IMPORTANT: Keep all outputs extremely short and concise. Use single-line responses where possible. No verbose explanations.

1. GitHub MCP Testing: Review the last 2 merged pull requests in ${{ github.repository }}
2. MCP Scripts GH CLI Testing: Use the mcpscripts-gh tool to query 2 pull requests from ${{ github.repository }} (use args: "pr list --repo ${{ github.repository }} --limit 2 --json number,title,author")
3. Serena MCP Testing:
   • Use the Serena MCP server tool activate_project to initialize the workspace at ${{ github.workspace }} and verify it succeeds (do NOT use bash to run go commands - use Serena's MCP tools)
   • After initialization, use the find_symbol tool to search for symbols (find which tool to call) and verify that at least 3 symbols are found in the results
4. Playwright Testing: Use the playwright tools to navigate to https://github.com and verify the page title contains "GitHub" (do NOT try to install playwright - use the provided MCP tools)
5. Web Fetch Testing: Use the web-fetch tool to fetch https://github.com and verify the response contains "GitHub" (do NOT use bash or playwright for this test - use the web-fetch tool directly)
6. File Writing Testing: Create a test file /tmp/gh-aw/agent/smoke-test-copilot-${{ github.run_id }}.txt with content "Smoke test passed for Copilot at $(date)" (create the directory if it doesn't exist)
7. Bash Tool Testing: Execute bash commands to verify file creation was successful (use cat to read the file back)
8. Discussion Interaction Testing:
   • Use the github-discussion-query mcp-script tool with params: limit=1, jq=".[0]" to get the latest discussion from ${{ github.repository }}
   • Extract the discussion number from the result (e.g., if the result is {"number": 123, "title": "...", ...}, extract 123)
   • Use the add_comment tool with discussion_number: <extracted_number> to add a fun, playful comment stating that the smoke test agent was here
9. Build gh-aw: Run GOCACHE=/tmp/go-cache GOMODCACHE=/tmp/go-mod make build to verify the agent can successfully build the gh-aw project (both caches must be set to /tmp because the default cache locations are not writable). If the command fails, mark this test as ❌ and report the failure.
10. Upload gh-aw binary as artifact: After a successful build, use bash to copy the ./gh-aw binary into the staging directory (mkdir -p $RUNNER_TEMP/gh-aw/safeoutputs/upload-artifacts && cp ./gh-aw $RUNNER_TEMP/gh-aw/safeoutputs/upload-artifacts/gh-aw), then call the upload_artifact safe-output tool with path: "gh-aw", retention_days: 1, and skip_archive: true. The upload_artifact tool is available and configured in this workflow run — use it directly, do NOT use missing_tool for it. Mark this test as ❌ if the build in step 9 failed.
11. Discussion Creation Testing: Use the create_discussion safe-output tool to create a discussion in the announcements category titled "copilot was here" with the label "ai-generated"
12. Workflow Dispatch Testing: Use the dispatch_workflow safe output tool to trigger the haiku-printer workflow with a haiku as the message input. Create an original, creative haiku about software testing or automation.
13. PR Review Testing: Review the diff of the current pull request. Leave 1-2 inline create_pull_request_review_comment comments on specific lines, then call submit_pull_request_review with a brief body summarizing your review and event COMMENT. To test reply_to_pull_request_review_comment: use the pull_request_read tool (with method: "get_review_comments" and pullNumber: ${{ github.event.pull_request.number }}) to fetch the PR's existing review comments, then reply to the most recent one using reply_to_pull_request_review_comment with its actual numeric id as the comment_id. Note: create_pull_request_review_comment does not return a comment_id — you must fetch existing comment IDs from the GitHub API. If the PR has no existing review comments, skip the reply sub-test.

1. Create an issue with a summary of the smoke test run:

   • Use a temporary ID (e.g. aw_smoke1) for the issue so you can reference it later
   • Title: "Smoke Test: Copilot - ${{ github.run_id }}"
   • Body should include:
     • Test results (✅ or ❌ for each test)
     • Overall status: PASS or FAIL
     • Run URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
     • Timestamp
     • Pull request author and assignees

2. Set Issue Type: Use the set_issue_type safe-output tool with issue_number: "aw_smoke1" (the temporary ID from step 1) and issue_type: "Bug" to set the type of the just-created smoke test issue.

3. Only if this workflow was triggered by a pull_request event: Use the add_comment tool to add a very brief comment (max 5-10 lines) to the triggering pull request (omit the item_number parameter to auto-target the triggering PR) with:

   • PR titles only (no descriptions)
   • ✅ or ❌ for each test result
   • Overall status: PASS or FAIL
   • Mention the pull request author and any assignees

4. Use the add_comment tool to add a fun and creative comment to the latest discussion (using the discussion_number you extracted in step 8) - be playful and entertaining in your comment

5. Use the send_slack_message tool to send a brief summary message (e.g., "Smoke test ${{ github.run_id }}: All tests passed! ✅")

If all tests pass and this workflow was triggered by a pull_request event:

• Use the add_labels safe-output tool to add the label smoke-copilot to the pull request (omit the item_number parameter to auto-target the triggering PR)
• Use the remove_labels safe-output tool to remove the label smoke from the pull request (omit the item_number parameter to auto-target the triggering PR)

Important: If no action is needed after completing your analysis, you MUST call the noop safe-output tool with a brief explanation. Failing to call any safe-output tool is the most common cause of safe-output workflow failures.

{"noop": {"message": "No action needed: [brief explanation of what was analyzed and why]"}}