8d1727b498
Adds a new specialist agent that gives the AI system control over its own infrastructure: - sysops_tools.py: docker SDK (ps/logs/restart) + git CLI (pull/status/log) + Odoo channel notifier for autonomous action broadcasts - sysops_agent.py: BaseAgent subclass handling on-demand chat requests, auto_heal() triggered by health failures, and sweep() for audits - Background auto-heal loop (main.py): runs every 2 minutes, calls _get_failing_systems() and triggers auto_heal() when degraded - health.py: extracted _get_failing_systems() helper reused by both the /health/detailed endpoint and the auto-heal loop - docker-compose.yml: mount docker socket + /root/odoo workspace + SSH keys for git authentication - Dockerfile: add git to apt-get - requirements.txt: add docker==7.1.0 Python SDK Auto-heal behavior: - Detects failing containers, restarts them, notifies all bot DM channels - Ollama (192.168.2.9) is flagged as external and skipped - On-demand via chat: "restart agent", "check logs", "pull latest code" Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
121 lines
3.3 KiB
Python
121 lines
3.3 KiB
Python
from __future__ import annotations
|
|
import asyncio
|
|
import logging
|
|
import time
|
|
|
|
from fastapi import APIRouter
|
|
from pydantic import BaseModel
|
|
|
|
logger = logging.getLogger(__name__)
|
|
router = APIRouter(prefix='/health', tags=['health'])
|
|
|
|
_start_time = time.time()
|
|
|
|
|
|
class HealthResponse(BaseModel):
|
|
status: str
|
|
uptime_seconds: float
|
|
|
|
|
|
class DetailedHealthResponse(BaseModel):
|
|
status: str
|
|
uptime_seconds: float
|
|
db: str
|
|
odoo: str
|
|
ollama: str
|
|
master_agent: str
|
|
privacy_mode: str
|
|
|
|
|
|
@router.get('', response_model=HealthResponse)
|
|
async def health():
|
|
return HealthResponse(status='ok', uptime_seconds=round(time.time() - _start_time, 1))
|
|
|
|
|
|
async def _get_failing_systems() -> list[str]:
|
|
"""Return a list of system names that are not reporting 'ok'."""
|
|
from ..app_state import get_db_pool, get_master_agent, get_llm_router
|
|
failing = []
|
|
|
|
pool = get_db_pool()
|
|
if not pool:
|
|
failing.append('db')
|
|
else:
|
|
try:
|
|
async with pool.acquire(timeout=5) as conn:
|
|
await conn.fetchval('SELECT 1')
|
|
except Exception:
|
|
failing.append('db')
|
|
|
|
master = get_master_agent()
|
|
if master is None:
|
|
failing.append('master_agent')
|
|
else:
|
|
if hasattr(master, '_odoo'):
|
|
try:
|
|
await asyncio.wait_for(master._odoo.ping(), timeout=5)
|
|
except Exception:
|
|
failing.append('odoo')
|
|
|
|
llm_router = get_llm_router()
|
|
if llm_router and hasattr(llm_router, '_ollama'):
|
|
try:
|
|
await asyncio.wait_for(llm_router._ollama.ping(), timeout=5)
|
|
except Exception:
|
|
failing.append('ollama')
|
|
|
|
return failing
|
|
|
|
|
|
@router.get('/detailed', response_model=DetailedHealthResponse)
|
|
async def health_detailed():
|
|
from ..app_state import get_db_pool, get_master_agent, get_llm_router
|
|
from ..config import get_settings
|
|
|
|
uptime = round(time.time() - _start_time, 1)
|
|
settings = get_settings()
|
|
|
|
# DB check
|
|
db_status = 'unavailable'
|
|
pool = get_db_pool()
|
|
if pool:
|
|
try:
|
|
async with pool.acquire(timeout=5) as conn:
|
|
await conn.fetchval('SELECT 1')
|
|
db_status = 'ok'
|
|
except Exception as exc:
|
|
db_status = f'error: {exc}'
|
|
|
|
# Odoo check
|
|
odoo_status = 'unavailable'
|
|
master = get_master_agent()
|
|
if master and hasattr(master, '_odoo'):
|
|
try:
|
|
await asyncio.wait_for(master._odoo.ping(), timeout=5)
|
|
odoo_status = 'ok'
|
|
except Exception as exc:
|
|
odoo_status = f'error: {exc}'
|
|
|
|
# Ollama check
|
|
ollama_status = 'unavailable'
|
|
llm_router = get_llm_router()
|
|
if llm_router and hasattr(llm_router, '_ollama'):
|
|
try:
|
|
await asyncio.wait_for(llm_router._ollama.ping(), timeout=5)
|
|
ollama_status = 'ok'
|
|
except Exception as exc:
|
|
ollama_status = f'error: {exc}'
|
|
|
|
master_status = 'ok' if master is not None else 'unavailable'
|
|
overall = 'ok' if all(s == 'ok' for s in [db_status, master_status]) else 'degraded'
|
|
|
|
return DetailedHealthResponse(
|
|
status=overall,
|
|
uptime_seconds=uptime,
|
|
db=db_status,
|
|
odoo=odoo_status,
|
|
ollama=ollama_status,
|
|
master_agent=master_status,
|
|
privacy_mode=settings.llm_privacy_mode,
|
|
)
|