Changelog

New fields to support reasoning models

The LlmConfig object now includes a enable_reasoner field, enables toggling on thinking steps for reasoning models like Sonnet 3.7. This change also includes support for specifying this along with max_reasoning_tokens in the agent creation API.

1
from letta_client import Letta
2
client = Letta(
3
    token="YOUR_API_KEY",
4
)
5
agent = client.agents.create(
6
    model="claude/sonnet-3-7",
7
    enable_reasoner=True,
8
    max_reasoning_tokens=10000,
9
    max_tokens=100000
10
)