v1.0.0: Intelligence — candle runtime, orchestrator, reranker, query expansion#10

Merged

devwhodevs merged 13 commits into

mainfrom

feat/v1.0-intelligence

Mar 25, 2026

Commits on Mar 25, 2026

feat: add LLM trait definitions and MockLlm (Task 1)

devwhodevs
and
claude
committed
fix(llm): remove unnecessary borrow, dead union==0 check, add empty-query test

devwhodevs
and
claude
committed
feat(config): add intelligence config and ModelConfig struct

devwhodevs
and
claude
committed
feat(store): add llm_cache table and cache methods

devwhodevs
and
claude
committed
feat: make init_vec_table accept a runtime dim parameter

devwhodevs
and
claude
committed
feat(llm): add GGUF download infrastructure

devwhodevs
and
claude
committed
feat(indexer): add dimension migration on model upgrade

devwhodevs
and
claude
committed
Task 11: Add cache key function for orchestration results
devwhodevs
committed
feat(llm): add CandleOrchestrator and JSON parsing for query expansion

devwhodevs
and
claude
committed
feat(llm): add CandleRerank cross-encoder for search result reranking

devwhodevs
and
claude
committed
feat(search): add two-pass RRF pipeline with reranker lane

devwhodevs
and
claude
committed
feat: show intent in --explain output and intelligence state in status

devwhodevs
and
claude
committed
chore: v1.0.0 — intelligence: candle runtime, orchestrator, reranker, query expansion

devwhodevs
and
claude
committed