Repository navigation
fix: schema-constrained managed classifier output - #47
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A Gemini fallback can reach Groq JSON-object validation and fail before the classifier receives an answer. Request schema-constrained output through Free AI while retaining automatic model/provider choice, compact score tuples, semantic validation, the 2,000-token cap, the two consumer attempts, and the shared 25-second pipeline deadline.
Use uniform numeric arrays rather than tuple-only schema keywords across providers. The decoder still enforces integer label indexes, exact result/score counts, finite probabilities in [0,1], and nonempty distributions. Safety and ranking semantics are unchanged.
Validation: focused classifier/ranking/deadline tests passed (58 tests); schema assertions cover full batches, 30-label perspectives, strict mode, and absence of provider/model pins. Full CI packaging and live qualification are required before closing the incident. Requires Free AI schema release 10c540d16290eb34e90fc1bd3a16c565572ac416, deployed via successful workflow 37358581359.