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

app/rag/retriever.py

@@ -56,6 +56,7 @@ _LEXICAL_SQL = text(
            d.content       AS doc_content,
            d.content_hash  AS content_hash,
            d.indexed_at    AS indexed_at,
+           c.is_summary    AS is_summary,
            ts_rank(c.tsv, to_tsquery('english', :tsquery)) AS rank
     FROM chunks c
     JOIN documents d ON d.id = c.document_id
@@ -75,6 +76,11 @@ class RetrievedChunk:
     * ``cosine`` — vector similarity ``1 − distance`` (the honesty-gate
       input; ``0.0`` for lexical-only hits that have no vector rank).
     * ``fts_hit`` — the chunk matched the question's OR-tsquery.
+    * ``is_summary`` — True for the lite-model summary chunk (phase 30,
+      position −1): its parent *is* the source document, so a summary hit
+      resolves to the full source document through the unchanged
+      chunk→document mapping (A7 revised). Default ``False`` keeps every
+      ordinary content chunk valid.
     """
 
     chunk_id: uuid.UUID
@@ -84,6 +90,7 @@ class RetrievedChunk:
     document: Document
     cosine: float = 0.0
     fts_hit: bool = False
+    is_summary: bool = False
 
 
 def lexical_tsquery(question: str) -> str | None:
@@ -148,7 +155,9 @@ def _vector_candidates(
     """Top-*limit* chunks by pgvector cosine distance (``<=>``).
 
     ``cosine = 1 − distance``. Chunks whose embedding is still NULL
-    (two-phase import in progress) are skipped.
+    (two-phase import in progress) are skipped. Each candidate carries
+    its ``Chunk.is_summary`` flag (phase 30) so a summary hit stays
+    identifiable after fusion.
     """
     distance = Chunk.embedding.cosine_distance(question_embedding)
     rows = db.execute(
@@ -166,6 +175,7 @@ def _vector_candidates(
             score=0.0,  # fused score is filled in by :func:`fuse`
             document=doc,
             cosine=round(1.0 - float(dist), 6),
+            is_summary=chunk.is_summary,
         )
         for chunk, dist, doc in rows
     ]
@@ -205,6 +215,7 @@ def _lexical_candidates(db: Session, question: str, limit: int) -> list[Retrieve
                 document=doc,
                 cosine=0.0,  # no vector rank — lexical-only hit
                 fts_hit=True,
+                is_summary=row.is_summary,
             )
         )
     return out