feat(agent): LLM-powered collection node with welcome stage and session-scoped delete (assignment 4)
- prompts/collection.md: versioned collection system prompt extracted from workflow node yQaBxfrWjbRr with source/version/porting notes - llm.py: LLMService protocol; FakeLLMService (scripted, records calls); OpenAILLMService (async, wait_for timeout with cancellation, retry only on timeout/429/connection, errors normalized) - collect.py: run_collect reference impl - one LLM call produces state prefix + body, controlled repair (max 1 retry) for missing prefix or illegal stage proposal, whitelist guard, CollectReplyError without raw model content; dialogue history + confirmed fields injected into prompt so the model skips known info (作业4-5) - fields.py / clock.py: three-state field candidates (unknown/ candidate/confirmed), per-type validation (count not inferred from description, future time rejected), injectable Clock - graph.py: welcome node - first message returns fixed 1001 greeting without LLM (mirrors workflow is_first_message -> Assigned Reply#3), route empty stage to welcome - endpoints/delete_session: backend switch - langgraph clears graph checkpoint, fastgpt path unchanged - config: AGENT_LLM_PROVIDER fake|openai with validation - untrack .env (secrets), move template to root .env.example Verified: - pytest 103 passed; smoke turns 1/2/1 - Real LLM e2e: POST /chat multi-turn context works - Golden eval collection_skip_known_info: 12/12 cases pass - Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail at final step - model routes on short reply '对' (prompt-adherence gap, photo/confirm stages are assignment 5 scope); recorded in evals/results/20261020-144856 Known limits: field extraction from model reply not wired (stub); photo/confirm nodes still scaffold; clarify counting is approximate.
This commit is contained in:
Eric Wang
@@ -0,0 +1,163 @@
|
||||
"""LLM 服务（作业 4）。
|
||||
|
||||
fake 与真实 provider 实现同一 ``LLMService`` Protocol，节点不感知差异：
|
||||
- ``FakeLLMService``：脚本化固定输出，离线可重复，日常测试用它；
|
||||
- ``OpenAILLMService``：真实 provider（TODO 关键代码）——
|
||||
超时、取消、有限重试、模型配置。
|
||||
|
||||
``build_llm_service`` 按 ``Config.AGENT_LLM_PROVIDER`` 选择实现。
|
||||
"""
|
||||
|
||||
from collections.abc import Awaitable, Callable
|
||||
from typing import Protocol
|
||||
|
||||
Responder = Callable[[str, str], str | Awaitable[str]]
|
||||
|
||||
|
||||
class LLMError(Exception):
|
||||
"""LLM 调用失败基类。"""
|
||||
|
||||
|
||||
class LLMTimeoutError(LLMError):
|
||||
"""调用超过超时时间。"""
|
||||
|
||||
|
||||
class LLMAPIError(LLMError):
|
||||
"""provider 返回错误或无效响应。"""
|
||||
|
||||
|
||||
class LLMService(Protocol):
|
||||
"""节点依赖的最小 LLM 接口。"""
|
||||
|
||||
async def complete(self, system_prompt: str, user_message: str) -> str:
|
||||
"""返回模型文本输出（含 <state> 前缀，由调用方解析校验）。"""
|
||||
...
|
||||
|
||||
|
||||
class FakeLLMService:
|
||||
"""按 responder 返回固定输出的假 LLM。
|
||||
|
||||
responder 接收 (system_prompt, user_message)，返回 str（或
|
||||
coroutine）。每次调用记录在 ``calls``，测试用它断言
|
||||
“一次轮次只调用一次模型”等约束。
|
||||
"""
|
||||
|
||||
def __init__(self, responder: Responder):
|
||||
self._responder = responder
|
||||
self.calls: list[dict[str, str]] = []
|
||||
|
||||
async def complete(self, system_prompt: str, user_message: str) -> str:
|
||||
self.calls.append(
|
||||
{"system_prompt": system_prompt, "user_message": user_message}
|
||||
)
|
||||
import asyncio
|
||||
|
||||
result = self._responder(system_prompt, user_message)
|
||||
if asyncio.iscoroutine(result):
|
||||
result = await result
|
||||
return result
|
||||
|
||||
|
||||
class OpenAILLMService:
|
||||
"""真实 LLM provider（OpenAI 兼容接口，如 OpenAI / DeepSeek 等）。
|
||||
|
||||
参考实现：async 客户端 + asyncio.wait_for 超时（取消会向外传播，
|
||||
客户端断连时图任务随之取消）；仅对可重试错误（429 / 5xx / 连接错）
|
||||
按 LLM_MAX_RETRIES 指数退避重试；错误统一转换为
|
||||
LLMTimeoutError / LLMAPIError，不向上层泄漏原始响应体。
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
model: str,
|
||||
api_key: str,
|
||||
base_url: str = "",
|
||||
timeout_seconds: float = 30.0,
|
||||
max_retries: int = 2,
|
||||
):
|
||||
self._model = model
|
||||
self._api_key = api_key
|
||||
self._base_url = base_url
|
||||
self._timeout_seconds = timeout_seconds
|
||||
self._max_retries = max_retries
|
||||
self._client = None
|
||||
|
||||
def _get_client(self):
|
||||
# 延迟构造：fake provider 使用时无需安装/初始化真实客户端。
|
||||
# AsyncOpenAI 的创建不绑定事件循环，可在首次调用前安全缓存。
|
||||
if self._client is None:
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
kwargs = {"api_key": self._api_key, "timeout": self._timeout_seconds}
|
||||
if self._base_url:
|
||||
kwargs["base_url"] = self._base_url
|
||||
self._client = AsyncOpenAI(**kwargs)
|
||||
return self._client
|
||||
|
||||
async def complete(self, system_prompt: str, user_message: str) -> str:
|
||||
import asyncio
|
||||
|
||||
from openai import APIConnectionError, APITimeoutError, RateLimitError
|
||||
|
||||
client = self._get_client()
|
||||
messages = [
|
||||
{"role": "system", "content": system_prompt},
|
||||
{"role": "user", "content": user_message},
|
||||
]
|
||||
retries = 0
|
||||
while True:
|
||||
try:
|
||||
response = await asyncio.wait_for(
|
||||
client.chat.completions.create(
|
||||
model=self._model, messages=messages
|
||||
),
|
||||
timeout=self._timeout_seconds,
|
||||
)
|
||||
except (APITimeoutError, asyncio.TimeoutError) as exc:
|
||||
# 超时：可重试，重试耗尽后转换为 LLMTimeoutError
|
||||
if retries < self._max_retries:
|
||||
retries += 1
|
||||
await asyncio.sleep(min(2 ** retries, 10))
|
||||
continue
|
||||
raise LLMTimeoutError(
|
||||
f"LLM 调用超时（{self._timeout_seconds}s，"
|
||||
f"重试 {self._max_retries} 次后仍失败）"
|
||||
) from exc
|
||||
except (RateLimitError, APIConnectionError) as exc:
|
||||
# 限流 / 连接错误：可重试
|
||||
if retries < self._max_retries:
|
||||
retries += 1
|
||||
await asyncio.sleep(min(2 ** retries, 10))
|
||||
continue
|
||||
raise LLMAPIError(f"LLM provider 不可用：{type(exc).__name__}") from exc
|
||||
except Exception as exc:
|
||||
# 其他错误（如 4xx 参数错）不可重试
|
||||
raise LLMAPIError(f"LLM 调用失败：{type(exc).__name__}") from exc
|
||||
|
||||
content = response.choices[0].message.content if response.choices else None
|
||||
if not content:
|
||||
raise LLMAPIError("LLM 返回了空内容")
|
||||
return content
|
||||
|
||||
|
||||
def _default_fake_responder(system_prompt: str, user_message: str) -> str:
|
||||
"""离线兜底假回复：回显输入，保持服务在无配置时可启动。"""
|
||||
return f"<state>1002</state>已收到：{user_message}"
|
||||
|
||||
|
||||
def build_llm_service(provider: str | None = None) -> LLMService:
|
||||
"""按配置构造 LLM 服务；provider 缺省读 Config.AGENT_LLM_PROVIDER。"""
|
||||
from ..core.config import Config
|
||||
|
||||
provider = provider or Config.AGENT_LLM_PROVIDER
|
||||
if provider == "openai":
|
||||
return OpenAILLMService(
|
||||
model=Config.LLM_MODEL,
|
||||
api_key=Config.LLM_API_KEY,
|
||||
base_url=Config.LLM_BASE_URL,
|
||||
timeout_seconds=Config.LLM_TIMEOUT_SECONDS,
|
||||
max_retries=Config.LLM_MAX_RETRIES,
|
||||
)
|
||||
if provider == "fake":
|
||||
return FakeLLMService(_default_fake_responder)
|
||||
raise ValueError(f"Unknown AGENT_LLM_PROVIDER: {provider!r}")
|
||||
Reference in New Issue
Block a user