Repository navigation
[aw] Smoke Copilot - AOAI (apikey): exceeded max AI credits #72472
Description
What happened
Smoke Copilot - AOAI (apikey) exceeded max AI credits.
View run #40522223615 · Workflow source · Previous failures
Branch: pelikhan/fictional-invention
Pull Request: #72415
Next step
Review the failure details below for a targeted fix, or assign this issue to a coding agent to investigate.
Failure details
Warning
AI Credits Budget Exceeded
The workflow hit the configured max-ai-credits guardrail. Used 63.8 of 60 max (over by 3.75).
Increase the limit
Update max-ai-credits in your workflow frontmatter:
max-ai-credits: 120Tips for reducing AI credit usage
- Review the cost optimization guidance.
- Reduce unnecessary model or tool calls in the prompt.
- Trim large inputs or excess context that does not change the outcome.
- Split large tasks across smaller runs when possible.
Runtime evidence
[!WARNING]
Task Could Not Be Completed: The workflow recorded areport_incompletesignal: the task was not completed or completion could not be confirmed.
Error details:
Failure classification: request_rejection
Driver exit code: 1. The engine driver exited before a terminal safe output was recorded.
Driver exit meaning: General failure
Last driver stderr summary: not recorded (no classified stderr diagnostic)
Last tool call status: succeeded
Last tool exit code: 0
Failed tool calls observed: 1
Token budget state: unknown (no exhaustion signal recorded)
Step budget state (LLM invocations): unknown (no exhaustion signal recorded)
Safe-output tools: available at gateway snapshot (registered 18 tools)
Safe-output CLI calls observed: unknown (not recorded)
Safe-output MCP calls observed: 0
Safe-output persistence: not recorded
Engine error: Authentication failed (authentication_failed)
Agent finished without emitting a terminal safe output; task completion could not be confirmed.
Engine HTTP error codes: 403
Last engine error type: authentication_failed
Retry attempts observed: 1
A comment or other safe output does not confirm that the requested task was completed. Only inferred runtime status and error codes are reported; agent text is excluded.
Failure Diagnostics
Agent job: agent
Agent job conclusion: failure
Failing step: Execute GitHub Copilot CLI
No additional engine error was captured. Check the reported failure signals and linked run for details.
Only runtime metadata is shown; agent-generated text is excluded.
Optimize token consumption
This failure was triggered by a guardrail limit (max-ai-credits). 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/40522223615
Copy a debugging prompt
Paste this into your coding agent:
Debug the agentic workflow "smoke-copilot-aoai-apikey" failure.
Follow https://raw.githubusercontent.com/github/gh-aw/main/debug.md
Failed run: https://github.com/github/gh-aw/actions/runs/40522223615
If the repository includes the agentic-workflows skill, load it before investigating.
Manage failure notifications
To stop creating failure issues for this workflow, set this in its frontmatter and recompile:
safe-outputs:
report-failure-as-issue: falseThis only disables issue reporting; it does not fix the failure.
Generated from Smoke Copilot - AOAI (apikey) · copilot · o40mini · ~64 AIC · ◷
- expires on Oct 28, 2026, 2:48 AM UTC
Activity
github-actions commentedon Oct 28, 2026
This issue was automatically closed because it expired on 2026-10-28T02:48:35.739Z.