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

refactor: convert f-string logging to lazy %-style format (G004)

Browse Source 
Sweep all 1676 G004 violations across 112 files, converting
`logger.<level>(f"…{x}…")` to `logger.<level>("…%s…", x)`.

Why: ruff rule G004 was added to pyproject.toml to enforce lazy
%-style logging — defers formatting until the log level is enabled
and lets structured log tooling match the unformatted template.

Conversion preserves rendered output byte-for-byte:
- `{x}` → `%s` + `x`
- `{x!r}` / `{x!s}` / `{x!a}` → `%r` / `%s` / `%a`
- Format specs (`{x:.2f}`, `{x:>10}`) → `%s` + `format(x, 'spec')`
  (printf-style specs aren't 1:1 with Python format specs, so we
  delegate to `format()` to keep identical output)
- Literal `%` → `%%`
- Concatenated f-strings (`f"a {x} " "b"`) flattened
- Trailing kwargs (`exc_info=True`) preserved

Verified:
- `uv run ruff check --select G004` → 0 violations
- `uv run ty check -- nextcloud_mcp_server` → passes
- `uv run pytest tests/unit/` → 1010 passed

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2026-05-13 01:12:17 +02:00
co-authored by Claude Opus 4.7
parent a4e6125d28
commit 665cb9b1eb
112 changed files with 2534 additions and 1859 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nextcloud_mcp_server/vector/document_chunker.py
+4 -2
View File
@@ -91,7 +91,9 @@ class DocumentChunker:
]
logger.debug(
f"Chunked document into {len(chunks)} chunks "
f"(chunk_size={self.chunk_size}, overlap={self.overlap})"
"Chunked document into %s chunks (chunk_size=%s, overlap=%s)",
len(chunks),
self.chunk_size,
self.overlap,
)
return chunks
nextcloud_mcp_server/vector/html_processor.py
+1 -1
View File
@@ -42,7 +42,7 @@ def html_to_markdown(html_content: str | None) -> str:
)
return markdown.strip()
except Exception as e:
logger.warning(f"Failed to convert HTML to Markdown: {e}")
logger.warning("Failed to convert HTML to Markdown: %s", e)
# Fallback: strip all HTML tags as a last resort
text = re.sub(r"<[^>]+>", " ", html_content)
nextcloud_mcp_server/vector/oauth_sync.py
+78 -38
View File
@@ -104,7 +104,7 @@ async def get_user_client_basic_auth(
f"User must configure background sync in Astrolabe personal settings."
)
logger.info(f"Using app password for background sync: {user_id}")
logger.info("Using app password for background sync: %s", user_id)
return NextcloudClient(
base_url=nextcloud_host,
username=user_id,
@@ -141,7 +141,7 @@ async def get_user_client_oauth(
f"User must complete the OAuth provisioning flow."
)
logger.info(f"Using OAuth refresh token for background sync: {user_id}")
logger.info("Using OAuth refresh token for background sync: %s", user_id)
return NextcloudClient.from_token(
base_url=nextcloud_host,
token=token,
@@ -208,7 +208,7 @@ async def user_scanner_task(
task_status: Status object for signaling task readiness
"""
mode_label = "BasicAuth" if use_basic_auth else "OAuth"
logger.info(f"[{mode_label}] Scanner started for user: {user_id}")
logger.info("[%s] Scanner started for user: %s", mode_label, user_id)
settings = get_settings()
max_consecutive_errors = 5
@@ -221,12 +221,14 @@ async def user_scanner_task(
)
try:
await nc_client.capabilities() # Lightweight OCS call to validate creds
logger.info(f"[{mode_label}] Credentials validated for {user_id}")
logger.info("[%s] Credentials validated for %s", mode_label, user_id)
except HTTPStatusError as e:
if e.response.status_code in (401, 403):
logger.warning(
f"[{mode_label}] Credential validation failed for {user_id} "
f"(HTTP {e.response.status_code}), not starting scan loop"
"[%s] Credential validation failed for %s (HTTP %s), not starting scan loop",
mode_label,
user_id,
e.response.status_code,
)
return
raise
@@ -234,13 +236,15 @@ async def user_scanner_task(
await nc_client.close()
except NotProvisionedError:
logger.warning(
f"[{mode_label}] User {user_id} not provisioned, not starting scan loop"
"[%s] User %s not provisioned, not starting scan loop", mode_label, user_id
)
return
except Exception as e:
logger.warning(
f"[{mode_label}] Pre-validation failed for {user_id}: {e}. "
f"Proceeding to scan loop (has its own error handling)."
"[%s] Pre-validation failed for %s: %s. Proceeding to scan loop (has its own error handling).",
mode_label,
user_id,
e,
)
consecutive_errors = 0
@@ -264,7 +268,9 @@ async def user_scanner_task(
except NotProvisionedError:
logger.warning(
f"[{mode_label}] User {user_id} no longer provisioned, stopping scanner"
"[%s] User %s no longer provisioned, stopping scanner",
mode_label,
user_id,
)
break
@@ -272,16 +278,19 @@ async def user_scanner_task(
status_code = e.response.status_code
if status_code in (401, 403):
logger.warning(
f"[{mode_label}] Scanner auth failed for {user_id} "
f"(HTTP {status_code}), stopping scanner. "
f"User may need to re-provision credentials."
"[%s] Scanner auth failed for %s (HTTP %s), stopping scanner. User may need to re-provision credentials.",
mode_label,
user_id,
status_code,
)
break
elif status_code == 429:
retry_after = min(int(e.response.headers.get("Retry-After", "60")), 300)
logger.warning(
f"[{mode_label}] Scanner rate-limited for {user_id}, "
f"backing off {retry_after}s"
"[%s] Scanner rate-limited for %s, backing off %ss",
mode_label,
user_id,
retry_after,
)
try:
with anyio.move_on_after(retry_after):
@@ -294,16 +303,24 @@ async def user_scanner_task(
else:
consecutive_errors += 1
logger.error(
f"[{mode_label}] Scanner HTTP error for {user_id}: {e} "
f"({consecutive_errors}/{max_consecutive_errors})",
"[%s] Scanner HTTP error for %s: %s (%s/%s)",
mode_label,
user_id,
e,
consecutive_errors,
max_consecutive_errors,
exc_info=True,
)
except Exception as e:
consecutive_errors += 1
logger.error(
f"[{mode_label}] Scanner error for {user_id}: {e} "
f"({consecutive_errors}/{max_consecutive_errors})",
"[%s] Scanner error for %s: %s (%s/%s)",
mode_label,
user_id,
e,
consecutive_errors,
max_consecutive_errors,
exc_info=True,
)
@@ -313,8 +330,10 @@ async def user_scanner_task(
if consecutive_errors >= max_consecutive_errors:
logger.error(
f"[{mode_label}] Scanner for {user_id} hit {max_consecutive_errors} "
f"consecutive errors, stopping scanner"
"[%s] Scanner for %s hit %s consecutive errors, stopping scanner",
mode_label,
user_id,
max_consecutive_errors,
)
break
@@ -325,7 +344,7 @@ async def user_scanner_task(
except anyio.get_cancelled_exc_class():
break
logger.info(f"[{mode_label}] Scanner stopped for user: {user_id}")
logger.info("[%s] Scanner stopped for user: %s", mode_label, user_id)
async def multi_user_processor_task(
@@ -352,7 +371,7 @@ async def multi_user_processor_task(
task_status: Status object for signaling task readiness
"""
mode_label = "BasicAuth" if use_basic_auth else "OAuth"
logger.info(f"[{mode_label}] Processor {worker_id} started")
logger.info("[%s] Processor %s started", mode_label, worker_id)
task_status.started()
while not shutdown_event.is_set():
@@ -378,34 +397,47 @@ async def multi_user_processor_task(
continue
except anyio.EndOfStream:
logger.info(f"[{mode_label}] Processor {worker_id}: Stream closed, exiting")
logger.info(
"[%s] Processor %s: Stream closed, exiting", mode_label, worker_id
)
break
except NotProvisionedError:
if doc_task:
logger.warning(
f"[{mode_label}] User {doc_task.user_id} not provisioned, "
f"skipping {doc_task.doc_type}_{doc_task.doc_id}"
"[%s] User %s not provisioned, skipping %s_%s",
mode_label,
doc_task.user_id,
doc_task.doc_type,
doc_task.doc_id,
)
continue
except Exception as e:
if doc_task:
logger.error(
f"[{mode_label}] Processor {worker_id} error processing "
f"{doc_task.doc_type}_{doc_task.doc_id}: {e}",
"[%s] Processor %s error processing %s_%s: %s",
mode_label,
worker_id,
doc_task.doc_type,
doc_task.doc_id,
e,
exc_info=True,
)
else:
logger.error(
f"[{mode_label}] Processor {worker_id} error: {e}", exc_info=True
"[%s] Processor %s error: %s",
mode_label,
worker_id,
e,
exc_info=True,
)
finally:
if nc_client:
await nc_client.close()
logger.info(f"[{mode_label}] Processor {worker_id} stopped")
logger.info("[%s] Processor %s stopped", mode_label, worker_id)
# Backward compatibility alias
@@ -482,7 +514,7 @@ async def user_manager_task(
mode_label = "BasicAuth" if use_basic_auth else "OAuth"
logger.info(
f"[{mode_label}] User manager started (poll interval: {poll_interval}s)"
"[%s] User manager started (poll interval: %ss)", mode_label, poll_interval
)
task_status.started()
@@ -503,7 +535,9 @@ async def user_manager_task(
new_users = provisioned_users - active_users
for user_id in new_users:
logger.info(
f"[{mode_label}] Starting scanner for newly provisioned user: {user_id}"
"[%s] Starting scanner for newly provisioned user: %s",
mode_label,
user_id,
)
cancel_scope = anyio.CancelScope()
user_states[user_id] = UserSyncState(
@@ -529,7 +563,7 @@ async def user_manager_task(
revoked_users = active_users - provisioned_users
for user_id in revoked_users:
logger.info(
f"[{mode_label}] Stopping scanner for revoked user: {user_id}"
"[%s] Stopping scanner for revoked user: %s", mode_label, user_id
)
state = user_states.get(user_id)
if state:
@@ -537,12 +571,16 @@ async def user_manager_task(
# Note: state will be removed by _run_user_scanner_with_scope on exit
if new_users:
logger.info(f"[{mode_label}] Started {len(new_users)} new scanner(s)")
logger.info(
"[%s] Started %s new scanner(s)", mode_label, len(new_users)
)
if revoked_users:
logger.info(f"[{mode_label}] Stopped {len(revoked_users)} scanner(s)")
logger.info(
"[%s] Stopped %s scanner(s)", mode_label, len(revoked_users)
)
except Exception as e:
logger.error(f"[{mode_label}] User manager error: {e}", exc_info=True)
logger.error("[%s] User manager error: %s", mode_label, e, exc_info=True)
# Sleep until next poll
try:
@@ -553,9 +591,11 @@ async def user_manager_task(
# Cancel all remaining scanners on shutdown
logger.info(
f"[{mode_label}] User manager shutting down, cancelling {len(user_states)} scanner(s)"
"[%s] User manager shutting down, cancelling %s scanner(s)",
mode_label,
len(user_states),
)
for state in list(user_states.values()):
state.cancel_scope.cancel()
logger.info(f"[{mode_label}] User manager stopped")
logger.info("[%s] User manager stopped", mode_label)
nextcloud_mcp_server/vector/pca.py
+5 -3
View File
@@ -92,9 +92,11 @@ class PCA:
self.explained_variance_ratio_ = np.zeros(self.n_components)
logger.debug(
f"PCA fit: {n_samples} samples, {n_features} features → "
f"{self.n_components} components, "
f"explained variance: {self.explained_variance_ratio_}"
"PCA fit: %s samples, %s features → %s components, explained variance: %s",
n_samples,
n_features,
self.n_components,
self.explained_variance_ratio_,
)
return self
nextcloud_mcp_server/vector/placeholder.py
+25 -9
View File
@@ -122,13 +122,19 @@ async def write_placeholder_point(
)
logger.debug(
f"Wrote placeholder for {doc_type}_{doc_id} (user={user_id}, "
f"modified_at={modified_at})"
"Wrote placeholder for %s_%s (user=%s, modified_at=%s)",
doc_type,
doc_id,
user_id,
modified_at,
)
except Exception as e:
logger.error(
f"Failed to write placeholder for {doc_type}_{doc_id}: {e}",
"Failed to write placeholder for %s_%s: %s",
doc_type,
doc_id,
e,
exc_info=True,
)
raise
@@ -180,7 +186,9 @@ async def query_document_metadata(
return None
except Exception as e:
logger.warning(f"Error querying document metadata for {doc_type}_{doc_id}: {e}")
logger.warning(
"Error querying document metadata for %s_%s: %s", doc_type, doc_id, e
)
return None
@@ -219,11 +227,16 @@ async def delete_placeholder_point(
),
)
logger.debug(f"Deleted placeholder for {doc_type}_{doc_id} (user={user_id})")
logger.debug(
"Deleted placeholder for %s_%s (user=%s)", doc_type, doc_id, user_id
)
except Exception as e:
logger.error(
f"Failed to delete placeholder for {doc_type}_{doc_id}: {e}",
"Failed to delete placeholder for %s_%s: %s",
doc_type,
doc_id,
e,
exc_info=True,
)
raise
@@ -271,13 +284,16 @@ async def update_placeholder_status(
)
logger.debug(
f"Updated placeholder status for {doc_type}_{doc_id} to '{status}' "
f"(user={user_id})"
"Updated placeholder status for %s_%s to '%s' (user=%s)",
doc_type,
doc_id,
status,
user_id,
)
except Exception as e:
logger.warning(
f"Failed to update placeholder status for {doc_type}_{doc_id}: {e}"
"Failed to update placeholder status for %s_%s: %s", doc_type, doc_id, e
)
# Don't raise - status updates are non-critical
nextcloud_mcp_server/vector/processor.py
+78 -37
View File
@@ -100,7 +100,7 @@ async def processor_task(
user_id: User being processed
task_status: Status object for signaling task readiness
"""
logger.info(f"Processor {worker_id} started")
logger.info("Processor %s started", worker_id)
# Signal that the task has started and is ready
task_status.started()
@@ -130,18 +130,21 @@ async def processor_task(
except anyio.EndOfStream:
# Scanner finished and closed stream, exit gracefully
logger.info(f"Processor {worker_id}: Scanner finished, exiting")
logger.info("Processor %s: Scanner finished, exiting", worker_id)
break
except Exception as e:
logger.error(
f"Processor {worker_id} error processing "
f"{doc_task.doc_type}_{doc_task.doc_id}: {e}",
"Processor %s error processing %s_%s: %s",
worker_id,
doc_task.doc_type,
doc_task.doc_id,
e,
exc_info=True,
)
# Continue to next document (no task_done() needed with streams)
logger.info(f"Processor {worker_id} stopped")
logger.info("Processor %s stopped", worker_id)
async def process_document(doc_task: DocumentTask, nc_client: NextcloudClient):
@@ -157,8 +160,11 @@ async def process_document(doc_task: DocumentTask, nc_client: NextcloudClient):
start_time = time.time()
logger.debug(
f"Processing {doc_task.doc_type}_{doc_task.doc_id} "
f"for {doc_task.user_id} ({doc_task.operation})"
"Processing %s_%s for %s (%s)",
doc_task.doc_type,
doc_task.doc_id,
doc_task.user_id,
doc_task.operation,
)
with trace_operation(
@@ -197,7 +203,10 @@ async def process_document(doc_task: DocumentTask, nc_client: NextcloudClient):
),
)
logger.info(
f"Deleted {doc_task.doc_type}_{doc_task.doc_id} for {doc_task.user_id}"
"Deleted %s_%s for %s",
doc_task.doc_type,
doc_task.doc_id,
doc_task.user_id,
)
# Record successful deletion metrics
@@ -223,15 +232,22 @@ async def process_document(doc_task: DocumentTask, nc_client: NextcloudClient):
except (HTTPStatusError, Exception) as e:
if attempt < max_retries - 1:
logger.warning(
f"Retry {attempt + 1}/{max_retries} for "
f"{doc_task.doc_type}_{doc_task.doc_id}: {e}"
"Retry %s/%s for %s_%s: %s",
attempt + 1,
max_retries,
doc_task.doc_type,
doc_task.doc_id,
e,
)
await anyio.sleep(retry_delay)
retry_delay *= 2 # Exponential backoff
else:
logger.error(
f"Failed to index {doc_task.doc_type}_{doc_task.doc_id} "
f"after {max_retries} retries: {e}"
"Failed to index %s_%s after %s retries: %s",
doc_task.doc_type,
doc_task.doc_id,
max_retries,
e,
)
# Record failed processing metrics
duration = time.time() - start_time
@@ -348,7 +364,11 @@ async def _index_document(
break
except Exception as e:
logger.warning(
f"Failed to fetch card with metadata (board_id={board_id}, stack_id={stack_id}, card_id={doc_task.doc_id}): {e}, falling back to iteration"
"Failed to fetch card with metadata (board_id=%s, stack_id=%s, card_id=%s): %s, falling back to iteration",
board_id,
stack_id,
doc_task.doc_id,
e,
)
# Fallback: Iterate through all boards/stacks (for legacy data or if fast path failed)
@@ -454,27 +474,32 @@ async def _index_document(
if "page_boundaries" in file_metadata:
page_boundaries = file_metadata["page_boundaries"]
logger.info(
f"Page boundaries for {file_path}: "
f"{len(page_boundaries)} pages, text length: {len(content)}"
"Page boundaries for %s: %s pages, text length: %s",
file_path,
len(page_boundaries),
len(content),
)
# Log first 3 page boundaries for debugging
for boundary in page_boundaries[:3]:
logger.debug(
f" Page {boundary['page']}: "
f"offsets [{boundary['start_offset']}:{boundary['end_offset']}]"
" Page %s: offsets [%s:%s]",
boundary["page"],
boundary["start_offset"],
boundary["end_offset"],
)
# Verify last boundary matches text length
if page_boundaries:
last_boundary = page_boundaries[-1]
if last_boundary["end_offset"] != len(content):
logger.warning(
f"Text length mismatch: content={len(content)}, "
f"last_boundary_end={last_boundary['end_offset']}"
"Text length mismatch: content=%s, last_boundary_end=%s",
len(content),
last_boundary["end_offset"],
)
else:
logger.debug(f"No page_boundaries in metadata for {file_path}")
logger.debug("No page_boundaries in metadata for %s", file_path)
except Exception as e:
logger.error(f"Failed to process file {file_path}: {e}")
logger.error("Failed to process file %s: %s", file_path, e)
raise
# Tokenize and chunk (using configured chunk size and overlap)
@@ -509,26 +534,32 @@ async def _index_document(
# Diagnostic: Verify page number assignment
assigned_count = sum(1 for c in chunks if c.page_number is not None)
logger.info(
f"Assigned page numbers to {assigned_count}/{len(chunks)} chunks "
f"for {file_path}"
"Assigned page numbers to %s/%s chunks for %s",
assigned_count,
len(chunks),
file_path,
)
# Log first 3 chunks to see their page assignments
for i, chunk in enumerate(chunks[:3]):
logger.debug(
f" Chunk {i}: page={chunk.page_number}, "
f"offsets=[{chunk.start_offset}:{chunk.end_offset}]"
" Chunk %s: page=%s, offsets=[%s:%s]",
i,
chunk.page_number,
chunk.start_offset,
chunk.end_offset,
)
# Warning if NO page numbers were assigned
if assigned_count == 0:
logger.warning(
f"NO page numbers assigned! "
f"Text length: {len(content)}, "
f"Chunks: {len(chunks)}, "
f"Chunk offset range: [{chunks[0].start_offset}:{chunks[-1].end_offset}], "
f"Page boundaries: {len(page_boundaries_list)} pages, "
f"First boundary: {page_boundaries_list[0] if page_boundaries_list else 'None'}"
"NO page numbers assigned! Text length: %s, Chunks: %s, Chunk offset range: [%s:%s], Page boundaries: %s pages, First boundary: %s",
len(content),
len(chunks),
chunks[0].start_offset,
chunks[-1].end_offset,
len(page_boundaries_list),
page_boundaries_list[0] if page_boundaries_list else "None",
)
# Extract chunk texts for embedding
@@ -603,7 +634,7 @@ async def _index_document(
page_boundaries_list = cast(list[dict[str, Any]], page_boundaries)
logger.info(f"Computing chunk bboxes for {len(chunk_data)} PDF chunks")
logger.info("Computing chunk bboxes for %s PDF chunks", len(chunk_data))
batch_results = await anyio.to_thread.run_sync( # type: ignore[attr-defined]
lambda: PDFHighlighter.compute_chunk_bboxes_batch(
@@ -617,7 +648,9 @@ async def _index_document(
for chunk_index, (bboxes, _) in batch_results.items():
chunk_bboxes[chunk_index] = bboxes
logger.info(f"Computed bboxes for {len(chunk_bboxes)}/{len(chunks)} chunks")
logger.info(
"Computed bboxes for %s/%s chunks", len(chunk_bboxes), len(chunks)
)
# Run all embedding/highlighting operations in parallel
# - Dense embeddings: I/O bound (API call)
@@ -753,7 +786,10 @@ async def _index_document(
except Exception as e:
# Log but don't fail indexing if placeholder deletion fails
logger.warning(
f"Failed to delete placeholder for {doc_task.doc_type}_{doc_task.doc_id}: {e}"
"Failed to delete placeholder for %s_%s: %s",
doc_task.doc_type,
doc_task.doc_id,
e,
)
# Upsert to Qdrant in batches. Now that we no longer embed PNG payloads,
@@ -779,10 +815,15 @@ async def _index_document(
)
if batch_end < len(points):
logger.debug(
f"Upserted batch {batch_start // BATCH_SIZE + 1}/{(len(points) + BATCH_SIZE - 1) // BATCH_SIZE}"
"Upserted batch %s/%s",
batch_start // BATCH_SIZE + 1,
(len(points) + BATCH_SIZE - 1) // BATCH_SIZE,
)
logger.info(
f"Indexed {doc_task.doc_type}_{doc_task.doc_id} for {doc_task.user_id} "
f"({len(chunks)} chunks)"
"Indexed %s_%s for %s (%s chunks)",
doc_task.doc_type,
doc_task.doc_id,
doc_task.user_id,
len(chunks),
)
nextcloud_mcp_server/vector/qdrant_client.py
+18 -16
View File
@@ -534,7 +534,7 @@ async def get_qdrant_client() -> AsyncQdrantClient:
# Detect mode and initialize client accordingly
if settings.qdrant_url:
# Network mode
logger.info(f"Using Qdrant network mode: {settings.qdrant_url}")
logger.info("Using Qdrant network mode: %s", settings.qdrant_url)
provisional = AsyncQdrantClient(
url=settings.qdrant_url,
api_key=settings.qdrant_api_key,
@@ -548,7 +548,7 @@ async def get_qdrant_client() -> AsyncQdrantClient:
else:
# Persistent local mode - use path parameter
logger.info(
f"Using Qdrant persistent mode: {settings.qdrant_location}"
"Using Qdrant persistent mode: %s", settings.qdrant_location
)
provisional = AsyncQdrantClient(path=settings.qdrant_location)
else:
@@ -580,14 +580,14 @@ async def get_qdrant_client() -> AsyncQdrantClient:
# `get_collection()`) is the only existence-probe permitted on a
# collection-scoped JWT — it returns 200 with the collection
# detail on hit and 404 on miss.
logger.debug(f"Fetching collection '{collection_name}' details...")
logger.debug("Fetching collection '%s' details...", collection_name)
collection_info = None
try:
collection_info = await provisional.get_collection(collection_name)
except UnexpectedResponse as exc:
if exc.status_code != 404:
raise
logger.debug(f"Collection '{collection_name}' not found (404).")
logger.debug("Collection '%s' not found (404).", collection_name)
except ValueError as exc:
# Local/in-memory qdrant_client raises ValueError(f"Collection
# {name} not found") instead of UnexpectedResponse — see
@@ -602,12 +602,12 @@ async def get_qdrant_client() -> AsyncQdrantClient:
# multi-user-basic CI jobs all exercise this path.
if "not found" not in str(exc):
raise
logger.debug(f"Collection '{collection_name}' not found (local mode).")
logger.debug("Collection '%s' not found (local mode).", collection_name)
if collection_info is not None:
# Collection exists - validate dimensions
logger.debug(
f"Collection '{collection_name}' found, validating dimensions..."
"Collection '%s' found, validating dimensions...", collection_name
)
# Handle both named vectors (dict) and legacy single vector
vectors = collection_info.config.params.vectors
@@ -633,8 +633,10 @@ async def get_qdrant_client() -> AsyncQdrantClient:
)
logger.info(
f"Using existing Qdrant collection: {collection_name} "
f"(dimension={actual_dimension}, model={settings.get_embedding_model_name()})"
"Using existing Qdrant collection: %s (dimension=%s, model=%s)",
collection_name,
actual_dimension,
settings.get_embedding_model_name(),
)
# Existing collections may pre-date the doc_id normalization /
@@ -658,8 +660,10 @@ async def get_qdrant_client() -> AsyncQdrantClient:
# Collection doesn't exist - create it
embedding_model = settings.get_embedding_model_name()
logger.info(
f"Collection '{collection_name}' not found, creating with "
f"dimension={expected_dimension}, model={embedding_model}..."
"Collection '%s' not found, creating with dimension=%s, model=%s...",
collection_name,
expected_dimension,
embedding_model,
)
await provisional.create_collection(
collection_name=collection_name,
@@ -678,12 +682,10 @@ async def get_qdrant_client() -> AsyncQdrantClient:
},
)
logger.info(
f"Created Qdrant collection: {collection_name}\n"
f" Dense vector dimension: {expected_dimension}\n"
f" Dense embedding model: {embedding_model}\n"
f" Sparse vectors: BM25 (for hybrid search)\n"
f" Distance: COSINE\n"
f"Background sync will index all documents with dense + sparse vectors."
"Created Qdrant collection: %s\\n Dense vector dimension: %s\\n Dense embedding model: %s\\n Sparse vectors: BM25 (for hybrid search)\\n Distance: COSINE\\nBackground sync will index all documents with dense + sparse vectors.",
collection_name,
expected_dimension,
embedding_model,
)
# Freshly created collection has no payload schema yet; pass
# {} explicitly to skip the otherwise-redundant
nextcloud_mcp_server/vector/scanner.py
+102 -55
View File
@@ -155,7 +155,7 @@ async def get_last_indexed_timestamp(user_id: str) -> int | None:
)
num_points = len(points)
logger.info(f"Found {num_points} indexed notes in Qdrant for user {user_id}")
logger.info("Found %s indexed notes in Qdrant for user %s", num_points, user_id)
if points:
timestamps = [
@@ -165,14 +165,16 @@ async def get_last_indexed_timestamp(user_id: str) -> int | None:
]
max_timestamp = max(timestamps) if timestamps else 0
logger.info(
f"Max indexed_at: {max_timestamp}, timestamps sample: {timestamps[:3]}"
"Max indexed_at: %s, timestamps sample: %s",
max_timestamp,
timestamps[:3],
)
return int(max_timestamp) if max_timestamp > 0 else None
logger.info(f"No indexed notes found for user {user_id}")
logger.info("No indexed notes found for user %s", user_id)
return None
except Exception as e:
logger.warning(f"Failed to get last indexed timestamp: {e}", exc_info=True)
logger.warning("Failed to get last indexed timestamp: %s", e, exc_info=True)
return None
@@ -198,7 +200,7 @@ async def scanner_task(
user_id: User to scan
task_status: Status object for signaling task readiness
"""
logger.info(f"Scanner task started for user: {user_id}")
logger.info("Scanner task started for user: %s", user_id)
settings = get_settings()
# Signal that the task has started and is ready
@@ -215,7 +217,7 @@ async def scanner_task(
)
except Exception as e:
logger.error(f"Scanner error: {e}", exc_info=True)
logger.error("Scanner error: %s", e, exc_info=True)
# Sleep until next interval or wake event
try:
@@ -247,7 +249,10 @@ async def scan_user_documents(
scan_id = random.randint(1000, 9999)
logger.info(
f"[SCAN-{scan_id}] Starting scan for user: {user_id}, initial_sync={initial_sync}"
"[SCAN-%s] Starting scan for user: %s, initial_sync=%s",
scan_id,
user_id,
initial_sync,
)
with trace_operation(
@@ -266,7 +271,9 @@ async def scan_user_documents(
)
if prune_before:
logger.info(
f"[SCAN-{scan_id}] Using pruneBefore={prune_before} to optimize data transfer"
"[SCAN-%s] Using pruneBefore=%s to optimize data transfer",
scan_id,
prune_before,
)
# For deletion tracking, get all doc_ids in Qdrant (for incremental sync)
@@ -303,7 +310,7 @@ async def scan_user_documents(
if point.payload is not None and "doc_id" in point.payload
}
logger.debug(f"Found {len(indexed_doc_ids)} indexed documents in Qdrant")
logger.debug("Found %s indexed documents in Qdrant", len(indexed_doc_ids))
# Stream notes from Nextcloud and process immediately
note_count = 0
@@ -341,7 +348,8 @@ async def scan_user_documents(
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
logger.debug(
f"Document {doc_id} reappeared, removing from deletion grace period"
"Document %s reappeared, removing from deletion grace period",
doc_id,
)
del _potentially_deleted[doc_key]
@@ -368,14 +376,17 @@ async def scan_user_documents(
stale_threshold = get_settings().vector_sync_scan_interval * 5
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for note {doc_id} "
f"(age={placeholder_age:.1f}s), requeuing"
"Found stale placeholder for note %s (age=%ss), requeuing",
doc_id,
format(placeholder_age, ".1f"),
)
needs_indexing = True
else:
logger.debug(
f"Skipping note {doc_id} with recent placeholder "
f"(age={placeholder_age:.1f}s < {stale_threshold:.1f}s)"
"Skipping note %s with recent placeholder (age=%ss < %ss)",
doc_id,
format(placeholder_age, ".1f"),
format(stale_threshold, ".1f"),
)
if needs_indexing:
@@ -399,11 +410,11 @@ async def scan_user_documents(
queued += 1
# Log and record metrics after streaming
logger.info(f"[SCAN-{scan_id}] Found {note_count} notes for {user_id}")
logger.info("[SCAN-%s] Found %s notes for %s", scan_id, note_count, user_id)
record_vector_sync_scan(note_count)
if initial_sync:
logger.info(f"Sent {queued} documents for initial sync: {user_id}")
logger.info("Sent %s documents for initial sync: %s", queued, user_id)
return
# Check for deleted documents (in Qdrant but not in Nextcloud)
@@ -426,8 +437,10 @@ async def scan_user_documents(
if time_missing >= grace_period:
# Grace period elapsed, send for deletion
logger.info(
f"Document {doc_id} missing for {time_missing:.1f}s "
f"(>{grace_period:.1f}s grace period), sending deletion"
"Document %s missing for %ss (>%ss grace period), sending deletion",
doc_id,
format(time_missing, ".1f"),
format(grace_period, ".1f"),
)
await send_stream.send(
DocumentTask(
@@ -443,13 +456,16 @@ async def scan_user_documents(
del _potentially_deleted[doc_key]
else:
logger.debug(
f"Document {doc_id} still missing "
f"({time_missing:.1f}s/{grace_period:.1f}s grace period)"
"Document %s still missing (%ss/%ss grace period)",
doc_id,
format(time_missing, ".1f"),
format(grace_period, ".1f"),
)
else:
# First time missing, add to grace period tracking
logger.debug(
f"Document {doc_id} missing for first time, starting grace period"
"Document %s missing for first time, starting grace period",
doc_id,
)
_potentially_deleted[doc_key] = current_time
@@ -476,7 +492,7 @@ async def scan_user_documents(
if point.payload is not None and "doc_id" in point.payload
}
logger.debug(f"Found {len(indexed_file_ids)} indexed files in Qdrant")
logger.debug("Found %s indexed files in Qdrant", len(indexed_file_ids))
# Scan for tagged PDF files
file_count = 0
@@ -568,7 +584,9 @@ async def scan_user_documents(
file_key = (user_id, file_id)
if file_key in _potentially_deleted:
logger.debug(
f"File {file_path} (ID: {file_id}) reappeared, removing from deletion grace period"
"File %s (ID: %s) reappeared, removing from deletion grace period",
file_path,
file_id,
)
del _potentially_deleted[file_key]
@@ -595,14 +613,19 @@ async def scan_user_documents(
stale_threshold = get_settings().vector_sync_scan_interval * 5
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for file {file_path} (ID: {file_id}) "
f"(age={placeholder_age:.1f}s), requeuing"
"Found stale placeholder for file %s (ID: %s) (age=%ss), requeuing",
file_path,
file_id,
format(placeholder_age, ".1f"),
)
needs_indexing = True
else:
logger.debug(
f"Skipping file {file_path} (ID: {file_id}) with recent placeholder "
f"(age={placeholder_age:.1f}s < {stale_threshold:.1f}s)"
"Skipping file %s (ID: %s) with recent placeholder (age=%ss < %ss)",
file_path,
file_id,
format(placeholder_age, ".1f"),
format(stale_threshold, ".1f"),
)
if needs_indexing:
@@ -627,7 +650,7 @@ async def scan_user_documents(
file_queued += 1
logger.info(
f"[SCAN-{scan_id}] Found {file_count} tagged PDFs for {user_id}"
"[SCAN-%s] Found %s tagged PDFs for %s", scan_id, file_count, user_id
)
record_vector_sync_scan(file_count)
@@ -645,8 +668,10 @@ async def scan_user_documents(
if time_missing >= grace_period:
# Grace period elapsed, send for deletion
logger.info(
f"File ID {file_id} missing for {time_missing:.1f}s "
f"(>{grace_period:.1f}s grace period), sending deletion"
"File ID %s missing for %ss (>%ss grace period), sending deletion",
file_id,
format(time_missing, ".1f"),
format(grace_period, ".1f"),
)
await send_stream.send(
DocumentTask(
@@ -662,12 +687,13 @@ async def scan_user_documents(
else:
# First time missing, add to grace period tracking
logger.debug(
f"File ID {file_id} missing for first time, starting grace period"
"File ID %s missing for first time, starting grace period",
file_id,
)
_potentially_deleted[file_key] = current_time
except Exception as e:
logger.warning(f"Failed to scan tagged files for {user_id}: {e}")
logger.warning("Failed to scan tagged files for %s: %s", user_id, e)
queued += file_queued
@@ -683,7 +709,7 @@ async def scan_user_documents(
)
queued += news_queued
except Exception as e:
logger.warning(f"Failed to scan news items for {user_id}: {e}")
logger.warning("Failed to scan news items for %s: %s", user_id, e)
# Scan Deck cards
deck_queued = 0
@@ -697,14 +723,19 @@ async def scan_user_documents(
)
queued += deck_queued
except Exception as e:
logger.warning(f"Failed to scan deck cards for {user_id}: {e}")
logger.warning("Failed to scan deck cards for %s: %s", user_id, e)
if queued > 0:
logger.info(
f"Sent {queued} documents ({file_queued} files, {news_queued} news items, {deck_queued} deck cards) for incremental sync: {user_id}"
"Sent %s documents (%s files, %s news items, %s deck cards) for incremental sync: %s",
queued,
file_queued,
news_queued,
deck_queued,
user_id,
)
else:
logger.debug(f"No changes detected for {user_id}")
logger.debug("No changes detected for %s", user_id)
async def scan_news_items(
@@ -754,7 +785,7 @@ async def scan_news_items(
for point in points
if point.payload is not None and "doc_id" in point.payload
}
logger.debug(f"Found {len(indexed_item_ids)} indexed news items in Qdrant")
logger.debug("Found %s indexed news items in Qdrant", len(indexed_item_ids))
# Fetch all items (News app caps at ~200 per feed via auto-purge)
all_items = await nc_client.news.get_items(
@@ -762,7 +793,7 @@ async def scan_news_items(
type_=NewsItemType.ALL,
get_read=True,
)
logger.debug(f"[SCAN-{scan_id}] Found {len(all_items)} news items")
logger.debug("[SCAN-%s] Found %s news items", scan_id, len(all_items))
item_count = len(all_items)
nextcloud_item_ids: set[str] = set()
@@ -800,7 +831,8 @@ async def scan_news_items(
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
logger.debug(
f"News item {doc_id} reappeared, removing from deletion grace period"
"News item %s reappeared, removing from deletion grace period",
doc_id,
)
del _potentially_deleted[doc_key]
@@ -820,8 +852,9 @@ async def scan_news_items(
stale_threshold = settings.vector_sync_scan_interval * 5
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for news item {doc_id} "
f"(age={placeholder_age:.1f}s), requeuing"
"Found stale placeholder for news item %s (age=%ss), requeuing",
doc_id,
format(placeholder_age, ".1f"),
)
needs_indexing = True
@@ -844,7 +877,10 @@ async def scan_news_items(
queued += 1
logger.info(
f"[SCAN-{scan_id}] Found {item_count} news items (starred+unread) for {user_id}"
"[SCAN-%s] Found %s news items (starred+unread) for %s",
scan_id,
item_count,
user_id,
)
record_vector_sync_scan(item_count)
@@ -864,8 +900,10 @@ async def scan_news_items(
if time_missing >= grace_period:
logger.info(
f"News item {doc_id} missing for {time_missing:.1f}s "
f"(>{grace_period:.1f}s grace period), sending deletion"
"News item %s missing for %ss (>%ss grace period), sending deletion",
doc_id,
format(time_missing, ".1f"),
format(grace_period, ".1f"),
)
await send_stream.send(
DocumentTask(
@@ -880,7 +918,8 @@ async def scan_news_items(
del _potentially_deleted[doc_key]
else:
logger.debug(
f"News item {doc_id} missing for first time, starting grace period"
"News item %s missing for first time, starting grace period",
doc_id,
)
_potentially_deleted[doc_key] = current_time
@@ -932,11 +971,11 @@ async def scan_deck_cards(
for point in points
if point.payload is not None and "doc_id" in point.payload
}
logger.debug(f"Found {len(indexed_card_ids)} indexed deck cards in Qdrant")
logger.debug("Found %s indexed deck cards in Qdrant", len(indexed_card_ids))
# Fetch all boards
boards = await nc_client.deck.get_boards()
logger.debug(f"[SCAN-{scan_id}] Found {len(boards)} deck boards")
logger.debug("[SCAN-%s] Found %s deck boards", scan_id, len(boards))
card_count = 0
nextcloud_card_ids: set[str] = set()
@@ -949,7 +988,7 @@ async def scan_deck_cards(
# Skip deleted boards (soft delete: deletedAt > 0)
if board.deletedAt > 0:
logger.debug(f"[SCAN-{scan_id}] Skipping deleted board {board.id}")
logger.debug("[SCAN-%s] Skipping deleted board %s", scan_id, board.id)
continue
# Get stacks for this board
@@ -998,7 +1037,8 @@ async def scan_deck_cards(
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
logger.debug(
f"Deck card {doc_id} reappeared, removing from deletion grace period"
"Deck card %s reappeared, removing from deletion grace period",
doc_id,
)
del _potentially_deleted[doc_key]
@@ -1018,8 +1058,9 @@ async def scan_deck_cards(
stale_threshold = settings.vector_sync_scan_interval * 5
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for deck card {doc_id} "
f"(age={placeholder_age:.1f}s), requeuing"
"Found stale placeholder for deck card %s (age=%ss), requeuing",
doc_id,
format(placeholder_age, ".1f"),
)
needs_indexing = True
@@ -1043,7 +1084,10 @@ async def scan_deck_cards(
queued += 1
logger.info(
f"[SCAN-{scan_id}] Found {card_count} deck cards (non-archived) for {user_id}"
"[SCAN-%s] Found %s deck cards (non-archived) for %s",
scan_id,
card_count,
user_id,
)
record_vector_sync_scan(card_count)
@@ -1062,8 +1106,10 @@ async def scan_deck_cards(
if time_missing >= grace_period:
logger.info(
f"Deck card {doc_id} missing for {time_missing:.1f}s "
f"(>{grace_period:.1f}s grace period), sending deletion"
"Deck card %s missing for %ss (>%ss grace period), sending deletion",
doc_id,
format(time_missing, ".1f"),
format(grace_period, ".1f"),
)
await send_stream.send(
DocumentTask(
@@ -1078,7 +1124,8 @@ async def scan_deck_cards(
del _potentially_deleted[doc_key]
else:
logger.debug(
f"Deck card {doc_id} missing for first time, starting grace period"
"Deck card %s missing for first time, starting grace period",
doc_id,
)
_potentially_deleted[doc_key] = current_time
nextcloud_mcp_server/vector/visualization.py
+16 -13
View File
@@ -92,7 +92,7 @@ async def compute_pca_coordinates(
if embedding_dim is None:
return {"coordinates_3d": [], "query_coords": []}
logger.info(f"Detected embedding dimension: {embedding_dim}")
logger.info("Detected embedding dimension: %s", embedding_dim)
# Build chunk vectors array in search_results order (1:1 mapping)
chunk_vectors = []
@@ -103,7 +103,7 @@ async def compute_pca_coordinates(
else:
# Chunk not found in vectors (shouldn't happen)
logger.warning(
f"Chunk {chunk_key} not found in fetched vectors, using zero vector"
"Chunk %s not found in fetched vectors, using zero vector", chunk_key
)
chunk_vectors.append(np.zeros(embedding_dim))
@@ -129,17 +129,19 @@ async def compute_pca_coordinates(
if zero_norm_mask.any():
zero_indices = np.where(zero_norm_mask)[0]
logger.warning(
f"Found {zero_norm_mask.sum()} zero-norm vectors at indices "
f"{zero_indices.tolist()}. Replacing with small epsilon to avoid "
"division by zero."
"Found %s zero-norm vectors at indices %s. Replacing with small epsilon to avoid division by zero.",
zero_norm_mask.sum(),
zero_indices.tolist(),
)
# Replace zero norms with small epsilon to avoid NaN
norms[zero_norm_mask] = 1e-10
all_vectors_normalized = all_vectors / norms
logger.info(
f"Normalized vectors: query_norm={norms[-1][0]:.3f}, "
f"doc_norm_range=[{norms[:-1].min():.3f}, {norms[:-1].max():.3f}]"
"Normalized vectors: query_norm=%s, doc_norm_range=[%s, %s]",
format(norms[-1][0], ".3f"),
format(norms[:-1].min(), ".3f"),
format(norms[:-1].max(), ".3f"),
)
# Apply PCA dimensionality reduction (768-dim → 3D)
@@ -161,9 +163,9 @@ async def compute_pca_coordinates(
if nan_mask.any():
nan_rows = np.where(nan_mask.any(axis=1))[0]
logger.error(
f"Found NaN values in PCA output at {len(nan_rows)} points: "
f"{nan_rows.tolist()[:10]}. Replacing NaN with 0.0 to prevent "
"JSON serialization error."
"Found NaN values in PCA output at %s points: %s. Replacing NaN with 0.0 to prevent JSON serialization error.",
len(nan_rows),
nan_rows.tolist()[:10],
)
# Replace NaN with 0 to allow JSON serialization
coords_3d = np.nan_to_num(coords_3d, nan=0.0)
@@ -174,9 +176,10 @@ async def compute_pca_coordinates(
chunk_coords_3d = coords_3d[:-1] # All but last are chunks
logger.info(
f"PCA explained variance: PC1={pca.explained_variance_ratio_[0]:.3f}, "
f"PC2={pca.explained_variance_ratio_[1]:.3f}, "
f"PC3={pca.explained_variance_ratio_[2]:.3f}"
"PCA explained variance: PC1=%s, PC2=%s, PC3=%s",
format(pca.explained_variance_ratio_[0], ".3f"),
format(pca.explained_variance_ratio_[1], ".3f"),
format(pca.explained_variance_ratio_[2], ".3f"),
)
# Coordinates already match search_results order (1:1 mapping)