AbstractProtected_JSON validator instance for cleaning and validating responses
Static ReadonlyCURRENT_Common placeholder for current payload injection
Determines if loop results should be injected as a temporary user message before the next prompt execution (for LLM reasoning).
Default: true (most agent types benefit from seeing loop results) Flow agents override to false (deterministic path navigation, no LLM)
true to inject results as message, false to skip
Indicates whether this agent type requires agent-level prompts (AI Agent Prompts relationship).
Some agent types (like Flow) use step-level prompts exclusively and don't need agent-level prompts. Other agent types (like Loop) require agent-level prompts for their main reasoning loop.
Default: true (most agent types require agent-level prompts)
True if agent-level prompts are required, false if optional
OptionalAfterCalled after each loop iteration completes to process results.
Flow agents use this to apply ActionOutputMapping and update payload. Loop agents typically don't need this (just collect results).
Results from this iteration
Modified payload or null for default behavior (just collect result)
OptionalBeforeCalled before each loop iteration to prepare parameters and payload.
Loop agents use this to resolve template variables ("item.email"). Flow agents typically don't need this (params already resolved).
Current iteration context
Modified context or null for default behavior
ProtectedcreateProtectedCreates a standardized next step object with common defaults
The payload type
The step type
Additional options to merge
The next step object
ProtectedcreateProtectedCreates a retry step with a standardized error message
The payload type
The error message
Additional options
Retry step
ProtectedcreateProtectedCreates a success step with optional payload changes
The payload type
Success options
Success step
AbstractDetermineDetermines the initial step when no previous decision exists.
This method allows agent types to customize how they begin execution. For example:
The full execution parameters including agent, payload, and context
The initial step, or null to use default behavior (prompt execution)
AbstractDetermineAnalyzes the output from prompt execution to determine the next step.
This method is called after the hierarchical prompts have been executed and should parse the LLM's response to determine what the agent should do next. The implementation depends on the specific agent type's logic and the format of output expected from its system prompt.
Result from prompt execution (null for non-prompt steps)
The full execution parameters including agent and context
The determined next step and optional return value
public async DetermineNextStep(): Promise<BaseAgentNextStep> {
// Implementation might parse JSON output from LLM
const response = JSON.parse(this.lastExecutionResult);
if (response.taskComplete) {
return { step: 'success', payload: response.payload };
} else if (response.needsSubAgent) {
return { step: 'subagent', payload: response.subAgentConfig };
} else {
return { step: 'action', payload: response.nextAction };
}
}
Provides agent-type-specific guidance for configuration errors related to missing prompts. This allows each agent type to give contextual help based on its architecture.
Default implementation provides generic guidance. Agent types should override to provide specific instructions relevant to their configuration requirements.
Configuration guidance specific to this agent type
AbstractGetAllows agent types to provide a custom prompt for a specific step. This is used by agent types that need to override the default prompt selection logic (e.g., Flow agents that use different prompts for different steps).
The base implementation should return the default prompt from configuration. Agent types can override this to provide custom prompt selection logic.
The full execution parameters for additional context
The loaded agent configuration with default prompts
OptionalpreviousDecision: BaseAgentNextStep<P>The previous step decision that may contain context
A prompt entity to use (either custom or config.childPrompt)
Determines how to handle Success or Failed steps when no explicit termination is requested.
This allows agent types to control their own fallback behavior:
Default implementation returns null, which causes base-agent to fall back to prompt execution if prompts are configured. Agent types can override this to provide custom behavior.
The Success or Failed step that needs fallback handling
The loaded agent configuration
The execution parameters
The current payload
Agent type's state
Custom step to execute, or null for default behavior
AbstractInitializeThis method allows each agent type to initialize its agent-run-specific state package as required. Not all agent types require this and are able to live off just the current payload or other properties passed to them to DetermineNextStep(), but some require more complex internal state tracking.
the agent execution params
the fully initialized initial agent-type state
AbstractInjectThe agent type is responsible for injecting a payload into the prompt. This can be done by updating the system prompt by replacing a special non-Nunjucks placeholder, or by adding extra messages to the prompt.
The payload to inject
The prompt parameters to update
Agent identification info including agent ID and run ID
ProtectedparseProtectedParses JSON response from prompt execution with automatic validation syntax cleaning
The expected response type
The prompt execution result
Parsed response or null if parsing fails
Post-processes the result of action execution.
This method is called by BaseAgent after action(s) have been executed. Agent types can override this method to perform custom processing of action results, such as mapping output parameters to the payload or storing results in agent-specific context.
The results from action execution
The actions that were executed
The current payload
The current step being executed
Optional payload change request
Post-processes the result of sub-agent execution.
This method is called by BaseAgent after a sub-agent has been executed. Agent types can override this method to perform custom processing of sub-agent results, such as extracting specific data from the sub-agent's payload or updating context.
The result from sub-agent execution
The sub-agent request that was executed
The current payload
The current step being executed
Optional payload change request
Pre-processes an action step before execution.
This method is called by BaseAgent before action(s) are executed. Agent types can override this method to perform custom pre-processing, such as mapping payload values to action input parameters or modifying action configurations.
The actions that will be executed (can be modified)
The current payload
The current step being executed
Optionalparams: ExecuteAgentParams<P>Actions are modified in place
AbstractPrePre-processes a retry step to allow agent types to customize retry behavior.
This method is called when the previous step returned 'Retry' as the next step. Agent types can override this to provide custom behavior instead of the default prompt execution. This is particularly useful for:
The full execution parameters
Custom next step, or null to use default retry behavior (prompt execution)
Protected StaticgetProtectedInstantiates an agent type class using a specific driver class name.
This method is used when an individual agent has its own DriverClass override, allowing for specialized implementations per agent instance.
The driver class name to instantiate
Instance of the agent type class
Protected StaticgetProtectedInstantiates the appropriate agent type class based on the agent type entity.
This method uses the MemberJunction class factory to dynamically instantiate agent type classes. It uses the DriverClass field. If DriverClass is not specified it throws an error.
The agent type entity to instantiate
Instance of the agent type class
StaticGetHelper method that retrieves an instance of the agent type based on the provided agent type entity.
This method uses the ClassFactory to create an instance of the agent type class specified in the DriverClass field of the agent type entity. If the DriverClass is not specified, it throws an error.
The agent type entity to instantiate
An instance of the agent type class
Abstract base class for agent type implementations.
Agent types define reusable execution patterns that control how agents behave. Each agent type is associated with a system prompt that guides the LLM's output format and decision-making process. Common agent type patterns include:
The agent type's system prompt should be designed to produce output that can be parsed by the DetermineNextStep method to decide what happens next in the agent's execution flow.
BaseAgentType
Example