fix(lemonade): surface reasoning in stream and non-stream chat#5586
Open
nehaaprasaad wants to merge 2 commits into
Open
fix(lemonade): surface reasoning in stream and non-stream chat#5586nehaaprasaad wants to merge 2 commits into
nehaaprasaad wants to merge 2 commits 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Pull Request Type
Relevant Issues
resolves #5585
Description
Lemonade used the default stream handler, which only forwarded delta.content, so reasoning models never showed chain-of-thought. Added a Lemonade handleStream that emits for reasoning_content / reasoning deltas (matching other providers) and merged the same fields into non-streaming responses via #parseReasoningFromResponse. File: server/utils/AiProviders/lemonade/index.js.
Visuals (if applicable)
N/A (backend only).
Additional Information
Close reasoning block on finish_reason when the model stops after reasoning and before any answer tokens, so stored text matches the UI.
Developer Validations
[ ] I ran yarn lint from the root of the repo & committed changes
[ ] Relevant documentation has been updated (if applicable)
[ ] I have tested my code functionality
[ ] Docker build succeeds locally