fix(provider): flush each OpenAI reasoning item as independent Thinking block#161
Merged
Merged
Conversation
…ng block (#161) OpenAI emits one reasoning item per web_search_call in a single response. The old code overwrote `thinking_signature` on each ThinkingSignature chunk, keeping only the last ID. On multi-turn replay, 4 of 5 web_search_call items lacked their required reasoning predecessor, causing API 400 errors. Fix: on each ThinkingSignature, immediately flush accumulated thinking text + signature as a ContentBlock::Thinking into server_blocks, preserving the 1:1 pairing between reasoning and web_search_call in stream order.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
thinking_signatureon each ThinkingSignature chunk, keeping only the last IDChanges
crates/loopal-runtime/src/agent_loop/llm_chunk.rs— flush ThinkingSignature into server_blocks instead of overwriting single fieldcrates/loopal-provider/tests/suite/openai_reasoning_test.rs— add multi-reasoning pairing testTest plan
bazel test //crates/loopal-provider:loopal-provider_testpassesbazel test //crates/loopal-runtime:loopal-runtime_testpassesbazel test //crates/loopal-context:loopal-context_testpassesbazel build //crates/loopal-runtime:loopal-runtime --config=clippyzero warnings