Hitonabi
154 lines
5.0 KiB
Python
154 lines
5.0 KiB
Python
"""System-Endpoints: Live-Status + Wartung (Restart/Self-Update — auf der Box).
|
|
|
|
Wartung läuft als systemd-USER-Dienst → KEIN sudo/Passwort (Nordstern).
|
|
Lokal (Windows) schlagen die Shell-Befehle harmlos fehl und werden als Fehler
|
|
zurückgegeben statt zu crashen.
|
|
"""
|
|
|
|
import os
|
|
import subprocess
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel
|
|
|
|
from config import GATEWAY_URL, HERMES_API_URL, HERMES_WEBUI_URL, LLAMA_SWAP_URL
|
|
from services import backup as backup_svc
|
|
from services.agent import agent_status
|
|
from services.gateway import gateway_reachable
|
|
from services.llamaswap import engine_reachable
|
|
from services.system import system_status
|
|
|
|
router = APIRouter(prefix="/api")
|
|
|
|
# Nur diese User-Dienste dürfen neugestartet werden.
|
|
ALLOWED_SERVICES = {"mission-control-2", "hermes-gateway", "hermes-webui"}
|
|
# Quelle für Self-Update (auf der Box ~/mission-control-v2).
|
|
SOURCE_DIR = os.path.expanduser(os.environ.get("MC2_SOURCE_DIR", "~/mission-control-v2"))
|
|
|
|
|
|
@router.get("/system/status")
|
|
def status() -> dict:
|
|
return system_status()
|
|
|
|
|
|
@router.get("/system/services")
|
|
def services() -> dict:
|
|
"""Aggregierte Erreichbarkeit aller Stack-Dienste (für die Health-Anzeige)."""
|
|
a = agent_status()
|
|
gw_url = f"{GATEWAY_URL}/v1"
|
|
return {
|
|
"services": [
|
|
{"name": "Engine (llama-swap)", "url": LLAMA_SWAP_URL, "ok": engine_reachable()},
|
|
{"name": "Gateway (integriert)", "url": gw_url, "ok": gateway_reachable()},
|
|
{"name": "Hermes-Gateway", "url": HERMES_API_URL, "ok": a["gateway_reachable"]},
|
|
{"name": "Hermes-WebUI", "url": HERMES_WEBUI_URL, "ok": a["webui_reachable"]},
|
|
],
|
|
"links": {
|
|
"engine_ui": f"{LLAMA_SWAP_URL}/ui",
|
|
"gateway": gw_url,
|
|
"hermes_webui": HERMES_WEBUI_URL,
|
|
},
|
|
}
|
|
|
|
|
|
@router.post("/system/backup")
|
|
def backup() -> dict:
|
|
return backup_svc.backup_now()
|
|
|
|
|
|
@router.get("/system/backups")
|
|
def backups() -> dict:
|
|
return {"backups": backup_svc.list_backups()}
|
|
|
|
|
|
def _run(cmd: list[str], cwd: str | None = None) -> dict:
|
|
try:
|
|
p = subprocess.run(cmd, cwd=cwd, capture_output=True, text=True, timeout=180)
|
|
return {"ok": p.returncode == 0, "code": p.returncode,
|
|
"out": (p.stdout or "")[-2000:], "err": (p.stderr or "")[-2000:]}
|
|
except Exception as exc: # noqa: BLE001
|
|
return {"ok": False, "code": -1, "out": "", "err": str(exc)}
|
|
|
|
|
|
class RestartReq(BaseModel):
|
|
service: str
|
|
|
|
|
|
@router.post("/system/restart")
|
|
def restart(req: RestartReq) -> dict:
|
|
if req.service not in ALLOWED_SERVICES:
|
|
raise HTTPException(400, f"Dienst '{req.service}' nicht erlaubt.")
|
|
return _run(["systemctl", "--user", "restart", req.service])
|
|
|
|
|
|
@router.post("/system/self-update")
|
|
def self_update() -> dict:
|
|
"""git pull (Source) → venv-Deps → Dienst-Restart. Auf der Box; lokal Fehler."""
|
|
pull = _run(["git", "fetch", "--all"], cwd=SOURCE_DIR)
|
|
reset = _run(["git", "reset", "--hard", "origin/main"], cwd=SOURCE_DIR)
|
|
restart_res = _run(["systemctl", "--user", "restart", "mission-control-2"])
|
|
return {"pull": pull, "reset": reset, "restart": restart_res}
|
|
|
|
|
|
from services.token_stats import get_stats
|
|
from services.llamaswap import list_models
|
|
|
|
@router.get("/system/token-stats")
|
|
def token_stats() -> dict:
|
|
stats = get_stats()
|
|
p = stats.get("prompt_tokens", 0)
|
|
c = stats.get("completion_tokens", 0)
|
|
total = p + c
|
|
|
|
# Map model IDs and aliases to their respective roles for pricing resolution
|
|
role_map = {}
|
|
try:
|
|
for m in list_models():
|
|
role_map[m["name"].lower()] = m.get("role")
|
|
for alias in m.get("aliases", []):
|
|
role_map[alias.lower()] = m.get("role")
|
|
except Exception:
|
|
pass
|
|
|
|
# Dynamic pricing tiers based on model class in June 2026
|
|
PRICING = {
|
|
"heavy": (15.0, 75.0),
|
|
"coder": (3.0, 15.0),
|
|
"hermes": (1.0, 5.0),
|
|
"fast": (0.15, 0.60),
|
|
"scout": (0.15, 0.60),
|
|
"vision": (0.15, 0.60),
|
|
"reasoning": (0.15, 0.60),
|
|
}
|
|
|
|
modeled_p = 0
|
|
modeled_c = 0
|
|
saved_usd = 0.0
|
|
|
|
models_data = stats.get("models") or {}
|
|
for m_name, m_tokens in models_data.items():
|
|
mp = m_tokens.get("prompt", 0)
|
|
mc = m_tokens.get("completion", 0)
|
|
modeled_p += mp
|
|
modeled_c += mc
|
|
|
|
role = role_map.get(m_name, m_name)
|
|
rate_in, rate_out = PRICING.get(role, (0.15, 0.60))
|
|
saved_usd += (mp * rate_in + mc * rate_out) / 1_000_000.0
|
|
|
|
# Baseline/legacy tokens calculated at premium rates ($15.00 / $75.00)
|
|
# to preserve historical savings value prior to model-specific logging
|
|
baseline_p = max(0, p - modeled_p)
|
|
baseline_c = max(0, c - modeled_c)
|
|
saved_usd += (baseline_p * 15.0 + baseline_c * 75.0) / 1_000_000.0
|
|
|
|
saved_eur = saved_usd * 0.92 # 1 USD = 0.92 EUR
|
|
|
|
return {
|
|
"prompt_tokens": p,
|
|
"completion_tokens": c,
|
|
"total_tokens": total,
|
|
"saved_usd": round(saved_usd, 2),
|
|
"saved_eur": round(saved_eur, 2)
|
|
}
|