feat(rag): feed whole matched documents to the LLM — no context truncation (A7 revised)

app/rag/retriever.py

@@ -10,10 +10,12 @@
   fused score ranks; :meth:`select_documents` and :func:`weak_hit_titles`
   keep working off ``score``.
 
-The product requirement is unchanged (LOCKED A7): the LLM receives the
-**entire relevant document**, not just the chunk — chunk hits map back to
-their parents, dedupe, rank by best fused score, and the combined context
-is capped at ``BOR_MAX_CONTEXT_CHARS``.
+The product requirement (LOCKED A7, revised 2026-08-24): the LLM receives
+the **entire relevant document**, not just the chunk — chunk hits map back
+to their parents, dedupe, rank by best fused score, and the full text of
+the top-N documents is always fed through, never truncated. If a future KB
+ever makes the prompt too large for the model, the ``LLMError`` → SSE
+``error`` path surfaces it loudly — no silent partial context.
 
 Deterministic tie-break for equal fused scores:
 ``(−fused, −cosine, document.path, chunk.position)``.
@@ -31,7 +33,9 @@ from sqlalchemy.orm import Session
 from app.config import get_settings
 from app.models import Chunk, Document
 
-#: Marker appended when the context budget is exceeded (PLAN §6).
+#: Shared overflow marker — now used by the steering (<tuning>) section
+#: only (phase 15; imported by ``app.rag.prompts``). The document context
+#: path never truncates (A7 revised, owner permission 2026-08-24).
 TRUNCATION_MARKER = "[…truncated…]"
 
 #: Alphanumeric tokens of a question (``to_tsquery`` input, OR-joined).
@@ -254,19 +258,17 @@ def weak_hit_titles(chunks: Sequence[RetrievedChunk]) -> list[str]:
 def select_documents(
     chunks: Sequence[RetrievedChunk],
     n: int | None = None,
-    max_chars: int | None = None,
 ) -> list[Document]:
     """Map chunk hits to distinct parent documents, ranked by best fused score.
 
     At most *n* documents are returned (default ``BOR_TOP_N_DOCS``). The
-    returned rows carry the full document content; if the combined content
-    would exceed *max_chars* (default ``BOR_MAX_CONTEXT_CHARS``), the
-    lowest-ranked overflowing document is truncated in place with the
-    ``[…truncated…]`` marker so the assembled context never exceeds the
-    budget (PLAN §6).
+    returned rows carry the full document content, byte-identical — a
+    matched parent document is **never truncated** (A7 revised, owner
+    permission 2026-08-24). There is deliberately no context budget: an
+    oversized prompt must fail loudly through the ``LLMError`` → SSE
+    ``error`` path, never arrive as silent partial context.
     """
     top_n = n if n is not None else get_settings().top_n_docs
-    budget = max_chars if max_chars is not None else get_settings().max_context_chars
 
     docs: list[Document] = []
     seen: set[uuid.UUID] = set()
@@ -275,14 +277,4 @@ def select_documents(
             continue
         seen.add(rc.document.id)
         docs.append(rc.document)
-    docs = docs[:top_n]
-
-    remaining = budget
-    for doc in docs:
-        if len(doc.content) <= remaining:
-            remaining -= len(doc.content)
-        else:
-            keep = max(0, remaining - len(TRUNCATION_MARKER))
-            doc.content = doc.content[:keep] + TRUNCATION_MARKER
-            remaining = 0
-    return docs
+    return docs[:top_n]