@google/gemini-cli 0.1.18 → 0.1.19-nightly.250813.9d023be1

package/README.md

@@ -1,215 +1,282 @@
 # Gemini CLI
 
 [![Gemini CLI CI](https://github.com/google-gemini/gemini-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/google-gemini/gemini-cli/actions/workflows/ci.yml)
+[![Version](https://img.shields.io/npm/v/@google/gemini-cli)](https://www.npmjs.com/package/@google/gemini-cli)
+[![License](https://img.shields.io/github/license/google-gemini/gemini-cli)](https://github.com/google-gemini/gemini-cli/blob/main/LICENSE)
 
 ![Gemini CLI Screenshot](./docs/assets/gemini-screenshot.png)
 
-This repository contains the Gemini CLI, a command-line AI workflow tool that connects to your
-tools, understands your code and accelerates your workflows.
+Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model.
 
-With the Gemini CLI you can:
+## 🚀 Why Gemini CLI?
 
-- Query and edit large codebases in and beyond Gemini's 1M token context window.
-- Generate new apps from PDFs or sketches, using Gemini's multimodal capabilities.
-- Automate operational tasks, like querying pull requests or handling complex rebases.
-- Use tools and MCP servers to connect new capabilities, including [media generation with Imagen,
-  Veo or Lyria](https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia)
-- Ground your queries with the [Google Search](https://ai.google.dev/gemini-api/docs/grounding)
-  tool, built into Gemini.
+- **🎯 Free tier**: 60 requests/min and 1,000 requests/day with personal Google account
+- **🧠 Powerful Gemini 2.5 Pro**: Access to 1M token context window
+- **🔧 Built-in tools**: Google Search grounding, file operations, shell commands, web fetching
+- **🔌 Extensible**: MCP (Model Context Protocol) support for custom integrations
+- **💻 Terminal-first**: Designed for developers who live in the command line
+- **🛡️ Open source**: Apache 2.0 licensed
 
-## Quickstart
+## 📦 Installation
 
-You have two options to install Gemini CLI.
+### Quick Install
 
-### With Node
+#### Run instantly with npx
 
-1. **Prerequisites:** Ensure you have [Node.js version 20](https://nodejs.org/en/download) or higher installed.
-2. **Run the CLI:** Execute the following command in your terminal:
+```bash
+# Using npx (no installation required)
+npx https://github.com/google-gemini/gemini-cli
+```
+
+#### Install globally with npm
+
+```bash
+npm install -g @google/gemini-cli
+```
 
-   ```bash
-   npx https://github.com/google-gemini/gemini-cli
-   ```
+#### Install globally with Homebrew (macOS/Linux)
 
-   Or install it with:
+```bash
+brew install gemini-cli
+```
 
-   ```bash
-   npm install -g @google/gemini-cli
-   ```
+#### System Requirements
 
-   Then, run the CLI from anywhere:
+- Node.js version 20 or higher
+- macOS, Linux, or Windows
 
-   ```bash
-   gemini
-   ```
+## 📋 Key Features
 
-### With Homebrew
+With Gemini CLI you can:
 
-1. **Prerequisites:** Ensure you have [Homebrew](https://brew.sh/) installed.
-2. **Install the CLI:** Execute the following command in your terminal:
+- **Code Understanding & Generation**
+  - Query and edit large codebases
+  - Generate new apps from PDFs, images, or sketches using multimodal capabilities
+  - Debug issues and troubleshoot with natural language
+- **Automation & Integration**
+  - Automate operational tasks like querying pull requests or handling complex rebases
+  - Use MCP servers to connect new capabilities, including [media generation with Imagen, Veo or Lyria](https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia)
+  - Run non-interactively in scripts for workflow automation
+- **Advanced Capabilities**
+  - Ground your queries with built-in [Google Search](https://ai.google.dev/gemini-api/docs/grounding) for real-time information
+  - Conversation checkpointing to save and resume complex sessions
+  - Custom context files (GEMINI.md) to tailor behavior for your projects
 
-   ```bash
-   brew install gemini-cli
-   ```
+- **🔗 GitHub Integration**
+  - Use the Gemini CLI GitHub Action for automated PR reviews
+  - Automated issue triage and on-demand AI assistance directly in your repositories
+  - Seamless integration with your GitHub workflows
 
-   Then, run the CLI from anywhere:
+## 🔐 Authentication Options
 
-   ```bash
-   gemini
-   ```
+Choose the authentication method that best fits your needs:
 
-### Common Configuration steps
+### Option 1: OAuth login (Using your Google Account)
 
-3. **Pick a color theme**
-4. **Authenticate:** When prompted, sign in with your personal Google account. This will grant you up to 60 model requests per minute and 1,000 model requests per day using Gemini.
+**✨ Best for:** Individual developers as well as anyone who has a Gemini Code Assist License. (see [quota limits and terms of service](https://cloud.google.com/gemini/docs/quotas) for details)
 
-You are now ready to use the Gemini CLI!
+**Benefits:**
 
-### Use a Gemini API key:
+- **Free tier**: 60 requests/min and 1,000 requests/day
+- **Gemini 2.5 Pro** with 1M token context window
+- **No API key management** - just sign in with your Google account
+- **Automatic updates** to latest models
 
-The Gemini API provides a free tier with [100 requests per day](https://ai.google.dev/gemini-api/docs/rate-limits#free-tier) using Gemini 2.5 Pro, control over which model you use, and access to higher rate limits (with a paid plan):
+#### Start Gemini CLI, then choose OAuth and follow the browser authentication flow when prompted
 
-1. Generate a key from [Google AI Studio](https://aistudio.google.com/apikey).
-2. Set it as an environment variable in your terminal. Replace `YOUR_API_KEY` with your generated key.
+```bash
+gemini
+```
 
-   ```bash
-   export GEMINI_API_KEY="YOUR_API_KEY"
-   ```
+#### If you are using a paid Code Assist License from your organization, remember to set the Google Cloud Project
 
-3. (Optionally) Upgrade your Gemini API project to a paid plan on the API key page (will automatically unlock [Tier 1 rate limits](https://ai.google.dev/gemini-api/docs/rate-limits#tier-1))
+```bash
+# Set your Google Cloud Project
+export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_NAME"
+gemini
+```
 
-### Use a Vertex AI API key:
+### Option 2: Gemini API Key
 
-The Vertex AI API provides a [free tier](https://cloud.google.com/vertex-ai/generative-ai/docs/start/express-mode/overview) using express mode for Gemini 2.5 Pro, control over which model you use, and access to higher rate limits with a billing account:
+**✨ Best for:** Developers who need specific model control or paid tier access
 
-1. Generate a key from [Google Cloud](https://cloud.google.com/vertex-ai/generative-ai/docs/start/api-keys).
-2. Set it as an environment variable in your terminal. Replace `YOUR_API_KEY` with your generated key and set GOOGLE_GENAI_USE_VERTEXAI to true
+**Benefits:**
 
-   ```bash
-   export GOOGLE_API_KEY="YOUR_API_KEY"
-   export GOOGLE_GENAI_USE_VERTEXAI=true
-   ```
+- **Free tier**: 100 requests/day with Gemini 2.5 Pro
+- **Model selection**: Choose specific Gemini models
+- **Usage-based billing**: Upgrade for higher limits when needed
 
-3. (Optionally) Add a billing account on your project to get access to [higher usage limits](https://cloud.google.com/vertex-ai/generative-ai/docs/quotas)
+```bash
+# Get your key from https://aistudio.google.com/apikey
+export GEMINI_API_KEY="YOUR_API_KEY"
+gemini
+```
 
-For other authentication methods, including Google Workspace accounts, see the [authentication](./docs/cli/authentication.md) guide.
+### Option 3: Vertex AI
 
-## Examples
+**✨ Best for:** Enterprise teams and production workloads
 
-Once the CLI is running, you can start interacting with Gemini from your shell.
+**Benefits:**
 
-You can start a project from a new directory:
+- **Enterprise features**: Advanced security and compliance
+- **Scalable**: Higher rate limits with billing account
+- **Integration**: Works with existing Google Cloud infrastructure
 
-```sh
-cd new-project/
+```bash
+# Get your key from Google Cloud Console
+export GOOGLE_API_KEY="YOUR_API_KEY"
+export GOOGLE_GENAI_USE_VERTEXAI=true
 gemini
-> Write me a Gemini Discord bot that answers questions using a FAQ.md file I will provide
 ```
 
-Or work with an existing project:
+For Google Workspace accounts and other authentication methods, see the [authentication guide](./docs/cli/authentication.md).
+
+## 🚀 Getting Started
+
+### Basic Usage
+
+#### Start in current directory
+
+```bash
+gemini
+```
+
+#### Include multiple directories
+
+```bash
+gemini --include-directories ../lib,../docs
+```
+
+#### Use specific model
+
+```bash
+gemini -m gemini-2.5-flash
+```
+
+#### Non-interactive mode for scripts
+
+```bash
+gemini -p "Explain the architecture of this codebase"
+```
+
+### Quick Examples
+
+#### Start a new project
+
+````bash
+cd new-project/
+gemini
+> Write me a Discord bot that answers questions using a FAQ.md file I will provide
 
-```sh
+#### Analyze existing code
+```bash
 git clone https://github.com/google-gemini/gemini-cli
 cd gemini-cli
 gemini
 > Give me a summary of all of the changes that went in yesterday
-```
+````
 
-### Next steps
+## 🔗 GitHub Integration
 
-- Learn how to [contribute to or build from the source](./CONTRIBUTING.md).
-- Explore the available **[CLI Commands](./docs/cli/commands.md)**.
-- If you encounter any issues, review the **[troubleshooting guide](./docs/troubleshooting.md)**.
-- For more comprehensive documentation, see the [full documentation](./docs/index.md).
-- Take a look at some [popular tasks](#popular-tasks) for more inspiration.
-- Check out our **[Official Roadmap](./ROADMAP.md)**
+Integrate Gemini CLI directly into your GitHub workflows with the [**Gemini CLI GitHub Action**](https://github.com/google-github-actions/run-gemini-cli). Key features include:
 
-### Troubleshooting
+- **Pull Request Reviews**: Automatically review pull requests when they're opened.
+- **Issue Triage**: Automatically triage and label GitHub issues.
+- **On-demand Collaboration**: Mention `@gemini-cli` in issues and pull requests for assistance and task delegation.
+- **Custom Workflows**: Set up your own scheduled tasks and event-driven automations.
 
-Head over to the [troubleshooting guide](docs/troubleshooting.md) if you're
-having issues.
+## 📚 Documentation
 
-## Popular tasks
+### Getting Started
 
-### Explore a new codebase
+- [**Quickstart Guide**](./docs/cli/index.md) - Get up and running quickly
+- [**Authentication Setup**](./docs/cli/authentication.md) - Detailed auth configuration
+- [**Configuration Guide**](./docs/cli/configuration.md) - Settings and customization
+- [**Keyboard Shortcuts**](./docs/keyboard-shortcuts.md) - Productivity tips
 
-Start by `cd`ing into an existing or newly-cloned repository and running `gemini`.
+### Core Features
 
-```text
-> Describe the main pieces of this system's architecture.
-```
+- [**Commands Reference**](./docs/cli/commands.md) - All slash commands (`/help`, `/chat`, `/mcp`, etc.)
+- [**Checkpointing**](./docs/checkpointing.md) - Save and resume conversations
+- [**Memory Management**](./docs/tools/memory.md) - Using GEMINI.md context files
+- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage
 
-```text
-> What security mechanisms are in place?
-```
+### Tools & Extensions
 
-```text
-> Provide a step-by-step dev onboarding doc for developers new to the codebase.
-```
+- [**Built-in Tools Overview**](./docs/tools/index.md)
+  - [File System Operations](./docs/tools/file-system.md)
+  - [Shell Commands](./docs/tools/shell.md)
+  - [Web Fetch & Search](./docs/tools/web-fetch.md)
+  - [Multi-file Operations](./docs/tools/multi-file.md)
+- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom tools
+- [**Custom Extensions**](./docs/extension.md) - Build your own commands
 
-```text
-> Summarize this codebase and highlight the most interesting patterns or techniques I could learn from.
-```
+### Advanced Topics
 
-```text
-> Identify potential areas for improvement or refactoring in this codebase, highlighting parts that appear fragile, complex, or hard to maintain.
-```
+- [**Architecture Overview**](./docs/architecture.md) - How Gemini CLI works
+- [**IDE Integration**](./docs/extension.md) - VS Code companion
+- [**Sandboxing & Security**](./docs/sandbox.md) - Safe execution environments
+- [**Enterprise Deployment**](./docs/deployment.md) - Docker, system-wide config
+- [**Telemetry & Monitoring**](./docs/telemetry.md) - Usage tracking
+- [**Tools API Development**](./docs/core/tools-api.md) - Create custom tools
 
-```text
-> Which parts of this codebase might be challenging to scale or debug?
-```
+### Configuration & Customization
 
-```text
-> Generate a README section for the [module name] module explaining what it does and how to use it.
-```
+- [**Settings Reference**](./docs/cli/configuration.md) - All configuration options
+- [**Theme Customization**](./docs/cli/themes.md) - Visual customization
+- [**.gemini Directory**](./docs/gemini-ignore.md) - Project-specific settings
+- [**Environment Variables**](./docs/cli/configuration.md#environment-variables)
 
-```text
-> What kind of error handling and logging strategies does the project use?
-```
+### Troubleshooting & Support
 
-```text
-> Which tools, libraries, and dependencies are used in this project?
-```
+- [**Troubleshooting Guide**](./docs/troubleshooting.md) - Common issues and solutions
+- [**FAQ**](./docs/troubleshooting.md#frequently-asked-questions) - Quick answers
+- Use `/bug` command to report issues directly from the CLI
 
-### Work with your existing code
+### Using MCP Servers
 
-```text
-> Implement a first draft for GitHub issue #123.
-```
+Configure MCP servers in `~/.gemini/settings.json` to extend Gemini CLI with custom tools:
 
 ```text
-> Help me migrate this codebase to the latest version of Java. Start with a plan.
+> @github List my open pull requests
+> @slack Send a summary of today's commits to #dev channel
+> @database Run a query to find inactive users
 ```
 
-### Automate your workflows
+See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup instructions.
 
-Use MCP servers to integrate your local system tools with your enterprise collaboration suite.
+## 🤝 Contributing
 
-```text
-> Make me a slide deck showing the git history from the last 7 days, grouped by feature and team member.
-```
+We welcome contributions! Gemini CLI is fully open source (Apache 2.0), and we encourage the community to:
 
-```text
-> Make a full-screen web app for a wall display to show our most interacted-with GitHub issues.
-```
+- Report bugs and suggest features
+- Improve documentation
+- Submit code improvements
+- Share your MCP servers and extensions
 
-### Interact with your system
+See our [Contributing Guide](./CONTRIBUTING.md) for development setup, coding standards, and how to submit pull requests.
 
-```text
-> Convert all the images in this directory to png, and rename them to use dates from the exif data.
-```
+Check our [Official Roadmap](https://github.com/orgs/google-gemini/projects/11/) for planned features and priorities.
 
-```text
-> Organize my PDF invoices by month of expenditure.
-```
+## 📖 Resources
+
+- **[Official Roadmap](./ROADMAP.md)** - See what's coming next
+- **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package registry
+- **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** - Report bugs or request features
+- **[Security Advisories](https://github.com/google-gemini/gemini-cli/security/advisories)** - Security updates
 
 ### Uninstall
 
-Head over to the [Uninstall](docs/Uninstall.md) guide for uninstallation instructions.
+See the [Uninstall Guide](docs/Uninstall.md) for removal instructions.
 
-## Terms of Service and Privacy Notice
+## 📄 Legal
 
-For details on the terms of service and privacy notice applicable to your use of Gemini CLI, see the [Terms of Service and Privacy Notice](./docs/tos-privacy.md).
+- **License**: [Apache License 2.0](LICENSE)
+- **Terms of Service**: [Terms & Privacy](./docs/tos-privacy.md)
+- **Security**: [Security Policy](SECURITY.md)
 
-## Security Disclosures
+---
 
-Please see our [security disclosure process](SECURITY.md). All [security advisories](https://github.com/google-gemini/gemini-cli/security/advisories) are managed on Github.
+<p align="center">
+  Built with ❤️ by Google and the open source community
+</p>

package/dist/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@google/gemini-cli",
-    "version": "0.1.18",
+    "version": "0.1.19-nightly.250813.9d023be1",
     "description": "Gemini CLI",
     "repository": {
         "type": "git",
@@ -25,12 +25,13 @@
         "dist"
     ],
     "config": {
-        "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.1.18"
+        "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.1.19-nightly.250813.9d023be1"
     },
     "dependencies": {
         "@google/gemini-cli-core": "file:../core",
         "@google/genai": "1.9.0",
         "@iarna/toml": "^2.2.5",
+        "@modelcontextprotocol/sdk": "^1.15.1",
         "@types/update-notifier": "^6.0.8",
         "command-exists": "^1.2.9",
         "diff": "^7.0.0",
@@ -52,6 +53,7 @@
         "string-width": "^7.1.0",
         "strip-ansi": "^7.1.0",
         "strip-json-comments": "^3.1.1",
+        "undici": "^7.10.0",
         "update-notifier": "^7.3.1",
         "yargs": "^17.7.2",
         "zod": "^3.23.8"

package/dist/src/acp/acpPeer.js

@@ -167,53 +167,54 @@ class GeminiAgent {
         if (!tool) {
             return errorResponse(new Error(`Tool "${fc.name}" not found in registry.`));
         }
-        let toolCallId;
-        const confirmationDetails = await tool.shouldConfirmExecute(args, abortSignal);
-        if (confirmationDetails) {
-            let content = null;
-            if (confirmationDetails.type === 'edit') {
-                content = {
-                    type: 'diff',
-                    path: confirmationDetails.fileName,
-                    oldText: confirmationDetails.originalContent,
-                    newText: confirmationDetails.newContent,
-                };
-            }
-            const result = await this.client.requestToolCallConfirmation({
-                label: tool.getDescription(args),
-                icon: tool.icon,
-                content,
-                confirmation: toAcpToolCallConfirmation(confirmationDetails),
-                locations: tool.toolLocations(args),
-            });
-            await confirmationDetails.onConfirm(toToolCallOutcome(result.outcome));
-            switch (result.outcome) {
-                case 'reject':
-                    return errorResponse(new Error(`Tool "${fc.name}" not allowed to run by the user.`));
-                case 'cancel':
-                    return errorResponse(new Error(`Tool "${fc.name}" was canceled by the user.`));
-                case 'allow':
-                case 'alwaysAllow':
-                case 'alwaysAllowMcpServer':
-                case 'alwaysAllowTool':
-                    break;
-                default: {
-                    const resultOutcome = result.outcome;
-                    throw new Error(`Unexpected: ${resultOutcome}`);
+        let toolCallId = undefined;
+        try {
+            const invocation = tool.build(args);
+            const confirmationDetails = await invocation.shouldConfirmExecute(abortSignal);
+            if (confirmationDetails) {
+                let content = null;
+                if (confirmationDetails.type === 'edit') {
+                    content = {
+                        type: 'diff',
+                        path: confirmationDetails.fileName,
+                        oldText: confirmationDetails.originalContent,
+                        newText: confirmationDetails.newContent,
+                    };
+                }
+                const result = await this.client.requestToolCallConfirmation({
+                    label: invocation.getDescription(),
+                    icon: tool.icon,
+                    content,
+                    confirmation: toAcpToolCallConfirmation(confirmationDetails),
+                    locations: invocation.toolLocations(),
+                });
+                await confirmationDetails.onConfirm(toToolCallOutcome(result.outcome));
+                switch (result.outcome) {
+                    case 'reject':
+                        return errorResponse(new Error(`Tool "${fc.name}" not allowed to run by the user.`));
+                    case 'cancel':
+                        return errorResponse(new Error(`Tool "${fc.name}" was canceled by the user.`));
+                    case 'allow':
+                    case 'alwaysAllow':
+                    case 'alwaysAllowMcpServer':
+                    case 'alwaysAllowTool':
+                        break;
+                    default: {
+                        const resultOutcome = result.outcome;
+                        throw new Error(`Unexpected: ${resultOutcome}`);
+                    }
                 }
+                toolCallId = result.id;
             }
-            toolCallId = result.id;
-        }
-        else {
-            const result = await this.client.pushToolCall({
-                icon: tool.icon,
-                label: tool.getDescription(args),
-                locations: tool.toolLocations(args),
-            });
-            toolCallId = result.id;
-        }
-        try {
-            const toolResult = await tool.execute(args, abortSignal);
+            else {
+                const result = await this.client.pushToolCall({
+                    icon: tool.icon,
+                    label: invocation.getDescription(),
+                    locations: invocation.toolLocations(),
+                });
+                toolCallId = result.id;
+            }
+            const toolResult = await invocation.execute(abortSignal);
             const toolCallContent = toToolCallContent(toolResult);
             await this.client.updateToolCall({
                 toolCallId,
@@ -234,11 +235,13 @@ class GeminiAgent {
         }
         catch (e) {
             const error = e instanceof Error ? e : new Error(String(e));
-            await this.client.updateToolCall({
-                toolCallId,
-                status: 'error',
-                content: { type: 'markdown', markdown: error.message },
-            });
+            if (toolCallId) {
+                await this.client.updateToolCall({
+                    toolCallId,
+                    status: 'error',
+                    content: { type: 'markdown', markdown: error.message },
+                });
+            }
             return errorResponse(error);
         }
     }
@@ -304,7 +307,7 @@ class GeminiAgent {
                     if (this.config.getEnableRecursiveFileSearch() && globTool) {
                         this.#debug(`Path ${pathName} not found directly, attempting glob search.`);
                         try {
-                            const globResult = await globTool.execute({
+                            const globResult = await globTool.buildAndExecute({
                                 pattern: `**/*${pathName}*`,
                                 path: this.config.getTargetDir(),
                             }, abortSignal);
@@ -398,12 +401,15 @@ class GeminiAgent {
             paths: pathSpecsToRead,
             respectGitIgnore, // Use configuration setting
         };
-        const toolCall = await this.client.pushToolCall({
-            icon: readManyFilesTool.icon,
-            label: readManyFilesTool.getDescription(toolArgs),
-        });
+        let toolCallId = undefined;
         try {
-            const result = await readManyFilesTool.execute(toolArgs, abortSignal);
+            const invocation = readManyFilesTool.build(toolArgs);
+            const toolCall = await this.client.pushToolCall({
+                icon: readManyFilesTool.icon,
+                label: invocation.getDescription(),
+            });
+            toolCallId = toolCall.id;
+            const result = await invocation.execute(abortSignal);
             const content = toToolCallContent(result) || {
                 type: 'markdown',
                 markdown: `Successfully read: ${contentLabelsForDisplay.join(', ')}`,
@@ -446,14 +452,16 @@ class GeminiAgent {
             return processedQueryParts;
         }
         catch (error) {
-            await this.client.updateToolCall({
-                toolCallId: toolCall.id,
-                status: 'error',
-                content: {
-                    type: 'markdown',
-                    markdown: `Error reading files (${contentLabelsForDisplay.join(', ')}): ${getErrorMessage(error)}`,
-                },
-            });
+            if (toolCallId) {
+                await this.client.updateToolCall({
+                    toolCallId,
+                    status: 'error',
+                    content: {
+                        type: 'markdown',
+                        markdown: `Error reading files (${contentLabelsForDisplay.join(', ')}): ${getErrorMessage(error)}`,
+                    },
+                });
+            }
             throw error;
         }
     }