# AiAgentInputTransforms
## Properties
Name | Type | Description | Notes
------------ | ------------- | ------------- | -------------
**provider** | Option<[**models::ProviderTransform**](ProviderTransform.md)> | | [optional]
**output_type** | Option<[**models::InputTransform**](InputTransform.md)> | Output format type. Valid values: 'text' (default) - plain text response, 'image' - image generation | [optional]
**user_message** | Option<[**models::InputTransform**](InputTransform.md)> | The user's prompt/message to the AI agent. Supports variable interpolation with flow.input syntax. Required unless memory is off and `previous_messages` supplies the prompt; image output always needs it. | [optional]
**system_prompt** | Option<[**models::InputTransform**](InputTransform.md)> | System instructions that guide the AI's behavior, persona, and response style. Optional. | [optional]
**streaming** | Option<[**models::InputTransform**](InputTransform.md)> | Boolean. If true, stream the AI response incrementally. Streaming events include: token_delta, reasoning_token_delta, tool_call, tool_call_arguments, tool_execution, tool_result | [optional]
**memory** | Option<[**models::MemoryTransform**](MemoryTransform.md)> | | [optional]
**memory_id** | Option<[**models::InputTransform**](InputTransform.md)> | String. Names the memory this step reads and writes, overriding the memory id the run was started with (the chat conversation, an app chat session or the `memory_id` run parameter). Leave unset to use the run's memory id. A fixed value shares one memory across every run; an expression such as `flow_input.customer_id` keeps one memory per key. When it evaluates to an empty value the agent runs without memory. Read only while `memory` is `window`: it is ignored when memory is off, and an older `auto` or `manual` memory reads neither history input. | [optional]
**previous_messages** | Option<[**models::InputTransform**](InputTransform.md)> | Array of MemoryMessage. History supplied by the flow, sent between the system prompt and the user message. Read only while `memory` is off or absent: managed memory ignores it, and an older `auto` or `manual` memory reads neither history input. | [optional]
**output_schema** | Option<[**models::InputTransform**](InputTransform.md)> | JSON Schema object defining structured output format. Used when you need the AI to return data in a specific shape. Supports standard JSON Schema properties: type, properties, required, items, enum, pattern, minLength, maxLength, minimum, maximum, etc. Example: { type: 'object', properties: { name: { type: 'string' }, age: { type: 'integer' } }, required: ['name'] } | [optional]
**user_attachments** | Option<[**models::InputTransform**](InputTransform.md)> | Array of file references (images or PDFs) for the AI agent. Format: Array<{ bucket: string, key: string }> - S3 object references Example: [{ bucket: 'my-bucket', key: 'documents/report.pdf' }] | [optional]
**enabled_tools** | Option<[**models::InputTransform**](InputTransform.md)> | Array of strings naming which of the tools configured in `tools` the agent may call this run. Leaving it unset carries every one of them; an empty array carries none. A tool is named as the model is shown it. An entry the model is shown nothing of is named by what identifies it instead: an MCP server by its resource path, carrying every tool it exposes (which of them stays that entry's include_tools/exclude_tools), and a websearch entry by the reserved name '__wm_web_search', whatever summary it carries (no tool may take that name). Example: ['get_user', 'u/admin/github_mcp', '__wm_web_search'] | [optional]
**max_completion_tokens** | Option<[**models::InputTransform**](InputTransform.md)> | Integer. Maximum number of tokens the AI will generate in its response. Range: 1 to 4,294,967,295. Typical values: 256-4096 for most use cases. | [optional]
**temperature** | Option<[**models::InputTransform**](InputTransform.md)> | Float. Controls randomness/creativity of responses. Range: 0.0 to 2.0 (provider-dependent) - 0.0 = deterministic, focused responses - 0.7 = balanced (common default) - 1.0+ = more creative/random | [optional]
**max_iterations** | Option<[**models::InputTransform**](InputTransform.md)> | Number. Limits how many times the agent can loop through reasoning and tool use. Range: 1-1000. | [optional]
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)