feat(agent): graceful Start/Stop with starting/stopping states + instant status

Operator: the buttons fire but the status view doesn't reflect the change. Cause: act() ignored the POST's own status response and waited on the separate /status poll (which lags behind the curator queue call). Now: - act() applies the POST's returned status immediately for instant feedback, and shows an optimistic "starting"/"stopping" state (pulsing, buttons disabled) the moment it's clicked. - A stop that still has in-flight jobs draining shows "stopping" until active hits 0, then resolves to "stopped" on its own. - applyStatus() guards the /status-only fields (connection pill + queue) so the lean action response can't blank them — the Start/Stop path deliberately skips the slow curator call to stay snappy. Also de-duplicate GPU reads: read_gpu() now caches (1s TTL) with one probe at a time, and /status no longer spawns its own nvidia-smi — so the fast /gpu poll + autoscaler + /status share a single subprocess instead of piling up in the server thread pool (which was what made clicks feel dead under load). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
2026-06-30 19:38:37 -04:00
parent 3b34230fbd
commit c2e9157822
2 changed files with 79 additions and 15 deletions
@@ -77,7 +77,8 @@ def status():
    s = worker.status()
    s["fc_url"] = cfg.fc_url
    s["configured"] = bool(cfg.token)
-    s["gpu"] = read_gpu()
+    # GPU is served by /gpu (cached); /status stays light so Start/Stop never
+    # queue behind it.
    try:
        s["queue"] = worker.client.queue_status()
    except Exception:
@@ -116,6 +117,9 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 .btn{font:600 14px system-ui;padding:.5rem 1rem;border:1px solid transparent;border-radius:9px;
  cursor:pointer;color:#fff;transition:.12s}
 .btn:hover{transform:translateY(-1px)}
+ .btn[disabled]{opacity:.45;pointer-events:none;transform:none}
+ @keyframes pulse{0%,100%{opacity:1}50%{opacity:.4}}
+ .tile .n.busy{color:var(--acc);animation:pulse 1s ease-in-out infinite}
 .btn.start{background:linear-gradient(180deg,#2f9c4c,#247a3c)}
 .btn.stop{background:linear-gradient(180deg,#3a3f48,#2a2f37);color:#e9edf2;border-color:var(--bd)}
 .switch{display:inline-flex;align-items:center;gap:8px;cursor:pointer;font-weight:600;user-select:none}
@@ -171,8 +175,8 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 <section class=card>
  <div class=card-h>Control</div>
  <div class=controls>
-   <button class="btn start" onclick=act('start')>▶ Start</button>
-   <button class="btn stop" onclick=act('stop')>■ Stop</button>
+   <button class="btn start" id=startbtn onclick=act('start')>▶ Start</button>
+   <button class="btn stop" id=stopbtn onclick=act('stop')>■ Stop</button>
   <div class=spacer></div>
   <label class=switch><input type=checkbox id=autochk onchange="setauto(this.checked)"><span class=track></span>Auto</label>
   <div class=stepper>
@@ -211,7 +215,20 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 </div>
 <script>
 let CAP=8
- async function act(p){await fetch('/'+p,{method:'POST'});refresh()}
+ // Optimistic transitional state on click, then apply the POST's own status
+ // response (it returns worker.status()) for instant feedback — don't wait on the
+ // separate /status poll, which can lag behind the curator queue call.
+ async function act(p){
+  pending(p==='start'?'starting':'stopping')
+  try{ applyStatus(await (await fetch('/'+p,{method:'POST'})).json()) }
+  catch{ /* leave the periodic refresh to recover the real state */ }
+  finally{ startbtn.disabled=false; stopbtn.disabled=false }
+ }
+ function pending(label){
+  state.textContent=label; state.className='n busy'
+  dot.className='dot amber'
+  startbtn.disabled=true; stopbtn.disabled=true
+ }
 function setc(d){ if(conc.disabled)return; setv((parseInt(conc.value||'1'))+d) }
 async function setv(v){
  v=Math.max(1,Math.min(CAP,parseInt(v)||1)); conc.value=v
@@ -224,24 +241,36 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 }
 async function refresh(){
  let s; try{ s=await (await fetch('/status')).json() }catch{ return }
+  applyStatus(s)
+ }
+ function applyStatus(s){
  CAP=s.max_concurrency||8; capn.textContent=CAP
-  const running=s.state==='running', ok=s.configured
-  state.textContent=s.state
+  const running=s.state==='running'
+  // "stopping" = stopped but in-flight jobs are still draining; resolves to
+  // "stopped" on its own once active hits 0.
+  const draining=!running && s.active>0
+  state.textContent=draining?'stopping':s.state
+  state.className='n'+(draining?' busy':'')
  active.textContent=s.active; done.textContent=s.processed
  err.textContent=s.errors; err.className='n'+(s.errors>0?' warn':'')
-  fc.textContent=s.fc_url; wait.textContent=s.transient||0
-  cfg.textContent=ok?'set':'MISSING'
-  // connection pill
-  dot.className='dot '+(!ok?'red':(running?(s.queue?'green':'amber'):'amber'))
-  connlbl.textContent=!ok?'no token':(running?(s.queue?'running':'running · curator unreachable'):'stopped')
-  banner.style.display=(running && !s.queue)?'block':'none'
+  wait.textContent=s.transient||0
  // Auto on → dial reflects the auto-chosen count (read-only); off → manual.
  if(document.activeElement!==autochk) autochk.checked=!!s.auto
  conc.disabled=!!s.auto; conc.style.opacity=s.auto?0.55:1
  conchint.textContent=s.auto?('auto-tuning to fill the GPU · max '+CAP):('manual · max '+CAP)
  if(document.activeElement!==conc) conc.value=s.concurrency
  conc.max=CAP
-  queue.textContent=s.queue?('queue · pending '+s.queue.pending+' · in flight '+s.queue.leased+' · done '+s.queue.done+' · errored '+s.queue.error):'queue · unreachable'
+  // Connection pill + queue come only from the /status poll (the Start/Stop POST
+  // responses skip the slow curator call to stay snappy) — guard so an action
+  // response doesn't blank them.
+  if('configured' in s){
+   const ok=s.configured
+   fc.textContent=s.fc_url; cfg.textContent=ok?'set':'MISSING'
+   dot.className='dot '+(!ok?'red':(running?(s.queue?'green':'amber'):'amber'))
+   connlbl.textContent=!ok?'no token':(running?(s.queue?'running':'running · curator unreachable'):'stopped')
+   banner.style.display=(running && !s.queue)?'block':'none'
+   queue.textContent=s.queue?('queue · pending '+s.queue.pending+' · in flight '+s.queue.leased+' · done '+s.queue.done+' · errored '+s.queue.error):'queue · unreachable'
+  }
 }
 // GPU meters poll their OWN endpoint on a fast cadence — kept off /status so a
 // slow curator queue call can't freeze the bars (they only stale on refresh).