name: Marvin Issue Dedupe
# description: Automatically dedupe GitHub issues using Marvin
on:
  issues:
    types: [opened]
  workflow_dispatch:
    inputs:
      issue_number:
        description: "Issue number to process for duplicate detection"
        required: true
        type: string

jobs:
  marvin-dedupe-issues:
    runs-on: ubuntu-latest
    timeout-minutes: 10
    permissions:
      contents: read
      issues: write
      id-token: write

    # TEMPORARY PIN — see the matching note in marvin-label-triage.yml.
    # Claude Code 2.1.216 broke every Bash call under the action's subprocess
    # isolation, which this workflow needs for all of its `gh` searching.
    # https://github.com/anthropics/claude-code/issues/79997
    env:
      PINNED_CLAUDE_CODE_VERSION: "2.1.215"

    steps:
      - name: Checkout repository
        uses: actions/checkout@v7

      - name: Generate Marvin App token
        id: marvin-token
        uses: actions/create-github-app-token@v3
        with:
          app-id: ${{ secrets.MARVIN_APP_ID }}
          private-key: ${{ secrets.MARVIN_APP_PRIVATE_KEY }}

      - name: Set dedupe prompt
        id: dedupe-prompt
        run: |
          cat >> $GITHUB_OUTPUT << 'EOF'
          PROMPT<<PROMPT_END
          Find up to 3 likely duplicate issues for GitHub issue ${{ github.repository }}/issues/${{ github.event.issue.number || inputs.issue_number }}.

          # Core Principle
          Silence is better than noise. A false positive wastes a human's time and erodes trust in every future report. Most runs should end with no comment — that means the system is working.

          # Steps

          1. Check if the GitHub issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.

          2. View the GitHub issue and produce a summary of the issue.

          3. Launch 3 parallel agents using the Task tool to search GitHub for duplicates, using diverse keywords and search approaches, using the summary from step 2.

          4. Filter aggressively for false positives. The bar for "duplicate" is high:

             A duplicate means the SAME bug or the SAME feature request. Apply this test to every candidate:
             - **Same fix test**: Could the candidate be closed by the exact same code change? If not, not a duplicate.
             - **Same symptom test**: Does the user experience the exact same broken behavior? "Both involve middleware" is not duplication. "Both get TypeError on line 42 of proxy.py when calling mount()" is duplication.
             - **Same request test** (for features): Are they asking for the same specific capability? "Both want better auth" is not duplication. "Both request OAuth PKCE flow for CLI login" is duplication.

             Candidates found by only one search agent deserve extra scrutiny — a single keyword match is often a false positive.

             When in doubt, do not flag. A missed duplicate is harmless; a false positive wastes the reporter's time.
             If there are no duplicates remaining, do not proceed — just exit.

          5. **Quality gate**: Before commenting, re-read each candidate as a skeptical reviewer. For each one, ask: "Would a maintainer who knows this codebase agree this is a duplicate, or would they dismiss it?" If you'd need to hedge with "might" or "possibly," drop it.

          6. Comment back on the issue with your findings (or exit silently if none remain). Do NOT add any labels — labeling is handled by a later workflow step.

          # Notes for your agents
          - Use `gh` to interact with GitHub, rather than web fetch
          - Do not use other tools beyond `gh` and Task (no MCP servers, file edit, etc.)
          - Never include this issue as a duplicate of itself
          - When searching, read the FULL body of candidate issues — titles alone are not enough to judge duplication

          For your comment, follow this format precisely (example with 3 suspected duplicates):

          ---
          Found 3 possible duplicate issues:

          1. #123: Issue title here
          2. #456: Another issue title
          3. #789: Third issue title

          This issue will be automatically closed as a duplicate in 3 days.

          - If your issue is a duplicate, please close it and 👍 the existing issue instead
          - To prevent auto-closure, add a comment or 👎 this comment

          ---
          PROMPT_END
          EOF

      - name: Clean up stale Claude locks
        run: rm -rf ~/.claude/.locks ~/.local/state/claude/locks || true

      - name: Install pinned Claude Code
        id: pin-claude
        run: |
          curl -fsSL https://claude.ai/install.sh | bash -s -- "$PINNED_CLAUDE_CODE_VERSION"
          echo "path=$HOME/.local/bin/claude" >> "$GITHUB_OUTPUT"
          "$HOME/.local/bin/claude" --version

      - name: Run Marvin dedupe command
        uses: anthropics/claude-code-action@v1
        with:
          path_to_claude_code_executable: ${{ steps.pin-claude.outputs.path }}
          github_token: ${{ steps.marvin-token.outputs.token }}
          bot_name: "Marvin Context Protocol"
          prompt: ${{ steps.dedupe-prompt.outputs.PROMPT }}
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY_FOR_CI }}
          allowed_non_write_users: "*"
          claude_args: |
            --allowedTools "Bash(gh issue view:*)","Bash(gh search:*)","Bash(gh issue list:*)","Bash(gh api:*)","Bash(gh issue comment:*)",Task
          settings: |
            {
              "model": "claude-sonnet-5",
              "env": {
                "GH_TOKEN": "${{ steps.marvin-token.outputs.token }}"
              }
            }

      - name: Add potential-duplicate label if bot commented in this run
        env:
          GH_TOKEN: ${{ steps.marvin-token.outputs.token }}
        run: |
          ISSUE=${{ github.event.issue.number || inputs.issue_number }}
          # Only match bot comments created in the last 10 minutes (this run)
          CUTOFF=$(date -u -d '10 minutes ago' '+%Y-%m-%dT%H:%M:%SZ' 2>/dev/null \
            || date -u -v-10M '+%Y-%m-%dT%H:%M:%SZ')
          HAS_RECENT=$(gh api "repos/${{ github.repository }}/issues/${ISSUE}/comments?sort=created&direction=desc&per_page=10" \
            --jq "[.[] | select(
              .user.type == \"Bot\" and
              (.body | test(\"possible duplicate issues\"; \"i\")) and
              .created_at >= \"${CUTOFF}\"
            )] | length")
          if [ "$HAS_RECENT" -gt 0 ]; then
            gh issue edit "$ISSUE" --add-label "potential-duplicate" -R "${{ github.repository }}"
            echo "Added potential-duplicate label to #${ISSUE}"
          else
            echo "No recent duplicate comment found, skipping label"
          fi