AIAgentPlannerContext
Represents a context for the AI agent of PlannerAIAgent type, responsible for managing execution pipelines, configurations, and other contextual data required for agent operations.
Parameters
The AI agent's operating environment, which provides tools, error reporting, and mechanism for execution.
A unique identifier for the agent.
A unique identifier representing the current execution run.
Input data provided to the agent for processing or decision-making.
Configuration details for the AI agent, dictating its behavior and settings.
The context for interactions with the underlying language model.
Responsible for managing the state of the agent across executions.
Provides long-term memory or storage for the agent's operations.
Name of the strategy guiding the agent's behavior.
The planning pipeline that orchestrates the agent's decision-making processes.
Metadata and details regarding the agent's execution, such as timestamps or states.
An optional parent context, allowing nested or hierarchical composition of agent contexts.
Constructors
Properties
Represents the input provided to the agent's execution.
Represents the configuration for an AI agent.
Represents the environment in which the agent operates.
Represents the observability data associated with the AI Agent context.
Represents the AI agent's LLM context, providing mechanisms for managing tools, prompts, and interaction with the execution environment. It ensures thread safety during concurrent read and write operations through the use of sessions.
Represents the parent context of the AI Agent.
Represents the pipeline associated with the AI agent.
Manages and tracks the state of an AI agent within the context of its execution.
Concurrent-safe key-value storage for an agent, used to manage and persist data within the context of the AI agent stage execution. The storage property provides a thread-safe mechanism for sharing and storing data specific to the agent's operation.
Represents the name of the strategy being used in the current AI agent context.
Functions
Utility function to get AIAgentContext.agentInput and try to cast it to some expected type.
Appends messages to the current LLM prompt without making an LLM request. Corresponds to nodeAppendPrompt.
Compresses the current LLM prompt (message history) into a summary, replacing messages with a TLDR.
Creates a copy of the current AIAgentPlannerContext, allowing for selective overriding of its properties. This method is useful for creating modified contexts during agent execution without mutating the original context.
Extension function to access the Debugger feature from an agent context.
Calls a specific tool directly using the provided arguments.
Executes a tool call and returns the result.
Executes all tool calls from a Message.Assistant and returns their results. Corresponds to nodeExecuteToolsAndGetReceivedResults.
Executes multiple tool calls and returns their results. These calls can optionally be executed in parallel.
Retrieves a feature from the AIAgentContext.pipeline associated with this context using the specified key.
Retrieves a feature from the AIAgentContext.pipeline associated with this context using the specified key or throws an exception if it is not available.
Retrieves the agent-specific context data associated with the current instance.
Retrieves the agent-specific context data associated with the current instance.
Extracts a list of tool call messages from a given list of response messages.
Extracts a list of tool call messages from a given list of response messages.
Retrieves the latest token usage from the prompt within the LLM session.
Moderates a message using the LLM. Corresponds to nodeLLMModerateMessage.
Executes the provided action if the given response is of type Message.Assistant.
Invokes the provided action when multiple tool call messages are found within a given list of response messages. Filters the list of responses to include only instances of MessagePart.Tool.Call and executes the action on the filtered list if it is not empty.
Removes the agent-specific context data associated with the current context.
Removes the agent-specific context data associated with the current context.
Sends a message to a Large Language Model (LLM) and optionally allows the use of tools during the LLM interaction. The message becomes part of the current prompt, and the LLM's response is processed accordingly, either with or without tool integrations based on the provided parameters. Corresponds to nodeLLMRequestWithUserText.
Sends a message to a Large Language Model (LLM) and forces it to use a specific tool. The message becomes part of the current prompt, and the LLM is instructed to use only the specified tool.
Sends a string message to the LLM and returns multiple response choices. Corresponds to nodeLLMRequestMultipleChoicesWithUserText.
Sends a string message to the LLM without tool calls. Corresponds to nodeLLMRequestOnlyCallingToolsWithUserText.
Sends a message to a Large Language Model (LLM) and streams the LLM response. The message becomes part of the current prompt, and the LLM's response is streamed as it's generated.
Sends a string message to the LLM and returns a structured response using a StructuredRequestConfig. Corresponds to nodeLLMRequestStructuredWithUserText.
Sends a structured request to the Large Language Model (LLM) and processes the response.
Sends a string message to the LLM without tool calls. Corresponds to nodeLLMRequestWithoutToolsWithUserText.
Provides the root context of the current agent. If the root context is not defined, this function defaults to returning the current instance.
Adds a tool result to the prompt and requests an LLM response.
Adds multiple tool results to the prompt and gets multiple LLM responses.
Sends tool results to the LLM and forces it to use a specific tool. Corresponds to nodeSendToolReceivedResultsForceOneTool.
Sends tool results to the LLM and returns multiple response choices. Corresponds to nodeSendToolReceivedResultsMultipleChoices.
Sends tool results to the LLM, restricting it to only calling tools. Corresponds to nodeSendToolReceivedResultsOnlyCallingTools.
Sends tool results to the LLM without allowing further tool calls. Corresponds to nodeSendToolReceivedResultsWithoutTools.
Stores the given agent context data within the current AI agent context.
Executes a subtask within the larger context of an AI agent's functional operation. This method allows defining a specific task to be performed with the given input, tools, and optional configuration.
Executes a subtask within the AI agent's functional context. This method enables the use of tools to achieve a specific task based on the input provided.
Executes a subtask with validation and verification of the results. The method defines a subtask for the AI agent using the provided input and additional parameters and ensures that the output is evaluated based on its correctness and feedback.
Executes a block of code with a modified execution context.
Executes a block of code with a modified execution context, creating a parent-child relationship between execution contexts for tracing purposes.