feat(ml): operator model swap — GPU re-embed + embedder as a setting (#1190)

Make the SigLIP embedder an operator choice (drop-in to SigLIP 2:
google/siglip2-so400m-patch16-512 is a verified 1152-d model at 512px → no
schema change, better small-cue fidelity). A swap = set model + re-embed +
retrain, all operator-driven; the GPU agent does the re-embed so it's fast.

- settings: embedder_model_name is now a setting (migration 0065) alongside the
  existing embedder_model_version; both editable + validated (non-empty) in the
  ml admin API. The server embedder loads by HF name (AutoImageProcessor/Model,
  model-agnostic), preferring the pre-downloaded local dir for the default so
  existing deploys don't re-download; rebuilds on a name change.
- agent: new 'embed' job = whole-image SigLIP embedding (mean-pool video frames)
  under the lease-announced model → POST /jobs/submit_embedding writes
  image_record.siglip_embedding + siglip_model_version. The lease now announces
  the model FROM THE SETTING (not a constant).
- re-embed routing: enqueue_gpu_backfill('embed') selects unembedded + stale-
  version images; 'siglip' now re-embeds concept crops whose version != current
  (so a swap re-triggers crops, not just the never-embedded back-catalogue). The
  CPU ml-worker backfill no longer re-embeds on a version mismatch (it can't
  churn the library at 512px) — the GPU agent owns version re-embeds. Daily
  'embed' + 'siglip' beats self-heal.
- scoring: score_image only bags embeddings in the CURRENT model's space (whole-
  image gated by siglip_model_version, concept regions by embedding_version) so a
  mid-swap stale vector isn't scored by new-space heads; legacy NULL = current.
- UI: GpuAgentCard "Embedding model (advanced)" — edit name/version, Save, and
  "Re-embed library (GPU)" (queues embed + siglip); points at SigLIP 2.

Tests: lease announces model + submit_embedding round-trip; enqueue 'embed'
selects stale/unembedded; stale-version excluded from scoring; embedder model
settable + empty rejected; siglip gate updated to current-version concept.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

frontend/src/components/settings/GpuAgentCard.vue

@@ -106,6 +106,37 @@
       reversible) — so identity tags keep flowing without review. Stricter than
       the suggest cut; 0.92 recommended.
     </p>
+
+    <!-- Embedding model (advanced) -->
+    <div v-if="ml.settings" class="fc-section-h mt-5 mb-1">Embedding model (advanced)</div>
+    <div v-if="ml.settings">
+      <v-text-field
+        v-model="modelName" label="HF model name" density="compact" hide-details
+        variant="outlined" class="mb-2"
+      />
+      <v-text-field
+        v-model="modelVersion" label="Version stamp" density="compact" hide-details
+        variant="outlined"
+      />
+      <div class="d-flex mt-3" style="gap:8px">
+        <v-btn
+          size="small" variant="tonal" rounded="pill" :loading="savingModel"
+          prepend-icon="mdi-content-save" @click="onSaveModel"
+        >Save model</v-btn>
+        <v-btn
+          size="small" color="accent" variant="flat" rounded="pill"
+          :loading="reembedding" prepend-icon="mdi-backup-restore" @click="onReembed"
+        >Re-embed library (GPU)</v-btn>
+      </div>
+      <p class="fc-muted text-caption mt-2 mb-0">
+        Changing the model means a DIFFERENT embedding space. After saving a new
+        model + version, run <b>Re-embed library</b> (the GPU agent re-embeds
+        whole images + concept crops), then <b>Retrain heads</b>. Suggestions
+        degrade until both finish. SigLIP 2 (<code>google/siglip2-so400m-patch16-512</code>,
+        version <code>siglip2-so400m-patch16-512</code>) is a 1152-d drop-in at
+        512px — no schema change.
+      </p>
+    </div>
   </MaintenanceTile>
 </template>
 
@@ -131,6 +162,10 @@ const savingThreshold = ref(false)
 const autoApply = ref(true)
 const autoThreshold = ref(0.92)
 const savingAuto = ref(false)
+const modelName = ref('')
+const modelVersion = ref('')
+const savingModel = ref(false)
+const reembedding = ref(false)
 const queue = ref({ pending: 0, leased: 0, done: 0, error: 0 })
 let pollTimer = null
 
@@ -157,9 +192,42 @@ onMounted(async () => {
       autoApply.value = ml.settings.ccip_auto_apply_enabled
       autoThreshold.value = ml.settings.ccip_auto_apply_threshold
     }
+    if (ml.settings?.embedder_model_name != null) {
+      modelName.value = ml.settings.embedder_model_name
+      modelVersion.value = ml.settings.embedder_model_version
+    }
   } catch { /* non-fatal */ }
 })
 
+async function onSaveModel() {
+  savingModel.value = true
+  try {
+    await ml.patchSettings({
+      embedder_model_name: modelName.value.trim(),
+      embedder_model_version: modelVersion.value.trim(),
+    })
+    toast({ text: 'Embedding model saved — now Re-embed library, then Retrain heads', type: 'success' })
+  } catch (e) {
+    toast({ text: `Could not save model: ${e.message}`, type: 'error' })
+  } finally {
+    savingModel.value = false
+  }
+}
+
+async function onReembed() {
+  reembedding.value = true
+  try {
+    await store.backfill('embed')
+    await store.backfill('siglip')
+    toast({ text: 'Queued whole-image + concept re-embed — run the agent, then Retrain heads', type: 'success' })
+    await refreshQueue()
+  } catch (e) {
+    toast({ text: `Could not queue re-embed: ${e.message}`, type: 'error' })
+  } finally {
+    reembedding.value = false
+  }
+}
+
 async function onSaveAuto() {
   savingAuto.value = true
   try {