Member Junction
    Preparing search index...

    Interface LoopAgentTypePromptParams

    Configuration parameters for Loop Agent Type.

    Controls prompt content (which sections are included), client tool availability, and content limits. Stored in AIAgent.AgentTypePromptParams as JSON.

    All boolean prompt-inclusion properties default to true (include section). Set to false to exclude a section from the prompt and save tokens.

    These parameters are configured at three levels with merge precedence:

    1. Schema defaults (from AIAgentType.PromptParamsSchema) - lowest priority
    2. Agent config (from AIAgent.AgentTypePromptParams) - medium priority
    3. Runtime override (from ExecuteAgentParams.data.__agentTypePromptParams) - highest priority
    // Agent configuration to disable unused features
    const agentConfig: LoopAgentTypePromptParams = {
        includeForEachDocs: false,      // Agent never iterates collections
        includeWhileDocs: false,        // Agent never polls/retries
        includeResponseFormDocs: false, // Agent never collects user input
        includeCommandDocs: false       // Agent doesn't trigger UI actions
    };

    // Runtime override to enable a feature for a specific execution
    const result = await agent.Execute({
        agent: myAgent,
        conversationMessages: messages,
        data: {
            __agentTypePromptParams: {
                includeForEachDocs: true  // Enable for this run only
            }
        }
    });

    // Minimal response type with granular control
    const minimalConfig: LoopAgentTypePromptParams = {
        includeResponseTypeDefinition: {
            payload: true,        // Keep payload in type
            responseForms: false, // Exclude responseForm from type
            commands: false,      // Exclude commands from type
            forEach: false,       // Exclude ForEach from nextStep.type
            while: false          // Exclude While from nextStep.type
        },
        includeForEachDocs: false,
        includeWhileDocs: false
    };
    interface LoopAgentTypePromptParams {
        includeArtifactToolsDocs?: boolean;
        includeCommandDocs?: boolean;
        includeConversationToolsDocs?: boolean;
        includeDateTimeInPrompt?: boolean;
        includeForEachDocs?: boolean;
        includeMessageExpansionDocs?: boolean;
        includePayloadInPrompt?: boolean;
        includePipelineDocs?: boolean;
        includeResponseFormDocs?: boolean;
        includeResponseTypeDefinition?: ResponseTypeInclusionRules;
        includeScratchpadDocs?: boolean;
        includeVariableRefsDocs?: boolean;
        includeWhileDocs?: boolean;
        maxActionsInPrompt?: number;
        maxSubAgentsInPrompt?: number;
        scratchpadMaxTasks?: number;
    }
    Index

    Properties

    includeArtifactToolsDocs? includeCommandDocs? includeConversationToolsDocs? includeDateTimeInPrompt? includeForEachDocs? includeMessageExpansionDocs? includePayloadInPrompt? includePipelineDocs? includeResponseFormDocs? includeResponseTypeDefinition? includeScratchpadDocs? includeVariableRefsDocs? includeWhileDocs? maxActionsInPrompt? maxSubAgentsInPrompt? scratchpadMaxTasks?

    Properties

    includeArtifactToolsDocs?: boolean

    Include artifact tools documentation and artifact manifest in the prompt. Artifact tools allow agents to explore input artifacts on demand. Only emitted when artifacts are present in the run. Disable for agents that never work with artifacts.

    true
    includeCommandDocs?: boolean

    Include actionable/automatic commands documentation. Actionable commands create clickable buttons (e.g., 'Open Record'), automatic commands trigger UI updates (e.g., refresh cache, show notification). Disable for agents that don't need to provide navigation or trigger UI actions.

    true
    includeConversationToolsDocs?: boolean

    Include conversation-history retrieval tool documentation in the prompt (the _CONVERSATION_TOOLS block). Only emitted when the run has a conversationId — these tools page exact pre-summary messages back in by their persisted Sequence handles. Disable for agents that should never dig into conversation history.

    true
    includeDateTimeInPrompt?: boolean

    Include current date, time, and day of week in the prompt. Provides the LLM with accurate temporal context so it doesn't hallucinate dates or claim it doesn't know the current time. Disable for agents where temporal context is irrelevant.

    true
    includeForEachDocs?: boolean

    Include ForEach operation documentation and examples. ForEach enables efficient batch processing of collections (e.g., processing all items in an array with a single LLM decision). Disable for agents that never need to iterate over collections.

    true
    includeMessageExpansionDocs?: boolean

    Include message expansion documentation. Message expansion allows agents to request full content from previously compacted messages. Disable for agents that don't use message compaction or don't need to access compacted content.

    true
    includePayloadInPrompt?: boolean

    Include the current payload state in the prompt. The payload is the agent's working memory that persists across iterations. Disable for agents that don't use the payload pattern or work purely from conversation context. Can save significant tokens for agents with large payloads.

    true
    includePipelineDocs?: boolean

    Include tool-pipeline documentation in the prompt (the _PIPELINE_TOOLS block). Only emitted when at least one pipeline source — an Action or artifact tool — is available. Disable for agents that should never compose pipelines.

    true
    includeResponseFormDocs?: boolean

    Include response form documentation for collecting user input. Response forms allow agents to request specific information from users via text fields, dropdowns, buttons, etc. Disable for agents that only output results and never need user input.

    true
    includeResponseTypeDefinition?: ResponseTypeInclusionRules

    Control response type definition inclusion in the prompt.

    • undefined or object with all defaults: Include full type definition
    • Object with granular rules: Include specific sections based on rules
      • Sections auto-align with their corresponding docs flags unless explicitly set
      • e.g., if includeForEachDocs=false and forEach not set, forEach type is excluded
    { payload: true, responseForms: true, commands: true, forEach: true, while: true }
    includeScratchpadDocs?: boolean

    Include scratchpad documentation and current scratchpad state in the prompt. The scratchpad is private working memory for notes and task tracking. Disable for agents that don't need internal task management or reasoning notes.

    true
    includeVariableRefsDocs?: boolean

    Include variable references documentation (payload., item., etc). These explain how to reference data in action parameters and loop contexts. Disable if agent has custom examples showing variable usage patterns.

    true
    includeWhileDocs?: boolean

    Include While operation documentation and examples. While loops enable polling, retrying, and conditional iteration (e.g., waiting for a job to complete). Disable for agents that never need polling or conditional loops.

    true
    maxActionsInPrompt?: number

    Maximum number of actions to include in prompt details. -1 = include all (default) 0 = include none (hide action capabilities) N = include first N actions Useful for agents with many actions where only a few are commonly used.

    -1
    maxSubAgentsInPrompt?: number

    Maximum number of sub-agents to include in prompt details. -1 = include all (default) 0 = include none (hide sub-agent capabilities) N = include first N sub-agents Useful for agents with many sub-agents where only a few are commonly used.

    -1
    scratchpadMaxTasks?: number

    Maximum number of tasks allowed in the scratchpad task list. When exceeded, completed tasks are auto-pruned oldest first.

    50

    Settings

    Member Visibility

    On This Page

    Properties