Cookbook polish: auto-reconnect, ctx slider fixes, scoring, lots of UI

Backend (services/hwfit + routes):
- VRAM column sort now shows global highest first (was special-cased to
  ascending then truncated top-N, which made "highest VRAM" mathematically
  unreachable). Every column path uses reverse=True for the truncation.
- Hardware probe cache TTL 30min -> 24h so changing filters doesn't keep
  re-probing the rig during a session; Rescan button still forces fresh.
- Multi-GPU rigs filter GGUF Q*/IQ quants (vLLM/SGLang can't serve them);
  default non-prequantized to BF16 on 2+ GPUs.
- AWQ / AWQ-8bit / GPTQ-8bit get a -1.0 quality penalty so FP8 wins ties.
- Version-aware tiebreaker (parse Mn.n / Vn) — MiniMax-M2.7 ranks above M2.5.
- hf_models.json: zai-org/GLM-5.1 added; zai-org/GLM-5 quantization flipped
  Q4_K_M -> BF16. DeepSeek-V4-Flash / -Pro + their -Base variants registered
  with new FP4-MoE-Mixed / FP8-Mixed quant keys (calibrated BPP from the
  actual 156 GB / 284 GB disk footprints).
- New FP4-MoE-Mixed + FP8-Mixed entries in QUANT_BPP / QUANT_SPEED_MULT /
  QUANT_QUALITY_PENALTY / QUANT_BYTES_PER_PARAM / PREQUANTIZED_PREFIXES.

Frontend — Scan/Download:
- Engine + Quant swapped in the toolbar; Quant defaults to "All".
- Ctx (range slider) ported from origin/main: 8k/16k/32k/50k/128k/Max. Drag
  re-sorts by vram ascending (smallest fitting first); back to Max → score.
- Ctx slider rail now visible — was background:transparent in a duplicate
  later-cascade rule. Hardcoded grey + !important.
- Search input moved to the far right of the toolbar.
- Type/Standard default; "Context" not uppercased; Search placeholder dimmed.
- Engine "?" + Quant "?" inline help chips inside their dropdown boxes.
- Fit-column dot toggles fit-only filter; un-toggling re-sorts by VRAM desc.
- Quant column truncates to 9 chars + ellipsis ("FP4-MoE-M..."), full in
  tooltip. Smart title-suffix strips the parts already in the repo name
  (QuantTrio/MiniMax-M2-AWQ + quant AWQ-4bit -> just "(4bit)").
- Conditional warning for safetensors models on non-GPU rigs only.
- Dependency Install / Installed / Installed▾ / N/A all 75.85px wide.
- Rebuild llama.cpp moved into the llama_cpp dep row, styled as a tag.
- Foldable Download admin-card (h2 chevron); line under h2 only when folded.
- HF token save gets a green ✓ + "Saved" flash.
- Cached scan no longer counts stalled rows as downloaded.
- Footer: "Request it →" link with GitHub mark to the public discussion
  (#1962) for model-add requests.

Frontend — Running tab:
- Strict download-finish check (DOWNLOAD_OK or /snapshots/, not bare
  "Download complete"). True overall % for multi-shard downloads:
  ((N-1)+frac)/total instead of hf_transfer's per-shard aggregate.
- ETA in the uptime ticker: "downloading: 12m 34s · ETA 1h 23m".
- Clear button kills the tmux session too; if the output still shows a
  live shard line, the pill is hidden + relabels as "reconnect" + revives
  on click.
- Self-heal: on cookbook open AND every bg-monitor cycle (10s, throttled
  to 8s), scan persisted done/error/crashed downloads and probe their
  tmux session — if alive, flip status back to running and reattach.
- Per-launch zombie probe: clicking Download on a model whose persisted
  state is done but tmux is still alive revives the existing task and
  refuses to start a duplicate.
- Pre-launch GPU probe: vllm / sglang / diffusers serve check
  /api/cookbook/gpus first; warns + confirms if no GPU is visible.
- Server-side state guard: rejects "done" POSTs for downloads lacking
  DOWNLOAD_OK / DOWNLOAD_FAILED / /snapshots/ when the last-mentioned
  shard is N<total — stale tabs can't poison persisted state any more.
- Running count includes tasks whose output looks active even if persisted
  status got stuck. Dir text on the running row, font matched to uptime.

Serve panel:
- Ctx text input always resets to model max on open (default 20000 when
  metadata is missing).
- Max Seqs default 8 -> 4. KV Cache dtype select 32px tall.
- Lightning icon on Launch (same as Action toggle).
- Diagnosis card simplified (no fold/copy/dismiss), suggestion font
  matches body; action buttons get icons on the left (Retry/Copy/Edit/
  Install/Kill/Switch/etc.).
- Incomplete-download serve warning when model status is
  downloading / stalled / has_incomplete.
- MTP "?" tooltip ("supported on a few model families … up to ~3× faster").

static/js/cookbook-diagnosis.js

@@ -23,6 +23,44 @@ import {
   // browser loads it once. See cookbook-hwfit.js.
 } from './cookbook.js';
 import uiModule from './ui.js';
+
+// Tiny HTML-escape — keeps the file standalone instead of leaning on a
+// shared helper that may not be exported from this module's import surface.
+function _diagEsc(s) {
+  return String(s ?? '').replace(/[&<>"']/g, c => ({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c]));
+}
+
+// Pick an icon for a diagnosis-action button based on the label. The icon
+// renders on the LEFT of the button text. Keeps the strokes consistent
+// across the set so they read as one family.
+function _diagFixIcon(label) {
+  const l = String(label || '').toLowerCase();
+  const _svg = (path) => `<svg width="11" height="11" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round" class="cookbook-diag-btn-ico" aria-hidden="true">${path}</svg>`;
+  if (l.startsWith('retry') || l.includes('relaunch') || l.includes('restart')) {
+    // Circular-arrow refresh
+    return _svg('<polyline points="23 4 23 10 17 10"/><polyline points="1 20 1 14 7 14"/><path d="M3.51 9a9 9 0 0 1 14.85-3.36L23 10M1 14l4.64 4.36A9 9 0 0 0 20.49 15"/>');
+  }
+  if (l.startsWith('copy')) {
+    return _svg('<rect x="9" y="9" width="13" height="13" rx="2"/><path d="M5 15H4a2 2 0 0 1-2-2V4a2 2 0 0 1 2-2h9a2 2 0 0 1 2 2v1"/>');
+  }
+  if (l.startsWith('edit')) {
+    return _svg('<path d="M12 20h9"/><path d="M16.5 3.5a2.121 2.121 0 0 1 3 3L7 19l-4 1 1-4Z"/>');
+  }
+  if (l.startsWith('open') || l.includes('dependencies')) {
+    return _svg('<path d="M14 3h7v7"/><path d="M21 3l-9 9"/><path d="M21 14v5a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V5a2 2 0 0 1 2-2h5"/>');
+  }
+  if (l.startsWith('install') || l.includes('upgrade')) {
+    return _svg('<path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4"/><polyline points="7 10 12 15 17 10"/><line x1="12" y1="15" x2="12" y2="3"/>');
+  }
+  if (l.startsWith('kill') || l.startsWith('stop')) {
+    return _svg('<rect x="6" y="6" width="12" height="12" rx="1"/>');
+  }
+  if (l.startsWith('switch') || l.includes('use ')) {
+    return _svg('<polyline points="17 1 21 5 17 9"/><path d="M3 11V9a4 4 0 0 1 4-4h14"/><polyline points="7 23 3 19 7 15"/><path d="M21 13v2a4 4 0 0 1-4 4H3"/>');
+  }
+  // Default: lightbulb (generic "suggestion")
+  return _svg('<path d="M9 21h6"/><path d="M12 17v4"/><path d="M12 3a6 6 0 0 0-4 10.5c1 1 1.5 2 1.5 3.5h5c0-1.5.5-2.5 1.5-3.5A6 6 0 0 0 12 3Z"/>');
+}
 import spinnerModule from './spinner.js';
 
 // ── Error diagnosis ──
@@ -577,7 +615,7 @@ export function _showDiagnosis(panel, diagnosis, sourceText) {
         const btn = document.createElement('button');
         btn.className = 'cookbook-btn cookbook-diag-btn';
         btn.type = 'button';
-        btn.textContent = fix.label;
+        btn.innerHTML = _diagFixIcon(fix.label) + '<span class="cookbook-diag-btn-label">' + _diagEsc(fix.label) + '</span>';
         btn.addEventListener('click', (e) => {
           e.stopPropagation();
           runFix(fix, btn);
@@ -603,7 +641,7 @@ export function _showDiagnosis(panel, diagnosis, sourceText) {
     for (const fix of fixes) {
       const item = document.createElement('button');
       item.type = 'button';
-      item.textContent = fix.label;
+      item.innerHTML = _diagFixIcon(fix.label) + '<span class="cookbook-diag-btn-label">' + _diagEsc(fix.label) + '</span>';
       item.addEventListener('click', async (e) => {
         e.stopPropagation();
         if (item.dataset.busy || trigger.dataset.busy) return;