메뉴
Configures agent behaviour via @agent() parameters and AgentConfig. Use when adjusting max_turns, temperature, max_tokens_per_turn, max_cost_usd, tool_error_policy, memory window, or when the agent must stop after a fixed number of turns.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Adds content safety filters to lauren-ai agents using @use_guardrails for input and output checks. Use when an agent needs prompt injection protection, PII redaction, topic filtering, length limiting, or LLM-powered content evaluation. Also covers creating custom guardrail classes injectable via @guardrail.
Aggregates per-model telemetry from SignalBus events using CostTracker and a custom PerformanceMetrics collector. Use when tracking total LLM calls, token consumption, average latency, error rate, and cost per model across agent runs.
Submit agent tasks to an asyncio queue and process them with a background worker, returning results by task ID. Use when you need non-blocking agent execution in web handlers, batch processing pipelines, or any situation where callers should not wait for agent completion.
Builds AI agents with the lauren-ai framework using @agent, @use_tools, and AgentRunner. Use when defining an agent class, setting up lifecycle hooks, streaming responses, implementing agent delegation, or configuring the agentic loop with tools, guardrails, and memory.
Creates tools for lauren-ai agents using @tool() on async functions or classes. Use when implementing a @tool() function or class, working with ToolContext for DI injection, adding caching, HITL approval, or using built-in skills like WebSearchTool, HttpFetchTool, or CodeExecutionTool.
Implements an in-memory calendar management tool for agents using @tool() class-form. Use when building agents that create, query, or cancel calendar events, with ISO 8601 time handling and date-based filtering. Supports @set_metadata for tool-type annotation.
| name | chat-model-configuration |
| description | Configures agent behaviour via @agent() parameters and AgentConfig. Use when adjusting max_turns, temperature, max_tokens_per_turn, max_cost_usd, tool_error_policy, memory window, or when the agent must stop after a fixed number of turns. |
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.
# 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: ...
| Parameter | Type | Default | Description |
|---|---|---|---|
model | str | required | Model identifier, e.g. "claude-opus-4-6" |
system | str | "" | System prompt for every turn |
max_turns | int | 10 | Loop iteration cap; raises AgentMaxTurnsError |
max_tokens_per_turn | int | 4096 | Output token limit per LLM call |
temperature | float | 1.0 | Sampling temperature (0.0–2.0) |
memory_window_tokens | int | 40_000 | Sliding context window in tokens |
max_cost_usd | float | None | None | Cost cap; raises AgentBudgetExceededError |
parallel_tool_calls | bool | False | Run all tool calls in a turn concurrently |
tool_error_policy | str | "return_error" | "raise" | "return_error" | "skip" |
conversation_store | ConversationStore | None | None | Persistent conversation history |
memory | ShortTermMemory | None | None | Per-agent shared short-term memory |
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
@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.
| File | Contents |
|---|---|
src/lauren_ai/_config.py | AgentConfig frozen dataclass — all defaults |
src/lauren_ai/_agents/__init__.py | @agent() decorator, AgentMeta |
src/lauren_ai/_agents/_runner.py | AgentRunnerBase loop with max_turns check |