Step
A Step represents a single phase within a
Context. Each step
has its own prompt text, completion criteria, available functions, and navigation
rules. The AI advances through steps automatically when criteria are met.
You create steps by calling add_step() on a Context object. All setter methods
return self for fluent method chaining.
Properties
name
Step name. Must be unique within the parent context.
Methods
Add a POM section with bullet points to the step.
Add a question to this step’s gather_info configuration.
Add a POM section to the step.
Remove all POM sections and direct text from this step.
Set whether the conversation should end after this step completes.
Set which SWAIG functions are available during this step.
Enable structured info gathering for this step.
Set whether to consolidate conversation history on context switch.
Set whether to completely replace the system prompt on context switch.
Set a new system prompt for context switching from this step.
Set a user message to inject when this step triggers a context switch.
Automatically advance to the next step without evaluating criteria.
Skip waiting for user input after this step completes.
Define when this step is considered complete.
Set the step’s prompt text directly.
Set which contexts the agent can navigate to from this step.
Set which steps the agent can navigate to from this step.
