feat(core): structured intent classification via Extractor#559
Merged
Conversation
github-actions
bot
added
enhancement
bug-ops
force-pushed
the
feat/549-structured-output-integration
branch
from
13fd961 to
fa6e0f9
Compare
Add LLM-based disambiguation when skill matching scores are ambiguous. Introduces IntentClassification struct with JsonSchema, chat_typed<T> free function in zeph-llm, and ScoredMatch to propagate similarity scores from both InMemory and Qdrant backends. Disambiguation triggers only when top-2 candidate delta falls below configurable threshold.
bug-ops
force-pushed
the
feat/549-structured-output-integration
branch
from
fa6e0f9 to
f8e436b
Compare
Add integration test validating full disambiguation pipeline through agent loop with MockProvider. Add unit test documenting that threshold 0.0 effectively disables disambiguation. Update changelog, docs, and README for #550.
github-actions
bot
added
documentation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
IntentClassificationstruct withJsonSchemaderive for LLM-based skill disambiguationchat_typed<T>()free function in zeph-llm for structured output extractionScoredMatchto propagate similarity scores from InMemory and Qdrant backendsrebuild_system_prompt()— triggers only when top-2 delta < configurable threshold (default 0.05)disambiguation_thresholdto[skills]config sectionTest plan
Closes #550
Part of Epic #549