Profiling page: per-turn phase timings, live in the web dashboard

The engine already tracks where each turn's wall time goes (expert-disk
service, I/O wait, expert matmul, attention, lm_head) — it just only spoke
at exit or under PROF=1. Stream it instead:

- glm.c: mux serve emits a per-turn "PROF" protocol line next to TIERS/HITS
  (window deltas per request, same convention as the STAT hit%); the phase
  window base is now always captured (a few loads per request).
- openai_server.py: parses PROF into a 120-turn rolling window and serves it
  at /profile (read-only, same trust level as /health).
- web: new Profiling tab — stat tiles (tok/s, wall, tokens/forward, disk
  service), wall-time composition bars for the last turn and the window,
  per-turn throughput and stacked phase columns with hover readouts, and a
  table of recent turns. Disk service is shown apart from the stack: it
  overlaps with compute, so only the I/O wait the compute thread felt counts
  inside wall time. Phase colours are a CVD-validated set with gaps + legend
  + table so identity never rides on colour alone.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WhTmF8yvEBgSkUKSVfZF7P

web/src/App.tsx

@@ -31,6 +31,7 @@ import { Textarea } from "@/components/ui/textarea"
 import { getHealth, listModels, streamChat, type ChatMessage, type HealthResponse, type StreamChatResult } from "@/lib/api"
 import { activeRequests, supportsCacheSlots } from "@/lib/runtime"
 import { Brain } from "./Brain"
+import { Profiling } from "./Profiling"
 import { persistPublicSettings, stored } from "@/lib/storage"
 import { cn } from "@/lib/utils"
 
@@ -73,7 +74,7 @@ export default function App() {
   const [totalTokens, setTotalTokens] = useState({ prompt: 0, completion: 0 })
   const [connecting, setConnecting] = useState(false)
   const [connected, setConnected] = useState(false)
-  const [view, setView] = useState<"chat" | "brain">("chat")
+  const [view, setView] = useState<"chat" | "brain" | "profiling">("chat")
   const [error, setError] = useState("")
   const autoConnected = useRef(false)
   const abortRef = useRef<AbortController | null>(null)
@@ -314,6 +315,7 @@ export default function App() {
           <div className="view-tabs">
             <button className={view === "chat" ? "active" : ""} onClick={() => setView("chat")}><MessageSquareText className="size-3.5" /> Chat</button>
             <button className={view === "brain" ? "active" : ""} onClick={() => setView("brain")}><BrainCircuit className="size-3.5" /> Brain</button>
+            <button className={view === "profiling" ? "active" : ""} onClick={() => setView("profiling")}><Gauge className="size-3.5" /> Profiling</button>
           </div>
           <div className="top-actions">
               {loading && tokenCount > 0 ? <Badge className="badge-live"><Zap className="size-3 flash" /> {tokenCount} tokens</Badge> : null}
@@ -326,7 +328,8 @@ export default function App() {
             </div>
         </header>
 
-        {view === "brain" ? <Brain baseUrl={baseUrl} apiKey={apiKey} connected={connected} /> : <>
+        {view === "brain" ? <Brain baseUrl={baseUrl} apiKey={apiKey} connected={connected} />
+          : view === "profiling" ? <Profiling baseUrl={baseUrl} apiKey={apiKey} connected={connected} /> : <>
 
         <div className="conversation">
           {!messages.length ? (