feat(rag): steering notes — tune how Brain answers, stored in Postgres and injected into every system prompt

app/models.py

@@ -6,8 +6,10 @@ Data model — see ``.agent/PLAN.md`` §Data Model:
 * ``chunks``    — retrieval units; each chunk points at its parent document
                   via ``document_id``. This is how an embedding maps back to
                   a document path (the "feed the whole document" requirement).
-* ``query_log`` — observability: every question, its retrieval score, the
-                  deflection decision, and latency.
+* ``query_log``     — observability: every question, its retrieval score,
+                      the deflection decision, and latency.
+* ``steering_notes`` — owner tuning notes injected into the system prompt
+                      of every chat turn (phase 15, ``<tuning>`` section).
 """
 from __future__ import annotations
 
@@ -82,3 +84,18 @@ class QueryLog(Base):
     sources: Mapped[str] = mapped_column(Text, default="")  # comma-joined source paths
     latency_ms: Mapped[int] = mapped_column(Integer, default=0)
     created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())
+
+
+class SteeringNote(Base):
+    """One owner tuning instruction (phase 15).
+
+    Notes are read into the system prompt of **every** chat turn as the
+    ``<tuning>`` section (oldest first, char-budgeted — see
+    :func:`app.rag.prompts.build_steering_section`).
+    """
+
+    __tablename__ = "steering_notes"
+
+    id: Mapped[uuid.UUID] = mapped_column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
+    note: Mapped[str] = mapped_column(Text)  # trimmed, 1–2000 chars (API-enforced)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), server_default=func.now())