Repository navigation
fix(router): disable DeepSeek reasoning and use 256 output tokens - #886
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Production's DeepSeek router exhausted its 30-token budget on reasoning and returned empty classifications, causing clear follow-up requests to display an agent picker. A live gateway probe reproduced the empty, length-limited response; disabling thinking returned the correct recipient with zero reasoning tokens.
Set conversation routing to 256 output tokens and send
thinking: {type: "disabled"}for DeepSeek models over the OpenAI-compatible API. This covers proactive human classification and agent handoffs; other models do not receive the DeepSeek-specific option. Prompt and UI behavior are unchanged.Validation: 169 tests pass across LLM routing, routing choices, completion routing, response modes, and thread collaboration. Includes request compatibility checks for DeepSeek, OpenAI, and Anthropic in both human and agent routing paths.