Use codemap find "SymbolName" to locate any symbol before reading — it gives exact file + line range and is faster than grep across the whole repo.

Chat Model Configuration & Parameter Tuning

Quick start

# agent.py — from __future__ import annotations is safe here (no @tool)
from __future__ import annotations

from lauren_ai import agent
from lauren_ai._memory._stores import InMemoryConversationStore

@agent(
    model="claude-opus-4-6",
    system="You are a helpful assistant.",
    max_turns=3,
    temperature=0.7,
    max_tokens_per_turn=2048,
    memory_window_tokens=20_000,
    tool_error_policy="return_error",
    conversation_store=InMemoryConversationStore(),
)
class ConfiguredAgent: ...

@agent() parameters

max_turns enforcement

from lauren_ai import agent, AgentMaxTurnsError
from lauren_ai._agents._runner import AgentRunnerBase as AgentRunner
from lauren_ai._config import LLMConfig
from lauren_ai._transport._mock import MockTransport

@agent(model="claude-opus-4-6", max_turns=2)
class LimitedAgent: ...

cfg = LLMConfig(provider="anthropic", model="mock-model", api_key="mock")
mock = MockTransport()
runner = AgentRunner(transport=mock)

# Queue 5 tool-use completions — runner stops at max_turns
# AgentMaxTurnsError is raised once the cap is hit

Lifecycle-doc class (using a docstring as system prompt)

@agent(model="claude-opus-4-6", max_turns=5)
class DocAgent:
    """You are an expert Python programmer.
    Always respond with working code.
    """

The class docstring becomes the system prompt when no system= kwarg is given.

Reference files