Merge branch 'upstream/main'
Ref: #issue_number - Merged upstream changes. - Resolved conflicts in 'api/extensions/ext_celery.py'. - Adjusted Celery beat schedule to prevent concurrent task execution: - 'clean_embedding_cache_task' now runs at 2:00. - 'clean_unused_datasets_task' now runs at 3:00. - 'clean_messages' now runs at 4:00.pull/22779/head
GuanMu
8 months ago
commit
2aa4820922
@ -0,0 +1,27 @@
|
||||
name: autofix.ci
|
||||
on:
|
||||
workflow_call:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [ "main" ]
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
autofix:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
# Use uv to ensure we have the same ruff version in CI and locally.
|
||||
- uses: astral-sh/setup-uv@7edac99f961f18b581bbd960d59d049f04c0002f
|
||||
- run: |
|
||||
cd api
|
||||
uv sync --dev
|
||||
# Fix lint errors
|
||||
uv run ruff check --fix-only .
|
||||
# Format code
|
||||
uv run ruff format .
|
||||
|
||||
- uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27
|
||||
|
||||
@ -1,48 +0,0 @@
|
||||
## Guidelines for Database Connection Management in App Runner and Task Pipeline
|
||||
|
||||
Due to the presence of tasks in App Runner that require long execution times, such as LLM generation and external requests, Flask-Sqlalchemy's strategy for database connection pooling is to allocate one connection (transaction) per request. This approach keeps a connection occupied even during non-DB tasks, leading to the inability to acquire new connections during high concurrency requests due to multiple long-running tasks.
|
||||
|
||||
Therefore, the database operations in App Runner and Task Pipeline must ensure connections are closed immediately after use, and it's better to pass IDs rather than Model objects to avoid detach errors.
|
||||
|
||||
Examples:
|
||||
|
||||
1. Creating a new record:
|
||||
|
||||
```python
|
||||
app = App(id=1)
|
||||
db.session.add(app)
|
||||
db.session.commit()
|
||||
db.session.refresh(app) # Retrieve table default values, like created_at, cached in the app object, won't affect after close
|
||||
|
||||
# Handle non-long-running tasks or store the content of the App instance in memory (via variable assignment).
|
||||
|
||||
db.session.close()
|
||||
|
||||
return app.id
|
||||
```
|
||||
|
||||
2. Fetching a record from the table:
|
||||
|
||||
```python
|
||||
app = db.session.query(App).filter(App.id == app_id).first()
|
||||
|
||||
created_at = app.created_at
|
||||
|
||||
db.session.close()
|
||||
|
||||
# Handle tasks (include long-running).
|
||||
|
||||
```
|
||||
|
||||
3. Updating a table field:
|
||||
|
||||
```python
|
||||
app = db.session.query(App).filter(App.id == app_id).first()
|
||||
|
||||
app.updated_at = time.utcnow()
|
||||
db.session.commit()
|
||||
db.session.close()
|
||||
|
||||
return app_id
|
||||
```
|
||||
|
||||
@ -0,0 +1,42 @@
|
||||
import re
|
||||
from collections.abc import Mapping
|
||||
from typing import Any, Optional
|
||||
|
||||
|
||||
def is_valid_trace_id(trace_id: str) -> bool:
|
||||
"""
|
||||
Check if the trace_id is valid.
|
||||
|
||||
Requirements: 1-128 characters, only letters, numbers, '-', and '_'.
|
||||
"""
|
||||
return bool(re.match(r"^[a-zA-Z0-9\-_]{1,128}$", trace_id))
|
||||
|
||||
|
||||
def get_external_trace_id(request: Any) -> Optional[str]:
|
||||
"""
|
||||
Retrieve the trace_id from the request.
|
||||
|
||||
Priority: header ('X-Trace-Id'), then parameters, then JSON body. Returns None if not provided or invalid.
|
||||
"""
|
||||
trace_id = request.headers.get("X-Trace-Id")
|
||||
if not trace_id:
|
||||
trace_id = request.args.get("trace_id")
|
||||
if not trace_id and getattr(request, "is_json", False):
|
||||
json_data = getattr(request, "json", None)
|
||||
if json_data:
|
||||
trace_id = json_data.get("trace_id")
|
||||
if isinstance(trace_id, str) and is_valid_trace_id(trace_id):
|
||||
return trace_id
|
||||
return None
|
||||
|
||||
|
||||
def extract_external_trace_id_from_args(args: Mapping[str, Any]) -> dict:
|
||||
"""
|
||||
Extract 'external_trace_id' from args.
|
||||
|
||||
Returns a dict suitable for use in extras. Returns an empty dict if not found.
|
||||
"""
|
||||
trace_id = args.get("external_trace_id")
|
||||
if trace_id:
|
||||
return {"external_trace_id": trace_id}
|
||||
return {}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue