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

@@ -29,6 +29,7 @@ from app.utils.fail2ban_client import (
Fail2BanResponse,
)
from app.utils.fail2ban_response import ok, to_dict
from app.utils.log_sanitizer import sanitize_for_logging
log: structlog.stdlib.BoundLogger = structlog.get_logger()
@@ -500,8 +501,8 @@ async def start_daemon(start_cmd_parts: list[str]) -> bool:
"fail2ban_start_failed",
command=" ".join(start_cmd_parts),
returncode=process.returncode,
stdout=stdout.decode("utf-8", errors="replace"),
stderr=stderr.decode("utf-8", errors="replace"),
stdout=sanitize_for_logging(stdout.decode("utf-8", errors="replace")),
stderr=sanitize_for_logging(stderr.decode("utf-8", errors="replace")),
)
return False
log.info(

View File

@@ -0,0 +1,70 @@
"""Correlation ID context variable for distributed tracing.
This module provides a :class:`contextvars.ContextVar` that stores the correlation
ID for the current execution context. Background tasks inherit or explicitly set
the correlation ID to enable log correlation across request/task boundaries.
Usage in background tasks::
from app.utils.correlation import get_correlation_id, set_correlation_id
async def my_background_task(correlation_id: str) -> None:
token = set_correlation_id(correlation_id)
try:
log.info("task_started") # Logs include correlation_id
finally:
reset_correlation_id(token)
For APScheduler jobs, pass the correlation ID through kwargs and call
:func:`set_correlation_id` at the start of the async callback.
"""
from __future__ import annotations
from contextvars import ContextVar
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from contextvars import Token
#: Default correlation ID used when no parent request context exists.
_DEFAULT_BG_CORRELATION_ID: str = "bg-task"
#: ContextVar holding the current correlation ID.
correlation_id_var: ContextVar[str] = ContextVar(
"correlation_id",
default=_DEFAULT_BG_CORRELATION_ID,
)
def get_correlation_id() -> str:
"""Return the current correlation ID from context.
Returns:
The current correlation ID string. Returns ``"bg-task"`` if no
correlation ID has been set in the current context.
"""
return correlation_id_var.get()
def set_correlation_id(correlation_id: str) -> Token[str]:
"""Set the correlation ID for the current context.
Args:
correlation_id: The correlation ID to bind (typically passed from
the triggering request).
Returns:
A :class:`contextvars.Token` that must be passed to
:func:`reset_correlation_id` when the task completes.
"""
return correlation_id_var.set(correlation_id)
def reset_correlation_id(token: Token[str]) -> None:
"""Reset the correlation ID to its previous value.
Args:
token: The token returned by :func:`set_correlation_id`.
"""
correlation_id_var.reset(token)

View File

@@ -0,0 +1,50 @@
"""Log sanitization utilities for preventing sensitive data leakage.
All external output (subprocess, API responses, config data) passed to
structlog MUST be sanitized first. This module provides the canonical
sanitize_for_logging() function used across the codebase.
"""
from __future__ import annotations
import re
# Patterns for sensitive data that must never appear in logs.
_SENSITIVE_PATTERNS: list[tuple[re.Pattern[str], str]] = [
# Passwords: password=PASS, password:PASS, password = PASS, etc.
(re.compile(r"password[=:]\S+", re.IGNORECASE), "password=***"),
# API keys: api_key=X, api-key=X, APIKEY=X, etc.
(re.compile(r"api[_-]?key[=:]\S+", re.IGNORECASE), "api_key=***"),
# Auth tokens: token=X, token: X, etc.
(re.compile(r"token[=:]\S+", re.IGNORECASE), "token=***"),
# Authorization headers: Authorization: Bearer <token>
(re.compile(r"(?i)Authorization:\s*(?:Bearer\s+)?\S+"), "Authorization: ***"),
# Secret values: secret=X, secret: X
(re.compile(r"secret[=:]\S+", re.IGNORECASE), "secret=***"),
# Private keys: -----BEGIN (RSA/DSA/EC/OPENSSH) PRIVATE KEY-----
(re.compile(r"-----BEGIN +(?:RSA|DSA|EC|OPENSSH) +PRIVATE KEY-----"), "*** PRIVATE KEY ***"),
# AWS access keys: AKIA...
(re.compile(r"AKIA[0-9A-Z]{16}"), "AKIA***"),
# Generic secret= patterns
(re.compile(r"secret[_-]?key[=:]\S+", re.IGNORECASE), "secret_key=***"),
# Bearer tokens in Authorization headers
(re.compile(r"Bearer\s+[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+"), "Bearer ***"),
]
def sanitize_for_logging(text: str) -> str:
"""Remove sensitive data patterns from text before logging.
Applies a set of regex substitutions to strip passwords, API keys,
tokens, secrets, private keys, and other credential-like strings.
Substituted values are replaced with a fixed redaction marker.
Args:
text: Raw text that may contain sensitive data.
Returns:
Text with sensitive patterns replaced by ``***``.
"""
for pattern, replacement in _SENSITIVE_PATTERNS:
text = pattern.sub(replacement, text)
return text