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.
2026-08-21 05:29:23 +03:00
parent a9cf2e0f90
commit 2005b00175
43 changed files with 2258 additions and 197 deletions
@@ -0,0 +1,100 @@
+"""Interactive setup wizard: files + LLM_RUNTIME + optional watchdog."""
+
+from __future__ import annotations
+
+import shutil
+from collections.abc import Callable
+from pathlib import Path
+
+from gpu_rent.llm_runtime import (
+    PRESET_HELP,
+    append_vars_llm_runtime,
+    ensure_ollama_manifest_from_example,
+    normalize_runtime,
+    write_ollama_models_preset,
+)
+from gpu_rent.paths import (
+    app_root,
+    env_path,
+    extensions_manifest_path,
+    models_manifest_path,
+    ollama_models_example_path,
+    ollama_models_manifest_path,
+    vars_example_path,
+    vars_path,
+)
+
+Log = Callable[[str], None]
+
+
+def _copy_if_missing(src: Path, dst: Path, label: str, log: Log) -> None:
+    if dst.is_file():
+        log(f"есть {label}")
+        return
+    if src.is_file():
+        shutil.copy2(src, dst)
+        log(f"создал {label} из example")
+    else:
+        log(f"нет example для {label}: {src}")
+
+
+def run_setup(
+    *,
+    llm: str | None = None,
+    ollama_preset: str | None = None,
+    install_watchdog: bool | None = None,
+    confirm: Callable[[str], bool] | None = None,
+    ask: Callable[[str, str], str] | None = None,
+    log: Log = print,
+) -> None:
+    root = app_root()
+    log(f"setup в {root}")
+
+    _copy_if_missing(root / "env.example", env_path(), ".env", log)
+    _copy_if_missing(root / "models.example.yaml", models_manifest_path(), "models.yaml", log)
+    _copy_if_missing(
+        root / "extensions.example.yaml", extensions_manifest_path(), "extensions.yaml", log
+    )
+    _copy_if_missing(vars_example_path(), vars_path(), "gpu-rent.vars", log)
+    _copy_if_missing(
+        ollama_models_example_path(), ollama_models_manifest_path(), "ollama-models.yaml", log
+    )
+
+    runtime = llm
+    if runtime is None:
+        if ask:
+            runtime = ask(
+                "LLM runtime [none/ollama/llamacpp]",
+                "none",
+            )
+        else:
+            runtime = "none"
+    runtime = normalize_runtime(runtime)
+    append_vars_llm_runtime(vars_path(), runtime)
+    log(f"LLM_RUNTIME={runtime} → gpu-rent.vars")
+
+    if runtime == "ollama":
+        preset = ollama_preset
+        if preset is None and ask:
+            log(PRESET_HELP)
+            preset = ask("Ollama preset [recommended/light/stock/alt/empty]", "recommended")
+        if preset is None:
+            preset = "recommended"
+        if preset.strip().lower() in {"keep", "example", ""}:
+            ensure_ollama_manifest_from_example()
+            log("ollama-models.yaml из example")
+        else:
+            write_ollama_models_preset(ollama_models_manifest_path(), preset)
+            log(f"ollama-models.yaml пресет={preset}")
+
+    do_wd = install_watchdog
+    if do_wd is None and confirm:
+        do_wd = confirm("Установить local-watchdog (аварийный stop без Ctrl+C)?")
+    if do_wd:
+        from gpu_rent.local_watchdog import install_watchdog as _install
+
+        _install(log=log)
+    elif do_wd is False:
+        log("local-watchdog: skip")
+
+    log("готово. Заполни .env (OS_*), потом: gpu-rent doctor && gpu-rent up")