Repository navigation
Description
Workflow Failure
Workflow: Matt Pocock Skills Reviewer
Branch: copilot/aw-top-10-handle-models-missing-pricing-table
Run: https://github.com/github/gh-aw/actions/runs/37628718128
Pull Request: #66552
Warning
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Error details:
missing_terminal_safe_output
Agent finished without emitting a terminal safe output; task completion could not be confirmed.
bash: cd /home/runner/work/gh-aw/gh-aw && grep -n '"?"' pkg/workflow/compiler_model_pricing.go: {"content":"\n(shellId: 21 completed with exit code 1)"}
bash: cd /home/runner/work/gh-aw/gh-aw && sed -n '87,115p' pkg/workflow/compiler_model_pricing.go | grep -n "?": {"content":"\n(shellId: 35 completed with exit code 1)"}
This is a structured incompletion signal (report_incomplete), not a real task outcome. Any other safe outputs emitted alongside this signal (e.g., comments) describe the failure state, not a completed review or action.
Agent Timed Out: The agent job exceeded the maximum allowed execution time (15 minutes).
To increase the timeout, add or update the timeout-minutes setting in your workflow's frontmatter:
---
timeout-minutes: 25
---Action Required
Assign this issue to an agent to debug and fix the issue.
Optimize token consumption
This failure was triggered by a guardrail limit (max-turns / timeout). Use this prompt with any coding agent (GitHub Copilot, Claude, Gemini, etc.) to analyze token usage and reduce costs:
Optimize the agentic workflow token consumption using https://raw.githubusercontent.com/github/gh-aw/main/optimize.md
The workflow run is at https://github.com/github/gh-aw/actions/runs/37628718128
Debug with 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/37628718128
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.
- Start your agent
- Load the
agentic-workflowsskill from.github/skills/agentic-workflows/SKILL.mdor https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.md - Type
debug the agentic workflow mattpocock-skills-reviewer failure in https://github.com/github/gh-aw/actions/runs/37628718128
Tip
Stop reporting this workflow as a failure
To stop a workflow from creating failure issues, set report-failure-as-issue: false in its frontmatter:
safe-outputs:
report-failure-as-issue: falseGenerated from Matt Pocock Skills Reviewer · copilot · 158.9 AIC · ◷
- expires on Oct 8, 2026, 2:16 AM UTC
Activity
github-actions commentedon Oct 7, 2026
Agent job 37628743260 failed.
Warning
Task Could Not Be Completed: The agent reported that the task could not be performed due to an infrastructure or tool failure.
Error details:
This is a structured incompletion signal (
report_incomplete), not a real task outcome. Any other safe outputs emitted alongside this signal (e.g., comments) describe the failure state, not a completed review or action.Agent Timed Out: The agent job exceeded the maximum allowed execution time (15 minutes).
To increase the timeout, add or update the
timeout-minutessetting in your workflow's frontmatter: