Add persistent Athena music mode switching

platform/llama-dashboard/app.py

@@ -20,6 +20,7 @@ HOST = os.getenv("DASHBOARD_HOST", "0.0.0.0")
 PORT = int(os.getenv("DASHBOARD_PORT", "8099"))
 ROUTER_URL = os.getenv("ROUTER_URL", "http://router:8081").rstrip("/")
 ROUTER_API_KEY = os.getenv("ROUTER_API_KEY", "")
+MUSIC_UI_URL = os.getenv("MUSIC_UI_URL", "http://127.0.0.1:7861/")
 HOST_PROC = Path(os.getenv("HOST_PROC", "/host/proc"))
 HOST_DATA = os.getenv("HOST_DATA", "/host/data")
 HOST_MODELS = Path(os.getenv("HOST_MODELS", "/host/models"))
@@ -268,6 +269,27 @@ def router_status() -> tuple[dict[str, Any], str | None]:
         return {}, str(exc)
 
 
+def change_mode(mode: str) -> tuple[int, dict[str, Any]]:
+    if mode not in {"llm", "music"}:
+        return 400, {"error": "invalid mode"}
+    headers = {"Accept": "application/json", "Content-Type": "application/json"}
+    if ROUTER_API_KEY:
+        headers["Authorization"] = f"Bearer {ROUTER_API_KEY}"
+    request = urllib.request.Request(
+        f"{ROUTER_URL}/mode", data=json.dumps({"mode": mode}).encode(),
+        headers=headers, method="POST")
+    try:
+        with urllib.request.urlopen(request, timeout=15) as response:
+            return response.status, json.load(response)
+    except urllib.error.HTTPError as exc:
+        try:
+            return exc.code, json.loads(exc.read())
+        except (ValueError, json.JSONDecodeError):
+            return exc.code, {"error": str(exc)}
+    except (OSError, urllib.error.URLError) as exc:
+        return 503, {"error": str(exc)}
+
+
 _MODEL_LOCK = threading.Lock()
 _MODEL_AT = 0.0
 _MODEL_CACHE: tuple[list[dict[str, Any]], dict[str, Any]] = ([], {"count": 0, "total_size": 0})
@@ -602,9 +624,11 @@ HTML = r'''<!doctype html>
 .span4 .metrics{grid-template-columns:repeat(2,1fr)}
 .history-controls{display:flex;flex-wrap:wrap;gap:7px;margin:10px 0 14px}.history-controls button{border:1px solid var(--line);background:#09111b;color:var(--muted);padding:6px 10px;border-radius:8px;cursor:pointer}.history-controls button.active{color:var(--cyan);border-color:var(--cyan)}.chart-legend{display:flex;flex-wrap:wrap;gap:8px;margin:2px 0 10px}.chart-legend button{border:1px solid var(--series);background:#09111b;color:var(--text);padding:6px 10px;border-radius:8px;cursor:pointer}.chart-legend button::before{content:'';display:inline-block;width:10px;height:3px;background:var(--series);margin:0 7px 3px 0}.chart-legend button.off{opacity:.4;text-decoration:line-through}.chart{width:100%;height:250px;display:block}.token-total{font-size:24px;font-weight:750;margin-top:5px}.history-note{color:var(--muted);font-size:11px;margin-top:8px}
 .usage-list{display:grid;gap:13px;margin-top:8px}.usage-head{display:flex;justify-content:space-between;gap:14px;align-items:baseline}.usage-head b{font-size:16px}.usage-head span{color:var(--muted)}.usage-meta{display:flex;justify-content:space-between;gap:12px;color:var(--muted);font-size:11px;margin-top:5px}
+.mode-row{display:flex;align-items:center;justify-content:space-between;gap:18px;flex-wrap:wrap}.mode-buttons{display:flex;gap:9px;flex-wrap:wrap}.mode-buttons button,.mode-buttons a{border:1px solid var(--line);background:#09111b;color:var(--text);padding:9px 14px;border-radius:9px;cursor:pointer;text-decoration:none;font:inherit}.mode-buttons button.active{border-color:var(--cyan);color:var(--cyan);box-shadow:inset 0 0 0 1px #45d7ff33}.mode-buttons button:disabled{opacity:.45;cursor:wait}.mode-buttons a[hidden]{display:none}.mode-error{color:var(--red)}
 </style></head><body><main>
 <div class="top"><div><div class="eyebrow">Mike AI · Live Telemetry</div><h1>Athena llama.cpp Dashboard</h1></div><div class="live"><span class="dot" id="dot"></span><span id="updated">verbinde …</span></div></div>
 <section class="grid">
+  <article class="card span12"><div class="mode-row"><div><div class="label">Athena Betriebsmodus</div><div class="value" id="operatingMode">–</div><div class="sub" id="modeStatus">Status wird geladen …</div></div><div class="mode-buttons"><button id="llmMode" onclick="setMode('llm')">LLM-Betrieb</button><button id="musicMode" onclick="setMode('music')">Musikstudio</button><a id="musicOpen" href="__MUSIC_UI_URL__" target="_blank" rel="noopener" hidden>Studio öffnen</a></div></div></article>
   <article class="card span3"><div class="label">Aktives Profil</div><div class="value" id="profile">–</div><div class="sub" id="profileSub">Router wird abgefragt</div></article>
   <article class="card span3"><div class="label">Modell</div><div class="value" id="model">–</div><div class="sub" id="modelSub">–</div></article>
   <article class="card span3"><div class="label">CPU</div><div class="value" id="cpu">–</div><div class="bar"><div class="fill" id="cpuBar"></div></div><div class="sub" id="load">–</div></article>
@@ -637,13 +661,15 @@ HTML = r'''<!doctype html>
   <article class="card span12"><div class="label">llama.cpp Laufzeitkonfiguration</div><div class="metrics" id="runtime"><div class="metric"><b>–</b><span>wird gelesen</span></div></div></article>
   <article class="card span12"><div class="row"><div><div class="label">Verfügbare GGUF-Dateien</div><div class="sub" id="modelSummary">–</div></div></div><div class="scroll"><table><thead><tr><th>Datei</th><th>Pfad</th><th>Größe</th><th>Geändert</th></tr></thead><tbody id="modelFiles"><tr><td colspan="4">–</td></tr></tbody></table></div></article>
   <article class="card span12 error" id="errors" hidden></article>
-</section><div class="footer">Aktualisierung jede Sekunde · Nur lesende Telemetrie</div>
+</section><div class="footer">Aktualisierung jede Sekunde · Umschaltung über Athena Router</div>
 </main><script>
 const $=id=>document.getElementById(id); const pct=n=>n==null?'–':`${n.toFixed?.(1)??n}%`; const gib=b=>b?`${(b/1073741824).toFixed(1)} GiB`:'–'; const dur=s=>{if(s==null)return'–';let d=Math.floor(s/86400),h=Math.floor(s%86400/3600),m=Math.floor(s%3600/60);return d?`${d}d ${h}h`:`${h}h ${m}m`};
 function gpuCard(g){let total=g.memory_total_mib||0,used=g.memory_used_mib||0,p=total?used/total*100:0,load=Math.max(0,Math.min(100,g.gpu_percent||0));return `<article class="card span6"><div class="gpu-title"><div><div class="label">GPU ${g.index}</div><div class="value">${g.name}</div></div><span class="badge">${g.pstate||'–'}</span></div><div class="metrics"><div class="metric"><b>${pct(g.gpu_percent)}</b><span>GPU-Kern</span></div><div class="metric"><b>${(used/1024).toFixed(1)} / ${(total/1024).toFixed(1)} GiB</b><span>VRAM</span></div><div class="metric"><b>${g.temperature_c??'–'} °C</b><span>Temperatur</span></div><div class="metric"><b>${g.power_w??'–'} / ${g.power_limit_w??'–'} W</b><span>Leistung</span></div><div class="metric"><b>${g.graphics_clock_mhz??'–'} MHz</b><span>Grafiktakt</span></div><div class="metric"><b>${g.memory_clock_mhz??'–'} MHz</b><span>Speichertakt</span></div><div class="metric"><b>${pct(g.memory_controller_percent)}</b><span>Memory Controller</span></div><div class="metric"><b>${pct(g.fan_percent)}</b><span>Lüfter</span></div></div><div class="bar-label"><span>GPU-Auslastung</span><span>${load.toFixed(1)} %</span></div><div class="bar"><div class="fill gpu-load" style="width:${load}%"></div></div><div class="bar-label"><span>VRAM-Belegung</span><span>${p.toFixed(1)} %</span></div><div class="bar"><div class="fill" style="width:${Math.min(100,p)}%"></div></div><div class="sub">${(g.memory_free_mib/1024).toFixed(1)} GiB VRAM frei</div></article>`}
 const imagePhaseLabel=p=>({"stopping-qwen":"Qwen wird entladen","loading-image":"Bildmodell wird geladen","generating":"Bild wird generiert","unloading-image":"Bildmodell wird entladen","restoring-qwen":"Qwen wird wiederhergestellt"}[p]||p||'bereit');
-async function refresh(){try{let r=await fetch('/api/status',{cache:'no-store'});if(!r.ok)throw Error(`HTTP ${r.status}`);let d=await r.json(),c=d.cpu||{},m=c.memory||{},rt=d.router||{},up=rt.upstream||{},q=rt.qwen||{},lr=d.llama_runtime||{},img=rt.image||{},imageActive=img.phase&&img.phase!=='idle';$('profile').textContent=imageActive?'Bildgenerierung':(rt.current_profile||'nicht geladen');$('profileSub').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching?`Wechsel zu ${rt.switching}`:`Kontext: ${up.ctx?up.ctx.toLocaleString('de-DE'):'–'} Token`);$('model').textContent=imageActive?(img.model||'Bildmodell'):(up.model||'–');$('modelSub').textContent=imageActive?`${img.model_loaded?'geladen':'wird vorbereitet'} · Worker ${img.worker||'–'}`:(lr.model_file|| (up.reachable?'llama.cpp erreichbar':'llama.cpp nicht erreichbar'));$('cpu').textContent=pct(c.usage_percent);$('cpuBar').style.width=`${c.usage_percent||0}%`;$('load').textContent=`${c.logical_cpus||'–'} Threads · Load ${(c.load||[]).join(' / ')}`;let rp=m.total?m.used/m.total*100:0;$('ram').textContent=pct(rp);$('ramBar').style.width=`${rp}%`;$('ramSub').textContent=`${gib(m.used)} / ${gib(m.total)}`;$('gpuCards').innerHTML=(d.gpus||[]).map(gpuCard).join('')||'<article class="card span12 error">Keine GPU-Daten verfügbar</article>';$('availability').textContent=imageActive?imagePhaseLabel(img.phase):(q.available?'bereit':'nicht bereit');$('availability').className=`value status ${(imageActive||q.available)?'':'bad'}`;$('activeChats').textContent=q.active_chats??'–';$('routerUptime').textContent=dur(rt.uptime_seconds);$('switching').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching||'nein');let disk=c.disk_data||{},dp=disk.total?disk.used/disk.total*100:null;$('dataDisk').textContent=pct(dp);$('processes').innerHTML=(d.gpu_processes||[]).map(p=>`<tr><td>${(d.gpus||[]).find(g=>g.uuid===p.gpu_uuid)?.index??'–'}</td><td>${p.name}</td><td>${p.pid}</td><td>${p.memory_mib??'–'} MiB</td></tr>`).join('')||'<tr><td colspan="4">Keine Compute-Prozesse gemeldet</td></tr>';let runtime=[['Modell-Datei',lr.model_file],['PID',lr.pid],['Kontext',lr.context_size?lr.context_size.toLocaleString('de-DE'):'–'],['Batch / µBatch',`${lr.batch_size??'–'} / ${lr.ubatch_size??'–'}`],['Parallel',lr.parallel],['Threads',`${lr.threads??'–'} / ${lr.threads_batch??'–'}`],['Geräte',lr.device],['Tensor-Split',lr.tensor_split],['KV-Cache',`${lr.cache_k??'–'} / ${lr.cache_v??'–'}`],['Flash Attention',lr.flash_attention?'an':'aus'],['Prompt-Cache',lr.prompt_cache?'an':'aus'],['MTP Draft',lr.mtp_draft_tokens]];$('runtime').innerHTML=runtime.map(([k,v])=>`<div class="metric"><b>${v??'–'}</b><span>${k}</span></div>`).join('');let es=Object.entries(d.errors||{}).filter(([,v])=>v);$('errors').hidden=!es.length;$('errors').textContent=es.map(([k,v])=>`${k}: ${v}`).join('\n');$('updated').textContent=`Live · ${new Date(d.timestamp*1000).toLocaleTimeString('de-DE')}`;$('dot').style.background='var(--green)'}catch(e){$('updated').textContent=`Verbindung gestört: ${e.message}`;$('dot').style.background='var(--red)'}}refresh();setInterval(refresh,1000);
-</script><script src="/full.js"></script><script src="/history.js"></script></body></html>'''
+let modeBusy=false;
+async function setMode(mode){if(modeBusy)return;modeBusy=true;$('llmMode').disabled=$('musicMode').disabled=true;$('modeStatus').textContent='Umschaltung angefordert …';try{let r=await fetch('/api/mode',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({mode})});let d=await r.json();if(!r.ok)throw Error(d?.error?.message||d?.error||`HTTP ${r.status}`);$('modeStatus').textContent='Umschaltung läuft …'}catch(e){$('modeStatus').textContent=e.message;$('modeStatus').classList.add('mode-error')}finally{modeBusy=false;setTimeout(refresh,250)}}
+async function refresh(){try{let r=await fetch('/api/status',{cache:'no-store'});if(!r.ok)throw Error(`HTTP ${r.status}`);let d=await r.json(),c=d.cpu||{},m=c.memory||{},rt=d.router||{},up=rt.upstream||{},q=rt.qwen||{},lr=d.llama_runtime||{},img=rt.image||{},imageActive=img.phase&&img.phase!=='idle';let md=rt.mode||{},switchingMode=md.phase&&md.phase!=='ready';$('operatingMode').textContent=md.active==='music'?'Musikstudio':'LLM-Betrieb';$('modeStatus').textContent=switchingMode?`Umschaltung: ${md.phase}`:(md.last_error||`Musik-Worker: ${md.music_worker||'–'}${md.return_profile?` · Rückkehr zu ${md.return_profile}`:''}`);$('modeStatus').classList.toggle('mode-error',!!md.last_error);$('llmMode').classList.toggle('active',md.active==='llm');$('musicMode').classList.toggle('active',md.active==='music');$('llmMode').disabled=$('musicMode').disabled=modeBusy||switchingMode||!md.enabled;$('musicOpen').hidden=md.active!=='music';$('profile').textContent=imageActive?'Bildgenerierung':(rt.current_profile||'nicht geladen');$('profileSub').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching?`Wechsel zu ${rt.switching}`:`Kontext: ${up.ctx?up.ctx.toLocaleString('de-DE'):'–'} Token`);$('model').textContent=imageActive?(img.model||'Bildmodell'):(up.model||'–');$('modelSub').textContent=imageActive?`${img.model_loaded?'geladen':'wird vorbereitet'} · Worker ${img.worker||'–'}`:(lr.model_file|| (up.reachable?'llama.cpp erreichbar':'llama.cpp nicht erreichbar'));$('cpu').textContent=pct(c.usage_percent);$('cpuBar').style.width=`${c.usage_percent||0}%`;$('load').textContent=`${c.logical_cpus||'–'} Threads · Load ${(c.load||[]).join(' / ')}`;let rp=m.total?m.used/m.total*100:0;$('ram').textContent=pct(rp);$('ramBar').style.width=`${rp}%`;$('ramSub').textContent=`${gib(m.used)} / ${gib(m.total)}`;$('gpuCards').innerHTML=(d.gpus||[]).map(gpuCard).join('')||'<article class="card span12 error">Keine GPU-Daten verfügbar</article>';$('availability').textContent=imageActive?imagePhaseLabel(img.phase):(q.available?'bereit':'nicht bereit');$('availability').className=`value status ${(imageActive||q.available)?'':'bad'}`;$('activeChats').textContent=q.active_chats??'–';$('routerUptime').textContent=dur(rt.uptime_seconds);$('switching').textContent=imageActive?imagePhaseLabel(img.phase):(rt.switching||'nein');let disk=c.disk_data||{},dp=disk.total?disk.used/disk.total*100:null;$('dataDisk').textContent=pct(dp);$('processes').innerHTML=(d.gpu_processes||[]).map(p=>`<tr><td>${(d.gpus||[]).find(g=>g.uuid===p.gpu_uuid)?.index??'–'}</td><td>${p.name}</td><td>${p.pid}</td><td>${p.memory_mib??'–'} MiB</td></tr>`).join('')||'<tr><td colspan="4">Keine Compute-Prozesse gemeldet</td></tr>';let runtime=[['Modell-Datei',lr.model_file],['PID',lr.pid],['Kontext',lr.context_size?lr.context_size.toLocaleString('de-DE'):'–'],['Batch / µBatch',`${lr.batch_size??'–'} / ${lr.ubatch_size??'–'}`],['Parallel',lr.parallel],['Threads',`${lr.threads??'–'} / ${lr.threads_batch??'–'}`],['Geräte',lr.device],['Tensor-Split',lr.tensor_split],['KV-Cache',`${lr.cache_k??'–'} / ${lr.cache_v??'–'}`],['Flash Attention',lr.flash_attention?'an':'aus'],['Prompt-Cache',lr.prompt_cache?'an':'aus'],['MTP Draft',lr.mtp_draft_tokens]];$('runtime').innerHTML=runtime.map(([k,v])=>`<div class="metric"><b>${v??'–'}</b><span>${k}</span></div>`).join('');let es=Object.entries(d.errors||{}).filter(([,v])=>v);$('errors').hidden=!es.length;$('errors').textContent=es.map(([k,v])=>`${k}: ${v}`).join('\n');$('updated').textContent=`Live · ${new Date(d.timestamp*1000).toLocaleTimeString('de-DE')}`;$('dot').style.background='var(--green)'}catch(e){$('updated').textContent=`Verbindung gestört: ${e.message}`;$('dot').style.background='var(--red)'}}refresh();setInterval(refresh,1000);
+</script><script src="/full.js"></script><script src="/history.js"></script></body></html>'''.replace("__MUSIC_UI_URL__", MUSIC_UI_URL)
 
 
 FULL_JS = r'''
@@ -785,6 +811,25 @@ class Handler(BaseHTTPRequestHandler):
         else:
             self._send(404, b'{"error":"not found"}', "application/json")
 
+    def do_POST(self) -> None:
+        path = self.path.split("?", 1)[0]
+        if path != "/api/mode":
+            self._send(404, b'{"error":"not found"}', "application/json")
+            return
+        try:
+            length = int(self.headers.get("Content-Length", "0"))
+            if length <= 0 or length > 1024:
+                raise ValueError("invalid body size")
+            payload = json.loads(self.rfile.read(length))
+            mode = payload.get("mode") if isinstance(payload, dict) else None
+        except (ValueError, json.JSONDecodeError):
+            self._send(400, b'{"error":"invalid request"}', "application/json")
+            return
+        status, response = change_mode(mode)
+        body = json.dumps(response, ensure_ascii=False,
+                          separators=(",", ":")).encode()
+        self._send(status, body, "application/json; charset=utf-8")
+
 
 if __name__ == "__main__":
     threading.Thread(target=history_collector, name="history-collector", daemon=True).start()