fix: error state, leg grouping, prompt→generating transition

- log_parser: detect model load failure (child + router patterns) → state=error;
  switch to generating at progress=1.00 and at prompt eval summary line
- frontend: add state-error (llama flashes red, CSS variable override);
  group each leg+hoof in <g> so walk animation moves hooves with legs

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

frontend/app.js

@@ -20,7 +20,7 @@
   // ── State class management ────────────────────────────────────────────────
   const ALL_STATES = [
     'offline','starting','loading','warming_up','idle',
-    'sleeping','waiting','processing_prompt','generating','unloading'
+    'sleeping','waiting','processing_prompt','generating','unloading','error'
   ];
 
   function applyState(stateName) {

frontend/index.html

@@ -64,18 +64,23 @@
             <!-- Mouth: open (talking) -->
             <ellipse class="part mouth-open" cx="50" cy="39" rx="4.5" ry="3"/>
 
-            <!-- Front legs -->
+            <!-- Legs + hooves (grouped so animation moves both together) -->
-            <rect class="part leg leg-fl" x="32" y="100" width="10" height="30" rx="4"/>
+            <g class="leg-fl">
-            <rect class="part leg leg-fr" x="46" y="100" width="10" height="30" rx="4"/>
+              <rect class="part leg" x="29" y="100" width="10" height="30" rx="4"/>
-            <!-- Back legs -->
+              <rect class="part hoof" x="29" y="126" width="10" height="4" rx="2"/>
-            <rect class="part leg leg-bl" x="57" y="100" width="10" height="30" rx="4"/>
+            </g>
-            <rect class="part leg leg-br" x="71" y="100" width="10" height="30" rx="4"/>
+            <g class="leg-fr">
-
+              <rect class="part leg" x="40" y="100" width="10" height="30" rx="4"/>
-            <!-- Hooves -->
+              <rect class="part hoof" x="40" y="126" width="10" height="4" rx="2"/>
-            <rect class="part hoof" x="32" y="126" width="10" height="4" rx="2"/>
+            </g>
-            <rect class="part hoof" x="46" y="126" width="10" height="4" rx="2"/>
+            <g class="leg-bl">
-            <rect class="part hoof" x="57" y="126" width="10" height="4" rx="2"/>
+              <rect class="part leg" x="51" y="100" width="10" height="30" rx="4"/>
-            <rect class="part hoof" x="71" y="126" width="10" height="4" rx="2"/>
+              <rect class="part hoof" x="51" y="126" width="10" height="4" rx="2"/>
+            </g>
+            <g class="leg-br">
+              <rect class="part leg" x="62" y="100" width="10" height="30" rx="4"/>
+              <rect class="part hoof" x="62" y="126" width="10" height="4" rx="2"/>
+            </g>
 
             <!-- Book (reading) -->
             <g class="part book">

frontend/style.css

@@ -145,6 +145,14 @@ body.state-processing_prompt #progress-wrap { display: flex; }
 /* offline */
 body.state-offline #llama { opacity: 0.15; }
 
+/* error: llama flashes red */
+body.state-error { --amber: var(--red); --amber-dim: #cc3333; --amber-dk: #882222; }
+body.state-error #llama { animation: error-flash 1s ease-in-out infinite; }
+@keyframes error-flash {
+  0%, 100% { opacity: 1;    }
+  50%       { opacity: 0.4; }
+}
+
 /* ── ZZZ ─────────────────────────────────────────────────────────────────── */
 #zzz-wrap {
   position: absolute;
@@ -341,6 +349,11 @@ body.state-unloading  #row-speed,
 body.state-unloading  #row-tokens,
 body.state-unloading  #row-load-stage { display: none; }
 
+body.state-error      #row-prompt,
+body.state-error      #row-speed,
+body.state-error      #row-tokens,
+body.state-error      #row-load-stage { display: none; }
+
 body.state-processing_prompt #row-speed,
 body.state-processing_prompt #row-load-stage { display: none; }
 
@@ -390,12 +403,12 @@ body.state-waiting .right-ear {
 body.state-loading .leg-fl,
 body.state-loading .leg-bl {
   animation: walk-a 0.7s ease-in-out infinite;
-  transform-origin: 37px 100px;
+  transform-origin: 34px 100px;
 }
 body.state-loading .leg-fr,
 body.state-loading .leg-br {
   animation: walk-b 0.7s ease-in-out infinite;
-  transform-origin: 51px 100px;
+  transform-origin: 45px 100px;
 }
 
 @keyframes walk-a {

log_parser.py

@@ -83,6 +83,8 @@ _PROMPT_SUMMARY_RE = re.compile(
 )
 _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')
 
 
 # ── State machine ─────────────────────────────────────────────────────────────
@@ -121,6 +123,8 @@ class LogParser:
             return self._set(state="waiting")
         if _UNLOAD_RE.search(content):
             return self._set(state="unloading")
+        if _EXIT_ERROR_RE.search(content):
+            return self._set(state="error")
         return None
 
     # ── Child-process lines ──────────────────────────────────────────────────
@@ -130,6 +134,8 @@ class LogParser:
 
         if m := _CMD_STATE_RE.match(content):
             return self._handle_cmd_state(m.group(1))
+        if _LOAD_ERROR_RE.search(content):
+            return self._set(state="error")
         if _WARMUP_RE.search(content):
             return self._set(state="warming_up")
         if _IDLE_RE.search(content):
@@ -137,14 +143,14 @@ class LogParser:
         if _LAUNCH_RE.search(content):
             return self._set(state="processing_prompt")
         if m := _PROMPT_TIMING_RE.search(content):
+            progress = float(m.group(2))
+            done = progress >= 1.0
             metrics = Metrics(
                 prompt_speed=float(m.group(3)),
                 prompt_tokens=int(m.group(1)),
-                prompt_progress=float(m.group(2)),
+                prompt_progress=None if done else progress,
-                gen_speed=self._state.metrics.gen_speed,
-                n_decoded=self._state.metrics.n_decoded,
             )
-            return self._set(state="processing_prompt", metrics=metrics)
+            return self._set(state="generating" if done else "processing_prompt", metrics=metrics)
         if m := _GEN_TIMING_RE.search(content):
             metrics = Metrics(
                 prompt_speed=self._state.metrics.prompt_speed,
@@ -154,14 +160,18 @@ class LogParser:
             )
             return self._set(state="generating", metrics=metrics)
         if m := _PROMPT_SUMMARY_RE.search(content):
-            # End-of-slot summary: update prompt speed without changing state.
-            # For short prompts this fires after generating starts (no live prompt line).
             metrics = Metrics(
                 prompt_speed=float(m.group(2)),
                 prompt_tokens=int(m.group(1)),
                 gen_speed=self._state.metrics.gen_speed,
                 n_decoded=self._state.metrics.n_decoded,
             )
+            if self._state.state == "processing_prompt":
+                # Summary fires right after prompt eval finishes, before first token.
+                # Advance to generating now rather than waiting for the first tg line.
+                # For short prompts the summary arrives after generating has already
+                # started, so the guard prevents stepping back.
+                return self._set(state="generating", metrics=metrics)
             return self._set(metrics=metrics)
         if _RELEASE_RE.search(content):
             return self._set(