fix(ocr): wire batch settings into _field_map + review nits

Round 1 review (PR #910):
- BLOCKING: add document_ocr_mode / _batch_poll_seconds / _batch_max_wait_seconds
  to config._field_map — without it dynaconf silently ignored the env vars and
  DOCUMENT_OCR_MODE=batch could never be enabled in production. Add a regression
  test asserting the three round-trip from env.
- migration 008: give batch_ocr_jobs a composite PRIMARY KEY on
  (user_id, doc_id, doc_type, etag) instead of a bare UniqueConstraint (N1).
- OcrProcessor: use a dedicated _batch_client_lock instead of sharing the sync
  backend lock (N3).
- tests: use https:// gateway URLs in the new fixtures to clear SonarCloud's
  "insecure http" security hotspots (all 14 were test-only http://gw literals).

1653 unit tests pass; ruff + ty green.

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

nextcloud_mcp_server/alembic/versions/20260615_1200_008_add_batch_ocr_jobs.py

@@ -36,7 +36,11 @@ def upgrade() -> None:
         # Document identity (the same keys the OCR tier receives via the
         # processor ``options``). ``etag`` is the content-version key: a changed
         # document (new etag) is a new job, so a stale row never serves results
-        # for the wrong content.
+        # for the wrong content. The four-column natural key IS the primary key:
+        # one in-flight job per (document, content version), and the PK doubles as
+        # the unique index ``insert_pending``'s ON CONFLICT target relies on. A
+        # resubmit for a new etag inserts a new row; the superseded row is swept on
+        # resubmit (delete_stale_for_doc).
         sa.Column("user_id", sa.Text(), nullable=False),
         sa.Column("doc_id", sa.Text(), nullable=False),
         sa.Column("doc_type", sa.Text(), nullable=False),
@@ -51,14 +55,8 @@ def upgrade() -> None:
         # (DOCUMENT_OCR_BATCH_MAX_WAIT_SECONDS).
         sa.Column("submitted_at", sa.BigInteger(), nullable=False),
         sa.Column("updated_at", sa.BigInteger(), nullable=False),
-        # One in-flight job per (document, content version). A resubmit for a new
-        # etag inserts a new row; the superseded row is swept on resubmit.
-        sa.UniqueConstraint(
-            "user_id",
-            "doc_id",
-            "doc_type",
-            "etag",
-            name="uq_batch_ocr_jobs_doc",
+        sa.PrimaryKeyConstraint(
+            "user_id", "doc_id", "doc_type", "etag", name="pk_batch_ocr_jobs"
         ),
     )
 

nextcloud_mcp_server/config.py

@@ -1521,6 +1521,9 @@ def get_settings() -> Settings:
         "document_ocr_provider": "DOCUMENT_OCR_PROVIDER",
         "document_ocr_model": "DOCUMENT_OCR_MODEL",
         "document_ocr_timeout_seconds": "DOCUMENT_OCR_TIMEOUT_SECONDS",
+        "document_ocr_mode": "DOCUMENT_OCR_MODE",
+        "document_ocr_batch_poll_seconds": "DOCUMENT_OCR_BATCH_POLL_SECONDS",
+        "document_ocr_batch_max_wait_seconds": "DOCUMENT_OCR_BATCH_MAX_WAIT_SECONDS",
         "document_ocr_min_text_quality": "DOCUMENT_OCR_MIN_TEXT_QUALITY",
         "document_ocr_page_fraction": "DOCUMENT_OCR_PAGE_FRACTION",
         "document_ocr_min_page_chars": "DOCUMENT_OCR_MIN_PAGE_CHARS",

nextcloud_mcp_server/document_processors/ocr.py

@@ -272,6 +272,7 @@ class OcrProcessor(DocumentProcessor):
         # using sync" warning to once per pod.
         self._batch_client_resolved = False
         self._batch_client: Any = None
+        self._batch_client_lock: anyio.Lock | None = None
         self._batch_fallback_warned = False
 
     @property
@@ -377,9 +378,9 @@ class OcrProcessor(DocumentProcessor):
         provider=mistral / no gateway). Resolved once under the backend lock so the
         token provider's M2M cache survives across documents."""
         if not self._batch_client_resolved:
-            if self._backend_lock is None:
-                self._backend_lock = anyio.Lock()
-            async with self._backend_lock:
+            if self._batch_client_lock is None:
+                self._batch_client_lock = anyio.Lock()
+            async with self._batch_client_lock:
                 if not self._batch_client_resolved:  # double-checked
                     self._batch_client = build_gateway_batch_client(get_settings())
                     self._batch_client_resolved = True