[codex] reject empty AnyLLM Chat Completions responses - #4559
Closed
seanxuu wants to merge 1 commit into
Closed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
This pull request fixes #4552 by making the AnyLLM Chat Completions path reject normalized responses with an empty
choiceslist.Why
AnyLLMModel._get_response_via_chat()previously treated an empty provider response as a successfulModelResponse(output=[]). The native Chat Completions adapter already raisesModelBehaviorErrorfor this malformed response shape, so this change keeps the provider adapters consistent and prevents malformed responses from entering the runner as successful turns.Validation
uv run pytest -q tests/models/test_any_llm_model.py -k any_llm_chat_path— 8 passeduv run pytest -q tests/models/test_any_llm_model.py— 72 passed, 11 skippedmake formatandmake lint— passedmake typecheckand the full test suite were attempted; unrelated optional-dependency and existing extension/voice/runloop failures remain in the local environment.Scope
The change is limited to the non-streaming AnyLLM Chat Completions path and its regression test. Responses, streaming, valid choices, and existing content-filter handling remain unchanged.