Scripted
A scripted LLM operations implementation for testing.
This allows tests to script exact sequences of:
Tool calls (with specific arguments)
Text responses
Object creation
The scripted operations track what was called for verification.
Functions
Script a tool call.
Create an output object, in the context of an AgentProcess.
Try to create an output object in the context of an AgentProcess. Return a failure result if the LLM does not have enough information to create the object.
Try to create an output object with thinking block extraction in the context of an AgentProcess. Return a failure result if the LLM does not have enough information to create the object.
Create an output object with thinking block extraction, in the context of an AgentProcess.
Low level transform, not necessarily aware of platform This is a convenience overload that creates a UserMessage from a String prompt
Low level transform, not necessarily aware of platform
Low level transform with thinking block extraction, not necessarily aware of platform.
Low level transform with thinking block extraction and MaybeReturn semantics, not necessarily aware of platform. Returns a failure result if the LLM indicates it cannot create the object.
Generate text in the context of an AgentProcess.
Script a text response.
Script returning an object.
Add a scripted action to the sequence.