[aw] Smoke Copilot BYOK AOAI (api-key) has no AI credits pricing for model (o4-mini-aw)

Chiusa
  • Qualcosa non va?
#10,175 3 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
25/100
Tipo di issue
Bug
Chiarezza
Abbastanza chiara
Stato di attività
Ferma
Stack tecnologico
github-actions, typescript, yaml
Ambito
ci-cd, devtools

Direzione di ricerca

Start with the workflow frontmatter in .github/workflows/smoke-copilot-byok-aoai-apikey.md on the linked branch and inspect the failed run for context. Check how the AWF pricing system handles o4-mini-aw and whether the workflow should define pricing, map the model, or use a recognized model. Done means the workflow completes without the missing-pricing error; PR #10149 is already linked.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

agentic-workflows
Workflow Failure

Workflow: Smoke Copilot BYOK AOAI (api-key)
Branch: copilot/rootless-startup-fix-config-audit
Run: https://github.com/github/gh-aw-firewall/actions/runs/39061401456
Pull Request: #10149

[!WARNING]
Model has no AI credits pricing: The agent failed because model o4-mini-aw is not in the built-in pricing table and no default fallback pricing is configured. The AWF API proxy rejected every inference request with HTTP 400.

This is a configuration issue — retrying will not help. The model must have pricing before the workflow can run.

How to fix this

Option 1 — Add pricing in the workflow frontmatter:

models:
  providers:
    github-copilot:
      models:
        'o4-mini-aw':
          cost:
            # Placeholder values — replace with actual pricing for this model
            input: "0e0"      # $0.00 per million input tokens
            output: "0e0"     # $0.00 per million output tokens
            cache_read: "0e0"  # $0.00 per million cache-read tokens
            cache_write: "0e0" # $0.00 per million cache-write tokens

Use the provider key matching your engine: github-copilot (Copilot), anthropic (Claude), openai (Codex), or google (Gemini). Only input and output are required; the rest default to zero (or output for reasoning).

Option 2 — Map the model to a known model using the models field:

If o4-mini-aw is an alias for a model already in the built-in pricing table, use the models frontmatter field to provide the mapping:

models:
  'o4-mini-aw':
    - claude-sonnet-4-5

Option 3 — Switch to a model already in the built-in pricing table:

Replace o4-mini-aw in the workflow frontmatter with a model name that the AWF pricing system recognizes (e.g. claude-sonnet-4-5, gpt-4.1, gemini-2.0-flash).

[!WARNING]
Task Could Not Be Completed: The workflow recorded a report_incomplete signal: 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.
Last tool call status: not recorded
Failed tool calls observed: 0
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 6 tools)
Safe-output CLI calls observed: unknown (not recorded)
Safe-output MCP calls observed: 0
Safe-output persistence: not recorded
Engine error: Model has no AI credits pricing (missing_model_pricing_error)
Agent finished without emitting a terminal safe output; task completion could not be confirmed.
Engine HTTP error codes: 400
Last engine error type: missing_model_pricing_error
Retry attempts observed: 0

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

The runtime did not record a specific cause. Check the linked run for failure details.

Only runtime metadata is shown; agent-generated text is excluded.

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/39061401456
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 Copilot BYOK AOAI (api-key) · ◷

  • expires on Oct 24, 2026, 7:23 PM UTC
Lingua principale
TypeScript
Stelle
157
Fork
80
Merge medio
4h 34m
PR unite (30g)
395

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di github/gh-aw-firewall

Tutte le issue di github/gh-aw-firewall

Issue simili

Altre issue su TypeScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.