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

app/api/chat.py

@@ -28,6 +28,14 @@ Steering (phase 15): the owner's stored tuning notes are loaded per turn
 (oldest first) and injected into the system prompt as a ``<tuning>``
 section — both the HIGH and the LOW prompt carry it. The per-turn log
 line records ``tuning=N`` (the number of injected notes).
+
+Summaries (phase 30): a lite-model summary chunk's parent *is* the
+source document, so a summary hit resolves to the full source document
+through the unchanged chunk→document mapping (A7 revised) — context
+assembly is untouched. ``TurnPlan.summary_hits`` counts the hit chunks
+with ``is_summary`` whose parent document landed in the selected
+top-N context, and the per-turn log line records ``summary_hits=N``
+after ``fts_hits`` (PLAN §9 line extension).
 """
 from __future__ import annotations
 
@@ -96,6 +104,9 @@ class TurnPlan:
     docs: list[Document]  # cited sources (weak hits when deflected)
     suggestions: list[str]  # "Maybe try" chips (deflected turns only)
     tuning_count: int = 0  # steering notes injected into the system prompt
+    #: Hit chunks with ``is_summary`` whose parent document made it into
+    #: *docs* (phase 30; per-turn log line ``summary_hits=N``).
+    summary_hits: int = 0
 
 
 def plan_turn(
@@ -121,12 +132,18 @@ def plan_turn(
     *notes* are the owner's steering notes (phase 15, oldest first):
     when non-empty, both the HIGH and the LOW prompt carry the
     ``<tuning>`` section; with no notes the prompts are unchanged.
+
+    ``summary_hits`` (phase 30) counts the hit chunks with
+    ``is_summary`` whose parent document is among the selected
+    top-N documents — both the HIGH and the LOW branch record it.
     """
     steering = list(notes or [])
     best_cosine = max((c.cosine for c in chunks), default=0.0)
     fts_hits = sum(1 for c in chunks if c.fts_hit)
+    docs = select_documents(chunks, n=settings.top_n_docs)
+    selected_ids = {d.id for d in docs}
+    summary_hits = sum(1 for c in chunks if c.is_summary and c.document.id in selected_ids)
     if best_cosine >= settings.relevance_threshold or fts_hits > 0:
-        docs = select_documents(chunks, n=settings.top_n_docs)
         return TurnPlan(
             best_cosine,
             fts_hits,
@@ -135,6 +152,7 @@ def plan_turn(
             docs,
             [],
             len(steering),
+            summary_hits,
         )
     titles = weak_hit_titles(chunks)
     return TurnPlan(
@@ -142,9 +160,10 @@ def plan_turn(
         fts_hits,
         True,
         build_deflect_prompt(titles, notes=steering),
-        select_documents(chunks, n=settings.top_n_docs),
+        docs,
         derive_suggestions(titles, settings.suggestions),
         len(steering),
+        summary_hits,
     )
 
 
@@ -264,12 +283,13 @@ async def chat(
             logger.exception("chat: failed to write query_log question=%r", request.message)
 
         logger.info(
-            "question=%r embed_ms=%d top_score=%.3f fts_hits=%d tuning=%d threshold=%.2f "
-            "deflected=%s sources=%r thinking_chars=%d total_ms=%d",
+            "question=%r embed_ms=%d top_score=%.3f fts_hits=%d summary_hits=%d tuning=%d "
+            "threshold=%.2f deflected=%s sources=%r thinking_chars=%d total_ms=%d",
             request.message,
             embed_ms,
             plan.top_score,
             plan.fts_hits,
+            plan.summary_hits,
             plan.tuning_count,
             settings.relevance_threshold,
             plan.deflected,