feat(principles): canonical_statement synthesis service + throttled backfill (Phase E groundwork, #152)

Grounded (INV-AH) multi-instance synthesis with drift guard + chair gate
(pending_review, G10). Single path used by backfill, MCP tool, nightly drain.
HELD from production run pending the principles-redesign (rename+cull, #152).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/services/db.py

@@ -6147,6 +6147,71 @@ async def update_canonical_statement(
     return result.split()[-1] != "0"
 
 
+async def fetch_canonical_synthesis_input(canonical_id: "UUID") -> "dict | None":
+    """Fetch everything the canonical-synthesis pass needs for one principle (V41 Phase 4).
+
+    Unlike :func:`get_canonical_halacha` (UI-facing) this returns the canonical's own
+    ``embedding`` (as a python list, for the drift guard) AND each instance's full text
+    fields (``rule_statement`` + ``supporting_quote`` + ``reasoning_summary``) — the
+    grounding evidence the LLM rewrites from (INV-AH). Returns None if not found.
+    """
+    pool = await get_pool()
+    row = await pool.fetchrow(
+        "SELECT id::text, canonical_statement, rule_type, practice_areas, "
+        "       subject_tags, review_status, instance_count, embedding "
+        "FROM canonical_halachot WHERE id=$1",
+        canonical_id,
+    )
+    if not row:
+        return None
+    instances = await pool.fetch(
+        "SELECT h.instance_type, h.treatment, h.rule_statement, "
+        "       h.supporting_quote, h.reasoning_summary, "
+        "       cl.case_number, cl.case_name "
+        "FROM halachot h JOIN case_law cl ON cl.id = h.case_law_id "
+        "WHERE h.canonical_id=$1 "
+        "ORDER BY (h.instance_type='original') DESC, cl.case_number",
+        canonical_id,
+    )
+    emb = row["embedding"]
+    out = dict(row)
+    out["embedding"] = list(emb) if emb is not None else None
+    out["instances"] = [dict(i) for i in instances]
+    return out
+
+
+async def apply_canonical_synthesis(
+    canonical_id: "UUID",
+    canonical_statement: str,
+    embedding: "list[float] | None" = None,
+    review_status: str = "pending_review",
+) -> bool:
+    """Atomically commit a synthesis outcome for one canonical (V41 Phase 4).
+
+    Always advances ``review_status`` (default → ``pending_review`` for the chair
+    gate, G10/INV-LRN1) and writes ``canonical_statement``. ``embedding`` is updated
+    only when provided (None = leave as-is) so the keep-original path on a
+    drift-rejected/abstained synthesis doesn't need to re-embed. Returns True if the
+    row existed.
+    """
+    pool = await get_pool()
+    if embedding is None:
+        result = await pool.execute(
+            "UPDATE canonical_halachot "
+            "SET canonical_statement=$2, review_status=$3, updated_at=now() "
+            "WHERE id=$1",
+            canonical_id, canonical_statement, review_status,
+        )
+    else:
+        result = await pool.execute(
+            "UPDATE canonical_halachot "
+            "SET canonical_statement=$2, embedding=$3, review_status=$4, updated_at=now() "
+            "WHERE id=$1",
+            canonical_id, canonical_statement, embedding, review_status,
+        )
+    return result.split()[-1] != "0"
+
+
 async def list_canonical_instances(canonical_id: "UUID") -> list[dict]:
     """List all halachot (instances) sharing a canonical_id — used by the UI accordion."""
     pool = await get_pool()