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/remote/install_llamacpp.sh

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+# Install llama-server (CUDA) for OpenAI-compatible API on loopback :8080.
+set -euo pipefail
+
+SWARM_USER="${SWARM_USER:-ubuntu}"
+DATA_ROOT="/mnt/swarm_data"
+LLAMA_ROOT="${DATA_ROOT}/llamacpp"
+MODELS_DIR="${LLAMA_ROOT}/models"
+BIN_DIR="${LLAMA_ROOT}/bin"
+UNIT="gpu-rent-llamacpp"
+
+log() { echo "[gpu-rent-llamacpp] $*"; }
+
+if [[ "$(id -u)" -ne 0 ]]; then
+  echo "нужен root" >&2
+  exit 1
+fi
+
+mkdir -p "$MODELS_DIR" "$BIN_DIR"
+chown -R "${SWARM_USER}:${SWARM_USER}" "$LLAMA_ROOT"
+
+SERVER_BIN="${BIN_DIR}/llama-server"
+if [[ ! -x "$SERVER_BIN" ]]; then
+  log "скачиваю llama-server (cuda) release…"
+  # Pin a known-good release asset pattern; fallback to CPU if CUDA asset missing.
+  TMP="$(mktemp -d)"
+  cd "$TMP"
+  API="https://api.github.com/repos/ggerganov/llama.cpp/releases/latest"
+  URL="$(curl -fsSL "$API" | python3 -c '
+import json,sys,re
+data=json.load(sys.stdin)
+assets=data.get("assets") or []
+prefer=[]
+for a in assets:
+    n=(a.get("name") or "").lower()
+    u=a.get("browser_download_url") or ""
+    if not u.endswith(".zip") and not u.endswith(".tar.gz"):
+        continue
+    if "cuda" in n or "cu12" in n or "cu11" in n:
+        prefer.append(u)
+    elif "ubuntu" in n or "linux" in n:
+        prefer.append(u)
+print(prefer[0] if prefer else "")
+')"
+  if [[ -z "$URL" ]]; then
+    log "не нашёл бинарь в latest release — поставь llama-server вручную в ${SERVER_BIN}"
+    exit 1
+  fi
+  log "asset $URL"
+  curl -fL "$URL" -o pkg.bin
+  if file pkg.bin | grep -qi zip; then
+    apt-get install -y -qq unzip >/dev/null 2>&1 || true
+    unzip -qo pkg.bin -d out
+  else
+    mkdir -p out
+    tar -xaf pkg.bin -C out 2>/dev/null || tar -xzf pkg.bin -C out
+  fi
+  FOUND="$(find out -type f -name 'llama-server' | head -n1 || true)"
+  if [[ -z "$FOUND" ]]; then
+    FOUND="$(find out -type f -name 'server' | head -n1 || true)"
+  fi
+  if [[ -z "$FOUND" ]]; then
+    log "в архиве нет llama-server"
+    exit 1
+  fi
+  install -m 755 "$FOUND" "$SERVER_BIN"
+  chown "${SWARM_USER}:${SWARM_USER}" "$SERVER_BIN"
+  rm -rf "$TMP"
+fi
+
+# Pick first GGUF if present; otherwise unit starts but API may idle without model.
+MODEL_ARG=""
+FIRST_GGUF="$(find "$MODELS_DIR" -type f \( -name '*.gguf' -o -name '*.GGUF' \) | head -n1 || true)"
+if [[ -n "$FIRST_GGUF" ]]; then
+  MODEL_ARG="-m ${FIRST_GGUF}"
+  log "модель ${FIRST_GGUF}"
+else
+  log "нет GGUF в ${MODELS_DIR} — положи файл вручную и systemctl restart ${UNIT}"
+fi
+
+cat >/etc/systemd/system/${UNIT}.service <<EOF
+[Unit]
+Description=gpu-rent llama.cpp server (loopback)
+After=network-online.target local-fs.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=${SWARM_USER}
+Group=${SWARM_USER}
+WorkingDirectory=${LLAMA_ROOT}
+ExecStart=${SERVER_BIN} ${MODEL_ARG} --host 127.0.0.1 --port 8080
+Restart=on-failure
+RestartSec=8
+
+[Install]
+WantedBy=multi-user.target
+EOF
+
+systemctl daemon-reload
+systemctl enable "$UNIT"
+systemctl restart "$UNIT" || log "unit стартовал с ошибкой (часто нет GGUF) — проверь journalctl -u ${UNIT}"
+log "ok — http://127.0.0.1:8080 models=${MODELS_DIR}"