fix: remove hardcoded service URLs, require ENV config
Build and Push / build (release) Successful in 29s
Build and Push / build (release) Successful in 29s
- Remove hardcoded default URLs (portainer, npm, ollama, etc.) - All external service URLs now required via ENV vars - Remove obsolete ai_client and ai_controller (core-ai proxy) - Clean up health_controller obsolete core-ai references - App fails fast at startup if required config missing 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Claude Opus 4.5
@@ -1,197 +0,0 @@
|
||||
"""
|
||||
Core-AI HTTP Client
|
||||
|
||||
Provides interface to Core-AI service for AI performance metrics.
|
||||
"""
|
||||
import httpx
|
||||
from typing import Optional, Dict, List, Any
|
||||
from src.logging_config import get_logger
|
||||
from src.config import get_settings
|
||||
|
||||
logger = get_logger(__name__)
|
||||
settings = get_settings()
|
||||
|
||||
|
||||
class CoreAIClient:
|
||||
"""
|
||||
HTTP client for Core-AI service
|
||||
|
||||
Provides access to AI performance metrics, tool execution stats,
|
||||
and memory system monitoring.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
base_url: Optional[str] = None,
|
||||
timeout: int = 10
|
||||
):
|
||||
"""
|
||||
Initialize Core-AI client
|
||||
|
||||
Args:
|
||||
base_url: Core-AI base URL (default from settings)
|
||||
timeout: Request timeout in seconds
|
||||
"""
|
||||
self.base_url = (base_url or getattr(settings, 'core_ai_base_url', 'http://core-ai:8086')).rstrip("/")
|
||||
self.timeout = timeout
|
||||
self.client = httpx.AsyncClient(timeout=self.timeout)
|
||||
|
||||
async def close(self):
|
||||
"""Close the HTTP client"""
|
||||
await self.client.aclose()
|
||||
|
||||
async def health_check(self) -> bool:
|
||||
"""
|
||||
Check if Core-AI service is accessible
|
||||
|
||||
Returns:
|
||||
True if accessible, False otherwise
|
||||
"""
|
||||
try:
|
||||
response = await self.client.get(f"{self.base_url}/health")
|
||||
return response.status_code == 200
|
||||
except Exception as e:
|
||||
logger.error(f"Core-AI health check failed: {e}")
|
||||
return False
|
||||
|
||||
async def get_metrics(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get comprehensive AI performance metrics
|
||||
|
||||
Returns:
|
||||
Dict with agent performance, tool execution, memory stats
|
||||
|
||||
Example:
|
||||
{
|
||||
"uptime_seconds": 3600,
|
||||
"timestamp": "2025-12-03T20:00:00Z",
|
||||
"agent": {
|
||||
"total_requests": 100,
|
||||
"avg_response_time_ms": 1250.5,
|
||||
"p95_response_time_ms": 3200.0,
|
||||
...
|
||||
},
|
||||
"tools": {
|
||||
"total_calls": 250,
|
||||
"success_rate": 0.98,
|
||||
"top_tools": {...}
|
||||
},
|
||||
"memory": {
|
||||
"tier1_hit_rate": 0.85,
|
||||
...
|
||||
},
|
||||
...
|
||||
}
|
||||
"""
|
||||
try:
|
||||
response = await self.client.get(f"{self.base_url}/metrics")
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except httpx.HTTPStatusError as e:
|
||||
logger.error(f"Failed to get metrics: HTTP {e.response.status_code}")
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get metrics: {e}")
|
||||
raise
|
||||
|
||||
async def get_recent_errors(self, limit: int = 20) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Get recent request errors
|
||||
|
||||
Args:
|
||||
limit: Maximum number of errors to return
|
||||
|
||||
Returns:
|
||||
List of error records with timestamps
|
||||
|
||||
Example:
|
||||
[
|
||||
{
|
||||
"timestamp": "2025-12-03T19:45:12Z",
|
||||
"agent_type": "pydantic",
|
||||
"error": "Connection timeout",
|
||||
"duration_ms": 5000
|
||||
},
|
||||
...
|
||||
]
|
||||
"""
|
||||
try:
|
||||
response = await self.client.get(
|
||||
f"{self.base_url}/metrics/errors",
|
||||
params={"limit": limit}
|
||||
)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
return data.get("errors", [])
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get recent errors: {e}")
|
||||
raise
|
||||
|
||||
async def get_tool_failures(self, limit: int = 20) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Get recent tool execution failures
|
||||
|
||||
Args:
|
||||
limit: Maximum number of failures to return
|
||||
|
||||
Returns:
|
||||
List of tool failure records
|
||||
|
||||
Example:
|
||||
[
|
||||
{
|
||||
"timestamp": "2025-12-03T19:50:30Z",
|
||||
"tool_name": "list_containers",
|
||||
"error": "Connection refused",
|
||||
"duration_ms": 150
|
||||
},
|
||||
...
|
||||
]
|
||||
"""
|
||||
try:
|
||||
response = await self.client.get(
|
||||
f"{self.base_url}/metrics/tool-failures",
|
||||
params={"limit": limit}
|
||||
)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
return data.get("failures", [])
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get tool failures: {e}")
|
||||
raise
|
||||
|
||||
async def reset_metrics(self) -> bool:
|
||||
"""
|
||||
Reset all metrics (admin operation)
|
||||
|
||||
Returns:
|
||||
True if successful
|
||||
"""
|
||||
try:
|
||||
response = await self.client.post(f"{self.base_url}/metrics/reset")
|
||||
response.raise_for_status()
|
||||
logger.info("Successfully reset Core-AI metrics")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to reset metrics: {e}")
|
||||
raise
|
||||
|
||||
async def __aenter__(self):
|
||||
"""Async context manager entry"""
|
||||
return self
|
||||
|
||||
async def __aexit__(self, exc_type, exc_val, exc_tb):
|
||||
"""Async context manager exit"""
|
||||
await self.close()
|
||||
|
||||
|
||||
# Singleton instance
|
||||
_ai_client: Optional[CoreAIClient] = None
|
||||
|
||||
|
||||
def get_ai_client() -> CoreAIClient:
|
||||
"""Get singleton Core-AI client instance"""
|
||||
global _ai_client
|
||||
if _ai_client is None:
|
||||
_ai_client = CoreAIClient()
|
||||
return _ai_client
|
||||
Reference in New Issue
Block a user