fix(openai): replay reasoning_content for Xiaomi MiMo tool calls#3350
Open
joaohildebrandt wants to merge 1 commit into
Open
fix(openai): replay reasoning_content for Xiaomi MiMo tool calls#3350joaohildebrandt wants to merge 1 commit into
joaohildebrandt wants to merge 1 commit into
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Xiaomi MiMo API requires
reasoning_contentin follow-up requests when tool calls exist in conversation history. Forge's pipeline already handles this for DeepSeek, Fireworks, and Kimi via the
ReasoningContent+DefaultReasoningContenttransformers, but Xiaomi MiMo was left out, causing tool-based conversations to fail after the first tool call.Fix
Three changes in
crates/forge_app/src/dto/openai/transformers/pipeline.rs:ReasoningContentguard — addedis_xiaomi_mimo_provider(provider)so thatreasoning_detailsare converted toreasoning_contentfor MiMo, matching DeepSeek/Fireworks/Kimi behavior.DefaultReasoningContentguard — added the same check so that assistant messages without reasoning still get an emptyreasoning_contentfield, which MiMo requires when tool calls are present.New helper — extracted
is_xiaomi_mimo_provider()following the existingis_deepseek_provider()/is_zai_provider()pattern.Testing
Two new tests added (mirroring existing DeepSeek tests):
test_xiaomi_mimo_provider_converts_reasoning_details_to_reasoning_content—reasoning_details→reasoning_contentconversiontest_xiaomi_mimo_provider_falls_back_to_empty_reasoning_content_when_none— verifies empty fallback when no reasoning is presentFull test suite: 702 passed, 0 failed. Clippy and fmt clean.
Related