Skip to content

[aw] Smoke Gemini hit AI credits rate limit #4980

Closed

Description

@github-actions

Workflow Failure

Workflow: Smoke Gemini
Branch: copilot/fix-duplicate-url-normalisation
Run: https://github.com/github/gh-aw-firewall/actions/runs/27507307563
Pull Request: #4949

Warning

AI Credits Budget Exceeded

The workflow hit the configured max-ai-credits guardrail.

Increase the limit

Update max-ai-credits in your workflow frontmatter:

max-ai-credits: 2000
Tips 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.

Warning

Unknown Model for AI Credits Pricing: The agent failed because the requested model is not in the built-in AI credits pricing table and max-ai-credits is active. The AWF API proxy rejected the request with an HTTP 400 error.

This is a configuration issue, not a transient error — retrying will not help.

How to fix this

Choose one of the following options:

Option 1 — Map the model to a known model using the models field:

Use the models frontmatter field to provide an alias from your custom model name to a model that exists in the built-in pricing table:

---
model: my-custom-model
max-ai-credits: 500
models:
  my-custom-model:
    model: gpt-4.1
---

Option 2 — Use a model already in the built-in pricing table:

Switch to a model name that the AWF pricing system recognizes directly (e.g. gpt-4.1, claude-sonnet-4-5, gemini-2.0-flash).

Option 3 — Set a default AI credits price as a fallback:

Add defaultAiCreditsPricing to supply a price for any unrecognized models:

---
model: my-custom-model
max-ai-credits: 500
models:
  my-custom-model:
    defaultAiCreditsPricing: 3.0
---

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-firewall/actions/runs/27507307563
Manually invoke the agent

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

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 21, 2026, 6:06 PM UTC

Activity

  1. github-actions commented on Jun 14, 2026

    @github-actions
    ContributorAuthor

    Agent job 27506401665 failed.

    Warning

    AI Credits Budget Exceeded

    The workflow hit the configured max-ai-credits guardrail.

    Increase the limit

    Update max-ai-credits in your workflow frontmatter:

    max-ai-credits: 2000
    Tips 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.

    Warning

    Unknown Model for AI Credits Pricing: The agent failed because the requested model is not in the built-in AI credits pricing table and max-ai-credits is active. The AWF API proxy rejected the request with an HTTP 400 error.

    This is a configuration issue, not a transient error — retrying will not help.

    How to fix this

    Choose one of the following options:

    Option 1 — Map the model to a known model using the models field:

    Use the models frontmatter field to provide an alias from your custom model name to a model that exists in the built-in pricing table:

    ---
    model: my-custom-model
    max-ai-credits: 500
    models:
      my-custom-model:
        model: gpt-4.1
    ---

    Option 2 — Use a model already in the built-in pricing table:

    Switch to a model name that the AWF pricing system recognizes directly (e.g. gpt-4.1, claude-sonnet-4-5, gemini-2.0-flash).

    Option 3 — Set a default AI credits price as a fallback:

    Add defaultAiCreditsPricing to supply a price for any unrecognized models:

    ---
    model: my-custom-model
    max-ai-credits: 500
    models:
      my-custom-model:
        defaultAiCreditsPricing: 3.0
    ---

    Generated from Smoke Gemini · ◷

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions