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>
2026-06-25 08:29:27 +02:00
parent c773dd7eae
commit 1f4c987652
13 changed files with 239 additions and 45 deletions
@@ -7,7 +7,7 @@ siehe Architektur-Plan (`docs/` bzw. der genehmigte Plan).
 Mission Control 2.0 (FastAPI + React/shadcn) · Hermes Agent + hermes-webui ·
 Shared Memory (SQLite via MCP). Jede Schicht hinter stabilem Vertrag austauschbar.

-## Status: Phase 4 (Hermes-Schicht — MC-Seite) ✅ · Box-Ausführung offen
+## Status: Phase 5 ✅ (Phasen 0–5 lokal fertig) · Box-Deploy/-Wiring + Cutover offen

 Fortschritt & Resume-Guide: siehe [`docs/STATUS.md`](docs/STATUS.md).

@@ -25,8 +25,12 @@ Fortschritt & Resume-Guide: siehe [`docs/STATUS.md`](docs/STATUS.md).
  `deploy/hermes-webui.service`, **Box-Runbook** [`docs/HERMES_SETUP.md`](docs/HERMES_SETUP.md)
  (hermes-webui, Brain=`auto`, Tools/MCP-Verdrahtung). Box-Ausführung steht noch aus.

+- **Phase 5** — **Backup** (Memory + Configs), **Services-Health** + Observability-Links,
+  **Theme-Toggle** (Hell/Dunkel). Box-Deploy/-Wiring + Cutover (Phase 6) brauchen die Box.
+
 API: `health · models · discover · fit · models/register · groups · routing · system/* · connect ·
 memory/* · agent/status` (Details in `docs/STATUS.md`). MCP: `mcp/` (siehe `mcp/requirements.txt`).
+Box-Runbooks: `docs/HERMES_SETUP.md` + `deploy/` (Units, deploy.sh, backup.sh).

 ## Entwickeln

@@ -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()
@@ -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)
@@ -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
@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+# Backup der Shared-Memory-SQLite + Configs (cron-bar auf der Box).
+# Behält die letzten 7 Snapshots. Identisch zur /api/system/backup-Logik.
+set -euo pipefail
+
+MODELS_DIR="${MC_MODELS_DIR:-/srv/models}"
+MEM_DB="${MC_MEMORY_DB:-$MODELS_DIR/mc2-memory.db}"
+LSWAP="${MC_CONFIG_PATH:-/etc/llama-swap/config.yaml}"
+GW="${MC_GATEWAY_CONFIG:-/opt/mission-control-2/gateway/config.yaml}"
+DEST="$MODELS_DIR/mc2-backups/$(date +%Y%m%d-%H%M%S)"
+
+mkdir -p "$DEST"
+for f in "$MEM_DB" "$MEM_DB-wal" "$MEM_DB-shm" "$LSWAP" "$GW"; do
+  [ -f "$f" ] && cp -p "$f" "$DEST/" || true
+done
+
+# nur die letzten 7 behalten
+ls -1dt "$MODELS_DIR"/mc2-backups/*/ 2>/dev/null | tail -n +8 | xargs -r rm -rf
+echo "OK — Backup unter $DEST"
@@ -24,7 +24,9 @@
 - [~] **Phase 4 — Hermes-Schicht:** MC-Seite ✅ (services/agent.py + /api/agent/status, AgentView mit
      Status-Tiles + „Hermes öffnen"), `deploy/hermes-webui.service`, **Runbook `docs/HERMES_SETUP.md`**.
      **Box-Ausführung offen** (hermes-webui installieren, Brain=auto, Tools/MCP verdrahten — Runbook).
- [ ] **Phase 5 — Betrieb/Observability/Politur** (Backup, LiteLLM-Traces, Health). 
+- [x] **Phase 5 — Betrieb/Observability/Politur:** Backup (Memory-SQLite + Configs, retain 7;
+      `/api/system/backup` + `deploy/backup.sh`), Services-Health (`/api/system/services`), Observability-
+      Links (llama-swap /ui, Gateway), **Theme-Toggle Hell/Dunkel**. Lokal verifiziert.
 - [ ] **Phase 6 — Cutover** (/opt → v2, v1 aus). **Braucht Box.**
 - Offen aus Phase 0/1: **Box-Deploy** (Gitea-Repo da; Box-Setup als systemd-USER-Dienst noch offen),
  LiteLLM **Complexity-Auto-Router** gegen installierte Version verifizieren.
@@ -6,8 +6,8 @@
    <meta name="theme-color" content="#0d1117" />
    <link rel="manifest" href="/manifest.webmanifest" />
    <title>Mission Control 2.0</title>
-    <script type="module" crossorigin src="/assets/index-umMcKqw6.js"></script>
-    <link rel="stylesheet" crossorigin href="/assets/index-nVsgoG2p.css">
+    <script type="module" crossorigin src="/assets/index-BYe3GDjZ.js"></script>
+    <link rel="stylesheet" crossorigin href="/assets/index-CatWSvf4.css">
  </head>
  <body>
    <div id="root"></div>
@@ -1,5 +1,5 @@
 import { useEffect, useState } from "react"
-import { Command as CommandIcon } from "lucide-react"
+import { Command as CommandIcon, Moon, Sun } from "lucide-react"
 import { NAV, type ViewId } from "@/nav"
 import { CommandPalette } from "@/components/CommandPalette"
 import { ModelsView } from "@/views/ModelsView"
@@ -15,6 +15,7 @@ import { cn } from "@/lib/utils"
 export default function App() {
  const [view, setView] = useState<ViewId>("models")
  const [health, setHealth] = useState<Health | null>(null)
+  const [dark, setDark] = useState(() => localStorage.getItem("mc_theme") !== "light")

  useEffect(() => {
    const load = () => api<Health>("/api/health").then(setHealth).catch(() => setHealth(null))
@@ -23,6 +24,11 @@ export default function App() {
    return () => clearInterval(t)
  }, [])

+  useEffect(() => {
+    document.documentElement.classList.toggle("dark", dark)
+    localStorage.setItem("mc_theme", dark ? "dark" : "light")
+  }, [dark])
+
  const active = NAV.find((n) => n.id === view)!

  return (
@@ -78,6 +84,14 @@ export default function App() {
      <div className="flex min-w-0 flex-1 flex-col">
        <header className="flex h-14 shrink-0 items-center justify-between border-b border-border px-6">
          <div className="text-sm text-muted-foreground">{active.hint}</div>
+          <div className="flex items-center gap-2">
+          <button
+            onClick={() => setDark((d) => !d)}
+            className="flex h-8 w-8 items-center justify-center rounded-md border border-border text-muted-foreground hover:bg-accent"
+            title="Hell/Dunkel"
+          >
+            {dark ? <Sun className="h-3.5 w-3.5" /> : <Moon className="h-3.5 w-3.5" />}
+          </button>
          <button
            onClick={() => {
              const ev = new KeyboardEvent("keydown", { key: "k", metaKey: true })
@@ -89,6 +103,7 @@ export default function App() {
            <span>Springen</span>
            <kbd className="rounded bg-muted px-1.5 py-0.5 font-mono text-[10px]">⌘K</kbd>
          </button>
+          </div>
        </header>

        <main className="flex-1 overflow-y-auto p-6">
@@ -88,6 +88,11 @@ export interface SystemStatus {
  disk: { total: number; used: number; percent: number } | null
 }

+export interface ServicesResp {
+  services: { name: string; url: string; ok: boolean }[]
+  links: { engine_ui: string; gateway: string; hermes_webui: string }
+}
+
 export interface ConnectTool {
  label: string
  lang: string
@@ -1,5 +1,7 @@
 import { useEffect, useState } from "react"
-import { api, type SystemStatus } from "@/lib/api"
+import { ExternalLink, Save } from "lucide-react"
+import { api, type ServicesResp, type SystemStatus } from "@/lib/api"
+import { cn } from "@/lib/utils"

 function gb(b: number) {
  return (b / 1024 ** 3).toFixed(1)
@@ -22,15 +24,30 @@ function Bar({ label, percent, detail }: { label: string; percent: number; detai

 export function SystemView() {
  const [s, setS] = useState<SystemStatus | null>(null)
+  const [svc, setSvc] = useState<ServicesResp | null>(null)
  const [error, setError] = useState("")
+  const [backupMsg, setBackupMsg] = useState("")

  useEffect(() => {
-    const load = () => api<SystemStatus>("/api/system/status").then(setS).catch((e) => setError(String(e)))
+    const load = () => {
+      api<SystemStatus>("/api/system/status").then(setS).catch((e) => setError(String(e)))
+      api<ServicesResp>("/api/system/services").then(setSvc).catch(() => {})
+    }
    load()
    const t = setInterval(load, 3000)
    return () => clearInterval(t)
  }, [])

+  async function doBackup() {
+    setBackupMsg("…")
+    try {
+      const r = await api<{ ok: boolean; snapshot: string; files: string[] }>("/api/system/backup", { method: "POST" })
+      setBackupMsg(r.ok ? `Snapshot ${r.snapshot} (${r.files.length} Dateien)` : "Nichts zu sichern")
+    } catch (e) {
+      setBackupMsg(`Fehler: ${e}`)
+    }
+  }
+
  return (
    <div className="space-y-4">
      <div>
@@ -75,6 +92,38 @@ export function SystemView() {
          {s.temp.gpu != null && <span>GPU {s.temp.gpu} °C</span>}
        </div>
      )}
+
+      {/* Dienste-Health + Observability-Links */}
+      {svc && (
+        <div className="rounded-xl border border-border bg-card p-4">
+          <div className="mb-3 text-sm font-medium">Dienste</div>
+          <div className="grid gap-2 sm:grid-cols-2">
+            {svc.services.map((x) => (
+              <div key={x.name} className="flex items-center gap-2 text-sm">
+                <span className={cn("h-2 w-2 rounded-full", x.ok ? "bg-emerald-500" : "bg-amber-500")} />
+                <span>{x.name}</span>
+                <span className="ml-auto font-mono text-xs text-muted-foreground">{x.url}</span>
+              </div>
+            ))}
+          </div>
+          <div className="mt-3 flex flex-wrap gap-3 text-xs">
+            <a href={svc.links.engine_ui} target="_blank" rel="noopener" className="flex items-center gap-1 text-primary hover:underline">
+              <ExternalLink className="h-3 w-3" /> Engine-Logs (llama-swap /ui)
+            </a>
+            <a href={svc.links.gateway} target="_blank" rel="noopener" className="flex items-center gap-1 text-primary hover:underline">
+              <ExternalLink className="h-3 w-3" /> Gateway
+            </a>
+          </div>
+        </div>
+      )}
+
+      {/* Backup */}
+      <div className="flex items-center gap-3">
+        <button onClick={doBackup} className="flex items-center gap-1.5 rounded-md border border-border px-3 py-1.5 text-sm hover:bg-accent">
+          <Save className="h-3.5 w-3.5 text-primary" /> Backup jetzt
+        </button>
+        {backupMsg && <span className="text-xs text-muted-foreground">{backupMsg}</span>}
+      </div>
    </div>
  )
 }