Skip to content

Azure OpenAI Responses throws 400 when prompt_cache_key is sent to endpoints that do not support it #102907

Description

@aniruddhaadak80

Description

In packages/ai/src/providers/azure-openai-responses.ts, the prompt_cache_key parameter is passed to the Azure OpenAI API. Since some Azure endpoints do not support this parameter, it results in a 400 Bad Request error for standard model completions unless caching options are explicitly disabled.

Location

Metadata

Metadata

Assignees

No one assigned

    Labels

    P2Normal backlog priority with limited blast radius.clawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.staleMarked as stale due to inactivity

    Type

    No type

    Fields

    Priority

    None yet

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions