refactor: simplify OpenTelemetry tracing configuration

Simplifies the OpenTelemetry tracing setup by removing the redundant
OTEL_ENABLED flag and using the presence of OTEL_EXPORTER_OTLP_ENDPOINT
to determine if tracing should be enabled. This follows the standard
OpenTelemetry environment variable conventions more closely.

Changes:
- Remove OTEL_ENABLED/tracing_enabled flag in favor of checking if
  OTEL_EXPORTER_OTLP_ENDPOINT is set
- Add OTEL_EXPORTER_VERIFY_SSL configuration option for OTLP endpoints
  with self-signed certificates (defaults to false for development)
- Move HTTPXClientInstrumentor initialization to module level to ensure
  httpx calls are traced across all Nextcloud API requests
- Add tracing spans to vector sync operations (scan_user_documents)
- Fix authorization header logging to only warn about missing headers
  in OAuth mode (BasicAuth mode doesn't use Authorization headers)
- Update observability documentation to reflect simplified configuration
- Refactor Dockerfile to use --no-editable flag for uv sync

Breaking changes:
- OTEL_ENABLED environment variable is removed
- Tracing is now automatically enabled when OTEL_EXPORTER_OTLP_ENDPOINT
  is set

Migration guide:
- Remove OTEL_ENABLED=true from environment configuration
- Tracing will be enabled automatically if OTEL_EXPORTER_OTLP_ENDPOINT
  is configured

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2025-11-10 22:48:37 +01:00
parent f44bf3e8f2
commit a6e5f3d8ff
13 changed files with 255 additions and 206 deletions
+59 -48
View File
@@ -15,6 +15,7 @@ from qdrant_client.models import FieldCondition, Filter, MatchValue, PointStruct
from nextcloud_mcp_server.client import NextcloudClient
from nextcloud_mcp_server.config import get_settings
from nextcloud_mcp_server.embedding import get_embedding_service
from nextcloud_mcp_server.observability.tracing import trace_operation
from nextcloud_mcp_server.vector.document_chunker import DocumentChunker
from nextcloud_mcp_server.vector.qdrant_client import get_qdrant_client
from nextcloud_mcp_server.vector.scanner import DocumentTask
@@ -94,58 +95,68 @@ async def process_document(doc_task: DocumentTask, nc_client: NextcloudClient):
f"for {doc_task.user_id} ({doc_task.operation})"
)
qdrant_client = await get_qdrant_client()
settings = get_settings()
with trace_operation(
"vector_sync.process_document",
attributes={
"vector_sync.operation": "process",
"vector_sync.user_id": doc_task.user_id,
"vector_sync.doc_id": doc_task.doc_id,
"vector_sync.doc_type": doc_task.doc_type,
"vector_sync.doc_operation": doc_task.operation,
},
):
qdrant_client = await get_qdrant_client()
settings = get_settings()
# Handle deletion
if doc_task.operation == "delete":
await qdrant_client.delete(
collection_name=settings.get_collection_name(),
points_selector=Filter(
must=[
FieldCondition(
key="user_id",
match=MatchValue(value=doc_task.user_id),
),
FieldCondition(
key="doc_id",
match=MatchValue(value=doc_task.doc_id),
),
FieldCondition(
key="doc_type",
match=MatchValue(value=doc_task.doc_type),
),
]
),
)
logger.info(
f"Deleted {doc_task.doc_type}_{doc_task.doc_id} for {doc_task.user_id}"
)
return
# Handle deletion
if doc_task.operation == "delete":
await qdrant_client.delete(
collection_name=settings.get_collection_name(),
points_selector=Filter(
must=[
FieldCondition(
key="user_id",
match=MatchValue(value=doc_task.user_id),
),
FieldCondition(
key="doc_id",
match=MatchValue(value=doc_task.doc_id),
),
FieldCondition(
key="doc_type",
match=MatchValue(value=doc_task.doc_type),
),
]
),
)
logger.info(
f"Deleted {doc_task.doc_type}_{doc_task.doc_id} for {doc_task.user_id}"
)
return
# Handle indexing with retry
max_retries = 3
retry_delay = 1.0
# Handle indexing with retry
max_retries = 3
retry_delay = 1.0
for attempt in range(max_retries):
try:
await _index_document(doc_task, nc_client, qdrant_client)
return # Success
for attempt in range(max_retries):
try:
await _index_document(doc_task, nc_client, qdrant_client)
return # Success
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}"
)
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}"
)
raise
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}"
)
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}"
)
raise
async def _index_document(
+135 -120
View File
@@ -13,6 +13,7 @@ from qdrant_client.models import FieldCondition, Filter, MatchValue
from nextcloud_mcp_server.client import NextcloudClient
from nextcloud_mcp_server.config import get_settings
from nextcloud_mcp_server.observability.tracing import trace_operation
from nextcloud_mcp_server.vector.qdrant_client import get_qdrant_client
logger = logging.getLogger(__name__)
@@ -154,134 +155,148 @@ async def scan_user_documents(
f"[SCAN-{scan_id}] Starting scan for user: {user_id}, initial_sync={initial_sync}"
)
# Calculate prune timestamp for optimized data transfer
# Only notes modified after this will be sent with full data
prune_before = None if initial_sync else await get_last_indexed_timestamp(user_id)
if prune_before:
logger.info(
f"[SCAN-{scan_id}] Using pruneBefore={prune_before} to optimize data transfer"
with trace_operation(
"vector_sync.scan_user_documents",
attributes={
"vector_sync.operation": "scan",
"vector_sync.user_id": user_id,
"vector_sync.initial_sync": initial_sync,
"vector_sync.scan_id": scan_id,
},
):
# Calculate prune timestamp for optimized data transfer
# Only notes modified after this will be sent with full data
prune_before = (
None if initial_sync else await get_last_indexed_timestamp(user_id)
)
if prune_before:
logger.info(
f"[SCAN-{scan_id}] Using pruneBefore={prune_before} to optimize data transfer"
)
# Fetch all notes from Nextcloud
notes = [
note
async for note in nc_client.notes.get_all_notes(prune_before=prune_before)
]
logger.info(f"[SCAN-{scan_id}] Found {len(notes)} notes for {user_id}")
if initial_sync:
# Send everything on first sync
for note in notes:
modified_at = note.get("modified", 0)
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=str(note["id"]),
doc_type="note",
operation="index",
modified_at=modified_at,
)
)
logger.info(f"Sent {len(notes)} documents for initial sync: {user_id}")
return
# Get indexed state from Qdrant
qdrant_client = await get_qdrant_client()
scroll_result = await qdrant_client.scroll(
collection_name=get_settings().get_collection_name(),
scroll_filter=Filter(
must=[
FieldCondition(key="user_id", match=MatchValue(value=user_id)),
FieldCondition(key="doc_type", match=MatchValue(value="note")),
]
),
with_payload=["doc_id", "indexed_at"],
with_vectors=False,
limit=10000,
)
# Fetch all notes from Nextcloud
notes = [
note async for note in nc_client.notes.get_all_notes(prune_before=prune_before)
]
logger.info(f"[SCAN-{scan_id}] Found {len(notes)} notes for {user_id}")
indexed_docs = {
point.payload["doc_id"]: point.payload["indexed_at"]
for point in scroll_result[0]
}
logger.debug(f"Found {len(indexed_docs)} indexed documents in Qdrant")
# Compare and queue changes
queued = 0
nextcloud_doc_ids = {str(note["id"]) for note in notes}
if initial_sync:
# Send everything on first sync
for note in notes:
doc_id = str(note["id"])
indexed_at = indexed_docs.get(doc_id)
modified_at = note.get("modified", 0)
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=str(note["id"]),
doc_type="note",
operation="index",
modified_at=modified_at,
)
)
logger.info(f"Sent {len(notes)} documents for initial sync: {user_id}")
return
# Get indexed state from Qdrant
qdrant_client = await get_qdrant_client()
scroll_result = await qdrant_client.scroll(
collection_name=get_settings().get_collection_name(),
scroll_filter=Filter(
must=[
FieldCondition(key="user_id", match=MatchValue(value=user_id)),
FieldCondition(key="doc_type", match=MatchValue(value="note")),
]
),
with_payload=["doc_id", "indexed_at"],
with_vectors=False,
limit=10000,
)
indexed_docs = {
point.payload["doc_id"]: point.payload["indexed_at"]
for point in scroll_result[0]
}
logger.debug(f"Found {len(indexed_docs)} indexed documents in Qdrant")
# Compare and queue changes
queued = 0
nextcloud_doc_ids = {str(note["id"]) for note in notes}
for note in notes:
doc_id = str(note["id"])
indexed_at = indexed_docs.get(doc_id)
modified_at = note.get("modified", 0)
# If document reappeared, remove from potentially_deleted
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
logger.debug(
f"Document {doc_id} reappeared, removing from deletion grace period"
)
del _potentially_deleted[doc_key]
# Send if never indexed or modified since last index
if indexed_at is None or modified_at > indexed_at:
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=doc_id,
doc_type="note",
operation="index",
modified_at=modified_at,
)
)
queued += 1
# Check for deleted documents (in Qdrant but not in Nextcloud)
# Use grace period: only delete after 2 consecutive scans confirm absence
settings = get_settings()
grace_period = settings.vector_sync_scan_interval * 1.5 # Allow 1.5 scan intervals
current_time = time.time()
for doc_id in indexed_docs:
if doc_id not in nextcloud_doc_ids:
# If document reappeared, remove from potentially_deleted
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
# Already marked as potentially deleted, check if grace period elapsed
first_missing_time = _potentially_deleted[doc_key]
time_missing = current_time - first_missing_time
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"
)
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=doc_id,
doc_type="note",
operation="delete",
modified_at=0,
)
)
queued += 1
# Remove from tracking after sending deletion
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)"
)
else:
# First time missing, add to grace period tracking
logger.debug(
f"Document {doc_id} missing for first time, starting grace period"
f"Document {doc_id} reappeared, removing from deletion grace period"
)
_potentially_deleted[doc_key] = current_time
del _potentially_deleted[doc_key]
if queued > 0:
logger.info(f"Sent {queued} documents for incremental sync: {user_id}")
else:
logger.debug(f"No changes detected for {user_id}")
# Send if never indexed or modified since last index
if indexed_at is None or modified_at > indexed_at:
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=doc_id,
doc_type="note",
operation="index",
modified_at=modified_at,
)
)
queued += 1
# Check for deleted documents (in Qdrant but not in Nextcloud)
# Use grace period: only delete after 2 consecutive scans confirm absence
settings = get_settings()
grace_period = (
settings.vector_sync_scan_interval * 1.5
) # Allow 1.5 scan intervals
current_time = time.time()
for doc_id in indexed_docs:
if doc_id not in nextcloud_doc_ids:
doc_key = (user_id, doc_id)
if doc_key in _potentially_deleted:
# Already marked as potentially deleted, check if grace period elapsed
first_missing_time = _potentially_deleted[doc_key]
time_missing = current_time - first_missing_time
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"
)
await send_stream.send(
DocumentTask(
user_id=user_id,
doc_id=doc_id,
doc_type="note",
operation="delete",
modified_at=0,
)
)
queued += 1
# Remove from tracking after sending deletion
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)"
)
else:
# First time missing, add to grace period tracking
logger.debug(
f"Document {doc_id} missing for first time, starting grace period"
)
_potentially_deleted[doc_key] = current_time
if queued > 0:
logger.info(f"Sent {queued} documents for incremental sync: {user_id}")
else:
logger.debug(f"No changes detected for {user_id}")