[braintrust-bot]

Automated regeneration of SDK types.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-11-05T16:53:29.757692Z	c3f71b2	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review" or "Codex (@codex) security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: c3f71b2013

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 (@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 (@codex) address that feedback".

[chatgpt-codex-connector]

Add runtime support for decisions prompt blocks

When load_prompt() returns the newly accepted "decisions" variant, PromptData.from_dict_deep() cannot deserialize it because py/src/braintrust/prompt.py still defines PromptBlockData as only PromptCompletionBlock | PromptChatBlock; it therefore leaves the block as a plain dictionary. Calling Prompt.build() then accesses self.prompt.type and raises AttributeError, so decisions prompts advertised by this public type cannot be loaded and built by the SDK. Add the corresponding runtime dataclasses/build handling and focused round-trip coverage before exposing this variant.

Useful? React with 👍 / 👎.