feat: add e2e triage CI workflow with Slack integration

.claude/skills/e2e/implement.md

@@ -2,6 +2,10 @@
 
 Apply fixes for E2E test failures, verify with scoped E2E tests.
 
+> **Before implementing any fixes, enter plan mode by invoking /plan.**
+> Analyze the findings (Steps 1-2 below), produce a complete fix plan with
+> specific file paths and code changes, and get user approval before executing.
+
 > **IMPORTANT: Running real E2E tests is a HARD REQUIREMENT of this procedure.**
 > Every fix MUST be verified with real E2E tests before the summary step.
 > Canary tests use the Vogon fake agent and cannot catch agent-specific issues.

.github/workflows/e2e-fix.yml

@@ -0,0 +1,140 @@
+name: E2E Fix
+
+on:
+  workflow_dispatch:
+    inputs:
+      triage_run_id:
+        description: Run ID of the triage workflow (for downloading plan artifacts)
+        required: true
+        type: string
+      run_url:
+        description: Original failed E2E run URL
+        required: true
+        type: string
+      failed_agents:
+        description: Comma-separated list of agents to fix
+        required: true
+        type: string
+      slack_channel:
+        description: Slack channel ID for thread replies
+        required: false
+        type: string
+      slack_thread_ts:
+        description: Slack thread timestamp for replies
+        required: false
+        type: string
+
+permissions:
+  actions: read
+  contents: write
+  pull-requests: write
+  id-token: write
+
+concurrency:
+  group: e2e-fix-${{ inputs.run_url || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  fix:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    env:
+      SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+      SLACK_CHANNEL: ${{ inputs.slack_channel }}
+      SLACK_THREAD_TS: ${{ inputs.slack_thread_ts }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Post fix started
+        if: ${{ env.SLACK_BOT_TOKEN != '' && env.SLACK_CHANNEL != '' && env.SLACK_THREAD_TS != '' }}
+        shell: bash
+        env:
+          FAILED_AGENTS: ${{ inputs.failed_agents }}
+        run: |
+          set -euo pipefail
+
+          scripts/post-slack-message.sh "Starting E2E fix for \`${FAILED_AGENTS}\`."
+
+      - name: Setup mise
+        uses: jdx/mise-action@v4
+
+      - name: Download plan artifacts
+        env:
+          GH_TOKEN: ${{ github.token }}
+          TRIAGE_RUN_ID: ${{ inputs.triage_run_id }}
+          FAILED_AGENTS: ${{ inputs.failed_agents }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          mkdir -p triage-plans
+
+          IFS=',' read -ra agents <<< "$FAILED_AGENTS"
+          for agent in "${agents[@]}"; do
+            agent="$(echo "$agent" | xargs)"  # trim whitespace
+            echo "Downloading plan for $agent..."
+            gh run download "$TRIAGE_RUN_ID" \
+              --name "e2e-plan-${agent}" \
+              --dir "triage-plans/${agent}" || {
+              echo "warning: no plan artifact found for $agent" >&2
+              continue
+            }
+          done
+
+          echo "Downloaded plans:"
+          find triage-plans -name '*.md' -type f
+
+      - name: Apply fixes
+        id: fix
+        uses: anthropics/claude-code-action@v1
+        with:
+          prompt: |
+            Read the fix plans in the triage-plans/ directory. Each subdirectory contains a plan.md for one agent.
+
+            Execute all fixes exactly as specified in the plans. After applying fixes, run:
+            1. mise run fmt
+            2. mise run lint
+            3. mise run test:e2e:canary
+
+            If verification passes, create a git branch fix/e2e-${{ github.run_id }}, commit all changes,
+            push, and create a draft PR with a summary of what was fixed.
+
+            If verification fails, fix the issues and retry. Do not give up without attempting to fix lint/format errors.
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_args: "--allowedTools 'Edit,Write,Read,Glob,Grep,Bash(git:*),Bash(mise:*),Bash(gh:*)'"
+
+      - name: Post success to Slack
+        if: success() && env.SLACK_BOT_TOKEN != '' && env.SLACK_CHANNEL != '' && env.SLACK_THREAD_TS != ''
+        shell: bash
+        env:
+          GH_TOKEN: ${{ github.token }}
+          FIX_BRANCH: fix/e2e-${{ github.run_id }}
+          RUN_URL: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}
+        run: |
+          set -euo pipefail
+
+          # Find the draft PR URL from the fix step output
+          pr_url="$(gh pr list --head "$FIX_BRANCH" --json url -q '.[0].url' 2>/dev/null || true)"
+
+          if [ -n "$pr_url" ]; then
+            message="E2E fix complete — draft PR ready: <${pr_url}|Review PR>"
+          else
+            message="E2E fix complete — changes applied but no PR was created. Check the <${RUN_URL}|workflow run> for details."
+          fi
+
+          scripts/post-slack-message.sh "$message"
+
+      - name: Post failure to Slack
+        if: failure() && env.SLACK_BOT_TOKEN != '' && env.SLACK_CHANNEL != '' && env.SLACK_THREAD_TS != ''
+        shell: bash
+        env:
+          RUN_URL: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}
+        run: |
+          set -euo pipefail
+
+          message="E2E fix failed. Check the <${RUN_URL}|workflow run> for details."
+
+          scripts/post-slack-message.sh "$message"