feat: container monitoring backend core (PR-1)

- Add instance_events and health_checks tables with Alembic migration
- InstanceEventBus: typed pub/sub singleton with wildcard support
- HealthMonitor: async background loop polling containers every 15s
- SSE endpoint GET /events/stream with auth and connection limits
- Lifecycle hooks in tool_instances.py (create/start/stop/restart/delete)
- Structured JSON logging with correlation IDs
- 15 new unit tests (EventBus, HealthMonitor, MonitoringModels)

Quality gates: pytest 15 new passed, ruff clean
This commit is contained in:
2026-05-28 23:09:27 +02:00
parent 0fdbef578f
commit 4a7f24348c
26 changed files with 4142 additions and 11 deletions
+41 -8
View File
@@ -1,15 +1,52 @@
"""Structured JSON logging configuration."""
import json
import logging
import sys
import time
import traceback
from typing import Callable
from collections.abc import Callable
from fastapi import Request, Response
from starlette.middleware.base import BaseHTTPMiddleware
from src.services.correlation import get_correlation_id
logger = logging.getLogger(__name__)
class CorrelationIdFilter(logging.Filter):
"""Inject correlation_id into every log record from context var."""
def filter(self, record: logging.LogRecord) -> bool:
record.correlation_id = get_correlation_id() # type: ignore[attr-defined]
return True
class JSONFormatter(logging.Formatter):
"""Emit log records as single-line JSON."""
def format(self, record: logging.LogRecord) -> str:
log_obj: dict = {
"timestamp": self.formatTime(record),
"level": record.levelname,
"logger": record.name,
"message": record.getMessage(),
"correlation_id": getattr(record, "correlation_id", None),
}
# Optional extra fields
for key in ("instance_id", "event_type"):
value = getattr(record, key, None)
if value is not None:
log_obj[key] = value
if record.exc_info:
log_obj["exception"] = self.formatException(record.exc_info)
return json.dumps(log_obj, default=str)
def formatTime(self, record: logging.LogRecord, datefmt: str | None = None) -> str:
return time.strftime("%Y-%m-%dT%H:%M:%S", time.gmtime(record.created))
class RequestLoggingMiddleware(BaseHTTPMiddleware):
"""Log all HTTP requests with timing and status codes."""
@@ -17,7 +54,6 @@ class RequestLoggingMiddleware(BaseHTTPMiddleware):
start_time = time.time()
client_host = request.client.host if request.client else "unknown"
# Log the incoming request
logger.info(
"→ Request: %s %s (client: %s)",
request.method,
@@ -29,7 +65,6 @@ class RequestLoggingMiddleware(BaseHTTPMiddleware):
response = await call_next(request)
duration = time.time() - start_time
# Log the response
logger.info(
"← Response: %s %s%d (%dms)",
request.method,
@@ -69,15 +104,13 @@ class ExceptionLoggingMiddleware(BaseHTTPMiddleware):
def configure_logging(level: int = logging.INFO) -> None:
"""Configure structured logging for the application."""
formatter = logging.Formatter(
fmt="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
)
"""Configure structured JSON logging for the application."""
formatter = JSONFormatter()
# Console handler
console_handler = logging.StreamHandler(sys.stdout)
console_handler.setFormatter(formatter)
console_handler.addFilter(CorrelationIdFilter())
# Configure root logger
root_logger = logging.getLogger()