max_steps 以前同时充当软预算和 recursion_limit,于是预算耗尽的那一刻 必然触发 GraphRecursionError:模型连一句收尾都来不及说,用户只收到 「处理消息时出错,请稍后再试」,已产出的内容也不会落库。 - 新增 StepBudgetMiddleware:按模型调用轮数计账(agent_rounds = max_steps // 2),剩余 <=4 轮时注入一次「立刻停止调用工具、给出结论」 的收尾提示,只提醒一次 - 新增 STEP_GRACE(20),recursion_limit = max_steps + STEP_GRACE,把余量 留给收尾动作 - GraphRecursionError 统一转成 StepBudgetExceeded,ainvoke 与流式两条 路径都覆盖 - AgentReply 把「步数用尽」渲染成可操作说明,接在已产出内容之后一并 下发并落库;用 _reported 标记让 on_error 不再补发通用错误文案,任务 状态仍如实记 failed - 同步 README / docs/architecture.md / db/schema.py 中 max_steps 的语义 测试:新增 tests/test_budget.py(7 个用例),全量 241 passed。
140 lines
4.7 KiB
Python
140 lines
4.7 KiB
Python
"""步数预算测试:预算换算、收尾提示注入、硬上限转成可读失败。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
from typing import Any
|
|
|
|
import pytest
|
|
from langgraph.errors import GraphRecursionError
|
|
|
|
from bot042.agent.middlewares.budget import (
|
|
BUDGET_PREFIX,
|
|
BUDGET_WARN_MARGIN,
|
|
StepBudget,
|
|
StepBudgetExceeded,
|
|
StepBudgetMiddleware,
|
|
bind,
|
|
current_budget,
|
|
unbind,
|
|
)
|
|
from bot042.config import STEP_GRACE, Settings
|
|
from bot042.flows import agent_task as agent_task_module
|
|
from bot042.flows.agent_task import run_task, stream_task
|
|
|
|
|
|
class RecordingAgent:
|
|
"""记录调用配置,并顺带把当时绑定的预算读出来。"""
|
|
|
|
def __init__(self) -> None:
|
|
self.config: dict[str, Any] | None = None
|
|
self.remaining: int | None = None
|
|
|
|
async def ainvoke(
|
|
self, state: dict[str, Any], config: dict[str, Any] | None = None
|
|
) -> dict[str, Any]:
|
|
_ = state
|
|
self.config = config
|
|
budget = current_budget()
|
|
self.remaining = budget.remaining if budget is not None else None
|
|
return {"messages": []}
|
|
|
|
|
|
class RecursionBoomAgent:
|
|
"""模拟 LangGraph 撞上硬上限。"""
|
|
|
|
async def ainvoke(
|
|
self, state: dict[str, Any], config: dict[str, Any] | None = None
|
|
) -> dict[str, Any]:
|
|
_ = state, config
|
|
raise GraphRecursionError("Recursion limit of 27 reached")
|
|
|
|
async def astream(self, *args: Any, **kwargs: Any) -> Any:
|
|
_ = args, kwargs
|
|
raise GraphRecursionError("Recursion limit of 27 reached")
|
|
yield # pragma: no cover - 让本方法成为异步生成器
|
|
|
|
|
|
def test_settings_derive_recursion_limit_and_rounds() -> None:
|
|
"""硬上限必须大于软预算,轮数预算按「一次往返约 2 步」换算。"""
|
|
settings = Settings(max_steps=200)
|
|
assert settings.recursion_limit == 200 + STEP_GRACE
|
|
assert settings.agent_rounds == 100
|
|
# 极小预算也要留出至少一轮,否则中间件永远来不及提醒
|
|
assert Settings(max_steps=1).agent_rounds == 1
|
|
|
|
|
|
def test_budget_take_counts_down() -> None:
|
|
budget = StepBudget(rounds=2)
|
|
assert budget.take() == 1
|
|
assert budget.take() == 0
|
|
assert budget.take() == 0 # 不为负
|
|
assert budget.used == 3
|
|
assert budget.remaining == 0
|
|
|
|
|
|
def test_middleware_noop_without_budget() -> None:
|
|
middleware = StepBudgetMiddleware()
|
|
assert asyncio.run(middleware.abefore_model({}, None)) is None # type: ignore[arg-type]
|
|
|
|
|
|
def test_middleware_warns_once_when_budget_runs_low() -> None:
|
|
budget = StepBudget(rounds=BUDGET_WARN_MARGIN + 2)
|
|
token = bind(budget)
|
|
try:
|
|
middleware = StepBudgetMiddleware()
|
|
# 剩余 5 → 安静;剩余 4 → 注入收尾提示
|
|
assert asyncio.run(middleware.abefore_model({}, None)) is None # type: ignore[arg-type]
|
|
update = asyncio.run(middleware.abefore_model({}, None)) # type: ignore[arg-type]
|
|
assert update is not None
|
|
message = update["messages"][0]
|
|
assert isinstance(message.content, str)
|
|
assert message.content.startswith(BUDGET_PREFIX)
|
|
assert "剩余约 4 轮" in message.content
|
|
assert budget.warned is True
|
|
# 只提醒一次:反复打断只会让模型更答不完
|
|
assert asyncio.run(middleware.abefore_model({}, None)) is None # type: ignore[arg-type]
|
|
finally:
|
|
unbind(token)
|
|
|
|
|
|
def test_run_task_passes_derived_limit_and_binds_budget(monkeypatch) -> None:
|
|
agent = RecordingAgent()
|
|
monkeypatch.setattr(
|
|
agent_task_module, "create_agent", lambda settings=None: agent
|
|
)
|
|
|
|
settings = Settings(max_steps=7)
|
|
asyncio.run(run_task("hi", settings))
|
|
|
|
assert agent.config == {"recursion_limit": 7 + STEP_GRACE}
|
|
assert agent.remaining == settings.agent_rounds # 预算已绑定且未被计数
|
|
# 运行结束必须解绑,否则下一个任务会读到上一轮的预算
|
|
assert current_budget() is None
|
|
|
|
|
|
def test_run_task_translates_recursion_error(monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
agent_task_module, "create_agent", lambda settings=None: RecursionBoomAgent()
|
|
)
|
|
|
|
with pytest.raises(StepBudgetExceeded) as info:
|
|
asyncio.run(run_task("hi", Settings(max_steps=7)))
|
|
assert info.value.max_steps == 7
|
|
assert "max_steps=7" in str(info.value)
|
|
assert current_budget() is None
|
|
|
|
|
|
def test_stream_task_translates_recursion_error(monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
agent_task_module, "create_agent", lambda settings=None: RecursionBoomAgent()
|
|
)
|
|
|
|
async def _consume() -> None:
|
|
async for _ in stream_task("hi", Settings(max_steps=7)):
|
|
pass
|
|
|
|
with pytest.raises(StepBudgetExceeded):
|
|
asyncio.run(_consume())
|
|
assert current_budget() is None
|