Skip to content

cagent update builtins #24053

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dvdksn wants to merge 2 commits into
base: main
Choose a base branch
from
+33 −6
Open

cagent update builtins #24053

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ed1bb72
cagent: "script_shell" toolset should be "script"
dvdksn Feb 1, 2026
63e1e61
cagent: add user_prompt toolset
dvdksn Feb 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 33 additions & 6 deletions content/manuals/ai/cagent/reference/toolsets.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ MCP toolsets
(stdio) or remote servers (HTTP/SSE). MCP enables access to a wide ecosystem
of standardized tools.
Custom toolsets
: Shell scripts wrapped as tools with typed parameters (`script_shell`). This
: Shell scripts wrapped as tools with typed parameters (`script`). This
lets you define domain-specific tools for your use case.

## Configuration
Expand Down Expand Up @@ -77,7 +77,7 @@ agents:
Authorization: Bearer ${API_TOKEN}

# Custom shell tools
- type: script_shell
- type: script
tools:
build:
cmd: npm run build
Expand Down Expand Up @@ -313,10 +313,37 @@ toolsets:
- type: fetch
```

### User Prompt

The `user_prompt` toolset lets your agent ask you questions during task
execution. When the agent needs clarification, decisions, or additional
information it can't determine on its own, it displays a dialog and waits for
your response.

You'll see a prompt with the agent's question. Depending on what the agent
needs, you might provide free-form text, select from options, or fill out a
form with multiple fields. You can accept and provide the information, decline
to answer, or cancel the operation entirely.

#### Configuration

```yaml
toolsets:
- type: user_prompt
```

No additional configuration is required. The tool becomes available to the
agent once configured. When the agent calls this tool, the user sees a dialog
with the prompt. The user can:

- **Accept**: Provide the requested information
- **Decline**: Refuse to provide the information
- **Cancel**: Cancel the operation

### API

The `api` toolset lets you define custom tools that call HTTP APIs. Similar to
`script_shell` but for web services, this allows you to expose REST APIs,
`script` but for web services, this allows you to expose REST APIs,
webhooks, or any HTTP endpoint as a tool your agent can use. The agent sees
these as typed tools with automatic parameter validation.

Expand Down Expand Up @@ -367,9 +394,9 @@ requests, parameters are sent as JSON in the request body.

Supported argument types: `string`, `number`, `boolean`, `array`, `object`.

### Script Shell
### Script

The `script_shell` toolset lets you define custom tools by wrapping shell
The `script` toolset lets you define custom tools by wrapping shell
commands with typed parameters. This allows you to expose domain-specific
operations to your agent as first-class tools. The agent sees these custom
tools just like built-in tools, with parameter validation and type checking
Expand All @@ -385,7 +412,7 @@ parameters:

```yaml
toolsets:
- type: script_shell
- type: script
tools:
deploy:
cmd: ./deploy.sh
Expand Down