Add BC PR-Review engine arm with BCQuality ref override

.github/workflows/copilot-evaluation.yml

@@ -36,6 +36,11 @@ on:
         required: false
         default: true
         type: boolean
+      publish-results:
+        description: "Publish results to the shared dashboard (Braintrust/Kusto + leaderboard). Turn off to run a full experiment (e.g. your own BCQuality) without touching the dashboard."
+        required: false
+        default: true
+        type: boolean
       al-mcp:
         description: "Enable AL MCP server"
         required: false
@@ -62,6 +67,16 @@ on:
         required: false
         default: ""
         type: string
+      bcquality-ref:
+        description: "Code-review only: BCQuality ref (branch/tag/SHA) to review against. Blank uses the pinned default (microsoft/BCQuality@main)."
+        required: false
+        default: ""
+        type: string
+      bcquality-repo:
+        description: "Code-review only: BCQuality repo as owner/name, for testing a fork. Blank uses microsoft/BCQuality."
+        required: false
+        default: ""
+        type: string
 
 concurrency:
   group: copilot-evaluation-${{ inputs.test-run && 'test' || 'full' }}-${{ inputs.category }}
@@ -82,6 +97,7 @@ jobs:
     needs: get-entries
     outputs:
       results-dir: ${{ env.EVALUATION_RESULTS_DIR }}
+      agent-label: ${{ steps.agent-label.outputs.label }}
     if: needs.get-entries.outputs.entries != '[]'
     environment:
       name: ado-read
@@ -100,6 +116,13 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v5
 
+      - name: Resolve agent label
+        id: agent-label
+        shell: pwsh
+        run: |
+          $label = if ('${{ inputs.category }}' -eq 'code-review') { 'BC PR-Review Engine' } else { 'GitHub Copilot CLI' }
+          "label=$label" | Out-File -FilePath $env:GITHUB_OUTPUT -Append
+
       - name: Setup BC Container and Repository
         id: setup-env
         timeout-minutes: 40
@@ -134,6 +157,13 @@ jobs:
         shell: pwsh
         env:
           COPILOT_GITHUB_TOKEN: ${{ github.token }}
+          GH_TOKEN: ${{ github.token }}
+          # Code-review only. The engine reads these directly; blank refs use the pinned
+          # defaults (microsoft/BCQuality@main, engine _DEFAULT_ENGINE_REF). A tester sets
+          # bcquality-ref (and bcquality-repo for a fork) at dispatch to review their own.
+          BCQUALITY_REF: ${{ inputs.bcquality-ref }}
+          BCQUALITY_REPO: ${{ inputs.bcquality-repo }}
+          ENGINE_REPO_TOKEN: ${{ secrets.ENGINE_REPO_TOKEN }}
         run: |
           Write-Output "::add-mask::$env:COPILOT_GITHUB_TOKEN"
 
@@ -162,8 +192,8 @@ jobs:
     with:
       results-dir: ${{ needs.evaluate-with-copilot-cli.outputs.results-dir }}
       model: ${{ inputs.model }}
-      agent: "GitHub Copilot CLI"
-      mock: ${{ inputs.test-run }}
+      agent: ${{ needs.evaluate-with-copilot-cli.outputs.agent-label }}
+      mock: ${{ inputs.test-run || !inputs.publish-results }}
       category: ${{ inputs.category }}
       git-ref: ${{ inputs.git-ref || github.ref_name }}
     secrets: inherit
@@ -179,4 +209,4 @@ jobs:
       workflow-file: copilot-evaluation.yml
       repeat: ${{ inputs.repeat }}
       workflow-inputs: |
-        {"model": "${{ inputs.model }}", "category": "${{ inputs.category }}", "test-run": "${{ inputs.test-run }}", "al-mcp": "${{ inputs.al-mcp }}", "al-lsp": "${{ inputs.al-lsp }}", "git-ref": "${{ inputs.git-ref || github.ref_name }}"}
+        {"model": "${{ inputs.model }}", "category": "${{ inputs.category }}", "test-run": "${{ inputs.test-run }}", "al-mcp": "${{ inputs.al-mcp }}", "al-lsp": "${{ inputs.al-lsp }}", "git-ref": "${{ inputs.git-ref || github.ref_name }}", "bcquality-ref": "${{ inputs.bcquality-ref }}", "bcquality-repo": "${{ inputs.bcquality-repo }}", "publish-results": "${{ inputs.publish-results }}"}

src/bcbench/agent/__init__.py

@@ -3,5 +3,13 @@
 from bcbench.agent.bcal import BCalBackendConfig, run_bcal_agent
 from bcbench.agent.claude import run_claude_code
 from bcbench.agent.copilot import run_copilot_agent
+from bcbench.agent.engine import code_review_uses_engine, run_engine_review
 
-__all__ = ["BCalBackendConfig", "run_bcal_agent", "run_claude_code", "run_copilot_agent"]
+__all__ = [
+    "BCalBackendConfig",
+    "code_review_uses_engine",
+    "run_bcal_agent",
+    "run_claude_code",
+    "run_copilot_agent",
+    "run_engine_review",
+]