fix(types): make ImageGenerationCall result and status optional - #3558
fix(types): make ImageGenerationCall result and status optional#3558okxint wants to merge 2 commits into
Conversation
Filters out content items where `text` is None before joining, preventing a TypeError crash when the API returns null for a text block (issue openai#3063).
result (base64 image string) and status are output-only fields populated by the API response. Marking them Required on an input TypedDict forces callers to provide values they don't have and wouldn't supply when referencing an existing image generation call by id and type. Fixes openai#2648
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 91f9172b37
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".
| result: Optional[str] | ||
| """The generated image encoded in base64.""" | ||
|
|
||
| status: Required[Literal["in_progress", "completed", "generating", "failed"]] | ||
| status: Literal["in_progress", "completed", "generating", "failed"] |
There was a problem hiding this comment.
This only fixes the standalone ResponseInputItemParam; the primary responses.create(..., input=...) overload imports ResponseInputParam from response_input_param.py, which defines a separate ImageGenerationCall union member that still has result: Required[Optional[str]] and status: Required[...]. In the usual responses.create(input=[{"type": "image_generation_call", "id": ...}]) path, type checkers will still require those output-only fields, so the typing bug remains for the main Responses API unless the mirrored type in response_input_param.py is updated too.
Useful? React with 👍 / 👎.
1 participant
result(base64 image string) andstatusare output-only fields populated by the API. Marking themRequiredon an inputTypedDictforces callers to supply values they don't have and wouldn't provide when referencing an existing image generation call byidandtype.Fixes #2648