fix(models): populate finish_reason on AnthropicLlm responses#5512
Open
sebastienc wants to merge 1 commit intogoogle:mainfrom
Open
fix(models): populate finish_reason on AnthropicLlm responses#5512sebastienc wants to merge 1 commit intogoogle:mainfrom
sebastienc wants to merge 1 commit intogoogle:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes #5394
Disclaimer: I'm using Claude Code to generate the following text. I find the summary is better than what I would've wrote.
AnthropicLlmwas callingto_google_genai_finish_reason()but never wiring its result intoLlmResponse, sofinish_reasonwas alwaysNone. This fix connects it end-to-end and expands the mapping to cover all stop reasons the current Anthropic API can return.to_google_genai_finish_reason— extended to coverpause_turn→STOP(streaming interruption, e.g. server-side tool use) andrefusal→SAFETY(model refusal); all other unknown values continue to returnFINISH_REASON_UNSPECIFIEDmessage_to_generate_content_response— passesstop_reasonthroughto_google_genai_finish_reasonand sets it on the returnedLlmResponse_generate_content_streaming— readsstop_reasonfrom themessage_deltaevent and setsfinish_reasonon the final aggregatedLlmResponseTesting plan
10 new tests added to
tests/unittests/models/test_anthropic_llm.py. Full suite: 69 passed.