fix(inference): forward max_tokens & extra_body in crop-describe#68
Merged
Merged
Conversation
CropDescribeRequest accepted neither field, so the router silently fell back to the engine default max_tokens (512). That is too small for the structured-JSON scene schema and truncated responses mid-output — cortex logged 2131 "Expecting , delimiter" parse failures over a single night. Adds both fields to the request schema and forwards them to engine.analyze_frame, matching what /describe at the same router already does. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
max_tokensandextra_bodyfields toCropDescribeRequestand forward them toengine.analyze_frame.max_tokens=512is too small for the structured-JSON scene schema; cortex logged 2131Expecting , delimiterJSON parse failures over a single night./describeat the same router already does.Test plan
max_tokens=4096andextra_body={"enable_thinking": False}reachanalyze_frame🤖 Generated with Claude Code