fix(aws): Handle thinking with tools, use CountTokens API for Haiku 4.5 #698
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
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Outdated suggestions cannot be applied.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.
Couple of updates to ChatBedrock/ChatBedrockConverse for Haiku 4.5 support:
get_num_tokens_from_messages().bind_tools()andwith_structured_output(), as Haiku (and Sonnet) 4.5 still do not support this.test_structured_output_tool_choice_not_supportedConverse integration test has not been updated to include Haiku 4.5, which appears to behave very inconsistently with a structured output schema compared to previous Claude thinking models. Sonnet 4.5 and older models produce a tool call 100% of the time if the query is directly applicable to the schema. However, on Haiku 4.5, the chance of this happening was observed to be <5%.