Declare the AI owner, and let every node borrow its model over the mesh

vv_is_ai_host() was `=== 'host1'`, which made a physical fact — that is where the
GPU is — look like a rule. AI_OWNER_HOST declares it, so the card can move to a
rebuilt host3 or a friend's spare.

The gate was also doing two jobs. Assistant docks and findings strips now ask
whether a model is reachable, so a node without a GPU gets them by borrowing;
the AI tab asks whether this is the owner, because that page carries the bug
reports, the index and the model configuration — the surface where the
vocabulary assumes you built the mesh.

Resolution is local, then owner, then anyone else declaring a model, pinned once
it answers. Pinned rather than re-derived per call: a mesh that re-decides every
request eventually decides differently mid-conversation, and a chat whose second
turn lands on another machine has no history there. Cleared only on a transport
failure, and only when there is somewhere else to go — a single-node mesh whose
model is down should say so, not report AI as unconfigured.

Plugin/unraid/Tools/ai_chat_worker.php

@@ -998,8 +998,13 @@ $ctx = stream_context_create(['http' => [
 
 $fh = @fopen($cfg['url'] . '/api/chat', 'r', false, $ctx);
 if ($fh === false) {
+    // Unpin, so the next question resolves to another node with a model rather than retrying a
+    // machine that is off. The error still names the endpoint that failed — "it moved on" is only
+    // useful alongside "here is what did not answer".
+    vv_ai_model_failed($cfg['model_host'] ?? '');
     jw($jobFile, ['status' => 'error',
-        'error' => 'Ollama did not respond within ' . max(30, $cfg['timeout']) . 's at ' . $cfg['url'],
+        'error' => 'Ollama did not respond within ' . max(30, $cfg['timeout']) . 's at ' . $cfg['url']
+                 . (!empty($cfg['borrowed']) ? ' (borrowed from ' . $cfg['model_host'] . ')' : ''),
         'sources' => $sources]);
     exit(1);
 }