feat(2.0): Phase 5 — Betrieb, Observability + Politur

Backup: services/backup.py (Memory-SQLite inkl. WAL/SHM + Configs, retain 7)
+ deploy/backup.sh + POST /api/system/backup + GET /api/system/backups.
Services-Health: GET /api/system/services (aggregierte Reachability +
Observability-Links). Frontend: SystemView mit Dienste-Health + Backup-
Button + Links; Theme-Toggle (Hell/Dunkel, persistent).

Lokal verifiziert: Backup-Snapshot + services-Aggregat (TestClient),
Frontend-Build + Browser (Light-Mode bestaetigt via computed styles).
Damit Phasen 0-5 lokal fertig. Docs aktualisiert.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/config.py

@@ -52,7 +52,7 @@ PORT = int(os.environ.get("MC_PORT", "9000"))
 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-phase4"
+VERSION = "2.0.0-phase5"
 
 # Gemeinsame YAML-Instanz (preserve_quotes hält Kommentare/Quotes in config.yaml).
 yaml = YAML()

backend/routers/system.py

@@ -11,6 +11,11 @@ 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")
@@ -26,6 +31,35 @@ 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()
+    return {
+        "services": [
+            {"name": "Engine (llama-swap)", "url": LLAMA_SWAP_URL, "ok": engine_reachable()},
+            {"name": "Gateway (LiteLLM)", "url": GATEWAY_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": GATEWAY_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)

backend/services/backup.py

@@ -0,0 +1,51 @@
+"""
+Backup der „Verfassung" (Shared-Memory-SQLite) + aller Configs.
+Snapshot in einen Zeitstempel-Ordner; die letzten N bleiben erhalten.
+"""
+
+import shutil
+import time
+from pathlib import Path
+
+from config import CONFIG_PATH, GATEWAY_CONFIG_PATH, MEMORY_DB, MODELS_DIR
+
+BACKUP_DIR = Path(MODELS_DIR) / "mc2-backups"
+RETAIN = 7
+
+
+def _safe_copy(src: Path, dst_dir: Path) -> str | None:
+    try:
+        if src and src.exists():
+            shutil.copy2(src, dst_dir / src.name)
+            return src.name
+    except Exception:
+        pass
+    return None
+
+
+def backup_now() -> dict:
+    """Erstellt einen Snapshot (Memory-DB inkl. WAL/SHM + Configs). Alte Snapshots
+    über RETAIN hinaus werden entfernt."""
+    ts = time.strftime("%Y%m%d-%H%M%S")
+    dst = BACKUP_DIR / ts
+    dst.mkdir(parents=True, exist_ok=True)
+    saved = []
+    for src in (MEMORY_DB, Path(str(MEMORY_DB) + "-wal"), Path(str(MEMORY_DB) + "-shm"),
+                CONFIG_PATH, GATEWAY_CONFIG_PATH):
+        if (name := _safe_copy(src, dst)):
+            saved.append(name)
+    # Aufräumen: nur die letzten RETAIN Snapshots behalten.
+    snaps = sorted([p for p in BACKUP_DIR.iterdir() if p.is_dir()], reverse=True)
+    for old in snaps[RETAIN:]:
+        shutil.rmtree(old, ignore_errors=True)
+    return {"ok": bool(saved), "snapshot": ts, "files": saved, "dir": str(dst)}
+
+
+def list_backups() -> list[dict]:
+    if not BACKUP_DIR.exists():
+        return []
+    out = []
+    for p in sorted([d for d in BACKUP_DIR.iterdir() if d.is_dir()], reverse=True):
+        files = [f.name for f in p.iterdir() if f.is_file()]
+        out.append({"snapshot": p.name, "files": files})
+    return out