fix: relax service_tier validation for OpenRouter responses#44
Merged
timeleft-- merged 1 commit intomainfrom May 5, 2026
Merged
fix: relax service_tier validation for OpenRouter responses#44timeleft-- merged 1 commit intomainfrom
timeleft-- merged 1 commit intomainfrom
Conversation
OpenRouter returns service_tier: "standard" which falls outside the OpenAI SDK's Literal["auto","default","flex","scale","priority"]. any-llm-sdk inherits this strict type and revalidates responses, causing propose_truth to fail with a Pydantic ValidationError. Monkey-patch ChatCompletion.service_tier to accept str | None at module load. Includes a regression test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ChatCompletion.service_tierto acceptstr | Noneat module load, fixing a PydanticValidationErrorwhen OpenRouter returnsservice_tier: "standard"(outside the OpenAI SDK's strict Literal set)any-llm-sdkinherits the strict type and revalidates responses in_convert_chat_completion, so fava-trails cannot recover the already-paid response from a wrapperChatCompletionaccepts non-standardservice_tiervalues after the patchContext
Trust gate
propose_truthconsistently errors on thoughts (e.g.01KQVCSTJ6CKM8H2YEZFFBTW70) with:Test plan
test_chatcompletion_accepts_nonstandard_service_tier— verifies the patch works🤖 Generated with Claude Code