update_settings | SignalWire

Update AI runtime settings dynamically during a call. Changes take effect for subsequent LLM turns.

Parameters

settings

dict[str, Any]Required

Dictionary of settings to update. Supported keys:

Key	Type	Range
`frequency-penalty`	`float`	-2.0 to 2.0
`presence-penalty`	`float`	-2.0 to 2.0
`max-tokens`	`int`	0 to 4096
`top-p`	`float`	0.0 to 1.0
`confidence`	`float`	0.0 to 1.0
`barge-confidence`	`float`	0.0 to 1.0
`temperature`	`float`	0.0 to 2.0 (clamped to 1.5)

Returns

FunctionResult — self, for chaining.

Example

1 from signalwire import AgentBase
2 from signalwire import FunctionResult
3 
4 agent = AgentBase(name="my-agent", route="/agent")
5 agent.set_prompt_text("You are a helpful assistant.")
6 
7 @agent.tool(name="adjust_for_technical_discussion", description="Adjust AI settings for technical topics")
8 def adjust_for_technical_discussion(args, raw_data):
9     return (
10         FunctionResult("Adjusting response parameters.")
11         .update_settings({
12             "temperature": 0.3,
13             "confidence": 0.9,
14             "barge-confidence": 0.8
15         })
16     )
17 
18 agent.serve()