[aw] Smoke Gemini failed

[github-actions]

Workflow Failure

Workflow: Smoke Gemini
Branch: copilot/add-step-download-usage-artifact
Run: https://github.com/github/gh-aw/actions/runs/27315872388
Pull Request: #38454

Warning

Engine Failure: The gemini engine terminated unexpectedly.

Last agent output:

    at async Models.generateContentStream (file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-FNPZLVJU.js:37043:16)
    at async file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:278424:19
    at async file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:255329:23
    at async retryWithBackoff (file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:275301:23)
    at async GeminiChat.makeApiCallAndProcessStream (file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:312614:28)
    at async GeminiChat.streamWithRetries (file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:312452:29)
    at async Turn.run (file:///opt/hostedtoolcache/node/24.16.0/x64/lib/node_modules/@google/gemini-cli/bundle/chunk-UIBQS45C.js:312945:24) {
  status: 400
}
{"type":"result","timestamp":"2026-06-11T00:43:20.002Z","status":"error","error":{"type":"unknown","message":"[API Error: {\"type\":\"unknown_model_ai_credits\",\"message\":\"Model \\\"gemini-3.1-flash-tts-preview\\\" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {\\\"input\\\": 3.0, \\\"output\\\": 15.0}) to provide a fallback rate, or add the model to the pricing table.\",\"model\":\"gemini-3.1-flash-tts-preview\"}]"},"stats":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0,"duration_ms":0,"tool_calls":0,"models":{"gemini-2.5-flash-lite":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0},"gemini-3.1-pro-preview":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0}}}}

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/actions/runs/27315872388

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 skill from .github/skills/agentic-workflows/SKILL.md or https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.md
• Type debug the agentic workflow smoke-gemini failure in https://github.com/github/gh-aw/actions/runs/27315872388

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: false

Generated from Smoke Gemini · ◷

• expires on Jun 11, 2026, 12:44 PM UTC

[github-actions]

Agent job 27320398264 failed.

Warning

Engine Failure: The gemini engine terminated unexpectedly.

Last agent output:

    at async Models.generateContentStream ((redacted)
    at async (redacted)
    at async (redacted)
    at async retryWithBackoff ((redacted)
    at async GeminiChat.makeApiCallAndProcessStream ((redacted)
    at async GeminiChat.streamWithRetries ((redacted)
    at async Turn.run ((redacted) {
  status: 400
}
{"type":"result","timestamp":"2026-06-11T02:51:55.395Z","status":"error","error":{"type":"unknown","message":"[API Error: {\"type\":\"unknown_model_ai_credits\",\"message\":\"Model \\\"gemini-3.1-flash-tts-preview\\\" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {\\\"input\\\": 3.0, \\\"output\\\": 15.0}) to provide a fallback rate, or add the model to the pricing table.\",\"model\":\"gemini-3.1-flash-tts-preview\"}]"},"stats":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0,"duration_ms":0,"tool_calls":0,"models":{"gemini-2.5-flash-lite":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0},"gemini-3.1-pro-preview":{"total_tokens":0,"input_tokens":0,"output_tokens":0,"cached":0,"input":0}}}}

Generated from Smoke Gemini · ◷