unsloth/studio/backend/loggers/handlers.py
2026-06-15 17:03:00 +02:00

123 lines
3.7 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""Structured logging handlers and middleware.
LoggingMiddleware (request/response logging with timing),
filter_sensitive_data (structlog processor for sanitization), and
get_logger (factory for structured loggers).
"""
import re
import time
import structlog
from starlette.types import ASGIApp, Message, Receive, Scope, Send
from utils.native_path_leases import redact_native_paths
logger = structlog.get_logger(__name__)
_NATIVE_PATH_LEASE_RE = re.compile(
r"(?i)(\b(?:native_path_lease|nativePathLease)[\"']?\s*[:=]\s*[\"']?)[A-Za-z0-9_-]+\.[A-Za-z0-9_-]+"
)
_EXCLUDED_PATHS = {
"/api/train/status",
"/api/train/metrics",
"/api/train/hardware",
"/api/system",
}
_EXCLUDED_SUFFIXES = (
".png",
".jpg",
".jpeg",
".svg",
".ico",
".woff",
".woff2",
".ttf",
)
class LoggingMiddleware:
"""ASGI request logger that avoids BaseHTTPMiddleware streaming wrappers."""
def __init__(self, app: ASGIApp) -> None:
self.app = app
async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
if scope["type"] != "http":
await self.app(scope, receive, send)
return
path = scope["path"]
excluded = (
path in _EXCLUDED_PATHS
or path.startswith("/assets/")
or path.endswith(_EXCLUDED_SUFFIXES)
)
start_time = time.perf_counter()
status_code = 500
async def send_wrapper(message: Message) -> None:
nonlocal status_code
if message["type"] == "http.response.start":
status_code = message["status"]
await send(message)
try:
await self.app(scope, receive, send_wrapper)
except Exception as exc:
logger.error(
"request_failed",
path = path,
method = scope["method"],
status_code = status_code,
error = str(exc),
process_time_ms = round((time.perf_counter() - start_time) * 1000, 2),
exc_info = True,
)
raise
else:
if not excluded:
logger.info(
"request_completed",
method = scope["method"],
path = path,
status_code = status_code,
process_time_ms = round((time.perf_counter() - start_time) * 1000, 2),
)
def filter_sensitive_data(logger, method_name, event_dict):
"""Structlog processor to redact native path leases from logs."""
def filter_value(value):
if isinstance(value, str):
try:
value = redact_native_paths(value)
except Exception:
pass
value = _NATIVE_PATH_LEASE_RE.sub(r"\1<redacted native path lease>", value)
return value
elif isinstance(value, dict):
return {
k: "<redacted native path lease>"
if str(k).replace("_", "").lower() == "nativepathlease"
else filter_value(v)
for k, v in value.items()
}
elif isinstance(value, list):
return [filter_value(item) for item in value]
return value
return {
k: "<redacted native path lease>"
if str(k).replace("_", "").lower() == "nativepathlease"
else filter_value(v)
for k, v in event_dict.items()
}
def get_logger(name: str) -> structlog.BoundLogger:
"""Get a bound structured logger for a module (name is usually __name__)."""
return structlog.get_logger(name)