stack kb agent-builder post-agent-builder-converse cli command

elastic stack kb agent-builder post-agent-builder-converse [options]

Send chat message

Behaviour flags:

--dry-run — validate all inputs and exit without performing any action

--execution-mode enum

define how to execute the agent (local execution or via task_manager)

Values: local, task_manager

--access-control string

Optional conversation access control. Defaults to private.

--action enum

Deprecated and ignored. The "regenerate" action has been removed; the field is still accepted for backward compatibility.

Values: regenerate

--agent-id string

The ID of the agent to chat with. Defaults to the default Elastic AI agent.

--attachments string[]

Optional attachments to send with the message.

Repeatable: pass --attachments multiple times to supply more than one value

--browser-api-tools string[]

Optional browser API tools to be registered as LLM tools with browser.* namespace. These tools execute on the client side.

Repeatable: pass --browser-api-tools multiple times to supply more than one value

--configuration-overrides string

Runtime configuration overrides. These override the stored agent configuration for this execution only.

--connector-id string

Optional connector ID for the agent to use for model routing. Mutually exclusive with inference_id; omit or use only one.

--conversation-id string

Optional existing conversation ID to continue a previous conversation.

--execution-id string

Optional client-generated execution ID. Provide it to address this execution later (for example, to abort it). Must be unique; defaults to a server-generated ID.

--inference-id string

Optional inference endpoint ID for model routing (public alias for the same internal identifier as connector_id). Mutually exclusive with connector_id.

--input string

The user input message to send to the agent.

--project-routing string

Cross-project search routing expression resolved from the header project picker, applied to the run's searches. Serverless (CPS) only; ignored elsewhere.

--prompts string

Use this field to respond to a confirmation, authorization, or ask_user_question prompt. Send an allow boolean to answer a confirmation prompt, an authorized boolean to answer an authorization prompt, or an answers array (one entry per question) to answer an ask_user_question prompt.

--read-only

When true, the created conversation is presented as read-only in the UI: its history is shown but no message input is offered. This carries no authorization meaning — the conversation can still be continued through the API. This setting is ignored when continuing an existing conversation.

--reasoning-level enum

Reasoning effort level for the LLM. One of: none, minimal, low, medium, high, xhigh. Support depends on the underlying model and provider.

Values: none, minimal, low, medium, high, xhigh

--input-file string

path to a JSON file to use as command input

--dry-run

validate all inputs and exit without performing any action (preview changes without applying them)

--no-validate

skip input validation and send the request as-is

--output-fields string

comma-separated list of fields to include in output (dot-notation supported)

--output-template string

Mustache-like template for custom text output (e.g. "{{id}}: {{name}}")

--json

output as JSON