refactor(usage): close out round-5 nits on PR #871

Non-blocking follow-ups from the merge-ready review:

- semantic.py: bound the doc_types copied into embeddings_queries metadata
  to _USAGE_METADATA_MAX_DOC_TYPES (16). doc_types is caller-supplied with
  no max_length on the tool signature; capping the stored copy keeps one
  JSONB row from ballooning (not a billing/injection risk — CP ignores
  metadata, binds are parameterized).
- migration: note that `metric` is intentionally unconstrained Text and
  that adding a third metric requires keeping the CP-side catalog in sync,
  else the rollup silently ignores the new rows.

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

nextcloud_mcp_server/alembic/versions/20260607_1200_007_add_usage_events.py

@@ -55,7 +55,11 @@ def upgrade() -> None:
             postgresql.TIMESTAMP(timezone=True) if is_pg else sa.TIMESTAMP(),
             nullable=False,
         ),
-        # Catalog metric: 'embeddings_queries' or 'pages_chunks'.
+        # Catalog metric: 'embeddings_queries' or 'pages_chunks'. Deliberately
+        # an unconstrained Text (no CHECK/enum) — the metric catalog lives in
+        # control-plane config, not the app-DB schema. If a third metric is
+        # ever added, the CP-side catalog must learn it too, or its rollup will
+        # silently ignore the new rows; keep the two in sync.
         sa.Column("metric", sa.Text(), nullable=False),
         sa.Column("value", sa.BigInteger(), nullable=False),
         # Rawest unit per request (provider, model, tokens, doc_type, ...).