Update configuration and documentation for LLM support and local watchdog

- Added `ollama-models.yaml` to .gitignore and implemented logic to copy it in gpu-rent.ps1 and gpu-rent.sh.
- Enhanced env.example to include new variables for LLM runtime options and local watchdog configuration.
- Updated CLI commands to support LLM options during setup and execution, including new flags for Ollama and llama.cpp.
- Improved documentation in cli.md and README.md to reflect changes in LLM integration and local watchdog functionality.
- Adjusted architecture and decisions documentation to clarify the role of LLMs and local watchdog in the system.

src/gpu_rent/session.py

@@ -84,12 +84,25 @@ def _bind_access(
     save_state(state)
     wait_ssh(cfg, ip)
     log(f"SSH {cfg.ssh_user}@{ip}")
+    state.phase = "bootstrapping"
+    save_state(state)
     if update:
         active = run_ssh(cfg, ip, "systemctl is-active swarmui 2>/dev/null || true", check=False).strip()
         if active == "active":
             log("systemctl stop swarmui перед git update")
             run_ssh(cfg, ip, "sudo -n systemctl stop swarmui", timeout=120, check=False)
-    run_bootstrap(cfg, ip, log, update=update)
+    # Skip apt-heavy bootstrap when the VM already finished first-boot.
+    marker = run_ssh(
+        cfg,
+        ip,
+        "test -f /opt/swarmui/.gpu-rent-bootstrapped && echo yes || echo no",
+        check=False,
+    ).strip()
+    if marker == "yes" and state.bootstrapped:
+        log("bootstrap уже на VM — лёгкий проход (без apt)")
+        run_bootstrap(cfg, ip, log, update=update, light=True)
+    else:
+        run_bootstrap(cfg, ip, log, update=update, light=False)
     provision_vm(
         cfg,
         ip,
@@ -135,6 +148,8 @@ def adopt_server(cfg: Config, log: Log = _log_default, *, update: bool = True) -
     save_state(state)
     log(f"подхватили {server.id} статус {server_status(server)}")
     if server_status(server) == "ACTIVE":
+        state.phase = "bootstrapping"
+        save_state(state)
         _bind_access(conn, server, state, cfg, log, update=update)
     return state
 
@@ -165,7 +180,7 @@ def cmd_up(
             if status == "ACTIVE":
                 if state.bootstrapped and state.floating_ip:
                     log("сервер уже ACTIVE — второй GPU не создаём")
-                    state.phase = "ready_cloud"
+                    state.phase = "bootstrapping"
                     save_state(state)
                     _bind_access(conn, existing, state, cfg, log, update=do_update)
                     return state
@@ -187,7 +202,7 @@ def cmd_up(
                 outcome = probe_ssh(cfg, fip, attempts=2) if fip else "down"
                 if outcome == "ok":
                     log("сервер ACTIVE, SSH ок — продолжаем bootstrap")
-                    state.phase = "ready_cloud"
+                    state.phase = "bootstrapping"
                     save_state(state)
                     _bind_access(conn, existing, state, cfg, log, update=do_update)
                     return state
@@ -213,7 +228,7 @@ def cmd_up(
             if existing is not None and status in {"EXPIRED", "SHELVED", "SHELVED_OFFLOADED"}:
                 existing = unshelve(conn, existing, log)
                 state.server_id = existing.id
-                state.phase = "ready_cloud"
+                state.phase = "bootstrapping"
                 state.unshelved_at = utc_now()
                 save_state(state)
                 _bind_access(conn, existing, state, cfg, log, update=do_update)
@@ -341,7 +356,7 @@ def cmd_up(
         state.server_name = getattr(server, "name", None)
         state.created_at = utc_now()
         state.unshelved_at = None
-        state.phase = "ready_cloud"
+        state.phase = "bootstrapping"
         save_state(state)
         _bind_access(conn, server, state, cfg, log, update=do_update)
         return state
@@ -396,7 +411,14 @@ def cmd_stop(
 
         state.server_id = None
         state.server_name = None
+        state.bootstrapped = False
         state.phase = "idle"
         save_state(state)
+        try:
+            from gpu_rent.local_watchdog import clear_lease
+
+            clear_lease()
+        except Exception:
+            pass
         log("фаза idle" + ("" if destroy_disks else " (диски на месте)"))
         return state