Skip to content

fix: correct prompt_cache_retention literal to use underscore#2893

Open
furkankoykiran wants to merge 2 commits intoopenai:mainfrom
furkankoykiran:fix/prompt-cache-retention-literal
Open

fix: correct prompt_cache_retention literal to use underscore#2893
furkankoykiran wants to merge 2 commits intoopenai:mainfrom
furkankoykiran:fix/prompt-cache-retention-literal

Conversation

@furkankoykiran
Copy link

Fixes #2883

Description

The SDK declares prompt_cache_retention with Literal["in-memory", "24h"] (hyphen), but the API rejects "in-memory" with a 400 error and only accepts "in_memory" (underscore). This PR fixes all Literal type definitions and test occurrences across the repository to correctly use "in_memory".

@furkankoykiran furkankoykiran requested a review from a team as a code owner February 25, 2026 20:06
Copy link

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2a2257e7be

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

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.

prompt_cache_retention type declares "in-memory" but API expects "in_memory"

1 participant