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/provision.py

@@ -254,6 +254,61 @@ def ensure_swarmui_running(cfg: Config, host: str, log: Log, restart: bool) -> N
     run_ssh(cfg, host, "sudo -n systemctl enable swarmui", check=False)
 
 
+def provision_llm(cfg: Config, host: str, log: Log) -> None:
+    from gpu_rent.llm_runtime import normalize_runtime, parse_ollama_models
+    from gpu_rent.ssh_ops import run_script_sudo
+    from gpu_rent.state import load_state, save_state
+
+    runtime = normalize_runtime(cfg.llm_runtime)
+    if runtime == "none":
+        st = load_state()
+        st.notes = dict(st.notes or {})
+        st.notes["llm_runtime"] = "none"
+        save_state(st)
+        return
+    if runtime == "ollama":
+        log("LLM: ставим/запускаем Ollama")
+        run_script_sudo(
+            cfg,
+            host,
+            _pkg_text("install_ollama.sh"),
+            remote_path="/tmp/gpu-rent-install_ollama.sh",
+            timeout=900,
+            env={"SWARM_USER": cfg.ssh_user},
+            log=log,
+        )
+        entries = parse_ollama_models(cfg.ollama_models_manifest)
+        names = [e.name for e in entries]
+        if not names:
+            log("ollama-models.yaml пуст — pull skip")
+        else:
+            put_text(cfg, host, "/tmp/gpu-rent-ollama-models.json", json.dumps(names, indent=2))
+            log(f"Ollama: pull {len(names)} из манифеста")
+            run_python(
+                cfg,
+                host,
+                _pkg_text("ollama_pull.py"),
+                remote_path="/tmp/gpu-rent-ollama_pull.py",
+                timeout=7200,
+                log=log,
+            )
+    elif runtime == "llamacpp":
+        log("LLM: ставим/запускаем llama.cpp server")
+        run_script_sudo(
+            cfg,
+            host,
+            _pkg_text("install_llamacpp.sh"),
+            remote_path="/tmp/gpu-rent-install_llamacpp.sh",
+            timeout=1200,
+            env={"SWARM_USER": cfg.ssh_user},
+            log=log,
+        )
+    st = load_state()
+    st.notes = dict(st.notes or {})
+    st.notes["llm_runtime"] = runtime
+    save_state(st)
+
+
 def provision_vm(
     cfg: Config,
     host: str,
@@ -282,10 +337,21 @@ def provision_vm(
     if cfg.pull_output:
         pull_tree(cfg, host, f"{DATA}/Output", cfg.local_output_dir, log)
     ensure_swarmui_running(cfg, host, log, restart=restart)
+    try:
+        provision_llm(cfg, host, log)
+    except Exception as exc:
+        log(f"LLM runtime: {exc}")
     if conn is not None and server_id:
         try:
             arm_idle_killer(cfg, host, conn, server_id, log)
         except GpuRentError as exc:
             log(f"idle-killer: {exc}")
     log("SwarmUI слушает 127.0.0.1:7801 — gpu-rent tunnel")
+    from gpu_rent.llm_runtime import normalize_runtime
+
+    rt = normalize_runtime(cfg.llm_runtime)
+    if rt == "ollama":
+        log(f"Ollama API → localhost:{cfg.ollama_local_port} (туннель)")
+    elif rt == "llamacpp":
+        log(f"llama.cpp → localhost:{cfg.llamacpp_local_port} (туннель)")
     log("Hold killer: gpu-rent hold   |  Стоп GPU: gpu-rent stop")