Creates a new PreloadMemoryTool
Maximum number of memories to inject (default: 3)
Name of the tool
Description of the tool
Whether the tool is a long running operation, which typically returns a resource id first and finishes the operation later.
Whether the tool execution should be retried on failure
Maximum retry attempts
Base delay for retry in ms (will be used with exponential backoff)
Maximum delay for retry in ms
ProtectedloggerProtectedapiGets the API variant for this tool
Executes the tool with error handling and retries
Arguments for the tool
Tool execution context
Result of the tool execution or error information
Processes the LLM request to inject relevant memories.
This method is called before the LLM request is sent, allowing memories to be added to the system instructions or conversation context.
Tool that automatically preloads relevant memories into the LLM request.
Unlike RecallMemoryTool which requires explicit agent invocation, this tool injects memories during request preprocessing based on the user's query.
This tool does not expose a function declaration to the LLM - it only processes the LLM request to inject context.