feat(rag): lite-model document summaries — non-markdown docs summarized at import, summary chunk retrieves and resolves to the full source doc

.env.example

@@ -15,6 +15,7 @@ BOR_LLM_BASE_URL=https://aipi.reeseapps.com/v1
 BOR_LLM_API_KEY=                  # falls back to $AIPI_KEY, then "not-needed"
 BOR_LLM_CHAT_MODEL=turbo
 BOR_LLM_EMBED_MODEL=embed
+BOR_LLM_SUMMARY_MODEL=lite          # one-shot completions: document summaries (phase 30), KB overview (phase 31)
 BOR_EMBEDDING_DIM=768             # verified 2026-08 via scripts/llm_probe.py
 BOR_STREAM_THINKING=1             # stream the model's thinking as `thinking` SSE events (0 to suppress)
 
@@ -23,6 +24,7 @@ BOR_TOP_N_DOCS=2
 BOR_RELEVANCE_THRESHOLD=0.62      # answer when best cosine >= this OR an FTS hit; else honest deflection
 BOR_MAX_OUTPUT_TOKENS=32768       # max answer length in tokens (answers must not be cut off)
 BOR_STEERING_MAX_CHARS=8000       # char budget for the <tuning> (steering notes) prompt section
+BOR_SUMMARY_MAX_CHARS=12000       # cap on document content sent to the lite summary model (phase 30)
 BOR_CHUNK_TARGET_CHARS=2000
 BOR_CHUNK_OVERLAP_CHARS=200
 BOR_EMBED_BATCH_SIZE=16