Open
Conversation
Apply tool_result_cache_type only to the last tool result message across all messages instead of applying it to each tool result during creation. This prevents cache accumulation when there are multiple tool call rounds.
1 task
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Refactor of #485.
Problem
When using
tool_result_cache_typein multi-step tool calling scenarios, cache_control was being applied to every ToolResultMessage instead of just the last one. This could exceed Anthropic's 4 cache breakpoint limit and is unnecessary since the system uses "longest matching prefix" caching.Solution
Move cache control application from
Text.php(per-message duringhandleToolCalls()) toMessageMap::map()where it applies cache_control only to the last ToolResultMessage across all messages.Changes