Return final answer first in AnthropicChatModel - #7001
Open
iuliiasobolevska wants to merge 1 commit into
Open
iuliiasobolevska wants to merge 1 commit into
iuliiasobolevska wants to merge 1 commit into
Conversation
Anthropic thinking blocks were added before the accumulated assistant response, so ChatResponse.getResult() exposed reasoning instead of the final answer. Place the assistant generation first while retaining thinking generations and replay state. Fixes spring-projects#7000 Signed-off-by: Iuliia Sobolevska <isobolevska@netflix.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
AnthropicChatModelcurrently adds thinking and redacted-thinking generations before the accumulated assistant response. SinceChatResponse.getResult()returns the first generation, callers receive reasoning content instead of the final answer, and typedChatClientconversion can fail on empty redacted-thinking content.This change places the final
AnthropicAssistantMessagefirst while preserving individual thinking generations ingetResults()and signed thinking content for tool-call replay.Fixes #7000
Testing
Tests run: 126, failures: 0, errors: 0, skipped: 0. Formatting, Checkstyle, JAR packaging, sources, and Javadocs also passed.
AI assistance was used for investigation, implementation, and test preparation.