feat(rag): hybrid FTS+vector retrieval and multi-format ingestion — name-your-tool questions find the right document

.env.example

@@ -18,13 +18,20 @@ BOR_LLM_EMBED_MODEL=embed
 BOR_EMBEDDING_DIM=768             # verified 2026-08 via scripts/llm_probe.py
 
 # --- RAG tuning ---
-BOR_TOP_K_CHUNKS=4
 BOR_TOP_N_DOCS=2
-BOR_RELEVANCE_THRESHOLD=0.30      # max cosine similarity required to answer (else honest deflection)
+BOR_RELEVANCE_THRESHOLD=0.62      # answer when best cosine >= this OR an FTS hit; else honest deflection
 BOR_MAX_CONTEXT_CHARS=24000       # cap on total document text sent to the LLM
 BOR_CHUNK_TARGET_CHARS=2000
 BOR_CHUNK_OVERLAP_CHARS=200
 BOR_EMBED_BATCH_SIZE=16
+
+# --- Hybrid retrieval (vector + Postgres FTS, RRF-fused) ---
+BOR_HYBRID_VECTOR_CANDIDATES=100  # cosine list width for the fusion
+BOR_HYBRID_LEXICAL_CANDIDATES=30  # FTS list width for the fusion
+BOR_RRF_K=60                      # Reciprocal Rank Fusion damping constant
+
+# --- Import scope (A9 formats; may only narrow, never widen) ---
+# BOR_IMPORT_EXTENSIONS=md,markdown,txt,yaml,yml,json,py
 # BOR_SUGGESTIONS=["How is my Kubernetes cluster set up?"]   # JSON list of onboarding chips
 
 # --- Debugging (0/1 — 1 enables attach-on-demand debugpy on port 5678) ---