fix(workbuddy): stop rewriting deepseek-v4.1-flash to deep-model - #163
Merged
Merged
Conversation
Current WorkBuddy catalogs already expose deepseek-v4.1-flash natively. The hardcoded alias sent deep-model upstream and let chat silently fall back to other models. Resolve the upstream ID from the live catalog instead, keeping the legacy deep-model path only when the catalog still publishes that native spelling.
2 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
deepseek-v4.1-flash→deep-modelwhen building the upstream request.deep-modelcatalogs still work via the alias entry.deepseek-v4.1-flashsilently came back askimi-k3/glm-5.3.Test plan
go test ./internal/providers/workbuddy -count=1deepseek-v4.1-flashand confirm chunkmodelstaysdeepseek-v4.1-flash(or at least notkimi-k3/glm-5.3)request_logs.mapped_modelfor the stream request is no longer a random fallback model/v1/modelsshowsnative_model=deepseek-v4.1-flash