v0.4.0 - NIM installer + dashboard resilience

Hotfix (was v0.3.1):
- services.py: cache 'unreachable' per (host,user) for 25s so a dead Spark doesn't hang every /api/services call behind 6s ssh timeout
- ssh_run timeout reduced 10 -> 6s for docker_state probes
- hardware probe: shorter SSH timeout (6s), longer cache TTL for failures (25s)
- JS pollStatus retries loadModels() if state.models is empty (recovers from cold-start proxy timeout)
- Unreachable hardware card now includes troubleshooting steps (Spark Control cannot SSH into an unreachable Spark to restart it)

v0.4 NIM installer:
- nim.py module: curated SUGGESTED_NIMS list (Parakeet, Magpie, Riva) + NimManager that runs docker login nvcr.io + docker pull + docker run -d --gpus all -p PORT:PORT -v VOL:/opt/nim/.cache -e NGC_API_KEY -e ... --restart=unless-stopped + chown the volume to uid 1000 + restart. Streams all output via SSE; redacts the API key from log lines.
- custom_services.py: persists installed NIMs to /data/services-overrides.yaml so they appear in the services panel after install
- services.py: merges custom services into the panel
- /api/nim/catalog GET, /api/nim/install POST + GET/SSE
- /api/services/{name} DELETE for custom services
- UI: '+ Install NIM' button next to 'Always-on services'; modal lists curated images each with a 'Pick' button + a custom-image form; installation runs in a second dialog with phase + elapsed timer + collapsible log
- NGC API key field added to Configure Sparks (masked); injected as NGC_API_KEY env var into the container

Package: bump 0.4.0:0; main.ts adds SERVICES_OVERRIDES + NGC_API_KEY env vars

image/app/static/index.html

@@ -76,8 +76,66 @@
     </section>
 
     <section id="services-panel" class="services hidden">
-      <h2 class="section-title">Always-on services</h2>
+      <div class="section-header">
+        <h2 class="section-title">Always-on services</h2>
+        <button id="open-nim" class="btn small-btn">+ Install NIM</button>
+      </div>
       <div id="services-grid" class="services-grid"></div>
+
+      <dialog id="nim-dialog" class="modal">
+        <form method="dialog" class="modal-form" id="nim-form">
+          <h3>Install a NVIDIA NIM container</h3>
+          <p class="muted small" id="nim-key-warn"></p>
+          <p class="muted small">Pick a curated container below or paste any image from <a href="#" id="nim-catalog-link" target="_blank" rel="noopener">the NGC NIM catalog</a>. Spark Control will <code>docker pull</code> and <code>docker run</code> it on the target Spark.</p>
+
+          <div id="nim-suggested" class="nim-grid"></div>
+
+          <fieldset class="modal-fieldset">
+            <legend>Custom image</legend>
+            <label class="modal-row"><span>Image (nvcr.io/...)</span><input type="text" id="nim-image" placeholder="nvcr.io/nim/nvidia/<name>:latest"></label>
+            <label class="modal-row"><span>Container name</span><input type="text" id="nim-container" placeholder="my-service"></label>
+            <label class="modal-row"><span>Port</span><input type="number" id="nim-port" min="1" max="65535"></label>
+            <label class="modal-row"><span>Kind</span>
+              <select id="nim-kind">
+                <option value="nim">NIM (other)</option>
+                <option value="stt">STT (speech-to-text)</option>
+                <option value="tts">TTS (text-to-speech)</option>
+                <option value="vision">Vision</option>
+                <option value="embedding">Embedding</option>
+              </select>
+            </label>
+            <label class="modal-row"><span>Target Spark</span>
+              <select id="nim-host">
+                <option value="spark2">Spark 2 (default for support services)</option>
+                <option value="spark1">Spark 1 (head node)</option>
+              </select>
+            </label>
+          </fieldset>
+
+          <div class="modal-actions">
+            <button type="button" id="nim-cancel" class="btn">Cancel</button>
+            <button type="submit" class="btn primary" id="nim-start">Install</button>
+          </div>
+        </form>
+      </dialog>
+
+      <dialog id="nim-progress-dialog" class="modal">
+        <form method="dialog" class="modal-form">
+          <h3 id="nim-prog-title">Installing…</h3>
+          <div class="phase-row">
+            <div class="phase" id="nim-prog-phase">Starting…</div>
+            <span class="spacer"></span>
+            <span class="timer" id="nim-prog-elapsed">0:00</span>
+          </div>
+          <details open>
+            <summary class="muted small">Log</summary>
+            <pre id="nim-prog-log" class="log"></pre>
+          </details>
+          <div class="modal-actions">
+            <button type="button" id="nim-prog-close" class="btn">Close</button>
+          </div>
+        </form>
+      </dialog>
     </section>
 
     <section id="models-section">