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

tests/unit/test_chat_gate.py

@@ -47,18 +47,23 @@ def _doc(title: str, content: str) -> Document:
 
 
 def _chunk(
-    doc: Document, score: float, cosine: float | None = None, fts_hit: bool = False
+    doc: Document,
+    score: float,
+    cosine: float | None = None,
+    fts_hit: bool = False,
+    is_summary: bool = False,
 ) -> RetrievedChunk:
     """Fake candidate: *score* is the fused rank score; *cosine* (defaults to
     *score*) is the vector-similarity gate input."""
     return RetrievedChunk(
         chunk_id=uuid.uuid4(),
-        position=0,
+        position=-1 if is_summary else 0,
         content=doc.content[:32],
         score=score,
         document=doc,
         cosine=score if cosine is None else cosine,
         fts_hit=fts_hit,
+        is_summary=is_summary,
     )
 
 
@@ -167,6 +172,70 @@ def test_gate_zero_chunks_deflects_with_fallback_chips() -> None:
     assert 2 <= len(plan.suggestions) <= MAX_SUGGESTIONS
 
 
+# ---------- summary hits (phase 30: summary → full source document) ----------
+
+
+def test_summary_hit_on_selected_top_doc_counts() -> None:
+    """HIGH branch: the top document was hit via its summary chunk ⇒ 1.
+
+    Context assembly is unchanged (A7 revised): the *source* document's
+    full content lands in the prompt, not the summary text alone.
+    """
+    a = _doc("Alpha", "ALPHA_FULL_SOURCE_CONTENT")
+    b = _doc("Beta", "BETA_FULL_SOURCE_CONTENT")
+    chunks = [
+        _chunk(a, 0.90, is_summary=True),  # top doc reached through its summary
+        _chunk(b, 0.50),
+    ]
+    plan = chat_api.plan_turn(chunks, _settings(threshold=0.30))
+    assert plan.deflected is False
+    assert plan.summary_hits == 1
+    # The full source document is what the LLM sees (phase 24 contract).
+    assert "ALPHA_FULL_SOURCE_CONTENT" in plan.system_prompt
+
+
+def test_summary_hit_outside_top_n_selection_not_counted() -> None:
+    """A summary chunk on a document outside the top-N (default 2) selection
+    does not count — only hits that landed in the selected context do."""
+    a = _doc("Alpha", "ALPHA_CONTENT")
+    b = _doc("Beta", "BETA_CONTENT")
+    c = _doc("Gamma", "GAMMA_CONTENT")
+    chunks = [
+        _chunk(a, 0.90),
+        _chunk(b, 0.80),
+        _chunk(c, 0.70, is_summary=True),  # 3rd-ranked doc — not selected
+    ]
+    plan = chat_api.plan_turn(chunks, _settings(threshold=0.30))
+    assert plan.deflected is False
+    assert [d.title for d in plan.docs] == ["Alpha", "Beta"]
+    assert plan.summary_hits == 0
+
+
+def test_low_branch_counts_summary_hit_on_selected_doc() -> None:
+    """LOW (deflected) branch records ``summary_hits`` too: the weak hit's
+    parent is still the selected (weak-hit) document."""
+    a = _doc("Gamma", "GAMMA_DOC_CONTENT")
+    b = _doc("Delta", "DELTA_DOC_CONTENT")
+    chunks = [
+        _chunk(a, 0.05, cosine=0.05, is_summary=True),  # weak cosine, no FTS
+        _chunk(b, 0.03, cosine=0.03),
+    ]
+    plan = chat_api.plan_turn(chunks, _settings(threshold=0.30))
+    assert plan.deflected is True
+    assert plan.summary_hits == 1
+
+
+def test_no_summary_chunks_yields_zero_summary_hits() -> None:
+    """Legacy chunks (``is_summary=false``) keep ``summary_hits == 0``."""
+    a = _doc("Alpha", "ALPHA_CONTENT")
+    b = _doc("Beta", "BETA_CONTENT")
+    plan = chat_api.plan_turn([_chunk(a, 0.90), _chunk(b, 0.40)], _settings(threshold=0.30))
+    assert plan.summary_hits == 0
+    plan_low = chat_api.plan_turn([_chunk(a, 0.05, cosine=0.05)], _settings(threshold=0.30))
+    assert plan_low.deflected is True
+    assert plan_low.summary_hits == 0
+
+
 # ---------- prompt content (LOW vs HIGH) ----------