feat(2.0): Phase 0 — Greenfield-Skeleton (FastAPI + React/shadcn)
Backend: FastAPI mit /api/health + /api/models (read-only aus llama-swap config, Logik aus v1 portiert). Frontend: Vite + React + Tailwind v4 + shadcn-Style App-Shell mit Cmd+K, Dark-default, PWA-Manifest; Modelle-View live aus /api/models. Deploy-Geruest (systemd-Unit :9001, build/deploy- Skripte, NOPASSWD-sudoers, kein Klartext-Passwort). Verifiziert: Backend-Endpunkte + Frontend-Build + gerenderte Shell. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
@@ -0,0 +1,50 @@
|
||||
"""
|
||||
Mission Control 2.0 — dünner FastAPI-Einstieg.
|
||||
|
||||
Hängt die Router ein, liefert (in Prod) das gebaute React-Frontend aus und
|
||||
setzt eine no-cache-Middleware. Im Dev läuft das Frontend über den Vite-Dev-
|
||||
Server (proxyt /api hierher), daher CORS für localhost offen.
|
||||
"""
|
||||
|
||||
from fastapi import FastAPI
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.responses import FileResponse
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
from starlette.requests import Request
|
||||
|
||||
from config import FRONTEND_DIST, VERSION
|
||||
from routers import health, models
|
||||
|
||||
app = FastAPI(title="Mission Control 2.0", version=VERSION)
|
||||
|
||||
# Dev: Vite-Dev-Server (5173) ruft das Backend per /api auf.
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["http://localhost:5173", "http://127.0.0.1:5173"],
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
|
||||
@app.middleware("http")
|
||||
async def no_cache(request: Request, call_next):
|
||||
resp = await call_next(request)
|
||||
if request.url.path.startswith("/api"):
|
||||
resp.headers["Cache-Control"] = "no-cache"
|
||||
return resp
|
||||
|
||||
|
||||
app.include_router(health.router)
|
||||
app.include_router(models.router)
|
||||
|
||||
|
||||
# Prod: gebautes Frontend ausliefern (falls vorhanden). SPA-Fallback auf index.html.
|
||||
if FRONTEND_DIST.exists():
|
||||
app.mount("/assets", StaticFiles(directory=FRONTEND_DIST / "assets"), name="assets")
|
||||
|
||||
@app.get("/{full_path:path}")
|
||||
def spa(full_path: str):
|
||||
index = FRONTEND_DIST / "index.html"
|
||||
if index.exists():
|
||||
return FileResponse(index)
|
||||
return {"detail": "frontend not built"}
|
||||
@@ -0,0 +1,34 @@
|
||||
"""
|
||||
Zentrale Konfiguration für Mission Control 2.0.
|
||||
|
||||
Eine Quelle der Wahrheit für Pfade, URLs und Defaults — alles über Env-Vars
|
||||
überschreibbar. Bewusst schlank: MC 2.0 ist ein Glue-Cockpit, das vorhandene
|
||||
Dienste (llama-swap, LiteLLM-Gateway, Hermes) steuert, statt sie nachzubauen.
|
||||
"""
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from ruamel.yaml import YAML
|
||||
|
||||
# --- Engine (llama-swap) -----------------------------------------------------
|
||||
LLAMA_SWAP_URL = os.environ.get("MC_LLAMA_SWAP_URL", "http://127.0.0.1:8080").rstrip("/")
|
||||
CONFIG_PATH = Path(os.environ.get("MC_CONFIG_PATH", "/etc/llama-swap/config.yaml"))
|
||||
MODELS_DIR = Path(os.environ.get("MC_MODELS_DIR", "/srv/models"))
|
||||
|
||||
# --- Routing-Gateway (LiteLLM, model: auto) ----------------------------------
|
||||
GATEWAY_URL = os.environ.get("MC_GATEWAY_URL", "http://127.0.0.1:4000").rstrip("/")
|
||||
|
||||
# --- Server ------------------------------------------------------------------
|
||||
HOST = os.environ.get("MC_HOST", "0.0.0.0")
|
||||
PORT = int(os.environ.get("MC_PORT", "9000"))
|
||||
# Gebautes React-Frontend (frontend/dist). In Prod liefert FastAPI es statisch aus;
|
||||
# im Dev läuft der Vite-Dev-Server separat und proxyt /api hierher.
|
||||
FRONTEND_DIST = Path(os.environ.get("MC_FRONTEND_DIST", str(Path(__file__).resolve().parent.parent / "frontend" / "dist")))
|
||||
|
||||
# Version (Phase 0 — Greenfield-Skeleton).
|
||||
VERSION = "2.0.0-phase0"
|
||||
|
||||
# Gemeinsame YAML-Instanz (preserve_quotes hält Kommentare/Quotes in config.yaml).
|
||||
yaml = YAML()
|
||||
yaml.preserve_quotes = True
|
||||
@@ -0,0 +1,4 @@
|
||||
fastapi>=0.115
|
||||
uvicorn[standard]>=0.30
|
||||
httpx>=0.27
|
||||
ruamel.yaml>=0.18
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Health-/Status-Endpoint — schlanker Lebenszeichen-Check für MC 2.0."""
|
||||
|
||||
from fastapi import APIRouter
|
||||
|
||||
from config import VERSION
|
||||
from services import llamaswap
|
||||
|
||||
router = APIRouter(prefix="/api")
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
def health() -> dict:
|
||||
return {
|
||||
"status": "ok",
|
||||
"version": VERSION,
|
||||
"engine_reachable": llamaswap.engine_reachable(),
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
"""Modelle-Endpoint (Phase 0: read-only Liste aus der llama-swap config.yaml)."""
|
||||
|
||||
from fastapi import APIRouter
|
||||
|
||||
from services import llamaswap
|
||||
|
||||
router = APIRouter(prefix="/api")
|
||||
|
||||
|
||||
@router.get("/models")
|
||||
def models() -> dict:
|
||||
items = llamaswap.list_models()
|
||||
return {"models": items, "count": len(items)}
|
||||
@@ -0,0 +1,94 @@
|
||||
"""
|
||||
Engine-Service: liest die llama-swap config.yaml (read-only in Phase 0) und
|
||||
spricht die llama-swap-API (/v1/models, /running). Schreiblogik (Modelle
|
||||
installieren, Gruppen/Routing verwalten) kommt in Phase 1.
|
||||
|
||||
Logik portiert aus Mission Control v1 (llamaswap.py + routers/models.py),
|
||||
auf das Nötigste reduziert.
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
|
||||
import httpx
|
||||
|
||||
from config import CONFIG_PATH, LLAMA_SWAP_URL, yaml
|
||||
|
||||
# Kanonische Rollen (vereinheitlicht ggü. v1: kein manager/reviewer mehr).
|
||||
# Eine Quelle der Wahrheit — Capability-Erkennung läuft separat über model_caps (Phase 1).
|
||||
ROLE_IDS = {"vision", "coder", "reasoning", "agent", "scout"}
|
||||
|
||||
_CTX_RE = re.compile(r"-(?:c|-ctx-size)\s+(\d+)")
|
||||
_PATH_RE = re.compile(r"-(?:m|-model)\s+([^\s]+)")
|
||||
_QUANT_RE = re.compile(r"(Q\d_[A-Z0-9_]+|IQ\d_[A-Z0-9_]+|fp16|bf16)\.gguf", re.IGNORECASE)
|
||||
|
||||
|
||||
def read_config() -> dict:
|
||||
"""llama-swap config.yaml laden. Existiert sie nicht (z.B. lokaler Dev-PC
|
||||
ohne Engine), wird ein leeres Modell-Set zurückgegeben statt zu werfen."""
|
||||
if not CONFIG_PATH.exists():
|
||||
return {"models": {}}
|
||||
with CONFIG_PATH.open("r", encoding="utf-8") as f:
|
||||
data = yaml.load(f) or {}
|
||||
if not data.get("models"):
|
||||
data["models"] = {}
|
||||
return data
|
||||
|
||||
|
||||
def _parse_model(name: str, spec: dict) -> dict:
|
||||
"""Ein config.yaml-Modell in ein flaches UI-Objekt übersetzen."""
|
||||
spec = spec or {}
|
||||
cmd = str(spec.get("cmd", "")).strip()
|
||||
|
||||
ctx = None
|
||||
if (m := _CTX_RE.search(cmd)):
|
||||
ctx = int(m.group(1))
|
||||
|
||||
path = ""
|
||||
filename = ""
|
||||
quant = ""
|
||||
size_bytes = None
|
||||
if (m := _PATH_RE.search(cmd)):
|
||||
path = m.group(1).replace("'", "").replace('"', "")
|
||||
filename = os.path.basename(path)
|
||||
if os.path.exists(path):
|
||||
size_bytes = os.path.getsize(path)
|
||||
if (q := _QUANT_RE.search(path)):
|
||||
quant = q.group(1).upper()
|
||||
|
||||
aliases = spec.get("aliases") or []
|
||||
if isinstance(aliases, str):
|
||||
aliases = [aliases]
|
||||
aliases = [str(a) for a in aliases]
|
||||
# Rolle = erster Alias; Legacy-Fallback: Key selbst ist eine Rolle.
|
||||
role = aliases[0].lower() if aliases else (name.lower() if name.lower() in ROLE_IDS else None)
|
||||
|
||||
return {
|
||||
"name": name,
|
||||
"role": role,
|
||||
"aliases": aliases,
|
||||
"api_ids": [name] + aliases,
|
||||
"ctx": ctx,
|
||||
"ttl": spec.get("ttl"),
|
||||
"cmd": cmd,
|
||||
"filename": filename,
|
||||
"quant": quant,
|
||||
"size_bytes": size_bytes,
|
||||
# "incomplete" = Eintrag ohne hinterlegtes Modell (-m), z.B. Platzhalter.
|
||||
"incomplete": not path,
|
||||
}
|
||||
|
||||
|
||||
def list_models() -> list[dict]:
|
||||
"""Alle in der config.yaml konfigurierten Modelle (read-only)."""
|
||||
cfg = read_config()
|
||||
return [_parse_model(name, spec) for name, spec in (cfg.get("models") or {}).items()]
|
||||
|
||||
|
||||
def engine_reachable() -> bool:
|
||||
"""Ist die llama-swap-API erreichbar?"""
|
||||
try:
|
||||
with httpx.Client(timeout=3.0) as c:
|
||||
return c.get(f"{LLAMA_SWAP_URL}/v1/models").status_code == 200
|
||||
except Exception:
|
||||
return False
|
||||
Reference in New Issue
Block a user