From ed1bb72dc84f316cdf874fcdd9acd332159132c3 Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Sun, 1 Feb 2026 15:13:49 +0100 Subject: [PATCH 1/2] cagent: "script_shell" toolset should be "script" Signed-off-by: David Karlsson <35727626+dvdksn@users.noreply.github.com> --- content/manuals/ai/cagent/reference/toolsets.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/manuals/ai/cagent/reference/toolsets.md b/content/manuals/ai/cagent/reference/toolsets.md index f9dfcf99441b..8126180ee98e 100644 --- a/content/manuals/ai/cagent/reference/toolsets.md +++ b/content/manuals/ai/cagent/reference/toolsets.md @@ -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 @@ -77,7 +77,7 @@ agents: Authorization: Bearer ${API_TOKEN} # Custom shell tools - - type: script_shell + - type: script tools: build: cmd: npm run build @@ -316,7 +316,7 @@ toolsets: ### 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. @@ -367,9 +367,9 @@ 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 @@ -385,7 +385,7 @@ parameters: ```yaml toolsets: - - type: script_shell + - type: script tools: deploy: cmd: ./deploy.sh From 63e1e61b57643d033c39379309ac9f1e0103925c Mon Sep 17 00:00:00 2001 From: David Karlsson <35727626+dvdksn@users.noreply.github.com> Date: Sun, 1 Feb 2026 15:27:59 +0100 Subject: [PATCH 2/2] cagent: add user_prompt toolset Signed-off-by: David Karlsson <35727626+dvdksn@users.noreply.github.com> --- .../manuals/ai/cagent/reference/toolsets.md | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/content/manuals/ai/cagent/reference/toolsets.md b/content/manuals/ai/cagent/reference/toolsets.md index 8126180ee98e..5f50e9d86bb9 100644 --- a/content/manuals/ai/cagent/reference/toolsets.md +++ b/content/manuals/ai/cagent/reference/toolsets.md @@ -313,6 +313,33 @@ 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