feat(rag): overlapping chunker, retrieval knobs, sqlite-vec index

- Chunker: char overlap across boundaries + hard-split of oversized paragraphs.
- Retrieval knobs: rag_top_k / rag_min_score in settings + Settings UI.
- Vector index: sqlite-vec ANN over document embeddings, dual-written and
  backfilled, with brute-force cosine as the guaranteed fallback.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

requirements-base.txt

@@ -40,6 +40,9 @@ PyYAML
 # Document ingest (RAG): pure-Python text extraction, no native deps
 pypdf
 python-docx
+# Vector search: loadable SQLite extension (prebuilt wheels). Brute-force cosine
+# stays as the fallback when the host Python can't load extensions.
+sqlite-vec
 
 # Documentation Support
 markdown-it-py