fix: wss support, polling fallback, cancellation, offline labels, screen sizing

- frontend/app.js: use wss:// when page is served over HTTPS; add HTTP polling
  fallback (/state every 2s) when WebSocket is down, amber dot = polling mode;
  stop polling on WS reconnect; clearer state labels (LOG OFFLINE, LOAD ERROR,
  DISCONNECTED); fix replace('_',' ') to use regex for multi-underscore states
- frontend/style.css: add #ws-dot.polling (amber); min-height 280px on screen;
  shrink llama-wrap/SVG; tighten screen padding and gap
- log_parser.py: detect cancelled requests (stop: cancel task / Connection
  handling canceled) → idle; fix: switch to generating at progress=1.00
- server.py: add GET /state endpoint for polling fallback

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

frontend/app.js

@@ -6,7 +6,7 @@
   const wsDot        = document.getElementById('ws-dot');
   const statsPanel   = document.getElementById('stats-panel');
   const resizeHandle = document.getElementById('resize-handle');
-  const stateLabel  = document.getElementById('state-label');
+  const stateLabelEl = document.getElementById('state-label');
   const progressFill  = document.getElementById('progress-fill');
   const progressLabel = document.getElementById('progress-label');
   const svModel     = document.getElementById('sv-model');
@@ -23,6 +23,15 @@
     'sleeping','waiting','processing_prompt','generating','unloading','error'
   ];
 
+  const STATE_LABELS = {
+    offline:  'LOG OFFLINE',   // llamagochi can't read the log file
+    error:    'LOAD ERROR',
+  };
+
+  function stateLabel(stateName) {
+    return STATE_LABELS[stateName] ?? stateName.replace(/_/g, ' ').toUpperCase();
+  }
+
   function applyState(stateName) {
     ALL_STATES.forEach(s => body.classList.remove('state-' + s));
     body.classList.add('state-' + (ALL_STATES.includes(stateName) ? stateName : 'offline'));
@@ -42,8 +51,8 @@
 
     applyState(state);
 
-    stateLabel.textContent = state.replace('_', ' ').toUpperCase();
+    stateLabelEl.textContent = stateLabel(state);
-    svState.textContent    = state.replace('_', ' ');
+    svState.textContent      = stateLabel(state).toLowerCase();
     svModel.textContent    = model || '—';
     svReqs.textContent     = request_count ?? 0;
 
@@ -111,16 +120,43 @@
   document.addEventListener('touchmove',  e => { if (dragging) { e.preventDefault(); onDrag(e.touches[0].clientX); } }, { passive: false });
   document.addEventListener('touchend',   endDrag);
 
+  // ── HTTP polling fallback ─────────────────────────────────────────────────
+  let pollTimer = null;
+  const POLL_MS = 2000;
+
+  async function pollOnce() {
+    try {
+      const r = await fetch('/state');
+      if (!r.ok) throw new Error(r.status);
+      update(await r.json());
+      wsDot.className = 'polling';
+    } catch {
+      wsDot.className = '';  // red: llamagochi itself unreachable
+    }
+  }
+
+  function startPolling() {
+    if (pollTimer) return;
+    pollOnce();
+    pollTimer = setInterval(pollOnce, POLL_MS);
+  }
+
+  function stopPolling() {
+    clearInterval(pollTimer);
+    pollTimer = null;
+  }
+
   // ── WebSocket with auto-reconnect ─────────────────────────────────────────
   let ws = null;
   let retryDelay = 1000;
   const MAX_DELAY = 30000;
 
   function connect() {
-    const url = 'ws://' + location.host + '/ws';
+    const url = (location.protocol === 'https:' ? 'wss:' : 'ws:') + '//' + location.host + '/ws';
     ws = new WebSocket(url);
 
     ws.addEventListener('open', () => {
+      stopPolling();
       wsDot.className = 'connected';
       retryDelay = 1000;
     });
@@ -134,9 +170,7 @@
     });
 
     ws.addEventListener('close', () => {
-      wsDot.className = '';
+      startPolling();
-      applyState('offline');
-      stateLabel.textContent = 'DISCONNECTED';
       setTimeout(connect, retryDelay);
       retryDelay = Math.min(retryDelay * 2, MAX_DELAY);
     });

frontend/style.css

@@ -46,15 +46,15 @@ html, body {
 #screen {
   position: relative;
   width: 280px;
-  min-height: 380px;
+  min-height: 280px;
   background: #0d0d06;
   border: 3px solid var(--amber-dim);
   border-radius: 12px;
-  padding: 1.5rem 1rem 1rem;
+  padding: 1.2rem 1rem 0.8rem;
   display: flex;
   flex-direction: column;
   align-items: center;
-  gap: 0.8rem;
+  gap: 0.5rem;
   /* CRT scanline overlay */
   background-image: repeating-linear-gradient(
     0deg,
@@ -78,6 +78,7 @@ html, body {
   transition: background 0.3s;
 }
 #ws-dot.connected   { background: var(--green); }
+#ws-dot.polling     { background: var(--amber-dim); }
 #ws-dot.pulse       { animation: pulse-dot 0.3s ease-out; }
 
 @keyframes pulse-dot {
@@ -88,16 +89,16 @@ html, body {
 /* ── Llama container ─────────────────────────────────────────────────────── */
 #llama-wrap {
   position: relative;
-  width: 160px;
+  width: 150px;
-  height: 200px;
+  height: 175px;
   display: flex;
   align-items: center;
   justify-content: center;
 }
 
 #llama {
-  width: 140px;
+  width: 135px;
-  height: 180px;
+  height: 160px;
 }
 
 /* SVG part colors */

log_parser.py

@@ -85,6 +85,8 @@ _RELEASE_RE = re.compile(r'slot\s+release:.*stop processing')
 _UNLOAD_RE = re.compile(r'unload_lru:|unload: stopping model instance')
 _LOAD_ERROR_RE = re.compile(r'exiting due to model loading error')
 _EXIT_ERROR_RE = re.compile(r'operator\(\):.*exited with status 1')
+_CLIENT_CANCEL_RE = re.compile(r'http client error: Connection handling canceled')
+_CANCEL_TASK_RE = re.compile(r'stop: cancel task')
 
 
 # ── State machine ─────────────────────────────────────────────────────────────
@@ -125,6 +127,8 @@ class LogParser:
             return self._set(state="unloading")
         if _EXIT_ERROR_RE.search(content):
             return self._set(state="error")
+        if _CLIENT_CANCEL_RE.search(content):
+            return self._set(state="idle", loading=None, metrics=Metrics())
         return None
 
     # ── Child-process lines ──────────────────────────────────────────────────
@@ -136,6 +140,8 @@ class LogParser:
             return self._handle_cmd_state(m.group(1))
         if _LOAD_ERROR_RE.search(content):
             return self._set(state="error")
+        if _CANCEL_TASK_RE.search(content):
+            return self._set(state="idle", loading=None, metrics=Metrics())
         if _WARMUP_RE.search(content):
             return self._set(state="warming_up")
         if _IDLE_RE.search(content):

server.py

@@ -29,6 +29,10 @@ def create_app(log_path: str, reopen_log: bool = False) -> FastAPI:
     async def index():
         return FileResponse(FRONTEND_DIR / "index.html")
 
+    @app.get("/state")
+    async def get_state():
+        return last_state
+
     @app.websocket("/ws")
     async def ws_endpoint(ws: WebSocket):
         await ws.accept()