Update observability docs and task utilities

- Add Observability.md documentation
- Standardize task logging with correlation_id support
- Add log_sanitizer utility for PII masking
- Update Tasks.md tracking
- Update geo_cache tasks and other task modules with correlation_id

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
2026-05-03 11:52:09 +02:00
parent 7b93499551
commit 0133489920
17 changed files with 582 additions and 124 deletions

View File

@@ -7,16 +7,21 @@ After Task 2 removed geo cache writes from GET requests, newly resolved IPs
are only held in the in-memory cache until this task flushes them. With the
default 60-second interval, at most one minute of new resolution results is
at risk on an unexpected process restart.
Correlation IDs are propagated through the task using :mod:`app.utils.correlation`
so that task logs can be correlated across runs.
"""
from __future__ import annotations
import uuid
from typing import TYPE_CHECKING
import structlog
from app.tasks.db import task_db
from app.tasks.timeout_utils import run_with_timeout
from app.utils.correlation import get_correlation_id, reset_correlation_id, set_correlation_id
from app.utils.runtime_state import get_effective_settings
if TYPE_CHECKING:
@@ -37,20 +42,37 @@ JOB_ID: str = "geo_cache_flush"
TASK_TIMEOUT_SECONDS: int = 60
async def _run_flush_with_resources(geo_cache: GeoCache, settings: Settings) -> None:
async def _run_flush_with_resources(
geo_cache: GeoCache,
settings: Settings,
correlation_id: str | None = None,
) -> None:
"""Flush the geo cache dirty set to the application database.
Args:
geo_cache: The application's GeoCache instance.
settings: The resolved application settings used for database access.
correlation_id: Optional correlation ID for log correlation.
"""
if correlation_id is None:
correlation_id = str(uuid.uuid4())
token = set_correlation_id(correlation_id)
try:
await _do_flush_with_resources(geo_cache, settings)
finally:
reset_correlation_id(token)
async def _do_flush_with_resources(geo_cache: GeoCache, settings: Settings) -> None:
"""Inner flush logic that runs with correlation context set."""
async def _do_flush() -> None:
async with task_db(settings) as db:
count = await geo_cache.flush_dirty(db)
if count > 0:
log.debug("geo_cache_flush_ran", flushed=count)
log.debug("geo_cache_flush_ran", correlation_id=get_correlation_id(), flushed=count)
await run_with_timeout("geo_cache_flush", _do_flush(), TASK_TIMEOUT_SECONDS)