pi-usereq 0.7.0 → 0.10.0

package/pi.dev-src/pi-mono/pods/scripts/pod_setup.sh

@@ -0,0 +1,336 @@
+#!/usr/bin/env bash
+# GPU pod bootstrap for vLLM deployment
+set -euo pipefail
+
+# Parse arguments passed from pi CLI
+MOUNT_COMMAND=""
+MODELS_PATH=""
+HF_TOKEN=""
+PI_API_KEY=""
+VLLM_VERSION="release"  # Default to release
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --mount)
+            MOUNT_COMMAND="$2"
+            shift 2
+            ;;
+        --models-path)
+            MODELS_PATH="$2"
+            shift 2
+            ;;
+        --hf-token)
+            HF_TOKEN="$2"
+            shift 2
+            ;;
+        --vllm-api-key)
+            PI_API_KEY="$2"
+            shift 2
+            ;;
+        --vllm)
+            VLLM_VERSION="$2"
+            shift 2
+            ;;
+        *)
+            echo "ERROR: Unknown option: $1" >&2
+            exit 1
+            ;;
+    esac
+done
+
+# Validate required parameters
+if [ -z "$HF_TOKEN" ]; then
+    echo "ERROR: HF_TOKEN is required" >&2
+    exit 1
+fi
+
+if [ -z "$PI_API_KEY" ]; then
+    echo "ERROR: PI_API_KEY is required" >&2
+    exit 1
+fi
+
+if [ -z "$MODELS_PATH" ]; then
+    echo "ERROR: MODELS_PATH is required" >&2
+    exit 1
+fi
+
+echo "=== Starting pod setup ==="
+
+# Install system dependencies
+apt update -y
+apt install -y python3-pip python3-venv git build-essential cmake ninja-build curl wget lsb-release htop pkg-config
+
+# --- Install matching CUDA toolkit -------------------------------------------
+echo "Checking CUDA driver version..."
+DRIVER_CUDA_VERSION=$(nvidia-smi | grep "CUDA Version" | awk '{print $9}')
+echo "Driver supports CUDA: $DRIVER_CUDA_VERSION"
+
+# Check if nvcc exists and its version
+if command -v nvcc &> /dev/null; then
+    NVCC_VERSION=$(nvcc --version | grep "release" | awk '{print $6}' | cut -d, -f1)
+    echo "Current nvcc version: $NVCC_VERSION"
+else
+    NVCC_VERSION="none"
+    echo "nvcc not found"
+fi
+
+# Install CUDA toolkit matching driver version if needed
+if [[ "$NVCC_VERSION" != "$DRIVER_CUDA_VERSION" ]]; then
+    echo "Installing CUDA Toolkit $DRIVER_CUDA_VERSION to match driver..."
+
+    # Detect Ubuntu version
+    UBUNTU_VERSION=$(lsb_release -rs)
+    UBUNTU_CODENAME=$(lsb_release -cs)
+
+    echo "Detected Ubuntu $UBUNTU_VERSION ($UBUNTU_CODENAME)"
+
+    # Map Ubuntu version to NVIDIA repo path
+    if [[ "$UBUNTU_VERSION" == "24.04" ]]; then
+        REPO_PATH="ubuntu2404"
+    elif [[ "$UBUNTU_VERSION" == "22.04" ]]; then
+        REPO_PATH="ubuntu2204"
+    elif [[ "$UBUNTU_VERSION" == "20.04" ]]; then
+        REPO_PATH="ubuntu2004"
+    else
+        echo "Warning: Unsupported Ubuntu version $UBUNTU_VERSION, trying ubuntu2204"
+        REPO_PATH="ubuntu2204"
+    fi
+
+    # Add NVIDIA package repositories
+    wget https://developer.download.nvidia.com/compute/cuda/repos/${REPO_PATH}/x86_64/cuda-keyring_1.1-1_all.deb
+    dpkg -i cuda-keyring_1.1-1_all.deb
+    rm cuda-keyring_1.1-1_all.deb
+    apt-get update
+
+    # Install specific CUDA toolkit version
+    # Convert version format (12.9 -> 12-9)
+    CUDA_VERSION_APT=$(echo $DRIVER_CUDA_VERSION | sed 's/\./-/')
+    echo "Installing cuda-toolkit-${CUDA_VERSION_APT}..."
+    apt-get install -y cuda-toolkit-${CUDA_VERSION_APT}
+
+    # Add CUDA to PATH
+    export PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:$PATH
+    export LD_LIBRARY_PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:${LD_LIBRARY_PATH:-}
+
+    # Verify installation
+    nvcc --version
+else
+    echo "CUDA toolkit $NVCC_VERSION matches driver version"
+    export PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:$PATH
+    export LD_LIBRARY_PATH=/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:${LD_LIBRARY_PATH:-}
+fi
+
+# --- Install uv (fast Python package manager) --------------------------------
+curl -LsSf https://astral.sh/uv/install.sh | sh
+export PATH="$HOME/.local/bin:$PATH"
+
+# --- Install Python 3.12 if not available ------------------------------------
+if ! command -v python3.12 &> /dev/null; then
+    echo "Python 3.12 not found. Installing via uv..."
+    uv python install 3.12
+fi
+
+# --- Clean up existing environments and caches -------------------------------
+echo "Cleaning up existing environments and caches..."
+
+# Remove existing venv for a clean installation
+VENV="$HOME/venv"
+if [ -d "$VENV" ]; then
+    echo "Removing existing virtual environment..."
+    rm -rf "$VENV"
+fi
+
+# Remove uv cache to ensure fresh installs
+if [ -d "$HOME/.cache/uv" ]; then
+    echo "Clearing uv cache..."
+    rm -rf "$HOME/.cache/uv"
+fi
+
+# Remove vLLM cache to avoid conflicts
+if [ -d "$HOME/.cache/vllm" ]; then
+    echo "Clearing vLLM cache..."
+    rm -rf "$HOME/.cache/vllm"
+fi
+
+# --- Create and activate venv ------------------------------------------------
+echo "Creating fresh virtual environment..."
+uv venv --python 3.12 --seed "$VENV"
+source "$VENV/bin/activate"
+
+# --- Install PyTorch and vLLM ------------------------------------------------
+echo "Installing vLLM and dependencies (version: $VLLM_VERSION)..."
+case "$VLLM_VERSION" in
+    release)
+        echo "Installing vLLM release with PyTorch..."
+        # Install vLLM with automatic PyTorch backend selection
+        # vLLM will automatically install the correct PyTorch version
+        uv pip install vllm>=0.10.0 --torch-backend=auto || {
+            echo "ERROR: Failed to install vLLM"
+            exit 1
+        }
+        ;;
+    nightly)
+        echo "Installing vLLM nightly with PyTorch..."
+        echo "This will install the latest nightly build of vLLM..."
+
+        # Install vLLM nightly with PyTorch
+        uv pip install -U vllm \
+            --torch-backend=auto \
+            --extra-index-url https://wheels.vllm.ai/nightly || {
+            echo "ERROR: Failed to install vLLM nightly"
+            exit 1
+        }
+
+        echo "vLLM nightly successfully installed!"
+        ;;
+    gpt-oss)
+        echo "Installing GPT-OSS special build with PyTorch nightly..."
+        echo "WARNING: This build is ONLY for GPT-OSS models!"
+        echo "Installing PyTorch nightly and cutting-edge dependencies..."
+
+        # Convert CUDA version format for PyTorch (12.4 -> cu124)
+        PYTORCH_CUDA="cu$(echo $DRIVER_CUDA_VERSION | sed 's/\.//')"
+        echo "Using PyTorch nightly with ${PYTORCH_CUDA} (driver supports ${DRIVER_CUDA_VERSION})"
+
+        # The GPT-OSS build will pull PyTorch nightly and other dependencies
+        # via the extra index URLs. We don't pre-install torch here to avoid conflicts.
+        uv pip install --pre vllm==0.10.1+gptoss \
+            --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
+            --extra-index-url https://download.pytorch.org/whl/nightly/${PYTORCH_CUDA} \
+            --index-strategy unsafe-best-match || {
+            echo "ERROR: Failed to install GPT-OSS vLLM build"
+            echo "This automatically installs PyTorch nightly with ${PYTORCH_CUDA}, Triton nightly, and other dependencies"
+            exit 1
+        }
+
+        # Install gpt-oss library for tool support
+        uv pip install gpt-oss || {
+            echo "WARNING: Failed to install gpt-oss library (needed for tool use)"
+        }
+        ;;
+    *)
+        echo "ERROR: Unknown vLLM version: $VLLM_VERSION"
+        exit 1
+        ;;
+esac
+
+# --- Install additional packages ---------------------------------------------
+echo "Installing additional packages..."
+# Note: tensorrt removed temporarily due to CUDA 13.0 compatibility issues
+# TensorRT still depends on deprecated nvidia-cuda-runtime-cu13 package
+uv pip install huggingface-hub psutil hf_transfer
+
+# --- FlashInfer installation (optional, improves performance) ----------------
+echo "Attempting FlashInfer installation (optional)..."
+if uv pip install flashinfer-python; then
+    echo "FlashInfer installed successfully"
+else
+    echo "FlashInfer not available, using Flash Attention instead"
+fi
+
+# --- Mount storage if provided -----------------------------------------------
+if [ -n "$MOUNT_COMMAND" ]; then
+    echo "Setting up mount..."
+
+    # Create mount point directory if it doesn't exist
+    mkdir -p "$MODELS_PATH"
+
+    # Execute the mount command
+    eval "$MOUNT_COMMAND" || {
+        echo "WARNING: Mount command failed, continuing without mount"
+    }
+
+    # Verify mount succeeded (optional, may not always be a mount point)
+    if mountpoint -q "$MODELS_PATH" 2>/dev/null; then
+        echo "Storage successfully mounted at $MODELS_PATH"
+    else
+        echo "Note: $MODELS_PATH is not a mount point (might be local storage)"
+    fi
+fi
+
+# --- Model storage setup ------------------------------------------------------
+echo ""
+echo "=== Setting up model storage ==="
+echo "Storage path: $MODELS_PATH"
+
+# Check if the path exists and is writable
+if [ ! -d "$MODELS_PATH" ]; then
+    echo "Creating model storage directory: $MODELS_PATH"
+    mkdir -p "$MODELS_PATH"
+fi
+
+if [ ! -w "$MODELS_PATH" ]; then
+    echo "ERROR: Model storage path is not writable: $MODELS_PATH"
+    echo "Please check permissions"
+    exit 1
+fi
+
+# Create the huggingface cache directory structure in the models path
+mkdir -p "${MODELS_PATH}/huggingface/hub"
+
+# Remove any existing cache directory or symlink
+if [ -e ~/.cache/huggingface ] || [ -L ~/.cache/huggingface ]; then
+    echo "Removing existing ~/.cache/huggingface..."
+    rm -rf ~/.cache/huggingface 2>/dev/null || true
+fi
+
+# Create parent directory if needed
+mkdir -p ~/.cache
+
+# Create symlink from ~/.cache/huggingface to the models path
+ln -s "${MODELS_PATH}/huggingface" ~/.cache/huggingface
+echo "Created symlink: ~/.cache/huggingface -> ${MODELS_PATH}/huggingface"
+
+# Verify the symlink works
+if [ -d ~/.cache/huggingface/hub ]; then
+    echo "✓ Model storage configured successfully"
+
+    # Check available space
+    AVAILABLE_SPACE=$(df -h "$MODELS_PATH" | awk 'NR==2 {print $4}')
+    echo "Available space: $AVAILABLE_SPACE"
+else
+    echo "ERROR: Could not verify model storage setup"
+    echo "The symlink was created but the target directory is not accessible"
+    exit 1
+fi
+
+# --- Configure environment ----------------------------------------------------
+mkdir -p ~/.config/vllm
+touch ~/.config/vllm/do_not_track
+
+# Write environment to .bashrc for persistence
+cat >> ~/.bashrc << EOF
+
+# Pi vLLM environment
+[ -d "\$HOME/venv" ] && source "\$HOME/venv/bin/activate"
+export PATH="/usr/local/cuda-${DRIVER_CUDA_VERSION}/bin:\$HOME/.local/bin:\$PATH"
+export LD_LIBRARY_PATH="/usr/local/cuda-${DRIVER_CUDA_VERSION}/lib64:\${LD_LIBRARY_PATH:-}"
+export HF_TOKEN="${HF_TOKEN}"
+export PI_API_KEY="${PI_API_KEY}"
+export HUGGING_FACE_HUB_TOKEN="${HF_TOKEN}"
+export HF_HUB_ENABLE_HF_TRANSFER=1
+export VLLM_NO_USAGE_STATS=1
+export VLLM_DO_NOT_TRACK=1
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+EOF
+
+# Create log directory for vLLM
+mkdir -p ~/.vllm_logs
+
+# --- Output GPU info for pi CLI to parse -------------------------------------
+echo ""
+echo "===GPU_INFO_START==="
+nvidia-smi --query-gpu=index,name,memory.total --format=csv,noheader | while IFS=, read -r id name memory; do
+    # Trim whitespace
+    id=$(echo "$id" | xargs)
+    name=$(echo "$name" | xargs)
+    memory=$(echo "$memory" | xargs)
+    echo "{\"id\": $id, \"name\": \"$name\", \"memory\": \"$memory\"}"
+done
+echo "===GPU_INFO_END==="
+
+echo ""
+echo "=== Setup complete ==="
+echo "Pod is ready for vLLM deployments"
+echo "Models will be cached at: $MODELS_PATH"

package/pi.dev-src/pi-mono/pods/src/cli.ts

@@ -0,0 +1,360 @@
+#!/usr/bin/env node
+import chalk from "chalk";
+import { spawn } from "child_process";
+import { readFileSync } from "fs";
+import { dirname, join } from "path";
+import { fileURLToPath } from "url";
+import { listModels, showKnownModels, startModel, stopAllModels, stopModel, viewLogs } from "./commands/models.js";
+import { listPods, removePodCommand, setupPod, switchActivePod } from "./commands/pods.js";
+import { promptModel } from "./commands/prompt.js";
+import { getActivePod, loadConfig } from "./config.js";
+import { sshExecStream } from "./ssh.js";
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const packageJson = JSON.parse(readFileSync(join(__dirname, "../package.json"), "utf-8"));
+
+function printHelp() {
+	console.log(`pi v${packageJson.version} - Manage vLLM deployments on GPU pods
+
+Pod Management:
+  pi pods setup <name> "<ssh>" --mount "<mount>"    Setup pod with mount command
+    Options:
+      --vllm release    Install latest vLLM release >=0.10.0 (default)
+      --vllm nightly    Install vLLM nightly build (latest features)
+      --vllm gpt-oss    Install vLLM 0.10.1+gptoss with PyTorch nightly (GPT-OSS only)
+  pi pods                                           List all pods (* = active)
+  pi pods active <name>                             Switch active pod
+  pi pods remove <name>                             Remove pod from local config
+  pi shell [<name>]                                 Open shell on pod (active or specified)
+  pi ssh [<name>] "<command>"                       Run SSH command on pod
+
+Model Management:
+  pi start <model> --name <name> [options]          Start a model
+    --memory <percent>   GPU memory allocation (30%, 50%, 90%)
+    --context <size>     Context window (4k, 8k, 16k, 32k, 64k, 128k)
+    --gpus <count>       Number of GPUs to use (predefined models only)
+    --vllm <args...>     Pass remaining args to vLLM (ignores other options)
+  pi stop [<name>]                                  Stop model (or all if no name)
+  pi list                                           List running models
+  pi logs <name>                                    Stream model logs
+  pi agent <name> ["<message>"...] [options]        Chat with model using agent & tools
+  pi agent <name> [options]                         Interactive chat mode
+    --continue, -c       Continue previous session
+    --json              Output as JSONL
+    (All pi-agent options are supported)
+
+  All model commands support --pod <name> to override the active pod.
+
+Environment:
+  HF_TOKEN         HuggingFace token for model downloads
+  PI_API_KEY     API key for vLLM endpoints
+  PI_CONFIG_DIR    Config directory (default: ~/.pi)`);
+}
+
+// Parse command line arguments
+const args = process.argv.slice(2);
+
+if (args.length === 0 || args[0] === "--help" || args[0] === "-h") {
+	printHelp();
+	process.exit(0);
+}
+
+if (args[0] === "--version" || args[0] === "-v") {
+	console.log(packageJson.version);
+	process.exit(0);
+}
+
+const command = args[0];
+const subcommand = args[1];
+
+// Main command handler
+try {
+	// Handle "pi pods" commands
+	if (command === "pods") {
+		if (!subcommand) {
+			// pi pods - list all pods
+			listPods();
+		} else if (subcommand === "setup") {
+			// pi pods setup <name> "<ssh>" [--mount "<mount>"] [--models-path <path>] [--vllm release|nightly|gpt-oss]
+			const name = args[2];
+			const sshCmd = args[3];
+
+			if (!name || !sshCmd) {
+				console.error(
+					'Usage: pi pods setup <name> "<ssh>" [--mount "<mount>"] [--models-path <path>] [--vllm release|nightly|gpt-oss]',
+				);
+				process.exit(1);
+			}
+
+			// Parse options
+			const options: { mount?: string; modelsPath?: string; vllm?: "release" | "nightly" | "gpt-oss" } = {};
+			for (let i = 4; i < args.length; i++) {
+				if (args[i] === "--mount" && i + 1 < args.length) {
+					options.mount = args[i + 1];
+					i++;
+				} else if (args[i] === "--models-path" && i + 1 < args.length) {
+					options.modelsPath = args[i + 1];
+					i++;
+				} else if (args[i] === "--vllm" && i + 1 < args.length) {
+					const vllmType = args[i + 1];
+					if (vllmType === "release" || vllmType === "nightly" || vllmType === "gpt-oss") {
+						options.vllm = vllmType;
+					} else {
+						console.error(chalk.red(`Invalid vLLM type: ${vllmType}`));
+						console.error("Valid options: release, nightly, gpt-oss");
+						process.exit(1);
+					}
+					i++;
+				}
+			}
+
+			// If --mount provided but no --models-path, try to extract path from mount command
+			if (options.mount && !options.modelsPath) {
+				// Extract last part of mount command as models path
+				const parts = options.mount.trim().split(" ");
+				const lastPart = parts[parts.length - 1];
+				if (lastPart?.startsWith("/")) {
+					options.modelsPath = lastPart;
+				}
+			}
+
+			await setupPod(name, sshCmd, options);
+		} else if (subcommand === "active") {
+			// pi pods active <name>
+			const name = args[2];
+			if (!name) {
+				console.error("Usage: pi pods active <name>");
+				process.exit(1);
+			}
+			switchActivePod(name);
+		} else if (subcommand === "remove") {
+			// pi pods remove <name>
+			const name = args[2];
+			if (!name) {
+				console.error("Usage: pi pods remove <name>");
+				process.exit(1);
+			}
+			removePodCommand(name);
+		} else {
+			console.error(`Unknown pods subcommand: ${subcommand}`);
+			process.exit(1);
+		}
+	} else {
+		// Parse --pod override for model commands
+		let podOverride: string | undefined;
+		const podIndex = args.indexOf("--pod");
+		if (podIndex !== -1 && podIndex + 1 < args.length) {
+			podOverride = args[podIndex + 1];
+			// Remove --pod and its value from args
+			args.splice(podIndex, 2);
+		}
+
+		// Handle SSH/shell commands and model commands
+		switch (command) {
+			case "shell": {
+				// pi shell [<name>] - open interactive shell
+				const podName = args[1];
+				let podInfo: { name: string; pod: import("./types.js").Pod } | null = null;
+
+				if (podName) {
+					const config = loadConfig();
+					const pod = config.pods[podName];
+					if (pod) {
+						podInfo = { name: podName, pod };
+					}
+				} else {
+					podInfo = getActivePod();
+				}
+
+				if (!podInfo) {
+					if (podName) {
+						console.error(chalk.red(`Pod '${podName}' not found`));
+					} else {
+						console.error(chalk.red("No active pod. Use 'pi pods active <name>' to set one."));
+					}
+					process.exit(1);
+				}
+
+				console.log(chalk.green(`Connecting to pod '${podInfo.name}'...`));
+
+				// Execute SSH in interactive mode
+				const sshArgs = podInfo.pod.ssh.split(" ").slice(1); // Remove 'ssh' from command
+				const sshProcess = spawn("ssh", sshArgs, {
+					stdio: "inherit",
+					env: process.env,
+				});
+
+				sshProcess.on("exit", (code) => {
+					process.exit(code || 0);
+				});
+				break;
+			}
+			case "ssh": {
+				// pi ssh [<name>] "<command>" - run command via SSH
+				let podName: string | undefined;
+				let sshCommand: string;
+
+				if (args.length === 2) {
+					// pi ssh "<command>" - use active pod
+					sshCommand = args[1];
+				} else if (args.length === 3) {
+					// pi ssh <name> "<command>"
+					podName = args[1];
+					sshCommand = args[2];
+				} else {
+					console.error('Usage: pi ssh [<name>] "<command>"');
+					process.exit(1);
+				}
+
+				let podInfo: { name: string; pod: import("./types.js").Pod } | null = null;
+
+				if (podName) {
+					const config = loadConfig();
+					const pod = config.pods[podName];
+					if (pod) {
+						podInfo = { name: podName, pod };
+					}
+				} else {
+					podInfo = getActivePod();
+				}
+
+				if (!podInfo) {
+					if (podName) {
+						console.error(chalk.red(`Pod '${podName}' not found`));
+					} else {
+						console.error(chalk.red("No active pod. Use 'pi pods active <name>' to set one."));
+					}
+					process.exit(1);
+				}
+
+				console.log(chalk.gray(`Running on pod '${podInfo.name}': ${sshCommand}`));
+
+				// Execute command and stream output
+				const exitCode = await sshExecStream(podInfo.pod.ssh, sshCommand);
+				process.exit(exitCode);
+				break;
+			}
+			case "start": {
+				// pi start <model> --name <name> [options]
+				const modelId = args[1];
+				if (!modelId) {
+					// Show available models
+					await showKnownModels();
+					process.exit(0);
+				}
+
+				// Parse options
+				let name: string | undefined;
+				let memory: string | undefined;
+				let context: string | undefined;
+				let gpus: number | undefined;
+				const vllmArgs: string[] = [];
+				let inVllmArgs = false;
+
+				for (let i = 2; i < args.length; i++) {
+					if (inVllmArgs) {
+						vllmArgs.push(args[i]);
+					} else if (args[i] === "--name" && i + 1 < args.length) {
+						name = args[i + 1];
+						i++;
+					} else if (args[i] === "--memory" && i + 1 < args.length) {
+						memory = args[i + 1];
+						i++;
+					} else if (args[i] === "--context" && i + 1 < args.length) {
+						context = args[i + 1];
+						i++;
+					} else if (args[i] === "--gpus" && i + 1 < args.length) {
+						gpus = parseInt(args[i + 1], 10);
+						if (Number.isNaN(gpus) || gpus < 1) {
+							console.error(chalk.red("--gpus must be a positive number"));
+							process.exit(1);
+						}
+						i++;
+					} else if (args[i] === "--vllm") {
+						inVllmArgs = true;
+					}
+				}
+
+				if (!name) {
+					console.error("--name is required");
+					process.exit(1);
+				}
+
+				// Warn if --vllm is used with other parameters
+				if (vllmArgs.length > 0 && (memory || context || gpus)) {
+					console.log(
+						chalk.yellow("⚠ Warning: --memory, --context, and --gpus are ignored when --vllm is specified"),
+					);
+					console.log(chalk.yellow("  Using only custom vLLM arguments"));
+					console.log("");
+				}
+
+				await startModel(modelId, name, {
+					pod: podOverride,
+					memory,
+					context,
+					gpus,
+					vllmArgs: vllmArgs.length > 0 ? vllmArgs : undefined,
+				});
+				break;
+			}
+			case "stop": {
+				// pi stop [name] - stop specific model or all models
+				const name = args[1];
+				if (!name) {
+					// Stop all models on the active pod
+					await stopAllModels({ pod: podOverride });
+				} else {
+					await stopModel(name, { pod: podOverride });
+				}
+				break;
+			}
+			case "list":
+				// pi list
+				await listModels({ pod: podOverride });
+				break;
+			case "logs": {
+				// pi logs <name>
+				const name = args[1];
+				if (!name) {
+					console.error("Usage: pi logs <name>");
+					process.exit(1);
+				}
+				await viewLogs(name, { pod: podOverride });
+				break;
+			}
+			case "agent": {
+				// pi agent <name> [messages...] [options]
+				const name = args[1];
+				if (!name) {
+					console.error("Usage: pi agent <name> [messages...] [options]");
+					process.exit(1);
+				}
+
+				const apiKey = process.env.PI_API_KEY;
+
+				// Pass all args after the model name
+				const agentArgs = args.slice(2);
+
+				// If no messages provided, it's interactive mode
+				await promptModel(name, agentArgs, {
+					pod: podOverride,
+					apiKey,
+				}).catch(() => {
+					// Error already handled in promptModel, just exit cleanly
+					process.exit(0);
+				});
+				break;
+			}
+			default:
+				console.error(`Unknown command: ${command}`);
+				printHelp();
+				process.exit(1);
+		}
+	}
+} catch (error) {
+	console.error("Error:", error);
+	process.exit(1);
+}