fix: Handle Pydantic models in ChatMessage cache key serialization #13
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The `_wrap` validator in `ChatMessageBase` creates a cache key by calling `json.dumps(data)`. However, `ChatMessageAssistant.extract_reasoning` (a mode="before" validator) may create `ContentReasoning` and `ContentText` Pydantic model objects in the data dict before `_wrap` runs. Standard `json.dumps` cannot serialize Pydantic models, causing a TypeError. This adds a custom JSON encoder that handles Pydantic BaseModel objects by calling `model_dump(mode="json")` on them. Fixes deserialization of eval logs containing ContentReasoning objects. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
TypeError: Object of type ContentReasoning is not JSON serializablewhen deserializing eval logs containing extended thinking/reasoning contentRoot Cause
The
_wrapvalidator inChatMessageBasecreates a cache key usingjson.dumps(data). However,ChatMessageAssistant.extract_reasoning(amode="before"validator) may createContentReasoningandContentTextPydantic model objects in the data dict before_wrapruns. Standardjson.dumpscannot serialize Pydantic models.Fix
Added a custom JSON encoder
_PydanticJSONEncoderthat handles PydanticBaseModelobjects by callingmodel_dump(mode="json").Test plan
<think>blocks🤖 Generated with Claude Code