fix(cli): strip virtual-LLM lifecycle fields from llm apply-doc YAML

The smoke test \`llm.smoke > round-trips yaml output → apply -f\` failed
after v1 of the virtual-LLM feature: \`mcpctl get llm <name> -o yaml\`
output now starts with \`kind: public\` (the new schema column) instead
of \`kind: llm\` (the apply-doc envelope), because toApplyDocs spread
the cleaned item AFTER setting the kind, so the cleaned item's \`kind\`
overwrote.

Fix: in toApplyDocs, when serialising the \`llms\` resource, drop the
new lifecycle fields (kind, status, lastHeartbeatAt, inactiveSince,
providerSessionId) before merging. They collide with the apply-doc
envelope and aren't apply-able anyway — they're derived runtime state
owned by VirtualLlmService. Public-LLM round-trip is now byte-clean
(those fields default to public/active anyway). Virtual rows are
created by the registrar, not via apply -f, so dropping them on
output is the right call.

CLI suite: 437/437. Smoke will re-run against the live mcpd via
scripts/release.sh after merge.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/cli/src/commands/get.ts

@@ -408,6 +408,17 @@ function toApplyDocs(resource: string, items: unknown[]): Array<{ kind: string }
   const kind = RESOURCE_KIND[resource] ?? resource;
   return items.map((item) => {
     const cleaned = stripInternalFields(item as Record<string, unknown>);
+    // Llm-specific: the new virtual-provider lifecycle fields collide with
+    // the apply-doc `kind` envelope (the schema uses `kind: public|virtual`)
+    // and aren't apply-able anyway — they're derived runtime state managed
+    // by VirtualLlmService. Drop them so YAML round-trips stay clean.
+    if (resource === 'llms') {
+      delete cleaned['kind'];
+      delete cleaned['status'];
+      delete cleaned['lastHeartbeatAt'];
+      delete cleaned['inactiveSince'];
+      delete cleaned['providerSessionId'];
+    }
     return { kind, ...cleaned };
   });
 }