web done

Author: DataBoySu

health_monitor.py

@@ -1,5 +1,12 @@
 #!/usr/bin/env python3
-"""Cluster Health Monitor - Real-time GPU cluster monitoring."""
+"""Cluster Health Monitor - Real-time GPU cluster monitoring.
+
+Maintenance:
+- Purpose: CLI entrypoint and small web/server launcher for the project.
+- Debug: run `python health_monitor.py web` to start the server; check
+    `config.yaml` for configuration. If debugging collectors, import and
+    instantiate `monitor.collectors` classes directly.
+"""
 
 import asyncio
 import sys

monitor/__init__.py

@@ -1 +1,13 @@
-"""Monitor package."""
+"""Top-level package for Cluster Health Monitor.
+
+Expose high-level package metadata and commonly-used helpers so callers
+can import from ``monitor`` conveniently. Keep this file minimal to avoid
+heavy import costs at package import time.
+"""
+
+__all__ = [
+	'__version__',
+]
+
+# Package version — keep in sync with distribution metadata
+__version__ = '1.2.0'

monitor/alerting/__init__.py

@@ -1,4 +1,7 @@
-"""Monitor alerting package."""
+"""Alerting helpers for monitor.
+
+Re-export the alert engine for convenient imports.
+"""
 
 from .rules import AlertEngine
 

monitor/alerting/rules.py

@@ -1,4 +1,11 @@
-"""Alert rules engine for evaluating metrics against thresholds."""
+"""Alert rules engine for evaluating metrics against thresholds.
+
+Maintenance:
+- Purpose: encapsulate alert logic for GPU and system metrics.
+- Debug: if alerts are not firing, verify metric keys (e.g., 'gpus', 'temperature')
+    and the configuration passed to the engine. Alerts are returned as a list
+    of dictionaries and not persisted by this module.
+"""
 
 from datetime import datetime
 from typing import Dict, Any, List

monitor/api/__init__.py

@@ -1 +1,18 @@
-"""Monitor API package."""
+"""API package for the monitor web dashboard.
+
+Re-export the primary application factory and common module-level
+constants so callers can do::
+
+	from monitor.api import create_app
+
+Keep this file small to avoid importing heavy web framework code at
+package import time.
+"""
+
+from .server import create_app, TEMPLATE_DIR, STATIC_DIR
+
+__all__ = [
+	'create_app',
+	'TEMPLATE_DIR',
+	'STATIC_DIR',
+]

monitor/api/server.py

@@ -1,4 +1,12 @@
-"""FastAPI server for REST API and web dashboard."""
+"""FastAPI server for REST API and web dashboard.
+
+Maintenance:
+- Purpose: defines the web endpoints and WebSocket handlers used by the
+    dashboard UI and simulation features.
+- Debug: enable request logging and inspect `/api/*` endpoints; WebSocket
+    simulation frames are sent from the benchmark runner. If server fails to
+    start, check dependency imports (FastAPI, uvicorn) and configuration paths.
+"""
 
 from datetime import datetime, timedelta
 from pathlib import Path