Repository navigation
V2 runner has no native route for @ai-sdk/xai models, dropping prompt cache key #35034
Description
The V2 session runner sets a prompt cache key on every request (packages/core/src/session/runner/llm.ts) and the OpenAI Responses protocol lowers it to prompt_cache_key. But SessionRunnerModel.fromCatalogModel has no branch for @ai-sdk/xai, so xai catalog models fail with UnsupportedApiError and never run through the native route that carries the key.
Related context: xAI's prompt caching relies on prompt_cache_key for the Responses API (https://docs.x.ai/developers/advanced-api-usage/prompt-caching/maximizing-cache-hits), and xAI's Responses API follows the OpenAI shape, so the existing OpenAIResponses route can serve these models.
One wrinkle: the OpenAIResponses route's default baseURL points at api.openai.com, so xai models without an explicit catalog URL need an explicit default of https://api.x.ai/v1.
Activity
github-actions commentedon Jul 2, 2026
This issue doesn't fully meet our contributing guidelines.
What needs to be fixed:
Please edit this issue to address the above within 2 hours, or it will be automatically closed.
This issue may overlap with a recently filed issue. Please check:
prompt_cache_key/x-grok-conv-id). The two issues describe related but distinct problems; consider whether they should be consolidated.If you believe this was flagged incorrectly, please let a maintainer know.
github-actions commentedon Jul 3, 2026
This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.
Feel free to open a new issue that follows our issue templates.