admin/mcp-nextcloud
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(vector): URL-encode DAV paths and unwrap TaskGroup exceptions

Browse Source 
Two ingest-robustness fixes from card 309 (OHR-Bench smoke-test triage).

WebDAV paths flowed through the client already URL-decoded (unquote on the
PROPFIND/REPORT <d:href>, or raw MCP-tool input), so a '#' reached httpx as a
URL fragment and silently truncated the request -> spurious 404 on otherwise
valid files (e.g. law filenames with '#', commas, double/trailing spaces).
Route every caller-path builder through a new _webdav_path helper that
percent-encodes the path once (preserving separators); the MOVE/COPY
Destination header is encoded too.

Vector-sync runs inside anyio task groups, so a child-task failure surfaced as
a BaseExceptionGroup whose str() is the useless "unhandled errors in a
TaskGroup (N sub-exception)" -- hiding the real ConnectError operators need.
Add format_exception_group to flatten the group to its leaf exceptions and use
it at the broad catch/log sites in processor.py and oauth_sync.py.

Refs: Deck board 12 card 309 (AC #4 filename handling, AC #2 observability).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2026-06-11 04:59:53 +02:00
co-authored by Claude Opus 4.8
parent 457c115ef4
commit 0388735593
6 changed files with 216 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nextcloud_mcp_server/client/webdav.py
+45 -22
View File
@@ -5,7 +5,7 @@ import mimetypes
import xml.etree.ElementTree as ET
from email.utils import parsedate_to_datetime
from typing import Any, Dict, List, Optional, Tuple
from urllib.parse import unquote
from urllib.parse import quote, unquote
from xml.sax.saxutils import escape as xml_escape
from httpx import HTTPStatusError
@@ -26,11 +26,37 @@ WEBDAV_SEARCH_PAGE_SIZE = 500
WEBDAV_SEARCH_MAX_RESULTS = 50000
def _encode_dav_path(path: str) -> str:
"""Percent-encode a *decoded* DAV path for use in a request URL/header.
Paths flow through this client already URL-decoded (e.g. ``unquote`` on the
``<d:href>`` of a PROPFIND/REPORT response, or raw user-supplied paths from
MCP tools), so characters like ``#``, ``,`` and spaces reach httpx verbatim.
An unencoded ``#`` is parsed as a URL fragment and silently truncates the
request path → spurious 404 on otherwise-valid files (issue: OHR-Bench
ingest, card 309). ``quote`` with ``safe="/"`` encodes the unsafe characters
while preserving the path separators; ASCII-only paths are unchanged.
Encode exactly once: the input is decoded, so a literal ``%`` becomes
``%25`` (correct) rather than being mistaken for an existing escape.
"""
return quote(path, safe="/")
class WebDAVClient(BaseNextcloudClient):
"""Client for Nextcloud WebDAV operations."""
app_name = "webdav"
def _webdav_path(self, path: str) -> str:
"""Build the request path for ``path`` under the user's DAV root.
Percent-encodes the caller-supplied portion (see ``_encode_dav_path``)
so names with ``#``, commas, or spaces don't truncate/404; the base
``/remote.php/dav/files/<user>`` segment is left as-is.
"""
return f"{self._get_webdav_base_path()}/{_encode_dav_path(path.lstrip('/'))}"
async def delete_resource(self, path: str) -> Dict[str, Any]:
"""Delete a resource (file or directory) via WebDAV DELETE."""
# Ensure path ends with a slash if it's a directory
@@ -39,7 +65,7 @@ class WebDAVClient(BaseNextcloudClient):
else:
path_with_slash = path
webdav_path = f"{self._get_webdav_base_path()}/{path_with_slash.lstrip('/')}"
webdav_path = self._webdav_path(path_with_slash)
logger.debug("Deleting WebDAV resource: %s", webdav_path)
headers = {"OCS-APIRequest": "true"}
@@ -124,15 +150,15 @@ class WebDAVClient(BaseNextcloudClient):
mime_type: Optional[str] = None,
) -> Dict[str, Any]:
"""Add/Update an attachment to a note via WebDAV PUT."""
# Construct paths based on provided category
webdav_base = self._get_webdav_base_path()
# Construct paths based on provided category. Encode via _webdav_path so
# categories/filenames with '#', commas or spaces don't truncate/404.
category_path_part = f"{category}/" if category else ""
attachment_dir_segment = f".attachments.{note_id}"
parent_dir_webdav_rel_path = (
f"Notes/{category_path_part}{attachment_dir_segment}"
)
parent_dir_path = f"{webdav_base}/{parent_dir_webdav_rel_path}"
attachment_path = f"{parent_dir_path}/{filename}"
parent_dir_path = self._webdav_path(parent_dir_webdav_rel_path)
attachment_path = self._webdav_path(f"{parent_dir_webdav_rel_path}/{filename}")
logger.debug("Uploading attachment '%s' for note %s", filename, note_id)
@@ -144,7 +170,7 @@ class WebDAVClient(BaseNextcloudClient):
headers = {"Content-Type": mime_type, "OCS-APIRequest": "true"}
try:
# First check if we can access WebDAV at all
notes_dir_path = f"{webdav_base}/Notes"
notes_dir_path = self._webdav_path("Notes")
propfind_headers = {"Depth": "0", "OCS-APIRequest": "true"}
notes_dir_response = await self._make_request(
"PROPFIND", notes_dir_path, headers=propfind_headers
@@ -209,10 +235,11 @@ class WebDAVClient(BaseNextcloudClient):
self, note_id: int, filename: str, category: Optional[str] = None
) -> Tuple[bytes, str]:
"""Fetch a specific attachment from a note via WebDAV GET."""
webdav_base = self._get_webdav_base_path()
category_path_part = f"{category}/" if category else ""
attachment_dir_segment = f".attachments.{note_id}"
attachment_path = f"{webdav_base}/Notes/{category_path_part}{attachment_dir_segment}/{filename}"
attachment_path = self._webdav_path(
f"Notes/{category_path_part}{attachment_dir_segment}/{filename}"
)
logger.debug("Fetching attachment '%s' for note %s", filename, note_id)
@@ -252,7 +279,7 @@ class WebDAVClient(BaseNextcloudClient):
async def list_directory(self, path: str = "") -> List[Dict[str, Any]]:
"""List files and directories in the specified path via WebDAV PROPFIND."""
webdav_path = f"{self._get_webdav_base_path()}/{path.lstrip('/')}"
webdav_path = self._webdav_path(path)
if not webdav_path.endswith("/"):
webdav_path += "/"
@@ -352,7 +379,7 @@ class WebDAVClient(BaseNextcloudClient):
async def read_file(self, path: str) -> Tuple[bytes, str]:
"""Read a file's content via WebDAV GET."""
webdav_path = f"{self._get_webdav_base_path()}/{path.lstrip('/')}"
webdav_path = self._webdav_path(path)
logger.debug("Reading file: %s", path)
@@ -379,7 +406,7 @@ class WebDAVClient(BaseNextcloudClient):
self, path: str, content: bytes, content_type: Optional[str] = None
) -> Dict[str, Any]:
"""Write content to a file via WebDAV PUT."""
webdav_path = f"{self._get_webdav_base_path()}/{path.lstrip('/')}"
webdav_path = self._webdav_path(path)
logger.debug("Writing file: %s", path)
@@ -410,7 +437,7 @@ class WebDAVClient(BaseNextcloudClient):
self, path: str, recursive: bool = False
) -> Dict[str, Any]:
"""Create a directory via WebDAV MKCOL."""
webdav_path = f"{self._get_webdav_base_path()}/{path.lstrip('/')}"
webdav_path = self._webdav_path(path)
if not webdav_path.endswith("/"):
webdav_path += "/"
@@ -468,10 +495,8 @@ class WebDAVClient(BaseNextcloudClient):
Returns:
Dict with status_code and optional message
"""
source_webdav_path = f"{self._get_webdav_base_path()}/{source_path.lstrip('/')}"
destination_webdav_path = (
f"{self._get_webdav_base_path()}/{destination_path.lstrip('/')}"
)
source_webdav_path = self._webdav_path(source_path)
destination_webdav_path = self._webdav_path(destination_path)
# Ensure paths have consistent trailing slashes for directories
if source_path.endswith("/") and not destination_path.endswith("/"):
@@ -552,10 +577,8 @@ class WebDAVClient(BaseNextcloudClient):
Returns:
Dict with status_code and optional message
"""
source_webdav_path = f"{self._get_webdav_base_path()}/{source_path.lstrip('/')}"
destination_webdav_path = (
f"{self._get_webdav_base_path()}/{destination_path.lstrip('/')}"
)
source_webdav_path = self._webdav_path(source_path)
destination_webdav_path = self._webdav_path(destination_path)
# Ensure paths have consistent trailing slashes for directories
if source_path.endswith("/") and not destination_path.endswith("/"):
@@ -1678,7 +1701,7 @@ class WebDAVClient(BaseNextcloudClient):
distinguish a definitive absence (HTTP 404) from a
brittle response (None).
"""
webdav_path = f"{self._get_webdav_base_path()}/{path.lstrip('/')}"
webdav_path = self._webdav_path(path)
propfind_body = """<?xml version="1.0"?>
<d:propfind xmlns:d="DAV:" xmlns:oc="http://owncloud.org/ns">