MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-03-11 06:31:01 -07:00
Code Issues Packages Projects Releases Wiki Activity
Files
resume-session-message
gemini-cli/docs/core/subagents.md

308 lines
12 KiB
Markdown
Raw Permalink Blame History

# Subagents (experimental)
Subagents are specialized agents that operate within your main Gemini CLI
session. They are designed to handle specific, complex tasks—like deep codebase
analysis, documentation lookup, or domain-specific reasoning—without cluttering
the main agent's context or toolset.
> **Note: Subagents are currently an experimental feature.**
>
> To use custom subagents, you must explicitly enable them in your
> `settings.json`:
>
> ```json
> {
> "experimental": { "enableAgents": true }
> }
> ```
>
> **Warning:** Subagents currently operate in
> ["YOLO mode"](../reference/configuration.md#command-line-arguments), meaning
> they may execute tools without individual user confirmation for each step.
> Proceed with caution when defining agents with powerful tools like
> `run_shell_command` or `write_file`.
## What are subagents?
Subagents are "specialists" that the main Gemini agent can hire for a specific
job.
- **Focused context:** Each subagent has its own system prompt and persona.
- **Specialized tools:** Subagents can have a restricted or specialized set of
tools.
- **Independent context window:** Interactions with a subagent happen in a
separate context loop, which saves tokens in your main conversation history.
Subagents are exposed to the main agent as a tool of the same name. When the
main agent calls the tool, it delegates the task to the subagent. Once the
subagent completes its task, it reports back to the main agent with its
findings.
## Built-in subagents
Gemini CLI comes with the following built-in subagents:
### Codebase Investigator
- **Name:** `codebase_investigator`
- **Purpose:** Analyze the codebase, reverse engineer, and understand complex
dependencies.
- **When to use:** "How does the authentication system work?", "Map out the
dependencies of the `AgentRegistry` class."
- **Configuration:** Enabled by default. You can configure it in
`settings.json`. Example (forcing a specific model):
```json
{
"experimental": {
"codebaseInvestigatorSettings": {
"enabled": true,
"maxNumTurns": 20,
"model": "gemini-2.5-pro"
}
}
}
```
### CLI Help Agent
- **Name:** `cli_help`
- **Purpose:** Get expert knowledge about Gemini CLI itself, its commands,
configuration, and documentation.
- **When to use:** "How do I configure a proxy?", "What does the `/rewind`
command do?"
- **Configuration:** Enabled by default.
### Generalist Agent
- **Name:** `generalist_agent`
- **Purpose:** Route tasks to the appropriate specialized subagent.
- **When to use:** Implicitly used by the main agent for routing. Not directly
invoked by the user.
- **Configuration:** Enabled by default. No specific configuration options.
### Browser Agent (experimental)
- **Name:** `browser_agent`
- **Purpose:** Automate web browser tasks — navigating websites, filling forms,
clicking buttons, and extracting information from web pages — using the
accessibility tree.
- **When to use:** "Go to example.com and fill out the contact form," "Extract
the pricing table from this page," "Click the login button and enter my
credentials."
> **Note:** This is a preview feature currently under active development.
#### Prerequisites
The browser agent requires:
- **Chrome** version 144 or later (any recent stable release will work).
- **Node.js** with `npx` available (used to launch the
[`chrome-devtools-mcp`](https://www.npmjs.com/package/chrome-devtools-mcp)
server).
#### Enabling the browser agent
The browser agent is disabled by default. Enable it in your `settings.json`:
```json
{
"agents": {
"overrides": {
"browser_agent": {
"enabled": true
}
}
}
}
```
#### Session modes
The `sessionMode` setting controls how Chrome is launched and managed. Set it
under `agents.browser`:
```json
{
"agents": {
"overrides": {
"browser_agent": {
"enabled": true
}
},
"browser": {
"sessionMode": "persistent"
}
}
}
```
The available modes are:
| Mode | Description |
| :----------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `persistent` | **(Default)** Launches Chrome with a persistent profile stored at `~/.gemini/cli-browser-profile/`. Cookies, history, and settings are preserved between sessions. |
| `isolated` | Launches Chrome with a temporary profile that is deleted after each session. Use this for clean-state automation. |
| `existing` | Attaches to an already-running Chrome instance. You must enable remote debugging first by navigating to `chrome://inspect/#remote-debugging` in Chrome. No new browser process is launched. |
#### Configuration reference
All browser-specific settings go under `agents.browser` in your `settings.json`.
| Setting | Type | Default | Description |
| :------------ | :-------- | :------------- | :---------------------------------------------------------------------------------------------- |
| `sessionMode` | `string` | `"persistent"` | How Chrome is managed: `"persistent"`, `"isolated"`, or `"existing"`. |
| `headless` | `boolean` | `false` | Run Chrome in headless mode (no visible window). |
| `profilePath` | `string` | — | Custom path to a browser profile directory. |
| `visualModel` | `string` | — | Model override for the visual agent (for example, `"gemini-2.5-computer-use-preview-10-2025"`). |
#### Security
The browser agent enforces the following security restrictions:
- **Blocked URL patterns:** `file://`, `javascript:`, `data:text/html`,
`chrome://extensions`, and `chrome://settings/passwords` are always blocked.
- **Sensitive action confirmation:** Actions like form filling, file uploads,
and form submissions require user confirmation through the standard policy
engine.
#### Visual agent
By default, the browser agent interacts with pages through the accessibility
tree using element `uid` values. For tasks that require visual identification
(for example, "click the yellow button" or "find the red error message"), you
can enable the visual agent by setting a `visualModel`:
```json
{
"agents": {
"overrides": {
"browser_agent": {
"enabled": true
}
},
"browser": {
"visualModel": "gemini-2.5-computer-use-preview-10-2025"
}
}
}
```
When enabled, the agent gains access to the `analyze_screenshot` tool, which
captures a screenshot and sends it to the vision model for analysis. The model
returns coordinates and element descriptions that the browser agent uses with
the `click_at` tool for precise, coordinate-based interactions.
> **Note:** The visual agent requires API key or Vertex AI authentication. It is
> not available when using Google Login.
## Creating custom subagents
You can create your own subagents to automate specific workflows or enforce
specific personas. To use custom subagents, you must enable them in your
`settings.json`:
```json
{
"experimental": {
"enableAgents": true
}
}
```
### Agent definition files
Custom agents are defined as Markdown files (`.md`) with YAML frontmatter. You
can place them in:
1. **Project-level:** `.gemini/agents/*.md` (Shared with your team)
2. **User-level:** `~/.gemini/agents/*.md` (Personal agents)
### File format
The file **MUST** start with YAML frontmatter enclosed in triple-dashes `---`.
The body of the markdown file becomes the agent's **System Prompt**.
**Example: `.gemini/agents/security-auditor.md`**
```markdown
---
name: security-auditor
description: Specialized in finding security vulnerabilities in code.
kind: local
tools:
- read_file
- grep_search
model: gemini-2.5-pro
temperature: 0.2
max_turns: 10
---
You are a ruthless Security Auditor. Your job is to analyze code for potential
vulnerabilities.
Focus on:
1. SQL Injection
2. XSS (Cross-Site Scripting)
3. Hardcoded credentials
4. Unsafe file operations
When you find a vulnerability, explain it clearly and suggest a fix. Do not fix
it yourself; just report it.
```
### Configuration schema
| Field | Type | Required | Description |
| :------------- | :----- | :------- | :------------------------------------------------------------------------------------------------------------------------ |
| `name` | string | Yes | Unique identifier (slug) used as the tool name for the agent. Only lowercase letters, numbers, hyphens, and underscores. |
| `description` | string | Yes | Short description of what the agent does. This is visible to the main agent to help it decide when to call this subagent. |
| `kind` | string | No | `local` (default) or `remote`. |
| `tools` | array | No | List of tool names this agent can use. If omitted, it may have access to a default set. |
| `model` | string | No | Specific model to use (e.g., `gemini-2.5-pro`). Defaults to `inherit` (uses the main session model). |
| `temperature` | number | No | Model temperature (0.0 - 2.0). |
| `max_turns` | number | No | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `15`. |
| `timeout_mins` | number | No | Maximum execution time in minutes. Defaults to `5`. |
### Optimizing your subagent
The main agent's system prompt encourages it to use an expert subagent when one
is available. It decides whether an agent is a relevant expert based on the
agent's description. You can improve the reliability with which an agent is used
by updating the description to more clearly indicate:
- Its area of expertise.
- When it should be used.
- Some example scenarios.
For example, the following subagent description should be called fairly
consistently for Git operations.
> Git expert agent which should be used for all local and remote git operations.
> For example:
>
> - Making commits
> - Searching for regressions with bisect
> - Interacting with source control and issues providers such as GitHub.
If you need to further tune your subagent, you can do so by selecting the model
to optimize for with `/model` and then asking the model why it does not think
that your subagent was called with a specific prompt and the given description.
## Remote subagents (Agent2Agent) (experimental)
Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
(A2A) protocol.
> **Note: Remote subagents are currently an experimental feature.**
See the [Remote Subagents documentation](/docs/core/remote-agents) for detailed
configuration and usage instructions.
## Extension subagents
Extensions can bundle and distribute subagents. See the
[Extensions documentation](../extensions/index.md#subagents) for details on how
to package agents within an extension.
Reference in New Issue View Git Blame Copy Permalink