Seed Assistent personas as overlay folders and tighten Ollama/Assistent glue.

gpu-rent now writes personas/<id>/ on the VM (not legacy personas.json), adds seed-personas/doctor checks, and shortens mid/high keep-alive now that Assistent parks the LLM before Generate.

Co-authored-by: Cursor <cursoragent@cursor.com>

src/gpu_rent/cli.py

@@ -324,6 +324,16 @@ def status() -> None:
                 table.add_row("idle-killer", f"{killer_line} · arm ok (сессия)")
             else:
                 table.add_row("idle-killer", killer_line)
+            try:
+                from gpu_rent.provision import count_wanted_models_on_vm
+
+                wanted_n = count_wanted_models_on_vm(cfg, state.floating_ip)
+                table.add_row(
+                    "Assistent wanted",
+                    f"{wanted_n} в очереди" if wanted_n else "пусто",
+                )
+            except Exception:
+                table.add_row("Assistent wanted", "—")
         except GpuRentError as exc:
             table.add_row("диск used/free", f"SSH: {exc}")
             table.add_row("idle-killer", "нет SSH")
@@ -932,6 +942,18 @@ def seed_extensions_cmd() -> None:
         _die(exc)
 
 
+@app.command("seed-personas")
+def seed_personas_cmd() -> None:
+    """Push assistent-personas.yaml → VM Assistent overlay (без полного up)."""
+    try:
+        from gpu_rent.provision import seed_assistent_personas
+
+        cfg, host = _live()
+        seed_assistent_personas(cfg, host, log)
+    except GpuRentError as exc:
+        _die(exc)
+
+
 capture_app = typer.Typer(
     help=(
         "Снять с VM инвентарь → локальные манифесты (только ссылки, без весов). "