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

app/config.py

@@ -41,6 +41,11 @@ class Settings(BaseSettings):
     llm_api_key: str = ""
     llm_chat_model: str = "turbo"
     llm_embed_model: str = "embed"
+    #: One-shot (non-streaming) completion model (A5 extended, phase 30):
+    #: document summaries at import time and the KB overview (phase 31).
+    #: Served by the same OpenAI-compatible endpoint — no new model
+    #: management. Called via ``LLMClient.chat()``.
+    llm_summary_model: str = "lite"
     #: Operator kill-switch for the ``thinking`` SSE events (phase 17,
     #: ``BOR_STREAM_THINKING``; ``0``/``false`` → off). When off, thinking
     #: pieces are still counted for the per-turn log line but never
@@ -66,6 +71,11 @@ class Settings(BaseSettings):
     #: (phase 15, steering notes). The newest-fitting notes are kept and the
     #: overflow is replaced by the ``[…truncated…]`` marker.
     steering_max_chars: int = 8_000
+    #: Cap on the document content sent to the ``lite`` summary model in one
+    #: call (phase 30, ``BOR_SUMMARY_MAX_CHARS``). Overflow is cut at the cap
+    #: and the shared ``[…truncated…]`` marker is appended (see
+    #: ``app.rag.summarizer``).
+    summary_max_chars: int = 12_000
 
     # --- Hybrid retrieval (A7, revised 2026-08-21) ---
     # cosine top-N ∪ Postgres FTS top-N, fused with Reciprocal Rank Fusion