Repository navigation
[aw] Smoke Gemini failed #3539
Description
Workflow Failure
Workflow: Smoke Gemini
Branch: salmanmkc/fix-squid-daemon-side-ownership
Run: https://github.com/github/gh-aw-firewall/actions/runs/26239168401
Pull Request: #3532
gemini engine terminated unexpectedly.
Last agent output:
exitCode: 1,
signal: undefined,
signalDescription: undefined,
stdout: undefined,
stderr: undefined,
failed: true,
timedOut: false,
isCanceled: false,
killed: false
}
Action Required
Assign this issue to an agent to debug and fix the issue.
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-firewall/actions/runs/26239168401
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the agentic-workflows prompt.
- Start your agent
- Load the
agentic-workflowsprompt from.github/agents/agentic-workflows.agent.mdor https://github.com/github/gh-aw/blob/main/.github/agents/agentic-workflows.agent.md - Type
debug the agentic workflow smoke-gemini failure in https://github.com/github/gh-aw-firewall/actions/runs/26239168401
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 Smoke Gemini · ◷
- expires on May 28, 2026, 4:33 PM UTC
Activity
github-actions commentedon May 21, 2026
Agent job 26240487657 failed.
⛔ Effective Token Budget Exhausted: The run failed due to effective-token budget/rate-limit enforcement in the API proxy.
Why this happened and how to optimize
Learn about effective tokens.
Configured ET budget:
25MRun: https://github.com/github/gh-aw-firewall/actions/runs/26240487657
You can tune this limit with
max-effective-tokensin workflow frontmatter.ET computation details (formula: 1×input + 0.1×cached + 4×output + 4×reasoning + 1×cache_write, then ×model multiplier)
Token counts unavailable — see step summary for per-model breakdown.