[aw] PR Triage Agent failed

[github-actions]

Workflow Failure

Workflow: PR Triage Agent
Branch: main
Run: https://github.com/github/gh-aw/actions/runs/23610864201

⚠️ Repo-Memory Push Failed: The push-repo-memory job failed to write memory back to the repository. This may indicate a permission issue, a configuration error, or a network problem. Check the workflow run for details.

⚠️ Engine Failure: The AI engine terminated before producing output.

Error details:

• Authentication failed (Request ID: CC41:357CE4:3BE054:41CEFD:69C57880)

Action Required

Option 1: Debug using any coding agent

Use this prompt with any coding agent (GitHub Copilot, Claude, Gemini, etc.):

Debug the agentic workflow failure using https://raw.githubusercontent.com/github/gh-aw/main/debug.md

The failed workflow run is at https://github.com/github/gh-aw/actions/runs/23610864201

Option 2: Assign this issue to Copilot

Assign this issue to Copilot using the agentic-workflows sub-agent to automatically debug and fix the workflow failure.

Option 3: Manually invoke the agent

Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.

• Start your agent
• Load the agentic-workflows prompt from .github/agents/agentic-workflows.agent.md or https://github.com/github/gh-aw/blob/main/.github/agents/agentic-workflows.agent.md
• Type debug the agentic workflow pr-triage-agent failure in https://github.com/github/gh-aw/actions/runs/23610864201

Tip

To stop a workflow from creating failure issues, set report-failure-as-issue: false in its frontmatter:

safe-outputs:
  report-failure-as-issue: false

Generated from PR Triage Agent · ◷

• expires on Apr 2, 2026, 6:19 PM UTC

[github-actions]

Agent job 23679184082 failed.

⚠️ Repo-Memory Push Failed: The push-repo-memory job failed to write memory back to the repository. This may indicate a permission issue, a configuration error, or a network problem. Check the workflow run for details.

Generated from PR Triage Agent · ◷

[github-actions]

🚨 WHM Escalation — 10 Consecutive Failures (2026-03-28T11:57Z)

Workflow Health Manager run §23684685577 has confirmed this issue is actively worsening.

Current Status

Run	Date	Conclusion
#297	2026-03-28T06:17Z	❌ failure
#296	2026-03-28T00:11Z	❌ failure
#295	2026-03-27T18:14Z	❌ failure
#294	2026-03-27T12:10Z	❌ failure
#288–#293	2026-03-26 to 2026-03-27	❌ failure (6 runs)

Streak: 10 consecutive failures (runs #288–#297). Last successful run was before 2026-03-26T00:12Z.

Root Cause (Confirmed)

All failures are in the push_repo_memory job with the same error:

##[error]Can't find 'action.yml', 'action.yaml' or 'Dockerfile' under
'/home/runner/work/gh-aw/gh-aw/actions/setup'.
Did you forget to run actions/checkout before running your local action?

This is the systemic push_repo_memory → Post Setup Scripts bug: after the push_repo_memory job checks out the memory/pr-triage branch, the actions/setup local action no longer exists in the working tree (it's on main, not the memory branch). The Post Setup cleanup step then fails to find it.

Note on Actual Work

The agent job itself is succeeding — it processes PRs and writes memory. The failure only occurs in push_repo_memory cleanup. However, this causes the overall workflow run to be marked as failure.

Fix Required

The push_repo_memory compiled job in compiler_yaml.go needs to restore the workspace to the main branch after the memory push, so that the Post Setup cleanup step can find actions/setup. Tracked as systemic issue across multiple workflows.

Priority: P1 — no fix in 10 runs. Urgent escalation needed.

Note

🔒 Integrity filter blocked 8 items

The following items were blocked because they don't meet the GitHub integrity level.

• #18407 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #21242 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #21784 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #17352 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #18991 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #23268 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #21813 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
• #21306 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".

To allow these resources, lower min-integrity in your GitHub frontmatter:

tools:
  github:
    min-integrity: approved  # merged | approved | unapproved | none

Generated by Workflow Health Manager - Meta-Orchestrator · ◷

[github-actions]

Agent job 23691137361 failed.

Generated from PR Triage Agent · ◷

[github-actions]

Agent job 23697425408 failed.

Generated from PR Triage Agent · ◷

[github-actions]

✅ WHM Update — PR Triage Agent Recovered (2026-03-29T12:00Z)

Workflow Health Manager run §23708489882 is pleased to report a recovery for this workflow.

Recovery Status

Run	Date	Conclusion
#301	2026-03-29T06:21Z	✅ success ← RECOVERED
#300	2026-03-29T00:11Z	❌ failure
#299	2026-03-28T18:05Z	❌ failure
#298	2026-03-28T12:05Z	❌ failure
#288–#297	2026-03-26 to 2026-03-28	❌ failure (10 runs)

Run #301 succeeded after 12 consecutive failures (runs #289–300). The systemic push_repo_memory → Post Setup Scripts bug appears to have been fixed or resolved for this workflow.

Recommendation

This issue can be closed if run #301 remains isolated and subsequent runs continue to succeed. Monitor for 2–3 more successful runs before closing.

Generated by Workflow Health Manager - Meta-Orchestrator

Generated by Workflow Health Manager - Meta-Orchestrator · ◷

[github-actions]

WHM Status Update — 2026-03-31 | Run §23796317224

✅ PR Triage Agent has fully recovered. 5 consecutive successful schedule runs:

Run	Date	Result
#309	2026-03-31T06:25Z	✅ success
#308	2026-03-31T00:12Z	✅ success
#307	2026-03-30T18:15Z	✅ success
#306	2026-03-30T12:13Z	✅ success
#305	2026-03-30T06:32Z	✅ success

This issue can be manually closed — the workflow is healthy and operating normally.

Generated by Workflow Health Manager - Meta-Orchestrator · ◷

[github-actions]

WHM Update — 2026-04-01 | Run §23847695461

✅ Fully recovered. Runs #308–#313 are all successful (9 consecutive successes from 2026-03-31 through 2026-04-01T06:30Z).

Please close this issue manually — WHM runs on a schedule and cannot call update_issue in that context.

Note

🔒 Integrity filter blocked 1 item

The following item were blocked because they don't meet the GitHub integrity level.

• #21188 search_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".

To allow these resources, lower min-integrity in your GitHub frontmatter:

tools:
  github:
    min-integrity: approved  # merged | approved | unapproved | none

Generated by Workflow Health Manager - Meta-Orchestrator · ◷