Merge pull request #878 from cbcoutinho/fix/windows-resource-import-877

fix(documents): guard Unix-only resource import for Windows (#877)

nextcloud_mcp_server/app.py

@@ -109,7 +109,6 @@ from nextcloud_mcp_server.config_validators import (
     validate_configuration,
 )
 from nextcloud_mcp_server.context import get_client as get_nextcloud_client
-from nextcloud_mcp_server.document_processors import get_registry
 from nextcloud_mcp_server.http import nextcloud_httpx_client
 from nextcloud_mcp_server.observability import (
     ObservabilityMiddleware,
@@ -159,6 +158,11 @@ def initialize_document_processors():
         logger.info("Document processing disabled")
         return
 
+    # Imported lazily so the API startup path never loads the ingest document
+    # stack (document_processors -> pymupdf -> _isolation) unless document
+    # processing is actually enabled -- see #877 / the API-vs-ingest split.
+    from nextcloud_mcp_server.document_processors import get_registry  # noqa: PLC0415
+
     registry = get_registry()
     registered_count = 0
 

nextcloud_mcp_server/document_processors/_isolation.py

@@ -13,7 +13,7 @@ in its process pool.
 """
 
 import logging
-import resource
+import sys
 from pathlib import Path
 from typing import Any
 
@@ -21,6 +21,15 @@ import anyio
 import anyio.to_process
 from anyio import BrokenWorkerProcess
 
+# ``resource`` is a Unix-only stdlib module -- it does not exist on Windows, and
+# importing it unconditionally crashed Windows startup (#877). The RLIMIT_AS cap
+# it provides is a Linux-pod safety measure, not a correctness requirement, so on
+# platforms without it we fall back to a no-op (``resource is None``).
+if sys.platform == "win32":  # pragma: no cover - win32-only path
+    resource = None
+else:
+    import resource
+
 logger = logging.getLogger(__name__)
 
 # Guard so the address-space limit is applied once per (reused) worker process.
@@ -44,10 +53,18 @@ def _apply_mem_limit(mem_limit_mb: int) -> None:
 
     Applied once per worker process. The hard limit is left untouched (we only
     lower the soft limit), and we never set a soft limit above the hard limit.
+
+    On a platform without the Unix-only ``resource`` module (e.g. Windows, see
+    #877) the cap is skipped -- the worker still runs, just without the
+    address-space limit.
     """
     global _MEM_LIMIT_APPLIED
     if _MEM_LIMIT_APPLIED or mem_limit_mb <= 0:
         return
+    if resource is None:
+        logger.debug("resource module unavailable; skipping RLIMIT_AS cap")
+        _MEM_LIMIT_APPLIED = True
+        return
     target = mem_limit_mb * 1024 * 1024
     soft, hard = resource.getrlimit(resource.RLIMIT_AS)
     soft_target = target if hard == resource.RLIM_INFINITY else min(target, hard)

nextcloud_mcp_server/server/webdav.py

@@ -13,10 +13,6 @@ from nextcloud_mcp_server.server.tag_exclusion import (
     get_excluded_file_paths,
     is_path_excluded,
 )
-from nextcloud_mcp_server.utils.document_parser import (
-    is_parseable_document,
-    parse_document,
-)
 
 logger = logging.getLogger(__name__)
 
@@ -115,6 +111,16 @@ def configure_webdav_tools(mcp: FastMCP):
 
         content, content_type = await client.webdav.read_file(path)
 
+        # Imported lazily so server startup never loads the document-parsing
+        # stack (document_processors -> pymupdf -> _isolation). That stack is an
+        # ingest-layer concern and, before this, broke Windows startup via a
+        # Unix-only ``import resource`` (#877). It is only needed when a file is
+        # actually read and parsed.
+        from nextcloud_mcp_server.utils.document_parser import (  # noqa: PLC0415
+            is_parseable_document,
+            parse_document,
+        )
+
         # Check if this is a parseable document (PDF, DOCX, etc.)
         # is_parseable_document() checks if document processing is enabled
         if is_parseable_document(content_type):

nextcloud_mcp_server/vector/processor.py

@@ -16,7 +16,6 @@ from qdrant_client.models import PointStruct
 from nextcloud_mcp_server.acl_hash import compute_acl_hash
 from nextcloud_mcp_server.client import NextcloudClient
 from nextcloud_mcp_server.config import get_settings
-from nextcloud_mcp_server.document_processors import get_registry
 from nextcloud_mcp_server.embedding import get_bm25_service, get_embedding_service
 from nextcloud_mcp_server.models.deck import DeckCard
 from nextcloud_mcp_server.observability.metrics import (
@@ -707,6 +706,12 @@ async def _index_document(
         ):
             # The registry runs the tiered PDF pipeline (tier-0 classify ->
             # tier-1 fast -> OCR escalation) and records classification metrics.
+            # Imported lazily so module import doesn't pull in the document stack
+            # (document_processors -> _isolation, Unix-only ``resource``; see #877).
+            from nextcloud_mcp_server.document_processors import (  # noqa: PLC0415
+                get_registry,
+            )
+
             registry = get_registry()
 
             try: