This document provides a high-level overview of the Gemini CLI's architecture.
The Gemini CLI is primarily composed of two main packages, along with a suite of tools that can be used by the system in the course of handling command-line input:
-
CLI package (
packages/cli):- Purpose: This contains the user-facing portion of the Gemini CLI, such as handling the initial user input, presenting the final output, and managing the overall user experience.
- Key functions contained in the package:
- Input processing
- History management
- Display rendering
- Theme and UI customization
- CLI configuration settings
-
Core package (
packages/core):- Purpose: This acts as the backend for the Gemini CLI. It receives
requests sent from
packages/cli, orchestrates interactions with the Gemini API, and manages the execution of available tools. - Key functions contained in the package:
- API client for communicating with the Google Gemini API
- Prompt construction and management
- Tool registration and execution logic
- State management for conversations or sessions
- Server-side configuration
- Purpose: This acts as the backend for the Gemini CLI. It receives
requests sent from
-
Tools (
packages/core/src/tools/):- Purpose: These are individual modules that extend the capabilities of the Gemini model, allowing it to interact with the local environment (e.g., file system, shell commands, web fetching).
- Interaction:
packages/coreinvokes these tools based on requests from the Gemini model.
A typical interaction with the Gemini CLI follows this flow:
- User input: The user types a prompt or command into the terminal, which
is managed by
packages/cli. - Request to core:
packages/clisends the user's input topackages/core. - Request processed: The core package:
- Constructs an appropriate prompt for the Gemini API, possibly including conversation history and available tool definitions.
- Sends the prompt to the Gemini API.
- Gemini API response: The Gemini API processes the prompt and returns a response. This response might be a direct answer or a request to use one of the available tools.
- Tool execution (if applicable):
- When the Gemini API requests a tool, the core package prepares to execute it.
- If the requested tool can modify the file system or execute shell commands, the user is first given details of the tool and its arguments, and the user must approve the execution.
- Read-only operations, such as reading files, might not require explicit user confirmation to proceed.
- Once confirmed, or if confirmation is not required, the core package executes the relevant action within the relevant tool, and the result is sent back to the Gemini API by the core package.
- The Gemini API processes the tool result and generates a final response.
- Response to CLI: The core package sends the final response back to the CLI package.
- Display to user: The CLI package formats and displays the response to the user in the terminal.
- Modularity: Separating the CLI (frontend) from the Core (backend) allows for independent development and potential future extensions (e.g., different frontends for the same backend).
- Extensibility: The tool system is designed to be extensible, allowing new capabilities to be added.
- User experience: The CLI focuses on providing a rich and interactive terminal experience.