          format: table
-          severity: HIGH,CRITICAL
-          vuln-type: os,library
-          scanners: vuln
-          ignore-unfixed: true
-          exit-code: '1'
-
-      - name: Prepare isolated runtime
-        shell: bash
-        run: |
-          set -euo pipefail
-          umask 0077
-          # Bind roots hand off ownership to the image-specific database users.
-          # Sticky directories keep that initialization compatible with user-namespaced runners.
-          install -d -m 1777 .runtime/postgres .runtime/redis
-          mkdir -p "$DIAGNOSTICS_DIR"
-          sudo install -d -m 0770 -o "$(id -u)" -g 10001 \
-            .runtime/data .runtime/logs
-          ruby <<'RUBY'
-          path = "deploy/config.example.yaml"
-          content = File.read(path)
-          replacements = {
-            "password: &postgres_password ''" => "password: &postgres_password '#{ENV.fetch("CI_POSTGRES_PASSWORD")}'",
-            "password: &redis_password ''" => "password: &redis_password '#{ENV.fetch("CI_REDIS_PASSWORD")}'",
-            "default_password: ''" => "default_password: '#{ENV.fetch("CI_ADMIN_PASSWORD")}'",
-          }
-          replacements.each do |placeholder, configured|
-            raise "missing config placeholder: #{placeholder}" unless content.sub!(placeholder, configured)
-          end
-          File.write("deploy/config.yaml", content)
-          RUBY
-          sudo chown "$(id -u):10001" deploy/config.yaml
-          chmod 0640 deploy/config.yaml
-
-      - name: Validate Docker Compose
-        shell: bash
-        run: |
-          set -euo pipefail
-          docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml config --quiet
-
-      - name: Configure Redis host memory overcommit
-        shell: bash
-        run: |
-          set -euo pipefail
-          sudo sysctl -w vm.overcommit_memory=1
-          test "$(sysctl -n vm.overcommit_memory)" = 1
-
-      - name: Verify PostgreSQL and Redis volume persistence
-        shell: bash
-        run: |
-          set -euo pipefail
-          compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml)
-          "${compose[@]}" up -d --no-build --wait postgres redis
-          test "$("${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
-            psql -At -U codex_proxy -d codex_proxy -c "SHOW TimeZone;" | tr -d '\r')" = Asia/Shanghai
-          "${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
-            psql -v ON_ERROR_STOP=1 -U codex_proxy -d codex_proxy -c \
-            "CREATE TABLE cpr_ci_persistence_probe (value text PRIMARY KEY); INSERT INTO cpr_ci_persistence_probe VALUES ('persisted');"
-          "${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
-            redis-cli SET cpr:ci:persistence-probe persisted
-          "${compose[@]}" up -d --no-build --wait --force-recreate postgres redis
-          test "$("${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
-            psql -At -U codex_proxy -d codex_proxy -c \
-            "SELECT value FROM cpr_ci_persistence_probe;")" = persisted
-          test "$("${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
-            redis-cli --raw GET cpr:ci:persistence-probe | tr -d '\r')" = persisted
-          "${compose[@]}" exec -T -e PGPASSWORD="$CI_POSTGRES_PASSWORD" postgres \
-            psql -v ON_ERROR_STOP=1 -U codex_proxy -d codex_proxy -c \
-            "DROP TABLE cpr_ci_persistence_probe;"
-          "${compose[@]}" exec -T -e REDISCLI_AUTH="$CI_REDIS_PASSWORD" redis \
-            redis-cli DEL cpr:ci:persistence-probe
-
-      - name: Start and verify application
-        shell: bash
-        run: |
-          set -euo pipefail
-          compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml)
-          "${compose[@]}" up -d --no-build --wait codex-proxy-rs
-          status="$(curl --silent --show-error --output /dev/null --write-out '%{http_code}' \
-            "http://127.0.0.1:8080/healthz")"
-          test "$status" = 204
-          test "$("${compose[@]}" exec -T codex-proxy-rs id -u | tr -d '\r')" = 10001
-          test "$("${compose[@]}" exec -T codex-proxy-rs id -g | tr -d '\r')" = 10001
-          test "$("${compose[@]}" exec -T codex-proxy-rs date +%z | tr -d '\r')" = +0800
-          test "$("${compose[@]}" exec -T codex-proxy-rs cat /etc/timezone | tr -d '\r')" = Asia/Shanghai
-          "${compose[@]}" exec -T codex-proxy-rs sh -c \
-            'touch /app/.runtime/data/.ci-write /app/.runtime/logs/.ci-write && rm /app/.runtime/data/.ci-write /app/.runtime/logs/.ci-write'
-
-      - name: Verify clean logs and graceful shutdown
-        shell: bash
-        run: |
-          set -euo pipefail
-          compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml)
-          "${compose[@]}" stop --timeout 30 codex-proxy-rs
-          container_id="$("${compose[@]}" ps -a -q codex-proxy-rs)"
-          test -n "$container_id"
-          test "$(docker inspect --format '{{.State.ExitCode}}' "$container_id")" = 0
-          "${compose[@]}" logs --no-color --timestamps codex-proxy-rs \
-            > "$DIAGNOSTICS_DIR/application.log"
-          "${compose[@]}" logs --no-color --timestamps postgres \
-            > "$DIAGNOSTICS_DIR/postgres.log"
-          "${compose[@]}" logs --no-color --timestamps redis \
-            > "$DIAGNOSTICS_DIR/redis.log"
-          if grep --extended-regexp --ignore-case \
-            '"level"[[:space:]]*:[[:space:]]*"(warn|error|fatal|panic)"|(^|[^[:alnum:]_])panic([^[:alnum:]_]|$)' \
-            "$DIAGNOSTICS_DIR/application.log" \
-            || grep --extended-regexp --ignore-case \
-              '(^|[[:space:]])(warning|error|fatal|panic):' \
-              "$DIAGNOSTICS_DIR/postgres.log" \
-            || grep --extended-regexp --ignore-case \
-              '[0-9]+:[A-Z][[:space:]].*[[:space:]]#[[:space:]]|(^|[|[:space:]])(warning|error|fatal|panic)(:|[[:space:]])' \
-              "$DIAGNOSTICS_DIR/redis.log"; then
-            echo "container logs contain a warning or error severity" >&2
-            exit 1
-          fi
-
-      - name: Collect container diagnostics
-        if: always()
-        shell: bash
-        run: |
-          set +e
-          mkdir -p "$DIAGNOSTICS_DIR"
-          raw_dir="$(mktemp -d)"
-          compose=(docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml)
-          "${compose[@]}" config > "$raw_dir/compose-config.yaml" 2>&1
-          "${compose[@]}" ps -a > "$raw_dir/compose-ps.txt" 2>&1
-          "${compose[@]}" logs --no-color --timestamps > "$raw_dir/compose.log" 2>&1
-          mapfile -t container_ids < <("${compose[@]}" ps -a -q)
-          if [ "${#container_ids[@]}" -gt 0 ]; then
-            docker inspect "${container_ids[@]}" > "$raw_dir/docker-inspect.json" 2>&1
-          fi
-          RAW_DIR="$raw_dir" OUTPUT_DIR="$DIAGNOSTICS_DIR" ruby <<'RUBY'
-          raw_dir = ENV.fetch("RAW_DIR")
-          output_dir = ENV.fetch("OUTPUT_DIR")
-          secrets = [
-            ENV.fetch("CI_ADMIN_PASSWORD"),
-            ENV.fetch("CI_POSTGRES_PASSWORD"),
-            ENV.fetch("CI_REDIS_PASSWORD"),
-          ]
-          encoded_secrets = secrets.map do |secret|
-            secret.encode("UTF-8").bytes.map do |byte|
-              character = byte.chr
-              character.match?(/[A-Za-z0-9]/) ? character : format("%%%02X", byte)
-            end.join
-          end
-
-          Dir.children(raw_dir).each do |name|
-            content = File.binread(File.join(raw_dir, name))
-            (secrets + encoded_secrets).each do |secret|
-              content = content.gsub(secret, "<redacted>")
-            end
-            File.binwrite(File.join(output_dir, name), content)
-          end
-          RUBY
-          rm -rf "$raw_dir"
-          cp trivy-results.sarif "$DIAGNOSTICS_DIR/" 2>/dev/null || true
-
-      - name: Upload container diagnostics
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: container-diagnostics-${{ github.run_id }}-${{ github.run_attempt }}
-          path: ${{ runner.temp }}/codex-proxy-rs-diagnostics
-          if-no-files-found: warn
-          retention-days: 7
-
-      - name: Remove isolated runtime
-        if: always()
-        shell: bash
-        run: |
-          docker compose --project-name "$COMPOSE_PROJECT_NAME" \
-            -f deploy/compose.yaml down --remove-orphans || true
-          sudo rm -rf "$GITHUB_WORKSPACE/.runtime" "$GITHUB_WORKSPACE/deploy/config.yaml"
+          image: ${{ env.CPR_IMAGE }}
+          platform: linux/amd64
+          artifact-name: container-diagnostics-${{ github.run_id }}-${{ github.run_attempt }}-amd64

.github/workflows/_quality.yml

@@ -33,6 +33,8 @@ jobs:
     timeout-minutes: 30
     env:
       CARGO_TERM_COLOR: always
+      # Rust 1.97 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
       CPR_TEST_REDIS_URL: redis://127.0.0.1:6379
     services:

.github/workflows/ci.yml

@@ -4,6 +4,8 @@ on:
   push:
     branches:
       - main
+    paths-ignore:
+      - 'release/version.yaml'
   pull_request:
     branches:
       - main
@@ -48,6 +50,7 @@ jobs:
               - 'deploy/**'
               - '.dockerignore'
               - 'release/version.yaml'
+              - '.github/actions/**'
               - '.github/workflows/_container.yml'
               - '.github/workflows/ci.yml'
 

.github/workflows/release.yml

@@ -185,8 +185,9 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             backend/target
-          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
+          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}-${{ needs.release-info.outputs.git_sha }}
           restore-keys: |
+            cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
             cargo-v2-${{ runner.os }}-${{ matrix.target }}-
 
       - name: Build binary
@@ -250,8 +251,9 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             backend/target
-          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
+          key: cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}-${{ needs.release-info.outputs.git_sha }}
           restore-keys: |
+            cargo-v2-${{ runner.os }}-${{ matrix.target }}-${{ hashFiles('backend/Cargo.lock', 'backend/rust-toolchain.toml', 'backend/**/Cargo.toml', 'backend/.cargo/config.toml') }}
             cargo-v2-${{ runner.os }}-${{ matrix.target }}-
 
       - name: Build binary
@@ -399,6 +401,7 @@ jobs:
       contents: read
       packages: write
       id-token: write
+      security-events: write
     env:
       TRIVY_QUIET: 'true'
       TRIVY_SKIP_VERSION_CHECK: 'true'
@@ -448,7 +451,7 @@ jobs:
           PY
 
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
 
       - name: Login to GHCR
         uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
@@ -482,19 +485,31 @@ jobs:
             org.opencontainers.image.source=https://github.com/zyycn/codex-proxy-rs
           tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:sha-${{ needs.release-info.outputs.git_sha }}-${{ matrix.arch }}
 
-      - name: Scan exact app image digest
-        uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
-        env:
-          TRIVY_PLATFORM: ${{ matrix.dockerPlatform }}
+      - name: Verify exact app image digest
+        uses: ./.github/actions/verify-container
         with:
-          image-ref: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}@${{ steps.build-and-push.outputs.digest }}
-          version: v0.72.0
-          format: table
-          severity: HIGH,CRITICAL
-          vuln-type: os,library
-          scanners: vuln
-          ignore-unfixed: true
-          exit-code: '1'
+          image: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}@${{ steps.build-and-push.outputs.digest }}
+          platform: ${{ matrix.dockerPlatform }}
+          artifact-name: container-diagnostics-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.arch }}
+
+      - name: Record verified image digest
+        shell: bash
+        env:
+          IMAGE_DIGEST: ${{ steps.build-and-push.outputs.digest }}
+          IMAGE_ARCH: ${{ matrix.arch }}
+        run: |
+          set -euo pipefail
+          [[ "$IMAGE_DIGEST" =~ ^sha256:[a-f0-9]{64}$ ]]
+          mkdir -p dist/digests
+          printf '%s\n' "$IMAGE_DIGEST" > "dist/digests/linux-${IMAGE_ARCH}.txt"
+
+      - name: Upload verified image digest
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: image-digest-${{ matrix.os }}-${{ matrix.arch }}
+          path: dist/digests/*.txt
+          if-no-files-found: error
+          retention-days: 1
 
   publish:
     needs: [release-info, package-assets, build-docker-image]
@@ -518,8 +533,15 @@ jobs:
           name: release-assets
           path: dist/release
 
+      - name: Download verified image digests
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          pattern: image-digest-*
+          path: dist/digests
+          merge-multiple: true
+
       - name: Setup Docker Buildx
-        uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
+        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4.3.0
 
       - name: Install Cosign
         uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2
@@ -549,7 +571,12 @@ jobs:
             platform="${platform//[[:space:]]/}"
             [ -n "${platform}" ] || continue
             arch="${platform##*/}"
-            sources+=("${image}:sha-${GIT_SHA}-${arch}")
+            digest="$(cat "dist/digests/linux-${arch}.txt")"
+            if [[ ! "$digest" =~ ^sha256:[a-f0-9]{64}$ ]]; then
+              echo "invalid verified image digest for ${platform}" >&2
+              exit 1
+            fi
+            sources+=("${image}@${digest}")
           done
 
           if [ "${#sources[@]}" -eq 0 ]; then
@@ -617,7 +644,7 @@ jobs:
           cosign sign --yes "${images[@]}"
 
       - name: Publish GitHub Release
-        uses: softprops/action-gh-release@3d0d9888cb7fd7b750713d6e236d1fcb99157228 # v3.0.2
+        uses: softprops/action-gh-release@efb35369e0ad2afab669f228072c1b0d510eae64 # v3.0.3
         with:
           tag_name: ${{ needs.release-info.outputs.tag }}
           generate_release_notes: true

README.md

@@ -5,195 +5,120 @@
 
 # Codex Proxy RS
 
-**基于 Rust 的多 Provider 透明 AI 网关**
+面向 Codex 的自托管多账号 AI 网关。
 
 [![CI](https://github.com/zyycn/codex-proxy-rs/actions/workflows/ci.yml/badge.svg)](https://github.com/zyycn/codex-proxy-rs/actions/workflows/ci.yml)
 [![Release](https://img.shields.io/github/v/release/zyycn/codex-proxy-rs?display_name=tag&sort=semver&style=flat-square)](https://github.com/zyycn/codex-proxy-rs/releases)
 [![GHCR](https://img.shields.io/badge/GHCR-codex--proxy--rs-2496ED?logo=docker&logoColor=white&style=flat-square)](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)
-[![MIT](https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square)](https://opensource.org/license/mit)
 
-[快速开始](#快速开始) · [客户端接入](#客户端接入) · [运行维护](#运行维护) · [部署](deploy/README.md) · [接口](docs/api.md) · [架构](docs/architecture.md)
+[功能](#功能) · [快速开始](#快速开始) · [客户端接入](#客户端接入) · [文档](#文档)
 
 </div>
 
-> [!NOTE]
-> 数据面支持 OpenAI Responses、Images 和模型目录协议，不提供 `/v1/chat/completions`。
+将 OpenAI、xAI 账号接入同一个服务，通过网页管理账号、分配客户端密钥和查看使用情况。
+客户端使用统一的访问地址与代理密钥，上游账号凭据由服务端管理。
 
 ## 功能
 
-| 领域 | 当前能力 |
-| --- | --- |
-| 数据面 | Responses JSON、SSE、WebSocket、review 子代理、Images 生成/编辑与模型目录 |
-| Provider | 固定 `openai`、`xai` 两个 Provider，各自拥有 OAuth、credential、额度、目录与 transport |
-| 路由 | Client Key 限定账号分组；按模型能力编译 Provider 候选；支持全局精确模型映射、会话亲和和安全 fallback |
-| 透明边界 | OpenAI 保留未知请求字段及字段顺序，并原样转发 SSE、WebSocket 与 Images 业务字节；xAI 在 Provider 内转换协议 |
-| 账号 | OAuth、OpenAI AT/RT、账号文件与 Agent Identity 导入，credential/额度刷新、账号恢复及主动额度重置卡 |
-| 管理 | 账号与分组、Client Key、运行设置、用量/错误观测、S3/R2 备份、系统更新与回滚 |
-| 计量 | Token、图片、费用、延迟、账号与 Provider 归因，并记录上游响应确认的实际 `service_tier` |
+- **账号管理**：OAuth 授权、账号导入、凭据刷新与额度查看。
+- **访问控制**：通过账号分组分配密钥权限，设置并发和请求频率。
+- **客户端接入**：支持 Codex CLI、桌面端与 Responses API 客户端，提供 HTTP 流式响应和 WebSocket。
+- **请求诊断**：查看请求记录、用量、费用、延迟和错误详情。
+- **部署运维**：Docker Compose 部署、S3/R2 数据库备份、同大版本在线更新与回滚。
 
-架构边界、状态所有权和请求不变量见 [架构文档](docs/architecture.md)。
+图片生成、编辑和 Codex 独立搜索由 OpenAI 账号提供；模型与功能的可用性取决于上游账号权限。
+
+> [!NOTE]
+> 本项目提供 Responses API，不支持 `/v1/chat/completions`。接入前请确认客户端支持 Responses 协议。
 
 ## 快速开始
 
-需要 Docker Engine 与 Docker Compose Plugin。
+使用 Docker Compose 部署发布镜像 `ghcr.io/zyycn/codex-proxy-rs:latest`，同时启动 PostgreSQL 和 Redis。
+以下命令适用于 Linux amd64/arm64，需要 Docker Engine、Docker Compose Plugin、curl 和 OpenSSL。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。
 
-### 1. 准备配置和目录
+### 1. 下载部署文件并配置
 
 ```bash
-git clone https://github.com/zyycn/codex-proxy-rs.git
+mkdir -p codex-proxy-rs/deploy
 cd codex-proxy-rs
 
+curl -fsSL https://raw.githubusercontent.com/zyycn/codex-proxy-rs/main/deploy/compose.yaml \
+  -o deploy/compose.yaml
+curl -fsSL https://raw.githubusercontent.com/zyycn/codex-proxy-rs/main/deploy/config.example.yaml \
+  -o deploy/config.example.yaml
+
 mkdir -p .runtime/data .runtime/logs
 install -d -m 0750 .runtime/postgres .runtime/redis
 cp deploy/config.example.yaml deploy/config.yaml
 sudo chown "$(id -u):10001" deploy/config.yaml
 chmod 0640 deploy/config.yaml
-```
-
-分别生成 PostgreSQL 与 Redis 密码：
-
-```bash
-openssl rand -hex 24
-openssl rand -hex 24
-```
-
-把两个结果分别写入 `deploy/config.yaml`，再设置管理员初始密码：
-
-| 配置 | 约束 |
-| --- | --- |
-| `store.database.password` | 48 位十六进制 |
-| `store.redis.password` | 48 位十六进制 |
-| `admin.default_password` | 至少 12 位，不能包含 `$` |
-
-PostgreSQL、Redis 和应用从同一份 `config.yaml` 读取基础设施密码，不需要额外导出环境变量。
-管理员密码只在首次创建管理员时生效。
-
-Linux 需要允许容器组写入运行目录：
-
-```bash
 sudo chown -R "$(id -u):10001" .runtime/data .runtime/logs
 chmod 0770 .runtime/data .runtime/logs
 ```
 
-### 2. 启动
+分别生成数据库和 Redis 密码：
+
+```bash
+openssl rand -hex 24
+openssl rand -hex 24
+```
+
+编辑 `deploy/config.yaml`，填好以下三项：
+
+| 配置项 | 填写内容 |
+| --- | --- |
+| `store.database.password` | 第一个生成的 48 位十六进制密码 |
+| `store.redis.password` | 第二个生成的 48 位十六进制密码 |
+| `admin.default_password` | 管理员初始密码，至少 12 位，不能包含 `$` |
+
+不需要创建 `.env`。管理员初始密码只在首次创建账号时使用。
+
+### 2. 启动服务
 
 ```bash
 docker compose -f deploy/compose.yaml config --quiet
 docker compose -f deploy/compose.yaml pull
-docker compose -f deploy/compose.yaml up -d --no-build
+docker compose -f deploy/compose.yaml up -d --no-build --wait
 curl -i http://127.0.0.1:8080/healthz
 ```
 
-`204 No Content` 表示应用、PostgreSQL 与 Redis 均可用。管理端地址为
-`http://127.0.0.1:8080`。
+健康检查返回 `204 No Content` 后，打开 `http://127.0.0.1:8080`，
+使用 `admin@cpr.local` 和刚设置的管理员密码登录。
 
-### 3. 初始化网关
+默认地址只能在服务器本机访问。从其他设备使用时，需要配置
+[HTTPS 反向代理](deploy/README.md#公网访问)。
 
-1. 使用 `admin@cpr.local` 与初始密码登录。
-2. 导入或授权 Provider 账号：OpenAI 支持 OAuth、逐行 AT/RT、OAuth JSON 与 Agent Identity；
-   xAI 支持 OAuth 和账号 JSON。
-3. 创建账号分组并按需配置全局模型映射。未命中的模型名原样交给候选 Provider。
-4. 创建 `sk_...` Client Key，选择可用账号分组，并设置速率和并发限制；空分组范围表示全部账号。
+### 3. 添加账号与客户端密钥
 
-OpenAI RT 导入会先向官方 token endpoint 换取 AT；仅 AT 的账号不具备自动续期能力，
-能否参与调度仍取决于 token 中可验证的身份与后续上游事实。账号导入和首次 OAuth 创建会尽力读取一次额度，
-额度上游暂时失败不会回滚已提交的账号。
-
-OpenAI 账号的主动重置卡只在用户打开相应弹窗或手工刷新时查询。消费成功后管理端重新查询卡片与额度；
-系统不会通过修改本地 `reset_at` 伪造重置。完整账号合同见 [账号接口](docs/api.md#5-账号)。
-
-> [!IMPORTANT]
-> xAI 使用 OAuth session，不支持把 xAI API Key 作为上游 credential。
-
-完整的权限、密码轮换、备份和升级规则见 [部署文档](deploy/README.md)。
+1. 在「账号」中添加 OpenAI 或 xAI 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。
 
 ## 客户端接入
 
+**Codex CLI / 桌面端**：在「使用密钥」中按操作系统复制配置，或通过 CCSwitch 导入。
+合并到客户端配置后重启 Codex。完整步骤、生图配置与排障见[客户端配置](deploy/README.md#客户端配置)。
+
+**其他 Responses API 客户端**：填写以下信息。
+
 | 配置 | 值 |
 | --- | --- |
-| Base URL | `http://127.0.0.1:8080/v1` |
-| API Key | 管理端创建的 `sk_...` |
-| 鉴权 | `Authorization: Bearer <client-api-key>` |
+| Base URL | `http://127.0.0.1:8080/v1`；远程接入使用服务器的 HTTPS 地址 |
+| API Key | 管理端创建的 `sk_...` 客户端密钥 |
+
+可用模型以该密钥查询到的模型列表为准：
 
 ```bash
 curl http://127.0.0.1:8080/v1/models \
   -H 'Authorization: Bearer <client-api-key>'
-
-curl http://127.0.0.1:8080/v1/responses \
-  -H 'Authorization: Bearer <client-api-key>' \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model": "<model-id>",
-    "input": "Reply with pong.",
-    "stream": false
-  }'
 ```
 
-<details>
-<summary>公开数据面路由</summary>
-
-| 路由 | 用途 |
-| --- | --- |
-| `POST /v1/responses` | JSON 响应或 SSE Responses 流 |
-| `GET /v1/responses` | Responses WebSocket 升级 |
-| `POST /v1/responses/review` | review 子代理请求 |
-| `POST /v1/images/generations` | OpenAI Images 生成 JSON 透明转发 |
-| `POST /v1/images/edits` | OpenAI Images 编辑 JSON 透明转发 |
-| `GET /v1/models` | 当前 Client Key 账号范围内的模型列表 |
-| `GET /v1/models/catalog` | Codex 客户端展示用模型目录 |
-| `GET /v1/models/{model_id}/info` | Codex 客户端展示用模型详情 |
-| `GET /v1/models/{model_id}` | OpenAI 兼容模型详情 |
-
-所有 `/v1/*` 路由都需要 Client Key。Images 是 OpenAI Provider 自有端点，不读取模型字段，也不参与
-文本模型映射。
-
-</details>
-
-完整的客户端与管理端路由、鉴权、请求字段和 mutation 语义见 [接口文档](docs/api.md)。
-
-## 运行维护
-
-```bash
-# 同一大版本内升级发布镜像
-docker compose -f deploy/compose.yaml pull codex-proxy-rs
-docker compose -f deploy/compose.yaml up -d --no-build
-
-# 查看日志
-docker compose -f deploy/compose.yaml logs -f codex-proxy-rs
-
-# 从当前源码构建
-docker compose -f deploy/compose.yaml build codex-proxy-rs
-docker compose -f deploy/compose.yaml up -d
-```
-
-> [!IMPORTANT]
-> `.runtime/` 保存 PostgreSQL、Redis、日志、OpenAI 会话锚点和在线更新状态。删除该目录会永久清除
-> 本地运行状态。
-
-> [!WARNING]
-> 不支持跨大版本在线升级。升级到新的大版本时请使用全新的 `.runtime/` 数据目录，并重新导入或授权
-> Provider 账号与 Client Key。
-
-Compose 默认只绑定 `127.0.0.1`。公网接入应使用 HTTPS 反向代理，转发 WebSocket upgrade 与真实客户端
-IP；不要暴露 PostgreSQL 或 Redis。当前运行拓扑为单副本，不能通过复制应用容器扩容。
-
-## 维护与发布
-
-仓库版本只能从干净、已同步上游的发布分支发布：
-
-```bash
-release/publish <version>
-```
-
-脚本依赖已登录的 GitHub CLI（`gh auth login`），会更新 `release/version.yaml`、创建约定提交和带注释的
-`v<version>` tag，原子推送分支与 tag，再触发 Release 构建。源码提交、仓库发版和运行实例升级是三个
-独立状态；脚本不会登录服务器或改变任何运行实例。
-
 ## 文档
 
-- [部署与运维](deploy/README.md)
-- [客户端与管理端接口](docs/api.md)
+- [客户端接入与生图](deploy/README.md#客户端配置)
+- [部署、备份与恢复](deploy/README.md)
+- [API 参考](docs/api.md)
 - [系统架构](docs/architecture.md)
-- [数据库迁移规则](backend/migrations/README.md)
-- [Release](https://github.com/zyycn/codex-proxy-rs/releases)
-- [容器镜像](https://github.com/zyycn/codex-proxy-rs/pkgs/container/codex-proxy-rs)
+- [管理端主题](docs/theme.md)
+- [数据库迁移](backend/migrations/README.md)

backend/apps/gateway/Cargo.toml

@@ -26,7 +26,7 @@ tokio = { version = "1.52.3", default-features = false, features = ["rt-multi-th
 [dev-dependencies]
 config = { version = "0.15.23", default-features = false, features = ["yaml"] }
 serde_json = "1"
-syn = { version = "3.0.3", features = ["full"] }
+syn = { version = "3.0.3", features = ["full", "visit"] }
 tempfile = "3.27.0"
 
 [lints]

backend/apps/gateway/src/bootstrap.rs

@@ -79,6 +79,7 @@ pub async fn run() -> Result<(), BootstrapError> {
         vec![openai.admin_provider(), xai.admin_provider()],
         core.snapshot_control(),
         core.account_probe(),
+        host.client_distribution_resolver(),
         host.system_operations(),
     )
     .await?;
@@ -86,6 +87,7 @@ pub async fn run() -> Result<(), BootstrapError> {
 
     let mut probes = store.health_probes();
     probes.extend(core.health_probes());
+    probes.push(host.logging_health_probe());
     let api = gateway_api::initialize(
         api,
         core.execution_service(),

backend/apps/gateway/src/main.rs

@@ -1,6 +1,6 @@
 use std::{env, error::Error, io};
 
-use provider_openai::transport::tls::ensure_rustls_provider;
+use provider_openai::ensure_rustls_provider;
 
 fn main() -> Result<(), Box<dyn Error + Send + Sync>> {
     ensure_rustls_provider();

backend/apps/gateway/tests/architecture.rs

@@ -1,12 +1,15 @@
 //! docs/architecture.md 依赖 DAG 与生产源码纪律的 workspace 级机器校验。
 
 use std::{
+    collections::{BTreeMap, BTreeSet},
     fs,
     path::{Path, PathBuf},
 };
 
+use syn::{Item, visit::Visit};
+
 /// workspace 成员冻结清单;新增 crate 必须同步扩展本文件的依赖规则。
-const WORKSPACE_MEMBERS: &[&str] = &[
+pub(super) const WORKSPACE_MEMBERS: &[&str] = &[
     "apps/gateway",
     "crates/gateway-admin",
     "crates/gateway-api",
@@ -58,6 +61,82 @@ fn gateway_core_depends_on_no_http_db_redis_or_provider_crate() {
     );
 }
 
+#[test]
+fn core_value_owners_do_not_depend_on_execution_or_routing() {
+    let root = backend_root().join("crates/gateway-core/src");
+    for relative in super::rust_files(&root) {
+        let allowed: Option<&[&str]> = match relative.to_str().expect("source path") {
+            "validation.rs" => Some(&[]),
+            "identity.rs" => Some(&["validation"]),
+            "upstream.rs" => Some(&["validation"]),
+            "event.rs" => Some(&["metering", "operation", "upstream", "validation"]),
+            "account/store.rs" => Some(&["account", "error", "identity", "validation"]),
+            path if path.starts_with("policy/") => Some(&["account", "policy", "validation"]),
+            path if path.starts_with("account/") => Some(&["account", "identity", "validation"]),
+            _ => None,
+        };
+        let Some(allowed) = allowed else { continue };
+        let source = fs::read_to_string(root.join(&relative)).expect("read core source");
+        let syntax = syn::parse_file(&source).expect("parse core source");
+        let mut references = CrateReferences::default();
+        references.visit_file(&syntax);
+        for dependency in references.0 {
+            assert!(
+                allowed.contains(&dependency.as_str()),
+                "{} must not depend on crate::{dependency}",
+                relative.display()
+            );
+        }
+    }
+}
+
+#[derive(Default)]
+struct CrateReferences(BTreeSet<String>);
+
+impl<'ast> Visit<'ast> for CrateReferences {
+    fn visit_path(&mut self, path: &'ast syn::Path) {
+        let mut segments = path.segments.iter();
+        if segments
+            .next()
+            .is_some_and(|segment| segment.ident == "crate")
+            && let Some(owner) = segments.next()
+        {
+            self.0.insert(owner.ident.to_string());
+        }
+        syn::visit::visit_path(self, path);
+    }
+
+    fn visit_item_use(&mut self, item: &'ast syn::ItemUse) {
+        self.use_tree(&item.tree, false);
+    }
+}
+
+impl CrateReferences {
+    fn use_tree(&mut self, tree: &syn::UseTree, crate_root: bool) {
+        match tree {
+            syn::UseTree::Path(path) if crate_root => {
+                self.0.insert(path.ident.to_string());
+            }
+            syn::UseTree::Name(name) if crate_root => {
+                self.0.insert(name.ident.to_string());
+            }
+            syn::UseTree::Rename(rename) if crate_root => {
+                self.0.insert(rename.ident.to_string());
+            }
+            syn::UseTree::Path(path) => self.use_tree(&path.tree, path.ident == "crate"),
+            syn::UseTree::Group(group) => {
+                for item in &group.items {
+                    self.use_tree(item, crate_root);
+                }
+            }
+            syn::UseTree::Glob(_) if crate_root => {
+                self.0.insert("*".to_owned());
+            }
+            _ => {}
+        }
+    }
+}
+
 #[test]
 fn gateway_protocol_has_no_workspace_dependencies() {
     for name in dependency_names("crates/gateway-protocol") {
@@ -95,6 +174,36 @@ const PACKAGE_TO_MEMBER: &[(&str, &str)] = &[
     ("provider-xai", "crates/providers/xai"),
 ];
 
+/// Adapter/provider 根门面的稳定合同模块；任何增减都必须同步完成边界审计。
+const ADAPTER_PUBLIC_MODULES: &[(&str, &[&str])] = &[
+    ("crates/gateway-api", &["admin", "openai"]),
+    (
+        "crates/gateway-host",
+        &[
+            "client_distribution",
+            "config",
+            "serve",
+            "system_update",
+            "workers",
+        ],
+    ),
+    ("crates/gateway-store", &["backup", "postgres", "redis"]),
+    (
+        "crates/providers/openai",
+        &["config", "credential", "transport"],
+    ),
+    (
+        "crates/providers/xai",
+        &["config", "credential", "transport"],
+    ),
+];
+
+/// 不对应单一生产模块、而是校验 crate/workspace 整体契约的根级测试场景。
+const ROOT_TEST_SCENARIOS: &[(&str, &[&str])] = &[
+    ("apps/gateway", &["architecture"]),
+    ("crates/gateway-api", &["architecture"]),
+];
+
 /// 冻结的 workspace 内部运行时依赖边；新增/删除任何边都必须同步本表。
 const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
     ("codex-proxy-rs", "gateway-admin"),
@@ -123,6 +232,46 @@ const ALLOWED_INTERNAL_EDGES: &[(&str, &str)] = &[
 #[test]
 fn workspace_internal_dependency_edges_match_frozen_dag() {
     let metadata = cargo_metadata_json();
+    let actual = workspace_runtime_dependency_edges(&metadata);
+    let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
+        .iter()
+        .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
+        .collect();
+    expected.sort();
+
+    assert_eq!(
+        actual, expected,
+        "workspace internal dependency edges diverged from the frozen DAG"
+    );
+}
+
+#[test]
+fn runtime_dependency_edges_exclude_dev_build_and_external_dependencies() {
+    let metadata = serde_json::json!({
+        "packages": [
+            {
+                "name": "gateway-api",
+                "dependencies": [
+                    { "name": "gateway-core", "kind": null },
+                    { "name": "gateway-store", "kind": "dev" },
+                    { "name": "gateway-host", "kind": "build" },
+                    { "name": "serde", "kind": null }
+                ]
+            },
+            {
+                "name": "external-package",
+                "dependencies": [{ "name": "gateway-core", "kind": null }]
+            }
+        ]
+    });
+
+    assert_eq!(
+        workspace_runtime_dependency_edges(&metadata),
+        vec![("gateway-api".to_owned(), "gateway-core".to_owned())]
+    );
+}
+
+fn workspace_runtime_dependency_edges(metadata: &serde_json::Value) -> Vec<(String, String)> {
     let packages = metadata["packages"]
         .as_array()
         .expect("cargo metadata packages");
@@ -140,31 +289,43 @@ fn workspace_internal_dependency_edges_match_frozen_dag() {
             if !internal_names.contains(dep_name) {
                 continue;
             }
-            let is_runtime_edge = dependency["dep_kinds"]
-                .as_array()
-                .map(|kinds| {
-                    kinds
-                        .iter()
-                        .any(|kind| kind["kind"].as_str() == Some("normal"))
-                })
-                .unwrap_or(true);
-            if is_runtime_edge {
+            if dependency.get("kind").expect("dependency kind").is_null() {
                 actual.push((name.to_owned(), dep_name.to_owned()));
             }
         }
     }
 
-    let mut expected: Vec<(String, String)> = ALLOWED_INTERNAL_EDGES
-        .iter()
-        .map(|(from, to)| ((*from).to_owned(), (*to).to_owned()))
-        .collect();
     actual.sort();
-    expected.sort();
+    actual
+}
 
-    assert_eq!(
-        actual, expected,
-        "workspace internal dependency edges diverged from the frozen DAG"
-    );
+#[test]
+fn adapter_public_module_surfaces_match_allowlist() {
+    for (member, allowed) in ADAPTER_PUBLIC_MODULES {
+        let root = backend_root().join(member).join("src/lib.rs");
+        let source = fs::read_to_string(&root).expect("read adapter crate root");
+        let syntax = syn::parse_file(&source).expect("parse adapter crate root");
+        let actual = syntax
+            .items
+            .iter()
+            .filter_map(|item| match item {
+                Item::Mod(module) if matches!(module.vis, syn::Visibility::Public(_)) => {
+                    Some(module.ident.to_string())
+                }
+                _ => None,
+            })
+            .collect::<BTreeSet<_>>();
+        let expected = allowed
+            .iter()
+            .map(|module| (*module).to_owned())
+            .collect::<BTreeSet<_>>();
+        assert_eq!(
+            actual,
+            expected,
+            "{} public module surface diverged from its allowlist",
+            root.display()
+        );
+    }
 }
 
 #[test]
@@ -185,7 +346,192 @@ fn production_sources_do_not_host_tests() {
     }
 }
 
-fn backend_root() -> PathBuf {
+#[test]
+fn workspace_modules_follow_conventional_file_layout() {
+    for member in WORKSPACE_MEMBERS {
+        let member_root = backend_root().join(member);
+        assert_module_tree(&member_root.join("src"), &["lib.rs", "main.rs"]);
+
+        let tests = member_root.join("tests");
+        if tests.is_dir() {
+            assert_module_tree(&tests, &["main.rs"]);
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+enum ModuleLayout {
+    File,
+    Directory,
+}
+
+#[test]
+fn integration_tests_mirror_production_module_tree() {
+    for member in WORKSPACE_MEMBERS {
+        let member_root = backend_root().join(member);
+        let tests_root = member_root.join("tests");
+        if !tests_root.is_dir() {
+            continue;
+        }
+
+        let production = module_layouts(&member_root.join("src"), &["lib.rs", "main.rs"]);
+        let tests = module_layouts(&tests_root, &["main.rs"]);
+        for (module, test_layout) in tests {
+            if module == Path::new("support") {
+                continue;
+            }
+
+            if let Some(production_layout) = production.get(&module) {
+                assert_eq!(
+                    test_layout,
+                    *production_layout,
+                    "{} must mirror the production module layout for {}",
+                    tests_root.join(module.with_extension("rs")).display(),
+                    member_root.join("src").join(&module).display(),
+                );
+                continue;
+            }
+
+            let has_production_owner = module
+                .parent()
+                .into_iter()
+                .flat_map(Path::ancestors)
+                .take_while(|ancestor| !ancestor.as_os_str().is_empty())
+                .any(|ancestor| production.contains_key(ancestor));
+            assert!(
+                has_production_owner || root_test_scenario_allowed(member, &module),
+                "{} has no mirrored production module owner",
+                tests_root.join(module.with_extension("rs")).display(),
+            );
+        }
+    }
+}
+
+fn module_layouts(root: &Path, crate_roots: &[&str]) -> BTreeMap<PathBuf, ModuleLayout> {
+    super::rust_files(root)
+        .into_iter()
+        .filter(|relative| {
+            !crate_roots
+                .iter()
+                .any(|candidate| relative == Path::new(candidate))
+        })
+        .map(|relative| {
+            if relative.file_name().and_then(|value| value.to_str()) == Some("mod.rs") {
+                (
+                    relative.parent().expect("mod.rs parent").to_path_buf(),
+                    ModuleLayout::Directory,
+                )
+            } else {
+                (relative.with_extension(""), ModuleLayout::File)
+            }
+        })
+        .collect()
+}
+
+fn root_test_scenario_allowed(member: &str, module: &Path) -> bool {
+    let Some(module) = module.to_str() else {
+        return false;
+    };
+    ROOT_TEST_SCENARIOS
+        .iter()
+        .any(|(candidate, scenarios)| *candidate == member && scenarios.contains(&module))
+}
+
+fn assert_module_tree(root: &Path, crate_roots: &[&str]) {
+    let files = super::rust_files(root);
+    for relative in &files {
+        if crate_roots
+            .iter()
+            .any(|candidate| relative == Path::new(candidate))
+        {
+            continue;
+        }
+
+        let file_name = relative
+            .file_name()
+            .and_then(|value| value.to_str())
+            .expect("Rust source file name");
+        let parent = relative.parent().expect("Rust source parent");
+        let module_name = if file_name == "mod.rs" {
+            parent
+                .file_name()
+                .and_then(|value| value.to_str())
+                .expect("mod.rs module name")
+        } else {
+            relative
+                .file_stem()
+                .and_then(|value| value.to_str())
+                .expect("Rust source module name")
+        };
+
+        if file_name != "mod.rs" {
+            assert_ne!(
+                parent.file_name().and_then(|value| value.to_str()),
+                Some(module_name),
+                "{} repeats its parent module name",
+                root.join(relative).display()
+            );
+            let child_directory = relative.with_extension("");
+            assert!(
+                !files
+                    .iter()
+                    .any(|candidate| candidate.starts_with(&child_directory)),
+                "{} mixes a leaf module with a same-name module directory",
+                root.join(relative).display()
+            );
+        }
+
+        let declaration_parents = if parent.as_os_str().is_empty()
+            || (file_name == "mod.rs"
+                && parent
+                    .parent()
+                    .is_some_and(|ancestor| ancestor.as_os_str().is_empty()))
+        {
+            crate_roots
+                .iter()
+                .map(|candidate| root.join(candidate))
+                .collect::<Vec<_>>()
+        } else {
+            let declaration_directory = if file_name == "mod.rs" {
+                parent.parent().expect("nested mod.rs parent")
+            } else {
+                parent
+            };
+            vec![root.join(declaration_directory).join("mod.rs")]
+        };
+        let declaration_count = declaration_parents
+            .iter()
+            .map(|path| external_module_declaration_count(path, module_name))
+            .sum::<usize>();
+        assert_eq!(
+            declaration_count,
+            1,
+            "{} must be declared exactly once by its parent module",
+            root.join(relative).display()
+        );
+    }
+}
+
+fn external_module_declaration_count(path: &Path, module_name: &str) -> usize {
+    if !path.is_file() {
+        return 0;
+    }
+    let source = fs::read_to_string(path).expect("read parent module source");
+    let syntax = syn::parse_file(&source).expect("parse parent module source");
+    syntax
+        .items
+        .iter()
+        .filter(|item| {
+            matches!(
+                item,
+                Item::Mod(module)
+                    if module.content.is_none() && module.ident == module_name
+            )
+        })
+        .count()
+}
+
+pub(super) fn backend_root() -> PathBuf {
     Path::new(env!("CARGO_MANIFEST_DIR"))
         .join("../..")
         .canonicalize()

backend/apps/gateway/tests/bootstrap.rs

@@ -143,10 +143,7 @@ fn config_loader_should_reject_removed_fingerprint_section() {
 
 #[test]
 fn config_loader_should_reject_invalid_codex_cli_version() {
-    assert_rejected(valid_config().replace(
-        "codex_version: '0.147.0-alpha.6.6'",
-        "codex_version: 'latest'",
-    ));
+    assert_rejected(valid_config().replace("codex_version: '0.153.4'", "codex_version: 'latest'"));
 }
 
 #[test]
@@ -165,7 +162,7 @@ fn config_loader_should_reject_zero_server_port() {
 
 #[test]
 fn config_loader_should_reject_invalid_desktop_profile_fields() {
-    assert_rejected(valid_config().replace("desktop_build: '6415'", "desktop_build: 'build'"));
+    assert_rejected(valid_config().replace("desktop_build: '8109'", "desktop_build: 'build'"));
 }
 
 fn assert_rejected(config: String) {

backend/apps/gateway/tests/main.rs

@@ -43,31 +43,33 @@ fn cargo_library_root_is_conventional_lib() {
 }
 
 #[test]
-fn production_files_have_no_hidden_modules_or_test_hooks() {
-    let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("src");
-    for relative in ["bootstrap.rs", "lib.rs", "main.rs"] {
-        let path = root.join(relative);
-        let source = fs::read_to_string(&path).expect("read production source");
-        assert!(
-            !source.contains("include!("),
-            "{} uses include!",
-            path.display()
-        );
-        let syntax = syn::parse_file(&source).expect("parse production source");
-        for item in &syntax.items {
-            if let Item::Mod(module) = item {
-                assert!(
-                    module.content.is_none(),
-                    "{} has an inline module",
-                    path.display()
-                );
-            }
-            for attribute in item_attrs(item) {
-                assert!(
-                    !is_path_or_test_cfg(attribute),
-                    "{} has a production test/path hook",
-                    path.display(),
-                );
+fn workspace_production_files_have_no_hidden_modules_or_test_hooks() {
+    for member in architecture::WORKSPACE_MEMBERS {
+        let root = architecture::backend_root().join(member).join("src");
+        for relative in rust_files(&root) {
+            let path = root.join(relative);
+            let source = fs::read_to_string(&path).expect("read production source");
+            assert!(
+                !source.contains("include!("),
+                "{} uses include!",
+                path.display()
+            );
+            let syntax = syn::parse_file(&source).expect("parse production source");
+            for item in &syntax.items {
+                if let Item::Mod(module) = item {
+                    assert!(
+                        module.content.is_none(),
+                        "{} has an inline module",
+                        path.display()
+                    );
+                }
+                for attribute in item_attrs(item) {
+                    assert!(
+                        !is_path_or_test_cfg(attribute),
+                        "{} has a production test/path hook",
+                        path.display(),
+                    );
+                }
             }
         }
     }

backend/crates/gateway-admin/Cargo.toml

@@ -12,15 +12,17 @@ name = "main"
 path = "tests/main.rs"
 
 [dependencies]
-argon2 = "0.5.3"
+argon2 = "0.6.0"
 async-trait = "0.1.89"
 base64 = "0.23.0"
+bytes = "1.11.1"
 chrono = "0.4.45"
 futures = "0.3.32"
 gateway-core = { path = "../gateway-core" }
 hex = "0.4.3"
 rand_core = { version = "0.6.4", features = ["getrandom"] }
 serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 secrecy = { version = "0.10.3", features = ["serde"] }
 subtle = "2.6.1"
 thiserror = "2.0.18"
@@ -28,10 +30,9 @@ tracing = "0.1.44"
 uuid = { version = "1.23.3", features = ["v7"] }
 cron = "0.17"
 chrono-tz = "0.10"
-tokio = { version = "1.52", features = ["rt", "time", "macros"] }
+tokio = { version = "1.52", features = ["rt", "time", "macros", "sync"] }
 
 [dev-dependencies]
-serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 sha2 = "0.11"
 tempfile = "3"
 tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt"] }

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

@@ -9,7 +9,7 @@ use std::time::Duration;
 use chrono::{DateTime, Utc};
 use futures::future::BoxFuture;
 use gateway_core::{
-    engine::CancellationToken,
+    lifecycle::CancellationToken,
     task::{DaemonTask, WorkerTaskError},
 };
 use tracing::{info, warn};

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

@@ -6,7 +6,8 @@ use std::{fmt, path::Path, sync::Arc, time::Duration};
 
 use gateway_core::{
     engine::probe::AccountProbe,
-    routing::{ProviderKind, snapshot::SnapshotControl},
+    routing::ProviderKind,
+    runtime::SnapshotControl,
     task::{
         DaemonRestartPolicy, WorkerContribution, WorkerId, WorkerKind, WorkerRegistration,
         WorkerRunnable,
@@ -22,19 +23,22 @@ mod use_case;
 
 pub use use_case::{
     account_groups::AccountGroupService, accounts::AccountsService, auth::AuthService,
-    backup::BackupService, client_keys::ClientKeyService, observability::ObservabilityService,
-    openai::OpenAiService, settings::SettingsService, system::SystemService, xai::XaiService,
+    backup::BackupService, client_distribution::ClientDistributionService,
+    client_keys::ClientKeyService, observability::ObservabilityService, openai::OpenAiService,
+    settings::SettingsService, system::SystemService, xai::XaiService,
 };
 
 use model::{AdminError, AdminErrorKind};
 use ports::{
+    client_distribution::ClientDistributionResolver,
     provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind, ProviderAdminRegistry},
     store::AdminStorePorts,
     system::SystemOperations,
 };
 use use_case::{
     account_groups::DefaultAccountGroupService, accounts::DefaultAccountsService,
-    auth::DefaultAuthService, backup::DefaultBackupService, client_keys::DefaultClientKeyService,
+    auth::DefaultAuthService, backup::DefaultBackupService,
+    client_distribution::DefaultClientDistributionService, client_keys::DefaultClientKeyService,
     observability::DefaultObservabilityService, openai::DefaultOpenAiService,
     settings::DefaultSettingsService, system::DefaultSystemService, xai::DefaultXaiService,
 };
@@ -134,9 +138,9 @@ impl fmt::Debug for AdminConfig {
 /// Admin-owned 启动配置错误；不回显任何配置值。
 #[derive(Debug, Clone, Copy, PartialEq, Eq, thiserror::Error)]
 pub enum AdminConfigError {
-    #[error("configuration field `{0}` is invalid")]
+    #[error("配置字段 `{0}` 不合法")]
     InvalidField(&'static str),
-    #[error("admin.default_password does not meet the initial password policy")]
+    #[error("admin.default_password 不符合初始密码策略")]
     WeakInitialPassword,
 }
 
@@ -149,6 +153,7 @@ pub struct AdminServices {
     accounts: Arc<dyn AccountsService>,
     account_groups: Arc<dyn AccountGroupService>,
     client_keys: Arc<dyn ClientKeyService>,
+    client_distribution: Arc<dyn ClientDistributionService>,
     observability: Arc<dyn ObservabilityService>,
     settings: Arc<dyn SettingsService>,
     system: Arc<dyn SystemService>,
@@ -178,6 +183,11 @@ impl AdminServices {
         self.client_keys.as_ref()
     }
 
+    #[must_use]
+    pub fn client_distribution(&self) -> &dyn ClientDistributionService {
+        self.client_distribution.as_ref()
+    }
+
     #[must_use]
     pub fn observability(&self) -> &dyn ObservabilityService {
         self.observability.as_ref()
@@ -238,6 +248,7 @@ pub async fn initialize(
     providers: Vec<Arc<dyn ProviderAdmin>>,
     snapshot: Arc<dyn SnapshotControl>,
     probe: Arc<dyn AccountProbe>,
+    client_distribution: Arc<dyn ClientDistributionResolver>,
     system: Arc<dyn SystemOperations>,
 ) -> Result<AdminBundle, AdminError> {
     config
@@ -261,6 +272,7 @@ pub async fn initialize(
 
     let accounts = Arc::new(DefaultAccountsService::new(
         store.accounts(),
+        store.account_runtime(),
         registry.clone(),
         snapshot.clone(),
         probe.clone(),
@@ -282,14 +294,17 @@ pub async fn initialize(
         accounts,
         account_groups: Arc::new(DefaultAccountGroupService::new(
             store.account_groups(),
+            store.account_runtime(),
             snapshot.clone(),
         )),
         client_keys: Arc::new(DefaultClientKeyService::new(
             store.client_keys(),
             snapshot.clone(),
         )),
+        client_distribution: Arc::new(DefaultClientDistributionService::new(client_distribution)),
         observability: Arc::new(DefaultObservabilityService::new(
             store.observability(),
+            store.accounts(),
             store.settings(),
             registry,
         )),
@@ -322,9 +337,9 @@ fn backup_worker_contribution(
     task: backup::task::BackupTask,
 ) -> Result<Vec<WorkerContribution>, AdminError> {
     let id = WorkerId::try_new(WorkerKind::Backup, BACKUP_WORKER_OWNER)
-        .map_err(|_| AdminError::internal("Backup worker id is invalid"))?;
+        .map_err(|_| AdminError::internal("备份 Worker ID 不合法"))?;
     let restart = DaemonRestartPolicy::try_new(Duration::from_secs(1), Duration::from_secs(60))
-        .map_err(|_| AdminError::internal("Backup worker restart policy is invalid"))?;
+        .map_err(|_| AdminError::internal("备份 Worker 重启策略不合法"))?;
     let registration = WorkerRegistration::try_new(
         id,
         WorkerRunnable::Daemon {
@@ -332,12 +347,12 @@ fn backup_worker_contribution(
             task: Box::new(task),
         },
     )
-    .map_err(|_| AdminError::internal("Backup worker registration is invalid"))?;
+    .map_err(|_| AdminError::internal("备份 Worker 注册信息不合法"))?;
     Ok(vec![WorkerContribution::Registration(registration)])
 }
 
 fn provider_kind(value: &'static str) -> Result<ProviderKind, AdminError> {
-    ProviderKind::new(value).map_err(|_| AdminError::internal("Built-in Provider kind is invalid"))
+    ProviderKind::new(value).map_err(|_| AdminError::internal("内置 Provider 类型不合法"))
 }
 
 fn map_provider_registry_error(error: ProviderAdminError) -> AdminError {
@@ -347,11 +362,12 @@ fn map_provider_registry_error(error: ProviderAdminError) -> AdminError {
         }
         ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
         ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
+        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
         ProviderAdminErrorKind::Unavailable | ProviderAdminErrorKind::CredentialRefreshRequired => {
             AdminErrorKind::Unavailable
         }
         ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
         ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
     };
-    AdminError::new(kind, "Provider registry initialization failed")
+    AdminError::new(kind, "Provider 注册表初始化失败")
 }

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

@@ -3,7 +3,7 @@
 use std::collections::BTreeMap;
 
 use chrono::{DateTime, Utc};
-use gateway_core::routing::AccountGroupId;
+use gateway_core::{account::AccountStatusFacts, routing::AccountGroupId};
 
 use super::{PageSize, Revision, observability::DecimalAmount};
 
@@ -45,7 +45,17 @@ pub struct AccountGroupCapacity {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountGroupUsage {
     pub today_usd: DecimalAmount,
-    pub total_usd: DecimalAmount,
+    /// 当前 usage retention 窗口内、按请求发生时 routing group 快照归属的累计成本。
+    pub retained_total_usd: DecimalAmount,
+}
+
+/// 当前页账号组 membership 对应的持久账号事实；运行态在 Admin query service 合并。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct AccountGroupMemberFact {
+    pub group_id: AccountGroupId,
+    pub account_id: String,
+    pub status: AccountStatusFacts,
+    pub total_slots: u64,
 }
 
 /// Lightweight group reference embedded in account and client-key views.

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

@@ -1,15 +1,18 @@
 //! 多 Provider 账号目录与连接测试的公共事实。
 
-use std::pin::Pin;
+use std::{collections::BTreeMap, pin::Pin};
 
 use chrono::{DateTime, Utc};
 use futures::Stream;
 
-use gateway_core::routing::ProviderKind;
+use gateway_core::{
+    engine::probe::AccountProbeErrorSource, error::GatewayErrorKind, routing::ProviderKind,
+    upstream::UpstreamSendState,
+};
 
 use super::{PageSize, Revision, account_groups::AccountGroupRef, observability::TimeRange};
 
-pub use gateway_core::engine::credential::{
+pub use gateway_core::account::{
     AccountConcurrencyLimit, AccountErrorReason, AccountStatus, AccountStatusFacts,
     AccountStatusProjection, AccountWeight, CredentialState, QuotaAccessState, QuotaEvidence,
     QuotaState, resolve_account_status,
@@ -52,6 +55,14 @@ pub struct AccountListQuery {
     pub sort: Option<AccountSort>,
 }
 
+/// Admin query service 从运行态存储取得的当前账号冷却快照。
+#[derive(Debug, Clone, Default, PartialEq, Eq)]
+pub struct AccountRuntimeSnapshot {
+    pub rate_limited_until: BTreeMap<String, DateTime<Utc>>,
+    /// `None` 表示实时 lease 存储不可用；`Some` 中未出现的账号当前使用量为零。
+    pub in_flight: Option<BTreeMap<String, u64>>,
+}
+
 /// Optional account membership filter.
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AccountGroupFilter {
@@ -206,7 +217,7 @@ pub struct UpdateAccount {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountUpdateResult {
     pub config_revision: Revision,
-    pub account_id: gateway_core::engine::credential::ProviderAccountId,
+    pub account_id: gateway_core::account::ProviderAccountId,
 }
 
 /// 一批账号可编辑事实的一次性替换命令。
@@ -223,7 +234,7 @@ pub struct BatchUpdateAccounts {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct AccountsUpdateResult {
     pub config_revision: Revision,
-    pub account_ids: Vec<gateway_core::engine::credential::ProviderAccountId>,
+    pub account_ids: Vec<gateway_core::account::ProviderAccountId>,
 }
 
 /// 账号批量删除命令。
@@ -249,6 +260,9 @@ pub enum AccountConnectionTestEvent {
     },
     Completed,
     Failed {
+        source: AccountProbeErrorSource,
+        gateway_error_code: GatewayErrorKind,
+        send_state: Option<UpstreamSendState>,
         message: String,
         provider_error_code: Option<String>,
         provider_error_type: Option<String>,

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

@@ -4,6 +4,12 @@ use chrono::{DateTime, Utc};
 
 use super::{MutationActor, MutationContext, Revision};
 
+/// 会话审计使用的稳定管理员标识。
+#[must_use]
+pub fn admin_session_actor_ref(admin_user_id: &str) -> String {
+    format!("admin:{admin_user_id}")
+}
+
 /// 已认证的管理主体。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum AdminPrincipal {

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

@@ -0,0 +1,34 @@
+//! 备份领域的稳定错误码。
+
+/// 配置或参数非法。
+pub const INVALID_CONFIG: &str = "backup.invalid_config";
+/// Cron 表达式非法。
+pub const INVALID_CRON: &str = "backup.invalid_cron";
+/// IANA 时区非法。
+pub const INVALID_TIMEZONE: &str = "backup.invalid_timezone";
+/// 记录不存在。
+pub const RECORD_NOT_FOUND: &str = "backup.record_not_found";
+/// 已存在活跃任务，拒绝创建。
+pub const ACTIVE_TASK_CONFLICT: &str = "backup.active_task_conflict";
+/// 记录状态与期望不符，无法迁移。
+pub const STATE_CONFLICT: &str = "backup.state_conflict";
+/// 已有记录时禁止切换存储目标。
+pub const STORAGE_IDENTITY_LOCKED: &str = "backup.storage_identity_locked";
+/// `pg_dump` 非零退出或失败。
+pub const PG_DUMP_FAILED: &str = "backup.pg_dump_failed";
+/// 暂存磁盘空间不足。
+pub const STAGING_SPACE_EXHAUSTED: &str = "backup.staging_space_exhausted";
+/// S3 认证失败。
+pub const S3_AUTH_FAILED: &str = "backup.s3_auth_failed";
+/// S3 权限拒绝。
+pub const S3_PERMISSION_DENIED: &str = "backup.s3_permission_denied";
+/// S3 上传失败。
+pub const S3_UPLOAD_FAILED: &str = "backup.s3_upload_failed";
+/// 远端对象校验失败。
+pub const REMOTE_VERIFICATION_FAILED: &str = "backup.remote_verification_failed";
+/// 任务被取消。
+pub const CANCELLED: &str = "backup.cancelled";
+/// 仓储或对象存储暂不可用。
+pub const STORE_UNAVAILABLE: &str = "backup.store_unavailable";
+/// 上游 S3 服务返回无效或失败响应。
+pub const UPSTREAM_FAILURE: &str = "backup.upstream_failure";

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

@@ -447,40 +447,7 @@ impl BackupError {
 }
 
 /// 构造稳定错误码常量。
-pub mod code {
-    /// 配置或参数非法。
-    pub const INVALID_CONFIG: &str = "backup.invalid_config";
-    /// Cron 表达式非法。
-    pub const INVALID_CRON: &str = "backup.invalid_cron";
-    /// IANA 时区非法。
-    pub const INVALID_TIMEZONE: &str = "backup.invalid_timezone";
-    /// 记录不存在。
-    pub const RECORD_NOT_FOUND: &str = "backup.record_not_found";
-    /// 已存在活跃任务，拒绝创建。
-    pub const ACTIVE_TASK_CONFLICT: &str = "backup.active_task_conflict";
-    /// 记录状态与期望不符，无法迁移。
-    pub const STATE_CONFLICT: &str = "backup.state_conflict";
-    /// 已有记录时禁止切换存储目标。
-    pub const STORAGE_IDENTITY_LOCKED: &str = "backup.storage_identity_locked";
-    /// `pg_dump` 非零退出或失败。
-    pub const PG_DUMP_FAILED: &str = "backup.pg_dump_failed";
-    /// 暂存磁盘空间不足。
-    pub const STAGING_SPACE_EXHAUSTED: &str = "backup.staging_space_exhausted";
-    /// S3 认证失败。
-    pub const S3_AUTH_FAILED: &str = "backup.s3_auth_failed";
-    /// S3 权限拒绝。
-    pub const S3_PERMISSION_DENIED: &str = "backup.s3_permission_denied";
-    /// S3 上传失败。
-    pub const S3_UPLOAD_FAILED: &str = "backup.s3_upload_failed";
-    /// 远端对象校验失败。
-    pub const REMOTE_VERIFICATION_FAILED: &str = "backup.remote_verification_failed";
-    /// 任务被取消。
-    pub const CANCELLED: &str = "backup.cancelled";
-    /// 仓储或对象存储暂不可用。
-    pub const STORE_UNAVAILABLE: &str = "backup.store_unavailable";
-    /// 上游 S3 服务返回无效或失败响应。
-    pub const UPSTREAM_FAILURE: &str = "backup.upstream_failure";
-}
+pub mod code;
 
 /// 构建对象 key：`{prefix}/YYYY/MM/DD/codex-proxy-rs_{UTC seconds}_{backup id}.dump`。
 ///

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

@@ -0,0 +1,58 @@
+//! 管理设置页使用的 Codex 客户端下载信息。
+
+use chrono::{DateTime, Utc};
+
+/// Windows 安装包架构。
+#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
+pub enum ClientArchitecture {
+    X64,
+    Arm64,
+}
+
+impl ClientArchitecture {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::X64 => "x64",
+            Self::Arm64 => "arm64",
+        }
+    }
+}
+
+/// 下载地址的可信来源。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ClientDownloadSource {
+    MicrosoftStore,
+    OfficialOpenAi,
+}
+
+impl ClientDownloadSource {
+    #[must_use]
+    pub const fn as_str(self) -> &'static str {
+        match self {
+            Self::MicrosoftStore => "microsoft_store",
+            Self::OfficialOpenAi => "official_openai",
+        }
+    }
+}
+
+/// 一个已经过 Host 校验、可以直接交给浏览器下载的安装包。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ClientDownloadPackage {
+    pub architecture: ClientArchitecture,
+    pub source: ClientDownloadSource,
+    pub version: Option<String>,
+    pub file_name: String,
+    pub size_bytes: Option<u64>,
+    pub download_url: String,
+    pub expires_at: Option<DateTime<Utc>>,
+}
+
+/// Codex Desktop Windows 下载解析结果。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct CodexDesktopWindowsDownloads {
+    pub resolved_at: DateTime<Utc>,
+    pub cached: bool,
+    pub warning: Option<String>,
+    pub packages: Vec<ClientDownloadPackage>,
+}

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

@@ -6,6 +6,7 @@ pub mod account_groups;
 pub mod accounts;
 pub mod auth;
 pub mod backup;
+pub mod client_distribution;
 pub mod client_keys;
 pub mod observability;
 pub mod provider_credentials;
@@ -21,11 +22,12 @@ pub enum AdminErrorKind {
     Conflict,
     RateLimited,
     BadGateway,
+    UpstreamResultUnknown,
     Unavailable,
     Internal,
 }
 
-/// 不携带基础设施细节的管理用例错误。
+/// 不携带基础设施细节、可安全返回给管理员的管理用例错误。
 #[derive(Debug, Clone, PartialEq, Eq, thiserror::Error)]
 #[error("{message}")]
 pub struct AdminError {
@@ -47,6 +49,12 @@ impl AdminError {
         self.kind
     }
 
+    /// 返回已脱敏、可公开给管理员的文案。
+    #[must_use]
+    pub fn message(&self) -> &str {
+        &self.message
+    }
+
     #[must_use]
     pub fn invalid(message: impl Into<String>) -> Self {
         Self::new(AdminErrorKind::Invalid, message)
@@ -72,6 +80,11 @@ impl AdminError {
         Self::new(AdminErrorKind::BadGateway, message)
     }
 
+    #[must_use]
+    pub fn upstream_result_unknown(message: impl Into<String>) -> Self {
+        Self::new(AdminErrorKind::UpstreamResultUnknown, message)
+    }
+
     #[must_use]
     pub fn unavailable(message: impl Into<String>) -> Self {
         Self::new(AdminErrorKind::Unavailable, message)

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

@@ -1,6 +1,6 @@
 //! 用量、成本、健康与错误诊断的 UTC 语义事实。
 
-use std::{num::NonZeroU32, str::FromStr};
+use std::str::FromStr;
 
 use chrono::{DateTime, TimeDelta, Timelike as _, Utc};
 
@@ -38,29 +38,6 @@ impl TimeRange {
     }
 }
 
-/// 从一开始的观测页码。
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub struct PageNumber(NonZeroU32);
-
-impl PageNumber {
-    #[must_use]
-    pub const fn new(value: NonZeroU32) -> Self {
-        Self(value)
-    }
-
-    #[must_use]
-    pub const fn get(self) -> u32 {
-        self.0.get()
-    }
-}
-
-/// 观测记录的稳定键集游标。
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub struct ObservabilityCursor {
-    pub observed_at: DateTime<Utc>,
-    pub stable_id: String,
-}
-
 /// 请求结果状态。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub enum RequestOutcome {
@@ -146,8 +123,7 @@ pub struct UsageFilter {
 pub struct UsageQuery {
     pub range: TimeRange,
     pub filter: UsageFilter,
-    pub cursor: Option<ObservabilityCursor>,
-    pub page: PageNumber,
+    pub current_page: u32,
     pub page_size: PageSize,
 }
 
@@ -164,7 +140,6 @@ pub struct OpsErrorFilter {
     pub attempt_index: Option<u32>,
     pub response_id: Option<String>,
     pub upstream_request_id: Option<String>,
-    pub failure_kind: Option<String>,
     pub status_code: Option<u16>,
     pub search: Option<String>,
 }
@@ -174,8 +149,7 @@ pub struct OpsErrorFilter {
 pub struct OpsErrorQuery {
     pub range: TimeRange,
     pub filter: OpsErrorFilter,
-    pub cursor: Option<ObservabilityCursor>,
-    pub page: PageNumber,
+    pub current_page: u32,
     pub page_size: PageSize,
 }
 
@@ -213,11 +187,11 @@ impl DecimalAmount {
         Self::from_decimal(self.to_decimal()?.checked_div_u64(divisor)?)
     }
 
-    fn to_decimal(&self) -> Option<gateway_core::accounting::Decimal> {
+    fn to_decimal(&self) -> Option<gateway_core::metering::Decimal> {
         self.0.parse().ok()
     }
 
-    fn from_decimal(value: gateway_core::accounting::Decimal) -> Option<Self> {
+    fn from_decimal(value: gateway_core::metering::Decimal) -> Option<Self> {
         Some(Self(value.canonical()))
     }
 }
@@ -402,6 +376,16 @@ pub struct RequestMetrics {
     pub max_latency_ms: Option<u64>,
     pub latency_percentiles: LatencyPercentiles,
     pub first_token_latency_percentiles: LatencyPercentiles,
+    pub admission_decision_count: u64,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_count: u64,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_sample_count: u64,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
     pub cache_eligible_request_count: u64,
     pub cache_hit_request_count: u64,
 }
@@ -507,6 +491,8 @@ pub struct DashboardAccountUsage {
     ///
     /// `None` 表示上游未提供可比较的百分比，不应伪造为零。
     pub quota_used_percent: Option<f64>,
+    /// Provider 返回的代表窗口；缺失时保留未知语义。
+    pub quota_window: Option<super::provider_credentials::ProviderQuotaWindow>,
     pub models: Vec<DashboardAccountModelUsage>,
 }
 
@@ -535,13 +521,60 @@ pub struct DashboardTotals {
 #[derive(Debug, Clone, PartialEq)]
 pub struct DashboardObservation {
     pub range: TimeRange,
-    pub requests: RequestMetrics,
-    pub attempts: AttemptMetrics,
     pub totals: DashboardTotals,
     pub provider_accounts: AccountPoolMetrics,
     pub trend: Vec<RequestMetricPoint>,
     pub account_usage: Vec<DashboardAccountUsage>,
-    pub recent_requests: Vec<UsageRecord>,
+    pub recent_requests: Vec<UsageListRecord>,
+}
+
+/// 使用记录表格的窄读模型。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct UsageListRecord {
+    pub id: String,
+    pub endpoint: String,
+    pub client_transport: String,
+    pub requested_model_id: Option<String>,
+    pub provider_kind: Option<String>,
+    pub provider_account_ref: Option<String>,
+    pub provider_account_name: Option<String>,
+    pub provider_account_email: Option<String>,
+    pub provider_account_authentication_kind: Option<String>,
+    pub upstream_model_id: Option<String>,
+    pub upstream_transport: Option<String>,
+    pub service_tier: Option<String>,
+    pub input_tokens: Option<u64>,
+    pub output_tokens: Option<u64>,
+    pub cached_tokens: Option<u64>,
+    pub cache_write_tokens: Option<u64>,
+    pub reasoning_tokens: Option<u64>,
+    pub image_input_tokens: Option<u64>,
+    pub image_output_tokens: Option<u64>,
+    pub total_tokens: Option<u64>,
+    pub cost_source: String,
+    pub cost_amount: Option<DecimalAmount>,
+    pub cost_currency: Option<String>,
+    pub billing: Option<UsageBilling>,
+    pub transport_decision_wait_ms: Option<u64>,
+    pub connect_ms: Option<u64>,
+    pub headers_ms: Option<u64>,
+    pub first_event_ms: Option<u64>,
+    pub first_reasoning_ms: Option<u64>,
+    pub first_text_ms: Option<u64>,
+    pub first_token_ms: Option<u64>,
+    pub provider_processing_ms: Option<u64>,
+    pub latency_ms: Option<u64>,
+    pub admission_decision_ms: Option<u64>,
+    pub account_selection_wait_ms: Option<u64>,
+    pub capacity_used_slots: Option<u64>,
+    pub capacity_total_slots: Option<u64>,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: bool,
+    pub started_at: DateTime<Utc>,
 }
 
 /// 一次完整模型请求的公共观测记录。
@@ -604,6 +637,10 @@ pub struct UsageRecord {
     pub first_token_ms: Option<u64>,
     pub provider_processing_ms: Option<u64>,
     pub latency_ms: Option<u64>,
+    pub admission_decision_ms: Option<u64>,
+    pub account_selection_wait_ms: Option<u64>,
+    pub capacity_used_slots: Option<u64>,
+    pub capacity_total_slots: Option<u64>,
     pub client_ip: Option<String>,
     pub user_agent: Option<String>,
     pub reasoning_effort: Option<String>,
@@ -621,9 +658,10 @@ pub struct UsageRecord {
 /// 用量分页结果。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UsagePage {
-    pub items: Vec<UsageRecord>,
+    pub items: Vec<UsageListRecord>,
+    pub current_page: u32,
+    pub page_size: u16,
     pub total: u64,
-    pub next_cursor: Option<ObservabilityCursor>,
 }
 
 /// 请求中的一次上游尝试或运维事件。
@@ -666,6 +704,8 @@ pub struct UsageAttempt {
 /// 一条请求及其全部尝试。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct UsageDetail {
+    pub trace: Option<serde_json::Value>,
+    pub related_requests: Vec<serde_json::Value>,
     pub request: UsageRecord,
     pub attempts: Vec<UsageAttempt>,
 }
@@ -708,6 +748,9 @@ pub struct DiagnosticObservation {
     pub total_tokens: u64,
     pub average_latency_ms: Option<u64>,
     pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub retry_count: u64,
     pub cost_coverage: CostCoverage,
     pub costs: Vec<CurrencyCost>,
 }
@@ -722,6 +765,10 @@ pub struct OpsError {
     pub client_api_key_ref: Option<String>,
     pub component: String,
     pub operation: String,
+    pub protocol: Option<String>,
+    pub client_transport: Option<String>,
+    pub requested_model_id: Option<String>,
+    pub service_tier: Option<String>,
     pub endpoint: Option<String>,
     pub provider_kind: Option<String>,
     pub provider_account_ref: Option<String>,
@@ -731,6 +778,7 @@ pub struct OpsError {
     pub upstream_model_id: Option<String>,
     pub upstream_transport: Option<String>,
     pub failure_kind: String,
+    pub upstream_send_state: Option<String>,
     pub client_status_code: Option<u16>,
     pub upstream_status_code: Option<u16>,
     pub provider_error_code: Option<String>,
@@ -738,7 +786,26 @@ pub struct OpsError {
     pub upstream_request_id: Option<String>,
     pub latency_ms: Option<u64>,
     pub message: String,
-    pub occurrence_count: u32,
+    pub raw_upstream_error: Option<String>,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub request_kind: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: Option<bool>,
+    pub continuation_affinity_hash: Option<String>,
+    pub continuation_previous_response_id_hash: Option<String>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_id: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub upstream_connection_age_ms: Option<u64>,
+    pub upstream_connection_idle_ms: Option<u64>,
+    pub recovery_request_id: Option<String>,
+    pub recovered_at: Option<DateTime<Utc>>,
+    pub recovery_attempt_count: u32,
+    pub recovery_retry_delay_ms: Option<u64>,
+    pub recovery_total_latency_ms: Option<u64>,
     pub occurred_at: DateTime<Utc>,
     pub stable_sort_id: String,
 }
@@ -747,8 +814,9 @@ pub struct OpsError {
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct OpsErrorPage {
     pub items: Vec<OpsError>,
+    pub current_page: u32,
+    pub page_size: u16,
     pub total: u64,
-    pub next_cursor: Option<ObservabilityCursor>,
 }
 
 /// 仪表盘趋势指标。
@@ -787,6 +855,9 @@ pub struct TrendSummary {
     pub average_latency_ms: Option<u64>,
     pub max_latency_ms: Option<u64>,
     pub min_latency_ms: Option<u64>,
+    pub peak_first_token_p95_ms: Option<f64>,
+    pub peak_latency_p95_ms: Option<f64>,
+    pub minimum_output_throughput_p50: Option<u64>,
     pub success_rate: Option<f64>,
     pub cache_hit_request_rate: Option<f64>,
     pub costs: Vec<CurrencyCost>,
@@ -935,6 +1006,7 @@ pub struct DashboardResult {
 /// 洞察健康时间点的语义结果。
 #[derive(Debug, Clone, PartialEq)]
 pub struct UsageInsightsHealthPoint {
+    pub total_requests: u64,
     pub bucket_start: DateTime<Utc>,
     pub success_requests: u64,
     pub failed_requests: u64,
@@ -954,6 +1026,7 @@ pub struct UsageInsightsHealth {
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
     pub success_rate: f64,
+    pub completion_rate: f64,
     pub points: Vec<UsageInsightsHealthPoint>,
 }
 
@@ -963,6 +1036,13 @@ pub struct UsageInsightsPerformancePoint {
     pub bucket_start: DateTime<Utc>,
     pub latency_percentiles: LatencyPercentiles,
     pub first_token_latency_percentiles: LatencyPercentiles,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
 }
 
 /// 洞察性能汇总与可观测覆盖率。
@@ -972,6 +1052,16 @@ pub struct UsageInsightsPerformance {
     pub first_token_latency_percentiles: LatencyPercentiles,
     pub latency_coverage: f64,
     pub first_token_coverage: f64,
+    pub admission_decision_percentiles: LatencyPercentiles,
+    pub account_selection_wait_percentiles: LatencyPercentiles,
+    pub admission_decision_coverage: f64,
+    pub account_selection_wait_coverage: f64,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization_avg_basis_points: Option<u64>,
+    pub capacity_utilization_p95_basis_points: Option<u64>,
+    pub capacity_coverage: f64,
     pub points: Vec<UsageInsightsPerformancePoint>,
 }
 
@@ -985,6 +1075,8 @@ pub struct UsageInsightsCostPoint {
     pub total_tokens: u64,
     pub estimated_cost: Option<DecimalAmount>,
     pub standard_cost: Option<DecimalAmount>,
+    pub no_cache_cost: Option<DecimalAmount>,
+    pub cache_savings: Option<DecimalAmount>,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
 }
@@ -994,7 +1086,11 @@ pub struct UsageInsightsCostPoint {
 pub struct UsageInsightsCost {
     pub estimated_cost: Option<DecimalAmount>,
     pub standard_cost: Option<DecimalAmount>,
+    pub no_cache_cost: Option<DecimalAmount>,
+    pub cache_savings: Option<DecimalAmount>,
+    pub tier_premium: Option<DecimalAmount>,
     pub cost_per_request: Option<DecimalAmount>,
+    pub cost_per_successful_request: Option<DecimalAmount>,
     pub tokens_per_request: f64,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
@@ -1030,6 +1126,12 @@ pub struct DiagnosticsItem {
     pub request_share: f64,
     pub average_latency_ms: Option<u64>,
     pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub non_completion_rate: f64,
+    pub retry_count: u64,
+    pub retry_rate: f64,
+    pub impact_score: f64,
     pub estimated_cost: Option<DecimalAmount>,
     pub attempt_count: u64,
     pub total_tokens: u64,

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

@@ -1,13 +1,17 @@
 //! Provider 管理能力交换的中立 Command 与 Result。
 
-use std::fmt;
+use std::{fmt, pin::Pin};
 
 use async_trait::async_trait;
-use chrono::{DateTime, Utc};
+use bytes::Bytes;
+use chrono::{DateTime, NaiveDate, Utc};
+use futures::Stream;
 use gateway_core::{
-    engine::credential::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
+    account::{OpaqueProviderData, ProviderAccountId, ProviderAccountIdentity},
     routing::{ProviderKind, UpstreamModelId},
 };
+use serde::Deserialize;
+use serde_json::{Map, Value};
 use uuid::Uuid;
 
 use super::{
@@ -277,6 +281,101 @@ impl PendingAuthorizationMutation {
     }
 }
 
+impl PendingAuthorizationMutation {
+    /// 编码 v1 中立事务字段；版本号的位置和 Provider 私有外层文档由 adapter 保持。
+    #[must_use]
+    pub fn to_storage_v1(&self) -> Map<String, Value> {
+        let target = match &self.target {
+            AuthorizationMutationTarget::Create { name } => {
+                serde_json::json!({"kind": "create", "name": name})
+            }
+            AuthorizationMutationTarget::Reauthorize { account_id } => {
+                serde_json::json!({"kind": "reauthorize", "account_id": account_id.to_string()})
+            }
+        };
+        let owner = match self.owner_binding.owner() {
+            AuthorizationOwner::AdminSession { admin_user_id } => {
+                serde_json::json!({"kind": "admin_session", "admin_user_id": admin_user_id})
+            }
+            AuthorizationOwner::AdminApiKey => serde_json::json!({"kind": "admin_api_key"}),
+            AuthorizationOwner::System => serde_json::json!({"kind": "system"}),
+        };
+        Map::from_iter([
+            (
+                "provider_kind".to_owned(),
+                Value::String(self.provider_kind.as_str().to_owned()),
+            ),
+            ("target".to_owned(), target),
+            ("owner".to_owned(), owner),
+            (
+                "started_request_id".to_owned(),
+                Value::String(self.owner_binding.started_request_id().to_owned()),
+            ),
+        ])
+    }
+
+    /// 恢复 adapter 已确认版本为 v1 的中立事务字段。
+    ///
+    /// # Errors
+    ///
+    /// 文档字段、Provider kind 或账号身份非法时返回错误，不携带原始 pending 内容。
+    pub fn from_storage_v1(value: Value) -> Result<Self, AdminError> {
+        let invalid = || AdminError::invalid("invalid pending authorization mutation");
+        let document: StoredAuthorizationMutationV1 =
+            serde_json::from_value(value).map_err(|_| invalid())?;
+        let provider_kind = ProviderKind::new(document.provider_kind).map_err(|_| invalid())?;
+        let target = match document.target {
+            StoredAuthorizationTargetV1::Create { name } => {
+                AuthorizationMutationTarget::Create { name }
+            }
+            StoredAuthorizationTargetV1::Reauthorize { account_id } => {
+                AuthorizationMutationTarget::Reauthorize {
+                    account_id: ProviderAccountId::new(account_id).map_err(|_| invalid())?,
+                }
+            }
+        };
+        let owner = match document.owner {
+            StoredAuthorizationOwnerV1::AdminSession { admin_user_id } => {
+                AuthorizationOwner::AdminSession { admin_user_id }
+            }
+            StoredAuthorizationOwnerV1::AdminApiKey => AuthorizationOwner::AdminApiKey,
+            StoredAuthorizationOwnerV1::System => AuthorizationOwner::System,
+        };
+        Ok(Self::new(
+            provider_kind,
+            target,
+            AuthorizationOwnerBinding {
+                owner,
+                started_request_id: document.started_request_id,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(deny_unknown_fields)]
+struct StoredAuthorizationMutationV1 {
+    provider_kind: String,
+    target: StoredAuthorizationTargetV1,
+    owner: StoredAuthorizationOwnerV1,
+    started_request_id: String,
+}
+
+#[derive(Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
+enum StoredAuthorizationTargetV1 {
+    Create { name: String },
+    Reauthorize { account_id: String },
+}
+
+#[derive(Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
+enum StoredAuthorizationOwnerV1 {
+    AdminSession { admin_user_id: String },
+    AdminApiKey,
+    System,
+}
+
 /// 启动 Provider OAuth Authorization Code 流程。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct StartAuthorization {
@@ -627,6 +726,87 @@ pub struct ProviderQuota {
     pub provider_data: Option<ProviderDocument>,
 }
 
+/// Provider 官方个人资料中的累计摘要。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileStatisticsSummary {
+    pub total_text_tokens: Option<u64>,
+    pub peak_tokens: Option<u64>,
+    pub longest_task_duration_ms: Option<u64>,
+    pub current_streak_days: Option<u64>,
+    pub longest_streak_days: Option<u64>,
+}
+
+/// Provider 官方个人资料中的单日 Token bucket。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileDailyUsage {
+    pub date: NaiveDate,
+    pub tokens: u64,
+}
+
+/// Provider 官方个人资料中的插件或 Skill 调用排行。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct ProviderProfileInvocation {
+    pub invocation_type: String,
+    pub plugin_id: Option<String>,
+    pub plugin_name: Option<String>,
+    pub skill_id: Option<String>,
+    pub skill_name: Option<String>,
+    pub usage_count: Option<u64>,
+}
+
+/// Provider 官方个人资料中的活动洞察。
+#[derive(Debug, Clone, PartialEq)]
+pub struct ProviderProfileActivityInsights {
+    pub fast_mode_percent: Option<f64>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_effort_percent: Option<f64>,
+    pub skills_explored: Option<u64>,
+    pub total_skills_used: Option<u64>,
+    pub total_threads: Option<u64>,
+    pub invocations: Option<Vec<ProviderProfileInvocation>>,
+}
+
+/// Provider 已解释的官方个人资料统计。
+#[derive(Debug, Clone, PartialEq)]
+pub struct ProviderProfileStatistics {
+    pub display_name: Option<String>,
+    pub username: Option<String>,
+    pub image_url: Option<String>,
+    pub has_stats_error: bool,
+    pub summary: ProviderProfileStatisticsSummary,
+    pub daily_usage: Option<Vec<ProviderProfileDailyUsage>>,
+    pub activity_insights: ProviderProfileActivityInsights,
+}
+
+/// Provider 头像正文的中立字节流；公共层不解释 MIME，也不限制总字节数。
+pub type ProviderProfileAvatarStream =
+    Pin<Box<dyn Stream<Item = Result<Bytes, ProviderProfileAvatarStreamError>> + Send + 'static>>;
+
+/// Provider 头像流在响应开始后的通用失败，不携带上游 URL 或正文。
+#[derive(Debug, thiserror::Error)]
+#[error("provider profile avatar stream failed")]
+pub struct ProviderProfileAvatarStreamError;
+
+/// Provider 已校验并打开的官方头像响应。
+pub struct ProviderProfileAvatar {
+    pub content_type: Option<String>,
+    pub content_length: Option<u64>,
+    pub etag: Option<String>,
+    pub body: ProviderProfileAvatarStream,
+}
+
+impl fmt::Debug for ProviderProfileAvatar {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("ProviderProfileAvatar")
+            .field("content_type", &self.content_type)
+            .field("content_length", &self.content_length)
+            .field("etag", &self.etag)
+            .field("body", &"<stream>")
+            .finish()
+    }
+}
+
 /// Provider 返回的一张安全主动额度重置卡。
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct ProviderResetCredit {
@@ -693,6 +873,20 @@ impl ProviderQuota {
             .map(|(_, used_percent)| used_percent)
     }
 
+    /// 选择 Dashboard 展示的真实窗口；没有百分比时仍保留 Provider 的滚动窗口语义。
+    #[must_use]
+    pub fn representative_window(&self) -> Option<&ProviderQuotaWindow> {
+        self.representative_used_window()
+            .map(|(index, _)| &self.windows[index])
+            .or_else(|| {
+                self.windows
+                    .iter()
+                    .enumerate()
+                    .min_by_key(|(index, window)| (quota_usage_priority(window), *index))
+                    .map(|(_, window)| window)
+            })
+    }
+
     /// 将已确认的账号级额度耗尽事实投影到展示窗口。
     ///
     /// Provider 已指出具体触顶窗口时只归一化这些窗口；否则归一化 Dashboard
@@ -825,7 +1019,7 @@ impl fmt::Debug for ProviderExport {
 #[derive(Debug, Clone, PartialEq)]
 pub struct AccountDirectoryItem {
     pub account: AccountRecord,
-    pub projection: gateway_core::engine::credential::AccountStatusProjection,
+    pub projection: gateway_core::account::AccountStatusProjection,
     pub usage: Option<super::accounts::AccountUsage>,
     pub quota: ProviderQuota,
 }

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

@@ -12,7 +12,7 @@ use super::Revision;
 pub type ModelMappings = BTreeMap<PublicModelId, UpstreamModelId>;
 
 /// 账号调度策略；由 Core 拥有稳定值与 wire 映射。
-pub use gateway_core::engine::credential::RotationStrategy;
+pub use gateway_core::account::RotationStrategy;
 
 /// 完整运行设置事实。
 #[derive(Debug, Clone, PartialEq, Eq)]
@@ -24,6 +24,8 @@ pub struct RuntimeSettings {
     pub max_concurrent_per_account: u32,
     pub request_interval_ms: u64,
     pub rotation_strategy: RotationStrategy,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
     pub usage_retention_days: u32,
     pub ops_event_retention_days: u32,
     pub audit_retention_days: u32,
@@ -39,6 +41,8 @@ pub struct ReplaceRuntimeSettings {
     pub max_concurrent_per_account: u32,
     pub request_interval_ms: u64,
     pub rotation_strategy: RotationStrategy,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
     pub usage_retention_days: u32,
     pub ops_event_retention_days: u32,
     pub audit_retention_days: u32,

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

@@ -145,7 +145,7 @@ pub trait DatabaseDumpPort: Send + Sync {
 #[derive(Debug, Clone)]
 pub struct DumpRequest {
     pub backup_id: String,
-    pub cancellation: gateway_core::engine::CancellationToken,
+    pub cancellation: gateway_core::lifecycle::CancellationToken,
 }
 
 /// 已完成并落盘的归档事实。
@@ -212,7 +212,7 @@ pub struct UploadObjectRequest {
     pub object_key: String,
     pub source: PathBuf,
     pub metadata: BackupObjectMetadata,
-    pub cancellation: gateway_core::engine::CancellationToken,
+    pub cancellation: gateway_core::lifecycle::CancellationToken,
 }
 
 /// 备份控制面所需的全部 Store 能力集合。

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

@@ -0,0 +1,10 @@
+//! 客户端安装包解析的外部能力端口。
+
+use async_trait::async_trait;
+
+use crate::model::client_distribution::CodexDesktopWindowsDownloads;
+
+#[async_trait]
+pub trait ClientDistributionResolver: Send + Sync {
+    async fn resolve_codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads;
+}

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

@@ -1,6 +1,7 @@
 //! 管理用例依赖的外部能力端口。
 
 pub mod backup;
+pub mod client_distribution;
 pub mod provider;
 pub mod store;
 pub mod system;

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

@@ -4,7 +4,7 @@ use std::{collections::BTreeMap, sync::Arc};
 
 use async_trait::async_trait;
 use gateway_core::{
-    engine::credential::ProviderAccountId,
+    account::ProviderAccountId,
     operation::Operation,
     routing::{ProviderKind, UpstreamModelId},
 };
@@ -17,7 +17,8 @@ use crate::model::provider_credentials::{
     PendingAuthorizationMutation, PrepareCredentialImport, PrepareCredentialRefresh,
     PrepareCredentialRotation, PreparedAuthorizationCommit, PreparedCredentialImport,
     PreparedCredentialRotation, ProviderExport, ProviderExportCredentialInput, ProviderModels,
-    ProviderQuota, ProviderQuotaRequest, ProviderResetCreditResult, ProviderResetCredits,
+    ProviderProfileAvatar, ProviderProfileStatistics, ProviderQuota, ProviderQuotaRequest,
+    ProviderResetCreditResult, ProviderResetCredits,
 };
 
 /// Provider 管理失败的稳定分类。
@@ -27,6 +28,8 @@ pub enum ProviderAdminErrorKind {
     Unsupported,
     NotFound,
     Conflict,
+    /// Provider 已发起不可逆操作，但无法确认最终执行结果。
+    Ambiguous,
     Unavailable,
     CredentialRefreshRequired,
     BadGateway,
@@ -35,8 +38,8 @@ pub enum ProviderAdminErrorKind {
 
 /// 不携带 OAuth 请求材料的管理错误。
 ///
-/// `message` 用于当前认证管理请求展示；上游没有标准 `error.message` 时，
-/// Provider 可以按其官方契约回退为完整的非成功响应正文。
+/// `message` 是 Provider 局部诊断，可能包含原始上游正文；通用管理用例不得自动把它作为公开文案。
+/// 只有明确拥有原始诊断合同的调用方才能读取，`Debug` 始终只记录是否存在。
 #[derive(Clone, PartialEq, Eq, thiserror::Error)]
 #[error("provider admin operation failed: {kind:?}")]
 pub struct ProviderAdminError {
@@ -146,6 +149,22 @@ pub trait ProviderAdmin: Send + Sync {
         request: ProviderQuotaRequest,
     ) -> Result<ProviderQuota, ProviderAdminError>;
 
+    /// 查询 Provider 官方个人资料统计；不支持该能力的 Provider 使用默认拒绝。
+    async fn profile_statistics(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
+    /// 打开 Provider 官方头像字节流；不支持该能力的 Provider 使用默认拒绝。
+    async fn profile_avatar(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, ProviderAdminError> {
+        Err(ProviderAdminError::new(ProviderAdminErrorKind::Unsupported))
+    }
+
     /// 查询 Provider 主动额度重置卡；不支持该能力的 Provider 使用默认拒绝。
     async fn reset_credits(
         &self,

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

@@ -6,18 +6,19 @@ use std::sync::Arc;
 
 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
+use futures::stream::BoxStream;
 
 use super::backup::BackupStorePorts;
 use crate::model::{
     MutationContext, Revision,
     account_groups::{
-        AccountGroupListQuery, AccountGroupMutation, AccountGroupPage, DeleteAccountGroup,
-        NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+        AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+        DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
     },
     accounts::{
-        AccountListQuery, AccountPage, AccountPageItem, AccountUpdateResult, AccountUsage,
-        AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
-        BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
+        AccountListQuery, AccountPage, AccountPageItem, AccountRuntimeSnapshot,
+        AccountUpdateResult, AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult,
+        AccountsUpdateResult, BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
     },
     auth::{AdminAuditEvent, AdminSession},
     client_keys::{
@@ -86,9 +87,17 @@ pub type AdminStoreResult<T> = Result<T, AdminStoreError>;
 /// 账号目录与公共账号写操作。
 #[async_trait]
 pub trait AccountStore: Send + Sync {
-    async fn list_accounts(&self, query: AccountListQuery) -> AdminStoreResult<AccountPage>;
+    async fn list_accounts(
+        &self,
+        query: AccountListQuery,
+        runtime: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage>;
 
-    async fn load_account(&self, account_id: &str) -> AdminStoreResult<Option<AccountPageItem>>;
+    async fn load_account(
+        &self,
+        account_id: &str,
+        runtime: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<Option<AccountPageItem>>;
 
     async fn load_account_usage(
         &self,
@@ -110,13 +119,13 @@ pub trait AccountStore: Send + Sync {
     async fn credential_details(
         &self,
         provider_kind: &gateway_core::routing::ProviderKind,
-        account_id: &gateway_core::engine::credential::ProviderAccountId,
+        account_id: &gateway_core::account::ProviderAccountId,
     ) -> AdminStoreResult<Option<CredentialDetails>>;
 
     async fn load_credentials_for_export(
         &self,
         provider_kind: &gateway_core::routing::ProviderKind,
-        account_ids: &[gateway_core::engine::credential::ProviderAccountId],
+        account_ids: &[gateway_core::account::ProviderAccountId],
     ) -> AdminStoreResult<Vec<ProviderExportCredentialInput>>;
 
     async fn commit_credential_import(
@@ -151,7 +160,7 @@ pub trait AccountStore: Send + Sync {
 
     async fn recover_account(
         &self,
-        account_id: &gateway_core::engine::credential::ProviderAccountId,
+        account_id: &gateway_core::account::ProviderAccountId,
         context: &MutationContext,
     ) -> AdminStoreResult<AccountUpdateResult>;
 
@@ -169,11 +178,22 @@ pub trait AccountStore: Send + Sync {
 
     async fn record_credential_export(
         &self,
-        account_ids: &[gateway_core::engine::credential::ProviderAccountId],
+        account_ids: &[gateway_core::account::ProviderAccountId],
         context: &MutationContext,
     ) -> AdminStoreResult<()>;
 }
 
+/// 可丢失账号运行态的管理读端口；跨存储编排由 Admin application service 拥有。
+#[async_trait]
+pub trait AccountRuntimeStore: Send + Sync {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot>;
+
+    async fn account_runtime(
+        &self,
+        account_ids: &[String],
+    ) -> AdminStoreResult<AccountRuntimeSnapshot>;
+}
+
 /// 管理员密码、会话和安全审计。
 #[async_trait]
 pub trait AuthStore: Send + Sync {
@@ -240,6 +260,11 @@ pub trait AccountGroupStore: Send + Sync {
         query: AccountGroupListQuery,
     ) -> AdminStoreResult<AccountGroupPage>;
 
+    async fn load_account_group_members(
+        &self,
+        group_ids: &[gateway_core::routing::AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>>;
+
     async fn create_account_group(
         &self,
         command: NewAccountGroup,
@@ -265,6 +290,10 @@ pub trait AccountGroupStore: Send + Sync {
     ) -> AdminStoreResult<AccountGroupMutation>;
 }
 
+/// 逐条读取的已计算费用事实；消费结束或丢弃时释放查询资源。
+pub type UsageCalculatedBillingStream<'a> =
+    BoxStream<'a, AdminStoreResult<UsageCalculatedBillingFact>>;
+
 /// 用量、趋势、诊断与运维错误的只读能力。
 #[async_trait]
 pub trait ObservabilityStore: Send + Sync {
@@ -294,12 +323,13 @@ pub trait ObservabilityStore: Send + Sync {
         filter: UsageFilter,
     ) -> AdminStoreResult<Vec<RequestMetricPoint>>;
 
-    /// 返回可由 Provider 重新校验的已计算费用事实，用于恢复标准费用趋势。
-    async fn usage_calculated_billing_facts(
+    /// 流式返回可由 Provider 重新校验的已计算费用事实，不保证顺序。
+    /// 查询及解码错误由流返回；调用方应逐条聚合，避免收集整个区间。
+    fn usage_calculated_billing_facts(
         &self,
         range: TimeRange,
         filter: UsageFilter,
-    ) -> AdminStoreResult<Vec<UsageCalculatedBillingFact>>;
+    ) -> UsageCalculatedBillingStream<'_>;
 
     async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage>;
 
@@ -346,13 +376,35 @@ pub trait SettingsStore: Send + Sync {
     ) -> AdminStoreResult<AdminApiKeyMutation>;
 }
 
+/// 账号目录、运行态与分组所需的 Store 能力集合。
+#[derive(Clone)]
+pub struct AdminAccountStorePorts {
+    accounts: Arc<dyn AccountStore>,
+    runtime: Arc<dyn AccountRuntimeStore>,
+    groups: Arc<dyn AccountGroupStore>,
+}
+
+impl AdminAccountStorePorts {
+    #[must_use]
+    pub fn new(
+        accounts: Arc<dyn AccountStore>,
+        runtime: Arc<dyn AccountRuntimeStore>,
+        groups: Arc<dyn AccountGroupStore>,
+    ) -> Self {
+        Self {
+            accounts,
+            runtime,
+            groups,
+        }
+    }
+}
+
 /// 管理用例所需能力的封闭集合。
 ///
 /// 字段保持私有，每个 getter 只交出一种明确能力。该类型不提供通用拆包入口。
 #[derive(Clone)]
 pub struct AdminStorePorts {
-    accounts: Arc<dyn AccountStore>,
-    account_groups: Arc<dyn AccountGroupStore>,
+    accounts: AdminAccountStorePorts,
     auth: Arc<dyn AuthStore>,
     client_keys: Arc<dyn ClientKeyStore>,
     observability: Arc<dyn ObservabilityStore>,
@@ -363,8 +415,7 @@ pub struct AdminStorePorts {
 impl AdminStorePorts {
     #[must_use]
     pub fn new(
-        accounts: Arc<dyn AccountStore>,
-        account_groups: Arc<dyn AccountGroupStore>,
+        accounts: AdminAccountStorePorts,
         auth: Arc<dyn AuthStore>,
         client_keys: Arc<dyn ClientKeyStore>,
         observability: Arc<dyn ObservabilityStore>,
@@ -373,7 +424,6 @@ impl AdminStorePorts {
     ) -> Self {
         Self {
             accounts,
-            account_groups,
             auth,
             client_keys,
             observability,
@@ -384,12 +434,17 @@ impl AdminStorePorts {
 
     #[must_use]
     pub fn accounts(&self) -> Arc<dyn AccountStore> {
-        self.accounts.clone()
+        self.accounts.accounts.clone()
+    }
+
+    #[must_use]
+    pub fn account_runtime(&self) -> Arc<dyn AccountRuntimeStore> {
+        self.accounts.runtime.clone()
     }
 
     #[must_use]
     pub fn account_groups(&self) -> Arc<dyn AccountGroupStore> {
-        self.account_groups.clone()
+        self.accounts.groups.clone()
     }
 
     #[must_use]

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

@@ -1,20 +1,30 @@
 //! Account group management use cases.
 
-use std::sync::Arc;
+use std::{
+    collections::{BTreeMap, BTreeSet},
+    sync::Arc,
+    time::SystemTime,
+};
 
 use async_trait::async_trait;
-use gateway_core::routing::{AccountGroupId, snapshot::SnapshotControl};
+use gateway_core::{
+    account::{AccountStatus, resolve_account_status},
+    routing::AccountGroupId,
+    runtime::SnapshotControl,
+};
 use uuid::Uuid;
 
 use crate::{
     model::{
         AdminError, MutationContext,
         account_groups::{
-            AccountGroupListQuery, AccountGroupMutation, AccountGroupPage, CreateAccountGroup,
-            DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+            AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupListQuery,
+            AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage, AccountGroupRecord,
+            CreateAccountGroup, DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled,
+            UpdateAccountGroup,
         },
     },
-    ports::store::AccountGroupStore,
+    ports::store::{AccountGroupStore, AccountRuntimeStore},
 };
 
 use super::{map_store_error, publish_committed};
@@ -47,6 +57,7 @@ pub trait AccountGroupService: Send + Sync {
 
 pub(crate) struct DefaultAccountGroupService {
     store: Arc<dyn AccountGroupStore>,
+    runtime: Arc<dyn AccountRuntimeStore>,
     snapshot: Arc<dyn SnapshotControl>,
 }
 
@@ -54,16 +65,54 @@ impl DefaultAccountGroupService {
     #[must_use]
     pub(crate) fn new(
         store: Arc<dyn AccountGroupStore>,
+        runtime: Arc<dyn AccountRuntimeStore>,
         snapshot: Arc<dyn SnapshotControl>,
     ) -> Self {
-        Self { store, snapshot }
+        Self {
+            store,
+            runtime,
+            snapshot,
+        }
+    }
+
+    async fn enrich_records(&self, records: &mut [AccountGroupRecord]) -> Result<(), AdminError> {
+        if records.is_empty() {
+            return Ok(());
+        }
+        let group_ids = records
+            .iter()
+            .map(|record| record.id.clone())
+            .collect::<Vec<_>>();
+        let members = self
+            .store
+            .load_account_group_members(&group_ids)
+            .await
+            .map_err(|error| map_store_error(error, "account group members"))?;
+        let account_ids = members
+            .iter()
+            .map(|member| member.account_id.clone())
+            .collect::<BTreeSet<_>>()
+            .into_iter()
+            .collect::<Vec<_>>();
+        let runtime = match self.runtime.account_runtime(&account_ids).await {
+            Ok(runtime) => runtime,
+            Err(error) => {
+                tracing::warn!(error = %error, "account group runtime projection is unavailable");
+                Default::default()
+            }
+        };
+        project_group_runtime(records, &members, &runtime);
+        Ok(())
     }
 
     async fn publish(
         &self,
         result: Result<AccountGroupMutation, crate::ports::store::AdminStoreError>,
     ) -> Result<AccountGroupMutation, AdminError> {
-        let result = result.map_err(|error| map_store_error(error, "account group"))?;
+        let mut result = result.map_err(|error| map_store_error(error, "account group"))?;
+        if let Some(record) = result.record.as_mut() {
+            self.enrich_records(std::slice::from_mut(record)).await?;
+        }
         publish_committed(self.snapshot.as_ref(), result.config_revision).await?;
         Ok(result)
     }
@@ -72,10 +121,13 @@ impl DefaultAccountGroupService {
 #[async_trait]
 impl AccountGroupService for DefaultAccountGroupService {
     async fn list(&self, query: AccountGroupListQuery) -> Result<AccountGroupPage, AdminError> {
-        self.store
+        let mut page = self
+            .store
             .list_account_groups(query)
             .await
-            .map_err(|error| map_store_error(error, "account group"))
+            .map_err(|error| map_store_error(error, "account group"))?;
+        self.enrich_records(&mut page.items).await?;
+        Ok(page)
     }
 
     async fn create(
@@ -84,7 +136,7 @@ impl AccountGroupService for DefaultAccountGroupService {
         command: CreateAccountGroup,
     ) -> Result<AccountGroupMutation, AdminError> {
         let id = AccountGroupId::new(format!("grp_{}", Uuid::now_v7().simple()))
-            .map_err(|_| AdminError::internal("Failed to create account group ID"))?;
+            .map_err(|_| AdminError::internal("创建账号组 ID 失败"))?;
         self.publish(
             self.store
                 .create_account_group(
@@ -128,3 +180,63 @@ impl AccountGroupService for DefaultAccountGroupService {
             .await
     }
 }
+
+fn project_group_runtime(
+    records: &mut [AccountGroupRecord],
+    members: &[AccountGroupMemberFact],
+    runtime: &crate::model::accounts::AccountRuntimeSnapshot,
+) {
+    let now = SystemTime::now();
+    let mut status_by_account = BTreeMap::new();
+    let mut slots_by_account = BTreeMap::new();
+    let mut accounts_by_group = BTreeMap::<&str, Vec<&str>>::new();
+    for member in members {
+        let mut status = member.status.clone();
+        status.rate_limited_until = runtime
+            .rate_limited_until
+            .get(&member.account_id)
+            .copied()
+            .map(Into::into);
+        status_by_account
+            .entry(member.account_id.as_str())
+            .or_insert_with(|| resolve_account_status(&status, now).status);
+        slots_by_account
+            .entry(member.account_id.as_str())
+            .or_insert(member.total_slots);
+        accounts_by_group
+            .entry(member.group_id.as_str())
+            .or_default()
+            .push(member.account_id.as_str());
+    }
+    for record in records {
+        let account_ids = accounts_by_group
+            .get(record.id.as_str())
+            .map_or(&[][..], Vec::as_slice);
+        let available_ids = account_ids
+            .iter()
+            .copied()
+            .filter(|account_id| status_by_account.get(account_id) == Some(&AccountStatus::Normal))
+            .collect::<Vec<_>>();
+        let total = u64::try_from(account_ids.len()).unwrap_or(u64::MAX);
+        let available = u64::try_from(available_ids.len()).unwrap_or(u64::MAX);
+        record.account_summary = AccountGroupAccountSummary {
+            available,
+            limited: total.saturating_sub(available),
+            total,
+        };
+        record.capacity = AccountGroupCapacity {
+            used_slots: if available_ids.is_empty() {
+                Some(0)
+            } else {
+                runtime.in_flight.as_ref().map(|in_flight| {
+                    available_ids.iter().fold(0_u64, |sum, account_id| {
+                        sum.saturating_add(in_flight.get(*account_id).copied().unwrap_or(0))
+                    })
+                })
+            },
+            total_slots: available_ids.iter().fold(0_u64, |sum, account_id| {
+                sum.saturating_add(slots_by_account.get(*account_id).copied().unwrap_or(0))
+            }),
+        };
+    }
+}

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

@@ -6,11 +6,10 @@ use async_trait::async_trait;
 use chrono::{Duration, Utc};
 use futures::StreamExt as _;
 use gateway_core::{
-    engine::{
-        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeRequest},
-    },
-    routing::{ProviderKind, UpstreamModelId, snapshot::SnapshotControl},
+    account::ProviderAccountId,
+    engine::probe::{AccountProbe, AccountProbeRequest},
+    routing::{ProviderKind, UpstreamModelId},
+    runtime::SnapshotControl,
 };
 
 use crate::{
@@ -24,12 +23,16 @@ use crate::{
         observability::TimeRange,
         provider_credentials::{
             AccountDirectoryItem, AccountDirectoryPage, AccountExportBundle, AccountRefreshResult,
-            ConsumeProviderResetCredit, PrepareCredentialRefresh, ProviderModels, ProviderQuota,
-            ProviderQuotaRequest, ProviderQuotaWindow, ProviderResetCreditResult,
-            ProviderResetCredits, QuotaLocalUsageAttribution,
+            ConsumeProviderResetCredit, PrepareCredentialRefresh, ProviderModels,
+            ProviderProfileAvatar, ProviderProfileStatistics, ProviderQuota, ProviderQuotaRequest,
+            ProviderQuotaWindow, ProviderResetCreditResult, ProviderResetCredits,
+            QuotaLocalUsageAttribution,
         },
     },
-    ports::{provider::ProviderAdminRegistry, store::AccountStore},
+    ports::{
+        provider::ProviderAdminRegistry,
+        store::{AccountRuntimeStore, AccountStore},
+    },
 };
 
 use super::{
@@ -80,14 +83,26 @@ pub trait AccountsService: Send + Sync {
         refresh: bool,
     ) -> Result<AccountDirectoryItem, AdminError>;
 
+    async fn profile_statistics(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持账号统计"))
+    }
+
+    async fn profile_avatar(
+        &self,
+        _account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, AdminError> {
+        Err(AdminError::invalid("当前 Provider 不支持账号头像"))
+    }
+
     async fn reset_credits(
         &self,
         _context: &MutationContext,
         _account_id: ProviderAccountId,
     ) -> Result<ProviderResetCredits, AdminError> {
-        Err(AdminError::invalid(
-            "Provider reset credits are not supported",
-        ))
+        Err(AdminError::invalid("当前 Provider 不支持重置额度"))
     }
 
     async fn consume_reset_credit(
@@ -95,9 +110,7 @@ pub trait AccountsService: Send + Sync {
         _context: &MutationContext,
         _command: ConsumeProviderResetCredit,
     ) -> Result<ProviderResetCreditResult, AdminError> {
-        Err(AdminError::invalid(
-            "Provider reset credits are not supported",
-        ))
+        Err(AdminError::invalid("当前 Provider 不支持重置额度"))
     }
 
     async fn models(
@@ -115,6 +128,7 @@ pub trait AccountsService: Send + Sync {
 
 pub(crate) struct DefaultAccountsService {
     accounts: Arc<dyn AccountStore>,
+    account_runtime: Arc<dyn AccountRuntimeStore>,
     providers: ProviderAdminRegistry,
     snapshot: Arc<dyn SnapshotControl>,
     probe: Arc<dyn AccountProbe>,
@@ -126,12 +140,14 @@ impl DefaultAccountsService {
     #[must_use]
     pub(crate) fn new(
         accounts: Arc<dyn AccountStore>,
+        account_runtime: Arc<dyn AccountRuntimeStore>,
         providers: ProviderAdminRegistry,
         snapshot: Arc<dyn SnapshotControl>,
         probe: Arc<dyn AccountProbe>,
     ) -> Self {
         Self {
             accounts,
+            account_runtime,
             providers,
             snapshot,
             probe,
@@ -155,11 +171,16 @@ impl DefaultAccountsService {
         &self,
         account_id: &ProviderAccountId,
     ) -> Result<AccountPageItem, AdminError> {
+        let runtime = self
+            .account_runtime
+            .account_runtime(&[account_id.as_str().to_owned()])
+            .await
+            .map_err(|error| map_store_error(error, "account runtime"))?;
         self.accounts
-            .load_account(account_id.as_str())
+            .load_account(account_id.as_str(), runtime)
             .await
             .map_err(|error| map_store_error(error, "provider account"))?
-            .ok_or_else(|| AdminError::not_found("Provider account was not found"))
+            .ok_or_else(|| AdminError::not_found("Provider 账号不存在"))
     }
 
     async fn provider_for_account(
@@ -248,6 +269,11 @@ impl DefaultAccountsService {
             })
             .await
             .map_err(|error| map_provider_error(error, "provider quota"))?;
+        let stored = if refresh_quota {
+            self.load_account(account_id).await?
+        } else {
+            stored
+        };
         self.attach_quota_local_usage(
             std::slice::from_ref(&stored),
             std::slice::from_mut(&mut quota),
@@ -266,9 +292,14 @@ impl DefaultAccountsService {
 #[async_trait]
 impl AccountsService for DefaultAccountsService {
     async fn list(&self, query: AccountListQuery) -> Result<AccountDirectoryPage, AdminError> {
+        let runtime = self
+            .account_runtime
+            .active_rate_limits()
+            .await
+            .map_err(|error| map_store_error(error, "account runtime"))?;
         let page = self
             .accounts
-            .list_accounts(query)
+            .list_accounts(query, runtime)
             .await
             .map_err(|error| map_store_error(error, "account directory"))?;
         let now = Utc::now();
@@ -293,7 +324,7 @@ impl AccountsService for DefaultAccountsService {
         let mut quotas = futures::future::join_all(page.items.iter().map(|item| async {
             let account = &item.account;
             let account_id = ProviderAccountId::new(account.id.clone())
-                .map_err(|_| AdminError::invalid("Invalid provider account ID"))?;
+                .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
             // 单个账号的 quota 投影失败（Provider 未注册或 quota 读取失败）不拖垮整页：
             // 该账号降级为空额度投影，其余账号与页面状态照常返回。
             let provider = match self.providers.require(&account.provider_kind) {
@@ -359,9 +390,7 @@ impl AccountsService for DefaultAccountsService {
         account_ids: Vec<ProviderAccountId>,
     ) -> Result<AccountExportBundle, AdminError> {
         if account_ids.is_empty() || account_ids.len() > 200 {
-            return Err(AdminError::invalid(
-                "Account export requires between 1 and 200 accounts",
-            ));
+            return Err(AdminError::invalid("账号导出数量必须在 1 到 200 之间"));
         }
         let exported_ids = account_ids.clone();
         let mut grouped = BTreeMap::<ProviderKind, Vec<ProviderAccountId>>::new();
@@ -376,7 +405,7 @@ impl AccountsService for DefaultAccountsService {
             let unique = ids.iter().collect::<std::collections::BTreeSet<_>>();
             unique.len() != ids.len()
         }) {
-            return Err(AdminError::invalid("Account export contains duplicate IDs"));
+            return Err(AdminError::invalid("账号导出列表包含重复 ID"));
         }
         let mut documents = Vec::with_capacity(grouped.len());
         for (provider_kind, ids) in grouped {
@@ -466,7 +495,7 @@ impl AccountsService for DefaultAccountsService {
         command: UpdateAccount,
     ) -> Result<AccountUpdateResult, AdminError> {
         let account_id = ProviderAccountId::new(command.account_id.clone())
-            .map_err(|_| AdminError::invalid("Invalid provider account ID"))?;
+            .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
         let (_, provider) = self.provider_for_account(&account_id).await?;
         let enabled = command.enabled;
         let result = self
@@ -494,7 +523,7 @@ impl AccountsService for DefaultAccountsService {
             .iter()
             .map(|id| {
                 ProviderAccountId::new(id.clone())
-                    .map_err(|_| AdminError::invalid("Invalid provider account ID"))
+                    .map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))
             })
             .collect::<Result<Vec<_>, _>>()?;
         let mut providers = BTreeMap::<
@@ -538,6 +567,28 @@ impl AccountsService for DefaultAccountsService {
         self.load_directory_item(account_id, refresh).await
     }
 
+    async fn profile_statistics(
+        &self,
+        account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileStatistics, AdminError> {
+        let (_, provider) = self.provider_for_account(account_id).await?;
+        provider
+            .profile_statistics(account_id)
+            .await
+            .map_err(|error| map_provider_error(error, "provider profile statistics"))
+    }
+
+    async fn profile_avatar(
+        &self,
+        account_id: &ProviderAccountId,
+    ) -> Result<ProviderProfileAvatar, AdminError> {
+        let (_, provider) = self.provider_for_account(account_id).await?;
+        provider
+            .profile_avatar(account_id)
+            .await
+            .map_err(|error| map_provider_error(error, "provider profile avatar"))
+    }
+
     async fn reset_credits(
         &self,
         context: &MutationContext,
@@ -654,6 +705,9 @@ impl AccountsService for DefaultAccountsService {
                         .map(|response| String::from_utf8_lossy(response.body()).into_owned());
                     let message = error.client_message().to_owned();
                     vec![AccountConnectionTestEvent::Failed {
+                        source: error.source(),
+                        gateway_error_code: error.kind(),
+                        send_state: error.send_state(),
                         message,
                         provider_error_code: error.client_error_code().map(ToOwned::to_owned),
                         provider_error_type: error.client_error_type().map(ToOwned::to_owned),
@@ -673,11 +727,7 @@ fn map_reset_credits_error_after_refresh(
     error: crate::ports::provider::ProviderAdminError,
 ) -> AdminError {
     if error.kind() == crate::ports::provider::ProviderAdminErrorKind::CredentialRefreshRequired {
-        return AdminError::bad_gateway(
-            error
-                .message()
-                .unwrap_or("OpenAI reset-credit upstream rejected the refreshed credential"),
-        );
+        return AdminError::bad_gateway("上游服务拒绝了刷新后的凭据");
     }
     map_provider_error(error, "provider reset credits")
 }

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

@@ -2,7 +2,7 @@
 
 use std::sync::Arc;
 
-use argon2::{Argon2, PasswordHash, PasswordHasher, PasswordVerifier, password_hash::SaltString};
+use argon2::{Argon2, PasswordHash, PasswordHasher, PasswordVerifier};
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use chrono::{Duration, Utc};
@@ -69,7 +69,7 @@ impl DefaultAuthService {
             id: format!("audit_{}", Uuid::now_v7().simple()),
             actor_kind: AuditActorKind::AdminSession,
             actor_admin_user_id: Some(self.default_admin_user_id.clone()),
-            actor_ref: format!("admin:{}", self.default_admin_user_id),
+            actor_ref: crate::model::auth::admin_session_actor_ref(&self.default_admin_user_id),
             request_id: None,
             action: action.to_owned(),
             entity_kind: "admin_session".to_owned(),
@@ -183,7 +183,7 @@ impl AuthService for DefaultAuthService {
         if let Some(session) = session {
             let mut event = self.auth_audit("admin.logout", Utc::now());
             event.actor_admin_user_id = Some(session.admin_user_id.clone());
-            event.actor_ref = format!("admin:{}", session.admin_user_id);
+            event.actor_ref = crate::model::auth::admin_session_actor_ref(&session.admin_user_id);
             event.entity_ref = session.admin_user_id;
             self.store
                 .append_audit_event(event)
@@ -195,16 +195,15 @@ impl AuthService for DefaultAuthService {
 }
 
 fn hash_admin_password(password: &str) -> Result<String, AdminError> {
-    let salt = SaltString::generate(&mut OsRng);
     Argon2::default()
-        .hash_password(password.as_bytes(), &salt)
+        .hash_password(password.as_bytes())
         .map(|hash| hash.to_string())
-        .map_err(|_| AdminError::internal("Failed to hash administrator password"))
+        .map_err(|_| AdminError::internal("管理员密码哈希失败"))
 }
 
 fn verify_admin_password(password: &str, encoded: &str) -> Result<bool, AdminError> {
     let hash = PasswordHash::new(encoded)
-        .map_err(|_| AdminError::internal("Stored administrator password hash is invalid"))?;
+        .map_err(|_| AdminError::internal("已保存的管理员密码哈希不合法"))?;
     Ok(Argon2::default()
         .verify_password(password.as_bytes(), &hash)
         .is_ok())

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

@@ -5,7 +5,7 @@ use std::time::Duration;
 
 use async_trait::async_trait;
 use chrono::{DateTime, Utc};
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;
 use secrecy::ExposeSecret as _;
 use uuid::Uuid;
 
@@ -326,7 +326,9 @@ impl DefaultBackupService {
             crate::model::MutationActor::System => AuditActorKind::System,
         };
         let actor_ref = match &context.actor {
-            crate::model::MutationActor::AdminSession { admin_user_id } => admin_user_id.clone(),
+            crate::model::MutationActor::AdminSession { admin_user_id } => {
+                crate::model::auth::admin_session_actor_ref(admin_user_id)
+            }
             crate::model::MutationActor::AdminApiKey => "admin_api_key".to_owned(),
             crate::model::MutationActor::System => "system".to_owned(),
         };
@@ -429,9 +431,7 @@ fn map_backup_error(error: BackupError) -> AdminError {
         code::ACTIVE_TASK_CONFLICT | code::STATE_CONFLICT | code::STORAGE_IDENTITY_LOCKED => {
             AdminError::conflict(error.message().to_owned())
         }
-        code::STORE_UNAVAILABLE => {
-            AdminError::new(AdminErrorKind::Unavailable, error.message().to_owned())
-        }
-        _ => AdminError::bad_gateway(error.message().to_owned()),
+        code::STORE_UNAVAILABLE => AdminError::new(AdminErrorKind::Unavailable, "备份服务暂不可用"),
+        _ => AdminError::bad_gateway("备份服务请求失败"),
     }
 }

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

@@ -0,0 +1,33 @@
+//! Codex 客户端下载信息用例。
+
+use std::sync::Arc;
+
+use async_trait::async_trait;
+
+use crate::{
+    model::client_distribution::CodexDesktopWindowsDownloads,
+    ports::client_distribution::ClientDistributionResolver,
+};
+
+#[async_trait]
+pub trait ClientDistributionService: Send + Sync {
+    async fn codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads;
+}
+
+pub(crate) struct DefaultClientDistributionService {
+    resolver: Arc<dyn ClientDistributionResolver>,
+}
+
+impl DefaultClientDistributionService {
+    #[must_use]
+    pub(crate) const fn new(resolver: Arc<dyn ClientDistributionResolver>) -> Self {
+        Self { resolver }
+    }
+}
+
+#[async_trait]
+impl ClientDistributionService for DefaultClientDistributionService {
+    async fn codex_desktop_windows(&self, refresh: bool) -> CodexDesktopWindowsDownloads {
+        self.resolver.resolve_codex_desktop_windows(refresh).await
+    }
+}

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

@@ -5,7 +5,7 @@ use std::sync::Arc;
 use async_trait::async_trait;
 use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
 use gateway_core::policy::ClientApiKeyId;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;
 use rand_core::{OsRng, RngCore as _};
 use uuid::Uuid;
 
@@ -77,7 +77,7 @@ impl ClientKeyService for DefaultClientKeyService {
             .reveal_client_key(id)
             .await
             .map_err(|error| map_store_error(error, "client API key"))?
-            .ok_or_else(|| AdminError::not_found("Client API key was not found"))
+            .ok_or_else(|| AdminError::not_found("Client API Key 不存在"))
     }
 
     async fn create(
@@ -86,7 +86,7 @@ impl ClientKeyService for DefaultClientKeyService {
         command: CreateClientKey,
     ) -> Result<CreatedClientKey, AdminError> {
         let id = ClientApiKeyId::new(format!("key_{}", Uuid::now_v7().simple()))
-            .map_err(|_| AdminError::internal("Failed to create Client API key ID"))?;
+            .map_err(|_| AdminError::internal("创建 Client API Key ID 失败"))?;
         let mut bytes = [0_u8; 32];
         OsRng.fill_bytes(&mut bytes);
         let plaintext = format!("sk_{}", URL_SAFE_NO_PAD.encode(bytes));
@@ -176,7 +176,7 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
     };
     if cursor.sort != query.sort {
         return Err(AdminError::invalid(
-            "Client API key cursor sort does not match the query",
+            "Client API Key 游标排序与查询条件不一致",
         ));
     }
     let matches = matches!(
@@ -198,6 +198,6 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
     if matches {
         Ok(())
     } else {
-        Err(AdminError::invalid("Invalid Client API key cursor"))
+        Err(AdminError::invalid("Client API Key 游标不合法"))
     }
 }

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

@@ -4,6 +4,7 @@ pub mod account_groups;
 pub mod accounts;
 pub mod auth;
 pub mod backup;
+pub mod client_distribution;
 pub mod client_keys;
 pub mod observability;
 pub mod openai;
@@ -29,8 +30,9 @@ use crate::{
     },
 };
 use gateway_core::{
-    engine::credential::ProviderAccountId,
-    routing::{ConfigRevision, ProviderKind, snapshot::SnapshotControl},
+    account::ProviderAccountId,
+    routing::{ConfigRevision, ProviderKind},
+    runtime::SnapshotControl,
 };
 
 fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError {
@@ -42,7 +44,15 @@ fn map_store_error(error: AdminStoreError, resource: &'static str) -> AdminError
         }
         AdminStoreErrorKind::Unavailable => AdminErrorKind::Unavailable,
     };
-    AdminError::new(kind, format!("{resource} operation failed"))
+    tracing::warn!(resource, error_kind = ?error.kind(), "admin store operation failed");
+    let message = match kind {
+        AdminErrorKind::Invalid => "请求参数不合法",
+        AdminErrorKind::NotFound => "请求的资源不存在",
+        AdminErrorKind::Conflict => "当前资源状态冲突，请刷新后重试",
+        AdminErrorKind::Unavailable => "依赖服务暂不可用",
+        _ => "服务内部错误",
+    };
+    AdminError::new(kind, message)
 }
 
 fn map_provider_error(
@@ -56,15 +66,23 @@ fn map_provider_error(
         ProviderAdminErrorKind::Unsupported => AdminErrorKind::Invalid,
         ProviderAdminErrorKind::NotFound => AdminErrorKind::NotFound,
         ProviderAdminErrorKind::Conflict => AdminErrorKind::Conflict,
+        ProviderAdminErrorKind::Ambiguous => AdminErrorKind::UpstreamResultUnknown,
         ProviderAdminErrorKind::Unavailable => AdminErrorKind::Unavailable,
         ProviderAdminErrorKind::CredentialRefreshRequired => AdminErrorKind::Unavailable,
         ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
         ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
     };
-    let message = error
-        .message()
-        .map(ToOwned::to_owned)
-        .unwrap_or_else(|| format!("{resource} operation failed"));
+    tracing::warn!(resource, error_kind = ?error.kind(), "admin provider operation failed");
+    let message = match kind {
+        AdminErrorKind::Invalid => "Provider 请求不合法",
+        AdminErrorKind::NotFound => "Provider 资源不存在",
+        AdminErrorKind::Conflict => "Provider 资源状态冲突，请刷新后重试",
+        AdminErrorKind::BadGateway => "上游服务请求失败",
+        AdminErrorKind::UpstreamResultUnknown => "上游执行结果未知，请刷新状态后再决定是否重试",
+        AdminErrorKind::Unavailable => "Provider 服务暂不可用",
+        AdminErrorKind::Internal => "服务内部错误",
+        _ => "Provider 操作失败",
+    };
     AdminError::new(kind, message)
 }
 
@@ -73,7 +91,7 @@ async fn publish_committed(
     revision: crate::model::Revision,
 ) -> Result<(), AdminError> {
     let revision = ConfigRevision::new(revision.get())
-        .map_err(|_| AdminError::internal("Committed configuration revision is invalid"))?;
+        .map_err(|_| AdminError::internal("已提交的配置版本不合法"))?;
     snapshot.publish_committed(revision).await;
     Ok(())
 }
@@ -88,7 +106,7 @@ async fn required_credential(
         .credential_details(provider_kind, account_id)
         .await
         .map_err(|error| map_store_error(error, resource))?
-        .ok_or_else(|| AdminError::not_found(format!("{resource} was not found")))
+        .ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
 }
 
 async fn pending_authorization(
@@ -120,7 +138,7 @@ async fn pending_authorization(
 fn validate_prepared_import(
     provider_kind: &ProviderKind,
     prepared: &PreparedCredentialImport,
-    resource: &'static str,
+    _resource: &'static str,
 ) -> Result<(), AdminError> {
     if prepared.provider_kind != *provider_kind
         || prepared
@@ -128,9 +146,7 @@ fn validate_prepared_import(
             .iter()
             .any(|credential| credential.provider_kind != *provider_kind)
     {
-        return Err(AdminError::conflict(format!(
-            "{resource} prepared facts do not match the requested Provider scope"
-        )));
+        return Err(AdminError::conflict("Provider 准备结果与请求范围不一致"));
     }
     Ok(())
 }
@@ -138,15 +154,13 @@ fn validate_prepared_import(
 fn validate_prepared_rotation(
     account: &crate::model::accounts::AccountRecord,
     prepared: &PreparedCredentialRotation,
-    resource: &'static str,
+    _resource: &'static str,
 ) -> Result<(), AdminError> {
     let facts = prepared.facts();
     if facts.account_id.as_str() != account.id.as_str()
         || facts.provider_kind != account.provider_kind
     {
-        return Err(AdminError::conflict(format!(
-            "{resource} prepared facts do not match the current credential"
-        )));
+        return Err(AdminError::conflict("Provider 准备结果与当前凭据不一致"));
     }
     Ok(())
 }
@@ -160,9 +174,7 @@ async fn validate_authorization_commit(
     if prepared.pending.provider_kind() != provider_kind
         || !prepared.pending.owner_binding().matches_context(context)
     {
-        let validation_error = AdminError::conflict(format!(
-            "{resource} pending authorization binding is invalid"
-        ));
+        let validation_error = AdminError::conflict("OAuth 授权绑定已失效，请重新发起授权");
         if let Err(error) = prepared.abort().await {
             tracing::warn!(
                 resource,
@@ -188,9 +200,7 @@ async fn validate_authorization_commit(
         _ => false,
     };
     if !matches_target {
-        let validation_error = AdminError::conflict(format!(
-            "{resource} prepared credential does not match its pending target"
-        ));
+        let validation_error = AdminError::conflict("OAuth 凭据与待提交目标不一致");
         if let Err(error) = prepared.abort().await {
             tracing::warn!(
                 resource,

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

@@ -1,13 +1,16 @@
 //! 观测查询、趋势、费用覆盖与健康阈值规则。
 
 use std::{
-    collections::{BTreeMap, btree_map::Entry},
+    collections::{BTreeMap, HashMap, btree_map::Entry},
+    str::FromStr,
     sync::Arc,
+    time::{Duration as StdDuration, Instant},
 };
 
 use async_trait::async_trait;
 use chrono::{DateTime, Duration, Timelike as _, Utc};
-use gateway_core::{engine::credential::ProviderAccountId, routing::ProviderKind};
+use futures::TryStreamExt;
+use gateway_core::{account::ProviderAccountId, routing::ProviderKind};
 
 use crate::{
     model::{
@@ -27,7 +30,7 @@ use crate::{
     },
     ports::{
         provider::{ProviderAdminErrorKind, ProviderAdminRegistry},
-        store::{ObservabilityStore, SettingsStore},
+        store::{AccountStore, ObservabilityStore, SettingsStore, UsageCalculatedBillingStream},
     },
 };
 
@@ -38,6 +41,58 @@ const HEALTH_TIMELINE_SLOTS: i64 = 24 * 4;
 const HEALTH_TIMELINE_MIN_SAMPLE_SIZE: u64 = 10;
 const HEALTH_TIMELINE_UNAVAILABLE_FAILURE_THRESHOLD: u64 = 3;
 const HEALTH_TIMELINE_STABLE_RELIABILITY: f64 = 99.0;
+const DASHBOARD_QUERY_BUCKET_SECONDS: i64 = 2;
+const DASHBOARD_QUERY_CACHE_RETENTION: StdDuration = StdDuration::from_secs(2);
+
+#[derive(Clone, Copy, PartialEq, Eq, Hash)]
+struct DashboardQueryKey {
+    start: DateTime<Utc>,
+    end_bucket: i64,
+}
+
+impl DashboardQueryKey {
+    fn new(range: TimeRange) -> Self {
+        Self {
+            start: range.start,
+            end_bucket: range
+                .end
+                .timestamp()
+                .div_euclid(DASHBOARD_QUERY_BUCKET_SECONDS),
+        }
+    }
+}
+
+struct DashboardQueryEntry {
+    created_at: Instant,
+    result: Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>>,
+}
+
+#[derive(Default)]
+struct DashboardQueryCache {
+    entries: tokio::sync::Mutex<HashMap<DashboardQueryKey, DashboardQueryEntry>>,
+}
+
+impl DashboardQueryCache {
+    async fn result_cell(
+        &self,
+        key: DashboardQueryKey,
+    ) -> Arc<tokio::sync::OnceCell<Result<DashboardResult, AdminError>>> {
+        let now = Instant::now();
+        let mut entries = self.entries.lock().await;
+        entries.retain(|_, entry| {
+            now.duration_since(entry.created_at) < DASHBOARD_QUERY_CACHE_RETENTION
+        });
+        Arc::clone(
+            &entries
+                .entry(key)
+                .or_insert_with(|| DashboardQueryEntry {
+                    created_at: now,
+                    result: Arc::new(tokio::sync::OnceCell::new()),
+                })
+                .result,
+        )
+    }
+}
 
 /// API 消费的观测控制面服务。
 #[async_trait]
@@ -72,31 +127,32 @@ pub trait ObservabilityService: Send + Sync {
 
 pub(crate) struct DefaultObservabilityService {
     store: Arc<dyn ObservabilityStore>,
+    accounts: Arc<dyn AccountStore>,
     settings: Arc<dyn SettingsStore>,
     providers: ProviderAdminRegistry,
+    dashboard_queries: DashboardQueryCache,
 }
 
 impl DefaultObservabilityService {
     #[must_use]
     pub(crate) fn new(
         store: Arc<dyn ObservabilityStore>,
+        accounts: Arc<dyn AccountStore>,
         settings: Arc<dyn SettingsStore>,
         providers: ProviderAdminRegistry,
     ) -> Self {
         Self {
             store,
+            accounts,
             settings,
             providers,
+            dashboard_queries: DashboardQueryCache::default(),
         }
     }
-}
 
-#[async_trait]
-impl ObservabilityService for DefaultObservabilityService {
-    async fn dashboard_summary(
+    async fn load_dashboard_summary(
         &self,
         range: TimeRange,
-        kind: TrendKind,
     ) -> Result<DashboardResult, AdminError> {
         let observed_at = Utc::now();
         let (mut observation, settings, runtime_slots) = futures::try_join!(
@@ -105,7 +161,7 @@ impl ObservabilityService for DefaultObservabilityService {
             self.store.dashboard_runtime_slots(observed_at),
         )
         .map_err(|error| map_store_error(error, "dashboard"))?;
-        self.enrich_billing(&mut observation.recent_requests);
+        self.enrich_list_billing(&mut observation.recent_requests);
         self.enrich_dashboard_quotas(&mut observation.account_usage)
             .await;
         let today_start = china_day_start(observation.range.end);
@@ -118,11 +174,18 @@ impl ObservabilityService for DefaultObservabilityService {
             observation.totals.cached_tokens,
             observation.totals.input_tokens,
         );
-        let average_first_token_latency_ms = average(
-            observation.requests.first_token_latency_sum_ms,
-            observation.requests.first_token_latency_count,
-        );
-        let trend = trend(kind, observation.trend.clone())?;
+        let (first_token_latency_sum_ms, first_token_latency_count) = observation
+            .trend
+            .iter()
+            .fold((0_u64, 0_u64), |(sum, count), point| {
+                (
+                    sum.saturating_add(point.metrics.first_token_latency_sum_ms),
+                    count.saturating_add(point.metrics.first_token_latency_count),
+                )
+            });
+        let average_first_token_latency_ms =
+            average(first_token_latency_sum_ms, first_token_latency_count);
+        let trend = trend(TrendKind::Usage, observation.trend.clone())?;
         let health_timeline = health_timeline_at(&observation.trend, Utc::now());
         let wire_profiles = self.providers.dashboard_wire_profiles();
         let max_concurrent_per_account = u64::from(settings.max_concurrent_per_account);
@@ -160,6 +223,26 @@ impl ObservabilityService for DefaultObservabilityService {
             wire_profiles,
         })
     }
+}
+
+#[async_trait]
+impl ObservabilityService for DefaultObservabilityService {
+    async fn dashboard_summary(
+        &self,
+        range: TimeRange,
+        kind: TrendKind,
+    ) -> Result<DashboardResult, AdminError> {
+        let cell = self
+            .dashboard_queries
+            .result_cell(DashboardQueryKey::new(range))
+            .await;
+        let mut result = cell
+            .get_or_init(|| self.load_dashboard_summary(range))
+            .await
+            .clone()?;
+        result.trend = trend(kind, result.observation.trend.clone())?;
+        Ok(result)
+    }
 
     async fn dashboard_trend(
         &self,
@@ -180,20 +263,20 @@ impl ObservabilityService for DefaultObservabilityService {
             .list_usage_records(query)
             .await
             .map_err(|error| map_store_error(error, "usage records"))?;
-        self.enrich_billing(&mut page.items);
+        self.enrich_list_billing(&mut page.items);
         Ok(page)
     }
 
     async fn usage_record_detail(&self, request_id: &str) -> Result<UsageDetail, AdminError> {
         if request_id.trim().is_empty() {
-            return Err(AdminError::invalid("Usage record ID is required"));
+            return Err(AdminError::invalid("用量记录 ID 不能为空"));
         }
         let mut detail = self
             .store
             .usage_record_detail(request_id)
             .await
             .map_err(|error| map_store_error(error, "usage record"))?;
-        self.enrich_billing(std::slice::from_mut(&mut detail.request));
+        self.enrich_detail_billing(std::slice::from_mut(&mut detail.request));
         Ok(detail)
     }
 
@@ -222,13 +305,21 @@ impl ObservabilityService for DefaultObservabilityService {
         range: TimeRange,
         filter: UsageFilter,
     ) -> Result<UsageInsights, AdminError> {
-        let (overview, trend, billing_facts) = futures::try_join!(
-            self.store.usage_summary(range, filter.clone()),
-            self.store.usage_trend(range, filter.clone()),
-            self.store.usage_calculated_billing_facts(range, filter),
-        )
-        .map_err(|error| map_store_error(error, "usage insights"))?;
-        let standard_costs = recover_standard_costs(&self.providers, billing_facts)?;
+        let aggregates = async {
+            futures::try_join!(
+                self.store.usage_summary(range, filter.clone()),
+                self.store.usage_trend(range, filter.clone()),
+            )
+            .map_err(|error| map_store_error(error, "usage insights"))
+        };
+        let ((overview, trend), standard_costs) = futures::try_join!(
+            aggregates,
+            recover_standard_costs(
+                &self.providers,
+                self.store
+                    .usage_calculated_billing_facts(range, filter.clone()),
+            ),
+        )?;
         build_usage_insights(overview, trend, standard_costs)
     }
 
@@ -246,26 +337,50 @@ impl ObservabilityService for DefaultObservabilityService {
         let total_requests = items.iter().fold(0_u64, |total, item| {
             total.saturating_add(item.request_count)
         });
-        Ok(DiagnosticsResult {
-            dimension,
-            items: items
-                .into_iter()
-                .map(|item| DiagnosticsItem {
+        let mut items = items
+            .into_iter()
+            .map(|item| {
+                let error_rate = rate_or_zero(item.failure_count, item.request_count);
+                let non_completion_rate =
+                    rate_or_zero(item.non_completion_count, item.request_count);
+                let retry_rate = rate_or_zero(item.retry_count, item.request_count);
+                let impact_score = diagnostic_impact_score(
+                    item.request_count,
+                    total_requests,
+                    error_rate,
+                    non_completion_rate,
+                    retry_rate,
+                    item.first_token_p95_ms,
+                );
+                DiagnosticsItem {
                     key: item.key,
                     name: item.name,
                     request_count: item.request_count,
-                    success_count: item.request_count.saturating_sub(item.failure_count),
+                    success_count: item.success_count,
                     error_count: item.failure_count,
-                    error_rate: rate_or_zero(item.failure_count, item.request_count),
+                    error_rate,
                     request_share: rate_or_zero(item.request_count, total_requests),
                     average_latency_ms: item.average_latency_ms,
                     latency_p95_ms: item.latency_p95_ms,
+                    first_token_p95_ms: item.first_token_p95_ms,
+                    non_completion_count: item.non_completion_count,
+                    non_completion_rate,
+                    retry_count: item.retry_count,
+                    retry_rate,
+                    impact_score,
                     estimated_cost: usd_cost(&item.costs),
                     attempt_count: item.attempt_count,
                     total_tokens: item.total_tokens,
-                })
-                .collect(),
-        })
+                }
+            })
+            .collect::<Vec<_>>();
+        items.sort_by(|left, right| {
+            right
+                .impact_score
+                .total_cmp(&left.impact_score)
+                .then_with(|| right.request_count.cmp(&left.request_count))
+        });
+        Ok(DiagnosticsResult { dimension, items })
     }
 
     async fn ops_errors(&self, query: OpsErrorQuery) -> Result<OpsErrorPage, AdminError> {
@@ -279,35 +394,40 @@ impl ObservabilityService for DefaultObservabilityService {
 fn build_usage_insights(
     overview: UsageOverview,
     trend: Vec<RequestMetricPoint>,
-    standard_costs: UsageStandardCosts,
+    standard_costs: UsageCostScenarios,
 ) -> Result<UsageInsights, AdminError> {
     let granularity = trend.first().map_or(
         crate::model::observability::Granularity::FifteenMinutes,
         |point| point.granularity,
     );
     if trend.iter().any(|point| point.granularity != granularity) {
-        return Err(AdminError::internal(
-            "Usage insight trend contains mixed granularities",
-        ));
+        return Err(AdminError::internal("用量洞察趋势包含不一致的时间粒度"));
     }
 
     let requests = &overview.requests;
     let failed_requests = service_failure_count(requests);
     let health_requests = requests.success_count.saturating_add(failed_requests);
     let health = UsageInsightsHealth {
-        total_requests: health_requests,
+        total_requests: requests.request_count,
         success_requests: requests.success_count,
         failed_requests,
         cancelled_requests: requests.cancelled_count,
         incomplete_requests: requests.incomplete_count,
         caller_error_requests: requests.caller_error_count,
         success_rate: rate_or_zero(requests.success_count, health_requests),
+        completion_rate: rate_or_zero(
+            requests
+                .success_count
+                .saturating_add(requests.failure_count),
+            requests.request_count,
+        ),
         points: trend
             .iter()
             .map(|point| {
                 let failed_requests = service_failure_count(&point.metrics);
                 let health_requests = point.metrics.success_count.saturating_add(failed_requests);
                 UsageInsightsHealthPoint {
+                    total_requests: point.metrics.request_count,
                     bucket_start: point.bucket_start,
                     success_requests: point.metrics.success_count,
                     failed_requests,
@@ -327,27 +447,74 @@ fn build_usage_insights(
             requests.first_token_latency_count,
             requests.request_count,
         ),
+        admission_decision_percentiles: requests.admission_decision_percentiles,
+        account_selection_wait_percentiles: requests.account_selection_wait_percentiles,
+        admission_decision_coverage: rate_or_zero(
+            requests.admission_decision_count,
+            requests.request_count,
+        ),
+        account_selection_wait_coverage: rate_or_zero(
+            requests.account_selection_wait_count,
+            requests.request_count,
+        ),
+        output_throughput_p10: requests.output_throughput_p10,
+        output_throughput_p50: requests.output_throughput_p50,
+        output_throughput_p90: requests.output_throughput_p90,
+        capacity_utilization_avg_basis_points: requests.capacity_utilization_avg_basis_points,
+        capacity_utilization_p95_basis_points: requests.capacity_utilization_p95_basis_points,
+        capacity_coverage: rate_or_zero(requests.capacity_sample_count, requests.request_count),
         points: trend
             .iter()
             .map(|point| UsageInsightsPerformancePoint {
                 bucket_start: point.bucket_start,
                 latency_percentiles: point.metrics.latency_percentiles,
                 first_token_latency_percentiles: point.metrics.first_token_latency_percentiles,
+                admission_decision_percentiles: point.metrics.admission_decision_percentiles,
+                account_selection_wait_percentiles: point
+                    .metrics
+                    .account_selection_wait_percentiles,
+                output_throughput_p10: point.metrics.output_throughput_p10,
+                output_throughput_p50: point.metrics.output_throughput_p50,
+                output_throughput_p90: point.metrics.output_throughput_p90,
+                capacity_utilization_avg_basis_points: point
+                    .metrics
+                    .capacity_utilization_avg_basis_points,
+                capacity_utilization_p95_basis_points: point
+                    .metrics
+                    .capacity_utilization_p95_basis_points,
             })
             .collect(),
     };
     let estimated_cost = usd_cost(&overview.attempts.costs);
-    let UsageStandardCosts {
-        total: standard_cost,
-        by_bucket: standard_costs_by_bucket,
+    let UsageCostScenarios {
+        standard:
+            ScenarioCosts {
+                total: standard_cost,
+                by_bucket: standard_costs_by_bucket,
+            },
+        no_cache:
+            ScenarioCosts {
+                total: no_cache_cost,
+                by_bucket: no_cache_costs_by_bucket,
+            },
     } = standard_costs;
+    let cache_savings = amount_difference(no_cache_cost.as_ref(), estimated_cost.as_ref());
+    let tier_premium = amount_difference(estimated_cost.as_ref(), standard_cost.as_ref());
+    let cost_per_request = estimated_cost
+        .as_ref()
+        .and_then(|cost| cost.checked_div_u64(requests.request_count));
+    let cost_per_successful_request = estimated_cost
+        .as_ref()
+        .and_then(|cost| cost.checked_div_u64(requests.success_count));
     let cost = UsageInsightsCost {
-        cost_per_request: estimated_cost
-            .as_ref()
-            .and_then(|cost| cost.checked_div_u64(requests.request_count)),
+        cost_per_request,
         estimated_cost,
         standard_cost,
+        no_cache_cost,
+        cache_savings,
+        tier_premium,
         tokens_per_request: rate_or_zero(requests.total_tokens, requests.request_count),
+        cost_per_successful_request,
         cached_token_rate: rate_or_zero(requests.cached_tokens, requests.input_tokens),
         cache_hit_request_rate: ratio(
             requests.cache_hit_request_count,
@@ -367,6 +534,11 @@ fn build_usage_insights(
                 total_tokens: point.metrics.total_tokens,
                 estimated_cost: usd_cost(&point.costs),
                 standard_cost: standard_costs_by_bucket.get(&point.bucket_start).cloned(),
+                no_cache_cost: no_cache_costs_by_bucket.get(&point.bucket_start).cloned(),
+                cache_savings: amount_difference(
+                    no_cache_costs_by_bucket.get(&point.bucket_start),
+                    usd_cost(&point.costs).as_ref(),
+                ),
                 cached_token_rate: rate_or_zero(
                     point.metrics.cached_tokens,
                     point.metrics.input_tokens,
@@ -391,12 +563,12 @@ fn build_usage_insights(
 }
 
 #[derive(Debug, Default)]
-struct UsageStandardCosts {
+struct ScenarioCosts {
     total: Option<DecimalAmount>,
     by_bucket: BTreeMap<DateTime<Utc>, DecimalAmount>,
 }
 
-impl UsageStandardCosts {
+impl ScenarioCosts {
     fn add(
         &mut self,
         bucket_start: DateTime<Utc>,
@@ -405,14 +577,15 @@ impl UsageStandardCosts {
         self.total = Some(match self.total.take() {
             Some(current) => current
                 .checked_add(&amount)
-                .ok_or_else(|| AdminError::internal("Usage standard cost exceeds decimal range"))?,
+                .ok_or_else(|| AdminError::internal("用量标准成本超出数值范围"))?,
             None => amount.clone(),
         });
         match self.by_bucket.entry(bucket_start) {
             Entry::Occupied(mut entry) => {
-                let sum = entry.get().checked_add(&amount).ok_or_else(|| {
-                    AdminError::internal("Usage standard cost exceeds decimal range")
-                })?;
+                let sum = entry
+                    .get()
+                    .checked_add(&amount)
+                    .ok_or_else(|| AdminError::internal("用量标准成本超出数值范围"))?;
                 entry.insert(sum);
             }
             Entry::Vacant(entry) => {
@@ -423,23 +596,33 @@ impl UsageStandardCosts {
     }
 }
 
-fn recover_standard_costs(
+#[derive(Debug, Default)]
+struct UsageCostScenarios {
+    standard: ScenarioCosts,
+    no_cache: ScenarioCosts,
+}
+
+async fn recover_standard_costs(
     providers: &ProviderAdminRegistry,
-    facts: Vec<UsageCalculatedBillingFact>,
-) -> Result<UsageStandardCosts, AdminError> {
-    let mut standard_costs = UsageStandardCosts::default();
-    for fact in facts {
-        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind) else {
+    mut facts: UsageCalculatedBillingStream<'_>,
+) -> Result<UsageCostScenarios, AdminError> {
+    let mut scenarios = UsageCostScenarios::default();
+    while let Some(fact) = facts
+        .try_next()
+        .await
+        .map_err(|error| map_store_error(error, "usage billing facts"))?
+    {
+        let Ok(provider_kind) = ProviderKind::new(fact.provider_kind.clone()) else {
             continue;
         };
         let input = ProviderBillingInput {
-            upstream_model_id: fact.upstream_model_id,
-            service_tier: fact.service_tier,
+            upstream_model_id: fact.upstream_model_id.clone(),
+            service_tier: fact.service_tier.clone(),
             input_tokens: fact.input_tokens,
             output_tokens: fact.output_tokens,
             cached_tokens: fact.cached_tokens,
             cache_write_tokens: fact.cache_write_tokens,
-            total: fact.total,
+            total: fact.total.clone(),
         };
         let breakdown = match providers.calculated_billing(&provider_kind, &input) {
             Ok(breakdown) => breakdown,
@@ -456,9 +639,80 @@ fn recover_standard_costs(
         {
             continue;
         }
-        standard_costs.add(fact.bucket_start, breakdown.standard_amount.amount)?;
+        scenarios
+            .standard
+            .add(fact.bucket_start, breakdown.standard_amount.amount.clone())?;
+        if let Some(no_cache_cost) = no_cache_cost(&fact, &breakdown) {
+            scenarios.no_cache.add(fact.bucket_start, no_cache_cost)?;
+        }
     }
-    Ok(standard_costs)
+    Ok(scenarios)
+}
+
+fn no_cache_cost(
+    fact: &UsageCalculatedBillingFact,
+    breakdown: &crate::model::observability::CalculatedBillingBreakdown,
+) -> Option<DecimalAmount> {
+    let input_tokens = fact.input_tokens?;
+    let cached_tokens = fact.cached_tokens.unwrap_or_default().min(input_tokens);
+    let cache_write_tokens = fact
+        .cache_write_tokens
+        .unwrap_or_default()
+        .min(input_tokens.saturating_sub(cached_tokens));
+    let input_rate = decimal(&breakdown.input_price_per_million.amount)?;
+    let replaced_input_amount = input_rate
+        .scaled()
+        .checked_mul(u128::from(cached_tokens.saturating_add(cache_write_tokens)))?
+        .checked_div(1_000_000)?;
+    let total = decimal(&breakdown.total_amount.amount)?
+        .scaled()
+        .checked_sub(decimal(&breakdown.cache_read_amount.amount)?.scaled())?
+        .checked_sub(decimal(&breakdown.cache_write_amount.amount)?.scaled())?
+        .checked_add(replaced_input_amount)?;
+    DecimalAmount::from_str(
+        &gateway_core::metering::Decimal::from_scaled(total)
+            .ok()?
+            .canonical(),
+    )
+    .ok()
+}
+
+fn amount_difference(
+    larger: Option<&DecimalAmount>,
+    smaller: Option<&DecimalAmount>,
+) -> Option<DecimalAmount> {
+    let difference = decimal(larger?)?
+        .scaled()
+        .checked_sub(decimal(smaller?)?.scaled())?;
+    DecimalAmount::from_str(
+        &gateway_core::metering::Decimal::from_scaled(difference)
+            .ok()?
+            .canonical(),
+    )
+    .ok()
+}
+
+fn decimal(value: &DecimalAmount) -> Option<gateway_core::metering::Decimal> {
+    value.as_str().parse().ok()
+}
+
+fn diagnostic_impact_score(
+    request_count: u64,
+    total_requests: u64,
+    error_rate: f64,
+    non_completion_rate: f64,
+    retry_rate: f64,
+    first_token_p95_ms: Option<u64>,
+) -> f64 {
+    let request_share = rate_or_zero(request_count, total_requests);
+    let slow_score = first_token_p95_ms
+        .map_or(0.0, |value| value as f64 / 30_000.0)
+        .min(1.0);
+    error_rate * 0.35
+        + non_completion_rate * 0.25
+        + retry_rate.min(1.0) * 0.20
+        + request_share * 0.10
+        + slow_score * 0.10
 }
 
 fn usd_cost(costs: &[CurrencyCost]) -> Option<DecimalAmount> {
@@ -470,8 +724,31 @@ fn usd_cost(costs: &[CurrencyCost]) -> Option<DecimalAmount> {
 
 impl DefaultObservabilityService {
     async fn enrich_dashboard_quotas(&self, accounts: &mut [DashboardAccountUsage]) {
+        if accounts.is_empty() {
+            return;
+        }
+        let now = Utc::now();
+        let ids = accounts
+            .iter()
+            .map(|account| account.account_id.clone())
+            .collect::<Vec<_>>();
+        let mut rolling_usage = self
+            .accounts
+            .load_account_usage(
+                TimeRange {
+                    start: now - Duration::hours(24),
+                    end: now,
+                },
+                &ids,
+            )
+            .await
+            .unwrap_or_default()
+            .into_iter()
+            .map(|usage| (usage.account_id.clone(), usage))
+            .collect::<HashMap<_, _>>();
         let providers = self.providers.clone();
         let quota_reads = accounts.iter().map(|account| {
+            let rolling_usage = rolling_usage.remove(&account.account_id);
             let account_id = ProviderAccountId::new(account.account_id.clone()).ok();
             let provider = ProviderKind::new(account.provider_kind.clone())
                 .ok()
@@ -484,22 +761,57 @@ impl DefaultObservabilityService {
                     .quota(ProviderQuotaRequest {
                         account_id,
                         refresh: false,
-                        rolling_usage: None,
+                        rolling_usage,
                     })
                     .await
                     .ok()
-                    .and_then(|quota| quota.representative_used_percent())
             }
         });
-        let quota_used = futures::future::join_all(quota_reads).await;
-        for (account, used_percent) in accounts.iter_mut().zip(quota_used) {
-            account.quota_used_percent = used_percent;
+        let quotas = futures::future::join_all(quota_reads).await;
+        for (account, quota) in accounts.iter_mut().zip(quotas) {
+            if let Some(mut quota) = quota {
+                quota.apply_limit_reached_display();
+                account.quota_used_percent = quota.representative_used_percent();
+                account.quota_window = quota.representative_window().cloned();
+            }
         }
     }
 
     /// 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_billing(&self, records: &mut [crate::model::observability::UsageRecord]) {
+    fn enrich_list_billing(&self, records: &mut [crate::model::observability::UsageListRecord]) {
+        for record in records {
+            let Some(UsageBilling::Total { source, total }) = record.billing.as_ref() else {
+                continue;
+            };
+            if !matches!(source.as_str(), "calculated" | "provider_reported") {
+                continue;
+            }
+            let (Some(provider), Some(upstream_model_id)) = (
+                record.provider_kind.as_deref(),
+                record.upstream_model_id.as_ref(),
+            ) else {
+                continue;
+            };
+            let Ok(provider_kind) = ProviderKind::new(provider.to_owned()) else {
+                continue;
+            };
+            let input = ProviderBillingInput {
+                upstream_model_id: upstream_model_id.clone(),
+                service_tier: record.service_tier.clone(),
+                input_tokens: record.input_tokens,
+                output_tokens: record.output_tokens,
+                cached_tokens: record.cached_tokens,
+                cache_write_tokens: record.cache_write_tokens,
+                total: total.clone(),
+            };
+            if let Ok(Some(breakdown)) = self.providers.calculated_billing(&provider_kind, &input) {
+                record.billing = Some(UsageBilling::Calculated(Box::new(breakdown)));
+            }
+        }
+    }
+
+    fn enrich_detail_billing(&self, records: &mut [crate::model::observability::UsageRecord]) {
         for record in records {
             let Some(UsageBilling::Total { source, total }) = record.billing.as_ref() else {
                 continue;
@@ -612,9 +924,9 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
             .saturating_add(point.cost_coverage.not_billable_count);
         for cost in &point.costs {
             if let Some(amount) = costs.get_mut(&cost.currency) {
-                *amount = amount.checked_add(&cost.amount).ok_or_else(|| {
-                    AdminError::internal("Cost aggregation exceeded numeric bounds")
-                })?;
+                *amount = amount
+                    .checked_add(&cost.amount)
+                    .ok_or_else(|| AdminError::internal("成本聚合结果超出数值范围"))?;
             } else {
                 costs.insert(cost.currency.clone(), cost.amount.clone());
             }
@@ -630,6 +942,20 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
         metrics.cache_hit_request_count,
         metrics.cache_eligible_request_count,
     );
+    let peak_first_token_p95_ms = points
+        .iter()
+        .filter_map(|point| point.metrics.first_token_latency_percentiles.p95_ms)
+        .map(|value| value.as_f64())
+        .reduce(f64::max);
+    let peak_latency_p95_ms = points
+        .iter()
+        .filter_map(|point| point.metrics.latency_percentiles.p95_ms)
+        .map(|value| value.as_f64())
+        .reduce(f64::max);
+    let minimum_output_throughput_p50 = points
+        .iter()
+        .filter_map(|point| point.metrics.output_throughput_p50)
+        .min();
     Ok(Trend {
         kind,
         points: points.into_iter().map(trend_point).collect(),
@@ -643,6 +969,9 @@ fn trend(kind: TrendKind, points: Vec<RequestMetricPoint>) -> Result<Trend, Admi
             average_latency_ms,
             max_latency_ms: metrics.max_latency_ms,
             min_latency_ms: metrics.min_latency_ms,
+            peak_first_token_p95_ms,
+            peak_latency_p95_ms,
+            minimum_output_throughput_p50,
             success_rate,
             cache_hit_request_rate,
             costs: costs

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

@@ -3,7 +3,7 @@
 use std::sync::Arc;
 
 use async_trait::async_trait;
-use gateway_core::{engine::credential::ProviderAccountId, routing::snapshot::SnapshotControl};
+use gateway_core::{account::ProviderAccountId, runtime::SnapshotControl};
 
 use crate::{
     model::{

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

@@ -3,7 +3,8 @@
 use std::sync::Arc;
 
 use async_trait::async_trait;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::policy::CodexClientVersion;
+use gateway_core::runtime::SnapshotControl;
 use rand_core::{OsRng, RngCore as _};
 
 use crate::{
@@ -119,10 +120,16 @@ fn validate_settings(command: &ReplaceRuntimeSettings) -> Result<(), AdminError>
         && command.usage_retention_days >= 31
         && command.ops_event_retention_days > 0
         && command.audit_retention_days > 0
+        && valid_client_version(command.min_codex_desktop_version.as_deref())
+        && valid_client_version(command.min_codex_cli_version.as_deref())
         && i64::try_from(command.request_interval_ms).is_ok();
     if valid {
         Ok(())
     } else {
-        Err(AdminError::invalid("Runtime settings violate constraints"))
+        Err(AdminError::invalid("运行时设置不满足约束"))
     }
 }
+
+fn valid_client_version(value: Option<&str>) -> bool {
+    value.is_none_or(|value| CodexClientVersion::parse(value).is_ok())
+}

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

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

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

@@ -3,7 +3,7 @@
 use std::sync::Arc;
 
 use async_trait::async_trait;
-use gateway_core::routing::snapshot::SnapshotControl;
+use gateway_core::runtime::SnapshotControl;
 
 use crate::{
     model::{

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

@@ -10,7 +10,7 @@ use gateway_admin::{
     },
     ports::backup::{BackupRepository, DatabaseDumpPort, DumpRequest},
 };
-use gateway_core::engine::CancellationToken;
+use gateway_core::lifecycle::CancellationToken;
 
 use super::support::{
     DUMP_CONTENT, FakeBackupRepository, FakeDumpPort, FakeObjectStore, backup_id,

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

@@ -1,7 +1,7 @@
 use std::str::FromStr as _;
 
 use chrono::{TimeDelta, Utc};
-use gateway_core::engine::credential::OpaqueProviderData;
+use gateway_core::account::OpaqueProviderData;
 
 use gateway_admin::{
     model::{

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

@@ -1,4 +1,4 @@
-//! 备份领域模型（model/backup.rs）的纯逻辑测试。
+//! 备份领域模型（model/backup）的纯逻辑测试。
 
 use chrono::{TimeZone as _, Utc};
 use secrecy::SecretString;

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

@@ -1,3 +1,4 @@
 //! 模型模块测试：镜像 src/model/ 中带逻辑的模块。
 
 mod backup;
+mod provider_credentials;

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

@@ -0,0 +1,134 @@
+use gateway_admin::model::provider_credentials::{
+    AuthorizationMutationTarget, AuthorizationOwnerBinding, PendingAuthorizationMutation,
+    ProviderQuota, ProviderQuotaWindow, ProviderQuotaWindowRole, QuotaLocalUsageAttribution,
+};
+use gateway_admin::model::{MutationActor, MutationContext};
+use gateway_core::account::ProviderAccountId;
+use gateway_core::routing::ProviderKind;
+use serde_json::{Value, json};
+
+#[test]
+fn dashboard_quota_should_preserve_unknown_and_actual_window_facts() {
+    let mut quota = ProviderQuota {
+        observed_at: None,
+        refresh_token_expires_at: None,
+        windows: Vec::new(),
+        limit_reached: false,
+        provider_data: None,
+    };
+    assert!(quota.representative_window().is_none());
+    assert!(quota.representative_used_percent().is_none());
+
+    let rolling = ProviderQuotaWindow {
+        key: "provider_rolling".to_owned(),
+        group: "requests".to_owned(),
+        label: "Provider rolling window".to_owned(),
+        limit_id: None,
+        limit_name: None,
+        role: Some(ProviderQuotaWindowRole::Primary),
+        local_usage_attribution: QuotaLocalUsageAttribution::AccountWide,
+        window_seconds: Some(86_400),
+        used_percent: None,
+        reset_at: None,
+        limit_reached: false,
+        local_usage: None,
+        provider_data: None,
+    };
+    quota.windows.push(rolling.clone());
+    assert_eq!(quota.representative_window(), Some(&rolling));
+    assert!(quota.representative_used_percent().is_none());
+
+    quota.windows[0].used_percent = Some(99.6);
+    quota.apply_limit_reached_display();
+    let actual = quota.representative_window().expect("actual window");
+    assert_eq!(actual.used_percent, Some(99.6));
+    assert!(
+        !actual.limit_reached,
+        "display rounding cannot exhaust quota"
+    );
+    assert_eq!(actual.window_seconds, Some(86_400));
+    assert_eq!(actual.reset_at, None);
+
+    quota.windows.insert(
+        0,
+        ProviderQuotaWindow {
+            key: "model_specific".to_owned(),
+            used_percent: Some(100.0),
+            local_usage_attribution: QuotaLocalUsageAttribution::Unavailable,
+            ..rolling
+        },
+    );
+    assert_eq!(
+        quota
+            .representative_window()
+            .map(|window| window.key.as_str()),
+        Some("provider_rolling")
+    );
+}
+
+#[test]
+fn pending_mutation_v1_should_round_trip_all_targets_and_owners() {
+    for provider in ["openai", "xai"] {
+        for target in [
+            AuthorizationMutationTarget::Create {
+                name: "account".to_owned(),
+            },
+            AuthorizationMutationTarget::Reauthorize {
+                account_id: ProviderAccountId::new("acct_1").expect("account id"),
+            },
+        ] {
+            for actor in [
+                MutationActor::AdminSession {
+                    admin_user_id: "admin-1".to_owned(),
+                },
+                MutationActor::AdminApiKey,
+                MutationActor::System,
+            ] {
+                let expected = PendingAuthorizationMutation::new(
+                    ProviderKind::new(provider).expect("provider"),
+                    target.clone(),
+                    AuthorizationOwnerBinding::from_context(&MutationContext {
+                        actor,
+                        request_id: "request-1".to_owned(),
+                    }),
+                );
+                assert_eq!(
+                    PendingAuthorizationMutation::from_storage_v1(Value::Object(
+                        expected.to_storage_v1()
+                    )),
+                    Ok(expected),
+                );
+            }
+        }
+    }
+}
+
+#[test]
+fn pending_mutation_v1_should_keep_existing_storage_fields_and_reject_invalid_documents() {
+    let legacy = json!({
+        "provider_kind": "openai",
+        "target": { "kind": "reauthorize", "account_id": "acct_1" },
+        "owner": { "kind": "admin_session", "admin_user_id": "admin-1" },
+        "started_request_id": "request-1"
+    });
+    let restored =
+        PendingAuthorizationMutation::from_storage_v1(legacy.clone()).expect("v1 document");
+    assert_eq!(Value::Object(restored.to_storage_v1()), legacy);
+    for (pointer, invalid) in [
+        ("/provider_kind", json!("")),
+        ("/target/account_id", json!("")),
+        ("/target/kind", json!("other")),
+        ("/owner/kind", json!("other")),
+        ("/started_request_id", json!(null)),
+    ] {
+        let mut document = legacy.clone();
+        *document.pointer_mut(pointer).expect("field") = invalid;
+        assert!(
+            PendingAuthorizationMutation::from_storage_v1(document).is_err(),
+            "{pointer}"
+        );
+    }
+    let mut document = legacy;
+    document["schema_version"] = json!(2);
+    assert!(PendingAuthorizationMutation::from_storage_v1(document).is_err());
+}

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

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

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

@@ -4,16 +4,18 @@ use async_trait::async_trait;
 use chrono::{TimeDelta, Utc};
 use futures::{StreamExt as _, future::BoxFuture};
 use gateway_core::{
-    engine::{
-        credential::{
-            AccountStatusFacts, CredentialState, OpaqueProviderData, ProviderAccountId,
-            QuotaEvidence, QuotaState, resolve_account_status,
-        },
-        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
+    account::{
+        AccountStatusFacts, CredentialState, OpaqueProviderData, ProviderAccountId, QuotaEvidence,
+        QuotaState, resolve_account_status,
+    },
+    engine::probe::{
+        AccountProbe, AccountProbeError, AccountProbeErrorSource, AccountProbeRequest,
+        AccountProbeResult,
     },
     error::{ClientVisibleUpstreamError, GatewayError, GatewayErrorKind},
     operation::{GenerateRequest, Operation, ProtocolPayload},
     routing::ProviderKind,
+    upstream::UpstreamSendState,
 };
 
 use gateway_admin::{
@@ -22,8 +24,8 @@ use gateway_admin::{
         AdminError, MutationContext, Revision,
         accounts::{
             AccountConnectionTestEvent, AccountListQuery, AccountPage, AccountPageItem,
-            AccountRecord, AccountSummary, AccountUpdateResult, AccountUsage,
-            AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
+            AccountRecord, AccountRuntimeSnapshot, AccountSummary, AccountUpdateResult,
+            AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
             BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
         },
         observability::TimeRange,
@@ -70,6 +72,7 @@ pub(super) struct FakeProviderAdmin {
     import_account_ids: Mutex<Vec<String>>,
     quota_requests: Mutex<Vec<ProviderQuotaRequest>>,
     quota: Mutex<ProviderQuota>,
+    quota_refresh_account: Mutex<Option<(Arc<FakeAccountStore>, AccountRecord)>>,
     current_credential_revision: Mutex<Revision>,
     reset_credit_commands: Mutex<Vec<ConsumeProviderResetCredit>>,
 }
@@ -87,6 +90,7 @@ impl FakeProviderAdmin {
             import_account_ids: Mutex::new(vec!["acct_prepared".to_owned()]),
             quota_requests: Mutex::new(Vec::new()),
             quota: Mutex::new(empty_quota()),
+            quota_refresh_account: Mutex::new(None),
             current_credential_revision: Mutex::new(revision(1)),
             reset_credit_commands: Mutex::new(Vec::new()),
         })
@@ -344,6 +348,14 @@ impl ProviderAdmin for FakeProviderAdmin {
     ) -> Result<ProviderQuota, ProviderAdminError> {
         if request.refresh {
             self.record("provider.quota");
+            if let Some((store, account)) = self
+                .quota_refresh_account
+                .lock()
+                .expect("quota refresh account")
+                .take()
+            {
+                store.set_accounts(vec![account]);
+            }
         }
         self.quota_requests
             .lock()
@@ -503,7 +515,11 @@ impl FakeAccountStore {
 
 #[async_trait]
 impl AccountStore for FakeAccountStore {
-    async fn list_accounts(&self, _: AccountListQuery) -> AdminStoreResult<AccountPage> {
+    async fn list_accounts(
+        &self,
+        _: AccountListQuery,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage> {
         self.record("store.list_accounts");
         let accounts = self.accounts.lock().expect("accounts").clone();
         let total = accounts.len() as u64;
@@ -522,7 +538,11 @@ impl AccountStore for FakeAccountStore {
         })
     }
 
-    async fn load_account(&self, account_id: &str) -> AdminStoreResult<Option<AccountPageItem>> {
+    async fn load_account(
+        &self,
+        account_id: &str,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<Option<AccountPageItem>> {
         self.record("store.load_account");
         // probe 后的账号状态覆盖只对同一 id 生效；其余按账号列表查询。
         let account = self
@@ -786,6 +806,8 @@ impl SettingsStore for StaticSettingsStore {
             max_concurrent_per_account: 1,
             request_interval_ms: 0,
             rotation_strategy: RotationStrategy::Smart,
+            min_codex_desktop_version: None,
+            min_codex_cli_version: None,
             usage_retention_days: 30,
             ops_event_retention_days: 30,
             audit_retention_days: 30,
@@ -950,6 +972,9 @@ async fn connection_test_should_probe_unavailable_account() {
     assert!(matches!(
         events.last(),
         Some(AccountConnectionTestEvent::Failed {
+            source: AccountProbeErrorSource::Upstream,
+            gateway_error_code: GatewayErrorKind::RateLimited,
+            send_state: Some(UpstreamSendState::NotSent),
             message,
             provider_error_code: Some(code),
             provider_error_type: Some(error_type),
@@ -984,6 +1009,9 @@ async fn connection_test_rate_limited_probe_returns_provider_failure() {
     assert!(matches!(
         events.last(),
         Some(AccountConnectionTestEvent::Failed {
+            source: AccountProbeErrorSource::Provider,
+            gateway_error_code: GatewayErrorKind::RateLimited,
+            send_state: Some(UpstreamSendState::NotSent),
             message,
             ..
         })
@@ -1080,6 +1108,47 @@ async fn accounts_refresh_should_keep_guard_through_store_commit() {
     assert_eq!(store.audit_requests(), ["refresh-request"]);
 }
 
+#[tokio::test]
+async fn accounts_quota_refresh_should_return_the_updated_account_status() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    let mut account = account_record("openai");
+    account.quota = QuotaState::exhausted(
+        QuotaEvidence::UsageLimitReached,
+        std::time::SystemTime::now(),
+        None,
+    );
+    let store = FakeAccountStore::with_account(account.clone(), events.clone());
+    account.quota = QuotaState::allowed(std::time::SystemTime::now());
+    *provider
+        .quota_refresh_account
+        .lock()
+        .expect("quota refresh account") = Some((store.clone(), account));
+
+    let result = accounts_service(provider, store)
+        .await
+        .accounts()
+        .quota(
+            &ProviderAccountId::new("acct_test").expect("account ID"),
+            true,
+        )
+        .await
+        .expect("refresh quota");
+
+    assert_eq!(
+        result.account.quota.access(),
+        gateway_core::account::QuotaAccessState::Allowed
+    );
+    assert_eq!(
+        result.projection.status,
+        gateway_admin::model::accounts::AccountStatus::Normal
+    );
+    assert_eq!(
+        recorded(&events),
+        ["store.load_account", "provider.quota", "store.load_account"]
+    );
+}
+
 #[tokio::test]
 async fn accounts_recover_should_commit_facts_then_return_normal_account() {
     let events = events();
@@ -1092,8 +1161,7 @@ async fn accounts_recover_should_commit_facts_then_return_normal_account() {
         std::time::SystemTime::now(),
         None,
     );
-    account.last_error_reason =
-        Some(gateway_core::engine::credential::AccountErrorReason::CredentialInvalid);
+    account.last_error_reason = Some(gateway_core::account::AccountErrorReason::CredentialInvalid);
     account.last_error_message = Some("invalid credential".to_owned());
     let store = FakeAccountStore::with_account(account, events.clone());
     let services = accounts_service(provider, store.clone()).await;
@@ -1115,7 +1183,7 @@ async fn accounts_recover_should_commit_facts_then_return_normal_account() {
     );
     assert_eq!(
         result.account.account.quota.access(),
-        gateway_core::engine::credential::QuotaAccessState::Allowed
+        gateway_core::account::QuotaAccessState::Allowed
     );
     assert_eq!(
         result.account.projection.status,
@@ -1148,7 +1216,7 @@ async fn accounts_update_should_commit_then_release_disabled_account_and_publish
                 account_id: "acct_test".to_owned(),
                 enabled: false,
                 concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                 group_ids: Vec::new(),
             },
         )
@@ -1184,7 +1252,7 @@ async fn accounts_update_should_not_notify_provider_when_store_commit_fails() {
                 account_id: "acct_test".to_owned(),
                 enabled: false,
                 concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                 group_ids: Vec::new(),
             },
         )
@@ -1225,7 +1293,7 @@ async fn accounts_batch_update_should_commit_once_and_notify_each_provider() {
                 account_ids: vec!["acct_openai".to_owned(), "acct_xai".to_owned()],
                 enabled: false,
                 concurrency_limit: None,
-                weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+                weight: gateway_core::account::AccountWeight::DEFAULT,
                 group_ids: Vec::new(),
             },
         )
@@ -1722,7 +1790,37 @@ async fn reset_credit_oauth_refresh_should_reuse_the_exact_consume_command() {
 }
 
 #[tokio::test]
-async fn accounts_refresh_should_preserve_the_provider_failure_message() {
+async fn reset_credit_unknown_result_should_keep_a_stable_admin_kind() {
+    let events = events();
+    let provider = FakeProviderAdmin::new("openai", events.clone());
+    provider.fail_next(ProviderAdminErrorKind::Ambiguous);
+    let store = FakeAccountStore::new("openai", events);
+    let services = accounts_service(provider, store).await;
+    let command = ConsumeProviderResetCredit {
+        account_id: ProviderAccountId::new("acct_test").expect("account ID"),
+        credit_id: Some("credit_1".to_owned()),
+        redeem_request_id: uuid::Uuid::parse_str("244e790c-42a3-4ec9-a45d-a32b218bc8ac")
+            .expect("UUID v4"),
+    };
+
+    let error = services
+        .accounts()
+        .consume_reset_credit(&context("reset-credit-ambiguous"), command)
+        .await
+        .expect_err("ambiguous consume result must remain classified");
+
+    assert_eq!(
+        error.kind(),
+        gateway_admin::model::AdminErrorKind::UpstreamResultUnknown
+    );
+    assert_eq!(
+        error.to_string(),
+        "上游执行结果未知，请刷新状态后再决定是否重试"
+    );
+}
+
+#[tokio::test]
+async fn accounts_refresh_should_not_expose_the_provider_failure_message() {
     let events = events();
     let provider = FakeProviderAdmin::new("openai", events.clone());
     let upstream_message = "Your refresh token has already been used.";
@@ -1740,7 +1838,8 @@ async fn accounts_refresh_should_preserve_the_provider_failure_message() {
         .expect_err("Provider preparation must fail");
 
     assert_eq!(error.kind(), gateway_admin::model::AdminErrorKind::Conflict);
-    assert_eq!(error.to_string(), upstream_message);
+    assert_eq!(error.to_string(), "Provider 资源状态冲突，请刷新后重试");
+    assert!(!error.to_string().contains(upstream_message));
     assert_eq!(
         recorded(&events),
         ["store.load_account", "provider.prepare_refresh"]
@@ -1847,7 +1946,7 @@ pub(super) fn account_record(kind: &str) -> AccountRecord {
         next_refresh_at: Some(now + TimeDelta::minutes(30)),
         enabled: true,
         concurrency_limit: None,
-        weight: gateway_core::engine::credential::AccountWeight::DEFAULT,
+        weight: gateway_core::account::AccountWeight::DEFAULT,
         credential_state: CredentialState::Ready,
         credential_observed_at: now,
         quota: QuotaState::allowed(now.into()),
@@ -1950,12 +2049,16 @@ impl AccountProbe for FailingAccountProbe {
                 Some("usage_exhausted".to_owned()),
                 Some("invalid_request_error".to_owned()),
             );
-            Err(GatewayError::new(
-                GatewayErrorKind::RateLimited,
-                "upstream capacity is temporarily unavailable",
-            )
-            .with_client_visible_upstream_error(detail)
-            .into())
+            Err(AccountProbeError::new(
+                GatewayError::new(
+                    GatewayErrorKind::RateLimited,
+                    "upstream capacity is temporarily unavailable",
+                )
+                .with_client_visible_upstream_error(detail),
+                AccountProbeErrorSource::Upstream,
+                Some(UpstreamSendState::NotSent),
+                None,
+            ))
         })
     }
 }
@@ -1971,11 +2074,15 @@ impl AccountProbe for FreeModelQuotaProbe {
     ) -> BoxFuture<'_, Result<AccountProbeResult, AccountProbeError>> {
         Box::pin(async move {
             self.store.set_account_after_probe(account_record("xai"));
-            Err(GatewayError::new(
-                GatewayErrorKind::RateLimited,
-                "xAI free model quota is exhausted",
-            )
-            .into())
+            Err(AccountProbeError::new(
+                GatewayError::new(
+                    GatewayErrorKind::RateLimited,
+                    "xAI free model quota is exhausted",
+                ),
+                AccountProbeErrorSource::Provider,
+                Some(UpstreamSendState::NotSent),
+                None,
+            ))
         })
     }
 }

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

@@ -1,3 +1,4 @@
+mod account_groups;
 mod accounts;
 mod auth;
 mod backup;
@@ -21,15 +22,16 @@ use gateway_admin::{
     model::{
         MutationContext, Revision,
         account_groups::{
-            AccountGroupListQuery, AccountGroupMutation, AccountGroupPage, DeleteAccountGroup,
-            NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+            DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled, UpdateAccountGroup,
         },
         accounts::{
-            AccountListQuery, AccountPage, AccountUpdateResult, AccountUsage,
-            AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
+            AccountListQuery, AccountPage, AccountRuntimeSnapshot, AccountUpdateResult,
+            AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
             BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
         },
         auth::{AdminAuditEvent, AdminSession},
+        client_distribution::CodexDesktopWindowsDownloads,
         client_keys::{
             ClientKeyListQuery, ClientKeyPage, ClientKeyRecord, ClientKeySecret, DeleteClientKey,
             NewClientKey, SetClientKeyEnabled, UpdateClientKey,
@@ -54,10 +56,12 @@ use gateway_admin::{
     },
     ports::{
         backup::BackupStorePorts,
+        client_distribution::ClientDistributionResolver,
         provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind},
         store::{
-            AccountGroupStore, AccountStore, AdminStoreError, AdminStoreErrorKind, AdminStorePorts,
-            AdminStoreResult, AuthStore, ClientKeyStore, ObservabilityStore, SettingsStore,
+            AccountGroupStore, AccountRuntimeStore, AccountStore, AdminAccountStorePorts,
+            AdminStoreError, AdminStoreErrorKind, AdminStorePorts, AdminStoreResult, AuthStore,
+            ClientKeyStore, ObservabilityStore, SettingsStore,
         },
         system::{
             SystemOperationError, SystemOperationErrorKind, SystemOperations,
@@ -66,19 +70,20 @@ use gateway_admin::{
     },
 };
 use gateway_core::{
-    engine::{
-        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
-    },
+    account::ProviderAccountId,
+    engine::probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
     error::{GatewayError, GatewayErrorKind},
     policy::ClientApiKeyId,
-    routing::{ConfigRevision, ProviderKind, snapshot::SnapshotControl},
+    routing::{ConfigRevision, ProviderKind},
+    runtime::SnapshotControl,
 };
 
 pub(super) struct AdminHarness {
     default_password: String,
     session_ttl_minutes: u64,
     accounts: Arc<dyn AccountStore>,
+    account_runtime: Arc<dyn AccountRuntimeStore>,
+    account_groups: Arc<dyn AccountGroupStore>,
     auth: Arc<dyn AuthStore>,
     client_keys: Arc<dyn ClientKeyStore>,
     observability: Arc<dyn ObservabilityStore>,
@@ -96,6 +101,8 @@ impl AdminHarness {
             default_password: "strong-test-password".to_owned(),
             session_ttl_minutes: 60,
             accounts: unavailable.clone(),
+            account_runtime: unavailable.clone(),
+            account_groups: Arc::new(UnavailableAccountGroupStore),
             auth: Arc::new(BootstrapAuthStore::default()),
             client_keys: unavailable.clone(),
             observability: unavailable.clone(),
@@ -125,6 +132,16 @@ impl AdminHarness {
         self
     }
 
+    pub(super) fn account_runtime(mut self, store: Arc<dyn AccountRuntimeStore>) -> Self {
+        self.account_runtime = store;
+        self
+    }
+
+    pub(super) fn account_groups(mut self, store: Arc<dyn AccountGroupStore>) -> Self {
+        self.account_groups = store;
+        self
+    }
+
     pub(super) fn auth(mut self, store: Arc<dyn AuthStore>) -> Self {
         self.auth = store;
         self
@@ -175,8 +192,11 @@ impl AdminHarness {
                 default_password: InitialAdminPassword::new(self.default_password),
             },
             AdminStorePorts::new(
-                self.accounts,
-                Arc::new(UnavailableAccountGroupStore),
+                AdminAccountStorePorts::new(
+                    self.accounts,
+                    self.account_runtime,
+                    self.account_groups,
+                ),
                 self.auth,
                 self.client_keys,
                 self.observability,
@@ -186,6 +206,7 @@ impl AdminHarness {
             self.providers,
             Arc::new(NoopSnapshot),
             self.probe,
+            Arc::new(NoopClientDistribution),
             self.system,
         )
         .await
@@ -194,6 +215,20 @@ impl AdminHarness {
     }
 }
 
+struct NoopClientDistribution;
+
+#[async_trait]
+impl ClientDistributionResolver for NoopClientDistribution {
+    async fn resolve_codex_desktop_windows(&self, _: bool) -> CodexDesktopWindowsDownloads {
+        CodexDesktopWindowsDownloads {
+            resolved_at: Utc::now(),
+            cached: false,
+            warning: None,
+            packages: Vec::new(),
+        }
+    }
+}
+
 #[derive(Default)]
 struct BootstrapAuthStore {
     password_hash: Mutex<Option<String>>,
@@ -252,6 +287,13 @@ impl AccountGroupStore for UnavailableAccountGroupStore {
         Err(unavailable("account groups"))
     }
 
+    async fn load_account_group_members(
+        &self,
+        _: &[gateway_core::routing::AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>> {
+        Err(unavailable("account group members"))
+    }
+
     async fn create_account_group(
         &self,
         _: NewAccountGroup,
@@ -287,13 +329,18 @@ impl AccountGroupStore for UnavailableAccountGroupStore {
 
 #[async_trait]
 impl AccountStore for UnavailableStore {
-    async fn list_accounts(&self, _: AccountListQuery) -> AdminStoreResult<AccountPage> {
+    async fn list_accounts(
+        &self,
+        _: AccountListQuery,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage> {
         Err(unavailable("accounts"))
     }
 
     async fn load_account(
         &self,
         _: &str,
+        _: AccountRuntimeSnapshot,
     ) -> AdminStoreResult<Option<gateway_admin::model::accounts::AccountPageItem>> {
         Err(unavailable("account"))
     }
@@ -410,6 +457,17 @@ impl AccountStore for UnavailableStore {
     }
 }
 
+#[async_trait]
+impl AccountRuntimeStore for UnavailableStore {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot::default())
+    }
+
+    async fn account_runtime(&self, _: &[String]) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot::default())
+    }
+}
+
 #[async_trait]
 impl ClientKeyStore for UnavailableStore {
     async fn list_client_keys(&self, _: ClientKeyListQuery) -> AdminStoreResult<ClientKeyPage> {
@@ -478,13 +536,14 @@ impl ObservabilityStore for UnavailableStore {
         Err(unavailable("usage trend"))
     }
 
-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
         &self,
         _: TimeRange,
         _: UsageFilter,
-    ) -> AdminStoreResult<Vec<gateway_admin::model::observability::UsageCalculatedBillingFact>>
-    {
-        Err(unavailable("usage billing facts"))
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        Box::pin(futures::stream::once(async {
+            Err(unavailable("usage billing facts"))
+        }))
     }
 
     async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {

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

@@ -1,7 +1,10 @@
 use std::{
-    num::NonZeroU32,
     str::FromStr as _,
-    sync::{Arc, Mutex},
+    sync::{
+        Arc, Mutex,
+        atomic::{AtomicBool, AtomicUsize, Ordering},
+    },
+    time::Duration as StdDuration,
 };
 
 use async_trait::async_trait;
@@ -14,10 +17,10 @@ use gateway_admin::{
         observability::{
             AccountPoolMetrics, AttemptMetrics, CostCoverage, CurrencyCost, DashboardObservation,
             DashboardRuntimeSlots, DiagnosticDimension, DiagnosticObservation, Granularity,
-            HealthStatus, OpsErrorPage, OpsErrorQuery, PageNumber, RequestMetricPoint,
-            RequestMetrics, RequestOutcome, TimeRange, TrendKind, UsageBilling,
-            UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageOverview, UsagePage,
-            UsageQuery, UsageRecord, china_day_start,
+            HealthStatus, LatencyPercentiles, OpsErrorPage, OpsErrorQuery, PercentileMilliseconds,
+            RequestMetricPoint, RequestMetrics, TimeRange, TrendKind, UsageBilling,
+            UsageCalculatedBillingFact, UsageDetail, UsageFilter, UsageListRecord, UsageOverview,
+            UsagePage, UsageQuery, china_day_start,
         },
         settings::{
             AdminApiKey, AdminApiKeyMutation, ReplaceRuntimeSettings, RotationStrategy,
@@ -105,6 +108,40 @@ async fn health_timeline_should_keep_exactly_china_day_quarter_hour_slots() {
     }));
 }
 
+#[tokio::test]
+async fn dashboard_summary_should_derive_first_token_average_from_trend() {
+    let now = Utc::now();
+    let current_slot = quarter_hour_start(now);
+    let store = Arc::new(FixtureObservabilityStore::new(observation_range(now)));
+    store.replace_trend(vec![
+        health_metric_point(
+            current_slot - Duration::minutes(15),
+            RequestMetrics {
+                first_token_latency_sum_ms: 120,
+                first_token_latency_count: 2,
+                ..RequestMetrics::default()
+            },
+        ),
+        health_metric_point(
+            current_slot,
+            RequestMetrics {
+                first_token_latency_sum_ms: 180,
+                first_token_latency_count: 1,
+                ..RequestMetrics::default()
+            },
+        ),
+    ]);
+    let services = observability_services(store).await;
+
+    let summary = services
+        .observability()
+        .dashboard_summary(observation_range(now), TrendKind::Usage)
+        .await
+        .expect("dashboard summary");
+
+    assert_eq!(summary.average_first_token_latency_ms, Some(100));
+}
+
 #[tokio::test]
 async fn health_timeline_should_match_legacy_status_precedence_and_thresholds() {
     let now = Utc::now();
@@ -160,11 +197,15 @@ async fn health_timeline_should_match_legacy_status_precedence_and_thresholds()
         ),
     ];
 
-    for (metrics, expected_status, expected_reliability) in fixtures {
+    for (index, (metrics, expected_status, expected_reliability)) in
+        fixtures.into_iter().enumerate()
+    {
         store.replace_trend(vec![health_metric_point(current_slot, metrics)]);
+        let range_end =
+            now + Duration::seconds(i64::try_from(index).expect("fixture index fits i64") * 2);
         let timeline = services
             .observability()
-            .dashboard_summary(observation_range(now), TrendKind::Usage)
+            .dashboard_summary(observation_range(range_end), TrendKind::Usage)
             .await
             .expect("dashboard summary")
             .health_timeline;
@@ -220,6 +261,53 @@ async fn dashboard_summary_should_share_one_current_observation_time_across_runt
     assert!(summary_observed_at.is_some_and(|value| value > historical_end));
 }
 
+#[tokio::test]
+async fn dashboard_summary_should_coalesce_concurrent_requests_in_one_short_window() {
+    let end_bucket = Utc::now().timestamp().div_euclid(2) * 2;
+    let first_end = DateTime::from_timestamp(end_bucket, 100_000_000).expect("first end");
+    let second_end = DateTime::from_timestamp(end_bucket, 900_000_000).expect("second end");
+    let first_range = TimeRange::new(china_day_start(first_end), first_end).expect("first range");
+    let second_range =
+        TimeRange::new(china_day_start(second_end), second_end).expect("second range");
+    let store = Arc::new(FixtureObservabilityStore::new(first_range));
+    store.set_dashboard_delay(StdDuration::from_millis(20));
+    let services = observability_services(store.clone()).await;
+    let observability = services.observability();
+
+    let (first, second) = tokio::join!(
+        observability.dashboard_summary(first_range, TrendKind::Usage),
+        observability.dashboard_summary(second_range, TrendKind::Errors),
+    );
+
+    first.expect("first dashboard summary");
+    second.expect("second dashboard summary");
+    assert_eq!(store.dashboard_summary_calls(), 1);
+}
+
+#[tokio::test]
+async fn dashboard_summary_should_reload_after_the_short_window_changes() {
+    let end_bucket = Utc::now().timestamp().div_euclid(2) * 2;
+    let first_end = DateTime::from_timestamp(end_bucket, 100_000_000).expect("first end");
+    let second_end = first_end + Duration::seconds(2);
+    let first_range = TimeRange::new(china_day_start(first_end), first_end).expect("first range");
+    let second_range =
+        TimeRange::new(china_day_start(second_end), second_end).expect("second range");
+    let store = Arc::new(FixtureObservabilityStore::new(first_range));
+    let services = observability_services(store.clone()).await;
+    let observability = services.observability();
+
+    observability
+        .dashboard_summary(first_range, TrendKind::Usage)
+        .await
+        .expect("first dashboard summary");
+    observability
+        .dashboard_summary(second_range, TrendKind::Usage)
+        .await
+        .expect("second dashboard summary");
+
+    assert_eq!(store.dashboard_summary_calls(), 2);
+}
+
 #[tokio::test]
 async fn observability_services_should_calculate_usage_insights_and_diagnostic_shares() {
     let now = Utc::now();
@@ -234,6 +322,24 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
         output_tokens: 200,
         total_tokens: 1_000,
         latency_count: 5,
+        admission_decision_count: 10,
+        admission_decision_percentiles: LatencyPercentiles {
+            p50_ms: Some(PercentileMilliseconds::new(2.0).expect("admission P50")),
+            p95_ms: Some(PercentileMilliseconds::new(5.0).expect("admission P95")),
+            p99_ms: Some(PercentileMilliseconds::new(8.0).expect("admission P99")),
+        },
+        account_selection_wait_count: 8,
+        account_selection_wait_percentiles: LatencyPercentiles {
+            p50_ms: Some(PercentileMilliseconds::new(10.0).expect("selection P50")),
+            p95_ms: Some(PercentileMilliseconds::new(40.0).expect("selection P95")),
+            p99_ms: Some(PercentileMilliseconds::new(70.0).expect("selection P99")),
+        },
+        output_throughput_p10: Some(40),
+        output_throughput_p50: Some(50),
+        output_throughput_p90: Some(60),
+        capacity_sample_count: 8,
+        capacity_utilization_avg_basis_points: Some(6_500),
+        capacity_utilization_p95_basis_points: Some(8_000),
         ..RequestMetrics::default()
     };
     store.replace_overview(UsageOverview {
@@ -294,10 +400,16 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
         .await
         .expect("usage diagnostics");
 
-    assert_eq!(insights.health.total_requests, 8);
+    assert_eq!(insights.health.total_requests, 10);
     assert_eq!(insights.health.failed_requests, 2);
+    assert_eq!(insights.health.success_rate, 0.75);
+    assert_eq!(insights.health.completion_rate, 1.0);
     assert_eq!(insights.granularity, Granularity::FifteenMinutes);
     assert_eq!(insights.performance.latency_coverage, 0.5);
+    assert_eq!(insights.performance.admission_decision_coverage, 1.0);
+    assert_eq!(insights.performance.account_selection_wait_coverage, 0.8);
+    assert_eq!(insights.performance.capacity_coverage, 0.8);
+    assert_eq!(insights.performance.output_throughput_p50, Some(50));
     assert_eq!(insights.cost.tokens_per_request, 100.0);
     assert_eq!(
         insights
@@ -337,8 +449,25 @@ async fn observability_services_should_calculate_usage_insights_and_diagnostic_s
             .map(gateway_admin::model::observability::DecimalAmount::as_str),
         Some("1")
     );
+    assert_eq!(
+        insights
+            .cost
+            .no_cache_cost
+            .as_ref()
+            .map(gateway_admin::model::observability::DecimalAmount::as_str),
+        Some("1.25")
+    );
+    assert_eq!(
+        insights
+            .cost
+            .tier_premium
+            .as_ref()
+            .map(gateway_admin::model::observability::DecimalAmount::as_str),
+        Some("0.25")
+    );
     assert_eq!(diagnostics.items[0].request_share, 0.75);
     assert_eq!(diagnostics.items[1].request_share, 0.25);
+    assert!((diagnostics.items[0].impact_score - 0.075).abs() < 1e-9);
 }
 
 #[tokio::test]
@@ -408,15 +537,48 @@ async fn usage_records_should_enrich_provider_reported_totals_when_pricing_match
     ));
 }
 
+#[tokio::test]
+async fn usage_insights_should_reject_partial_costs_when_billing_stream_fails() {
+    let now = Utc::now();
+    let range = observation_range(now);
+    let store = Arc::new(FixtureObservabilityStore::new(range));
+    store.replace_calculated_billing_facts(vec![UsageCalculatedBillingFact {
+        bucket_start: quarter_hour_start(now),
+        provider_kind: "openai".to_owned(),
+        upstream_model_id: "gpt-5.5".to_owned(),
+        service_tier: None,
+        input_tokens: Some(800),
+        output_tokens: Some(200),
+        cached_tokens: Some(0),
+        cache_write_tokens: Some(0),
+        total: CurrencyCost {
+            currency: "USD".to_owned(),
+            amount: "1.25".parse().expect("cost"),
+        },
+    }]);
+    store.billing_stream_fails.store(true, Ordering::SeqCst);
+    let services = observability_services_with_calculated_billing(store).await;
+    assert!(
+        services
+            .observability()
+            .usage_insights(range, UsageFilter::default())
+            .await
+            .is_err()
+    );
+}
+
 struct FixtureObservabilityStore {
     trend: Mutex<Vec<RequestMetricPoint>>,
     overview: Mutex<UsageOverview>,
     calculated_billing_facts: Mutex<Vec<UsageCalculatedBillingFact>>,
+    billing_stream_fails: AtomicBool,
     diagnostics: Mutex<Vec<DiagnosticObservation>>,
     runtime_slots: Mutex<Option<DashboardRuntimeSlots>>,
     summary_observed_at: Mutex<Option<DateTime<Utc>>>,
     slots_observed_at: Mutex<Option<DateTime<Utc>>>,
-    usage_records: Mutex<Vec<UsageRecord>>,
+    usage_records: Mutex<Vec<UsageListRecord>>,
+    dashboard_delay: Mutex<StdDuration>,
+    dashboard_summary_calls: AtomicUsize,
 }
 
 impl FixtureObservabilityStore {
@@ -430,14 +592,25 @@ impl FixtureObservabilityStore {
                 providers: Vec::new(),
             }),
             calculated_billing_facts: Mutex::new(Vec::new()),
+            billing_stream_fails: AtomicBool::new(false),
             diagnostics: Mutex::new(Vec::new()),
             runtime_slots: Mutex::new(None),
             summary_observed_at: Mutex::new(None),
             slots_observed_at: Mutex::new(None),
             usage_records: Mutex::new(Vec::new()),
+            dashboard_delay: Mutex::new(StdDuration::ZERO),
+            dashboard_summary_calls: AtomicUsize::new(0),
         }
     }
 
+    fn set_dashboard_delay(&self, delay: StdDuration) {
+        *self.dashboard_delay.lock().expect("dashboard delay") = delay;
+    }
+
+    fn dashboard_summary_calls(&self) -> usize {
+        self.dashboard_summary_calls.load(Ordering::Relaxed)
+    }
+
     fn replace_trend(&self, trend: Vec<RequestMetricPoint>) {
         *self.trend.lock().expect("trend") = trend;
     }
@@ -471,7 +644,7 @@ impl FixtureObservabilityStore {
         )
     }
 
-    fn replace_usage_records(&self, records: Vec<UsageRecord>) {
+    fn replace_usage_records(&self, records: Vec<UsageListRecord>) {
         *self.usage_records.lock().expect("usage records") = records;
     }
 }
@@ -483,14 +656,17 @@ impl ObservabilityStore for FixtureObservabilityStore {
         range: TimeRange,
         observed_at: DateTime<Utc>,
     ) -> AdminStoreResult<DashboardObservation> {
+        self.dashboard_summary_calls.fetch_add(1, Ordering::Relaxed);
         *self
             .summary_observed_at
             .lock()
             .expect("summary observed at") = Some(observed_at);
+        let dashboard_delay = *self.dashboard_delay.lock().expect("dashboard delay");
+        if !dashboard_delay.is_zero() {
+            tokio::time::sleep(dashboard_delay).await;
+        }
         Ok(DashboardObservation {
             range,
-            requests: RequestMetrics::default(),
-            attempts: AttemptMetrics::default(),
             totals: Default::default(),
             provider_accounts: AccountPoolMetrics::default(),
             trend: self.trend.lock().expect("trend").clone(),
@@ -519,25 +695,33 @@ impl ObservabilityStore for FixtureObservabilityStore {
         Ok(self.trend.lock().expect("trend").clone())
     }
 
-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
         &self,
         _: TimeRange,
         _: UsageFilter,
-    ) -> AdminStoreResult<Vec<UsageCalculatedBillingFact>> {
-        Ok(self
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        let facts = self
             .calculated_billing_facts
             .lock()
             .expect("calculated billing facts")
-            .clone())
+            .clone();
+        let error = self
+            .billing_stream_fails
+            .load(Ordering::SeqCst)
+            .then(|| Err(super::unavailable("billing stream failed")));
+        Box::pin(futures::stream::iter(
+            facts.into_iter().map(Ok).chain(error),
+        ))
     }
 
-    async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {
+    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
         let items = self.usage_records.lock().expect("usage records").clone();
         let total = u64::try_from(items.len()).unwrap_or(u64::MAX);
         Ok(UsagePage {
             items,
+            current_page: query.current_page,
+            page_size: query.page_size.get(),
             total,
-            next_cursor: None,
         })
     }
 
@@ -576,6 +760,8 @@ impl SettingsStore for FixtureSettingsStore {
             max_concurrent_per_account: 1,
             request_interval_ms: 0,
             rotation_strategy: RotationStrategy::Smart,
+            min_codex_desktop_version: None,
+            min_codex_cli_version: None,
             usage_retention_days: 31,
             ops_event_retention_days: 30,
             audit_retention_days: 30,
@@ -639,8 +825,7 @@ fn usage_query(now: DateTime<Utc>) -> UsageQuery {
     UsageQuery {
         range: observation_range(now),
         filter: UsageFilter::default(),
-        cursor: None,
-        page: PageNumber::new(NonZeroU32::new(1).expect("page number")),
+        current_page: 1,
         page_size: PageSize::new(50).expect("page size"),
     }
 }
@@ -650,16 +835,9 @@ fn total_record(
     provider_kind: Option<&str>,
     source: &str,
     now: DateTime<Utc>,
-) -> UsageRecord {
-    UsageRecord {
+) -> UsageListRecord {
+    UsageListRecord {
         id: id.to_owned(),
-        client_api_key_ref: "key_billing".to_owned(),
-        config_revision: 1,
-        routing_scope: "all".to_owned(),
-        routing_group_refs: Vec::new(),
-        routing_group_names_snapshot: Vec::new(),
-        protocol: "openai".to_owned(),
-        operation: "generate".to_owned(),
         endpoint: "/v1/responses".to_owned(),
         client_transport: "http_sse".to_owned(),
         requested_model_id: Some("gpt-5.5".to_owned()),
@@ -670,23 +848,7 @@ fn total_record(
         provider_account_authentication_kind: None,
         upstream_model_id: Some("gpt-5.5".to_owned()),
         upstream_transport: None,
-        http_version: None,
-        websocket_pool: None,
         service_tier: None,
-        provider_metadata_json: None,
-        attempt_count: 1,
-        upstream_send_state: "sent".to_owned(),
-        downstream_committed_at: None,
-        outcome: RequestOutcome::Succeeded,
-        client_status_code: Some(200),
-        upstream_status_code: Some(200),
-        client_response_id: None,
-        upstream_request_id: None,
-        upstream_response_id: None,
-        error_kind: None,
-        provider_error_code: None,
-        error_message: None,
-        retry_after_ms: None,
         input_tokens: Some(800),
         output_tokens: Some(200),
         cached_tokens: Some(0),
@@ -715,18 +877,17 @@ fn total_record(
         first_token_ms: None,
         provider_processing_ms: None,
         latency_ms: Some(100),
+        admission_decision_ms: None,
+        account_selection_wait_ms: None,
+        capacity_used_slots: None,
+        capacity_total_slots: None,
         client_ip: None,
         user_agent: None,
         reasoning_effort: None,
         reasoning_preset: None,
-        request_kind: None,
         subagent_kind: None,
         compact: false,
-        image_generation_requested: false,
-        image_generation_succeeded: None,
         started_at: now,
-        deadline_at: now,
-        completed_at: Some(now),
     }
 }
 
@@ -742,6 +903,9 @@ 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,
+        retry_count: 0,
         key: name.to_owned(),
         name: name.to_owned(),
         request_count,

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

@@ -1,6 +1,6 @@
 use std::sync::Arc;
 
-use gateway_core::engine::credential::ProviderAccountId;
+use gateway_core::account::ProviderAccountId;
 
 use gateway_admin::{
     AdminServices,

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

@@ -67,6 +67,8 @@ async fn settings_should_reject_zero_refresh_margin_before_store_call() {
                 max_concurrent_per_account: 1,
                 request_interval_ms: 0,
                 rotation_strategy: RotationStrategy::Smart,
+                min_codex_desktop_version: None,
+                min_codex_cli_version: None,
                 usage_retention_days: 31,
                 ops_event_retention_days: 30,
                 audit_retention_days: 30,

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

@@ -1,6 +1,6 @@
 use std::sync::Arc;
 
-use gateway_core::engine::credential::ProviderAccountId;
+use gateway_core::account::ProviderAccountId;
 
 use gateway_admin::{
     AdminServices,

backend/crates/gateway-api/Cargo.toml

@@ -24,7 +24,7 @@ secrecy = "0.10"
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
 thiserror = "2.0.18"
-tokio = { version = "1.52.3", default-features = false, features = ["macros", "time"] }
+tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt", "sync", "time"] }
 tower-http = { version = "0.7.0", features = ["cors", "fs", "request-id", "timeout", "trace"] }
 tracing = "0.1.44"
 url = "2.5.8"
@@ -33,7 +33,7 @@ uuid = { version = "1.23.3", features = ["v7"] }
 [dev-dependencies]
 async-trait = "0.1.89"
 axum = { version = "0.8.9", default-features = false, features = ["http1", "tokio"] }
-tokio = { version = "1.52.3", default-features = false, features = ["macros", "net", "rt-multi-thread"] }
+tokio = { version = "1.52.3", default-features = false, features = ["macros", "net", "rt-multi-thread", "test-util"] }
 tokio-tungstenite = "0.29.0"
 tower = { version = "0.5.3", features = ["util"] }
 

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

@@ -3,8 +3,8 @@
 use std::collections::BTreeMap;
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::StatusCode,
     response::IntoResponse,
     routing::{get, post},
@@ -22,8 +22,8 @@ use gateway_core::routing::AccountGroupId;
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, PageMeta,
-    WireValidationError, wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    PageMeta, WireValidationError, wire::map_admin_service_error,
 };
 
 const DEFAULT_PAGE_SIZE: u32 = 50;
@@ -127,7 +127,7 @@ struct AccountGroupCapacityView {
 #[serde(rename_all = "camelCase")]
 struct AccountGroupUsageView {
     today_usd: String,
-    total_usd: String,
+    retained_total_usd: String,
 }
 
 impl From<AccountGroupRecord> for AccountGroupView {
@@ -168,7 +168,7 @@ fn capacity_view(capacity: AccountGroupCapacity) -> AccountGroupCapacityView {
 fn usage_view(usage: AccountGroupUsage) -> AccountGroupUsageView {
     AccountGroupUsageView {
         today_usd: usage.today_usd.to_string(),
-        total_usd: usage.total_usd.to_string(),
+        retained_total_usd: usage.retained_total_usd.to_string(),
     }
 }
 
@@ -235,7 +235,7 @@ where
 async fn list<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<ListAccountGroupsQuery>,
+    AdminQuery(query): AdminQuery<ListAccountGroupsQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -255,7 +255,7 @@ where
 async fn create<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<CreateAccountGroupRequest>,
+    AdminJson(request): AdminJson<CreateAccountGroupRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -281,7 +281,7 @@ where
 async fn update<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<UpdateAccountGroupRequest>,
+    AdminJson(request): AdminJson<UpdateAccountGroupRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -308,7 +308,7 @@ where
 async fn enable<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<AccountGroupIdRequest>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -319,7 +319,7 @@ where
 async fn disable<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<AccountGroupIdRequest>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -355,7 +355,7 @@ where
 async fn delete<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<AccountGroupIdRequest>,
+    AdminJson(request): AdminJson<AccountGroupIdRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -387,12 +387,11 @@ fn mutation_response(
 }
 
 fn group_id(value: String) -> Result<AccountGroupId, AdminError> {
-    AccountGroupId::new(value).map_err(|_| AdminError::bad_request("Invalid account group ID"))
+    AccountGroupId::new(value).map_err(|_| AdminError::bad_request("账号组 ID 不合法"))
 }
 
 fn group_color(value: &str) -> Result<AccountGroupColor, AdminError> {
-    AccountGroupColor::parse(value)
-        .ok_or_else(|| AdminError::bad_request("Invalid account group color"))
+    AccountGroupColor::parse(value).ok_or_else(|| AdminError::bad_request("账号组颜色不合法"))
 }
 
 fn validate_group_fields(name: &str, description: Option<&str>) -> Result<(), AdminError> {
@@ -403,15 +402,15 @@ fn validate_group_fields(name: &str, description: Option<&str>) -> Result<(), Ad
         || description
             .is_some_and(|value| value.len() > 4096 || value.chars().any(char::is_control))
     {
-        return Err(AdminError::bad_request("Invalid account group request"));
+        return Err(AdminError::bad_request("账号组请求不合法"));
     }
     Ok(())
 }
 
 fn map_wire_error(_: WireValidationError) -> AdminError {
-    AdminError::bad_request("Invalid account group query")
+    AdminError::bad_request("账号组查询参数不合法")
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Account group repository unavailable")
+    map_admin_service_error(error)
 }

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

@@ -0,0 +1,488 @@
+//! Provider-owned 凭据请求、命令转换与敏感材料校验。
+
+use super::*;
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(super) enum AccountProvider {
+    OpenAi,
+    Xai,
+}
+
+impl AccountProvider {
+    fn parse(value: &str) -> Result<Self, WireValidationError> {
+        match value.trim() {
+            "openai" => Ok(Self::OpenAi),
+            "xai" => Ok(Self::Xai),
+            _ => Err(WireValidationError::new("provider")),
+        }
+    }
+}
+
+/// Provider-owned 账号导入请求；公共 API 不解释 `data` 内部字段。
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountImportRequest {
+    pub provider: String,
+    pub data: Value,
+}
+
+impl AccountImportRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        if !self.data.is_object()
+            || serde_json::to_vec(&self.data)
+                .map_or(true, |encoded| encoded.len() > MAX_IMPORT_DATA_BYTES)
+        {
+            return Err(WireValidationError::new("data"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, ImportCredentials), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            ImportCredentials {
+                context,
+                document: provider_document(self.data, "data")?,
+            },
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct StartAccountAuthorizationRequest {
+    pub provider: String,
+    pub name: String,
+    pub account_id: Option<String>,
+}
+
+impl StartAccountAuthorizationRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        require_text(&self.name, MAX_NAME_BYTES, "name")?;
+        if let Some(account_id) = self.account_id.as_deref() {
+            require_account_id(account_id, "accountId")?;
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, StartAuthorization), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        let reauthorization = self
+            .account_id
+            .map(ProviderAccountId::new)
+            .transpose()
+            .map_err(|_| WireValidationError::new("accountId"))?;
+        Ok((
+            provider,
+            StartAuthorization {
+                context,
+                name: self.name,
+                reauthorization,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct CompleteAccountAuthorizationRequest {
+    pub provider: String,
+    pub flow_id: String,
+    pub callback_url: String,
+}
+
+impl CompleteAccountAuthorizationRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        let provider = AccountProvider::parse(&self.provider)?;
+        match provider {
+            AccountProvider::OpenAi => {
+                if !URL_SAFE_NO_PAD
+                    .decode(&self.flow_id)
+                    .is_ok_and(|decoded| decoded.len() == 32)
+                {
+                    return Err(WireValidationError::new("flowId"));
+                }
+            }
+            AccountProvider::Xai => require_wire_id(&self.flow_id, "flowId")?,
+        }
+        require_text(&self.callback_url, MAX_CALLBACK_URL_BYTES, "callbackUrl")
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, CompleteAuthorization), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            CompleteAuthorization {
+                context,
+                flow_id: self.flow_id,
+                callback_url: self.callback_url,
+            },
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct UpdateAccountRequest {
+    pub account_id: String,
+    pub enabled: bool,
+    #[serde(deserialize_with = "deserialize_required_nullable")]
+    pub concurrency_limit: Option<u64>,
+    pub weight: u64,
+    pub group_ids: Vec<String>,
+}
+
+impl UpdateAccountRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        parse_concurrency_limit(self.concurrency_limit)?;
+        parse_account_weight(self.weight)?;
+        validate_wire_group_ids(&self.group_ids)?;
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<UpdateAccount, WireValidationError> {
+        self.validate()?;
+        Ok(UpdateAccount {
+            account_id: self.account_id,
+            enabled: self.enabled,
+            concurrency_limit: parse_concurrency_limit(self.concurrency_limit)?,
+            weight: parse_account_weight(self.weight)?,
+            group_ids: validate_wire_group_ids(&self.group_ids)?,
+        })
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UpdatedAccountData {
+    pub account_id: String,
+    pub config_revision: u64,
+}
+
+impl From<AccountUpdateResult> for UpdatedAccountData {
+    fn from(result: AccountUpdateResult) -> Self {
+        Self {
+            account_id: result.account_id.to_string(),
+            config_revision: result.config_revision.get(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountDeletionRequest {
+    pub provider: String,
+    pub account_ids: Vec<String>,
+}
+
+impl AccountDeletionRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        AccountProvider::parse(&self.provider)?;
+        if self.account_ids.is_empty() || self.account_ids.len() > MAX_ACCOUNT_DELETE_BATCH {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        let mut unique = BTreeSet::new();
+        for account_id in &self.account_ids {
+            require_account_id(account_id, "accountIds")?;
+            if !unique.insert(account_id.as_str()) {
+                return Err(WireValidationError::new("accountIds"));
+            }
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<(AccountProvider, CredentialDeletion), WireValidationError> {
+        self.validate()?;
+        let provider = AccountProvider::parse(&self.provider)?;
+        Ok((
+            provider,
+            CredentialDeletion {
+                context,
+                account_ids: self
+                    .account_ids
+                    .into_iter()
+                    .map(ProviderAccountId::new)
+                    .collect::<Result<Vec<_>, _>>()
+                    .map_err(|_| WireValidationError::new("accountIds"))?,
+            },
+        ))
+    }
+}
+
+#[derive(Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct RotateAccountRequest {
+    pub provider: String,
+    pub account_id: String,
+    pub access_token: String,
+    pub refresh_token: Option<String>,
+    pub id_token: Option<String>,
+}
+
+impl RotateAccountRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        if AccountProvider::parse(&self.provider)? != AccountProvider::OpenAi {
+            return Err(WireValidationError::new("provider"));
+        }
+        require_account_id(&self.account_id, "accountId")?;
+        validate_oauth_material(
+            &self.access_token,
+            self.refresh_token.as_deref(),
+            self.id_token.as_deref(),
+        )
+    }
+
+    pub(super) fn into_command(
+        self,
+        context: gateway_admin::model::MutationContext,
+    ) -> Result<RotateCredential, WireValidationError> {
+        self.validate()?;
+        let mut material = Map::new();
+        material.insert("access_token".to_owned(), Value::String(self.access_token));
+        material.insert(
+            "refresh_token".to_owned(),
+            self.refresh_token.map_or(Value::Null, Value::String),
+        );
+        material.insert(
+            "id_token".to_owned(),
+            self.id_token.map_or(Value::Null, Value::String),
+        );
+        Ok(RotateCredential {
+            mutation: CredentialMutation {
+                context,
+                account_id: ProviderAccountId::new(self.account_id)
+                    .map_err(|_| WireValidationError::new("accountId"))?,
+            },
+            provider_material: ProviderDocument::new(OpaqueProviderData::new(material)),
+        })
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountImportData {
+    pub imported_count: usize,
+    pub account_ids: Vec<String>,
+}
+
+impl AccountImportData {
+    pub fn from_result(result: CredentialImportResult) -> Self {
+        let account_ids = result
+            .credential_ids
+            .into_iter()
+            .map(|account_id| account_id.to_string())
+            .collect::<Vec<_>>();
+        Self {
+            imported_count: account_ids.len(),
+            account_ids,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountAuthorizationData {
+    pub flow_id: String,
+    pub authorization_url: String,
+    pub expires_at: DateTime<Utc>,
+}
+
+impl From<AuthorizationStarted> for AccountAuthorizationData {
+    fn from(started: AuthorizationStarted) -> Self {
+        Self {
+            flow_id: started.flow_id,
+            authorization_url: started.authorization_url,
+            expires_at: started.expires_at,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountMutationData {
+    pub account_id: String,
+}
+
+impl From<CredentialMutationResult> for AccountMutationData {
+    fn from(result: CredentialMutationResult) -> Self {
+        Self {
+            account_id: result.account_id.to_string(),
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountDeletionData {
+    pub deleted_count: usize,
+    pub account_ids: Vec<String>,
+}
+
+impl From<CredentialDeletionResult> for AccountDeletionData {
+    fn from(result: CredentialDeletionResult) -> Self {
+        let account_ids = result
+            .account_ids
+            .into_iter()
+            .map(|account_id| account_id.to_string())
+            .collect::<Vec<_>>();
+        Self {
+            deleted_count: account_ids.len(),
+            account_ids,
+        }
+    }
+}
+
+pub(super) fn require_account_id(
+    value: &str,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.trim().is_empty()
+        || value.len() > 128
+        || value.chars().any(char::is_control)
+        || !value.starts_with("acct_")
+    {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+pub(super) fn parse_concurrency_limit(
+    value: Option<u64>,
+) -> Result<Option<AccountConcurrencyLimit>, WireValidationError> {
+    value
+        .map(|value| {
+            u32::try_from(value)
+                .ok()
+                .and_then(AccountConcurrencyLimit::new)
+                .ok_or_else(|| WireValidationError::new("concurrencyLimit"))
+        })
+        .transpose()
+}
+
+pub(super) fn deserialize_required_nullable<'de, D>(
+    deserializer: D,
+) -> Result<Option<u64>, D::Error>
+where
+    D: Deserializer<'de>,
+{
+    Option::<u64>::deserialize(deserializer)
+}
+
+pub(super) fn parse_account_weight(value: u64) -> Result<AccountWeight, WireValidationError> {
+    u16::try_from(value)
+        .ok()
+        .and_then(AccountWeight::new)
+        .ok_or_else(|| WireValidationError::new("weight"))
+}
+
+pub(super) fn validate_wire_group_ids(
+    values: &[String],
+) -> Result<Vec<AccountGroupId>, WireValidationError> {
+    if values.len() > MAX_ACCOUNT_GROUP_BATCH
+        || values.iter().collect::<BTreeSet<_>>().len() != values.len()
+    {
+        return Err(WireValidationError::new("groupIds"));
+    }
+    values
+        .iter()
+        .cloned()
+        .map(|value| AccountGroupId::new(value).map_err(|_| WireValidationError::new("groupIds")))
+        .collect()
+}
+
+fn provider_document(
+    value: Value,
+    field: &'static str,
+) -> Result<ProviderDocument, WireValidationError> {
+    match value {
+        Value::Object(document) => Ok(ProviderDocument::new(OpaqueProviderData::new(document))),
+        _ => Err(WireValidationError::new(field)),
+    }
+}
+
+fn require_wire_id(value: &str, field: &'static str) -> Result<(), WireValidationError> {
+    require_text(value, MAX_ID_BYTES, field)?;
+    if value.starts_with("__")
+        || !value
+            .bytes()
+            .all(|byte| byte.is_ascii_alphanumeric() || matches!(byte, b'_' | b'-' | b'.' | b':'))
+    {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+fn require_text(
+    value: &str,
+    max_bytes: usize,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.trim().is_empty() || value.len() > max_bytes || value.chars().any(char::is_control) {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
+fn validate_oauth_material(
+    access_token: &str,
+    refresh_token: Option<&str>,
+    id_token: Option<&str>,
+) -> Result<(), WireValidationError> {
+    if access_token.len() > MAX_ACCESS_TOKEN_BYTES
+        || !valid_visible_ascii(access_token)
+        || !valid_compact_jwt_shape(access_token)
+    {
+        return Err(WireValidationError::new("accessToken"));
+    }
+    if refresh_token.is_some_and(|token| {
+        token.len() > MAX_REFRESH_TOKEN_BYTES
+            || !valid_visible_ascii(token)
+            || token == access_token
+    }) {
+        return Err(WireValidationError::new("refreshToken"));
+    }
+    if id_token.is_some_and(|token| {
+        token.len() > MAX_ID_TOKEN_BYTES
+            || !valid_visible_ascii(token)
+            || !valid_compact_jwt_shape(token)
+    }) {
+        return Err(WireValidationError::new("idToken"));
+    }
+    Ok(())
+}
+
+fn valid_compact_jwt_shape(value: &str) -> bool {
+    let mut segments = value.split('.');
+    matches!(
+        (segments.next(), segments.next(), segments.next(), segments.next()),
+        (Some(header), Some(payload), Some(signature), None)
+            if !header.is_empty() && !payload.is_empty() && !signature.is_empty()
+    )
+}
+
+fn valid_visible_ascii(value: &str) -> bool {
+    !value.is_empty() && value.bytes().all(|byte| (0x21..=0x7e).contains(&byte))
+}
+
+pub(super) fn provider_document_value(document: ProviderDocument) -> Value {
+    Value::Object(document.into_provider_data().into_inner())
+}

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

@@ -0,0 +1,573 @@
+//! 账号管理路由与 HTTP handler 编排。
+
+use super::*;
+
+/// 构造统一账号管理路由。
+pub fn router<S>() -> Router<S>
+where
+    S: AdminSessionState + Clone + Send + Sync + 'static,
+{
+    Router::new()
+        .route("/api/admin/accounts", get(list_accounts::<S>))
+        .route("/api/admin/accounts/detail", get(account_detail::<S>))
+        .route("/api/admin/accounts/export", get(export_accounts::<S>))
+        .route("/api/admin/accounts/import", post(import_accounts::<S>))
+        .route("/api/admin/accounts/refresh", post(refresh_account::<S>))
+        .route("/api/admin/accounts/recover", post(recover_account::<S>))
+        .route("/api/admin/accounts/rotate", post(rotate_account::<S>))
+        .route("/api/admin/accounts/update", post(update_account::<S>))
+        .route("/api/admin/accounts/delete", post(delete_accounts::<S>))
+        .route(
+            "/api/admin/accounts/batch-update",
+            post(batch_update_accounts::<S>),
+        )
+        .route("/api/admin/accounts/quota", get(account_quota::<S>))
+        .route(
+            "/api/admin/accounts/profile-statistics",
+            get(account_profile_statistics::<S>),
+        )
+        .route(
+            "/api/admin/accounts/profile-avatar",
+            get(account_profile_avatar::<S>),
+        )
+        .route(
+            "/api/admin/accounts/reset-credits",
+            get(account_reset_credits::<S>).post(consume_account_reset_credit::<S>),
+        )
+        .route(
+            "/api/admin/accounts/quota/refresh",
+            post(refresh_account_quota::<S>),
+        )
+        .route("/api/admin/accounts/models", get(account_models::<S>))
+        .route(
+            "/api/admin/accounts/models/refresh",
+            post(refresh_account_models::<S>),
+        )
+        .route(
+            "/api/admin/accounts/connection-test",
+            get(test_account_connection::<S>),
+        )
+        .route(
+            "/api/admin/accounts/oauth/start",
+            post(start_account_authorization::<S>),
+        )
+        .route(
+            "/api/admin/accounts/oauth/complete",
+            post(complete_account_authorization::<S>),
+        )
+}
+
+async fn batch_update_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<BatchUpdateAccountsRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .batch_update(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(BatchUpdatedAccountsData::from(result)),
+    ))
+}
+
+async fn list_accounts<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ListQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = query.validate().map_err(map_wire_error)?;
+    let page = command.page;
+    let page_size = command.page_size.get();
+    let result = state
+        .admin_services()
+        .accounts()
+        .list(command)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_page_data(result, page, page_size, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_detail<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn export_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountExportQuery>,
+) -> Result<Response, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let ids = query.into_ids().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .export(&auth.context().mutation_context(), ids)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountExportData::from_result(result);
+    let mut response = AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)).into_response();
+    response
+        .headers_mut()
+        .insert(header::CACHE_CONTROL, HeaderValue::from_static("no-store"));
+    Ok(response)
+}
+
+async fn import_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountImportRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .import_document(command)
+                .await
+        }
+        AccountProvider::Xai => state.admin_services().xai().import_document(command).await,
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountImportData::from_result(result)),
+    ))
+}
+
+async fn start_account_authorization<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<StartAccountAuthorizationRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .start_authorization(command)
+                .await
+        }
+        AccountProvider::Xai => {
+            state
+                .admin_services()
+                .xai()
+                .start_authorization(command)
+                .await
+        }
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountAuthorizationData::from(result)),
+    ))
+}
+
+async fn complete_account_authorization<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<CompleteAccountAuthorizationRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => {
+            state
+                .admin_services()
+                .openai()
+                .complete_authorization(command)
+                .await
+        }
+        AccountProvider::Xai => {
+            state
+                .admin_services()
+                .xai()
+                .complete_authorization(command)
+                .await
+        }
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::CREATED,
+        AdminEnvelope::ok(AccountMutationData::from(result)),
+    ))
+}
+
+async fn rotate_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<RotateAccountRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .openai()
+        .rotate(command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountMutationData::from(result)),
+    ))
+}
+
+async fn update_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<UpdateAccountRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .update(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(UpdatedAccountData::from(result)),
+    ))
+}
+
+async fn delete_accounts<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountDeletionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (provider, command) = request
+        .into_command(auth.context().mutation_context())
+        .map_err(map_wire_error)?;
+    let result = match provider {
+        AccountProvider::OpenAi => state.admin_services().openai().delete(command).await,
+        AccountProvider::Xai => state.admin_services().xai().delete(command).await,
+    }
+    .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountDeletionData::from(result)),
+    ))
+}
+
+async fn refresh_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountRefreshRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .refresh(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_refresh_data(result, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn recover_account<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .recover(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_refresh_data(result, Utc::now());
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_quota<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_profile_statistics<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .profile_statistics(&account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountProfileStatisticsData::from(result)),
+    ))
+}
+
+async fn account_profile_avatar<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountProfileAvatarQuery>,
+) -> Result<Response, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let avatar = state
+        .admin_services()
+        .accounts()
+        .profile_avatar(&account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(profile_avatar_response(avatar))
+}
+
+/// 将 Provider 头像流投影为受保护的同源 HTTP 响应。
+#[must_use]
+pub fn profile_avatar_response(avatar: ProviderProfileAvatar) -> Response {
+    let ProviderProfileAvatar {
+        content_type,
+        content_length,
+        etag,
+        body,
+    } = avatar;
+    let mut response = Response::new(Body::from_stream(body));
+    *response.status_mut() = StatusCode::OK;
+    let headers = response.headers_mut();
+    headers.insert(
+        header::CONTENT_TYPE,
+        content_type
+            .and_then(|value| HeaderValue::from_str(&value).ok())
+            .unwrap_or_else(|| HeaderValue::from_static("application/octet-stream")),
+    );
+    if let Some(value) =
+        content_length.and_then(|length| HeaderValue::from_str(&length.to_string()).ok())
+    {
+        headers.insert(header::CONTENT_LENGTH, value);
+    }
+    if let Some(value) = etag.and_then(|value| HeaderValue::from_str(&value).ok()) {
+        headers.insert(header::ETAG, value);
+    }
+    headers.insert(
+        header::CACHE_CONTROL,
+        HeaderValue::from_static("private, max-age=3600"),
+    );
+    headers.insert(
+        HeaderName::from_static("x-content-type-options"),
+        HeaderValue::from_static("nosniff"),
+    );
+    headers.insert(
+        HeaderName::from_static("cross-origin-resource-policy"),
+        HeaderValue::from_static("same-origin"),
+    );
+    headers.insert(
+        HeaderName::from_static("content-security-policy"),
+        HeaderValue::from_static("sandbox; default-src 'none'"),
+    );
+    response
+}
+
+async fn refresh_account_quota<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .quota(&account_id, true)
+        .await
+        .map_err(map_service_error)?;
+    let data = AccountQuotaData {
+        account: account_view(result, Utc::now()),
+    };
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn account_reset_credits<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .reset_credits(&auth.context().mutation_context(), account_id)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountResetCreditsData::from(result)),
+    ))
+}
+
+async fn consume_account_reset_credit<S>(
+    auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountResetCreditConsumeRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let command = request.into_command().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .consume_reset_credit(&auth.context().mutation_context(), command)
+        .await
+        .map_err(map_service_error)?;
+    Ok(AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(AccountResetCreditResultData::from(result)),
+    ))
+}
+
+async fn account_models<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountIdQuery>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = query.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .models(&account_id, false)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_models_data(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn refresh_account_models<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminJson(request): AdminJson<AccountActionRequest>,
+) -> Result<impl IntoResponse, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let account_id = request.into_id().map_err(map_wire_error)?;
+    let result = state
+        .admin_services()
+        .accounts()
+        .models(&account_id, true)
+        .await
+        .map_err(map_service_error)?;
+    let data = account_models_data(result);
+    Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
+}
+
+async fn test_account_connection<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<AccountTestQuery>,
+) -> Result<Sse<impl Stream<Item = Result<Event, Infallible>>>, AdminError>
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let (account_id, upstream_model) = query.into_command().map_err(map_wire_error)?;
+    let stream = state
+        .admin_services()
+        .accounts()
+        .test_connection(account_id, upstream_model)
+        .await
+        .map_err(map_service_error)?
+        .map(|event| {
+            let event = AccountConnectionTestEvent::from(event);
+            let data = serde_json::to_string(&event.data).unwrap_or_else(|_| "{}".to_owned());
+            Ok(Event::default().data(data))
+        });
+    Ok(Sse::new(stream).keep_alive(KeepAlive::default()))
+}

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

@@ -0,0 +1,81 @@
+//! 管理端账号目录的 HTTP 合同、凭据动作、路由处理与安全响应投影。
+
+use std::{collections::BTreeSet, convert::Infallible, fmt};
+
+use axum::{
+    Router,
+    body::Body,
+    extract::State,
+    http::{HeaderName, HeaderValue, StatusCode, header},
+    response::{
+        IntoResponse, Response,
+        sse::{Event, KeepAlive, Sse},
+    },
+    routing::{get, post},
+};
+use base64::{Engine as _, engine::general_purpose::URL_SAFE_NO_PAD};
+use chrono::{DateTime, FixedOffset, Utc};
+use futures::{Stream, StreamExt as _};
+use gateway_admin::model::{
+    AdminError as AdminServiceError, PageSize,
+    accounts::{
+        AccountConcurrencyLimit, AccountConnectionTestEvent as DomainConnectionTestEvent,
+        AccountCost, AccountGroupFilter, AccountListQuery, AccountModelUsage, AccountSort,
+        AccountSortField, AccountStatus as DomainAccountStatus, AccountUpdateResult, AccountUsage,
+        AccountWeight, AccountsUpdateResult, BatchUpdateAccounts, SortDirection, UpdateAccount,
+    },
+    provider_credentials::{
+        AccountDirectoryItem, AccountDirectoryPage, AccountExportBundle, AccountRefreshResult,
+        AuthorizationStarted, CompleteAuthorization, ConsumeProviderResetCredit,
+        CredentialDeletion, CredentialDeletionResult, CredentialImportResult, CredentialMutation,
+        CredentialMutationResult, ImportCredentials, ProviderDocument, ProviderModels,
+        ProviderProfileActivityInsights, ProviderProfileAvatar, ProviderProfileDailyUsage,
+        ProviderProfileInvocation, ProviderProfileStatistics, ProviderProfileStatisticsSummary,
+        ProviderQuota, ProviderQuotaWindow, ProviderResetCredit, ProviderResetCreditResult,
+        ProviderResetCredits, RotateCredential, StartAuthorization,
+    },
+};
+use gateway_core::{
+    account::{OpaqueProviderData, ProviderAccountId},
+    routing::{AccountGroupId, ProviderKind, UpstreamModelId},
+};
+use serde::{Deserialize, Deserializer, Serialize};
+use serde_json::{Map, Value};
+use uuid::{Uuid, Version};
+
+use super::presenter::{format_compact_number, format_decimal_currency, format_number};
+use super::{
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    PageMeta, WireValidationError,
+};
+
+const DEFAULT_PAGE_SIZE: u32 = 50;
+const MAX_PAGE_SIZE: u32 = 200;
+const MAX_SEARCH_BYTES: usize = 256;
+const MAX_ID_BYTES: usize = 256;
+const MAX_NAME_BYTES: usize = 512;
+const MAX_IMPORT_DATA_BYTES: usize = 64 * 1024 * 1024;
+const MAX_ACCESS_TOKEN_BYTES: usize = 16 * 1024;
+const MAX_REFRESH_TOKEN_BYTES: usize = 64 * 1024;
+const MAX_ID_TOKEN_BYTES: usize = 16 * 1024;
+const MAX_CALLBACK_URL_BYTES: usize = 64 * 1024;
+const MAX_ACCOUNT_DELETE_BATCH: usize = 200;
+const MAX_ACCOUNT_GROUP_BATCH: usize = 1000;
+const MAX_AVATAR_VERSION_BYTES: usize = 32;
+
+mod credentials;
+mod handlers;
+mod presenter;
+mod wire;
+
+pub use credentials::*;
+pub use handlers::{profile_avatar_response, router};
+pub(super) use presenter::quota_window_view;
+pub use wire::*;
+
+use credentials::{
+    AccountProvider, deserialize_required_nullable, parse_account_weight, parse_concurrency_limit,
+    provider_document_value, require_account_id, validate_wire_group_ids,
+};
+use presenter::*;
+use wire::BatchUpdatedAccountsData;

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

@@ -0,0 +1,417 @@
+//! Admin 领域结果到安全 HTTP wire 的展示投影。
+
+use super::*;
+
+pub(super) fn account_page_data(
+    result: AccountDirectoryPage,
+    page: u32,
+    page_size: u16,
+    now: DateTime<Utc>,
+) -> AccountPageData {
+    let total_pages = if result.total == 0 {
+        0
+    } else {
+        u32::try_from(result.total.div_ceil(u64::from(page_size))).unwrap_or(u32::MAX)
+    };
+    AccountPageData {
+        items: result
+            .items
+            .into_iter()
+            .map(|item| account_view(item, now))
+            .collect(),
+        page: PageMeta::new(page, u32::from(page_size), result.total, total_pages),
+        summary: AccountSummaryView {
+            total: result.summary.total,
+            normal: result.summary.normal,
+            quota_exhausted: result.summary.quota_exhausted,
+            rate_limited: result.summary.rate_limited,
+            disabled: result.summary.disabled,
+            error: result.summary.error,
+        },
+    }
+}
+
+pub(super) fn account_refresh_data(
+    result: AccountRefreshResult,
+    now: DateTime<Utc>,
+) -> AccountRefreshData {
+    AccountRefreshData {
+        account: account_view(result.account, now),
+    }
+}
+
+pub(super) fn account_models_data(result: ProviderModels) -> AccountModelsData {
+    AccountModelsData {
+        models: result
+            .models
+            .into_iter()
+            .map(|model| {
+                let id = model.id.to_string();
+                AccountModelView {
+                    label: id.clone(),
+                    id,
+                }
+            })
+            .collect(),
+    }
+}
+
+pub(super) fn account_view(item: AccountDirectoryItem, now: DateTime<Utc>) -> AccountView {
+    let AccountDirectoryItem {
+        account,
+        projection,
+        usage,
+        quota,
+    } = item;
+    let status = projection.status.as_str().to_owned();
+    let rate_limited_until = projection.rate_limited_until.map(DateTime::<Utc>::from);
+    let expires_at = account.access_token_expires_at.as_ref().map(china_rfc3339);
+    let added_at = china_rfc3339(&account.created_at);
+    let updated_at = china_rfc3339(&account.updated_at);
+    let (quota, refresh_token_expires_at) = account_quota_view(quota, rate_limited_until, now);
+    AccountView {
+        id: account.id.clone(),
+        name: account.name,
+        provider: account.provider_kind.to_string(),
+        groups: account
+            .groups
+            .into_iter()
+            .map(|group| AccountGroupRefView {
+                id: group.id.to_string(),
+                name: group.name,
+                color: group.color.as_str().to_owned(),
+                enabled: group.enabled,
+            })
+            .collect(),
+        resource_ref: account.id,
+        email: account.email,
+        account_id: account.upstream_account_id,
+        user_id: account.upstream_user_id,
+        label: None,
+        plan_type: account.plan_type,
+        authentication_kind: account.authentication_kind,
+        has_refresh_token: account.has_refresh_token,
+        status,
+        error_reason: projection
+            .error_reason
+            .map(|reason| reason.as_str().to_owned()),
+        error_message: projection.error_message,
+        enabled: account.enabled,
+        concurrency_limit: account.concurrency_limit.map(|limit| limit.get()),
+        weight: account.weight.get(),
+        access_token_expires_at: expires_at,
+        access_token_expires_at_display: account
+            .access_token_expires_at
+            .as_ref()
+            .map(china_datetime),
+        refresh_token_expires_at,
+        next_refresh_at: account.next_refresh_at.map(|value| china_rfc3339(&value)),
+        added_at,
+        added_at_display: china_datetime(&account.created_at),
+        updated_at,
+        updated_at_display: china_datetime(&account.updated_at),
+        quota,
+        usage: account_usage_view(usage, now),
+    }
+}
+
+pub(super) fn account_quota_view(
+    mut quota: ProviderQuota,
+    rate_limited_until: Option<DateTime<Utc>>,
+    now: DateTime<Utc>,
+) -> (AccountQuotaView, Option<String>) {
+    quota.apply_limit_reached_display();
+    let refresh_token_expires_at = quota
+        .refresh_token_expires_at
+        .map(|value| china_rfc3339(&value));
+    let refreshed_at_display = quota
+        .observed_at
+        .map_or_else(|| "—".to_owned(), |value| relative_time(value, now));
+    let windows = quota.windows.into_iter().map(quota_window_view).collect();
+    let rate_limited_until = rate_limited_until.map(|until| china_datetime(&until));
+    (
+        AccountQuotaView {
+            refreshed_at_display,
+            limit_reached: quota.limit_reached,
+            rate_limited_until,
+            windows,
+        },
+        refresh_token_expires_at,
+    )
+}
+
+pub(crate) fn quota_window_view(window: ProviderQuotaWindow) -> AccountQuotaWindowView {
+    let ProviderQuotaWindow {
+        key,
+        group,
+        label,
+        limit_id,
+        limit_name,
+        role,
+        local_usage_attribution: _,
+        window_seconds,
+        used_percent,
+        reset_at,
+        limit_reached,
+        local_usage,
+        provider_data: _,
+    } = window;
+    let label_display = limit_name
+        .as_ref()
+        .map_or_else(|| label.clone(), |name| format!("{name} · {label}"));
+    AccountQuotaWindowView {
+        label_display,
+        window_label_display: label,
+        key,
+        group,
+        limit_id,
+        limit_name,
+        role: role.map(|value| value.as_str().to_owned()),
+        window_seconds,
+        used_percent,
+        used_percent_display: used_percent
+            .map_or_else(|| "—".to_owned(), |value| format!("{value:.1}%")),
+        limit_reached,
+        local_usage: local_usage.as_ref().map(quota_local_usage),
+        reset_at_display: reset_at.map_or_else(|| "—".to_owned(), |value| china_datetime(&value)),
+    }
+}
+
+pub(super) fn quota_local_usage(usage: &AccountUsage) -> Value {
+    let total_tokens = usage.total_tokens.unwrap_or_default();
+    serde_json::json!({
+        "requestCount": usage.request_count,
+        "requestCountDisplay": format_number(usage.request_count),
+        "inputTokens": usage.input_tokens.unwrap_or_default(),
+        "inputTokensDisplay": display_optional_tokens(usage.input_tokens),
+        "outputTokens": usage.output_tokens.unwrap_or_default(),
+        "outputTokensDisplay": display_optional_tokens(usage.output_tokens),
+        "cachedTokens": usage.cached_tokens.unwrap_or_default(),
+        "cachedTokensDisplay": display_optional_tokens(usage.cached_tokens),
+        "imageInputTokens": usage.image_input_tokens.unwrap_or_default(),
+        "imageInputTokensDisplay": display_optional_tokens(usage.image_input_tokens),
+        "imageOutputTokens": usage.image_output_tokens.unwrap_or_default(),
+        "imageOutputTokensDisplay": display_optional_tokens(usage.image_output_tokens),
+        "imageRequestCount": usage.image_request_count,
+        "imageRequestFailedCount": usage.image_request_failed_count,
+        "totalTokens": total_tokens,
+        "totalTokensDisplay": format_compact_number(total_tokens),
+        "requestBuckets": usage.request_buckets.iter().map(|bucket| serde_json::json!({
+            "bucketStart": bucket.bucket_start,
+            "requestCount": bucket.request_count,
+        })).collect::<Vec<_>>(),
+    })
+}
+
+pub(super) fn account_usage_view(
+    usage: Option<AccountUsage>,
+    now: DateTime<Utc>,
+) -> AccountUsageView {
+    let Some(usage) = usage else {
+        return empty_account_usage();
+    };
+    let known_count = usage
+        .cost_coverage
+        .provider_reported_count
+        .saturating_add(usage.cost_coverage.calculated_count);
+    let cost_estimate_status = if known_count == 0 {
+        "unknown"
+    } else if usage.cost_coverage.unavailable_count > 0 {
+        "partial"
+    } else {
+        "known"
+    };
+    AccountUsageView {
+        request_count: Some(usage.request_count),
+        request_count_display: format_number(usage.request_count),
+        input_tokens: usage.input_tokens,
+        input_tokens_display: display_optional_tokens(usage.input_tokens),
+        output_tokens: usage.output_tokens,
+        output_tokens_display: display_optional_tokens(usage.output_tokens),
+        cached_tokens: usage.cached_tokens,
+        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
+        reasoning_tokens: usage.reasoning_tokens,
+        reasoning_tokens_display: display_optional_tokens(usage.reasoning_tokens),
+        image_input_tokens: usage.image_input_tokens,
+        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
+        image_output_tokens: usage.image_output_tokens,
+        image_output_tokens_display: display_optional_tokens(usage.image_output_tokens),
+        image_request_count: Some(usage.image_request_count),
+        image_request_count_display: format_number(usage.image_request_count),
+        image_request_failed_count: Some(usage.image_request_failed_count),
+        image_request_failed_count_display: format_number(usage.image_request_failed_count),
+        total_tokens: usage.total_tokens,
+        total_tokens_display: display_optional_tokens(usage.total_tokens),
+        created_tokens: usage.cache_write_tokens,
+        created_tokens_display: display_optional_tokens(usage.cache_write_tokens),
+        read_tokens: usage.cached_tokens,
+        read_tokens_display: display_optional_tokens(usage.cached_tokens),
+        last_used_at: usage.last_used_at.map(|value| china_rfc3339(&value)),
+        last_used_at_display: usage
+            .last_used_at
+            .map_or_else(|| "—".to_owned(), |value| relative_time(value, now)),
+        cost_estimate_status: cost_estimate_status.to_owned(),
+        known_cost_count: Some(known_count),
+        partial_cost_count: Some(u64::from(cost_estimate_status == "partial")),
+        unknown_cost_count: Some(usage.cost_coverage.unavailable_count),
+        costs: usage.costs.iter().map(account_currency_cost_view).collect(),
+        models: usage
+            .models
+            .into_iter()
+            .map(|model| account_model_usage_view(model, now))
+            .collect(),
+    }
+}
+
+pub(super) fn account_model_usage_view(
+    usage: AccountModelUsage,
+    now: DateTime<Utc>,
+) -> ModelUsageView {
+    let known_count = usage
+        .cost_coverage
+        .provider_reported_count
+        .saturating_add(usage.cost_coverage.calculated_count);
+    let cost_estimate_status = if known_count == 0 {
+        "unknown"
+    } else if usage.cost_coverage.unavailable_count > 0 {
+        "partial"
+    } else {
+        "known"
+    };
+    let usd = usage
+        .costs
+        .iter()
+        .find(|cost| cost.currency.eq_ignore_ascii_case("USD"));
+    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
+            )
+        },
+        input_tokens: usage.input_tokens,
+        input_tokens_display: display_optional_tokens(usage.input_tokens),
+        output_tokens: usage.output_tokens,
+        output_tokens_display: display_optional_tokens(usage.output_tokens),
+        cached_tokens: usage.cached_tokens,
+        cached_tokens_display: display_optional_tokens(usage.cached_tokens),
+        image_input_tokens: usage.image_input_tokens,
+        image_input_tokens_display: display_optional_tokens(usage.image_input_tokens),
+        image_output_tokens: usage.image_output_tokens,
+        image_output_tokens_display: display_optional_tokens(usage.image_output_tokens),
+        image_request_count: usage.image_request_count,
+        image_request_count_display: format_number(usage.image_request_count),
+        image_request_failed_count: usage.image_request_failed_count,
+        image_request_failed_count_display: format_number(usage.image_request_failed_count),
+        total_tokens: usage.total_tokens,
+        total_tokens_display: display_optional_tokens(usage.total_tokens),
+        billing_amount_usd: usd.map(|cost| cost.amount.as_str().to_owned()),
+        billing_amount_usd_display: usd.map_or_else(
+            || "—".to_owned(),
+            |cost| format_decimal_currency(cost.amount.as_str(), "USD"),
+        ),
+        cost_estimate_status: cost_estimate_status.to_owned(),
+        known_cost_count: known_count,
+        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: china_rfc3339(&usage.last_used_at),
+        last_used_at_display: relative_time(usage.last_used_at, now),
+    }
+}
+
+pub(super) fn account_currency_cost_view(cost: &AccountCost) -> CurrencyCostView {
+    CurrencyCostView {
+        currency: cost.currency.clone(),
+        estimated_amount: cost.amount.as_str().to_owned(),
+        estimated_amount_display: format_decimal_currency(cost.amount.as_str(), &cost.currency),
+    }
+}
+
+pub(super) fn display_optional_tokens(value: Option<u64>) -> String {
+    value.map_or_else(|| "—".to_owned(), format_compact_number)
+}
+
+pub(super) fn empty_account_usage() -> AccountUsageView {
+    AccountUsageView {
+        request_count: None,
+        request_count_display: "—".to_owned(),
+        input_tokens: None,
+        input_tokens_display: "—".to_owned(),
+        output_tokens: None,
+        output_tokens_display: "—".to_owned(),
+        cached_tokens: None,
+        cached_tokens_display: "—".to_owned(),
+        reasoning_tokens: None,
+        reasoning_tokens_display: "—".to_owned(),
+        image_input_tokens: None,
+        image_input_tokens_display: "—".to_owned(),
+        image_output_tokens: None,
+        image_output_tokens_display: "—".to_owned(),
+        image_request_count: None,
+        image_request_count_display: "—".to_owned(),
+        image_request_failed_count: None,
+        image_request_failed_count_display: "—".to_owned(),
+        total_tokens: None,
+        total_tokens_display: "—".to_owned(),
+        created_tokens: None,
+        created_tokens_display: "—".to_owned(),
+        read_tokens: None,
+        read_tokens_display: "—".to_owned(),
+        last_used_at: None,
+        last_used_at_display: "—".to_owned(),
+        cost_estimate_status: "unavailable".to_owned(),
+        known_cost_count: None,
+        partial_cost_count: None,
+        unknown_cost_count: None,
+        costs: Vec::new(),
+        models: Vec::new(),
+    }
+}
+
+pub(super) fn relative_time(value: DateTime<Utc>, now: DateTime<Utc>) -> String {
+    let elapsed = now.signed_duration_since(value);
+    if elapsed.num_seconds() < 0 {
+        return china_datetime(&value);
+    }
+    if elapsed.num_seconds() < 60 {
+        return "刚刚".to_owned();
+    }
+    if elapsed.num_minutes() < 60 {
+        return format!("{} 分钟前", elapsed.num_minutes());
+    }
+    if elapsed.num_hours() < 24 {
+        return format!("{} 小时前", elapsed.num_hours());
+    }
+    format!("{} 天前", elapsed.num_days())
+}
+
+pub(super) fn china_offset() -> FixedOffset {
+    FixedOffset::east_opt(8 * 60 * 60).expect("UTC+8 is a valid fixed offset")
+}
+
+pub(super) fn china_rfc3339(value: &DateTime<Utc>) -> String {
+    value.with_timezone(&china_offset()).to_rfc3339()
+}
+
+pub(super) fn china_datetime(value: &DateTime<Utc>) -> String {
+    value
+        .with_timezone(&china_offset())
+        .format("%Y-%m-%d %H:%M:%S")
+        .to_string()
+}
+
+pub(super) fn map_wire_error(error: WireValidationError) -> AdminError {
+    AdminError::bad_request(format!("{} 字段不合法", error.field()))
+}
+
+pub(super) fn map_service_error(error: AdminServiceError) -> AdminError {
+    super::super::wire::map_admin_service_error(error)
+}

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

@@ -0,0 +1,840 @@
+//! 账号管理请求、响应与查询 wire contract。
+
+use super::*;
+
+/// 账号列表查询参数。
+#[derive(Debug, Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct ListQuery {
+    pub page: Option<u32>,
+    pub page_size: Option<u32>,
+    pub provider: Option<String>,
+    pub group_id: Option<String>,
+    pub search: Option<String>,
+    pub status: Option<String>,
+    pub sort_by: Option<String>,
+    pub sort_direction: Option<String>,
+}
+
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct BatchUpdateAccountsRequest {
+    pub account_ids: Vec<String>,
+    pub enabled: bool,
+    #[serde(deserialize_with = "deserialize_required_nullable")]
+    pub concurrency_limit: Option<u64>,
+    pub weight: u64,
+    pub group_ids: Vec<String>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub(super) struct BatchUpdatedAccountsData {
+    account_ids: Vec<String>,
+    config_revision: u64,
+}
+
+impl From<AccountsUpdateResult> for BatchUpdatedAccountsData {
+    fn from(result: AccountsUpdateResult) -> Self {
+        Self {
+            account_ids: result
+                .account_ids
+                .into_iter()
+                .map(|id| id.to_string())
+                .collect(),
+            config_revision: result.config_revision.get(),
+        }
+    }
+}
+
+impl BatchUpdateAccountsRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        if self.account_ids.is_empty()
+            || self.account_ids.len() > MAX_ACCOUNT_GROUP_BATCH
+            || self
+                .account_ids
+                .iter()
+                .any(|id| require_account_id(id, "accountIds").is_err())
+            || self.account_ids.iter().collect::<BTreeSet<_>>().len() != self.account_ids.len()
+        {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        validate_wire_group_ids(&self.group_ids)?;
+        parse_concurrency_limit(self.concurrency_limit)?;
+        parse_account_weight(self.weight)?;
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<BatchUpdateAccounts, WireValidationError> {
+        self.validate()?;
+        Ok(BatchUpdateAccounts {
+            account_ids: self.account_ids,
+            enabled: self.enabled,
+            concurrency_limit: parse_concurrency_limit(self.concurrency_limit)?,
+            weight: parse_account_weight(self.weight)?,
+            group_ids: validate_wire_group_ids(&self.group_ids)?,
+        })
+    }
+}
+
+impl ListQuery {
+    /// 解析并校验全部 wire 字段，生成 Admin 查询命令。
+    pub fn validate(self) -> Result<AccountListQuery, WireValidationError> {
+        let page = self.page.unwrap_or(1);
+        if page == 0 {
+            return Err(WireValidationError::new("page"));
+        }
+        let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
+        if page_size == 0 || page_size > MAX_PAGE_SIZE {
+            return Err(WireValidationError::new("pageSize"));
+        }
+        let provider_kind = parse_provider(self.provider.as_deref().unwrap_or("all"))?;
+        let group_filter = match self.group_id.as_deref().map(str::trim) {
+            None | Some("") => None,
+            Some("ungrouped") => Some(AccountGroupFilter::Ungrouped),
+            Some(value) => Some(AccountGroupFilter::Group(
+                AccountGroupId::new(value.to_owned())
+                    .map_err(|_| WireValidationError::new("groupId"))?,
+            )),
+        };
+        let search = self
+            .search
+            .map(|value| value.trim().to_owned())
+            .filter(|value| !value.is_empty());
+        if search.as_deref().is_some_and(|value| {
+            value.len() > MAX_SEARCH_BYTES || value.chars().any(char::is_control)
+        }) {
+            return Err(WireValidationError::new("search"));
+        }
+        let status = match self.status.as_deref().map(str::trim) {
+            None | Some("") => None,
+            Some(value) => Some(
+                DomainAccountStatus::parse(&value.to_ascii_lowercase())
+                    .ok_or_else(|| WireValidationError::new("status"))?,
+            ),
+        };
+        let sort = match (self.sort_by.as_deref(), self.sort_direction.as_deref()) {
+            (None, None) => None,
+            (Some(field), Some(direction)) => Some(AccountSort {
+                field: parse_sort_field(field).ok_or_else(|| WireValidationError::new("sortBy"))?,
+                direction: parse_sort_direction(direction)
+                    .ok_or_else(|| WireValidationError::new("sortDirection"))?,
+            }),
+            _ => return Err(WireValidationError::new("sort")),
+        };
+        Ok(AccountListQuery {
+            page,
+            page_size: PageSize::new(
+                u16::try_from(page_size).map_err(|_| WireValidationError::new("pageSize"))?,
+            )
+            .map_err(|_| WireValidationError::new("pageSize"))?,
+            provider_kind,
+            group_filter,
+            search,
+            status,
+            sort,
+        })
+    }
+}
+
+fn parse_provider(value: &str) -> Result<Option<ProviderKind>, WireValidationError> {
+    let value = value.trim();
+    if value.is_empty() || value.eq_ignore_ascii_case("all") {
+        return Ok(None);
+    }
+    ProviderKind::new(value.to_owned())
+        .map(Some)
+        .map_err(|_| WireValidationError::new("provider"))
+}
+
+fn parse_sort_field(value: &str) -> Option<AccountSortField> {
+    match value.trim() {
+        "email" => Some(AccountSortField::Email),
+        "status" => Some(AccountSortField::Status),
+        "planType" => Some(AccountSortField::PlanType),
+        "usage" => Some(AccountSortField::Usage),
+        "lastUsedAt" => Some(AccountSortField::LastUsedAt),
+        "expiresAt" => Some(AccountSortField::ExpiresAt),
+        _ => None,
+    }
+}
+
+fn parse_sort_direction(value: &str) -> Option<SortDirection> {
+    match value.trim().to_ascii_lowercase().as_str() {
+        "asc" => Some(SortDirection::Asc),
+        "desc" => Some(SortDirection::Desc),
+        _ => None,
+    }
+}
+
+/// 账号列表响应数据。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountPageData {
+    pub items: Vec<AccountView>,
+    pub page: PageMeta,
+    pub summary: AccountSummaryView,
+}
+
+/// 账号概览计数。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountSummaryView {
+    pub total: u64,
+    pub normal: u64,
+    pub quota_exhausted: u64,
+    pub rate_limited: u64,
+    pub disabled: u64,
+    pub error: u64,
+}
+
+/// 一条安全账号视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountView {
+    pub id: String,
+    pub name: String,
+    pub provider: String,
+    pub groups: Vec<AccountGroupRefView>,
+    pub resource_ref: String,
+    pub email: Option<String>,
+    pub account_id: Option<String>,
+    pub user_id: Option<String>,
+    pub label: Option<String>,
+    pub plan_type: Option<String>,
+    pub authentication_kind: String,
+    pub has_refresh_token: bool,
+    pub status: String,
+    /// `status == "error"` 时的具体原因；其余状态为 `null`。
+    pub error_reason: Option<String>,
+    /// 最近一次失败的上游错误描述；仅错误状态存在。
+    pub error_message: Option<String>,
+    pub enabled: bool,
+    pub concurrency_limit: Option<u32>,
+    pub weight: u16,
+    pub access_token_expires_at: Option<String>,
+    pub access_token_expires_at_display: Option<String>,
+    pub refresh_token_expires_at: Option<String>,
+    pub next_refresh_at: Option<String>,
+    pub added_at: String,
+    pub added_at_display: String,
+    pub updated_at: String,
+    pub updated_at_display: String,
+    pub quota: AccountQuotaView,
+    pub usage: AccountUsageView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountGroupRefView {
+    pub id: String,
+    pub name: String,
+    pub color: String,
+    pub enabled: bool,
+}
+
+/// Provider quota 安全视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountQuotaView {
+    pub refreshed_at_display: String,
+    pub limit_reached: bool,
+    /// 429 临时限流（Redis 冷却）到期时间展示；非限流中为 `null`。
+    pub rate_limited_until: Option<String>,
+    pub windows: Vec<AccountQuotaWindowView>,
+}
+
+/// 一个 quota 时间窗口。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountQuotaWindowView {
+    pub key: String,
+    pub group: String,
+    pub limit_id: Option<String>,
+    pub limit_name: Option<String>,
+    pub role: Option<String>,
+    pub window_seconds: Option<u64>,
+    pub label_display: String,
+    pub window_label_display: String,
+    pub used_percent: Option<f64>,
+    pub used_percent_display: String,
+    pub limit_reached: bool,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub local_usage: Option<serde_json::Value>,
+    pub reset_at_display: String,
+}
+
+/// 账号观测用量。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountUsageView {
+    pub request_count: Option<u64>,
+    pub request_count_display: String,
+    pub input_tokens: Option<u64>,
+    pub input_tokens_display: String,
+    pub output_tokens: Option<u64>,
+    pub output_tokens_display: String,
+    pub cached_tokens: Option<u64>,
+    pub cached_tokens_display: String,
+    pub reasoning_tokens: Option<u64>,
+    pub reasoning_tokens_display: String,
+    pub image_input_tokens: Option<u64>,
+    pub image_input_tokens_display: String,
+    pub image_output_tokens: Option<u64>,
+    pub image_output_tokens_display: String,
+    pub image_request_count: Option<u64>,
+    pub image_request_count_display: String,
+    pub image_request_failed_count: Option<u64>,
+    pub image_request_failed_count_display: String,
+    pub total_tokens: Option<u64>,
+    pub total_tokens_display: String,
+    pub created_tokens: Option<u64>,
+    pub created_tokens_display: String,
+    pub read_tokens: Option<u64>,
+    pub read_tokens_display: String,
+    pub last_used_at: Option<String>,
+    pub last_used_at_display: String,
+    pub cost_estimate_status: String,
+    pub known_cost_count: Option<u64>,
+    pub partial_cost_count: Option<u64>,
+    pub unknown_cost_count: Option<u64>,
+    pub costs: Vec<CurrencyCostView>,
+    pub models: Vec<ModelUsageView>,
+}
+
+/// 凭据在单个上游模型上的观测用量。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct ModelUsageView {
+    pub model: String,
+    pub request_count: u64,
+    pub request_count_display: String,
+    pub success_rate: Option<f64>,
+    pub success_rate_display: String,
+    pub input_tokens: Option<u64>,
+    pub input_tokens_display: String,
+    pub output_tokens: Option<u64>,
+    pub output_tokens_display: String,
+    pub cached_tokens: Option<u64>,
+    pub cached_tokens_display: String,
+    pub image_input_tokens: Option<u64>,
+    pub image_input_tokens_display: String,
+    pub image_output_tokens: Option<u64>,
+    pub image_output_tokens_display: String,
+    pub image_request_count: u64,
+    pub image_request_count_display: String,
+    pub image_request_failed_count: u64,
+    pub image_request_failed_count_display: String,
+    pub total_tokens: Option<u64>,
+    pub total_tokens_display: String,
+    pub billing_amount_usd: Option<String>,
+    pub billing_amount_usd_display: String,
+    pub cost_estimate_status: String,
+    pub known_cost_count: u64,
+    pub partial_cost_count: u64,
+    pub unknown_cost_count: u64,
+    pub costs: Vec<CurrencyCostView>,
+    pub last_used_at: String,
+    pub last_used_at_display: String,
+}
+
+/// 单一货币的可查询成本。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct CurrencyCostView {
+    pub currency: String,
+    pub estimated_amount: String,
+    pub estimated_amount_display: String,
+}
+
+/// 账号详情类 GET 的固定 ID query。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountIdQuery {
+    pub account_id: String,
+}
+
+impl AccountIdQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 头像 GET 的固定 query；`version` 只参与浏览器缓存键，不进入上游请求。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountProfileAvatarQuery {
+    pub account_id: String,
+    pub version: Option<String>,
+}
+
+impl AccountProfileAvatarQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.version.as_deref().is_some_and(|version| {
+            version.is_empty()
+                || version.len() > MAX_AVATAR_VERSION_BYTES
+                || !version.bytes().all(|byte| byte.is_ascii_alphanumeric())
+        }) {
+            return Err(WireValidationError::new("version"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 敏感导出的固定 query；IDs 使用逗号分隔，禁止隐式导出全部账号。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountExportQuery {
+    pub account_ids: String,
+    pub confirm: String,
+}
+
+impl AccountExportQuery {
+    pub fn into_ids(self) -> Result<Vec<ProviderAccountId>, WireValidationError> {
+        if self.confirm != "export_sensitive_accounts" {
+            return Err(WireValidationError::new("confirm"));
+        }
+        let ids = self
+            .account_ids
+            .split(',')
+            .map(str::trim)
+            .filter(|id| !id.is_empty())
+            .map(ToOwned::to_owned)
+            .collect::<Vec<_>>();
+        if ids.is_empty()
+            || ids.len() > 200
+            || ids
+                .iter()
+                .any(|id| require_account_id(id, "accountIds").is_err())
+        {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        let unique = ids.iter().collect::<BTreeSet<_>>();
+        if unique.len() != ids.len() {
+            return Err(WireValidationError::new("accountIds"));
+        }
+        ids.into_iter()
+            .map(|id| {
+                ProviderAccountId::new(id).map_err(|_| WireValidationError::new("accountIds"))
+            })
+            .collect()
+    }
+}
+
+/// 账号运行期动作。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountActionRequest {
+    pub account_id: String,
+}
+
+impl AccountActionRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_id(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 主动额度重置卡消费请求。幂等键由 UI 生成并在不确定重试时复用，与官方一致。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountResetCreditConsumeRequest {
+    pub account_id: String,
+    #[serde(default)]
+    pub credit_id: Option<String>,
+    pub redeem_request_id: String,
+}
+
+impl AccountResetCreditConsumeRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.credit_id.as_deref().is_some_and(|value| {
+            let value = value.trim();
+            value.is_empty() || value.len() > 512 || value.chars().any(char::is_control)
+        }) {
+            return Err(WireValidationError::new("creditId"));
+        }
+        let value = self.redeem_request_id.trim();
+        let redeem_request_id =
+            Uuid::parse_str(value).map_err(|_| WireValidationError::new("redeemRequestId"))?;
+        if redeem_request_id.get_version() != Some(Version::Random)
+            || redeem_request_id.hyphenated().to_string() != value
+        {
+            return Err(WireValidationError::new("redeemRequestId"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(self) -> Result<ConsumeProviderResetCredit, WireValidationError> {
+        self.validate()?;
+        Ok(ConsumeProviderResetCredit {
+            account_id: ProviderAccountId::new(self.account_id)
+                .map_err(|_| WireValidationError::new("accountId"))?,
+            credit_id: self.credit_id.map(|value| value.trim().to_owned()),
+            redeem_request_id: Uuid::parse_str(&self.redeem_request_id)
+                .map_err(|_| WireValidationError::new("redeemRequestId"))?,
+        })
+    }
+}
+
+/// 手工 OAuth 刷新会变更持久 credential。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountRefreshRequest {
+    pub account_id: String,
+}
+
+impl AccountRefreshRequest {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")
+    }
+
+    pub(super) fn into_command(self) -> Result<ProviderAccountId, WireValidationError> {
+        self.validate()?;
+        ProviderAccountId::new(self.account_id).map_err(|_| WireValidationError::new("accountId"))
+    }
+}
+
+/// 连接测试 query；测试仍经唯一 Core/Provider 模型请求路径执行。
+#[derive(Debug, Clone, Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+pub struct AccountTestQuery {
+    pub account_id: String,
+    pub model_id: String,
+}
+
+impl AccountTestQuery {
+    pub fn validate(&self) -> Result<(), WireValidationError> {
+        require_account_id(&self.account_id, "accountId")?;
+        if self.model_id.trim().is_empty() || self.model_id.chars().any(char::is_control) {
+            return Err(WireValidationError::new("modelId"));
+        }
+        Ok(())
+    }
+
+    pub(super) fn into_command(
+        self,
+    ) -> Result<(ProviderAccountId, UpstreamModelId), WireValidationError> {
+        self.validate()?;
+        Ok((
+            ProviderAccountId::new(self.account_id)
+                .map_err(|_| WireValidationError::new("accountId"))?,
+            UpstreamModelId::new(self.model_id).map_err(|_| WireValidationError::new("modelId"))?,
+        ))
+    }
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountModelView {
+    pub id: String,
+    pub label: String,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountModelsData {
+    pub models: Vec<AccountModelView>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountRefreshData {
+    pub account: AccountView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+pub struct AccountQuotaData {
+    pub account: AccountView,
+}
+
+/// Provider 官方个人资料统计响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileStatisticsData {
+    pub display_name: Option<String>,
+    pub username: Option<String>,
+    pub image_url: Option<String>,
+    pub has_stats_error: bool,
+    pub summary: AccountProfileStatisticsSummaryView,
+    pub daily_usage: Option<Vec<AccountProfileDailyUsageView>>,
+    pub activity_insights: AccountProfileActivityInsightsView,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileStatisticsSummaryView {
+    pub total_text_tokens: Option<u64>,
+    pub peak_tokens: Option<u64>,
+    pub longest_task_duration_ms: Option<u64>,
+    pub current_streak_days: Option<u64>,
+    pub longest_streak_days: Option<u64>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileDailyUsageView {
+    pub date: String,
+    pub tokens: u64,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileActivityInsightsView {
+    pub fast_mode_percent: Option<f64>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_effort_percent: Option<f64>,
+    pub skills_explored: Option<u64>,
+    pub total_skills_used: Option<u64>,
+    pub total_threads: Option<u64>,
+    pub invocations: Option<Vec<AccountProfileInvocationView>>,
+}
+
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountProfileInvocationView {
+    #[serde(rename = "type")]
+    pub invocation_type: String,
+    pub plugin_id: Option<String>,
+    pub plugin_name: Option<String>,
+    pub skill_id: Option<String>,
+    pub skill_name: Option<String>,
+    pub usage_count: Option<u64>,
+}
+
+impl From<ProviderProfileStatistics> for AccountProfileStatisticsData {
+    fn from(statistics: ProviderProfileStatistics) -> Self {
+        Self {
+            display_name: statistics.display_name,
+            username: statistics.username,
+            image_url: statistics.image_url,
+            has_stats_error: statistics.has_stats_error,
+            summary: profile_statistics_summary_view(statistics.summary),
+            daily_usage: statistics
+                .daily_usage
+                .map(|daily| daily.into_iter().map(profile_daily_usage_view).collect()),
+            activity_insights: profile_activity_insights_view(statistics.activity_insights),
+        }
+    }
+}
+
+const fn profile_statistics_summary_view(
+    summary: ProviderProfileStatisticsSummary,
+) -> AccountProfileStatisticsSummaryView {
+    AccountProfileStatisticsSummaryView {
+        total_text_tokens: summary.total_text_tokens,
+        peak_tokens: summary.peak_tokens,
+        longest_task_duration_ms: summary.longest_task_duration_ms,
+        current_streak_days: summary.current_streak_days,
+        longest_streak_days: summary.longest_streak_days,
+    }
+}
+
+fn profile_daily_usage_view(daily: ProviderProfileDailyUsage) -> AccountProfileDailyUsageView {
+    AccountProfileDailyUsageView {
+        date: daily.date.to_string(),
+        tokens: daily.tokens,
+    }
+}
+
+fn profile_activity_insights_view(
+    insights: ProviderProfileActivityInsights,
+) -> AccountProfileActivityInsightsView {
+    AccountProfileActivityInsightsView {
+        fast_mode_percent: insights.fast_mode_percent,
+        reasoning_effort: insights.reasoning_effort,
+        reasoning_effort_percent: insights.reasoning_effort_percent,
+        skills_explored: insights.skills_explored,
+        total_skills_used: insights.total_skills_used,
+        total_threads: insights.total_threads,
+        invocations: insights.invocations.map(|invocations| {
+            invocations
+                .into_iter()
+                .map(profile_invocation_view)
+                .collect()
+        }),
+    }
+}
+
+fn profile_invocation_view(invocation: ProviderProfileInvocation) -> AccountProfileInvocationView {
+    AccountProfileInvocationView {
+        invocation_type: invocation.invocation_type,
+        plugin_id: invocation.plugin_id,
+        plugin_name: invocation.plugin_name,
+        skill_id: invocation.skill_id,
+        skill_name: invocation.skill_name,
+        usage_count: invocation.usage_count,
+    }
+}
+
+/// 主动额度重置卡列表响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditsData {
+    pub available_count: u64,
+    pub credits: Vec<AccountResetCreditView>,
+}
+
+/// 一张安全主动额度重置卡视图。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditView {
+    pub id: String,
+    pub status: Option<String>,
+    pub title: Option<String>,
+    pub expires_at: Option<String>,
+    pub reset_type: Option<String>,
+}
+
+/// 主动额度重置卡消费响应。
+#[derive(Debug, Clone, Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct AccountResetCreditResultData {
+    pub code: String,
+    pub credit: Option<AccountResetCreditView>,
+}
+
+impl From<ProviderResetCredit> for AccountResetCreditView {
+    fn from(credit: ProviderResetCredit) -> Self {
+        Self {
+            id: credit.id,
+            status: credit.status,
+            title: credit.title,
+            expires_at: credit.expires_at.map(|value| value.to_rfc3339()),
+            reset_type: credit.reset_type,
+        }
+    }
+}
+
+impl From<ProviderResetCredits> for AccountResetCreditsData {
+    fn from(credits: ProviderResetCredits) -> Self {
+        Self {
+            available_count: credits.available_count,
+            credits: credits
+                .credits
+                .into_iter()
+                .map(AccountResetCreditView::from)
+                .collect(),
+        }
+    }
+}
+
+impl From<ProviderResetCreditResult> for AccountResetCreditResultData {
+    fn from(result: ProviderResetCreditResult) -> Self {
+        Self {
+            code: result.code,
+            credit: result.credit.map(AccountResetCreditView::from),
+        }
+    }
+}
+
+/// Provider-owned 明文导出文档；Debug 永远不输出内部 JSON。
+#[derive(Serialize)]
+#[serde(transparent)]
+pub struct AccountExportData(Value);
+
+impl AccountExportData {
+    #[must_use]
+    pub const fn new(value: Value) -> Self {
+        Self(value)
+    }
+
+    pub(super) fn from_result(bundle: AccountExportBundle) -> Self {
+        let documents = bundle
+            .documents
+            .into_iter()
+            .map(|document| {
+                serde_json::json!({
+                    "provider": document.provider_kind.to_string(),
+                    "document": provider_document_value(document.document),
+                })
+            })
+            .collect::<Vec<_>>();
+        Self::new(serde_json::json!({
+            "exportedAt": bundle.exported_at.to_rfc3339(),
+            "documents": documents,
+        }))
+    }
+}
+
+impl fmt::Debug for AccountExportData {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter.write_str("AccountExportData(<redacted>)")
+    }
+}
+
+pub struct AccountConnectionTestEvent {
+    pub data: Value,
+}
+
+impl From<DomainConnectionTestEvent> for AccountConnectionTestEvent {
+    fn from(event: DomainConnectionTestEvent) -> Self {
+        let data = match event {
+            DomainConnectionTestEvent::Started { model } => serde_json::json!({
+                "type": "test_start",
+                "model": model,
+                "text": "正在连接上游 Responses"
+            }),
+            DomainConnectionTestEvent::Request {
+                model,
+                input_text,
+                stream,
+                store,
+            } => serde_json::json!({
+                "type": "request",
+                "payload": {
+                    "model": model,
+                    "input": [{
+                        "role": "user",
+                        "content": [{ "type": "input_text", "text": input_text }]
+                    }],
+                    "stream": stream,
+                    "store": store
+                }
+            }),
+            DomainConnectionTestEvent::Content { text } => {
+                serde_json::json!({ "type": "content", "text": text })
+            }
+            DomainConnectionTestEvent::Completed => serde_json::json!({
+                "type": "test_complete",
+                "success": true
+            }),
+            DomainConnectionTestEvent::Failed {
+                source,
+                gateway_error_code,
+                send_state,
+                message,
+                provider_error_code,
+                provider_error_type,
+                upstream_status,
+                upstream_content_type,
+                upstream_body,
+            } => serde_json::json!({
+                "type": "error",
+                "source": source.as_str(),
+                "gatewayErrorCode": gateway_error_code.as_str(),
+                "sendState": send_state.map(gateway_core::upstream::UpstreamSendState::as_str),
+                "error": message,
+                "providerErrorCode": provider_error_code,
+                "providerErrorType": provider_error_type,
+                "upstreamStatus": upstream_status,
+                "upstreamContentType": upstream_content_type,
+                "upstreamBody": upstream_body
+            }),
+        };
+        Self { data }
+    }
+}

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

@@ -3,7 +3,7 @@
 use std::fmt;
 
 use axum::{
-    Json, Router,
+    Router,
     extract::{FromRequestParts, State},
     http::{HeaderMap, HeaderValue, StatusCode, header::SET_COOKIE, request::Parts},
     response::{IntoResponse, Response},
@@ -16,7 +16,7 @@ use gateway_admin::{
 use serde::{Deserialize, Serialize};
 use tower_http::request_id::RequestId;
 
-use super::{AdminEnvelope, AdminError, AdminResponse};
+use super::{AdminEnvelope, AdminError, AdminJson, AdminResponse};
 
 const REQUEST_ID_HEADER: &str = "x-request-id";
 const ADMIN_SESSION_COOKIE: &str = "cpr_admin_session";
@@ -37,11 +37,6 @@ impl AdminAuth {
     pub const fn context(&self) -> &AdminRequestContext {
         &self.context
     }
-
-    #[must_use]
-    pub fn into_context(self) -> AdminRequestContext {
-        self.context
-    }
 }
 
 impl<S> FromRequestParts<S> for AdminAuth
@@ -52,8 +47,7 @@ where
 
     async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
         let principal = require_admin_auth(state, &parts.headers).await?;
-        let request_id = admin_request_id(parts)
-            .ok_or_else(|| AdminError::internal("Missing admin request context"))?;
+        let request_id = admin_request_id(parts).ok_or_else(AdminError::internal)?;
         Ok(Self {
             context: AdminRequestContext {
                 principal,
@@ -90,7 +84,7 @@ where
     {
         Ok(Some(admin_user_id)) => Ok(admin_user_id),
         Ok(None) => Err(AdminError::admin_session_required()),
-        Err(_) => Err(AdminError::internal("Failed to validate admin session")),
+        Err(_) => Err(AdminError::internal()),
     }
 }
 
@@ -107,7 +101,7 @@ where
         {
             Ok(true) => Ok(AdminPrincipal::ApiKey),
             Ok(false) => Err(AdminError::invalid_admin_api_key()),
-            Err(_) => Err(AdminError::internal("Failed to validate admin API key")),
+            Err(_) => Err(AdminError::internal()),
         };
     }
 
@@ -209,7 +203,7 @@ where
 
 async fn login<S>(
     State(state): State<S>,
-    Json(payload): Json<AdminLoginRequest>,
+    AdminJson(payload): AdminJson<AdminLoginRequest>,
 ) -> Result<Response, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -232,8 +226,7 @@ where
     );
     response.headers_mut().insert(
         SET_COOKIE,
-        HeaderValue::from_str(&cookie)
-            .map_err(|_| AdminError::internal("Failed to create admin session cookie"))?,
+        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
     );
     Ok(response)
 }
@@ -250,7 +243,7 @@ where
         .auth()
         .validate_session(admin_session_cookie(&headers).as_deref())
         .await
-        .map_err(|_| AdminError::internal("Failed to validate admin session"))?;
+        .map_err(|_| AdminError::internal())?;
     Ok(AdminResponse::new(
         StatusCode::OK,
         AdminEnvelope::ok(AdminSessionStatusData::new(authenticated)),
@@ -270,8 +263,7 @@ where
     let cookie = format!("{ADMIN_SESSION_COOKIE}=; {ADMIN_SESSION_COOKIE_ATTRS}; Max-Age=0");
     response.headers_mut().insert(
         SET_COOKIE,
-        HeaderValue::from_str(&cookie)
-            .map_err(|_| AdminError::internal("Failed to clear admin session cookie"))?,
+        HeaderValue::from_str(&cookie).map_err(|_| AdminError::internal())?,
     );
     Ok(response)
 }
@@ -287,6 +279,6 @@ fn admin_session_cookie(headers: &HeaderMap) -> Option<String> {
 fn map_login_error(error: LoginError) -> AdminError {
     match error {
         LoginError::InvalidCredentials => AdminError::invalid_admin_credentials(),
-        LoginError::Unavailable => AdminError::internal("Failed to create admin session"),
+        LoginError::Unavailable => AdminError::internal(),
     }
 }

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

@@ -3,8 +3,8 @@
 //! 路径统一位于 `/api/admin/settings/backups/*`，内部由独立 `BackupService` 承担业务。
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::StatusCode,
     response::IntoResponse,
     routing::{get, post},
@@ -18,8 +18,8 @@ use secrecy::{ExposeSecret as _, SecretString};
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminPageData, AdminResponse, AdminSessionState,
-    PageMeta, wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminPageData, AdminQuery, AdminResponse,
+    AdminSessionState, PageMeta, wire::map_admin_service_error,
 };
 
 /// 备份设置视图；`secretAccessKey` 返回已保存的明文凭据，由前端掩码显示。
@@ -256,7 +256,7 @@ where
 async fn update_backup_storage<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<UpdateBackupStorageRequest>,
+    AdminJson(request): AdminJson<UpdateBackupStorageRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -304,7 +304,7 @@ where
 async fn update_backup_schedule<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<UpdateBackupScheduleRequest>,
+    AdminJson(request): AdminJson<UpdateBackupScheduleRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -331,28 +331,28 @@ where
 async fn backup_records<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<BackupRecordsQuery>,
+    AdminQuery(query): AdminQuery<BackupRecordsQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
     let page_size = gateway_admin::model::PageSize::new(query.page_size.unwrap_or(20))
-        .map_err(|_| AdminError::bad_request("Invalid pageSize"))?;
+        .map_err(|_| AdminError::bad_request("pageSize 不合法"))?;
     let page = query.page.unwrap_or(1);
     if page == 0 {
-        return Err(AdminError::bad_request("Invalid page"));
+        return Err(AdminError::bad_request("page 不合法"));
     }
     let status = match query.status.as_deref() {
         None => None,
         Some(value) => BackupStatus::parse(value)
             .map(Some)
-            .ok_or_else(|| AdminError::bad_request("Invalid status"))?,
+            .ok_or_else(|| AdminError::bad_request("status 不合法"))?,
     };
     let trigger = match query.trigger.as_deref() {
         None => None,
         Some(value) => BackupTriggerKind::parse(value)
             .map(Some)
-            .ok_or_else(|| AdminError::bad_request("Invalid trigger"))?,
+            .ok_or_else(|| AdminError::bad_request("trigger 不合法"))?,
     };
     let domain_query = gateway_admin::model::backup::BackupRecordListQuery {
         page,
@@ -386,7 +386,7 @@ where
 async fn create_backup<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    body: Option<Json<CreateBackupRequest>>,
+    body: Option<AdminJson<CreateBackupRequest>>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -417,7 +417,7 @@ pub struct CreateBackupRequest {
 async fn download_backup_url<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<BackupIdRequest>,
+    AdminJson(request): AdminJson<BackupIdRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -437,7 +437,7 @@ where
 async fn delete_backup<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<BackupIdRequest>,
+    AdminJson(request): AdminJson<BackupIdRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -455,5 +455,5 @@ where
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Backup service unavailable")
+    map_admin_service_error(error)
 }

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

@@ -17,16 +17,16 @@ use gateway_core::{
 use serde::{Deserialize, Serialize};
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::{HeaderValue, StatusCode, header::CACHE_CONTROL},
     response::{IntoResponse, Response},
     routing::{get, post},
 };
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, WireValidationError,
-    wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    WireValidationError, wire::map_admin_service_error,
 };
 
 const MAX_CURSOR_BYTES: usize = 512;
@@ -669,7 +669,7 @@ where
 async fn list_client_keys<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<ListClientKeysQuery>,
+    AdminQuery(query): AdminQuery<ListClientKeysQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -680,15 +680,14 @@ where
         .list(query.into_command().map_err(map_wire_error)?)
         .await
         .map_err(map_service_error)?;
-    let data = ClientKeyListData::try_from(result)
-        .map_err(|_| AdminError::internal("Failed to encode client key cursor"))?;
+    let data = ClientKeyListData::try_from(result).map_err(|_| AdminError::internal())?;
     Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
 }
 
 async fn create_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<CreateClientKeyRequest>,
+    AdminJson(payload): AdminJson<CreateClientKeyRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -709,7 +708,7 @@ where
 async fn reveal_client_key<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<ClientKeyIdQuery>,
+    AdminQuery(query): AdminQuery<ClientKeyIdQuery>,
 ) -> Result<Response, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -735,7 +734,7 @@ where
 async fn update_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<UpdateClientKeyRequest>,
+    AdminJson(payload): AdminJson<UpdateClientKeyRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -753,7 +752,7 @@ where
 async fn disable_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyMutationRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -774,7 +773,7 @@ where
 async fn enable_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyMutationRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -795,7 +794,7 @@ where
 async fn delete_client_key<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(payload): Json<ClientKeyMutationRequest>,
+    AdminJson(payload): AdminJson<ClientKeyMutationRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -822,13 +821,14 @@ fn mutation_response(
 
 fn map_wire_error(error: WireValidationError) -> AdminError {
     match error.field() {
-        "cursor" => AdminError::bad_request("Invalid client key cursor"),
-        "clientKeyRevealNotFound" => AdminError::not_found("Client API key was not found"),
-        "clientKeyMutationNotFound" => AdminError::not_found("client API key was not found"),
-        _ => AdminError::bad_request("Invalid client API key request"),
+        "cursor" => AdminError::bad_request("Client API Key 游标不合法"),
+        "clientKeyRevealNotFound" | "clientKeyMutationNotFound" => {
+            AdminError::not_found("Client API Key 不存在")
+        }
+        _ => AdminError::bad_request("Client API Key 请求不合法"),
     }
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Configuration repository unavailable")
+    map_admin_service_error(error)
 }

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

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

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

@@ -5,6 +5,7 @@ use axum::{
     http::{HeaderValue, header},
     middleware,
     response::Response,
+    routing::any,
 };
 
 pub mod account_groups;
@@ -12,6 +13,7 @@ pub mod accounts;
 pub mod auth;
 pub mod backups;
 pub mod client_keys;
+mod extract;
 pub mod observability;
 pub mod presenter;
 pub mod settings;
@@ -19,6 +21,7 @@ pub mod system;
 pub mod wire;
 
 pub use auth::{AdminAuth, AdminSessionState};
+pub use extract::{AdminJson, AdminQuery};
 pub use wire::{
     ADMIN_OK_CODE, ADMIN_OK_MESSAGE, AdminEnvelope, AdminError, AdminErrorBody, AdminErrorCode,
     AdminPageData, AdminResponse, PageMeta, WireValidationError,
@@ -38,12 +41,24 @@ where
         .merge(observability::router::<S>())
         .merge(settings::router::<S>())
         .merge(system::router::<S>())
+        .method_not_allowed_fallback(method_not_allowed)
+        .route("/api/admin", any(admin_not_found))
+        .route("/api/admin/{*path}", any(admin_not_found))
         .layer(middleware::map_response(no_store))
 }
 
+async fn method_not_allowed() -> AdminError {
+    AdminError::method_not_allowed()
+}
+
+async fn admin_not_found() -> AdminError {
+    AdminError::admin_route_not_found()
+}
+
 async fn no_store(mut response: Response) -> Response {
     response
         .headers_mut()
-        .insert(header::CACHE_CONTROL, HeaderValue::from_static("no-store"));
+        .entry(header::CACHE_CONTROL)
+        .or_insert(HeaderValue::from_static("no-store"));
     response
 }

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

@@ -1,15 +1,8 @@
 //! Dashboard、用量与诊断查询的 wire 映射和固定路由。
 
-use std::{collections::BTreeMap, num::NonZeroU32};
+use std::collections::BTreeMap;
 
-use axum::{
-    Router,
-    extract::{Query, State},
-    http::StatusCode,
-    response::IntoResponse,
-    routing::get,
-};
-use base64::engine::general_purpose::URL_SAFE_NO_PAD;
+use axum::{Router, extract::State, http::StatusCode, response::IntoResponse, routing::get};
 use chrono::{DateTime, Duration, Utc};
 use gateway_admin::model::{PageSize as DomainPageSize, observability as domain};
 use serde::{Deserialize, Serialize};
@@ -17,7 +10,7 @@ use serde_json::Value;
 
 use super::presenter::{format_compact_number, format_decimal_currency, format_number};
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, PageMeta,
+    AdminAuth, AdminEnvelope, AdminError, AdminQuery, AdminResponse, AdminSessionState,
     WireValidationError, wire::map_admin_service_error,
 };
 

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

@@ -17,6 +17,21 @@ pub(crate) fn display_duration(value: Option<u64>) -> String {
     }
 }
 
+fn display_duration_f64(value: Option<f64>) -> String {
+    let Some(value) = value.filter(|value| value.is_finite() && *value >= 0.0) else {
+        return "—".to_owned();
+    };
+    if value < 1_000.0 {
+        format!("{value:.0} ms")
+    } else if value < 60_000.0 {
+        format!("{:.2} s", value / 1_000.0)
+    } else if value < 3_600_000.0 {
+        format!("{:.1} min", value / 60_000.0)
+    } else {
+        format!("{:.1} h", value / 3_600_000.0)
+    }
+}
+
 pub(crate) fn display_rate(value: f64) -> String {
     if value.is_finite() {
         format!("{:.1}%", value * 100.0)
@@ -25,6 +40,10 @@ pub(crate) fn display_rate(value: f64) -> String {
     }
 }
 
+fn basis_points_rate(value: u64) -> f64 {
+    value as f64 / 10_000.0
+}
+
 pub(crate) fn china_datetime(value: &DateTime<Utc>) -> String {
     (*value + Duration::hours(8))
         .format("%Y-%m-%d %H:%M:%S")
@@ -127,6 +146,43 @@ pub(crate) fn token_details(record: &domain::UsageRecord) -> TokenDetailsView {
     }
 }
 
+pub(crate) fn usage_list_token_details(record: &domain::UsageListRecord) -> TokenDetailsView {
+    TokenDetailsView {
+        input_tokens: record.input_tokens,
+        output_tokens: record.output_tokens,
+        cached_tokens: record.cached_tokens,
+        cache_write_tokens: record.cache_write_tokens,
+        reasoning_tokens: record.reasoning_tokens,
+        image_input_tokens: record.image_input_tokens,
+        image_output_tokens: record.image_output_tokens,
+        total_tokens: record.total_tokens,
+        input_tokens_display: record
+            .input_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+        output_tokens_display: record
+            .output_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+        cached_tokens_display: record
+            .cached_tokens
+            .map_or_else(|| "-".to_owned(), format_compact_number),
+        cache_write_tokens_display: record
+            .cache_write_tokens
+            .map_or_else(|| "-".to_owned(), format_compact_number),
+        reasoning_tokens_display: record
+            .reasoning_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+        image_input_tokens_display: record
+            .image_input_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+        image_output_tokens_display: record
+            .image_output_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+        total_tokens_display: record
+            .total_tokens
+            .map_or_else(|| "-".to_owned(), format_number),
+    }
+}
+
 pub(crate) fn format_money(cost: &domain::CurrencyCost) -> String {
     format_decimal_currency(cost.amount.as_str(), &cost.currency)
 }
@@ -142,20 +198,32 @@ pub(crate) fn format_service_tier(service_tier: Option<&str>) -> String {
     match service_tier {
         Some("priority" | "fast") => "Fast".to_owned(),
         Some("flex") => "Flex".to_owned(),
-        Some("default") | None => "Default".to_owned(),
-        Some(other) => other.to_owned(),
+        Some("default" | "standard") | None => "Standard".to_owned(),
+        Some(other) => capitalize_first(other),
     }
 }
 
+fn capitalize_first(value: &str) -> String {
+    let mut chars = value.chars();
+    chars
+        .next()
+        .map(|first| first.to_uppercase().chain(chars).collect())
+        .unwrap_or_default()
+}
+
 pub(crate) fn billing_view(billing: Option<&domain::UsageBilling>) -> Option<BillingView> {
     match billing? {
-        domain::UsageBilling::Total { total, .. } => Some(BillingView {
+        domain::UsageBilling::Total { source, total } => Some(BillingView {
             input_amount_display: "—".to_owned(),
             output_amount_display: "—".to_owned(),
             cache_read_amount_display: "—".to_owned(),
             cache_write_amount_display: "—".to_owned(),
             standard_amount_display: "—".to_owned(),
-            total_amount_display: format_money(total),
+            total_amount_display: if source == "calculated" {
+                format!("≈ {}", format_money(total))
+            } else {
+                format_money(total)
+            },
             input_price_display: "—".to_owned(),
             output_price_display: "—".to_owned(),
             cache_read_price_display: "—".to_owned(),
@@ -180,6 +248,57 @@ pub(crate) fn billing_view(billing: Option<&domain::UsageBilling>) -> Option<Bil
     }
 }
 
+pub(crate) fn usage_list_record_view(record: domain::UsageListRecord) -> UsageListRecordView {
+    let token_details = usage_list_token_details(&record);
+    let billing = billing_view(record.billing.as_ref());
+    let created_at_display = china_datetime(&record.started_at);
+    let model = record
+        .upstream_model_id
+        .clone()
+        .or_else(|| record.requested_model_id.clone());
+    UsageListRecordView {
+        id: record.id,
+        provider: record.provider_kind,
+        authentication_kind: record.provider_account_authentication_kind,
+        account_id: record.provider_account_ref,
+        account_email: record.provider_account_email,
+        account_name: record.provider_account_name,
+        route: record.endpoint,
+        model,
+        requested_model: record.requested_model_id,
+        upstream_model: record.upstream_model_id,
+        service_tier: record.service_tier,
+        client_transport: record.client_transport,
+        upstream_transport: record.upstream_transport,
+        reasoning_effort: record.reasoning_effort,
+        reasoning_preset: record.reasoning_preset,
+        subagent_kind: record.subagent_kind,
+        compact: record.compact,
+        token_details,
+        billing,
+        latency_details: UsageLatencyDetailsView {
+            admission_decision_ms: record.admission_decision_ms,
+            account_selection_wait_ms: record.account_selection_wait_ms,
+            capacity_used_slots: record.capacity_used_slots,
+            capacity_total_slots: record.capacity_total_slots,
+            transport_decision_wait_ms: record.transport_decision_wait_ms,
+            ws_connect_ms: record.connect_ms,
+            upstream_headers_ms: record.headers_ms,
+            first_event_ms: record.first_event_ms,
+            first_reasoning_ms: record.first_reasoning_ms,
+            first_text_ms: record.first_text_ms,
+            first_token_ms: record.first_token_ms,
+            openai_processing_ms: record.provider_processing_ms,
+        },
+        first_token_latency_ms: record.first_token_ms,
+        latency_ms: record.latency_ms,
+        created_at: record.started_at,
+        created_at_display,
+        client_ip: record.client_ip,
+        user_agent: record.user_agent,
+    }
+}
+
 pub(crate) fn usage_record_view(record: domain::UsageRecord) -> UsageRecordView {
     let tokens = token_details(&record);
     let billing = billing_view(record.billing.as_ref());
@@ -223,10 +342,6 @@ pub(crate) fn usage_record_view(record: domain::UsageRecord) -> UsageRecordView
         .upstream_model_id
         .clone()
         .or_else(|| record.requested_model_id.clone());
-    let transport = record
-        .upstream_transport
-        .clone()
-        .or_else(|| Some(record.client_transport.clone()));
     let metadata = provider_metadata_fields(record.provider_metadata_json.as_deref());
     UsageRecordView {
         id: record.id.clone(),
@@ -247,7 +362,8 @@ pub(crate) fn usage_record_view(record: domain::UsageRecord) -> UsageRecordView
         upstream_model: record.upstream_model_id,
         service_tier: record.service_tier,
         status_code,
-        transport,
+        client_transport: record.client_transport,
+        upstream_transport: record.upstream_transport,
         protocol: record.protocol.clone(),
         http_version: record.http_version.clone(),
         client_status_code: record.client_status_code.map(i64::from),
@@ -259,6 +375,10 @@ pub(crate) fn usage_record_view(record: domain::UsageRecord) -> UsageRecordView
         image_generation_requested: record.image_generation_requested,
         image_generation_succeeded: record.image_generation_succeeded,
         latency_details: UsageLatencyDetailsView {
+            admission_decision_ms: record.admission_decision_ms,
+            account_selection_wait_ms: record.account_selection_wait_ms,
+            capacity_used_slots: record.capacity_used_slots,
+            capacity_total_slots: record.capacity_total_slots,
             transport_decision_wait_ms: record.transport_decision_wait_ms,
             ws_connect_ms: record.connect_ms,
             upstream_headers_ms: record.headers_ms,
@@ -318,6 +438,8 @@ pub(crate) fn provider_metadata_fields(value: Option<&str>) -> BTreeMap<String,
         "requestKind",
         "subagentKind",
         "transport",
+        "clientTransport",
+        "upstreamTransport",
         "httpVersion",
         "clientStatusCode",
         "upstreamStatusCode",
@@ -387,6 +509,8 @@ pub(crate) fn usage_attempt_view(attempt: domain::UsageAttempt) -> UsageAttemptV
 
 pub(crate) fn usage_detail_view(detail: domain::UsageDetail) -> UsageRecordDetailView {
     UsageRecordDetailView {
+        trace: detail.trace,
+        related_requests: detail.related_requests,
         request: usage_record_view(detail.request),
         attempts: detail
             .attempts
@@ -397,31 +521,13 @@ pub(crate) fn usage_detail_view(detail: domain::UsageDetail) -> UsageRecordDetai
     }
 }
 
-pub(crate) fn page_meta(page: u32, page_size: u16, total: u64) -> PageMeta {
-    let page_size_u64 = u64::from(page_size);
-    let total_pages = total.saturating_add(page_size_u64 - 1) / page_size_u64;
-    PageMeta::new(
-        page,
-        u32::from(page_size),
-        total,
-        u32::try_from(total_pages).unwrap_or(u32::MAX),
-    )
-}
-
-pub(crate) fn usage_page_view(
-    page: domain::UsagePage,
-    page_number: u32,
-    page_size: u16,
-) -> Result<PageData<UsageRecordView>, WireValidationError> {
-    Ok(PageData {
-        items: page.items.into_iter().map(usage_record_view).collect(),
-        page: page_meta(page_number, page_size, page.total),
-        next_cursor: page
-            .next_cursor
-            .as_ref()
-            .map(encode_observability_cursor)
-            .transpose()?,
-    })
+pub(crate) fn usage_page_view(page: domain::UsagePage) -> PageData<UsageListRecordView> {
+    PageData {
+        items: page.items.into_iter().map(usage_list_record_view).collect(),
+        current_page: page.current_page,
+        page_size: page.page_size,
+        total: page.total,
+    }
 }
 
 pub(crate) fn ops_error_view(error: domain::OpsError) -> OpsErrorView {
@@ -431,50 +537,77 @@ pub(crate) fn ops_error_view(error: domain::OpsError) -> OpsErrorView {
         .or(error.provider_account_name.as_ref())
         .or(error.provider_account_ref.as_ref())
         .cloned();
+    let model = error
+        .upstream_model_id
+        .clone()
+        .or_else(|| error.requested_model_id.clone());
     OpsErrorView {
         id: error.event_id,
         request_id: error.request_id,
         client_api_key_id: error.client_api_key_ref,
         kind: error.component.clone(),
+        operation: error.operation,
+        protocol: error.protocol,
+        client_transport: error.client_transport,
         provider: error.provider_kind,
         authentication_kind: error.provider_account_authentication_kind,
         account_id: error.provider_account_ref,
+        account_name: error.provider_account_name,
+        account_email: error.provider_account_email,
         route: error.endpoint.unwrap_or_else(|| "—".to_owned()),
-        model: error.upstream_model_id,
+        model,
+        requested_model: error.requested_model_id,
+        upstream_model: error.upstream_model_id,
+        service_tier: error.service_tier,
         client_status_code: error.client_status_code.map(i64::from),
         upstream_status_code: error.upstream_status_code.map(i64::from),
         transport: error.upstream_transport,
         attempt_index: error.attempt_index,
         failure_class: error.failure_kind,
+        upstream_send_state: error.upstream_send_state,
+        provider_error_code: error.provider_error_code,
         response_id: error.client_response_id,
         upstream_request_id: error.upstream_request_id,
         latency_ms: error.latency_ms,
+        client_ip: error.client_ip,
+        user_agent: error.user_agent,
+        reasoning_effort: error.reasoning_effort,
+        reasoning_preset: error.reasoning_preset,
+        request_kind: error.request_kind,
+        subagent_kind: error.subagent_kind,
+        compact: error.compact,
         message: error.message,
+        raw_upstream_error: error.raw_upstream_error,
         metadata: OpsErrorMetadataView {
             source: error.source,
             component: error.component,
             attempt_id: None,
             account_label,
+            continuation_affinity_hash: error.continuation_affinity_hash,
+            continuation_previous_response_id_hash: error.continuation_previous_response_id_hash,
+            continuation_unavailable_reason: error.continuation_unavailable_reason,
+            upstream_connection_id: error.upstream_connection_id,
+            upstream_connection_exit_reason: error.upstream_connection_exit_reason,
+            upstream_connection_age_ms: error.upstream_connection_age_ms,
+            upstream_connection_idle_ms: error.upstream_connection_idle_ms,
+            recovery_request_id: error.recovery_request_id,
+            recovered_at: error.recovered_at,
+            recovery_attempt_count: error.recovery_attempt_count,
+            recovery_retry_delay_ms: error.recovery_retry_delay_ms,
+            recovery_total_latency_ms: error.recovery_total_latency_ms,
         },
         created_at: error.occurred_at,
         created_at_display: china_datetime(&error.occurred_at),
     }
 }
 
-pub(crate) fn ops_page_view(
-    page: domain::OpsErrorPage,
-    page_number: u32,
-    page_size: u16,
-) -> Result<PageData<OpsErrorView>, WireValidationError> {
-    Ok(PageData {
+pub(crate) fn ops_page_view(page: domain::OpsErrorPage) -> PageData<OpsErrorView> {
+    PageData {
         items: page.items.into_iter().map(ops_error_view).collect(),
-        page: page_meta(page_number, page_size, page.total),
-        next_cursor: page
-            .next_cursor
-            .as_ref()
-            .map(encode_observability_cursor)
-            .transpose()?,
-    })
+        current_page: page.current_page,
+        page_size: page.page_size,
+        total: page.total,
+    }
 }
 
 pub(crate) fn trend_point_view(point: domain::TrendPoint) -> TrendPointView {
@@ -506,6 +639,36 @@ pub(crate) fn trend_point_view(point: domain::TrendPoint) -> TrendPointView {
         success_rate: success_rate_value
             .map_or_else(|| "—".to_owned(), |value| format!("{value:.1}%")),
         success_rate_value,
+        first_token_p50_ms: point
+            .metrics
+            .first_token_latency_percentiles
+            .p50_ms
+            .map(|value| value.as_f64()),
+        first_token_p95_ms: point
+            .metrics
+            .first_token_latency_percentiles
+            .p95_ms
+            .map(|value| value.as_f64()),
+        latency_p95_ms: point
+            .metrics
+            .latency_percentiles
+            .p95_ms
+            .map(|value| value.as_f64()),
+        output_throughput_p50: point.metrics.output_throughput_p50,
+        admission_decision_p95_ms: point
+            .metrics
+            .admission_decision_percentiles
+            .p95_ms
+            .map(|value| value.as_f64()),
+        account_selection_wait_p95_ms: point
+            .metrics
+            .account_selection_wait_percentiles
+            .p95_ms
+            .map(|value| value.as_f64()),
+        capacity_utilization: point
+            .metrics
+            .capacity_utilization_p95_basis_points
+            .map(basis_points_rate),
     }
 }
 
@@ -533,18 +696,20 @@ pub(crate) fn trend_summary_view(
         ],
         TrendKind::Latency => vec![
             TrendSummaryView {
-                label: "平均".to_owned(),
-                value: display_duration(summary.average_latency_ms),
+                label: "首字 P95".to_owned(),
+                value: display_duration_f64(summary.peak_first_token_p95_ms),
                 ratio: None,
             },
             TrendSummaryView {
-                label: "最高".to_owned(),
-                value: display_duration(summary.max_latency_ms),
+                label: "总耗时 P95".to_owned(),
+                value: display_duration_f64(summary.peak_latency_p95_ms),
                 ratio: None,
             },
             TrendSummaryView {
-                label: "最低".to_owned(),
-                value: display_duration(summary.min_latency_ms),
+                label: "吞吐 P50".to_owned(),
+                value: summary
+                    .minimum_output_throughput_p50
+                    .map_or_else(|| "—".to_owned(), |value| format!("{value} tok/s")),
                 ratio: None,
             },
         ],
@@ -704,6 +869,28 @@ pub(crate) fn dashboard_view(
     } = observation;
     let mut account_usage_views = Vec::with_capacity(account_usage.len());
     for credential in account_usage {
+        let local_requests = credential
+            .quota_window
+            .as_ref()
+            .filter(|window| window.used_percent.is_none())
+            .and_then(|window| window.local_usage.as_ref())
+            .map(|usage| usage.request_count);
+        let (metric_label, metric_value) = match local_requests {
+            Some(count) => (
+                "次数".to_owned(),
+                if count > 0 {
+                    format_compact_number(count)
+                } else {
+                    "—".to_owned()
+                },
+            ),
+            None => (
+                "今日 Token".to_owned(),
+                credential
+                    .total_tokens
+                    .map_or_else(|| "—".to_owned(), format_compact_number),
+            ),
+        };
         account_usage_views.push(DashboardAccountUsageView {
             id: credential.account_id.clone(),
             provider: credential.provider_kind.clone(),
@@ -726,6 +913,11 @@ pub(crate) fn dashboard_view(
                 })
                 .collect(),
             quota_used_percent: credential.quota_used_percent,
+            usage_window: credential
+                .quota_window
+                .map(crate::admin::accounts::quota_window_view),
+            metric_label,
+            metric_value,
             last_used: relative_time(credential.last_used_at, range.end),
         });
     }
@@ -771,7 +963,10 @@ pub(crate) fn dashboard_view(
         health_timeline: health_timeline_view(health_timeline),
         wire_profiles: wire_profiles.into_iter().map(wire_profile_view).collect(),
         account_usage: account_usage_views,
-        usage_records: recent_requests.into_iter().map(usage_record_view).collect(),
+        usage_records: recent_requests
+            .into_iter()
+            .map(usage_list_record_view)
+            .collect(),
         pool_summary: DashboardPoolSummaryView {
             total: provider_accounts.total,
             normal: provider_accounts.normal,
@@ -813,6 +1008,7 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
         .map(|point| OverviewHealthPointView {
             bucket: point.bucket_start,
             label: china_label(point.bucket_start, "%m-%d %H:%M"),
+            total_requests: point.total_requests,
             success_requests: point.success_requests,
             failed_requests: point.failed_requests,
             cancelled_requests: point.cancelled_requests,
@@ -843,6 +1039,31 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
                 .first_token_latency_percentiles
                 .p99_ms
                 .map(|value| value.as_f64()),
+            admission_decision_p50_ms: point
+                .admission_decision_percentiles
+                .p50_ms
+                .map(|value| value.as_f64()),
+            admission_decision_p95_ms: point
+                .admission_decision_percentiles
+                .p95_ms
+                .map(|value| value.as_f64()),
+            account_selection_wait_p50_ms: point
+                .account_selection_wait_percentiles
+                .p50_ms
+                .map(|value| value.as_f64()),
+            account_selection_wait_p95_ms: point
+                .account_selection_wait_percentiles
+                .p95_ms
+                .map(|value| value.as_f64()),
+            output_throughput_p10: point.output_throughput_p10,
+            output_throughput_p50: point.output_throughput_p50,
+            output_throughput_p90: point.output_throughput_p90,
+            capacity_utilization: point
+                .capacity_utilization_avg_basis_points
+                .map(basis_points_rate),
+            capacity_utilization_p95: point
+                .capacity_utilization_p95_basis_points
+                .map(basis_points_rate),
         })
         .collect();
     let cost_points = insights
@@ -858,6 +1079,8 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
             total_tokens: point.total_tokens,
             estimated_cost: point.estimated_cost.as_ref().map(ToString::to_string),
             standard_cost: point.standard_cost.as_ref().map(ToString::to_string),
+            no_cache_cost: point.no_cache_cost.as_ref().map(ToString::to_string),
+            cache_savings: point.cache_savings.as_ref().map(ToString::to_string),
             cached_token_rate: point.cached_token_rate,
             cache_hit_request_rate: point.cache_hit_request_rate,
         })
@@ -872,6 +1095,7 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
             incomplete_requests: insights.health.incomplete_requests,
             caller_error_requests: insights.health.caller_error_requests,
             success_rate: insights.health.success_rate,
+            completion_rate: insights.health.completion_rate,
             request_change_rate: None,
             success_rate_change: None,
             points: health_points,
@@ -907,8 +1131,42 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
                 .first_token_latency_percentiles
                 .p99_ms
                 .map(|value| value.as_f64()),
+            admission_decision_p50_ms: insights
+                .performance
+                .admission_decision_percentiles
+                .p50_ms
+                .map(|value| value.as_f64()),
+            admission_decision_p95_ms: insights
+                .performance
+                .admission_decision_percentiles
+                .p95_ms
+                .map(|value| value.as_f64()),
+            account_selection_wait_p50_ms: insights
+                .performance
+                .account_selection_wait_percentiles
+                .p50_ms
+                .map(|value| value.as_f64()),
+            account_selection_wait_p95_ms: insights
+                .performance
+                .account_selection_wait_percentiles
+                .p95_ms
+                .map(|value| value.as_f64()),
+            output_throughput_p10: insights.performance.output_throughput_p10,
+            output_throughput_p50: insights.performance.output_throughput_p50,
+            output_throughput_p90: insights.performance.output_throughput_p90,
+            capacity_utilization: insights
+                .performance
+                .capacity_utilization_avg_basis_points
+                .map(basis_points_rate),
+            capacity_utilization_p95: insights
+                .performance
+                .capacity_utilization_p95_basis_points
+                .map(basis_points_rate),
             latency_coverage: insights.performance.latency_coverage,
             first_token_coverage: insights.performance.first_token_coverage,
+            admission_decision_coverage: insights.performance.admission_decision_coverage,
+            account_selection_wait_coverage: insights.performance.account_selection_wait_coverage,
+            capacity_coverage: insights.performance.capacity_coverage,
             points: performance_points,
         },
         cost: OverviewCostView {
@@ -922,11 +1180,27 @@ pub(crate) fn usage_insights_view(insights: domain::UsageInsights) -> UsageInsig
                 .standard_cost
                 .as_ref()
                 .map(ToString::to_string),
+            no_cache_cost: insights
+                .cost
+                .no_cache_cost
+                .as_ref()
+                .map(ToString::to_string),
+            cache_savings: insights
+                .cost
+                .cache_savings
+                .as_ref()
+                .map(ToString::to_string),
+            tier_premium: insights.cost.tier_premium.as_ref().map(ToString::to_string),
             cost_per_request: insights
                 .cost
                 .cost_per_request
                 .as_ref()
                 .map(ToString::to_string),
+            cost_per_successful_request: insights
+                .cost
+                .cost_per_successful_request
+                .as_ref()
+                .map(ToString::to_string),
             tokens_per_request: insights.cost.tokens_per_request,
             cached_token_rate: insights.cost.cached_token_rate,
             cache_hit_request_rate: insights.cost.cache_hit_request_rate,
@@ -984,6 +1258,12 @@ pub(crate) fn diagnostics_view(
                 request_share: item.request_share,
                 average_latency_ms: item.average_latency_ms,
                 latency_p95_ms: item.latency_p95_ms,
+                first_token_p95_ms: item.first_token_p95_ms,
+                non_completion_count: item.non_completion_count,
+                non_completion_rate: item.non_completion_rate,
+                retry_count: item.retry_count,
+                retry_rate: item.retry_rate,
+                impact_score: item.impact_score,
                 estimated_cost: item.estimated_cost.as_ref().map(ToString::to_string),
                 attempt_count: item.attempt_count,
                 total_tokens: item.total_tokens,
@@ -993,21 +1273,21 @@ pub(crate) fn diagnostics_view(
 }
 
 pub(crate) fn map_wire_error(error: WireValidationError) -> AdminError {
+    if error.field() == "timeRange" {
+        return AdminError::invalid_time_range();
+    }
     let message = match error.field() {
-        "timeRange" => "Invalid time range",
-        "statusCode" => "Status code must be between 100 and 599",
-        "attemptIndex" => "Attempt index is out of range",
-        "kind" => "Invalid dashboard trend kind",
-        "dimension" => "Invalid diagnostics dimension",
-        "outcome" => "Invalid Observability query",
-        "id" => "Usage record ID is required",
-        "page" | "pageSize" => "Invalid Observability query",
-        "cursor" => "Invalid observability cursor",
-        _ => "Invalid observability query",
+        "statusCode" => "statusCode 必须在 100 到 599 之间",
+        "attemptIndex" => "attemptIndex 超出有效范围",
+        "kind" => "Dashboard 趋势类型不合法",
+        "dimension" => "诊断维度不合法",
+        "id" => "用量记录 ID 不能为空",
+        "cursor" => "观测数据游标不合法",
+        _ => "观测查询参数不合法",
     };
     AdminError::bad_request(message)
 }
 
 pub(crate) fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Observability repository unavailable")
+    map_admin_service_error(error)
 }

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

@@ -2,14 +2,10 @@
 
 use super::*;
 
-use base64::Engine as _;
-
 /// 观测列表默认页大小。
 pub const DEFAULT_PAGE_SIZE: u16 = 50;
 /// 观测列表允许的最大页大小。
 pub const MAX_PAGE_SIZE: u16 = 100;
-/// 游标编码在 HTTP 层解码前允许的最大长度。
-pub const MAX_CURSOR_BYTES: usize = 1024;
 
 /// Dashboard 查询参数。
 #[derive(Clone, Default, Deserialize)]
@@ -31,9 +27,8 @@ impl DashboardQuery {
 #[derive(Clone, Default, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct UsageQuery {
-    pub page: Option<u32>,
+    pub current_page: Option<u32>,
     pub page_size: Option<u16>,
-    pub cursor: Option<String>,
     pub kind: Option<String>,
     pub outcome: Option<String>,
     pub client_api_key_id: Option<String>,
@@ -53,22 +48,17 @@ pub struct UsageQuery {
 }
 
 impl UsageQuery {
-    /// 校验分页字段，不改变仓储层的分页 owner。
-    pub fn validate_page(&self) -> Result<(u32, u16), WireValidationError> {
-        let page = self.page.unwrap_or(1);
-        if page == 0 {
-            return Err(WireValidationError::new("page"));
+    /// 校验 Element Plus 风格的页码分页字段。
+    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
+        let current_page = self.current_page.unwrap_or(1);
+        if current_page == 0 {
+            return Err(WireValidationError::new("currentPage"));
         }
         let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
         if page_size == 0 || page_size > MAX_PAGE_SIZE {
             return Err(WireValidationError::new("pageSize"));
         }
-        Ok((page, page_size))
-    }
-
-    /// 校验游标的 wire 边界；编码和排序语义由应用层负责。
-    pub fn validate_cursor(&self) -> Result<(), WireValidationError> {
-        validate_cursor(self.cursor.as_deref())
+        Ok((current_page, page_size))
     }
 }
 
@@ -110,22 +100,19 @@ impl DiagnosticsQuery {
 #[derive(Clone, Default, Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 pub struct OpsQuery {
-    pub page: Option<u32>,
+    pub current_page: Option<u32>,
     pub page_size: Option<u16>,
-    pub cursor: Option<String>,
     pub kind: Option<String>,
     pub client_api_key_id: Option<String>,
     pub provider: Option<String>,
     pub request_id: Option<String>,
     pub account_id: Option<String>,
-    pub route: Option<String>,
     pub model: Option<String>,
     pub status_code: Option<i64>,
     pub client_status_code: Option<i64>,
     pub upstream_status_code: Option<i64>,
     pub transport: Option<String>,
     pub attempt_index: Option<i64>,
-    pub failure_class: Option<String>,
     pub response_id: Option<String>,
     pub upstream_request_id: Option<String>,
     pub search: Option<String>,
@@ -134,22 +121,17 @@ pub struct OpsQuery {
 }
 
 impl OpsQuery {
-    /// 校验分页字段。
-    pub fn validate_page(&self) -> Result<(u32, u16), WireValidationError> {
-        let page = self.page.unwrap_or(1);
-        if page == 0 {
-            return Err(WireValidationError::new("page"));
+    /// 校验 Element Plus 风格的页码分页字段。
+    pub fn validate_pagination(&self) -> Result<(u32, u16), WireValidationError> {
+        let current_page = self.current_page.unwrap_or(1);
+        if current_page == 0 {
+            return Err(WireValidationError::new("currentPage"));
         }
         let page_size = self.page_size.unwrap_or(DEFAULT_PAGE_SIZE);
         if page_size == 0 || page_size > MAX_PAGE_SIZE {
             return Err(WireValidationError::new("pageSize"));
         }
-        Ok((page, page_size))
-    }
-
-    /// 校验游标的 wire 边界。
-    pub fn validate_cursor(&self) -> Result<(), WireValidationError> {
-        validate_cursor(self.cursor.as_deref())
+        Ok((current_page, page_size))
     }
 }
 
@@ -258,13 +240,6 @@ pub(crate) fn require_text(value: &str, field: &'static str) -> Result<(), WireV
     }
 }
 
-pub(crate) fn validate_cursor(value: Option<&str>) -> Result<(), WireValidationError> {
-    if value.is_some_and(|value| value.is_empty() || value.len() > MAX_CURSOR_BYTES) {
-        return Err(WireValidationError::new("cursor"));
-    }
-    Ok(())
-}
-
 pub(crate) fn trimmed(value: Option<&str>) -> Option<&str> {
     value.map(str::trim).filter(|value| !value.is_empty())
 }
@@ -345,37 +320,20 @@ pub(crate) fn usage_filter(query: &UsageQuery) -> Result<domain::UsageFilter, Wi
     })
 }
 
-pub(crate) fn usage_command(
-    query: &UsageQuery,
-) -> Result<(domain::UsageQuery, u32, u16), WireValidationError> {
-    let (page, page_size) = query.validate_page()?;
-    query.validate_cursor()?;
-    let page_number = NonZeroU32::new(page)
-        .map(domain::PageNumber::new)
-        .ok_or_else(|| WireValidationError::new("page"))?;
+pub(crate) fn usage_command(query: &UsageQuery) -> Result<domain::UsageQuery, WireValidationError> {
+    let (current_page, page_size) = query.validate_pagination()?;
     let page_size_value =
         DomainPageSize::new(page_size).map_err(|_| WireValidationError::new("pageSize"))?;
-    Ok((
-        domain::UsageQuery {
-            range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
-            filter: usage_filter(query)?,
-            cursor: decode_observability_cursor(query.cursor.as_deref())?,
-            page: page_number,
-            page_size: page_size_value,
-        },
-        page,
-        page_size,
-    ))
+    Ok(domain::UsageQuery {
+        range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
+        filter: usage_filter(query)?,
+        current_page,
+        page_size: page_size_value,
+    })
 }
 
-pub(crate) fn ops_command(
-    query: &OpsQuery,
-) -> Result<(domain::OpsErrorQuery, u32, u16), WireValidationError> {
-    let (page, page_size) = query.validate_page()?;
-    query.validate_cursor()?;
-    let page_number = NonZeroU32::new(page)
-        .map(domain::PageNumber::new)
-        .ok_or_else(|| WireValidationError::new("page"))?;
+pub(crate) fn ops_command(query: &OpsQuery) -> Result<domain::OpsErrorQuery, WireValidationError> {
+    let (current_page, page_size) = query.validate_pagination()?;
     let page_size_value =
         DomainPageSize::new(page_size).map_err(|_| WireValidationError::new("pageSize"))?;
     let status_code = parse_status(
@@ -384,66 +342,25 @@ pub(crate) fn ops_command(
             .or(query.client_status_code)
             .or(query.status_code),
     )?;
-    Ok((
-        domain::OpsErrorQuery {
-            range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
-            filter: domain::OpsErrorFilter {
-                client_api_key_ref: non_empty(query.client_api_key_id.clone()),
-                request_id: non_empty(query.request_id.clone()),
-                provider_kind: non_empty(query.provider.clone()),
-                provider_account_ref: non_empty(query.account_id.clone()),
-                operation: non_empty(query.route.clone()).or_else(|| non_empty(query.kind.clone())),
-                model: non_empty(query.model.clone()),
-                transport: non_empty(query.transport.clone()),
-                attempt_index: parse_attempt_index(query.attempt_index)?,
-                response_id: non_empty(query.response_id.clone()),
-                upstream_request_id: non_empty(query.upstream_request_id.clone()),
-                failure_kind: non_empty(query.failure_class.clone()),
-                status_code,
-                search: non_empty(query.search.clone()),
-            },
-            cursor: decode_observability_cursor(query.cursor.as_deref())?,
-            page: page_number,
-            page_size: page_size_value,
+    Ok(domain::OpsErrorQuery {
+        range: usage_range(query.start_time.as_deref(), query.end_time.as_deref())?,
+        filter: domain::OpsErrorFilter {
+            client_api_key_ref: non_empty(query.client_api_key_id.clone()),
+            request_id: non_empty(query.request_id.clone()),
+            provider_kind: non_empty(query.provider.clone()),
+            provider_account_ref: non_empty(query.account_id.clone()),
+            operation: non_empty(query.kind.clone()),
+            model: non_empty(query.model.clone()),
+            transport: non_empty(query.transport.clone()),
+            attempt_index: parse_attempt_index(query.attempt_index)?,
+            response_id: non_empty(query.response_id.clone()),
+            upstream_request_id: non_empty(query.upstream_request_id.clone()),
+            status_code,
+            search: non_empty(query.search.clone()),
         },
-        page,
-        page_size,
-    ))
-}
-
-pub(crate) fn decode_observability_cursor(
-    value: Option<&str>,
-) -> Result<Option<domain::ObservabilityCursor>, WireValidationError> {
-    value
-        .map(|encoded| {
-            if encoded.is_empty() || encoded.len() > MAX_CURSOR_BYTES {
-                return Err(WireValidationError::new("cursor"));
-            }
-            let bytes = URL_SAFE_NO_PAD
-                .decode(encoded)
-                .map_err(|_| WireValidationError::new("cursor"))?;
-            let wire: CursorWire =
-                serde_json::from_slice(&bytes).map_err(|_| WireValidationError::new("cursor"))?;
-            if wire.stable_id.trim().is_empty() {
-                return Err(WireValidationError::new("cursor"));
-            }
-            Ok(domain::ObservabilityCursor {
-                observed_at: wire.observed_at,
-                stable_id: wire.stable_id,
-            })
-        })
-        .transpose()
-}
-
-pub(crate) fn encode_observability_cursor(
-    cursor: &domain::ObservabilityCursor,
-) -> Result<String, WireValidationError> {
-    let bytes = serde_json::to_vec(&CursorWire {
-        observed_at: cursor.observed_at,
-        stable_id: cursor.stable_id.clone(),
+        current_page,
+        page_size: page_size_value,
     })
-    .map_err(|_| WireValidationError::new("cursor"))?;
-    Ok(URL_SAFE_NO_PAD.encode(bytes))
 }
 
 pub(crate) fn non_empty(value: Option<String>) -> Option<String> {

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

@@ -32,7 +32,7 @@ where
 pub(crate) async fn dashboard_summary<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<DashboardQuery>,
+    AdminQuery(query): AdminQuery<DashboardQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -56,7 +56,7 @@ where
 pub(crate) async fn dashboard_trend<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<DashboardQuery>,
+    AdminQuery(query): AdminQuery<DashboardQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -79,27 +79,26 @@ where
 pub(crate) async fn usage_records<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<UsageQuery>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let (command, page, page_size) = usage_command(&query).map_err(map_wire_error)?;
+    let command = usage_command(&query).map_err(map_wire_error)?;
     let result = state
         .admin_services()
         .observability()
         .usage_records(command)
         .await
         .map_err(map_service_error)?;
-    let data = usage_page_view(result, page, page_size)
-        .map_err(|_| AdminError::internal("Failed to encode observability cursor"))?;
+    let data = usage_page_view(result);
     Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
 }
 
 pub(crate) async fn usage_record_detail<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<DetailQuery>,
+    AdminQuery(query): AdminQuery<DetailQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -120,7 +119,7 @@ where
 pub(crate) async fn usage_records_summary<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<UsageQuery>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -143,7 +142,7 @@ where
 pub(crate) async fn usage_insights_overview<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<UsageQuery>,
+    AdminQuery(query): AdminQuery<UsageQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -166,7 +165,7 @@ where
 pub(crate) async fn usage_insights_diagnostics<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<DiagnosticsQuery>,
+    AdminQuery(query): AdminQuery<DiagnosticsQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -196,19 +195,18 @@ where
 pub(crate) async fn ops_errors<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<OpsQuery>,
+    AdminQuery(query): AdminQuery<OpsQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
 {
-    let (command, page, page_size) = ops_command(&query).map_err(map_wire_error)?;
+    let command = ops_command(&query).map_err(map_wire_error)?;
     let result = state
         .admin_services()
         .observability()
         .ops_errors(command)
         .await
         .map_err(map_service_error)?;
-    let data = ops_page_view(result, page, page_size)
-        .map_err(|_| AdminError::internal("Failed to encode observability cursor"))?;
+    let data = ops_page_view(result);
     Ok(AdminResponse::new(StatusCode::OK, AdminEnvelope::ok(data)))
 }

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

@@ -2,21 +2,14 @@
 
 use super::*;
 
-/// 观测列表游标的稳定 wire 形状。
-#[derive(Clone, Serialize, serde::Deserialize)]
-#[serde(rename_all = "camelCase", deny_unknown_fields)]
-pub struct CursorWire {
-    pub observed_at: DateTime<Utc>,
-    pub stable_id: String,
-}
-
 /// 观测列表响应数据。
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct PageData<T> {
     pub items: Vec<T>,
-    pub page: PageMeta,
-    pub next_cursor: Option<String>,
+    pub current_page: u32,
+    pub page_size: u16,
+    pub total: u64,
 }
 
 /// Token 详情展示。
@@ -77,7 +70,39 @@ pub struct BillingView {
     pub multiplier_display: String,
 }
 
-/// 单条逻辑请求展示。
+/// 使用记录表格的窄展示。
+#[derive(Serialize)]
+#[serde(rename_all = "camelCase")]
+pub struct UsageListRecordView {
+    pub id: String,
+    pub provider: Option<String>,
+    pub authentication_kind: Option<String>,
+    pub account_id: Option<String>,
+    pub account_email: Option<String>,
+    pub account_name: Option<String>,
+    pub route: String,
+    pub model: Option<String>,
+    pub requested_model: Option<String>,
+    pub upstream_model: Option<String>,
+    pub service_tier: Option<String>,
+    pub client_transport: String,
+    pub upstream_transport: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: bool,
+    pub token_details: TokenDetailsView,
+    pub billing: Option<BillingView>,
+    pub latency_details: UsageLatencyDetailsView,
+    pub first_token_latency_ms: Option<u64>,
+    pub latency_ms: Option<u64>,
+    pub created_at: DateTime<Utc>,
+    pub created_at_display: String,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+}
+
+/// 单条逻辑请求详情展示。
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageRecordView {
@@ -99,7 +124,8 @@ pub struct UsageRecordView {
     pub upstream_model: Option<String>,
     pub service_tier: Option<String>,
     pub status_code: Option<i64>,
-    pub transport: Option<String>,
+    pub client_transport: String,
+    pub upstream_transport: Option<String>,
     pub protocol: String,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub http_version: Option<String>,
@@ -157,6 +183,14 @@ pub struct WebSocketPoolMetadataView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageLatencyDetailsView {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub admission_decision_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub account_selection_wait_ms: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub capacity_used_slots: Option<u64>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub capacity_total_slots: Option<u64>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub transport_decision_wait_ms: Option<u64>,
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -213,6 +247,8 @@ pub struct UsageAttemptView {
 #[derive(Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct UsageRecordDetailView {
+    pub trace: Option<serde_json::Value>,
+    pub related_requests: Vec<serde_json::Value>,
     #[serde(flatten)]
     pub request: UsageRecordView,
     pub attempts: Vec<UsageAttemptView>,
@@ -256,6 +292,13 @@ pub struct TrendPointView {
     pub min_latency_value: Option<u64>,
     pub success_rate: String,
     pub success_rate_value: Option<f64>,
+    pub first_token_p50_ms: Option<f64>,
+    pub first_token_p95_ms: Option<f64>,
+    pub latency_p95_ms: Option<f64>,
+    pub output_throughput_p50: Option<u64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub capacity_utilization: Option<f64>,
 }
 
 /// Dashboard 趋势摘要。
@@ -334,6 +377,9 @@ pub struct DashboardAccountUsageView {
     pub request_count: u64,
     pub request_buckets: Vec<DashboardAccountRequestBucketView>,
     pub quota_used_percent: Option<f64>,
+    pub usage_window: Option<crate::admin::accounts::AccountQuotaWindowView>,
+    pub metric_label: String,
+    pub metric_value: String,
     pub last_used: String,
 }
 
@@ -510,7 +556,7 @@ pub struct DashboardDataView {
     pub health_timeline: HealthTimelineView,
     pub wire_profiles: Vec<DashboardWireProfileView>,
     pub account_usage: Vec<DashboardAccountUsageView>,
-    pub usage_records: Vec<UsageRecordView>,
+    pub usage_records: Vec<UsageListRecordView>,
     pub pool_summary: DashboardPoolSummaryView,
     pub capacity_info: DashboardCapacityInfoView,
     pub rotation_strategy: String,
@@ -537,6 +583,7 @@ pub struct UsageSummaryView {
 pub struct OverviewHealthPointView {
     pub bucket: DateTime<Utc>,
     pub label: String,
+    pub total_requests: u64,
     pub success_requests: u64,
     pub failed_requests: u64,
     pub cancelled_requests: u64,
@@ -556,6 +603,7 @@ pub struct OverviewHealthView {
     pub incomplete_requests: u64,
     pub caller_error_requests: u64,
     pub success_rate: f64,
+    pub completion_rate: f64,
     pub request_change_rate: Option<f64>,
     pub success_rate_change: Option<f64>,
     pub points: Vec<OverviewHealthPointView>,
@@ -573,6 +621,15 @@ pub struct OverviewPerformancePointView {
     pub first_token_p50_ms: Option<f64>,
     pub first_token_p95_ms: Option<f64>,
     pub first_token_p99_ms: Option<f64>,
+    pub admission_decision_p50_ms: Option<f64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p50_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization: Option<f64>,
+    pub capacity_utilization_p95: Option<f64>,
 }
 
 /// 洞察性能摘要。
@@ -585,8 +642,20 @@ pub struct OverviewPerformanceView {
     pub first_token_p50_ms: Option<f64>,
     pub first_token_p95_ms: Option<f64>,
     pub first_token_p99_ms: Option<f64>,
+    pub admission_decision_p50_ms: Option<f64>,
+    pub admission_decision_p95_ms: Option<f64>,
+    pub account_selection_wait_p50_ms: Option<f64>,
+    pub account_selection_wait_p95_ms: Option<f64>,
+    pub output_throughput_p10: Option<u64>,
+    pub output_throughput_p50: Option<u64>,
+    pub output_throughput_p90: Option<u64>,
+    pub capacity_utilization: Option<f64>,
+    pub capacity_utilization_p95: Option<f64>,
     pub latency_coverage: f64,
     pub first_token_coverage: f64,
+    pub admission_decision_coverage: f64,
+    pub account_selection_wait_coverage: f64,
+    pub capacity_coverage: f64,
     pub points: Vec<OverviewPerformancePointView>,
 }
 
@@ -602,6 +671,8 @@ pub struct OverviewCostPointView {
     pub total_tokens: u64,
     pub estimated_cost: Option<String>,
     pub standard_cost: Option<String>,
+    pub no_cache_cost: Option<String>,
+    pub cache_savings: Option<String>,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
 }
@@ -612,7 +683,11 @@ pub struct OverviewCostPointView {
 pub struct OverviewCostView {
     pub estimated_cost: Option<String>,
     pub standard_cost: Option<String>,
+    pub no_cache_cost: Option<String>,
+    pub cache_savings: Option<String>,
+    pub tier_premium: Option<String>,
     pub cost_per_request: Option<String>,
+    pub cost_per_successful_request: Option<String>,
     pub tokens_per_request: f64,
     pub cached_token_rate: f64,
     pub cache_hit_request_rate: Option<f64>,
@@ -661,6 +736,12 @@ pub struct DiagnosticItemView {
     pub request_share: f64,
     pub average_latency_ms: Option<u64>,
     pub latency_p95_ms: Option<u64>,
+    pub first_token_p95_ms: Option<u64>,
+    pub non_completion_count: u64,
+    pub non_completion_rate: f64,
+    pub retry_count: u64,
+    pub retry_rate: f64,
+    pub impact_score: f64,
     pub estimated_cost: Option<String>,
     pub attempt_count: u64,
     pub total_tokens: u64,
@@ -682,20 +763,39 @@ pub struct OpsErrorView {
     pub request_id: Option<String>,
     pub client_api_key_id: Option<String>,
     pub kind: String,
+    pub operation: String,
+    pub protocol: Option<String>,
+    pub client_transport: Option<String>,
     pub provider: Option<String>,
     pub authentication_kind: Option<String>,
     pub account_id: Option<String>,
+    pub account_name: Option<String>,
+    pub account_email: Option<String>,
     pub route: String,
     pub model: Option<String>,
+    pub requested_model: Option<String>,
+    pub upstream_model: Option<String>,
+    pub service_tier: Option<String>,
     pub client_status_code: Option<i64>,
     pub upstream_status_code: Option<i64>,
     pub transport: Option<String>,
     pub attempt_index: Option<u32>,
     pub failure_class: String,
+    pub upstream_send_state: Option<String>,
+    pub provider_error_code: Option<String>,
     pub response_id: Option<String>,
     pub upstream_request_id: Option<String>,
     pub latency_ms: Option<u64>,
+    pub client_ip: Option<String>,
+    pub user_agent: Option<String>,
+    pub reasoning_effort: Option<String>,
+    pub reasoning_preset: Option<String>,
+    pub request_kind: Option<String>,
+    pub subagent_kind: Option<String>,
+    pub compact: Option<bool>,
     pub message: String,
+    /// 上游错误正文或 WebSocket close/error frame 原文；不做脱敏。
+    pub raw_upstream_error: Option<String>,
     pub metadata: OpsErrorMetadataView,
     pub created_at: DateTime<Utc>,
     pub created_at_display: String,
@@ -709,4 +809,16 @@ pub struct OpsErrorMetadataView {
     pub component: String,
     pub attempt_id: Option<String>,
     pub account_label: Option<String>,
+    pub continuation_affinity_hash: Option<String>,
+    pub continuation_previous_response_id_hash: Option<String>,
+    pub continuation_unavailable_reason: Option<String>,
+    pub upstream_connection_id: Option<String>,
+    pub upstream_connection_exit_reason: Option<String>,
+    pub upstream_connection_age_ms: Option<u64>,
+    pub upstream_connection_idle_ms: Option<u64>,
+    pub recovery_request_id: Option<String>,
+    pub recovered_at: Option<DateTime<Utc>>,
+    pub recovery_attempt_count: u32,
+    pub recovery_retry_delay_ms: Option<u64>,
+    pub recovery_total_latency_ms: Option<u64>,
 }

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

@@ -3,7 +3,7 @@
 //! 当前 wire 仍保留 display 字段；统一由本模块提供，避免 accounts/observability
 //! 各自维护格式化规则。
 
-use gateway_core::accounting::Decimal;
+use gateway_core::metering::Decimal;
 
 /// 千分位格式化。
 #[must_use]

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

@@ -3,22 +3,26 @@
 use std::{collections::BTreeMap, fmt};
 
 use axum::{
-    Json, Router,
+    Router,
     extract::State,
     http::StatusCode,
     response::IntoResponse,
     routing::{get, post},
 };
 use chrono::{DateTime, Utc};
+use gateway_admin::model::client_distribution::{
+    ClientDownloadPackage, CodexDesktopWindowsDownloads,
+};
 use gateway_admin::model::settings::{
     ModelMappings as DomainModelMappings, ReplaceRuntimeSettings, RotationStrategy, RuntimeSettings,
 };
+use gateway_core::policy::CodexClientVersion;
 use gateway_core::routing::{PublicModelId, UpstreamModelId};
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState, WireValidationError,
-    wire::map_admin_service_error,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
+    WireValidationError, wire::map_admin_service_error,
 };
 
 /// 客户端模型到上游模型的全局精确映射。
@@ -34,6 +38,8 @@ pub struct RuntimeSettingsView {
     pub max_concurrent_per_account: u64,
     pub request_interval_ms: u64,
     pub rotation_strategy: String,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
     pub usage_retention_days: u64,
     pub ops_event_retention_days: u64,
     pub audit_retention_days: u64,
@@ -50,6 +56,8 @@ pub struct UpdateRuntimeSettingsRequest {
     pub max_concurrent_per_account: u64,
     pub request_interval_ms: u64,
     pub rotation_strategy: String,
+    pub min_codex_desktop_version: Option<String>,
+    pub min_codex_cli_version: Option<String>,
     pub usage_retention_days: u64,
     pub ops_event_retention_days: u64,
     pub audit_retention_days: u64,
@@ -75,6 +83,14 @@ impl UpdateRuntimeSettingsRequest {
         if RotationStrategy::parse(&self.rotation_strategy).is_none() {
             return Err(WireValidationError::new("rotationStrategy"));
         }
+        validate_optional_client_version(
+            self.min_codex_desktop_version.as_deref(),
+            "minCodexDesktopVersion",
+        )?;
+        validate_optional_client_version(
+            self.min_codex_cli_version.as_deref(),
+            "minCodexCliVersion",
+        )?;
         Ok(())
     }
 
@@ -90,6 +106,8 @@ impl UpdateRuntimeSettingsRequest {
             request_interval_ms: self.request_interval_ms,
             rotation_strategy: RotationStrategy::parse(&self.rotation_strategy)
                 .ok_or_else(|| WireValidationError::new("rotationStrategy"))?,
+            min_codex_desktop_version: self.min_codex_desktop_version,
+            min_codex_cli_version: self.min_codex_cli_version,
             usage_retention_days: u32::try_from(self.usage_retention_days)
                 .map_err(|_| WireValidationError::new("settingsUsageRetentionOverflow"))?,
             ops_event_retention_days: u32::try_from(self.ops_event_retention_days)
@@ -109,6 +127,8 @@ impl From<RuntimeSettings> for RuntimeSettingsView {
             max_concurrent_per_account: u64::from(settings.max_concurrent_per_account),
             request_interval_ms: settings.request_interval_ms,
             rotation_strategy: settings.rotation_strategy.as_str().to_owned(),
+            min_codex_desktop_version: settings.min_codex_desktop_version,
+            min_codex_cli_version: settings.min_codex_cli_version,
             usage_retention_days: u64::from(settings.usage_retention_days),
             ops_event_retention_days: u64::from(settings.ops_event_retention_days),
             audit_retention_days: u64::from(settings.audit_retention_days),
@@ -145,6 +165,58 @@ pub struct DeletedAdminApiKey {
     pub message: &'static str,
 }
 
+#[derive(Debug, Clone, Copy, Default, Deserialize)]
+#[serde(default, deny_unknown_fields)]
+struct ClientDownloadsQuery {
+    refresh: bool,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct ClientDownloadPackageView {
+    architecture: String,
+    source: String,
+    version: Option<String>,
+    file_name: String,
+    size_bytes: Option<u64>,
+    download_url: String,
+    expires_at: Option<DateTime<Utc>>,
+}
+
+impl From<ClientDownloadPackage> for ClientDownloadPackageView {
+    fn from(package: ClientDownloadPackage) -> Self {
+        Self {
+            architecture: package.architecture.as_str().to_owned(),
+            source: package.source.as_str().to_owned(),
+            version: package.version,
+            file_name: package.file_name,
+            size_bytes: package.size_bytes,
+            download_url: package.download_url,
+            expires_at: package.expires_at,
+        }
+    }
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Serialize)]
+#[serde(rename_all = "camelCase")]
+struct CodexDesktopWindowsDownloadsView {
+    resolved_at: DateTime<Utc>,
+    cached: bool,
+    warning: Option<String>,
+    packages: Vec<ClientDownloadPackageView>,
+}
+
+impl From<CodexDesktopWindowsDownloads> for CodexDesktopWindowsDownloadsView {
+    fn from(downloads: CodexDesktopWindowsDownloads) -> Self {
+        Self {
+            resolved_at: downloads.resolved_at,
+            cached: downloads.cached,
+            warning: downloads.warning,
+            packages: downloads.packages.into_iter().map(Into::into).collect(),
+        }
+    }
+}
+
 impl Default for DeletedAdminApiKey {
     fn default() -> Self {
         Self {
@@ -161,6 +233,10 @@ where
     Router::new()
         .route("/api/admin/settings", get(settings::<S>))
         .route("/api/admin/settings/update", post(update_settings::<S>))
+        .route(
+            "/api/admin/settings/client-downloads/codex-desktop/windows",
+            get(codex_desktop_windows_downloads::<S>),
+        )
         .route(
             "/api/admin/settings/admin-api-key",
             get(admin_api_key_status::<S>),
@@ -175,6 +251,25 @@ where
         )
 }
 
+async fn codex_desktop_windows_downloads<S>(
+    _auth: AdminAuth,
+    State(state): State<S>,
+    AdminQuery(query): AdminQuery<ClientDownloadsQuery>,
+) -> impl IntoResponse
+where
+    S: AdminSessionState + Send + Sync,
+{
+    let downloads = state
+        .admin_services()
+        .client_distribution()
+        .codex_desktop_windows(query.refresh)
+        .await;
+    AdminResponse::new(
+        StatusCode::OK,
+        AdminEnvelope::ok(CodexDesktopWindowsDownloadsView::from(downloads)),
+    )
+}
+
 async fn settings<S>(
     _auth: AdminAuth,
     State(state): State<S>,
@@ -197,7 +292,7 @@ where
 async fn update_settings<S>(
     auth: AdminAuth,
     State(state): State<S>,
-    Json(request): Json<UpdateRuntimeSettingsRequest>,
+    AdminJson(request): AdminJson<UpdateRuntimeSettingsRequest>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -322,18 +417,30 @@ fn valid_model_name(value: &str, max_len: usize) -> bool {
         && !value.bytes().any(|byte| byte.is_ascii_control())
 }
 
+fn validate_optional_client_version(
+    value: Option<&str>,
+    field: &'static str,
+) -> Result<(), WireValidationError> {
+    if value.is_some_and(|value| CodexClientVersion::parse(value).is_err()) {
+        return Err(WireValidationError::new(field));
+    }
+    Ok(())
+}
+
 fn map_wire_error(error: WireValidationError) -> AdminError {
     let message = match error.field() {
-        "settingsRefreshConcurrencyOverflow" => "Invalid refreshConcurrency".to_owned(),
-        "settingsMaxConcurrencyOverflow" => "Invalid maxConcurrentPerAccount".to_owned(),
-        "settingsUsageRetentionOverflow" => "Invalid usageRetentionDays".to_owned(),
-        "settingsOpsRetentionOverflow" => "Invalid opsEventRetentionDays".to_owned(),
-        "settingsAuditRetentionOverflow" => "Invalid auditRetentionDays".to_owned(),
-        field => format!("Invalid field: {field}"),
+        "settingsRefreshConcurrencyOverflow" => "refreshConcurrency 不合法".to_owned(),
+        "settingsMaxConcurrencyOverflow" => "maxConcurrentPerAccount 不合法".to_owned(),
+        "settingsUsageRetentionOverflow" => "usageRetentionDays 不合法".to_owned(),
+        "settingsOpsRetentionOverflow" => "opsEventRetentionDays 不合法".to_owned(),
+        "settingsAuditRetentionOverflow" => "auditRetentionDays 不合法".to_owned(),
+        "minCodexDesktopVersion" => "Codex Desktop 最低版本格式不合法".to_owned(),
+        "minCodexCliVersion" => "Codex CLI 最低版本格式不合法".to_owned(),
+        field => format!("{field} 字段不合法"),
     };
     AdminError::bad_request(message)
 }
 
 fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "Settings repository unavailable")
+    map_admin_service_error(error)
 }

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

@@ -5,8 +5,8 @@
 use std::convert::Infallible;
 
 use axum::{
-    Json, Router,
-    extract::{Query, State},
+    Router,
+    extract::State,
     http::StatusCode,
     response::{
         IntoResponse,
@@ -23,7 +23,7 @@ use gateway_admin::model::system::{
 use serde::{Deserialize, Serialize};
 
 use super::{
-    AdminAuth, AdminEnvelope, AdminError, AdminResponse, AdminSessionState,
+    AdminAuth, AdminEnvelope, AdminError, AdminJson, AdminQuery, AdminResponse, AdminSessionState,
     wire::map_admin_service_error,
 };
 
@@ -251,7 +251,7 @@ where
 async fn update_detail<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    Query(query): Query<UpdateDetailQuery>,
+    AdminQuery(query): AdminQuery<UpdateDetailQuery>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -290,7 +290,7 @@ where
 async fn perform_update<S>(
     _auth: AdminAuth,
     State(state): State<S>,
-    payload: Option<Json<UpdateRequest>>,
+    payload: Option<AdminJson<UpdateRequest>>,
 ) -> Result<impl IntoResponse, AdminError>
 where
     S: AdminSessionState + Send + Sync,
@@ -298,7 +298,7 @@ where
     let result = state
         .admin_services()
         .system()
-        .perform_update(payload.map(|Json(value)| value.into_target_version()))
+        .perform_update(payload.map(|AdminJson(value)| value.into_target_version()))
         .await
         .map_err(map_system_error)?;
     let SystemOperationAccepted::Update {
@@ -309,7 +309,7 @@ where
         target_version,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system update result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -361,7 +361,7 @@ where
         need_restart,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system rollback result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -391,7 +391,7 @@ where
         message,
     } = result
     else {
-        return Err(AdminError::internal("Invalid system restart result"));
+        return Err(AdminError::internal());
     };
     Ok(AdminResponse::new(
         StatusCode::OK,
@@ -477,5 +477,5 @@ const fn update_event_level_name(level: SystemUpdateEventLevel) -> &'static str
 }
 
 fn map_system_error(error: gateway_admin::model::AdminError) -> AdminError {
-    map_admin_service_error(error, "System operation unavailable")
+    map_admin_service_error(error)
 }

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

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

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

@@ -180,13 +180,16 @@ pub fn initialize(
                 "request",
                 request_id = %request_id,
                 method = %request.method().as_str(),
-                uri = %request
-                    .uri()
-                    .path_and_query()
-                    .map(axum::http::uri::PathAndQuery::as_str)
-                    .unwrap_or_default(),
+                uri = %request.uri().path(),
             )
         }
+    })
+    .on_request(|_request: &Request<_>, _span: &tracing::Span| {
+        tracing::info!(target: "request_trace", stage = "http.received", "HTTP request received");
+    })
+    .on_response(|response: &axum::http::Response<_>, latency: Duration, _span: &tracing::Span| {
+        tracing::info!(target: "request_trace", stage = "http.response", status = response.status().as_u16(),
+            headers_ms = latency.as_millis(), "HTTP response headers ready");
     });
     let router = router
         .layer(PropagateRequestIdLayer::new(request_id_header.clone()))

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

@@ -5,9 +5,13 @@ use axum::{
     response::{IntoResponse, Response},
 };
 use gateway_core::engine::execution::AuthenticatedClient;
+use gateway_core::policy::{ClientVersionRejection, CodexClientKind, CodexClientVersion};
 
 use super::{
-    error::{missing_client_api_key_response, runtime_unavailable_response},
+    error::{
+        client_version_rejection_response, missing_client_api_key_response,
+        runtime_unavailable_response,
+    },
     service::OpenAiService,
 };
 
@@ -26,6 +30,44 @@ pub enum ClientApiKeyAuthError {
     RuntimeUnavailable,
 }
 
+/// Client API Key 或最低版本准入失败。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum ClientAccessError {
+    Authentication(ClientApiKeyAuthError),
+    Version(ClientVersionRejection),
+}
+
+impl From<ClientApiKeyAuthError> for ClientAccessError {
+    fn from(error: ClientApiKeyAuthError) -> Self {
+        Self::Authentication(error)
+    }
+}
+
+impl From<ClientVersionRejection> for ClientAccessError {
+    fn from(error: ClientVersionRejection) -> Self {
+        Self::Version(error)
+    }
+}
+
+/// 从有界请求头中识别出的客户端及其可选合法版本。
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct IdentifiedCodexClient {
+    kind: CodexClientKind,
+    version: Option<CodexClientVersion>,
+}
+
+impl IdentifiedCodexClient {
+    #[must_use]
+    pub const fn kind(&self) -> CodexClientKind {
+        self.kind
+    }
+
+    #[must_use]
+    pub const fn version(&self) -> Option<&CodexClientVersion> {
+        self.version.as_ref()
+    }
+}
+
 impl ClientApiKeyAuthError {
     /// 返回可用于日志和指标的稳定失败原因。
     #[must_use]
@@ -67,19 +109,121 @@ pub fn bearer_client_api_key(headers: &HeaderMap) -> Result<&str, ClientApiKeyAu
 pub(crate) fn authenticate_client(
     service: &OpenAiService,
     headers: &HeaderMap,
-) -> Result<AuthenticatedClient, ClientApiKeyAuthError> {
-    bearer_client_api_key(headers).and_then(|key| service.authenticate(key))
+) -> Result<AuthenticatedClient, ClientAccessError> {
+    let key = bearer_client_api_key(headers)?;
+    let client = service.authenticate(key)?;
+    if let Some(identified) = identify_codex_client(headers) {
+        client
+            .snapshot()
+            .min_codex_client_versions()
+            .enforce(identified.kind(), identified.version())?;
+    }
+    Ok(client)
 }
 
-pub(crate) fn authentication_error_response(error: ClientApiKeyAuthError) -> Response {
-    log_client_api_key_auth_failure(error);
-    if error == ClientApiKeyAuthError::RuntimeUnavailable {
-        runtime_unavailable_response().into_response()
-    } else {
-        missing_client_api_key_response().into_response()
+pub(crate) fn client_access_error_response(error: ClientAccessError) -> Response {
+    match error {
+        ClientAccessError::Authentication(error) => {
+            log_client_api_key_auth_failure(error);
+            if error == ClientApiKeyAuthError::RuntimeUnavailable {
+                runtime_unavailable_response().into_response()
+            } else {
+                missing_client_api_key_response().into_response()
+            }
+        }
+        ClientAccessError::Version(error) => {
+            tracing::info!(
+                client = error.kind().as_str(),
+                current_version = error.current().map(ToString::to_string),
+                min_version = %error.min(),
+                "Codex client version requirement rejected request"
+            );
+            client_version_rejection_response(&error).into_response()
+        }
     }
 }
 
+/// Desktop 优先于其内嵌的 CLI/Core 标记；未知客户端保持兼容并返回 `None`。
+#[must_use]
+pub fn identify_codex_client(headers: &HeaderMap) -> Option<IdentifiedCodexClient> {
+    const MAXIMUM_HEADER_LENGTH: usize = 4096;
+
+    let originator = bounded_ascii_header(headers, "originator", MAXIMUM_HEADER_LENGTH);
+    let user_agent = bounded_ascii_header(headers, "user-agent", MAXIMUM_HEADER_LENGTH);
+    let is_desktop = originator.is_some_and(|value| value.eq_ignore_ascii_case("Codex Desktop"))
+        || user_agent.is_some_and(|value| contains_ascii_case_insensitive(value, "Codex Desktop"));
+    if is_desktop {
+        let explicit_version = bounded_ascii_header(headers, "version", MAXIMUM_HEADER_LENGTH);
+        let version = match explicit_version {
+            Some(value) => CodexClientVersion::parse(value).ok(),
+            None => user_agent
+                .and_then(desktop_version_from_user_agent)
+                .and_then(|value| CodexClientVersion::parse(value).ok()),
+        };
+        return Some(IdentifiedCodexClient {
+            kind: CodexClientKind::Desktop,
+            version,
+        });
+    }
+
+    let user_agent = user_agent?;
+    for product in user_agent.split(|character: char| {
+        character.is_ascii_whitespace() || matches!(character, '(' | ')' | ';' | ',' | '[' | ']')
+    }) {
+        for prefix in ["codex_cli_rs", "codex-cli"] {
+            if product.eq_ignore_ascii_case(prefix) {
+                return Some(IdentifiedCodexClient {
+                    kind: CodexClientKind::Cli,
+                    version: None,
+                });
+            }
+            let Some((name, version)) = product.split_once('/') else {
+                continue;
+            };
+            if name.eq_ignore_ascii_case(prefix) {
+                return Some(IdentifiedCodexClient {
+                    kind: CodexClientKind::Cli,
+                    version: CodexClientVersion::parse(version).ok(),
+                });
+            }
+        }
+    }
+    None
+}
+
+fn bounded_ascii_header<'a>(
+    headers: &'a HeaderMap,
+    name: &'static str,
+    maximum_length: usize,
+) -> Option<&'a str> {
+    let value = headers.get(name)?.to_str().ok()?;
+    if !value.is_ascii() {
+        return None;
+    }
+    Some(&value[..value.len().min(maximum_length)])
+}
+
+fn desktop_version_from_user_agent(user_agent: &str) -> Option<&str> {
+    let marker = "Codex Desktop;";
+    let start = find_ascii_case_insensitive(user_agent, marker)? + marker.len();
+    let version = user_agent[start..]
+        .trim_start()
+        .split([')', ' ', ';', ','])
+        .next()?;
+    (!version.is_empty()).then_some(version)
+}
+
+fn contains_ascii_case_insensitive(haystack: &str, needle: &str) -> bool {
+    find_ascii_case_insensitive(haystack, needle).is_some()
+}
+
+fn find_ascii_case_insensitive(haystack: &str, needle: &str) -> Option<usize> {
+    haystack
+        .as_bytes()
+        .windows(needle.len())
+        .position(|window| window.eq_ignore_ascii_case(needle.as_bytes()))
+}
+
 fn log_client_api_key_auth_failure(error: ClientApiKeyAuthError) {
     match error {
         ClientApiKeyAuthError::RuntimeUnavailable => {

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

@@ -0,0 +1,124 @@
+//! OpenAI Provider 原生非流式 JSON 端点的公共交付边界。
+
+use axum::{
+    body::{Body, Bytes},
+    http::{HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
+    response::{IntoResponse, Response},
+};
+use gateway_core::engine::execution::StartedExecution;
+use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
+
+use super::{
+    error::{engine_error_response, protocol_error_response},
+    responses::{PendingExecution, ProtocolError, ProtocolErrorBody},
+};
+
+/// 收集一个 Provider 原生 JSON 响应，并在 Core commit 后按原始 bytes 交付。
+pub(super) async fn collect_raw_json_response(started: StartedExecution) -> Response {
+    let mut execution = PendingExecution::new(started.session);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    let events = match session.collect_uncommitted().await {
+        Ok(events) => events,
+        Err(error) => {
+            let response = engine_error_response(&error);
+            return execution.record_response_status(response).await;
+        }
+    };
+    let body = match raw_json_body(events) {
+        Some(body) => body,
+        None => {
+            let response = invalid_upstream_response();
+            let response = execution.record_response_status(response).await;
+            execution.cancel_and_finalize().await;
+            return response;
+        }
+    };
+    let status = session
+        .response_status_code()
+        .and_then(|status| StatusCode::from_u16(status).ok())
+        .filter(StatusCode::is_success)
+        .unwrap_or(StatusCode::OK);
+    let response_headers = session.response_headers().to_vec();
+    let response = json_body_response(body, status, &response_headers);
+    let Some(session) = execution.session_mut() else {
+        return invalid_upstream_response();
+    };
+    if let Err(error) = session.commit_downstream(Some(status.as_u16())).await {
+        execution.cancel_and_finalize().await;
+        let response = engine_error_response(&error);
+        return execution.record_response_status(response).await;
+    }
+    if !session.is_finalized() {
+        execution.cancel_and_finalize().await;
+        return invalid_upstream_response();
+    }
+    execution.disarm();
+    response
+}
+
+fn raw_json_body(events: Vec<ProviderEvent>) -> Option<Bytes> {
+    let mut body = None;
+    for event in events {
+        let (_, wire) = event.into_parts();
+        let Some(wire) = wire.filter(|wire| wire.protocol() == "openai") else {
+            continue;
+        };
+        let Some(raw) = wire.into_raw_json_body() else {
+            continue;
+        };
+        if body.replace(raw).is_some() {
+            return None;
+        }
+    }
+    body
+}
+
+fn json_body_response(
+    body: Bytes,
+    status: StatusCode,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let mut response = Response::new(Body::from(body));
+    *response.status_mut() = status;
+    response
+        .headers_mut()
+        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
+    apply_response_headers(response, response_headers)
+}
+
+fn apply_response_headers(
+    mut response: Response,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    let connection_options = super::responses::response_connection_options(response_headers);
+    for header in response_headers {
+        if !super::responses::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
+            continue;
+        };
+        response.headers_mut().append(name, value);
+    }
+    response
+}
+
+fn invalid_upstream_response() -> Response {
+    protocol_error_response(
+        StatusCode::BAD_GATEWAY,
+        ProtocolErrorBody {
+            error: ProtocolError {
+                kind: "server_error",
+                code: "invalid_upstream_response",
+                message: "The gateway could not forward the upstream JSON response.".to_owned(),
+                param: None,
+            },
+        },
+    )
+    .into_response()
+}

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

@@ -9,6 +9,7 @@ use axum::{
 use gateway_core::{
     engine::EngineError,
     error::{GatewayError, GatewayErrorKind},
+    policy::{ClientVersionRejection, CodexClientKind},
 };
 use serde_json::{Value, json};
 
@@ -58,6 +59,47 @@ pub fn runtime_unavailable_response() -> (StatusCode, Json<Value>) {
     )
 }
 
+/// 已识别 Codex 客户端不满足最低版本要求。
+pub fn client_version_rejection_response(
+    rejection: &ClientVersionRejection,
+) -> (StatusCode, Json<Value>) {
+    let client_label = match rejection.kind() {
+        CodexClientKind::Desktop => "Codex Desktop",
+        CodexClientKind::Cli => "Codex CLI",
+    };
+    let (message, code, current_version) = match rejection.current() {
+        Some(current) => (
+            format!(
+                "{client_label} {current} is below the minimum required version {}. Upgrade {client_label} and retry.",
+                rejection.min()
+            ),
+            "client_version_too_old",
+            Some(current.to_string()),
+        ),
+        None => (
+            format!(
+                "A valid {client_label} version is required. Upgrade to version {} or newer and retry.",
+                rejection.min()
+            ),
+            "client_version_unavailable",
+            None,
+        ),
+    };
+    (
+        StatusCode::UPGRADE_REQUIRED,
+        Json(json!({
+            "error": {
+                "message": message,
+                "type": "invalid_request_error",
+                "code": code,
+                "client": rejection.kind().as_str(),
+                "current_version": current_version,
+                "min_version": rejection.min().to_string()
+            }
+        })),
+    )
+}
+
 /// 对外模型不存在。
 pub fn model_not_found_response() -> (StatusCode, Json<Value>) {
     openai_error_response(

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

@@ -3,22 +3,21 @@
 use std::net::SocketAddr;
 
 use axum::{
-    body::{Body, Bytes},
+    body::Bytes,
     extract::{Extension, State, connect_info::ConnectInfo},
-    http::{HeaderMap, HeaderName, HeaderValue, StatusCode, header::CONTENT_TYPE},
-    response::{IntoResponse, Response},
+    http::HeaderMap,
+    response::Response,
 };
-use gateway_core::engine::execution::StartedExecution;
 use gateway_core::error::{GatewayError, GatewayErrorKind};
-use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
 use gateway_core::operation::{ImageRequest, ImageRequestKind, Operation, RawJsonPayload};
-use serde_json::{Map, Value};
+use serde_json::Value;
 
 use crate::ApiState;
 use crate::openai::{
-    auth::{authenticate_client, authentication_error_response},
-    error::{engine_error_response, gateway_error_response, protocol_error_response},
-    responses::{PendingExecution, ProtocolError, ProtocolErrorBody, request_client_context},
+    auth::{authenticate_client, client_access_error_response},
+    endpoint::collect_raw_json_response,
+    error::gateway_error_response,
+    responses::{OpenAiRequestHeaders, request_client_context},
 };
 
 const OPENAI_PROTOCOL: &str = "openai";
@@ -71,7 +70,7 @@ async fn handle_image_request(
     let service = state.openai();
     let client = match authenticate_client(service, &headers) {
         Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
     };
     let (client_ip, user_agent) = request_client_context(
         &headers,
@@ -82,13 +81,13 @@ async fn handle_image_request(
         Err(error) => return gateway_error_response(&error),
     };
     let started = match service
-        .start_image(client, operation, client_ip, user_agent, endpoint)
+        .start_provider_endpoint(client, operation, client_ip, user_agent, endpoint)
         .await
     {
         Ok(started) => started,
         Err(error) => return gateway_error_response(&error),
     };
-    collect_image_response(started).await
+    collect_raw_json_response(started).await
 }
 
 fn image_operation(
@@ -96,7 +95,7 @@ fn image_operation(
     headers: &HeaderMap,
     kind: ImageRequestKind,
 ) -> Result<Operation, GatewayError> {
-    let mut context = Map::new();
+    let mut context = OpenAiRequestHeaders::from_headers(headers).session_context();
     if let Some(turn_id) = headers
         .get("x-codex-image-turn-id")
         .and_then(|value| value.to_str().ok())
@@ -118,116 +117,3 @@ fn image_operation(
         kind, payload,
     )))
 }
-
-async fn collect_image_response(started: StartedExecution) -> Response {
-    let mut execution = PendingExecution::new(started.session);
-    let Some(session) = execution.session_mut() else {
-        return invalid_upstream_response();
-    };
-    let events = match session.collect_uncommitted().await {
-        Ok(events) => events,
-        Err(error) => {
-            let response = engine_error_response(&error);
-            return execution.record_response_status(response).await;
-        }
-    };
-    let body = match raw_json_body(events) {
-        Some(body) => body,
-        None => {
-            let response = invalid_upstream_response();
-            let response = execution.record_response_status(response).await;
-            execution.cancel_and_finalize().await;
-            return response;
-        }
-    };
-    let status = session
-        .response_status_code()
-        .and_then(|status| StatusCode::from_u16(status).ok())
-        .filter(StatusCode::is_success)
-        .unwrap_or(StatusCode::OK);
-    let response_headers = session.response_headers().to_vec();
-    let response = json_body_response(body, status, &response_headers);
-    let Some(session) = execution.session_mut() else {
-        return invalid_upstream_response();
-    };
-    if let Err(error) = session.commit_downstream(Some(status.as_u16())).await {
-        execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
-        return execution.record_response_status(response).await;
-    }
-    if !session.is_finalized() {
-        execution.cancel_and_finalize().await;
-        return invalid_upstream_response();
-    }
-    execution.disarm();
-    response
-}
-
-fn raw_json_body(events: Vec<ProviderEvent>) -> Option<Bytes> {
-    let mut body = None;
-    for event in events {
-        let (_, wire) = event.into_parts();
-        let Some(wire) = wire.filter(|wire| wire.protocol() == "openai") else {
-            continue;
-        };
-        let Some(raw) = wire.into_raw_json_body() else {
-            continue;
-        };
-        if body.replace(raw).is_some() {
-            return None;
-        }
-    }
-    body
-}
-
-fn json_body_response(
-    body: Bytes,
-    status: StatusCode,
-    response_headers: &[ProviderResponseHeader],
-) -> Response {
-    let mut response = Response::new(Body::from(body));
-    *response.status_mut() = status;
-    response
-        .headers_mut()
-        .insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
-    apply_response_headers(response, response_headers)
-}
-
-fn apply_response_headers(
-    mut response: Response,
-    response_headers: &[ProviderResponseHeader],
-) -> Response {
-    let connection_options =
-        crate::openai::responses::response_connection_options(response_headers);
-    for header in response_headers {
-        if !crate::openai::responses::response_header_is_forwardable(
-            header.name(),
-            &connection_options,
-        ) {
-            continue;
-        }
-        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
-            continue;
-        };
-        let Ok(value) = HeaderValue::from_bytes(header.value()) else {
-            continue;
-        };
-        response.headers_mut().append(name, value);
-    }
-    response
-}
-
-fn invalid_upstream_response() -> Response {
-    protocol_error_response(
-        StatusCode::BAD_GATEWAY,
-        ProtocolErrorBody {
-            error: ProtocolError {
-                kind: "server_error",
-                code: "invalid_upstream_response",
-                message: "The gateway could not forward the upstream image response.".to_owned(),
-                param: None,
-            },
-        },
-    )
-    .into_response()
-}

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

@@ -1,9 +1,11 @@
 //! OpenAI 客户端协议 adapter。
 
 pub mod auth;
+mod endpoint;
 pub mod error;
 pub mod images;
 pub mod models;
 pub mod responses;
 pub mod router;
+pub mod search;
 pub(crate) mod service;

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

@@ -13,7 +13,7 @@ use serde_json::{Value, json};
 use crate::ApiState;
 
 use super::{
-    auth::{authenticate_client, authentication_error_response},
+    auth::{authenticate_client, client_access_error_response},
     error::model_not_found_response,
 };
 
@@ -34,7 +34,7 @@ pub(crate) async fn models(
     let service = state.openai();
     let client = match authenticate_client(service, &headers) {
         Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
     };
 
     if query
@@ -81,7 +81,7 @@ pub(crate) async fn model_detail(
     let service = state.openai();
     let client = match authenticate_client(service, &headers) {
         Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
     };
     let Ok(public_model) = PublicModelId::new(model_id) else {
         return model_not_found_response().into_response();
@@ -97,50 +97,6 @@ pub(crate) async fn model_detail(
         .into_response()
 }
 
-/// `GET /v1/models/catalog`。
-///
-/// 新架构的目录由 core 按客户端 Provider 范围裁剪；这里不读取或重建任一
-/// Provider 的 wire catalog，只恢复 Codex 客户端依赖的稳定展示合同。
-pub(crate) async fn model_catalog(State(state): State<ApiState>, headers: HeaderMap) -> Response {
-    let service = state.openai();
-    let client = match authenticate_client(service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let models = service
-        .public_models(&client)
-        .into_iter()
-        .map(|model| catalog_model_json(model.as_str()))
-        .collect::<Vec<_>>();
-
-    (StatusCode::OK, Json(models)).into_response()
-}
-
-/// `GET /v1/models/{model_id}/info`。
-pub(crate) async fn model_info(
-    State(state): State<ApiState>,
-    headers: HeaderMap,
-    Path(model_id): Path<String>,
-) -> Response {
-    let service = state.openai();
-    let client = match authenticate_client(service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let Ok(public_model) = PublicModelId::new(model_id) else {
-        return model_not_found_response().into_response();
-    };
-    if !service.contains_public_model(&client, &public_model) {
-        return model_not_found_response().into_response();
-    }
-
-    (
-        StatusCode::OK,
-        Json(catalog_model_json(public_model.as_str())),
-    )
-        .into_response()
-}
-
 fn openai_model_json(id: &str) -> Value {
     json!({
         "id": id,
@@ -150,22 +106,6 @@ fn openai_model_json(id: &str) -> Value {
     })
 }
 
-fn catalog_model_json(id: &str) -> Value {
-    json!({
-        "id": id,
-        "displayName": id,
-        "description": "",
-        "isDefault": false,
-        "supportedReasoningEfforts": [],
-        "defaultReasoningEffort": "",
-        "inputModalities": ["text"],
-        "outputModalities": ["text"],
-        "supportsPersonality": false,
-        "upgrade": Value::Null,
-        "source": "gateway",
-    })
-}
-
 fn codex_model_json(profile: &PublicModelProfile, index: usize) -> Value {
     let id = profile.model().as_str();
     let presentation = profile.presentation();

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

@@ -3,6 +3,7 @@
 use std::collections::VecDeque;
 use std::convert::Infallible;
 use std::net::{IpAddr, SocketAddr};
+use std::time::Duration;
 
 use axum::{
     body::{Body, Bytes},
@@ -13,9 +14,10 @@ use axum::{
     },
     response::{IntoResponse, Response},
 };
-use futures::stream;
-use gateway_core::engine::CommitRequirement;
+use futures::{StreamExt, stream};
+use gateway_core::diagnostics::TraceContext;
 use gateway_core::engine::execution::{ClientTransport, ExecutionSession, StartedExecution};
+use gateway_core::engine::{CommitRequirement, EngineError};
 use gateway_core::error::{GatewayError, GatewayErrorKind};
 use gateway_core::event::{ProviderEvent, ProviderResponseHeader};
 use gateway_core::lifecycle::ConnectionGuard;
@@ -23,7 +25,7 @@ use gateway_protocol::openai::sse::{DONE_SSE_FRAME, response_failed_sse_event_wi
 
 use crate::ApiState;
 use crate::openai::{
-    auth::{authenticate_client, authentication_error_response},
+    auth::{authenticate_client, client_access_error_response},
     error::{
         engine_error_response, gateway_error_contract, gateway_error_from_engine,
         gateway_error_response, protocol_error_response, runtime_unavailable_response,
@@ -32,46 +34,25 @@ use crate::openai::{
 
 use super::{
     OpenAiResponsesEncoder, ProtocolErrorBody, ResponseEncodeError,
-    request::{decode_request_with_headers, decode_review_request_with_headers},
+    request::decode_request_with_headers,
 };
 
+const SSE_KEEPALIVE_INTERVAL: Duration = Duration::from_secs(15);
+
 /// `POST /v1/responses`。
 pub(crate) async fn responses(
     State(state): State<ApiState>,
     connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    ingress_id: Option<Extension<tower_http::request_id::RequestId>>,
     headers: HeaderMap,
     body: Bytes,
-) -> Response {
-    handle_responses(state, connect_info, headers, body, false).await
-}
-
-/// `POST /v1/responses/review`。
-pub(crate) async fn review_responses(
-    State(state): State<ApiState>,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    body: Bytes,
-) -> Response {
-    handle_responses(state, connect_info, headers, body, true).await
-}
-
-async fn handle_responses(
-    state: ApiState,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    body: Bytes,
-    review: bool,
 ) -> Response {
     let service = state.openai();
     let client = match authenticate_client(service, &headers) {
         Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
+        Err(error) => return client_access_error_response(error),
     };
-    let decoded = match if review {
-        decode_review_request_with_headers(&body, &headers)
-    } else {
-        decode_request_with_headers(&body, &headers)
-    } {
+    let decoded = match decode_request_with_headers(&body, &headers) {
         Ok(decoded) => decoded,
         Err(error) => {
             return protocol_error_response(StatusCode::BAD_REQUEST, error.protocol_body());
@@ -100,26 +81,32 @@ async fn handle_responses(
             } else {
                 ClientTransport::HttpJson
             },
-            if review {
-                "/v1/responses/review"
-            } else {
-                "/v1/responses"
-            },
+            "/v1/responses",
         )
         .await
     {
         Ok(started) => started,
         Err(error) => return gateway_error_response(&error),
     };
+    let trace = started.session.trace();
+    trace.headers("client.request", serde_json::json!({
+        "ingressRequestId": ingress_id.as_ref().and_then(|Extension(id)| id.header_value().to_str().ok()),
+    }), headers.iter().map(|(name, value)| (name.as_str(), value.as_bytes())));
+    trace.capture("client.request.body", &body);
+    let request_id_header = HeaderValue::from_str(started.request_id.as_str()).ok();
     let StartedExecution {
         stream, session, ..
     } = started;
-    if stream {
+    let mut response = if stream {
         stream_execution_response(session, connection_guard).await
     } else {
         drop(connection_guard);
         collect_execution_response(session).await
+    };
+    if let Some(id) = request_id_header {
+        response.headers_mut().insert("x-gateway-request-id", id);
     }
+    response
 }
 
 /// 从 socket 与标准转发头提取旧 Usage 页面使用的诊断事实。
@@ -180,7 +167,8 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
     let events = match session.collect_uncommitted().await {
         Ok(events) => events,
         Err(error) => {
-            let response = engine_error_response(&error);
+            let response_headers = session.response_headers().to_vec();
+            let response = engine_error_response_with_headers(&error, &response_headers);
             return execution.record_response_status(response).await;
         }
     };
@@ -196,6 +184,11 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
         }
     };
     let response_headers = session.response_headers().to_vec();
+    session.trace().record(
+        "downstream.encoded",
+        serde_json::json!({"transport": "http_json", "bytes": encoded.len()}),
+    );
+    session.trace().dump("downstream.body", &encoded);
     let response = json_body_response(encoded, &response_headers);
 
     let Some(session) = execution.session_mut() else {
@@ -206,7 +199,7 @@ pub async fn collect_execution_response(session: Box<dyn ExecutionSession>) -> R
         .await
     {
         execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
+        let response = engine_error_response_with_headers(&error, &response_headers);
         return execution.record_response_status(response).await;
     }
     if !session.is_finalized() {
@@ -274,6 +267,13 @@ fn apply_response_headers(
     response
 }
 
+fn engine_error_response_with_headers(
+    error: &EngineError,
+    response_headers: &[ProviderResponseHeader],
+) -> Response {
+    apply_response_headers(engine_error_response(error), response_headers)
+}
+
 /// 编码首个 SSE frame 后提交下游，再持续驱动同一执行会话。
 pub async fn stream_execution_response(
     session: Box<dyn ExecutionSession>,
@@ -295,7 +295,8 @@ pub async fn stream_execution_response(
             return response;
         }
         Err(error) => {
-            let response = engine_error_response(&error);
+            let response_headers = session.response_headers().to_vec();
+            let response = engine_error_response_with_headers(&error, &response_headers);
             return execution.record_response_status(response).await;
         }
     };
@@ -327,7 +328,7 @@ pub async fn stream_execution_response(
         .await
     {
         execution.cancel_and_finalize().await;
-        let response = engine_error_response(&error);
+        let response = engine_error_response_with_headers(&error, &response_headers);
         return execution.record_response_status(response).await;
     }
     let Some(session) = execution.into_session() else {
@@ -337,9 +338,11 @@ pub async fn stream_execution_response(
     if state.encoder.is_completed() {
         state.finish_completed(Vec::new()).await;
     }
-    let body = Body::from_stream(stream::unfold(state, |mut state| async move {
+    let output = Box::pin(stream::unfold(state, |mut state| async move {
         loop {
             if let Some(chunk) = state.pending.pop_front() {
+                state.trace.dump("downstream.chunk", &chunk);
+                state.handed_off_bytes += chunk.len() as u64;
                 return Some((Ok::<Bytes, Infallible>(chunk), state));
             }
             if state.output_finished {
@@ -348,19 +351,35 @@ pub async fn stream_execution_response(
             state.advance().await;
         }
     }));
+    // 保活只轮询已固定的输出 stream；不能取消并重建 advance/next_event future，
+    // 否则一次心跳就可能丢失正在等待的上游事件或执行终态清理。
+    let body = Body::from_stream(stream::unfold(output, |mut output| async move {
+        let chunk = tokio::select! {
+            biased;
+            chunk = output.next() => chunk?,
+            () = tokio::time::sleep(SSE_KEEPALIVE_INTERVAL) => {
+                Ok(Bytes::from_static(b": keep-alive\n\n"))
+            }
+        };
+        Some((chunk, output))
+    }));
     event_stream_response(body, &response_headers)
 }
 
 fn event_stream_response(body: Body, response_headers: &[ProviderResponseHeader]) -> Response {
-    let mut response = Response::new(body);
+    let mut response = apply_response_headers(Response::new(body), response_headers);
     *response.status_mut() = StatusCode::OK;
     response
         .headers_mut()
         .insert(CONTENT_TYPE, HeaderValue::from_static("text/event-stream"));
+    response.headers_mut().insert(
+        CACHE_CONTROL,
+        HeaderValue::from_static("no-cache, no-transform"),
+    );
     response
         .headers_mut()
-        .insert(CACHE_CONTROL, HeaderValue::from_static("no-cache"));
-    apply_response_headers(response, response_headers)
+        .insert("x-accel-buffering", HeaderValue::from_static("no"));
+    response
 }
 
 fn internal_gateway_response(message: &'static str) -> Response {
@@ -422,12 +441,18 @@ impl Drop for PendingExecution {
         if session.is_finalized() {
             return;
         }
+        session.trace().record(
+            "downstream.cancelled",
+            serde_json::json!({"reason": "response_guard_dropped"}),
+        );
         session.cancel();
         detach_finalize(session);
     }
 }
 
 struct ResponsesStreamState {
+    trace: TraceContext,
+    handed_off_bytes: u64,
     session: Option<Box<dyn ExecutionSession>>,
     encoder: OpenAiResponsesEncoder,
     pending: VecDeque<Bytes>,
@@ -444,6 +469,8 @@ impl ResponsesStreamState {
         connection_guard: Option<Box<dyn ConnectionGuard>>,
     ) -> Self {
         Self {
+            trace: session.trace(),
+            handed_off_bytes: 0,
             session: Some(session),
             encoder,
             pending: initial_frames.into_iter().collect(),
@@ -599,6 +626,11 @@ impl ResponsesStreamState {
 
 impl Drop for ResponsesStreamState {
     fn drop(&mut self) {
+        self.trace.record("downstream.body.closed", serde_json::json!({
+            "handedOffBytes": self.handed_off_bytes,
+            "pendingChunks": self.pending.len(),
+            "outputFinished": self.output_finished, "executionTerminal": self.execution_terminal,
+        }));
         if self.execution_terminal {
             return;
         }

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

@@ -4,12 +4,12 @@ mod error;
 mod http;
 mod request;
 mod response;
-mod websocket;
+pub mod websocket;
 
 pub use error::{ProtocolError, ProtocolErrorBody, RequestDecodeError, ResponseEncodeError};
+pub(crate) use http::responses;
 pub(super) use http::{PendingExecution, request_client_context};
 pub use http::{collect_execution_response, stream_execution_response};
-pub(crate) use http::{responses, review_responses};
 pub use request::{
     ContinuationIntent, DecodedResponsesRequest, OpenAiRequestHeaders, ResponsesRequestMetadata,
     decode_request_with_headers,

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

@@ -13,9 +13,19 @@ use serde_json::{Map, Value};
 use super::error::RequestDecodeError;
 
 const OPENAI_PROTOCOL: &str = "openai";
-const REVIEW_SUBAGENT: &str = "review";
 const OPENAI_SUBAGENT_KEY: &str = "x-openai-subagent";
+const CODEX_TURN_METADATA_KEY: &str = "x-codex-turn-metadata";
 const PASSTHROUGH_HEADERS_CONTEXT_KEY: &str = "opaque_request_headers";
+const DOWNSTREAM_WEBSOCKET_CONNECTION_ID_CONTEXT_KEY: &str = "downstream_websocket_connection_id";
+
+/// Responses 请求进入共享解码内核时的下游传输来源。
+#[derive(Clone, Copy)]
+pub(super) enum RequestDecodeSource {
+    /// 单次 HTTP 请求，请求头与正文属于同一请求。
+    Http,
+    /// 复用连接上的 WebSocket `response.create` 帧。
+    WebSocketFrame,
+}
 
 #[derive(Clone, Default)]
 pub struct OpenAiRequestHeaders {
@@ -26,6 +36,7 @@ pub struct OpenAiRequestHeaders {
     include_timing_metrics: Option<String>,
     codex_window_id: Option<String>,
     parent_thread_id: Option<String>,
+    downstream_websocket_connection_id: Option<String>,
 
     conversation_id: Option<String>,
     session_id: Option<String>,
@@ -51,6 +62,7 @@ impl OpenAiRequestHeaders {
             include_timing_metrics: header_string(headers, "x-responsesapi-include-timing-metrics"),
             codex_window_id: header_string(headers, "x-codex-window-id"),
             parent_thread_id: header_string(headers, "x-codex-parent-thread-id"),
+            downstream_websocket_connection_id: None,
             conversation_id: header_string(headers, "conversation-id")
                 .or_else(|| header_string(headers, "conversation_id")),
             session_id: header_string(headers, "session-id")
@@ -65,16 +77,43 @@ impl OpenAiRequestHeaders {
         }
     }
 
-    fn apply_subagent(&self, body: &mut Map<String, Value>, forced_subagent: Option<&str>) {
-        if let Some(subagent) = forced_subagent.or(self.subagent.as_deref()) {
+    /// 绑定代理为当前下游 WebSocket 分配的连接身份。
+    #[must_use]
+    pub(super) fn with_downstream_websocket_connection_id(
+        mut self,
+        connection_id: impl Into<String>,
+    ) -> Self {
+        self.downstream_websocket_connection_id = Some(connection_id.into());
+        self
+    }
+
+    fn apply_subagent(&self, body: &mut Map<String, Value>) {
+        if let Some(subagent) = self.subagent.as_deref() {
             inject_subagent_metadata(body, subagent);
         }
     }
 
-    fn protocol_context(&self, use_websocket: Option<bool>) -> Map<String, Value> {
+    /// 独立端点只消费会话身份与 turn metadata，不携带 Responses 的连接状态。
+    pub(crate) fn session_context(&self) -> Map<String, Value> {
+        let mut context = Map::new();
+        insert_protocol_context(&mut context, "session_id", self.session_id.as_ref());
+        insert_protocol_context(&mut context, "thread_id", self.thread_id.as_ref());
+        insert_protocol_context(&mut context, "turn_metadata", self.turn_metadata.as_ref());
+        context
+    }
+
+    fn protocol_context(
+        &self,
+        use_websocket: Option<bool>,
+        frame_turn_metadata: Option<&String>,
+    ) -> Map<String, Value> {
         let mut context = Map::new();
         insert_protocol_context(&mut context, "turn_state", self.turn_state.as_ref());
-        insert_protocol_context(&mut context, "turn_metadata", self.turn_metadata.as_ref());
+        insert_protocol_context(
+            &mut context,
+            "turn_metadata",
+            frame_turn_metadata.or(self.turn_metadata.as_ref()),
+        );
         insert_protocol_context(&mut context, "beta_features", self.beta_features.as_ref());
         insert_protocol_context(&mut context, "version", self.version.as_ref());
         insert_protocol_context(
@@ -92,6 +131,11 @@ impl OpenAiRequestHeaders {
             "parent_thread_id",
             self.parent_thread_id.as_ref(),
         );
+        insert_protocol_context(
+            &mut context,
+            DOWNSTREAM_WEBSOCKET_CONNECTION_ID_CONTEXT_KEY,
+            self.downstream_websocket_connection_id.as_ref(),
+        );
         insert_protocol_context(
             &mut context,
             "conversation_id",
@@ -136,12 +180,6 @@ pub enum ContinuationIntent {
 }
 
 impl ContinuationIntent {
-    /// 返回是否请求了对话延续。
-    #[must_use]
-    pub const fn is_continuation(&self) -> bool {
-        matches!(self, Self::PreviousResponseId(_))
-    }
-
     /// 返回待 history owner 解析的 response ID。
     #[must_use]
     pub fn previous_response_id(&self) -> Option<&str> {
@@ -289,20 +327,11 @@ pub fn decode_request_with_headers(
     body: &[u8],
     headers: &HeaderMap,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
-    decode_request_inner(body, false, &OpenAiRequestHeaders::from_headers(headers))
-}
-
-/// 解码 `POST /v1/responses/review` 请求并冻结 review subagent 语义。
-pub(super) fn decode_review_request_with_headers(
-    body: &[u8],
-    headers: &HeaderMap,
-) -> Result<DecodedResponsesRequest, RequestDecodeError> {
-    decode_request_inner(body, true, &OpenAiRequestHeaders::from_headers(headers))
+    decode_request_inner(body, &OpenAiRequestHeaders::from_headers(headers))
 }
 
 pub(super) fn decode_request_inner(
     body: &[u8],
-    review: bool,
     request_headers: &OpenAiRequestHeaders,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
     let value =
@@ -310,14 +339,14 @@ pub(super) fn decode_request_inner(
     let Value::Object(object) = value else {
         return Err(RequestDecodeError::ExpectedObject);
     };
-    decode_request_object(object, review, request_headers)
+    decode_request_object(object, request_headers, RequestDecodeSource::Http)
 }
 
-/// 解码已解析的顶层 object；WebSocket 帧解码复用此内核，避免序列化往返。
+/// 解码已解析的顶层 object；按下游传输来源恢复连接级协议上下文。
 pub(super) fn decode_request_object(
     mut object: Map<String, Value>,
-    review: bool,
     request_headers: &OpenAiRequestHeaders,
+    source: RequestDecodeSource,
 ) -> Result<DecodedResponsesRequest, RequestDecodeError> {
     // 仅消费已识别的本地 transport 开关；未知同名值保留给未来上游协议。
     let use_websocket = object.get("use_websocket").and_then(Value::as_bool);
@@ -346,8 +375,12 @@ pub(super) fn decode_request_object(
         .map(|response_id| ContinuationIntent::PreviousResponseId(response_id.to_owned()))
         .unwrap_or(ContinuationIntent::None);
 
-    request_headers.apply_subagent(&mut object, review.then_some(REVIEW_SUBAGENT));
-    let protocol_context = request_headers.protocol_context(use_websocket);
+    request_headers.apply_subagent(&mut object);
+    let frame_turn_metadata = match source {
+        RequestDecodeSource::Http => None,
+        RequestDecodeSource::WebSocketFrame => frame_turn_metadata(&object),
+    };
+    let protocol_context = request_headers.protocol_context(use_websocket, frame_turn_metadata);
 
     let payload = ProtocolPayload::json_object(OPENAI_PROTOCOL, object)
         .map_err(|_| RequestDecodeError::CanonicalContract {
@@ -368,6 +401,16 @@ pub(super) fn decode_request_object(
     })
 }
 
+fn frame_turn_metadata(body: &Map<String, Value>) -> Option<&String> {
+    body.get("client_metadata")
+        .and_then(Value::as_object)
+        .and_then(|metadata| metadata.get(CODEX_TURN_METADATA_KEY))
+        .and_then(|value| match value {
+            Value::String(value) if !value.trim().is_empty() => Some(value),
+            _ => None,
+        })
+}
+
 fn inject_subagent_metadata(body: &mut Map<String, Value>, subagent: &str) {
     let metadata = body
         .entry("client_metadata".to_owned())
@@ -449,6 +492,8 @@ fn passthrough_header_name(name: &str, connection_headers: &[String]) -> bool {
             // 下游鉴权和账号 cookie 绝不能成为上游账号身份。
             | "authorization"
             | "x-api-key"
+            // Codex 的服务端托管认证标记只用于客户端能力判断，不代表上游身份。
+            | "x-openai-actor-authorization"
             | "cookie"
             | "cookie2"
             | "chatgpt-account-id"
@@ -461,10 +506,11 @@ fn passthrough_header_name(name: &str, connection_headers: &[String]) -> bool {
             | "x-openai-project"
             // installation ID 始终由当前 lease 重建。
             | "x-codex-installation-id"
-            // 上游指纹必须由运行时画像统一生成，客户端 originator/User-Agent
-            // 不能透传覆盖，避免不同下游客户端暴露不一致的设备指纹。
+            // 上游指纹必须由运行时画像统一生成，客户端 originator/User-Agent/version
+            // 不能作为不透明头透传覆盖，避免不同下游客户端暴露不一致的设备指纹。
             | "originator"
             | "user-agent"
+            | "version"
             // 设备 attestation/integrity 头只能由官方客户端或网关自身生成，
             // 客户端注入的 x-oai-attestation / X-OAI-IS 不得透传上游。
             | "x-oai-attestation"

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

@@ -1,699 +0,0 @@
-//! OpenAI Responses WebSocket adapter。
-
-use std::net::{IpAddr, SocketAddr};
-use std::sync::Arc;
-
-use axum::{
-    extract::{
-        Extension, State,
-        connect_info::ConnectInfo,
-        ws::{CloseFrame, Message, WebSocket, WebSocketUpgrade, close_code},
-    },
-    http::{HeaderMap, HeaderName, StatusCode},
-    response::{IntoResponse, Response},
-};
-use futures::StreamExt;
-use gateway_core::engine::execution::{AuthenticatedClient, ClientTransport, StartedExecution};
-use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
-use gateway_core::error::{GatewayError, GatewayErrorKind};
-use gateway_core::event::ProviderResponseHeader;
-use gateway_core::lifecycle::{ConnectionGuard, ConnectionLifecycle};
-use gateway_core::operation::ProviderSessionState;
-use serde_json::{Map, Value, json};
-use thiserror::Error;
-
-use crate::{
-    ApiState,
-    openai::{
-        auth::{authenticate_client, authentication_error_response},
-        error::{gateway_error_contract, gateway_error_from_engine, runtime_unavailable_response},
-        service::OpenAiService,
-    },
-};
-
-use super::{
-    DecodedResponsesRequest, OpenAiResponsesEncoder, ProtocolErrorBody, RequestDecodeError,
-    http::{PendingExecution, request_client_context},
-    request::OpenAiRequestHeaders,
-};
-
-const ACTIVE_RESPONSE_VIOLATION: &str = "Only one response.create may be active per connection";
-const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
-
-/// 将已认证的 `GET /v1/responses` 升级为 Responses WebSocket。
-pub(crate) async fn responses_websocket(
-    State(state): State<ApiState>,
-    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
-    headers: HeaderMap,
-    websocket: WebSocketUpgrade,
-) -> Response {
-    let service = state.openai().clone();
-    let client = match authenticate_client(&service, &headers) {
-        Ok(client) => client,
-        Err(error) => return authentication_error_response(error),
-    };
-    let (client_ip, user_agent) = request_client_context(
-        &headers,
-        connect_info.map(|Extension(ConnectInfo(address))| address),
-    );
-    ResponsesWebSocketAdapter::new(service).upgrade_with_client_context(
-        websocket,
-        client,
-        client_ip,
-        user_agent,
-        OpenAiRequestHeaders::from_headers(&headers),
-    )
-}
-
-/// 已鉴权 Responses WebSocket 升级边界。
-#[derive(Clone)]
-pub(crate) struct ResponsesWebSocketAdapter {
-    service: OpenAiService,
-}
-
-impl ResponsesWebSocketAdapter {
-    /// 绑定应用提供的唯一 OpenAI 客户端服务端口。
-    #[must_use]
-    pub const fn new(service: OpenAiService) -> Self {
-        Self { service }
-    }
-
-    fn upgrade_with_client_context(
-        &self,
-        websocket: WebSocketUpgrade,
-        client: AuthenticatedClient,
-        client_ip: Option<IpAddr>,
-        user_agent: Option<String>,
-        request_headers: OpenAiRequestHeaders,
-    ) -> Response {
-        let connection_guard = match self.service.try_register_connection() {
-            Ok(guard) => guard,
-            Err(_) => return runtime_unavailable_response().into_response(),
-        };
-        let session = ResponsesWebSocketSession {
-            service: self.service.clone(),
-            client,
-            connection_id: self.service.next_request_id().replacen("req_", "ws_", 1),
-            client_ip,
-            user_agent,
-            request_headers,
-            lifecycle: self.service.lifecycle(),
-            _connection_guard: connection_guard,
-        };
-        websocket
-            // 覆盖 axum/tungstenite 的私有 64 MiB message 与 16 MiB frame 默认值。
-            // Responses JSON 的协议可接受性由上游决定，代理不另设 wire 长度上限。
-            .max_message_size(usize::MAX)
-            .max_frame_size(usize::MAX)
-            .on_upgrade(move |socket| async move {
-                serve_responses_websocket(socket, session).await;
-            })
-    }
-}
-
-struct ResponsesWebSocketSession {
-    service: OpenAiService,
-    client: AuthenticatedClient,
-    connection_id: String,
-    client_ip: Option<IpAddr>,
-    user_agent: Option<String>,
-    request_headers: OpenAiRequestHeaders,
-    lifecycle: Arc<dyn ConnectionLifecycle>,
-    _connection_guard: Box<dyn ConnectionGuard>,
-}
-
-async fn serve_responses_websocket(mut socket: WebSocket, session: ResponsesWebSocketSession) {
-    tracing::info!(
-        websocket_connection_id = %session.connection_id,
-        "Responses WebSocket connected"
-    );
-    let mut request_count = 0_u64;
-    let mut replay = ConnectionReplaySnapshot::default();
-
-    let cancellation = session.lifecycle.cancellation();
-    loop {
-        let message = tokio::select! {
-            () = cancellation.cancelled() => break,
-            message = socket.next() => message,
-        };
-        let Some(message) = message else {
-            break;
-        };
-        let payload = match message {
-            Ok(Message::Text(payload)) => payload,
-            Ok(Message::Ping(_) | Message::Pong(_)) => continue,
-            Ok(Message::Close(_)) => break,
-            Ok(Message::Binary(_)) => {
-                close_for_protocol_violation(&mut socket, TEXT_FRAMES_ONLY).await;
-                break;
-            }
-            Err(error) => {
-                tracing::info!(
-                    websocket_connection_id = %session.connection_id,
-                    error = %error,
-                    "Responses WebSocket receive failed"
-                );
-                break;
-            }
-        };
-        request_count = request_count.saturating_add(1);
-        let correlation_id = session.service.next_request_id();
-        let decoded =
-            match decode_response_create_with_context(payload.as_str(), &session.request_headers) {
-                Ok(decoded) => {
-                    decoded.with_client_context(session.client_ip, session.user_agent.clone())
-                }
-                Err(error) => {
-                    tracing::info!(
-                        websocket_connection_id = %session.connection_id,
-                        request_id = %correlation_id,
-                        error = %error,
-                        "Responses WebSocket request rejected"
-                    );
-                    if send_protocol_error(
-                        &mut socket,
-                        StatusCode::BAD_REQUEST,
-                        error.protocol_body(),
-                        &correlation_id,
-                    )
-                    .await
-                        == ForwardOutcome::Disconnect
-                    {
-                        break;
-                    }
-                    continue;
-                }
-            };
-        let decoded = replay.prepare(decoded);
-        let started = match session
-            .service
-            .start_response(
-                session.client.clone(),
-                decoded,
-                ClientTransport::WebSocket,
-                "/v1/responses",
-            )
-            .await
-        {
-            Ok(started) => started,
-            Err(error) => {
-                if send_gateway_error(&mut socket, &error, &correlation_id).await
-                    == ForwardOutcome::Disconnect
-                {
-                    break;
-                }
-                continue;
-            }
-        };
-
-        if forward_execution(&mut socket, started, &mut replay).await == ForwardOutcome::Disconnect
-        {
-            break;
-        }
-    }
-
-    tracing::info!(
-        websocket_connection_id = %session.connection_id,
-        request_count,
-        "Responses WebSocket disconnected"
-    );
-}
-
-#[derive(Clone, Copy, PartialEq, Eq)]
-enum ForwardOutcome {
-    Continue,
-    Disconnect,
-}
-
-#[derive(Default)]
-struct ConnectionReplaySnapshot {
-    last_response_id: Option<String>,
-    provider_state: Option<ProviderSessionState>,
-}
-
-impl ConnectionReplaySnapshot {
-    fn prepare(&self, request: DecodedResponsesRequest) -> DecodedResponsesRequest {
-        match (
-            request.metadata().continuation().previous_response_id(),
-            self.last_response_id.as_deref(),
-            self.provider_state.as_ref(),
-        ) {
-            (Some(previous), Some(last), Some(state)) if previous == last => {
-                request.with_provider_session_state(state.clone())
-            }
-            _ => request,
-        }
-    }
-
-    fn commit(&mut self, response_id: String, provider_state: Option<ProviderSessionState>) {
-        self.last_response_id = Some(response_id);
-        self.provider_state = provider_state;
-    }
-}
-
-async fn forward_execution(
-    socket: &mut WebSocket,
-    started: StartedExecution,
-    replay: &mut ConnectionReplaySnapshot,
-) -> ForwardOutcome {
-    let request_id = started.request_id.to_string();
-    let streaming = started.stream;
-    let mut execution = PendingExecution::new(started.session);
-    if !streaming {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "WebSocket execution was not initialized as a stream",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let first = loop {
-        match next_active_input(socket, &mut execution).await {
-            ActiveInput::Event(Ok(Some(event))) => break event,
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended before its first event",
-                );
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Control => continue,
-            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return ForwardOutcome::Disconnect;
-            }
-        }
-    };
-    let requirement = first.commit_requirement();
-    let mut first = first.into_provider_events();
-    if requirement != CommitRequirement::CommitBeforeDelivery {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway first event did not require commit",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let mut encoder = OpenAiResponsesEncoder::new();
-    let mut provider_state = None;
-    let mut first_messages = Vec::new();
-    for event in &mut first {
-        if let Some(update) = event.take_session_update() {
-            provider_state = Some(update);
-        }
-        first_messages.extend(encoder.push_websocket(event));
-    }
-    if first_messages.is_empty() {
-        let error = GatewayError::new(
-            GatewayErrorKind::Internal,
-            "gateway commit batch encoded no output",
-        );
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    let Some(response_session) = execution.session_mut() else {
-        return ForwardOutcome::Disconnect;
-    };
-    let response_headers = response_session.response_headers().to_vec();
-    if let Err(error) = response_session.commit_downstream(None).await {
-        let error = gateway_error_from_engine(&error);
-        return send_gateway_error(socket, &error, &request_id).await;
-    }
-    if encoder.is_completed() {
-        if let Err(outcome) = confirm_completed_execution(socket, &mut execution, &request_id).await
-        {
-            return outcome;
-        }
-        commit_connection_replay(replay, &encoder, provider_state.take());
-        if !send_text(
-            socket,
-            response_metadata_event(&request_id, &response_headers),
-        )
-        .await
-            || !send_messages(socket, first_messages).await
-        {
-            return ForwardOutcome::Disconnect;
-        }
-        execution.disarm();
-        return ForwardOutcome::Continue;
-    }
-    if !send_text(
-        socket,
-        response_metadata_event(&request_id, &response_headers),
-    )
-    .await
-        || !send_messages(socket, first_messages).await
-    {
-        return ForwardOutcome::Disconnect;
-    }
-
-    loop {
-        match next_active_input(socket, &mut execution).await {
-            ActiveInput::Event(Ok(Some(delivery))) => {
-                let requirement = delivery.commit_requirement();
-                let mut events = delivery.into_provider_events();
-                if requirement != CommitRequirement::AlreadyCommitted {
-                    let error = GatewayError::new(
-                        GatewayErrorKind::Internal,
-                        "gateway requested another downstream commit",
-                    );
-                    return send_gateway_error(socket, &error, &request_id).await;
-                }
-                let mut messages = Vec::new();
-                for event in &mut events {
-                    if let Some(update) = event.take_session_update() {
-                        provider_state = Some(update);
-                    }
-                    messages.extend(encoder.push_websocket(event));
-                }
-                if encoder.is_completed() {
-                    if let Err(outcome) =
-                        confirm_completed_execution(socket, &mut execution, &request_id).await
-                    {
-                        return outcome;
-                    }
-                    commit_connection_replay(replay, &encoder, provider_state.take());
-                    if !send_messages(socket, messages).await {
-                        return ForwardOutcome::Disconnect;
-                    }
-                    execution.disarm();
-                    return ForwardOutcome::Continue;
-                }
-                if !send_messages(socket, messages).await {
-                    return ForwardOutcome::Disconnect;
-                }
-            }
-            ActiveInput::Event(Ok(None)) => {
-                if execution
-                    .session_mut()
-                    .is_some_and(|session| session.is_finalized())
-                {
-                    commit_connection_replay(replay, &encoder, provider_state.take());
-                    execution.disarm();
-                    return ForwardOutcome::Continue;
-                }
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response ended without finalizing the execution",
-                );
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Event(Err(error)) => {
-                if encoder.has_wire_failure() {
-                    execution.disarm();
-                    return ForwardOutcome::Continue;
-                }
-                let error = gateway_error_from_engine(&error);
-                return send_gateway_error(socket, &error, &request_id).await;
-            }
-            ActiveInput::Control => {}
-            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return ForwardOutcome::Disconnect;
-            }
-        }
-    }
-}
-
-fn commit_connection_replay(
-    replay: &mut ConnectionReplaySnapshot,
-    encoder: &OpenAiResponsesEncoder,
-    provider_state: Option<ProviderSessionState>,
-) {
-    if let Some(response_id) = encoder.response_id() {
-        replay.commit(response_id.to_owned(), provider_state);
-    }
-}
-
-async fn confirm_completed_execution(
-    socket: &mut WebSocket,
-    execution: &mut PendingExecution,
-    request_id: &str,
-) -> Result<(), ForwardOutcome> {
-    loop {
-        match next_active_input(socket, execution).await {
-            ActiveInput::Event(Ok(None))
-                if execution
-                    .session_mut()
-                    .is_some_and(|session| session.is_finalized()) =>
-            {
-                return Ok(());
-            }
-            ActiveInput::Event(Ok(None)) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response was not finalized after its terminal event",
-                );
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Event(Ok(Some(_))) => {
-                let error = GatewayError::new(
-                    GatewayErrorKind::Internal,
-                    "gateway response continued after its terminal event",
-                );
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Event(Err(error)) => {
-                let error = gateway_error_from_engine(&error);
-                return Err(send_gateway_error(socket, &error, request_id).await);
-            }
-            ActiveInput::Control => {}
-            ActiveInput::Disconnect => return Err(ForwardOutcome::Disconnect),
-            ActiveInput::ProtocolViolation => {
-                close_for_protocol_violation(socket, ACTIVE_RESPONSE_VIOLATION).await;
-                return Err(ForwardOutcome::Disconnect);
-            }
-        }
-    }
-}
-
-enum ActiveInput {
-    Event(Result<Option<CoordinatedEvent>, EngineError>),
-    Control,
-    Disconnect,
-    ProtocolViolation,
-}
-
-async fn next_active_input(
-    socket: &mut WebSocket,
-    execution: &mut PendingExecution,
-) -> ActiveInput {
-    let Some(session) = execution.session_mut() else {
-        return ActiveInput::Disconnect;
-    };
-    tokio::select! {
-        event = session.next_event() => ActiveInput::Event(event),
-        message = socket.next() => match message {
-            Some(Ok(Message::Ping(_) | Message::Pong(_))) => ActiveInput::Control,
-            Some(Ok(Message::Close(_))) | None | Some(Err(_)) => ActiveInput::Disconnect,
-            Some(Ok(Message::Text(_) | Message::Binary(_))) => ActiveInput::ProtocolViolation,
-        },
-    }
-}
-
-/// 使用连接级请求头和 Provider 上下文解码官方 `response.create` 文本帧。
-///
-/// 缺省 `stream` 等价于 WebSocket 固有的流式语义；显式 `false` 会被拒绝。
-///
-/// # Errors
-///
-/// 帧不是合法 JSON object、消息类型错误、显式关闭 stream，或 Responses 请求
-/// 无法映射到 canonical operation 时返回不包含正文内容的稳定错误。
-pub fn decode_response_create_with_context(
-    payload: &str,
-    request_headers: &OpenAiRequestHeaders,
-) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
-    decode_response_create_inner(payload, request_headers)
-}
-
-fn decode_response_create_inner(
-    payload: &str,
-    request_headers: &OpenAiRequestHeaders,
-) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
-    let Value::Object(mut body) = serde_json::from_str::<Value>(payload)
-        .map_err(|_| ResponseCreateFrameError::InvalidJson)?
-    else {
-        return Err(ResponseCreateFrameError::ExpectedObject);
-    };
-    match body.remove("type") {
-        Some(Value::String(message_type)) if message_type == "response.create" => {}
-        _ => return Err(ResponseCreateFrameError::UnsupportedType),
-    }
-    if matches!(body.get("stream"), Some(value) if value.as_bool() != Some(true)) {
-        return Err(ResponseCreateFrameError::StreamingRequired);
-    }
-    super::request::decode_request_object(body, false, request_headers)
-        .map_err(ResponseCreateFrameError::Request)
-}
-
-/// `response.create` 帧的稳定安全错误。
-#[derive(Debug, Clone, PartialEq, Eq, Error)]
-pub enum ResponseCreateFrameError {
-    /// 文本不是合法 JSON。
-    #[error("response.create frame must be valid JSON")]
-    InvalidJson,
-    /// 顶层不是 object。
-    #[error("response.create frame must be a JSON object")]
-    ExpectedObject,
-    /// `type` 缺失或不是 `response.create`。
-    #[error("unsupported Responses WebSocket message type")]
-    UnsupportedType,
-    /// WebSocket 请求显式声明 `stream=false`。
-    #[error("Responses WebSocket requests require stream=true")]
-    StreamingRequired,
-    /// 内层 Responses 请求无法映射到 canonical operation。
-    #[error(transparent)]
-    Request(RequestDecodeError),
-}
-
-impl ResponseCreateFrameError {
-    fn protocol_body(&self) -> ProtocolErrorBody {
-        match self {
-            Self::Request(error) => error.protocol_body(),
-            Self::InvalidJson => RequestDecodeError::MalformedJson.protocol_body(),
-            Self::ExpectedObject => RequestDecodeError::ExpectedObject.protocol_body(),
-            Self::UnsupportedType => RequestDecodeError::InvalidValue {
-                field: "type".to_owned(),
-            }
-            .protocol_body(),
-            Self::StreamingRequired => RequestDecodeError::InvalidValue {
-                field: "stream".to_owned(),
-            }
-            .protocol_body(),
-        }
-    }
-}
-
-fn response_metadata_event(
-    request_id: &str,
-    response_headers: &[ProviderResponseHeader],
-) -> String {
-    let connection_options = super::response_connection_options(response_headers);
-    let mut headers = Map::new();
-    for header in response_headers {
-        if !super::response_header_is_forwardable(header.name(), &connection_options) {
-            continue;
-        }
-        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
-            continue;
-        };
-        let Ok(value) = std::str::from_utf8(header.value()) else {
-            continue;
-        };
-        // 官方 response.metadata 使用 string map，无法表达同名多值；后值保持既有覆盖语义。
-        headers.insert(name.as_str().to_owned(), Value::String(value.to_owned()));
-    }
-    headers
-        .entry("x-request-id".to_owned())
-        .or_insert_with(|| Value::String(request_id.to_owned()));
-    json!({
-        "type": "response.metadata",
-        "headers": headers,
-    })
-    .to_string()
-}
-
-async fn send_gateway_error(
-    socket: &mut WebSocket,
-    error: &GatewayError,
-    request_id: &str,
-) -> ForwardOutcome {
-    let (status, default_type, default_code) = gateway_error_contract(error.kind());
-    if send_error_event(
-        socket,
-        status,
-        error.client_error_type().unwrap_or(default_type),
-        error.client_error_code().unwrap_or(default_code),
-        error.client_message(),
-        None,
-        request_id,
-    )
-    .await
-    {
-        ForwardOutcome::Continue
-    } else {
-        ForwardOutcome::Disconnect
-    }
-}
-
-async fn send_protocol_error(
-    socket: &mut WebSocket,
-    status: StatusCode,
-    body: ProtocolErrorBody,
-    request_id: &str,
-) -> ForwardOutcome {
-    let error = body.error;
-    if send_error_event(
-        socket,
-        status,
-        error.kind,
-        error.code,
-        &error.message,
-        error.param.as_deref(),
-        request_id,
-    )
-    .await
-    {
-        ForwardOutcome::Continue
-    } else {
-        ForwardOutcome::Disconnect
-    }
-}
-
-async fn send_error_event(
-    socket: &mut WebSocket,
-    status: StatusCode,
-    error_type: &str,
-    code: &str,
-    message: &str,
-    param: Option<&str>,
-    request_id: &str,
-) -> bool {
-    let mut error = Map::new();
-    error.insert("type".to_owned(), Value::String(error_type.to_owned()));
-    error.insert("code".to_owned(), Value::String(code.to_owned()));
-    error.insert("message".to_owned(), Value::String(message.to_owned()));
-    if let Some(param) = param {
-        error.insert("param".to_owned(), Value::String(param.to_owned()));
-    }
-    send_text(
-        socket,
-        json!({
-            "type": "error",
-            "status": status.as_u16(),
-            "error": error,
-            "request_id": request_id,
-        })
-        .to_string(),
-    )
-    .await
-}
-
-async fn send_messages(socket: &mut WebSocket, messages: Vec<String>) -> bool {
-    for message in messages {
-        if !send_text(socket, message).await {
-            return false;
-        }
-    }
-    true
-}
-
-async fn send_text(socket: &mut WebSocket, payload: String) -> bool {
-    if let Err(error) = socket.send(Message::Text(payload.into())).await {
-        tracing::info!(error = %error, "Responses WebSocket send failed");
-        return false;
-    }
-    true
-}
-
-async fn close_for_protocol_violation(socket: &mut WebSocket, reason: &'static str) {
-    let _ = socket
-        .send(Message::Close(Some(CloseFrame {
-            code: close_code::POLICY,
-            reason: reason.into(),
-        })))
-        .await;
-}

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

@@ -0,0 +1,672 @@
+//! 下游客户端 WebSocket 的单 owner pump 与有界收发边界。
+
+use std::{
+    fmt,
+    sync::{
+        Arc,
+        atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
+    },
+    time::Duration,
+};
+
+use axum::extract::ws::{CloseFrame, Message, WebSocket, close_code};
+use futures::{Sink, SinkExt, Stream, StreamExt};
+use gateway_core::lifecycle::CancellationToken;
+use thiserror::Error;
+use tokio::{
+    sync::{mpsc, oneshot},
+    task::JoinHandle,
+    time::{Instant, timeout},
+};
+
+const OUTBOUND_COMMAND_BUFFER: usize = 32;
+const INBOUND_EVENT_BUFFER: usize = 32;
+const DOWNSTREAM_WRITE_TIMEOUT: Duration = Duration::from_secs(5 * 60);
+const CONNECTION_MAX_AGE: Duration = Duration::from_secs(60 * 60);
+const DOWNSTREAM_PING_INTERVAL: Duration = Duration::from_secs(25);
+
+/// WebSocket pump 的写入与生命周期预算。
+#[derive(Clone, Copy)]
+pub struct ConnectionConfig {
+    write_timeout: Duration,
+    max_age: Duration,
+}
+
+impl ConnectionConfig {
+    /// 生产环境固定预算。
+    pub const PRODUCTION: Self = Self {
+        write_timeout: DOWNSTREAM_WRITE_TIMEOUT,
+        max_age: CONNECTION_MAX_AGE,
+    };
+}
+
+/// 业务层可观察的客户端输入；Ping/Pong 始终由 pump 消费。
+pub enum ConnectionEvent {
+    Text(String),
+    Binary,
+    Expired,
+    Exited(PumpExitReason),
+}
+
+/// 下游写入阶段；名称刻意使用 write，而不是暗示客户端已消费的 delivery。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum FramePhase {
+    Metadata,
+    First,
+    Data,
+    Terminal,
+    FirstAndTerminal,
+    Error,
+    ConnectionLimit,
+    Close,
+}
+
+impl FramePhase {
+    const fn as_str(self) -> &'static str {
+        match self {
+            Self::Metadata => "metadata",
+            Self::First => "first",
+            Self::Data => "data",
+            Self::Terminal => "terminal",
+            Self::FirstAndTerminal => "first_and_terminal",
+            Self::Error => "error",
+            Self::ConnectionLimit => "connection_limit",
+            Self::Close => "close",
+        }
+    }
+
+    const fn is_milestone(self) -> bool {
+        matches!(
+            self,
+            Self::First
+                | Self::Terminal
+                | Self::FirstAndTerminal
+                | Self::Error
+                | Self::ConnectionLimit
+                | Self::Close
+        )
+    }
+}
+
+/// 一次下游写入的请求归属与协议阶段。
+#[derive(Clone)]
+pub struct WriteContext {
+    request_id: Option<Arc<str>>,
+    phase: FramePhase,
+}
+
+impl WriteContext {
+    /// 创建归属于某个请求的写入上下文。
+    #[must_use]
+    pub fn request(request_id: &Arc<str>, phase: FramePhase) -> Self {
+        Self {
+            request_id: Some(Arc::clone(request_id)),
+            phase,
+        }
+    }
+
+    /// 创建连接级写入上下文。
+    #[must_use]
+    pub const fn connection(phase: FramePhase) -> Self {
+        Self {
+            request_id: None,
+            phase,
+        }
+    }
+}
+
+/// WebSocket pump 停止的稳定原因。
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum PumpExitReason {
+    ClientClose,
+    PeerEof,
+    ReadError,
+    WriteError,
+    WriteTimeout,
+    LifecycleShutdown,
+    ConnectionMaxAge,
+    CoordinatorDropped,
+    InboundOverload,
+    ServerClose,
+    PumpStopped,
+}
+
+impl PumpExitReason {
+    pub(super) const fn as_str(self) -> &'static str {
+        match self {
+            Self::ClientClose => "client_close",
+            Self::PeerEof => "peer_eof",
+            Self::ReadError => "read_error",
+            Self::WriteError => "write_error",
+            Self::WriteTimeout => "write_timeout",
+            Self::LifecycleShutdown => "lifecycle_shutdown",
+            Self::ConnectionMaxAge => "connection_max_age",
+            Self::CoordinatorDropped => "coordinator_dropped",
+            Self::InboundOverload => "inbound_overload",
+            Self::ServerClose => "server_close",
+            Self::PumpStopped => "pump_stopped",
+        }
+    }
+}
+
+/// 下游 WebSocket 写入失败。
+#[derive(Debug, Error)]
+pub enum ConnectionWriteError {
+    #[error("downstream WebSocket pump is closed")]
+    Closed,
+    #[error("downstream WebSocket write timed out after {timeout:?}")]
+    Timeout { timeout: Duration },
+    #[error("downstream WebSocket transport write failed: {message}")]
+    Transport { message: String },
+}
+
+struct ConnectionCommand {
+    message: Message,
+    context: WriteContext,
+    acknowledged: oneshot::Sender<Result<(), ConnectionWriteError>>,
+}
+
+#[derive(Default)]
+struct ConnectionStats {
+    command_queue_high_water: AtomicUsize,
+    command_backpressure_count: AtomicU64,
+    ping_received_count: AtomicU64,
+    pong_written_count: AtomicU64,
+    ping_written_count: AtomicU64,
+    pong_received_count: AtomicU64,
+    last_read_ms: AtomicU64,
+    last_write_ms: AtomicU64,
+}
+
+impl ConnectionStats {
+    fn record_read(&self, opened_at: Instant) {
+        self.last_read_ms.store(
+            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
+            Ordering::Relaxed,
+        );
+    }
+
+    fn record_write(&self, opened_at: Instant) {
+        self.last_write_ms.store(
+            u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
+            Ordering::Relaxed,
+        );
+    }
+
+    fn observe_command_queue(&self, sender: &mpsc::Sender<ConnectionCommand>) {
+        let queued = OUTBOUND_COMMAND_BUFFER
+            .saturating_sub(sender.capacity())
+            .saturating_add(1)
+            .min(OUTBOUND_COMMAND_BUFFER);
+        self.command_queue_high_water
+            .fetch_max(queued, Ordering::Relaxed);
+        if sender.capacity() == 0 {
+            self.command_backpressure_count
+                .fetch_add(1, Ordering::Relaxed);
+        }
+    }
+}
+
+/// 协调层持有的单 owner WebSocket 连接句柄。
+pub struct ResponsesWebSocketConnection {
+    connection_id: Arc<str>,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    commands: Option<mpsc::Sender<ConnectionCommand>>,
+    incoming: mpsc::Receiver<ConnectionEvent>,
+    exited: oneshot::Receiver<PumpExitReason>,
+    pump_task: Option<JoinHandle<()>>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+    exit_reason: Option<PumpExitReason>,
+}
+
+impl ResponsesWebSocketConnection {
+    pub(super) fn new(
+        socket: WebSocket,
+        connection_id: String,
+        cancellation: CancellationToken,
+    ) -> Self {
+        spawn_connection(
+            socket,
+            Arc::<str>::from(connection_id),
+            cancellation,
+            ConnectionConfig::PRODUCTION,
+        )
+    }
+
+    pub(super) fn id(&self) -> &str {
+        &self.connection_id
+    }
+
+    /// 返回连接是否已经达到生命周期上限。
+    #[must_use]
+    pub fn is_expired(&self) -> bool {
+        self.expired.load(Ordering::Acquire)
+    }
+
+    pub(super) fn age(&self) -> Duration {
+        self.opened_at.elapsed()
+    }
+
+    /// 等待下一个需要业务层处理的客户端事件。
+    pub async fn next_event(&mut self) -> Option<ConnectionEvent> {
+        if let Some(reason) = self.exit_reason {
+            return Some(ConnectionEvent::Exited(reason));
+        }
+        let event = tokio::select! {
+            biased;
+            reason = &mut self.exited => {
+                Some(ConnectionEvent::Exited(reason.unwrap_or(PumpExitReason::PumpStopped)))
+            }
+            event = self.incoming.recv() => event,
+        };
+        if let Some(ConnectionEvent::Exited(reason)) = event.as_ref() {
+            self.exit_reason.get_or_insert(*reason);
+        } else if event.is_none() {
+            self.exit_reason.get_or_insert(PumpExitReason::PumpStopped);
+        }
+        event
+    }
+
+    /// 等待连接退出，不消费留给后续串行请求的业务帧。
+    pub async fn wait_for_exit(&mut self) -> PumpExitReason {
+        if let Some(reason) = self.exit_reason {
+            return reason;
+        }
+        let reason = (&mut self.exited)
+            .await
+            .unwrap_or(PumpExitReason::PumpStopped);
+        self.exit_reason = Some(reason);
+        reason
+    }
+
+    /// 串行写入文本帧，并等待 pump 确认 transport 写入结果。
+    ///
+    /// # Errors
+    ///
+    /// pump 已关闭、写入超时或 transport 失败时返回稳定错误。
+    pub async fn send_text(
+        &mut self,
+        payload: String,
+        context: WriteContext,
+    ) -> Result<(), ConnectionWriteError> {
+        self.send(Message::Text(payload.into()), context).await
+    }
+
+    pub(super) async fn close_policy(
+        &mut self,
+        reason: &'static str,
+        request_id: Option<&Arc<str>>,
+    ) {
+        let context = request_id.map_or_else(
+            || WriteContext::connection(FramePhase::Close),
+            |request_id| WriteContext::request(request_id, FramePhase::Close),
+        );
+        self.close(
+            CloseFrame {
+                code: close_code::POLICY,
+                reason: reason.into(),
+            },
+            context,
+            PumpExitReason::ServerClose,
+        )
+        .await;
+    }
+
+    pub(super) async fn close_for_connection_limit(&mut self, reason: &'static str) {
+        self.close(
+            CloseFrame {
+                code: close_code::NORMAL,
+                reason: reason.into(),
+            },
+            WriteContext::connection(FramePhase::Close),
+            PumpExitReason::ConnectionMaxAge,
+        )
+        .await;
+    }
+
+    async fn close(
+        &mut self,
+        frame: CloseFrame,
+        context: WriteContext,
+        exit_reason: PumpExitReason,
+    ) {
+        if self
+            .send(Message::Close(Some(frame)), context)
+            .await
+            .is_ok()
+        {
+            self.exit_reason.get_or_insert(exit_reason);
+        }
+    }
+
+    async fn send(
+        &mut self,
+        message: Message,
+        context: WriteContext,
+    ) -> Result<(), ConnectionWriteError> {
+        let Some(commands) = self.commands.as_ref().cloned() else {
+            return Err(ConnectionWriteError::Closed);
+        };
+        self.stats.observe_command_queue(&commands);
+        let (acknowledged, acknowledgement) = oneshot::channel();
+        let started_at = Instant::now();
+        let request_id = context.request_id.clone();
+        let phase = context.phase;
+        let command = ConnectionCommand {
+            message,
+            context,
+            acknowledged,
+        };
+        let write = async move {
+            commands
+                .send(command)
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?;
+            acknowledgement
+                .await
+                .map_err(|_| ConnectionWriteError::Closed)?
+        };
+        let result = match timeout(self.config.write_timeout, write).await {
+            Ok(result) => result,
+            Err(_) => Err(ConnectionWriteError::Timeout {
+                timeout: self.config.write_timeout,
+            }),
+        };
+        let duration = started_at.elapsed();
+        match &result {
+            Ok(()) if phase.is_milestone() => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                "Responses WebSocket frame write succeeded"
+            ),
+            Ok(()) => tracing::debug!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                "Responses WebSocket frame write succeeded"
+            ),
+            Err(error) => tracing::info!(
+                websocket_connection_id = %self.connection_id,
+                request_id = request_id.as_deref().unwrap_or(""),
+                frame_phase = phase.as_str(),
+                write_duration_ms = duration.as_millis(),
+                error = %error,
+                "Responses WebSocket frame write failed"
+            ),
+        }
+        if let Err(error) = &result {
+            let reason = match error {
+                ConnectionWriteError::Timeout { .. } => PumpExitReason::WriteTimeout,
+                ConnectionWriteError::Transport { .. } => PumpExitReason::WriteError,
+                ConnectionWriteError::Closed => PumpExitReason::PumpStopped,
+            };
+            self.terminate(reason);
+        }
+        result
+    }
+
+    fn terminate(&mut self, reason: PumpExitReason) {
+        self.exit_reason.get_or_insert(reason);
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+
+    pub(super) fn log_summary(&self, request_count: u64) {
+        let connection_age_ms = self.age().as_millis();
+        let read_idle_ms = connection_age_ms
+            .saturating_sub(u128::from(self.stats.last_read_ms.load(Ordering::Relaxed)));
+        let write_idle_ms = connection_age_ms
+            .saturating_sub(u128::from(self.stats.last_write_ms.load(Ordering::Relaxed)));
+        tracing::info!(
+            websocket_connection_id = %self.connection_id,
+            request_count,
+            connection_age_ms,
+            pump_exit_reason = self
+                .exit_reason
+                .map_or("unknown", PumpExitReason::as_str),
+            command_queue_high_water = self
+                .stats
+                .command_queue_high_water
+                .load(Ordering::Relaxed),
+            command_backpressure_count = self
+                .stats
+                .command_backpressure_count
+                .load(Ordering::Relaxed),
+            ping_received_count = self.stats.ping_received_count.load(Ordering::Relaxed),
+            pong_written_count = self.stats.pong_written_count.load(Ordering::Relaxed),
+            ping_written_count = self.stats.ping_written_count.load(Ordering::Relaxed),
+            pong_received_count = self.stats.pong_received_count.load(Ordering::Relaxed),
+            read_idle_ms,
+            write_idle_ms,
+            "Responses WebSocket disconnected"
+        );
+    }
+}
+
+impl Drop for ResponsesWebSocketConnection {
+    fn drop(&mut self) {
+        self.commands.take();
+        if let Some(task) = self.pump_task.take() {
+            task.abort();
+        }
+    }
+}
+
+/// 为一个 socket 启动单 owner pump，并返回协调层句柄。
+pub fn spawn_connection<S, E>(
+    socket: S,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    config: ConnectionConfig,
+) -> ResponsesWebSocketConnection
+where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin + Send + 'static,
+    E: fmt::Display + Send + 'static,
+{
+    let opened_at = Instant::now();
+    let expired = Arc::new(AtomicBool::new(false));
+    let stats = Arc::new(ConnectionStats::default());
+    let (command_tx, command_rx) = mpsc::channel(OUTBOUND_COMMAND_BUFFER);
+    let (incoming_tx, incoming_rx) = mpsc::channel(INBOUND_EVENT_BUFFER);
+    let (exit_tx, exit_rx) = oneshot::channel();
+    let pump_task = tokio::spawn(run_pump(
+        socket,
+        command_rx,
+        incoming_tx,
+        exit_tx,
+        Arc::clone(&connection_id),
+        cancellation,
+        opened_at,
+        Arc::clone(&expired),
+        Arc::clone(&stats),
+        config,
+    ));
+    ResponsesWebSocketConnection {
+        connection_id,
+        opened_at,
+        expired,
+        commands: Some(command_tx),
+        incoming: incoming_rx,
+        exited: exit_rx,
+        pump_task: Some(pump_task),
+        stats,
+        config,
+        exit_reason: None,
+    }
+}
+
+#[expect(clippy::too_many_arguments)]
+async fn run_pump<S, E>(
+    mut socket: S,
+    mut commands: mpsc::Receiver<ConnectionCommand>,
+    incoming: mpsc::Sender<ConnectionEvent>,
+    exited: oneshot::Sender<PumpExitReason>,
+    connection_id: Arc<str>,
+    cancellation: CancellationToken,
+    opened_at: Instant,
+    expired: Arc<AtomicBool>,
+    stats: Arc<ConnectionStats>,
+    config: ConnectionConfig,
+) where
+    S: Stream<Item = Result<Message, E>> + Sink<Message, Error = E> + Unpin,
+    E: fmt::Display,
+{
+    let deadline = tokio::time::sleep_until(opened_at + config.max_age);
+    tokio::pin!(deadline);
+    let mut deadline_elapsed = false;
+    let mut heartbeat = tokio::time::interval_at(
+        opened_at + DOWNSTREAM_PING_INTERVAL,
+        DOWNSTREAM_PING_INTERVAL,
+    );
+    heartbeat.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
+    let mut ping_sequence = 0_u64;
+    let reason = loop {
+        tokio::select! {
+            biased;
+            () = cancellation.cancelled() => break PumpExitReason::LifecycleShutdown,
+            () = &mut deadline, if !deadline_elapsed => {
+                deadline_elapsed = true;
+                expired.store(true, Ordering::Release);
+                // 满队列本身已能唤醒空闲协调层；到期标志仍阻止启动下一轮。
+                // 不能因无法追加 Expired 通知而中断正在收尾的响应。
+                match incoming.try_send(ConnectionEvent::Expired) {
+                    Ok(()) | Err(mpsc::error::TrySendError::Full(_)) => {}
+                    Err(mpsc::error::TrySendError::Closed(_)) => {
+                        break PumpExitReason::CoordinatorDropped;
+                    }
+                }
+            }
+            command = commands.recv() => {
+                let Some(command) = command else {
+                    break PumpExitReason::CoordinatorDropped;
+                };
+                let ConnectionCommand {
+                    message,
+                    context,
+                    acknowledged,
+                } = command;
+                let closing = matches!(message, Message::Close(_));
+                let result = socket.send(message).await.map_err(|error| {
+                    let message = error.to_string();
+                    tracing::debug!(
+                        websocket_connection_id = %connection_id,
+                        request_id = context.request_id.as_deref().unwrap_or(""),
+                        frame_phase = context.phase.as_str(),
+                        error = %message,
+                        "Responses WebSocket pump transport write failed"
+                    );
+                    ConnectionWriteError::Transport { message }
+                });
+                let failed = result.is_err();
+                if !failed {
+                    stats.record_write(opened_at);
+                }
+                let _ = acknowledged.send(result);
+                if failed {
+                    break PumpExitReason::WriteError;
+                }
+                if closing {
+                    break PumpExitReason::ServerClose;
+                }
+            }
+            // 官方 Codex WsStream 在独立 pump 中回复 Pong，且不将控制帧交给业务流。
+            // 这里只为下游链路保活，不设置 Pong deadline，也不延长业务请求预算。
+            _ = heartbeat.tick() => {
+                ping_sequence = ping_sequence.wrapping_add(1);
+                let ping = Message::Ping(ping_sequence.to_be_bytes().to_vec().into());
+                let result = tokio::select! {
+                    biased;
+                    () = cancellation.cancelled() => break PumpExitReason::LifecycleShutdown,
+                    result = timeout(config.write_timeout, socket.send(ping)) => result,
+                };
+                match result {
+                    Ok(Ok(())) => {
+                        stats.ping_written_count.fetch_add(1, Ordering::Relaxed);
+                        stats.record_write(opened_at);
+                    }
+                    Ok(Err(error)) => {
+                        tracing::info!(
+                            websocket_connection_id = %connection_id,
+                            error = %error,
+                            "Responses WebSocket Ping write failed"
+                        );
+                        break PumpExitReason::WriteError;
+                    }
+                    Err(_) => break PumpExitReason::WriteTimeout,
+                }
+            }
+            message = socket.next() => {
+                if matches!(&message, Some(Ok(_))) {
+                    stats.record_read(opened_at);
+                }
+                match message {
+                    Some(Ok(Message::Text(payload))) => {
+                        if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Text(payload.to_string())) {
+                            break reason;
+                        }
+                    }
+                    Some(Ok(Message::Binary(_))) => {
+                        if let Err(reason) = emit_incoming(&incoming, ConnectionEvent::Binary) {
+                            break reason;
+                        }
+                    }
+                    Some(Ok(Message::Ping(payload))) => {
+                        stats.ping_received_count.fetch_add(1, Ordering::Relaxed);
+                        match timeout(config.write_timeout, socket.send(Message::Pong(payload))).await {
+                            Ok(Ok(())) => {
+                                stats.pong_written_count.fetch_add(1, Ordering::Relaxed);
+                                stats.record_write(opened_at);
+                            }
+                            Ok(Err(error)) => {
+                                tracing::info!(
+                                    websocket_connection_id = %connection_id,
+                                    error = %error,
+                                    "Responses WebSocket Pong write failed"
+                                );
+                                break PumpExitReason::WriteError;
+                            }
+                            Err(_) => break PumpExitReason::WriteTimeout,
+                        }
+                    }
+                    Some(Ok(Message::Pong(_))) => {
+                        stats.pong_received_count.fetch_add(1, Ordering::Relaxed);
+                    }
+                    Some(Ok(Message::Close(_))) => break PumpExitReason::ClientClose,
+                    Some(Err(error)) => {
+                        tracing::info!(
+                            websocket_connection_id = %connection_id,
+                            error = %error,
+                            "Responses WebSocket receive failed"
+                        );
+                        break PumpExitReason::ReadError;
+                    }
+                    None => break PumpExitReason::PeerEof,
+                }
+            },
+        }
+    };
+    // 退出不能排在待执行请求之后，也不能因业务队列已满而丢失。
+    let _ = exited.send(reason);
+    tracing::debug!(
+        websocket_connection_id = %connection_id,
+        pump_exit_reason = reason.as_str(),
+        "Responses WebSocket pump exited"
+    );
+}
+
+fn emit_incoming(
+    incoming: &mpsc::Sender<ConnectionEvent>,
+    event: ConnectionEvent,
+) -> Result<(), PumpExitReason> {
+    incoming.try_send(event).map_err(|error| match error {
+        mpsc::error::TrySendError::Full(_) => PumpExitReason::InboundOverload,
+        mpsc::error::TrySendError::Closed(_) => PumpExitReason::CoordinatorDropped,
+    })
+}

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

@@ -0,0 +1,481 @@
+//! 已启动 Responses execution 到客户端 WebSocket wire event 的串行转发。
+
+use std::sync::Arc;
+
+use axum::http::StatusCode;
+use gateway_core::engine::execution::StartedExecution;
+use gateway_core::engine::{CommitRequirement, CoordinatedEvent, EngineError};
+use gateway_core::error::{GatewayError, GatewayErrorKind};
+use gateway_core::operation::ProviderSessionState;
+use tokio::time::Instant;
+
+use crate::openai::error::{gateway_error_contract, gateway_error_from_engine};
+
+use super::{
+    super::{DecodedResponsesRequest, OpenAiResponsesEncoder, PendingExecution, ProtocolErrorBody},
+    connection::{FramePhase, ResponsesWebSocketConnection, WriteContext},
+    protocol::{error_event, response_metadata_event},
+};
+
+#[derive(Clone, Copy, PartialEq, Eq)]
+pub(super) enum ForwardOutcome {
+    Continue,
+    Disconnect,
+}
+
+#[derive(Default)]
+pub(super) struct ConnectionReplaySnapshot {
+    last_response_id: Option<String>,
+    provider_state: Option<ProviderSessionState>,
+}
+
+impl ConnectionReplaySnapshot {
+    pub(super) fn prepare(&self, request: DecodedResponsesRequest) -> DecodedResponsesRequest {
+        match (
+            request.metadata().continuation().previous_response_id(),
+            self.last_response_id.as_deref(),
+            self.provider_state.as_ref(),
+        ) {
+            (Some(previous), Some(last), Some(state)) if previous == last => {
+                request.with_provider_session_state(state.clone())
+            }
+            _ => request,
+        }
+    }
+
+    fn commit(&mut self, response_id: String, provider_state: Option<ProviderSessionState>) {
+        self.last_response_id = Some(response_id);
+        self.provider_state = provider_state;
+    }
+}
+
+pub(super) async fn forward_execution(
+    connection: &mut ResponsesWebSocketConnection,
+    started: StartedExecution,
+    replay: &mut ConnectionReplaySnapshot,
+) -> ForwardOutcome {
+    let request_id = Arc::<str>::from(started.request_id.to_string());
+    let streaming = started.stream;
+    let mut execution = PendingExecution::new(started.session);
+    if !streaming {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "WebSocket execution was not initialized as a stream",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let first = match next_active_input(connection, &mut execution).await {
+        ActiveInput::Event(Ok(Some(event))) => event,
+        ActiveInput::Event(Ok(None)) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response ended before its first event",
+            );
+            return send_gateway_error(connection, &error, &request_id).await;
+        }
+        ActiveInput::Event(Err(error)) => {
+            return send_initial_engine_error(connection, &mut execution, &error, &request_id)
+                .await;
+        }
+        ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
+    };
+    let requirement = first.commit_requirement();
+    let mut first = first.into_provider_events();
+    if requirement != CommitRequirement::CommitBeforeDelivery {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "gateway first event did not require commit",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let mut encoder = OpenAiResponsesEncoder::new();
+    let mut provider_state = None;
+    let mut first_messages = Vec::new();
+    for event in &mut first {
+        if let Some(update) = event.take_session_update() {
+            provider_state = Some(update);
+        }
+        first_messages.extend(encoder.push_websocket(event));
+    }
+    if first_messages.is_empty() {
+        let error = GatewayError::new(
+            GatewayErrorKind::Internal,
+            "gateway commit batch encoded no output",
+        );
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let Some(response_session) = execution.session_mut() else {
+        return ForwardOutcome::Disconnect;
+    };
+    let response_headers = response_session.response_headers().to_vec();
+    if let Err(error) = response_session.commit_downstream(None).await {
+        let error = gateway_error_from_engine(&error);
+        return send_gateway_error(connection, &error, &request_id).await;
+    }
+    let mut first_frame_written = false;
+    if encoder.is_completed() {
+        if let Err(outcome) =
+            confirm_completed_execution(connection, &mut execution, &request_id).await
+        {
+            return outcome;
+        }
+        let provider_terminal_at = Instant::now();
+        commit_connection_replay(replay, &encoder, provider_state.take());
+        let writes_succeeded = send_metadata(
+            connection,
+            &request_id,
+            response_metadata_event(&request_id, &response_headers),
+        )
+        .await
+            && send_messages(
+                connection,
+                first_messages,
+                &request_id,
+                &mut first_frame_written,
+                true,
+            )
+            .await;
+        if !writes_succeeded {
+            log_terminal_write_failure(connection, &request_id, provider_terminal_at.elapsed());
+            return ForwardOutcome::Disconnect;
+        }
+        log_terminal_write_success(connection, &request_id, provider_terminal_at.elapsed());
+        execution.disarm();
+        return ForwardOutcome::Continue;
+    }
+    if !send_metadata(
+        connection,
+        &request_id,
+        response_metadata_event(&request_id, &response_headers),
+    )
+    .await
+        || !send_messages(
+            connection,
+            first_messages,
+            &request_id,
+            &mut first_frame_written,
+            encoder.has_wire_failure(),
+        )
+        .await
+    {
+        return ForwardOutcome::Disconnect;
+    }
+
+    loop {
+        match next_active_input(connection, &mut execution).await {
+            ActiveInput::Event(Ok(Some(delivery))) => {
+                let requirement = delivery.commit_requirement();
+                let mut events = delivery.into_provider_events();
+                if requirement != CommitRequirement::AlreadyCommitted {
+                    let error = GatewayError::new(
+                        GatewayErrorKind::Internal,
+                        "gateway requested another downstream commit",
+                    );
+                    return send_gateway_error(connection, &error, &request_id).await;
+                }
+                let mut messages = Vec::new();
+                for event in &mut events {
+                    if let Some(update) = event.take_session_update() {
+                        provider_state = Some(update);
+                    }
+                    messages.extend(encoder.push_websocket(event));
+                }
+                if encoder.is_completed() {
+                    if let Err(outcome) =
+                        confirm_completed_execution(connection, &mut execution, &request_id).await
+                    {
+                        return outcome;
+                    }
+                    let provider_terminal_at = Instant::now();
+                    commit_connection_replay(replay, &encoder, provider_state.take());
+                    if !send_messages(
+                        connection,
+                        messages,
+                        &request_id,
+                        &mut first_frame_written,
+                        true,
+                    )
+                    .await
+                    {
+                        log_terminal_write_failure(
+                            connection,
+                            &request_id,
+                            provider_terminal_at.elapsed(),
+                        );
+                        return ForwardOutcome::Disconnect;
+                    }
+                    log_terminal_write_success(
+                        connection,
+                        &request_id,
+                        provider_terminal_at.elapsed(),
+                    );
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let terminal_batch = encoder.has_wire_failure();
+                if !send_messages(
+                    connection,
+                    messages,
+                    &request_id,
+                    &mut first_frame_written,
+                    terminal_batch,
+                )
+                .await
+                {
+                    return ForwardOutcome::Disconnect;
+                }
+            }
+            ActiveInput::Event(Ok(None)) => {
+                if execution
+                    .session_mut()
+                    .is_some_and(|session| session.is_finalized())
+                {
+                    commit_connection_replay(replay, &encoder, provider_state.take());
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let error = GatewayError::new(
+                    GatewayErrorKind::Internal,
+                    "gateway response ended without finalizing the execution",
+                );
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Event(Err(error)) => {
+                if encoder.has_wire_failure() {
+                    execution.disarm();
+                    return ForwardOutcome::Continue;
+                }
+                let error = gateway_error_from_engine(&error);
+                return send_gateway_error(connection, &error, &request_id).await;
+            }
+            ActiveInput::Disconnect => return ForwardOutcome::Disconnect,
+        }
+    }
+}
+
+async fn send_initial_engine_error(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+    error: &EngineError,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let response_headers = execution
+        .session_mut()
+        .map(|session| session.response_headers().to_vec())
+        .unwrap_or_default();
+    if !response_headers.is_empty()
+        && !send_metadata(
+            connection,
+            request_id,
+            response_metadata_event(request_id, &response_headers),
+        )
+        .await
+    {
+        return ForwardOutcome::Disconnect;
+    }
+    let error = gateway_error_from_engine(error);
+    send_gateway_error(connection, &error, request_id).await
+}
+
+fn commit_connection_replay(
+    replay: &mut ConnectionReplaySnapshot,
+    encoder: &OpenAiResponsesEncoder,
+    provider_state: Option<ProviderSessionState>,
+) {
+    if let Some(response_id) = encoder.response_id() {
+        replay.commit(response_id.to_owned(), provider_state);
+    }
+}
+
+async fn confirm_completed_execution(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+    request_id: &Arc<str>,
+) -> Result<(), ForwardOutcome> {
+    match next_active_input(connection, execution).await {
+        ActiveInput::Event(Ok(None))
+            if execution
+                .session_mut()
+                .is_some_and(|session| session.is_finalized()) =>
+        {
+            Ok(())
+        }
+        ActiveInput::Event(Ok(None)) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response was not finalized after its terminal event",
+            );
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Event(Ok(Some(_))) => {
+            let error = GatewayError::new(
+                GatewayErrorKind::Internal,
+                "gateway response continued after its terminal event",
+            );
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Event(Err(error)) => {
+            let error = gateway_error_from_engine(&error);
+            Err(send_gateway_error(connection, &error, request_id).await)
+        }
+        ActiveInput::Disconnect => Err(ForwardOutcome::Disconnect),
+    }
+}
+
+enum ActiveInput {
+    Event(Result<Option<CoordinatedEvent>, EngineError>),
+    Disconnect,
+}
+
+async fn next_active_input(
+    connection: &mut ResponsesWebSocketConnection,
+    execution: &mut PendingExecution,
+) -> ActiveInput {
+    let Some(session) = execution.session_mut() else {
+        return ActiveInput::Disconnect;
+    };
+    // 与 Codex stream_request 的连接锁一致：本轮结束前不消费下一条请求。
+    // pump 继续接收有界业务帧和处理 Ping/Pong；退出通过独立通知取消本轮。
+    tokio::select! {
+        biased;
+        _ = connection.wait_for_exit() => {
+            session.trace().record("downstream.cancelled", serde_json::json!({
+                "reason": "websocket_connection_exit", "connectionId": connection.id(),
+            }));
+            ActiveInput::Disconnect
+        },
+        event = session.next_event() => ActiveInput::Event(event),
+    }
+}
+
+pub(super) async fn send_gateway_error(
+    connection: &mut ResponsesWebSocketConnection,
+    error: &GatewayError,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let (status, default_type, default_code) = gateway_error_contract(error.kind());
+    send_error(
+        connection,
+        status,
+        error.client_error_type().unwrap_or(default_type),
+        error.client_error_code().unwrap_or(default_code),
+        error.client_message(),
+        None,
+        request_id,
+    )
+    .await
+}
+
+pub(super) async fn send_protocol_error(
+    connection: &mut ResponsesWebSocketConnection,
+    status: StatusCode,
+    body: ProtocolErrorBody,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    let error = body.error;
+    send_error(
+        connection,
+        status,
+        error.kind,
+        error.code,
+        &error.message,
+        error.param.as_deref(),
+        request_id,
+    )
+    .await
+}
+
+async fn send_error(
+    connection: &mut ResponsesWebSocketConnection,
+    status: StatusCode,
+    error_type: &str,
+    code: &str,
+    message: &str,
+    param: Option<&str>,
+    request_id: &Arc<str>,
+) -> ForwardOutcome {
+    if connection
+        .send_text(
+            error_event(status, error_type, code, message, param, Some(request_id)),
+            WriteContext::request(request_id, FramePhase::Error),
+        )
+        .await
+        .is_ok()
+    {
+        ForwardOutcome::Continue
+    } else {
+        ForwardOutcome::Disconnect
+    }
+}
+
+async fn send_metadata(
+    connection: &mut ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    message: String,
+) -> bool {
+    connection
+        .send_text(
+            message,
+            WriteContext::request(request_id, FramePhase::Metadata),
+        )
+        .await
+        .is_ok()
+}
+
+async fn send_messages(
+    connection: &mut ResponsesWebSocketConnection,
+    messages: Vec<String>,
+    request_id: &Arc<str>,
+    first_frame_written: &mut bool,
+    terminal_batch: bool,
+) -> bool {
+    let message_count = messages.len();
+    for (index, message) in messages.into_iter().enumerate() {
+        let is_terminal = terminal_batch && index + 1 == message_count;
+        let phase = match (*first_frame_written, is_terminal) {
+            (false, true) => FramePhase::FirstAndTerminal,
+            (false, false) => FramePhase::First,
+            (true, true) => FramePhase::Terminal,
+            (true, false) => FramePhase::Data,
+        };
+        if connection
+            .send_text(message, WriteContext::request(request_id, phase))
+            .await
+            .is_err()
+        {
+            return false;
+        }
+        *first_frame_written = true;
+    }
+    true
+}
+
+fn log_terminal_write_success(
+    connection: &ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    provider_terminal_to_write: std::time::Duration,
+) {
+    tracing::info!(
+        target: "request_trace", stage = "downstream.terminal.written",
+        websocket_connection_id = connection.id(),
+        request_id = %request_id,
+        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
+        terminal_frame_written = true,
+        "Provider execution terminal was written to the WebSocket transport"
+    );
+}
+
+fn log_terminal_write_failure(
+    connection: &ResponsesWebSocketConnection,
+    request_id: &Arc<str>,
+    provider_terminal_to_write: std::time::Duration,
+) {
+    tracing::info!(
+        target: "request_trace", stage = "downstream.terminal.write_failed",
+        websocket_connection_id = connection.id(),
+        request_id = %request_id,
+        provider_terminal_to_terminal_write_ms = provider_terminal_to_write.as_millis(),
+        provider_succeeded_but_terminal_write_failed = true,
+        "Provider execution succeeded before the terminal WebSocket frame write failed"
+    );
+}

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

@@ -0,0 +1,307 @@
+//! OpenAI Responses WebSocket 的升级、连接与串行 session 编排。
+
+pub mod connection;
+mod forward;
+mod protocol;
+
+use std::{
+    net::{IpAddr, SocketAddr},
+    sync::Arc,
+};
+
+use axum::{
+    extract::{
+        Extension, State,
+        connect_info::ConnectInfo,
+        ws::{WebSocket, WebSocketUpgrade},
+    },
+    http::{HeaderMap, StatusCode},
+    response::{IntoResponse, Response},
+};
+use gateway_core::{
+    diagnostics::{TraceContext, diagnostic_json},
+    engine::execution::{AuthenticatedClient, ClientTransport},
+    lifecycle::{ConnectionGuard, ConnectionLifecycle},
+};
+
+use crate::{
+    ApiState,
+    openai::{
+        auth::{authenticate_client, client_access_error_response},
+        error::runtime_unavailable_response,
+        service::OpenAiService,
+    },
+};
+
+use super::{http::request_client_context, request::OpenAiRequestHeaders};
+use connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext};
+use forward::{
+    ConnectionReplaySnapshot, ForwardOutcome, forward_execution, send_gateway_error,
+    send_protocol_error,
+};
+use protocol::connection_limit_event;
+pub use protocol::{ResponseCreateFrameError, decode_response_create_with_context};
+
+const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
+const CONNECTION_LIMIT_CLOSE_REASON: &str = "Responses websocket connection limit reached";
+
+/// 将已认证的 `GET /v1/responses` 升级为 Responses WebSocket。
+pub(crate) async fn responses_websocket(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    websocket: WebSocketUpgrade,
+) -> Response {
+    let service = state.openai().clone();
+    let client = match authenticate_client(&service, &headers) {
+        Ok(client) => client,
+        Err(error) => return client_access_error_response(error),
+    };
+    let (client_ip, user_agent) = request_client_context(
+        &headers,
+        connect_info.map(|Extension(ConnectInfo(address))| address),
+    );
+    let request_headers = OpenAiRequestHeaders::from_headers(&headers);
+    ResponsesWebSocketAdapter::new(service).upgrade_with_client_context(
+        websocket,
+        client,
+        client_ip,
+        user_agent,
+        request_headers,
+        headers,
+    )
+}
+
+/// 已鉴权 Responses WebSocket 升级边界。
+#[derive(Clone)]
+pub(crate) struct ResponsesWebSocketAdapter {
+    service: OpenAiService,
+}
+
+impl ResponsesWebSocketAdapter {
+    /// 绑定应用提供的唯一 OpenAI 客户端服务端口。
+    #[must_use]
+    pub const fn new(service: OpenAiService) -> Self {
+        Self { service }
+    }
+
+    fn upgrade_with_client_context(
+        &self,
+        websocket: WebSocketUpgrade,
+        client: AuthenticatedClient,
+        client_ip: Option<IpAddr>,
+        user_agent: Option<String>,
+        request_headers: OpenAiRequestHeaders,
+        raw_headers: HeaderMap,
+    ) -> Response {
+        let connection_guard = match self.service.try_register_connection() {
+            Ok(guard) => guard,
+            Err(_) => return runtime_unavailable_response().into_response(),
+        };
+        let connection_id = self.service.next_request_id().replacen("req_", "ws_", 1);
+        TraceContext::new(&connection_id).headers(
+            "client.connection.headers",
+            serde_json::json!({"transport": "websocket", "method": "GET", "path": "/v1/responses"}),
+            raw_headers
+                .iter()
+                .map(|(name, value)| (name.as_str(), value.as_bytes())),
+        );
+        let session = ResponsesWebSocketSession {
+            service: self.service.clone(),
+            client,
+            connection_id,
+            client_ip,
+            user_agent,
+            request_headers,
+            lifecycle: self.service.lifecycle(),
+            connection_guard,
+        };
+        websocket
+            // 覆盖 axum/tungstenite 的私有 64 MiB message 与 16 MiB frame 默认值。
+            // Responses JSON 的协议可接受性由上游决定，代理不另设 wire 长度上限。
+            .max_message_size(usize::MAX)
+            .max_frame_size(usize::MAX)
+            .on_upgrade(move |socket| async move {
+                serve_responses_websocket(socket, session).await;
+            })
+    }
+}
+
+struct ResponsesWebSocketSession {
+    service: OpenAiService,
+    client: AuthenticatedClient,
+    connection_id: String,
+    client_ip: Option<IpAddr>,
+    user_agent: Option<String>,
+    request_headers: OpenAiRequestHeaders,
+    lifecycle: Arc<dyn ConnectionLifecycle>,
+    connection_guard: Box<dyn ConnectionGuard>,
+}
+
+async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocketSession) {
+    let ResponsesWebSocketSession {
+        service,
+        client,
+        connection_id,
+        client_ip,
+        user_agent,
+        request_headers,
+        lifecycle,
+        connection_guard,
+    } = session;
+    tracing::info!(
+        websocket_connection_id = %connection_id,
+        "Responses WebSocket connected"
+    );
+    let _connection_guard = connection_guard;
+    let cancellation = lifecycle.cancellation();
+    let request_headers =
+        request_headers.with_downstream_websocket_connection_id(connection_id.clone());
+    let mut connection = ResponsesWebSocketConnection::new(socket, connection_id, cancellation);
+    let mut request_count = 0_u64;
+    let mut replay = ConnectionReplaySnapshot::default();
+
+    loop {
+        let Some(event) = connection.next_event().await else {
+            break;
+        };
+        let payload = match event {
+            ConnectionEvent::Text(payload) => payload,
+            ConnectionEvent::Binary => {
+                connection.close_policy(TEXT_FRAMES_ONLY, None).await;
+                break;
+            }
+            ConnectionEvent::Expired => {
+                expire_connection(&mut connection).await;
+                break;
+            }
+            ConnectionEvent::Exited(_) => break,
+        };
+        if connection.is_expired() {
+            expire_connection(&mut connection).await;
+            break;
+        }
+        request_count = request_count.saturating_add(1);
+        let correlation_id = Arc::<str>::from(service.next_request_id());
+        let decoded = match decode_response_create_with_context(&payload, &request_headers) {
+            Ok(decoded) => decoded.with_client_context(client_ip, user_agent.clone()),
+            Err(error) => {
+                trace_rejected_request(
+                    &correlation_id,
+                    connection.id(),
+                    &payload,
+                    "decode",
+                    &error.to_string(),
+                );
+                if send_protocol_error(
+                    &mut connection,
+                    StatusCode::BAD_REQUEST,
+                    error.protocol_body(),
+                    &correlation_id,
+                )
+                .await
+                    == ForwardOutcome::Disconnect
+                {
+                    break;
+                }
+                continue;
+            }
+        };
+        let decoded = replay.prepare(decoded);
+        // deadline 与 Text 可能同时就绪；在任何上游执行开始前再次封住该竞争窗口。
+        if connection.is_expired() {
+            trace_rejected_request(
+                &correlation_id,
+                connection.id(),
+                &payload,
+                "connection_expired",
+                "",
+            );
+            expire_connection(&mut connection).await;
+            break;
+        }
+        let started = match service
+            .start_response(
+                client.clone(),
+                decoded,
+                ClientTransport::WebSocket,
+                "/v1/responses",
+            )
+            .await
+        {
+            Ok(started) => started,
+            Err(error) => {
+                trace_rejected_request(
+                    &correlation_id,
+                    connection.id(),
+                    &payload,
+                    "start",
+                    &error.to_string(),
+                );
+                if send_gateway_error(&mut connection, &error, &correlation_id).await
+                    == ForwardOutcome::Disconnect
+                {
+                    break;
+                }
+                continue;
+            }
+        };
+        started.session.trace().record("client.connection", serde_json::json!({
+            "transport": "websocket", "connectionId": connection.id(), "correlationId": correlation_id.as_ref(),
+            "requestIndex": request_count,
+        }));
+        started
+            .session
+            .trace()
+            .capture("client.request.body", payload.as_bytes());
+
+        if forward_execution(&mut connection, started, &mut replay).await
+            == ForwardOutcome::Disconnect
+        {
+            break;
+        }
+        if connection.is_expired() {
+            expire_connection(&mut connection).await;
+            break;
+        }
+    }
+
+    connection.log_summary(request_count);
+}
+
+// 尚未建立模型请求的拒绝也保留原文入口，用返回给客户端的 correlation ID 检索。
+fn trace_rejected_request(
+    correlation_id: &str,
+    connection_id: &str,
+    payload: &str,
+    phase: &'static str,
+    error: &str,
+) {
+    let trace = TraceContext::new(correlation_id);
+    trace.record(
+        "client.connection",
+        serde_json::json!({"connectionId": connection_id}),
+    );
+    trace.capture("client.request.body", payload.as_bytes());
+    trace.record(
+        "client.request.rejected",
+        serde_json::json!({
+            "phase": phase, "detail": diagnostic_json(&serde_json::json!({"message": error})),
+        }),
+    );
+}
+
+async fn expire_connection(connection: &mut ResponsesWebSocketConnection) {
+    if connection
+        .send_text(
+            connection_limit_event(),
+            WriteContext::connection(FramePhase::ConnectionLimit),
+        )
+        .await
+        .is_ok()
+    {
+        connection
+            .close_for_connection_limit(CONNECTION_LIMIT_CLOSE_REASON)
+            .await;
+    }
+}

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

@@ -0,0 +1,156 @@
+//! Responses WebSocket 入站请求与下行事件的纯协议映射。
+
+use axum::http::{HeaderName, StatusCode};
+use gateway_core::event::ProviderResponseHeader;
+use serde_json::{Map, Value, json};
+use thiserror::Error;
+
+use super::super::{
+    DecodedResponsesRequest, ProtocolErrorBody, RequestDecodeError,
+    request::{OpenAiRequestHeaders, RequestDecodeSource},
+};
+
+/// 使用连接级请求头和 Provider 上下文解码官方 `response.create` 文本帧。
+///
+/// 缺省 `stream` 等价于 WebSocket 固有的流式语义；显式 `false` 会被拒绝。
+///
+/// # Errors
+///
+/// 帧不是合法 JSON object、消息类型错误、显式关闭 stream，或 Responses 请求
+/// 无法映射到 canonical operation 时返回不包含正文内容的稳定错误。
+pub fn decode_response_create_with_context(
+    payload: &str,
+    request_headers: &OpenAiRequestHeaders,
+) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
+    decode_response_create_inner(payload, request_headers)
+}
+
+fn decode_response_create_inner(
+    payload: &str,
+    request_headers: &OpenAiRequestHeaders,
+) -> Result<DecodedResponsesRequest, ResponseCreateFrameError> {
+    let Value::Object(mut body) = serde_json::from_str::<Value>(payload)
+        .map_err(|_| ResponseCreateFrameError::InvalidJson)?
+    else {
+        return Err(ResponseCreateFrameError::ExpectedObject);
+    };
+    match body.remove("type") {
+        Some(Value::String(message_type)) if message_type == "response.create" => {}
+        _ => return Err(ResponseCreateFrameError::UnsupportedType),
+    }
+    if matches!(body.get("stream"), Some(value) if value.as_bool() != Some(true)) {
+        return Err(ResponseCreateFrameError::StreamingRequired);
+    }
+    super::super::request::decode_request_object(
+        body,
+        request_headers,
+        RequestDecodeSource::WebSocketFrame,
+    )
+    .map_err(ResponseCreateFrameError::Request)
+}
+
+/// `response.create` 帧的稳定安全错误。
+#[derive(Debug, Clone, PartialEq, Eq, Error)]
+pub enum ResponseCreateFrameError {
+    /// 文本不是合法 JSON。
+    #[error("response.create frame must be valid JSON")]
+    InvalidJson,
+    /// 顶层不是 object。
+    #[error("response.create frame must be a JSON object")]
+    ExpectedObject,
+    /// `type` 缺失或不是 `response.create`。
+    #[error("unsupported Responses WebSocket message type")]
+    UnsupportedType,
+    /// WebSocket 请求显式声明 `stream=false`。
+    #[error("Responses WebSocket requests require stream=true")]
+    StreamingRequired,
+    /// 内层 Responses 请求无法映射到 canonical operation。
+    #[error(transparent)]
+    Request(RequestDecodeError),
+}
+
+impl ResponseCreateFrameError {
+    pub(super) fn protocol_body(&self) -> ProtocolErrorBody {
+        match self {
+            Self::Request(error) => error.protocol_body(),
+            Self::InvalidJson => RequestDecodeError::MalformedJson.protocol_body(),
+            Self::ExpectedObject => RequestDecodeError::ExpectedObject.protocol_body(),
+            Self::UnsupportedType => RequestDecodeError::InvalidValue {
+                field: "type".to_owned(),
+            }
+            .protocol_body(),
+            Self::StreamingRequired => RequestDecodeError::InvalidValue {
+                field: "stream".to_owned(),
+            }
+            .protocol_body(),
+        }
+    }
+}
+
+pub(super) fn response_metadata_event(
+    request_id: &str,
+    response_headers: &[ProviderResponseHeader],
+) -> String {
+    let connection_options = super::super::response_connection_options(response_headers);
+    let mut headers = Map::new();
+    for header in response_headers {
+        if !super::super::response_header_is_forwardable(header.name(), &connection_options) {
+            continue;
+        }
+        let Ok(name) = HeaderName::from_bytes(header.name().as_bytes()) else {
+            continue;
+        };
+        let Ok(value) = std::str::from_utf8(header.value()) else {
+            continue;
+        };
+        // 官方 response.metadata 使用 string map，无法表达同名多值；后值保持既有覆盖语义。
+        headers.insert(name.as_str().to_owned(), Value::String(value.to_owned()));
+    }
+    headers
+        .entry("x-request-id".to_owned())
+        .or_insert_with(|| Value::String(request_id.to_owned()));
+    json!({
+        "type": "response.metadata",
+        "headers": headers,
+    })
+    .to_string()
+}
+
+pub(super) fn error_event(
+    status: StatusCode,
+    error_type: &str,
+    code: &str,
+    message: &str,
+    param: Option<&str>,
+    request_id: Option<&str>,
+) -> String {
+    let mut error = Map::new();
+    error.insert("type".to_owned(), Value::String(error_type.to_owned()));
+    error.insert("code".to_owned(), Value::String(code.to_owned()));
+    error.insert("message".to_owned(), Value::String(message.to_owned()));
+    if let Some(param) = param {
+        error.insert("param".to_owned(), Value::String(param.to_owned()));
+    }
+    let mut event = Map::new();
+    event.insert("type".to_owned(), Value::String("error".to_owned()));
+    event.insert("status".to_owned(), Value::Number(status.as_u16().into()));
+    event.insert("error".to_owned(), Value::Object(error));
+    if let Some(request_id) = request_id {
+        event.insert(
+            "request_id".to_owned(),
+            Value::String(request_id.to_owned()),
+        );
+    }
+    Value::Object(event).to_string()
+}
+
+pub(super) fn connection_limit_event() -> String {
+    error_event(
+        StatusCode::BAD_REQUEST,
+        "invalid_request_error",
+        "websocket_connection_limit_reached",
+        "Responses websocket connection limit reached (60 minutes). Create a new websocket connection to continue.",
+        None,
+        None,
+    )
+}

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

@@ -8,8 +8,9 @@ use axum::{
 
 use super::{
     images::{image_edits, image_generations},
-    models::{model_catalog, model_detail, model_info, models},
-    responses::{responses, responses_websocket, review_responses},
+    models::{model_detail, models},
+    responses::{responses, responses_websocket},
+    search::standalone_search,
 };
 
 use crate::ApiState;
@@ -19,11 +20,9 @@ pub(crate) fn router() -> Router<ApiState> {
     Router::new()
         .route("/v1/images/generations", post(image_generations))
         .route("/v1/images/edits", post(image_edits))
+        .route("/v1/alpha/search", post(standalone_search))
         .route("/v1/responses", get(responses_websocket).post(responses))
-        .route("/v1/responses/review", post(review_responses))
         .route("/v1/models", get(models))
-        .route("/v1/models/catalog", get(model_catalog))
-        .route("/v1/models/{model_id}/info", get(model_info))
         // 官方 OpenAI 模型详情合同使用 path ID；它不属于 Admin API 约束。
         .route("/v1/models/{model_id}", get(model_detail))
         // OpenAI 数据面正文属于客户端/上游协议；代理不能用私有大小上限提前拒绝

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

@@ -0,0 +1,67 @@
+//! Codex standalone search 非流式 HTTP adapter。
+
+use std::net::SocketAddr;
+
+use axum::{
+    body::Bytes,
+    extract::{Extension, State, connect_info::ConnectInfo},
+    http::HeaderMap,
+    response::Response,
+};
+use gateway_core::error::{GatewayError, GatewayErrorKind};
+use gateway_core::operation::{Operation, RawJsonPayload, StandaloneSearchRequest};
+
+use crate::ApiState;
+use crate::openai::{
+    auth::{authenticate_client, client_access_error_response},
+    endpoint::collect_raw_json_response,
+    error::gateway_error_response,
+    responses::{OpenAiRequestHeaders, request_client_context},
+};
+
+const OPENAI_PROTOCOL: &str = "openai";
+
+/// `POST /v1/alpha/search`。
+pub(crate) async fn standalone_search(
+    State(state): State<ApiState>,
+    connect_info: Option<Extension<ConnectInfo<SocketAddr>>>,
+    headers: HeaderMap,
+    body: Bytes,
+) -> Response {
+    let service = state.openai();
+    let client = match authenticate_client(service, &headers) {
+        Ok(client) => client,
+        Err(error) => return client_access_error_response(error),
+    };
+    let (client_ip, user_agent) = request_client_context(
+        &headers,
+        connect_info.map(|Extension(ConnectInfo(address))| address),
+    );
+    let operation = match search_operation(body, &headers) {
+        Ok(operation) => operation,
+        Err(error) => return gateway_error_response(&error),
+    };
+    let started = match service
+        .start_provider_endpoint(client, operation, client_ip, user_agent, "/v1/alpha/search")
+        .await
+    {
+        Ok(started) => started,
+        Err(error) => return gateway_error_response(&error),
+    };
+    collect_raw_json_response(started).await
+}
+
+fn search_operation(body: Bytes, headers: &HeaderMap) -> Result<Operation, GatewayError> {
+    let context = OpenAiRequestHeaders::from_headers(headers).session_context();
+    let payload = RawJsonPayload::new(OPENAI_PROTOCOL, body)
+        .map_err(|_| {
+            GatewayError::new(
+                GatewayErrorKind::Internal,
+                "OpenAI protocol identifier is invalid",
+            )
+        })?
+        .with_context(context);
+    Ok(Operation::Search(StandaloneSearchRequest::from_raw_json(
+        payload,
+    )))
+}

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

@@ -0,0 +1,5 @@
+//! Codex standalone search HTTP adapter。
+
+mod http;
+
+pub(crate) use http::standalone_search;

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

@@ -106,7 +106,7 @@ impl OpenAiService {
             .await
     }
 
-    pub(crate) async fn start_image(
+    pub(crate) async fn start_provider_endpoint(
         &self,
         client: AuthenticatedClient,
         operation: gateway_core::operation::Operation,

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

@@ -40,7 +40,10 @@ async fn list_route_should_keep_camel_case_group_and_page_wire() {
     assert_eq!(value["data"]["items"][0]["capacity"]["usedSlots"], 0);
     assert_eq!(value["data"]["items"][0]["capacity"]["totalSlots"], 1);
     assert_eq!(value["data"]["items"][0]["usage"]["todayUsd"], "1.25");
-    assert_eq!(value["data"]["items"][0]["usage"]["totalUsd"], "5.5");
+    assert_eq!(
+        value["data"]["items"][0]["usage"]["retainedTotalUsd"],
+        "5.5"
+    );
     assert!(value["data"]["items"][0].get("member_count").is_none());
 }
 

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

@@ -70,6 +70,140 @@ mod query {
     }
 }
 
+mod profile_statistics {
+    use chrono::NaiveDate;
+    use gateway_admin::model::provider_credentials::{
+        ProviderProfileActivityInsights, ProviderProfileDailyUsage, ProviderProfileInvocation,
+        ProviderProfileStatistics, ProviderProfileStatisticsSummary,
+    };
+    use gateway_api::admin::accounts::{AccountProfileAvatarQuery, AccountProfileStatisticsData};
+    use serde_json::json;
+
+    #[test]
+    fn profile_statistics_response_preserves_nullable_official_fields() {
+        let response = AccountProfileStatisticsData::from(ProviderProfileStatistics {
+            display_name: Some("Ada".to_owned()),
+            username: Some("ada".to_owned()),
+            image_url: Some("https://example.test/avatar.png".to_owned()),
+            has_stats_error: false,
+            summary: ProviderProfileStatisticsSummary {
+                total_text_tokens: Some(409_500_000),
+                peak_tokens: Some(267_000_000),
+                longest_task_duration_ms: Some(51_900_000),
+                current_streak_days: Some(16),
+                longest_streak_days: Some(32),
+            },
+            daily_usage: Some(vec![ProviderProfileDailyUsage {
+                date: NaiveDate::from_ymd_opt(2026, 8, 25).expect("usage date"),
+                tokens: 42,
+            }]),
+            activity_insights: ProviderProfileActivityInsights {
+                fast_mode_percent: Some(0.0),
+                reasoning_effort: Some("high".to_owned()),
+                reasoning_effort_percent: Some(48.0),
+                skills_explored: Some(8),
+                total_skills_used: Some(61),
+                total_threads: Some(2_391),
+                invocations: Some(vec![ProviderProfileInvocation {
+                    invocation_type: "plugin".to_owned(),
+                    plugin_id: Some("plugin_1".to_owned()),
+                    plugin_name: Some("example".to_owned()),
+                    skill_id: None,
+                    skill_name: None,
+                    usage_count: Some(29),
+                }]),
+            },
+        });
+        let value = serde_json::to_value(response).expect("serialize profile statistics");
+
+        assert_eq!(value["displayName"], "Ada");
+        assert_eq!(value["summary"]["totalTextTokens"], 409_500_000);
+        assert_eq!(
+            value["dailyUsage"][0],
+            json!({"date": "2026-08-25", "tokens": 42})
+        );
+        assert_eq!(
+            value["activityInsights"]["invocations"][0]["type"],
+            "plugin"
+        );
+        assert_eq!(
+            value["activityInsights"]["invocations"][0]["usageCount"],
+            29
+        );
+        assert!(value.get("cycle").is_none());
+        assert!(value.get("models").is_none());
+        assert!(value.get("estimatedCost").is_none());
+    }
+
+    #[test]
+    fn profile_avatar_query_accepts_only_bounded_cache_versions() {
+        let valid: AccountProfileAvatarQuery = serde_json::from_value(json!({
+            "accountId": "acct_openai",
+            "version": "k9m2z1"
+        }))
+        .expect("decode avatar query");
+        valid.validate().expect("validate avatar query");
+
+        for version in ["", "contains-dash", "x23456789012345678901234567890123"] {
+            let query: AccountProfileAvatarQuery = serde_json::from_value(json!({
+                "accountId": "acct_openai",
+                "version": version
+            }))
+            .expect("decode invalid avatar query");
+            assert_eq!(
+                query.validate().expect_err("reject version").field(),
+                "version"
+            );
+        }
+        assert!(
+            serde_json::from_value::<AccountProfileAvatarQuery>(json!({
+                "accountId": "acct_openai",
+                "sourceUrl": "https://example.test/avatar"
+            }))
+            .is_err()
+        );
+    }
+}
+
+mod profile_avatar {
+    use axum::body::to_bytes;
+    use bytes::Bytes;
+    use futures::stream;
+    use gateway_admin::model::provider_credentials::ProviderProfileAvatar;
+    use gateway_api::admin::accounts::profile_avatar_response;
+
+    #[tokio::test]
+    async fn profile_avatar_response_preserves_stream_metadata_and_private_cache() {
+        let response = profile_avatar_response(ProviderProfileAvatar {
+            content_type: Some("image/svg+xml".to_owned()),
+            content_length: Some(6),
+            etag: Some("\"v1\"".to_owned()),
+            body: Box::pin(stream::iter([Ok(Bytes::from_static(b"avatar"))])),
+        });
+
+        assert_eq!(response.status(), 200);
+        assert_eq!(response.headers()["content-type"], "image/svg+xml");
+        assert_eq!(response.headers()["content-length"], "6");
+        assert_eq!(response.headers()["etag"], "\"v1\"");
+        assert_eq!(response.headers()["cache-control"], "private, max-age=3600");
+        assert_eq!(response.headers()["x-content-type-options"], "nosniff");
+        assert_eq!(
+            response.headers()["cross-origin-resource-policy"],
+            "same-origin"
+        );
+        assert_eq!(
+            response.headers()["content-security-policy"],
+            "sandbox; default-src 'none'"
+        );
+        assert_eq!(
+            to_bytes(response.into_body(), 16)
+                .await
+                .expect("avatar response body"),
+            Bytes::from_static(b"avatar")
+        );
+    }
+}
+
 mod batch_update {
     use gateway_api::admin::accounts::{BatchUpdateAccountsRequest, UpdateAccountRequest};
     use serde_json::json;
@@ -214,6 +348,8 @@ mod response {
             output_tokens_display: "-".to_owned(),
             cached_tokens: None,
             cached_tokens_display: "-".to_owned(),
+            reasoning_tokens: None,
+            reasoning_tokens_display: "-".to_owned(),
             image_input_tokens: None,
             image_input_tokens_display: "-".to_owned(),
             image_output_tokens: None,
@@ -240,6 +376,8 @@ mod response {
         let value = serde_json::to_value(view).expect("serialize account usage");
         assert!(value["inputTokens"].is_null());
         assert!(value["totalTokens"].is_null());
+        assert!(value["reasoningTokens"].is_null());
+        assert_eq!(value["reasoningTokensDisplay"], "-");
         assert_eq!(value["createdTokensDisplay"], "-");
     }
 
@@ -269,7 +407,10 @@ mod actions {
         AccountResetCreditConsumeRequest, AccountTestQuery, CompleteAccountAuthorizationRequest,
         RotateAccountRequest, StartAccountAuthorizationRequest,
     };
-    use gateway_core::engine::credential::ProviderAccountId;
+    use gateway_core::{
+        account::ProviderAccountId, engine::probe::AccountProbeErrorSource,
+        error::GatewayErrorKind, upstream::UpstreamSendState,
+    };
     use serde_json::json;
 
     #[test]
@@ -554,6 +695,9 @@ mod actions {
             },
             DomainConnectionTestEvent::Completed {},
             DomainConnectionTestEvent::Failed {
+                source: AccountProbeErrorSource::Upstream,
+                gateway_error_code: GatewayErrorKind::RateLimited,
+                send_state: Some(UpstreamSendState::Sent),
                 message: "upstream unavailable".to_owned(),
                 provider_error_code: Some("usage_exhausted".to_owned()),
                 provider_error_type: Some("invalid_request_error".to_owned()),
@@ -587,6 +731,9 @@ mod actions {
                 json!({ "type": "test_complete", "success": true }),
                 json!({
                     "type": "error",
+                    "source": "upstream",
+                    "gatewayErrorCode": "rate_limited",
+                    "sendState": "sent",
                     "error": "upstream unavailable",
                     "providerErrorCode": "usage_exhausted",
                     "providerErrorType": "invalid_request_error",

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

@@ -0,0 +1,320 @@
+use axum::{
+    Router,
+    body::{Body, to_bytes},
+    http::{Method, Request, StatusCode, header},
+};
+use gateway_api::admin;
+use serde_json::{Value, json};
+use tower::ServiceExt as _;
+
+use super::{AdminTestFixture, AdminTestState};
+
+const SESSION_COOKIE: &str = "cpr_admin_session=valid-session";
+
+fn app(state: AdminTestState) -> Router {
+    admin::router::<AdminTestState>().with_state(state)
+}
+
+fn request(method: Method, uri: &str, body: Body) -> Request<Body> {
+    Request::builder()
+        .method(method)
+        .uri(uri)
+        .header("x-request-id", "req_admin_errors")
+        .body(body)
+        .expect("build admin error request")
+}
+
+async fn response_json(response: axum::response::Response) -> (StatusCode, String, Value) {
+    let status = response.status();
+    let content_type = response
+        .headers()
+        .get(header::CONTENT_TYPE)
+        .and_then(|value| value.to_str().ok())
+        .unwrap_or_default()
+        .to_owned();
+    let body = to_bytes(response.into_body(), 64 * 1024)
+        .await
+        .expect("read admin error response body");
+    let body = serde_json::from_slice(&body).expect("parse admin error response JSON");
+    (status, content_type, body)
+}
+
+#[tokio::test]
+async fn malformed_login_json_should_use_the_admin_error_envelope() {
+    let fixture = AdminTestFixture::new().await;
+    let mut request = request(
+        Method::POST,
+        "/api/admin/auth/login",
+        Body::from(r#"{"password":"secret""#),
+    );
+    request
+        .headers_mut()
+        .insert(header::CONTENT_TYPE, "application/json".parse().unwrap());
+
+    let response = app(fixture.state())
+        .oneshot(request)
+        .await
+        .expect("malformed JSON response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::BAD_REQUEST,
+            "application/json".to_owned(),
+            json!({
+                "code": 40000,
+                "message": "请求体不是合法 JSON",
+                "data": null
+            })
+        )
+    );
+}
+
+#[tokio::test]
+async fn invalid_login_json_data_should_not_echo_the_submitted_value() {
+    let fixture = AdminTestFixture::new().await;
+    let submitted = "password-must-not-leak";
+    let mut request = request(
+        Method::POST,
+        "/api/admin/auth/login",
+        Body::from(json!({ "password": submitted, "rememberMe": true }).to_string()),
+    );
+    request
+        .headers_mut()
+        .insert(header::CONTENT_TYPE, "application/json".parse().unwrap());
+
+    let response = app(fixture.state())
+        .oneshot(request)
+        .await
+        .expect("invalid JSON data response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::UNPROCESSABLE_ENTITY,
+            "application/json".to_owned(),
+            json!({
+                "code": 40001,
+                "message": "请求字段不合法",
+                "data": null
+            })
+        )
+    );
+    assert!(!actual.2.to_string().contains(submitted));
+}
+
+#[tokio::test]
+async fn login_without_json_content_type_should_keep_415_with_an_admin_envelope() {
+    let fixture = AdminTestFixture::new().await;
+    let response = app(fixture.state())
+        .oneshot(request(
+            Method::POST,
+            "/api/admin/auth/login",
+            Body::from(json!({ "password": "secret" }).to_string()),
+        ))
+        .await
+        .expect("missing JSON content type response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::UNSUPPORTED_MEDIA_TYPE,
+            "application/json".to_owned(),
+            json!({
+                "code": 40001,
+                "message": "请求必须使用 application/json",
+                "data": null
+            })
+        )
+    );
+}
+
+#[tokio::test]
+async fn malformed_admin_query_should_use_a_safe_bad_request_envelope() {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let mut request = request(
+        Method::GET,
+        "/api/admin/usage/records?page=not-a-number",
+        Body::empty(),
+    );
+    request
+        .headers_mut()
+        .insert(header::COOKIE, SESSION_COOKIE.parse().unwrap());
+
+    let response = app(fixture.state())
+        .oneshot(request)
+        .await
+        .expect("invalid query response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::BAD_REQUEST,
+            "application/json".to_owned(),
+            json!({
+                "code": 40001,
+                "message": "请求参数不合法",
+                "data": null
+            })
+        )
+    );
+}
+
+#[tokio::test]
+async fn invalid_time_range_should_use_its_published_business_code() {
+    let fixture = AdminTestFixture::new().await;
+    fixture.auth.insert_session("valid-session");
+    let mut request = request(
+        Method::GET,
+        "/api/admin/dashboard/summary?startTime=not-a-time",
+        Body::empty(),
+    );
+    request
+        .headers_mut()
+        .insert(header::COOKIE, SESSION_COOKIE.parse().unwrap());
+
+    let response = app(fixture.state())
+        .oneshot(request)
+        .await
+        .expect("invalid time range response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::BAD_REQUEST,
+            "application/json".to_owned(),
+            json!({
+                "code": 40002,
+                "message": "时间范围不合法",
+                "data": null
+            })
+        )
+    );
+}
+
+#[tokio::test]
+async fn unknown_admin_path_should_not_fall_through_to_the_spa() {
+    let fixture = AdminTestFixture::new().await;
+    let response = app(fixture.state())
+        .oneshot(request(
+            Method::GET,
+            "/api/admin/not-a-real-route",
+            Body::empty(),
+        ))
+        .await
+        .expect("unknown admin path response");
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        actual,
+        (
+            StatusCode::NOT_FOUND,
+            "application/json".to_owned(),
+            json!({
+                "code": 40401,
+                "message": "管理接口不存在",
+                "data": null
+            })
+        )
+    );
+}
+
+#[tokio::test]
+async fn unsupported_admin_method_should_keep_allow_and_return_an_envelope() {
+    let fixture = AdminTestFixture::new().await;
+    let response = app(fixture.state())
+        .oneshot(request(
+            Method::POST,
+            "/api/admin/auth/status",
+            Body::empty(),
+        ))
+        .await
+        .expect("unsupported admin method response");
+    let allow = response
+        .headers()
+        .get(header::ALLOW)
+        .and_then(|value| value.to_str().ok())
+        .unwrap_or_default()
+        .to_owned();
+    let actual = response_json(response).await;
+
+    assert_eq!(
+        (allow, actual),
+        (
+            "GET,HEAD".to_owned(),
+            (
+                StatusCode::METHOD_NOT_ALLOWED,
+                "application/json".to_owned(),
+                json!({
+                    "code": 40001,
+                    "message": "请求方法不受支持",
+                    "data": null
+                })
+            )
+        )
+    );
+}
+
+#[tokio::test]
+async fn admin_auth_failures_should_use_stable_chinese_contracts() {
+    let fixture = AdminTestFixture::new().await;
+    let unauthenticated = app(fixture.state())
+        .clone()
+        .oneshot(request(Method::GET, "/api/admin/accounts", Body::empty()))
+        .await
+        .expect("missing session response");
+    let mut invalid_api_key = request(Method::GET, "/api/admin/accounts", Body::empty());
+    invalid_api_key
+        .headers_mut()
+        .insert("x-api-key", "admin-invalid".parse().unwrap());
+    let invalid_api_key = app(fixture.state())
+        .clone()
+        .oneshot(invalid_api_key)
+        .await
+        .expect("invalid API key response");
+    let mut invalid_login = request(
+        Method::POST,
+        "/api/admin/auth/login",
+        Body::from(json!({ "password": "wrong-password" }).to_string()),
+    );
+    invalid_login
+        .headers_mut()
+        .insert(header::CONTENT_TYPE, "application/json".parse().unwrap());
+    let invalid_login = app(fixture.state())
+        .oneshot(invalid_login)
+        .await
+        .expect("invalid credentials response");
+
+    let actual = [
+        response_json(unauthenticated).await,
+        response_json(invalid_login).await,
+        response_json(invalid_api_key).await,
+    ];
+
+    assert_eq!(
+        actual.map(|(status, _, body)| (status, body["code"].clone(), body["message"].clone())),
+        [
+            (
+                StatusCode::UNAUTHORIZED,
+                json!(40101),
+                json!("需要管理员登录")
+            ),
+            (
+                StatusCode::UNAUTHORIZED,
+                json!(40102),
+                json!("管理员用户名或密码错误")
+            ),
+            (
+                StatusCode::UNAUTHORIZED,
+                json!(40103),
+                json!("管理 API Key 无效")
+            ),
+        ]
+    );
+}

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

@@ -15,16 +15,20 @@ use gateway_admin::{
         MutationContext, Revision,
         account_groups::{
             AccountGroupAccountSummary, AccountGroupCapacity, AccountGroupColor,
-            AccountGroupListQuery, AccountGroupMutation, AccountGroupPage, AccountGroupRecord,
-            AccountGroupUsage, DeleteAccountGroup, NewAccountGroup, SetAccountGroupEnabled,
-            UpdateAccountGroup,
+            AccountGroupListQuery, AccountGroupMemberFact, AccountGroupMutation, AccountGroupPage,
+            AccountGroupRecord, AccountGroupUsage, DeleteAccountGroup, NewAccountGroup,
+            SetAccountGroupEnabled, UpdateAccountGroup,
         },
         accounts::{
-            AccountListQuery, AccountPage, AccountPageItem, AccountUpdateResult, AccountUsage,
-            AccountUsageWindowQuery, AccountUsageWindowResult, AccountsUpdateResult,
-            BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
+            AccountListQuery, AccountPage, AccountPageItem, AccountRuntimeSnapshot,
+            AccountUpdateResult, AccountUsage, AccountUsageWindowQuery, AccountUsageWindowResult,
+            AccountsUpdateResult, BatchUpdateAccounts, DeleteAccounts, UpdateAccount,
         },
         auth::{AdminAuditEvent, AdminSession},
+        client_distribution::{
+            ClientArchitecture, ClientDownloadPackage, ClientDownloadSource,
+            CodexDesktopWindowsDownloads,
+        },
         client_keys::{
             ClientKeyListQuery, ClientKeyPage, ClientKeyRecord, ClientKeySecret, DeleteClientKey,
             NewClientKey, SetClientKeyEnabled, UpdateClientKey,
@@ -32,7 +36,7 @@ use gateway_admin::{
         observability::{
             DashboardObservation, DecimalAmount, DiagnosticDimension, DiagnosticObservation,
             OpsError, OpsErrorPage, OpsErrorQuery, RequestMetricPoint, TimeRange, UsageDetail,
-            UsageFilter, UsageOverview, UsagePage, UsageQuery, UsageRecord,
+            UsageFilter, UsageListRecord, UsageOverview, UsagePage, UsageQuery,
         },
         provider_credentials::{
             AuthorizationCommit, AuthorizationStarted, CompleteAuthorization, CredentialDetails,
@@ -50,10 +54,12 @@ use gateway_admin::{
         system::{SystemOperationAccepted, SystemUpdateDetail, SystemUpdateStatus, SystemVersion},
     },
     ports::{
+        client_distribution::ClientDistributionResolver,
         provider::{ProviderAdmin, ProviderAdminError, ProviderAdminErrorKind},
         store::{
-            AccountGroupStore, AccountStore, AdminStoreError, AdminStoreErrorKind, AdminStorePorts,
-            AdminStoreResult, AuthStore, ClientKeyStore, ObservabilityStore, SettingsStore,
+            AccountGroupStore, AccountRuntimeStore, AccountStore, AdminAccountStorePorts,
+            AdminStoreError, AdminStoreErrorKind, AdminStorePorts, AdminStoreResult, AuthStore,
+            ClientKeyStore, ObservabilityStore, SettingsStore,
         },
         system::{
             SystemOperationError, SystemOperationErrorKind, SystemOperations,
@@ -63,20 +69,18 @@ use gateway_admin::{
 };
 use gateway_api::admin::AdminSessionState;
 use gateway_core::{
-    engine::{
-        credential::ProviderAccountId,
-        probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
-    },
+    account::{AccountStatusFacts, CredentialState, ProviderAccountId, QuotaState},
+    engine::probe::{AccountProbe, AccountProbeError, AccountProbeRequest, AccountProbeResult},
     policy::{ClientApiKeyId, RateLimits},
-    routing::{
-        ConfigRevision, ProviderKind, PublicModelId, UpstreamModelId, snapshot::SnapshotControl,
-    },
+    routing::{ConfigRevision, ProviderKind, PublicModelId, UpstreamModelId},
+    runtime::SnapshotControl,
 };
 
 mod account_groups;
 mod accounts;
 mod auth;
 mod client_keys;
+mod errors;
 mod observability;
 mod settings;
 mod system;
@@ -86,7 +90,7 @@ pub(super) struct AdminTestFixture {
     pub services: AdminServices,
     pub auth: Arc<MemoryAuthStore>,
     pub settings: Arc<MemorySettingsStore>,
-    pub usage_records: Arc<Mutex<Vec<UsageRecord>>>,
+    pub usage_records: Arc<Mutex<Vec<UsageListRecord>>>,
     pub usage_detail: Arc<Mutex<Option<UsageDetail>>>,
     pub diagnostics: Arc<Mutex<Vec<DiagnosticObservation>>>,
     pub ops_errors: Arc<Mutex<Vec<OpsError>>>,
@@ -120,8 +124,7 @@ impl AdminTestFixture {
             dashboard_summary_range: Arc::clone(&dashboard_summary_range),
         });
         let stores = AdminStorePorts::new(
-            unused.clone(),
-            account_groups.clone(),
+            AdminAccountStorePorts::new(unused.clone(), unused.clone(), account_groups.clone()),
             auth.clone(),
             client_keys.clone(),
             unused,
@@ -142,6 +145,7 @@ impl AdminTestFixture {
             providers,
             Arc::new(NoopSnapshot),
             Arc::new(NoopProbe),
+            Arc::new(StaticClientDistribution),
             system,
         )
         .await
@@ -164,6 +168,30 @@ impl AdminTestFixture {
     }
 }
 
+struct StaticClientDistribution;
+
+#[async_trait]
+impl ClientDistributionResolver for StaticClientDistribution {
+    async fn resolve_codex_desktop_windows(&self, _: bool) -> CodexDesktopWindowsDownloads {
+        CodexDesktopWindowsDownloads {
+            resolved_at: Utc::now(),
+            cached: false,
+            warning: None,
+            packages: vec![ClientDownloadPackage {
+                architecture: ClientArchitecture::X64,
+                source: ClientDownloadSource::MicrosoftStore,
+                version: Some("26.825.6671.0".to_owned()),
+                file_name: "OpenAI.Codex_26.825.6671.0_x64__2p2nqsd0c76g0.msix".to_owned(),
+                size_bytes: Some(744_250_000),
+                download_url:
+                    "https://dl.delivery.mp.microsoft.com/filestreamingservice/files/test"
+                        .to_owned(),
+                expires_at: Some(Utc::now() + Duration::hours(1)),
+            }],
+        }
+    }
+}
+
 #[derive(Clone)]
 pub(super) struct AdminTestState(AdminServices);
 
@@ -318,6 +346,8 @@ impl SettingsStore for MemorySettingsStore {
             max_concurrent_per_account: command.max_concurrent_per_account,
             request_interval_ms: command.request_interval_ms,
             rotation_strategy: command.rotation_strategy,
+            min_codex_desktop_version: command.min_codex_desktop_version,
+            min_codex_cli_version: command.min_codex_cli_version,
             usage_retention_days: command.usage_retention_days,
             ops_event_retention_days: command.ops_event_retention_days,
             audit_retention_days: command.audit_retention_days,
@@ -465,6 +495,45 @@ impl AccountGroupStore for MemoryAccountGroupStore {
         })
     }
 
+    async fn load_account_group_members(
+        &self,
+        group_ids: &[gateway_core::routing::AccountGroupId],
+    ) -> AdminStoreResult<Vec<AccountGroupMemberFact>> {
+        if !group_ids.iter().any(|id| id.as_str() == PRIMARY_GROUP_ID) {
+            return Ok(Vec::new());
+        }
+        Ok(vec![
+            AccountGroupMemberFact {
+                group_id: group_id(PRIMARY_GROUP_ID),
+                account_id: "acct_group_ready".to_owned(),
+                status: AccountStatusFacts {
+                    enabled: true,
+                    credential_state: CredentialState::Ready,
+                    access_token_expires_at: None,
+                    quota: QuotaState::default(),
+                    rate_limited_until: None,
+                    last_error_reason: None,
+                    last_error_message: None,
+                },
+                total_slots: 1,
+            },
+            AccountGroupMemberFact {
+                group_id: group_id(PRIMARY_GROUP_ID),
+                account_id: "acct_group_disabled".to_owned(),
+                status: AccountStatusFacts {
+                    enabled: false,
+                    credential_state: CredentialState::Ready,
+                    access_token_expires_at: None,
+                    quota: QuotaState::default(),
+                    rate_limited_until: None,
+                    last_error_reason: None,
+                    last_error_message: None,
+                },
+                total_slots: 1,
+            },
+        ])
+    }
+
     async fn create_account_group(
         &self,
         command: NewAccountGroup,
@@ -621,7 +690,7 @@ impl ClientKeyStore for MemoryClientKeyStore {
 }
 
 struct UnusedStore {
-    usage_records: Arc<Mutex<Vec<UsageRecord>>>,
+    usage_records: Arc<Mutex<Vec<UsageListRecord>>>,
     usage_detail: Arc<Mutex<Option<UsageDetail>>>,
     diagnostics: Arc<Mutex<Vec<DiagnosticObservation>>>,
     ops_errors: Arc<Mutex<Vec<OpsError>>>,
@@ -631,11 +700,19 @@ struct UnusedStore {
 
 #[async_trait]
 impl AccountStore for UnusedStore {
-    async fn list_accounts(&self, _: AccountListQuery) -> AdminStoreResult<AccountPage> {
+    async fn list_accounts(
+        &self,
+        _: AccountListQuery,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<AccountPage> {
         Err(unavailable("account list"))
     }
 
-    async fn load_account(&self, _: &str) -> AdminStoreResult<Option<AccountPageItem>> {
+    async fn load_account(
+        &self,
+        _: &str,
+        _: AccountRuntimeSnapshot,
+    ) -> AdminStoreResult<Option<AccountPageItem>> {
         Err(unavailable("account"))
     }
 
@@ -751,6 +828,23 @@ impl AccountStore for UnusedStore {
     }
 }
 
+#[async_trait]
+impl AccountRuntimeStore for UnusedStore {
+    async fn active_rate_limits(&self) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot {
+            rate_limited_until: BTreeMap::new(),
+            in_flight: Some(BTreeMap::new()),
+        })
+    }
+
+    async fn account_runtime(&self, _: &[String]) -> AdminStoreResult<AccountRuntimeSnapshot> {
+        Ok(AccountRuntimeSnapshot {
+            rate_limited_until: BTreeMap::new(),
+            in_flight: Some(BTreeMap::new()),
+        })
+    }
+}
+
 #[async_trait]
 impl ObservabilityStore for UnusedStore {
     async fn dashboard_summary(
@@ -781,21 +875,23 @@ impl ObservabilityStore for UnusedStore {
         Err(unavailable("usage trend"))
     }
 
-    async fn usage_calculated_billing_facts(
+    fn usage_calculated_billing_facts(
         &self,
         _: TimeRange,
         _: UsageFilter,
-    ) -> AdminStoreResult<Vec<gateway_admin::model::observability::UsageCalculatedBillingFact>>
-    {
-        Err(unavailable("usage billing facts"))
+    ) -> gateway_admin::ports::store::UsageCalculatedBillingStream<'_> {
+        Box::pin(futures::stream::once(async {
+            Err(unavailable("usage billing facts"))
+        }))
     }
 
-    async fn list_usage_records(&self, _: UsageQuery) -> AdminStoreResult<UsagePage> {
+    async fn list_usage_records(&self, query: UsageQuery) -> AdminStoreResult<UsagePage> {
         let items = self.usage_records.lock().expect("usage records").clone();
         Ok(UsagePage {
+            current_page: query.current_page,
+            page_size: query.page_size.get(),
             total: items.len() as u64,
             items,
-            next_cursor: None,
         })
     }
 
@@ -820,12 +916,13 @@ impl ObservabilityStore for UnusedStore {
         Ok(self.diagnostics.lock().expect("diagnostics").clone())
     }
 
-    async fn list_ops_errors(&self, _: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage> {
+    async fn list_ops_errors(&self, query: OpsErrorQuery) -> AdminStoreResult<OpsErrorPage> {
         let items = self.ops_errors.lock().expect("ops errors").clone();
         Ok(OpsErrorPage {
+            current_page: query.current_page,
+            page_size: query.page_size.get(),
             total: items.len() as u64,
             items,
-            next_cursor: None,
         })
     }
 }
@@ -1006,6 +1103,8 @@ fn test_runtime_settings() -> RuntimeSettings {
         max_concurrent_per_account: 3,
         request_interval_ms: 50,
         rotation_strategy: RotationStrategy::Smart,
+        min_codex_desktop_version: None,
+        min_codex_cli_version: None,
         usage_retention_days: 31,
         ops_event_retention_days: 30,
         audit_retention_days: 90,
@@ -1036,10 +1135,12 @@ fn capacity(used_slots: Option<u64>, total_slots: u64) -> AccountGroupCapacity {
     }
 }
 
-fn usage(today_usd: &str, total_usd: &str) -> AccountGroupUsage {
+fn usage(today_usd: &str, retained_total_usd: &str) -> AccountGroupUsage {
     AccountGroupUsage {
         today_usd: today_usd.parse::<DecimalAmount>().expect("today cost"),
-        total_usd: total_usd.parse::<DecimalAmount>().expect("total cost"),
+        retained_total_usd: retained_total_usd
+            .parse::<DecimalAmount>()
+            .expect("retained total cost"),
     }
 }