ci: Backfill content workflow (skip crawl) + empty-snapshot purge guard (#98)

perf: store chunk content in Neon so hydration needs no live fetch (Stage A) (#97)

QuOTE questions in the enrichment pipeline + one-click eval default (#88)

Fix synopsis extraction: read the Sphinx definition line, not the signature head

Extractive synopsis: lead every api chunk with the page's own summary sentence

Contextual Retrieval: LLM glosses for api reference pages

Parametrize the embedding model for a proper bake-off on v1

Revert the embedder to bge-small: the bge-base A/B showed no gain

Swap the embedder: bge-small (384d) -> bge-base (768d)

Cut oversized sections at natural seams; embed only the new parts

Serve questions concurrently instead of one-at-a-time (#49)

Codebase quality pass: kill silent-truncation hacks, fix latent bugs, cover them (#46)

Enrich indexed text with symbol + heading path (give URL/title semantic weight)

Fix polluted anchors/titles, purge stale chunks, add channel debug to search

Switch embeddings to a local CPU model (bge-small): free tier APIs can't index the corpus

M2 indexing: Neon schema, resumable Gemini embedding, one-command build script