cryptorugmunch
628c1d2a10
Some checks failed
CI / build (push) Failing after 3s
PHASE 2.3 (AUDIT-2026-Q3.md):
Task 1 — Wire-in Wave 3 (1 router mounted, 2 deferred):
- app.routers.unified_scanner_router mounted at /api/v2/scanner/* (2 routes:
POST /api/v2/scanner/token/scan, POST /api/v2/scanner/wallet/scan).
Refactored prefix from /api/v2 -> /api/v2/scanner to avoid future conflicts
with the v1 /api/v1/scanner/ stub.
- app.routers.unified_wallet_scanner DEFERRED (no router APIRouter attribute;
library module consumed by unified_scanner_router via get_wallet_scanner()).
- app.routers.admin_extensions DEFERRED (DORMANT per audit; 25 routes at
/api/v1/admin/* would shadow /api/v1/admin/alerts_webhook).
Task 2 — Archive 136 dead-code files to app/_archive/legacy_2026_07/:
- 73 routers in app/routers/ (reach graph showed zero reach into mount.py).
- 63 flat app/*.py (domain modules never imported by live code).
- 1 file RESTORED post-archive: app/routers/x402_bridge_health.py (caught by
tests/unit/test_bridge_health.py which directly imports it; reach graph
considered tests/ only as transitive reach — to be patched in next cycle).
Forced-LIVE (NOT archived per user directive):
- app/ai_pipeline_v3.py (3 importers in audit window, importers themselves DEAD)
- app/splade_bm25.py (LIVE via app.rag_service)
- app/wallet_manager_v2.py (LIVE via x402_enforcement, x402_tools, sweep_all, sweep_now)
- app/crypto_embeddings.py (NOT in audit ARCHIVE list; heavy import graph)
Verification (forward-import closure from mount.py + main.py + factory.py + lifespan.py):
- imports = 348 app.* modules
- reached = 194 files reachable from roots
- archive set = audit_dead (186) - reached - forced_live (4) - test_live (1) = 136
- Net delta: 136 files moved, 44,932 LOC reduction, 293->295 active routes (+2 from Wave 3)
pyproject.toml updates:
- setuptools.packages.find: added exclude for app._archive*
- ruff.extend-exclude: added "app/_archive/"
- mypy.exclude: added "app/_archive/"
Smoke test: pytest tests/ — 817 passed, 3 pre-existing failures unchanged
(0 new failures; 0 routes lost; all 4 forced-LIVE files still importable).
Restoration: git mv app/_archive/legacy_2026_07/<name>.py <original-path>
and add the import to app/mount.py ROUTER_MODULES.
Refs: AUDIT-2026-Q3.md /home/dev/pry/rmi-final-deadcode-2026-07-06.md
84 lines
3 KiB
Python
84 lines
3 KiB
Python
"""Auto-Healing Infrastructure - self-diagnosing, self-repairing platform."""
|
|
|
|
import os
|
|
from datetime import UTC, datetime
|
|
|
|
import httpx
|
|
import psutil
|
|
from fastapi import APIRouter
|
|
|
|
router = APIRouter(prefix="/api/v1/health", tags=["auto-healing"])
|
|
|
|
BACKEND = os.getenv("BACKEND_URL", "http://localhost:8000")
|
|
CHECKS = [
|
|
("redis", "http://localhost:6379", "Redis"),
|
|
("postgres", "http://localhost:5432", "Postgres"),
|
|
("ollama", "http://localhost:11434/api/tags", "Ollama"),
|
|
("backend", f"{BACKEND}/health", "RMI Backend"),
|
|
("clickhouse", "http://localhost:8123/ping", "ClickHouse"),
|
|
("qdrant", "http://localhost:6333/health", "Qdrant"),
|
|
]
|
|
|
|
|
|
@router.get("/full")
|
|
async def full_health_check():
|
|
"""Comprehensive system health check - all services."""
|
|
results = {}
|
|
all_healthy = True
|
|
|
|
async with httpx.AsyncClient(timeout=5) as c:
|
|
for name, url, label in CHECKS:
|
|
try:
|
|
r = await c.get(url)
|
|
healthy = r.status_code < 500
|
|
except Exception:
|
|
healthy = False
|
|
|
|
results[name] = {"service": label, "healthy": healthy, "last_checked": datetime.now(UTC).isoformat()}
|
|
if not healthy:
|
|
all_healthy = False
|
|
|
|
# System resources
|
|
mem = psutil.virtual_memory()
|
|
disk = psutil.disk_usage("/")
|
|
|
|
return {
|
|
"overall": "HEALTHY" if all_healthy else "DEGRADED",
|
|
"timestamp": datetime.now(UTC).isoformat(),
|
|
"services": results,
|
|
"system": {
|
|
"cpu_pct": psutil.cpu_percent(interval=1),
|
|
"memory_pct": mem.percent,
|
|
"memory_available_gb": round(mem.available / (1024**3), 1),
|
|
"disk_pct": disk.percent,
|
|
"disk_free_gb": round(disk.free / (1024**3), 1),
|
|
"swap_pct": psutil.swap_memory().percent,
|
|
},
|
|
"alerts": _check_alerts(mem, disk),
|
|
}
|
|
|
|
|
|
def _check_alerts(mem, disk) -> list:
|
|
"""Generate alerts for concerning metrics."""
|
|
alerts = []
|
|
if mem.percent > 90:
|
|
alerts.append({"level": "CRITICAL", "msg": f"Memory usage at {mem.percent}% - consider restarting services"})
|
|
elif mem.percent > 80:
|
|
alerts.append({"level": "WARNING", "msg": f"Memory usage at {mem.percent}%"})
|
|
if disk.percent > 90:
|
|
alerts.append({"level": "CRITICAL", "msg": f"Disk usage at {disk.percent}% - prune logs immediately"})
|
|
elif disk.percent > 80:
|
|
alerts.append({"level": "WARNING", "msg": f"Disk usage at {disk.percent}%"})
|
|
return alerts
|
|
|
|
|
|
@router.post("/heal/{service}")
|
|
async def heal_service(service: str):
|
|
"""Attempt to heal a failed service."""
|
|
if service == "backend":
|
|
os.system("docker restart rmi-backend")
|
|
return {"service": service, "action": "restarted", "note": "Backend restart initiated"}
|
|
if service == "redis":
|
|
os.system("docker restart rmi-redis")
|
|
return {"service": service, "action": "restarted"}
|
|
return {"service": service, "action": "unknown", "note": "Manual intervention required"}
|