fix(anthropic): accept dict format for reasoning_effort parameter #17441
+146
−8
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
SDKs like openai-agents-python pass reasoning_effort as a dict:
{"effort": "medium", "summary": "auto"}
The Anthropic provider now extracts the "effort" key from dict format,
ignoring "summary" (Anthropic doesn't support configurable summary).
This is backward compatible - string format still works.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Title
fix(anthropic): accept dict format for reasoning_effort parameter
Pre-Submission checklist
tests/litellm/directorymake test-unitType
🐛 Bug Fix
Changes
SDKs like
openai-agents-pythonpassreasoning_effortas a dict containing botheffortandsummaryfields:The OpenAI Responses API handler already supports this dict format, but the Anthropic provider only accepted string format, causing the parameter to be silently ignored.
What was changed
File:
litellm/llms/anthropic/chat/transformation.pyUpdated the
reasoning_efforthandling to accept both formats:"medium"→ works as before{"effort": "medium", "summary": "auto"}→ extractseffort, ignoressummary(Anthropic doesn't support configurable summary)Tests added
6 new unit tests in
tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py:test_reasoning_effort_string_format_opus_45test_reasoning_effort_dict_format_opus_45test_reasoning_effort_dict_format_other_modelstest_reasoning_effort_string_format_other_modelstest_reasoning_effort_dict_without_effort_keytest_reasoning_effort_dict_with_none_effortBackward compatibility
This is fully backward compatible - existing string format behavior is unchanged.