fix(anthropic): tolerate models that reject an explicit temperature#84
Merged
Conversation
Agent.execute() always passes temperature=, but the newest Claude models (e.g. Sonnet 5) reject it with "temperature is deprecated for this model". OpenAIModel already strips temperature for its reasoning models by name, but Claude's naming gives no reliable signal (a "5" appears in models that both do and don't accept it). So AnthropicModel learns from the first rejection: it retries once without temperature and remembers, skipping it on subsequent calls. Unrelated BadRequestErrors are re-raised untouched. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…ting Base `ainvoke` printed every caught error to stdout before delegating to handle_invoke_error, so an error a subclass expects and recovers from -- e.g. AnthropicModel retrying without a rejected `temperature` -- still dumped a scary 400 to the console and looked like a failure. Demote it to a debug log; genuinely unhandled errors still surface upstream with a traceback. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
mattprintz
approved these changes
Jul 1, 2026
mattprintz
left a comment
mattprintz
left a comment
Collaborator
There was a problem hiding this comment.
Slick solution. Looks good to me.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent.execute()always passestemperature=, but the newest Claude models (e.g. Sonnet 5) reject it with"temperature is deprecated for this model".OpenAIModel already strips temperature for its reasoning models by name, but Claude's naming gives no reliable signal (a "5" appears in models that both do and don't accept it). So AnthropicModel learns from the first rejection: it retries once without temperature and remembers, skipping it on subsequent calls. UnrelatedBadRequestErrorsare re-raised untouched.