Skip to content

fix(ai): route Copilot Grok 4.5 to responses - #906

Closed
jay-tau wants to merge 1 commit into
PrimeIntellect-ai:mainfrom
jay-tau:codex/fix-875-copilot-grok-responses
Closed

fix(ai): route Copilot Grok 4.5 to responses#906
jay-tau wants to merge 1 commit into
PrimeIntellect-ai:mainfrom
jay-tau:codex/fix-875-copilot-grok-responses

Conversation

@jay-tau

@jay-tau jay-tau commented Aug 8, 2026

Copy link
Copy Markdown

Summary

  • Route GitHub Copilot grok-4.5 through the OpenAI Responses API.
  • Regenerate the Copilot model catalog and add regression coverage.

Testing

  • npx tsx ../../node_modules/vitest/dist/cli.js --run test/github-copilot-models.test.ts
  • npm run check

Fixes #875

Note

Route GitHub Copilot grok-4.5 to the Responses API instead of Chat Completions

The grok-4.5 model under the github-copilot provider does not support the Chat Completions endpoint, so it is now assigned openai-responses in generate-models.ts alongside the existing gpt-5 and oswe models. The generated catalog and a new test in github-copilot-models.test.ts confirm the correct routing.

Macroscope summarized 76b84a2.

@jay-tau
jay-tau marked this pull request as ready for review August 8, 2026 06:42

Copy link
Copy Markdown
Member

Hi, thanks for taking the time to contribute to Prime Agent! Since open sourcing the project, we’ve received far more pull requests than we can responsibly review and validate. Prime Agent runs directly on users’ machines, so we need to be deliberate about which changes we accept and how they are reviewed. Rather than leave a large backlog that we cannot meaningfully work through, we’re closing the current PR queue and moving to a discussion-first contribution process.

We have established new contribution guidelines to help us continue iterating on Prime Agent and better manage contributions from the community. Going forward, we won’t review unsolicited pull requests. Instead, please start with a GitHub Discussion. We’ll identify recurring bugs and feature requests, create Issues for work we want to pursue, and invite pull requests from maintainers or vouched contributors when implementation is ready. Please read the full process documented in our contribution guidelines.

While we’re closing this backlog, we’re still reviewing it at a high level to identify recurring bugs, useful ideas, and important problems that we should address ourselves. Thanks again for the time you put into this!

snimu added a commit that referenced this pull request Sep 5, 2026
….8 Max route

Two regen blockers surfaced by fresh upstream data:

- Copilot now serves gpt-6-astra; the classification coverage invariant fails
  regen on the unclassified family, as designed. Classified as
  openai-responses: native OpenAI serves its whole catalog (including
  gpt-6-astra) through the Responses API here, and every OpenAI family
  Copilot has shipped since gpt-5 is Responses-only (upstream pi-mono #906
  probe class); no Copilot family has moved from responses back to chat
  completions. models.dev lists it live (1.05M context, reasoning,
  tool-capable) so the next regen ships it on 8 provider rows.
- OpenRouter renamed qwen/qwen3.8-max to qwen/qwen3.8-max-0902 while Prime
  Inference still serves the undated id, so fresh regens dropped the row's
  OpenRouter-derived thinkingLevelMap and failed the mandatory-efforts pin in
  prime-inference-models.test.ts (pre-existing on main, A/B-verified by the
  sandbox gate). Added the alias PRIME_INFERENCE_OPENROUTER_ALIASES exists
  for; the regenerated row keeps its exact previous map.

Catalog regenerated: 42 rows differ (8 gpt-6-astra additions, the qwen rename
pair, and fetch-time upstream drift: price updates including Copilot
gpt-5.6-sol doubling, new ling-sante/muse rows, granite-4.1 removal). Regen
byte-stable across a second run; full ai suite green against the fresh
catalog.

Linear: RES-1273
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

GitHub Copilot Grok 4.5 is incorrectly routed to /chat/completions

2 participants