pub struct AiAgentInputTransforms {Show 16 fields
pub provider: Option<Box<ProviderTransform>>,
pub output_type: Option<Box<InputTransform>>,
pub user_message: Option<Box<InputTransform>>,
pub system_prompt: Option<Box<InputTransform>>,
pub streaming: Option<Box<InputTransform>>,
pub memory: Option<Box<MemoryTransform>>,
pub memory_id: Option<Box<InputTransform>>,
pub previous_messages: Option<Box<InputTransform>>,
pub output_schema: Option<Box<InputTransform>>,
pub user_attachments: Option<Box<InputTransform>>,
pub enabled_tools: Option<Box<InputTransform>>,
pub max_completion_tokens: Option<Box<InputTransform>>,
pub temperature: Option<Box<InputTransform>>,
pub max_iterations: Option<Box<InputTransform>>,
pub model: Option<Box<InputTransform>>,
pub reasoning_effort: Option<Box<InputTransform>>,
}Expand description
AiAgentInputTransforms : Input parameters for the AI agent mapped to their values
Fields§
§provider: Option<Box<ProviderTransform>>§output_type: Option<Box<InputTransform>>Output format type. Valid values: ‘text’ (default) - plain text response, ‘image’ - image generation
user_message: Option<Box<InputTransform>>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.
system_prompt: Option<Box<InputTransform>>System instructions that guide the AI’s behavior, persona, and response style. Optional.
streaming: Option<Box<InputTransform>>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
memory: Option<Box<MemoryTransform>>§memory_id: Option<Box<InputTransform>>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 or compaction: it is ignored when memory is off, and an older auto or manual memory reads neither history input.
previous_messages: Option<Box<InputTransform>>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.
output_schema: Option<Box<InputTransform>>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’] }
user_attachments: Option<Box<InputTransform>>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’ }]
enabled_tools: Option<Box<InputTransform>>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’]
max_completion_tokens: Option<Box<InputTransform>>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.
temperature: Option<Box<InputTransform>>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
max_iterations: Option<Box<InputTransform>>Number. Limits how many times the agent can loop through reasoning and tool use. Range: 1-1000.
model: Option<Box<InputTransform>>String. Only on a step linked to a saved agent (see agent): replaces the model saved on the agent for this step’s runs, on the agent’s own provider resource. An empty value keeps the saved model. Set it to an expression such as flow_input.model to choose the model per run.
reasoning_effort: Option<Box<InputTransform>>String. Only on a step linked to a saved agent (see agent): replaces the reasoning effort saved on the agent for this step’s runs, as a provider-native token (e.g. ‘low’, ‘high’, ‘none’). An empty value sends no effort, so the model runs at its default. Leave the input out to keep the saved effort, which holds only while the step runs the saved model. A step that is not linked sets both inside provider.
Implementations§
Source§impl AiAgentInputTransforms
impl AiAgentInputTransforms
Sourcepub fn new() -> AiAgentInputTransforms
pub fn new() -> AiAgentInputTransforms
Input parameters for the AI agent mapped to their values