diff --git a/.env.example b/.env.example index 7b7dab7..546ee30 100644 --- a/.env.example +++ b/.env.example @@ -9,11 +9,22 @@ APP_ID=replace-with-fastgpt-app-id # Voice demo (Pipecat /ws-product). Relative to project root, or an absolute path. VOICE_CONFIG=config/voice.json -# LangGraph chat backend + LLM provider (作业 2/4) +# LangGraph chat backend（作业 2） # AGENT_BACKEND=langgraph -# AGENT_LLM_PROVIDER=openai -# LLM_BASE_URL=https://api.openai.com/v1 -# LLM_API_KEY=replace-with-llm-api-key -# LLM_MODEL=gpt-4o-mini -# LLM_TIMEOUT_SECONDS=30 -# LLM_MAX_RETRIES=2 +# +# 命名 LLM 提供商组（均为 OpenAI 兼容接口）：LLM_PROVIDERS 声明名单， +# LLM_PROVIDER 选择当前生效组；缺省或 fake = 离线脚本模型。 +# 每组 LLM_<名>_BASE_URL / _API_KEY / _MODEL 必填； +# 可选 _TIMEOUT_SECONDS / _MAX_RETRIES / _TEMPERATURE / _EXTRA_BODY（JSON 字符串， +# 如思考开关 KIMI 网关为 {"reasoning_effort":"none"}）。 +# LLM_PROVIDERS=deepseek,kimi +# LLM_PROVIDER=deepseek +# LLM_DEEPSEEK_BASE_URL=https://api.openai.com/v1 +# LLM_DEEPSEEK_API_KEY=replace-with-llm-api-key +# LLM_DEEPSEEK_MODEL=gpt-4o-mini +# LLM_KIMI_BASE_URL=http://127.0.0.1:3425/v1 +# LLM_KIMI_API_KEY=magpie +# LLM_KIMI_MODEL=kimi-code-cn/kimi-for-coding +# LLM_KIMI_EXTRA_BODY={"reasoning_effort":"none"} +# 本地网关需直连（系统代理会导致 5xx）；外部网关如需代理： +# LLM_HTTP_TRUST_ENV=true diff --git a/evals/prompt_compare.py b/evals/prompt_compare.py index d5ad430..930b17d 100644 --- a/evals/prompt_compare.py +++ b/evals/prompt_compare.py @@ -39,13 +39,13 @@ def main(): path = args.prompt_dir / (name+'.md') return path.read_text(encoding='utf-8') if path.exists() else original_loader(name) registry.load_prompt = snapshot_loader - if Config.AGENT_BACKEND != 'langgraph' or Config.AGENT_LLM_PROVIDER != 'openai': + if Config.AGENT_BACKEND != 'langgraph' or not Config.LLM_PROVIDER or Config.LLM_PROVIDER == 'fake': raise SystemExit('Requires langgraph backend and real openai provider') args.output_dir.mkdir(parents=True, exist_ok=True) cases = load_cases(DEFAULT_CASES_DIR, args.case) from src.agent.prompts import load_prompt metadata = { - 'model': Config.LLM_MODEL, 'temperature': Config.LLM_TEMPERATURE, + **{k: v for k, v in (Config.llm_profile(Config.LLM_PROVIDER) or {}).items() if k in ('model', 'temperature')}, 'backend': Config.AGENT_BACKEND, 'workers': args.workers, 'commit': subprocess.check_output(['git', 'rev-parse', 'HEAD'], text=True).strip(), 'case_hashes': {str(p.relative_to(DEFAULT_CASES_DIR)): sha256(p.read_bytes()).hexdigest() diff --git a/evals/prompt_probes.py b/evals/prompt_probes.py index faed519..f231ee0 100644 --- a/evals/prompt_probes.py +++ b/evals/prompt_probes.py @@ -63,7 +63,7 @@ async def main(args): if args.prompt_dir: import src.agent.prompts as registry registry.load_prompt = lambda name: (args.prompt_dir / (name+'.md')).read_text(encoding='utf-8') - llm = build_llm_service('openai') + llm = build_llm_service() semaphore = asyncio.Semaphore(4) async def run(case): async with semaphore: @@ -107,7 +107,8 @@ async def main(args): results = await asyncio.gather(*(run(c) for c in selected)) from src.core.config import Config from src.agent.prompts import load_prompt - output = dict(model=Config.LLM_MODEL, temperature=Config.LLM_TEMPERATURE, + profile = Config.llm_profile(Config.LLM_PROVIDER) or {} + output = dict(model=profile.get('model'), temperature=profile.get('temperature'), execution_mode='runtime' if args.runtime else 'raw_prompt', prompt_hashes={name:sha256(load_prompt(name).encode('utf-8')).hexdigest() for name in (COLLECTION,EXTRACTION)}, passed=sum(r['passed'] for r in results), total=len(results), results=results) diff --git a/evals/time_boundary.py b/evals/time_boundary.py index f823681..1fd39c9 100644 --- a/evals/time_boundary.py +++ b/evals/time_boundary.py @@ -26,7 +26,7 @@ def parsed_time(value): async def main(output): - llm = build_llm_service('openai') + llm = build_llm_service() cases = [] for delay in (75,135): cases.append(dict(name=f'anchored_cross_midnight_delay_{delay}',now=ORIGIN+timedelta(minutes=delay), diff --git a/src/agent/llm.py b/src/agent/llm.py index 85637b2..ec9f918 100644 --- a/src/agent/llm.py +++ b/src/agent/llm.py @@ -5,7 +5,8 @@ fake 与真实 provider 实现同一 ``LLMService`` Protocol，节点不感知 - ``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。 +``build_llm_service`` 按命名提供商列表（Config.LLM_PROVIDERS / LLM_PROVIDER） +选择实现，见 core.config。 """ from collections.abc import Awaitable, Callable @@ -92,6 +93,7 @@ class OpenAILLMService: timeout_seconds: float = 30.0, max_retries: int = 2, temperature: float | None = None, + extra_body: dict | None = None, ): self._model = model self._api_key = api_key @@ -99,17 +101,24 @@ class OpenAILLMService: self._timeout_seconds = timeout_seconds self._max_retries = max_retries self._temperature = temperature + # 附加请求体（如思考开关），原样合并进 chat.completions.create 参数。 + self._extra_body = dict(extra_body or {}) 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。 + # trust_env=False：不走系统代理，本地网关直连（代理曾导致 503/500）。 if self._client is None: + import httpx from openai import AsyncOpenAI + from ..core.config import Config + kwargs = {"api_key": self._api_key, "timeout": self._timeout_seconds} if self._base_url: kwargs["base_url"] = self._base_url + kwargs["http_client"] = httpx.AsyncClient(trust_env=Config.LLM_HTTP_TRUST_ENV) self._client = AsyncOpenAI(**kwargs) return self._client @@ -130,6 +139,7 @@ class OpenAILLMService: kwargs: dict = {"model": self._model, "messages": messages} if self._temperature is not None: kwargs["temperature"] = self._temperature + kwargs.update(self._extra_body) retries = 0 while True: try: @@ -225,19 +235,41 @@ def workflow_fake_llm() -> "FakeLLMService": 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。""" + """按命名提供商列表构造 LLM 服务；provider 缺省读 Config.LLM_PROVIDER。 + + 配置见 Config.llm_profiles（LLM_PROVIDERS 名单 + LLM_<名>_* 变量）。 + provider 为空或 fake = 离线脚本模型。 + """ 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, - temperature=Config.LLM_TEMPERATURE, - ) - if provider == "fake": + provider = (provider if provider is not None else Config.LLM_PROVIDER) + provider = (provider or "").strip().lower() + if not provider or provider == "fake": return FakeLLMService(_default_fake_responder) - raise ValueError(f"Unknown AGENT_LLM_PROVIDER: {provider!r}") + profiles = Config.llm_profiles() + if provider not in profiles: + raise ValueError( + f"Unknown LLM provider {provider!r}; configured: {sorted(profiles)}" + ) + profile = profiles[provider] + extra_body: dict = {} + if profile["extra_body"]: + import json as _json + + try: + parsed = _json.loads(profile["extra_body"]) + if isinstance(parsed, dict): + extra_body = parsed + except ValueError as exc: + raise ValueError( + f"extra_body of provider {provider!r} is not valid JSON: {exc}" + ) from exc + return OpenAILLMService( + model=profile["model"], + api_key=profile["api_key"], + base_url=profile["base_url"], + timeout_seconds=profile["timeout_seconds"], + max_retries=profile["max_retries"], + temperature=profile["temperature"], + extra_body=extra_body, + ) diff --git a/src/core/config.py b/src/core/config.py index 6e05594..a37473f 100644 --- a/src/core/config.py +++ b/src/core/config.py @@ -19,18 +19,110 @@ class Config: # "fastgpt" 保持现有行为；"langgraph" 使用内存图 fake 回复。 AGENT_BACKEND = os.getenv("AGENT_BACKEND", "fastgpt") - # LLM provider（作业 4）：fake 为脚本化假模型，离线可运行； - # openai 为真实 provider（OpenAI 兼容接口）。 - AGENT_LLM_PROVIDER = os.getenv("AGENT_LLM_PROVIDER", "fake") - LLM_MODEL = os.getenv("LLM_MODEL", "fake-reply-model") - LLM_BASE_URL = os.getenv("LLM_BASE_URL", "") - LLM_API_KEY = os.getenv("LLM_API_KEY", "") - LLM_TIMEOUT_SECONDS = float(os.getenv("LLM_TIMEOUT_SECONDS", "30")) - LLM_MAX_RETRIES = int(os.getenv("LLM_MAX_RETRIES", "2")) - # 采样温度；None 表示使用 provider 缺省。对照 FastGPT 应用配置调整。 - LLM_TEMPERATURE = ( - float(os.getenv("LLM_TEMPERATURE")) if os.getenv("LLM_TEMPERATURE") else None + # 命名 LLM 提供商列表（均为 OpenAI 兼容接口），两种写法二选一： + # ① JSON 字典（推荐，单变量管理）： + # LLM_PROVIDERS={"deepseek": {"base_url": "https://...", "api_key": "...", + # "model": "deepseek-v4.1-flash"}, + # "kimi": {"base_url": "http://127.0.0.1:3425/v1", + # "api_key": "magpie", "model": "kimi-code-cn/kimi-for-coding", + # "extra_body": {"reasoning_effort": "none"}}} + # 每组 base_url/api_key/model 必填；timeout_seconds/max_retries/ + # temperature 可选；extra_body 为对象时直接合并进请求体（思考开关等）。 + # ② 逗号分隔名单 + 分散变量： + # LLM_PROVIDERS=deepseek,kimi + LLM_DEEPSEEK_BASE_URL/_API_KEY/_MODEL 等。 + # 运行时选择：LLM_PROVIDER=<名>；缺省或 fake = 离线脚本模型。 + LLM_PROVIDERS = os.getenv("LLM_PROVIDERS", "") + LLM_PROVIDER = os.getenv("LLM_PROVIDER", "") + # LLM 客户端是否信任系统代理（Windows 注册表）。缺省 False： + # 本地网关（127.0.0.1）必须直连；外部网关若需代理设为 true。 + LLM_HTTP_TRUST_ENV = os.getenv("LLM_HTTP_TRUST_ENV", "false").lower() in ( + "true", "1", "t", ) + + @classmethod + def _declared_provider_names(cls) -> list[str]: + """LLM_PROVIDERS 中声明的提供商名（JSON 字典取键，名单取逗号项）。""" + raw = cls.LLM_PROVIDERS.strip() + if not raw: + return [] + if raw.startswith("{"): + import json + + data = json.loads(raw) + return [str(k).strip().lower() for k in data] + return [n.strip().lower() for n in raw.split(",") if n.strip()] + + @classmethod + def llm_profiles(cls) -> dict[str, dict]: + """解析命名提供商列表为统一结构；声明了但缺必填项的组不收录 + （由 validate() 统一报错）。extra_body 统一为 JSON 字符串。""" + raw = cls.LLM_PROVIDERS.strip() + if not raw: + return {} + if raw.startswith("{"): + return cls._profiles_from_json(raw) + return cls._profiles_from_prefixed(raw) + + @classmethod + def _profiles_from_json(cls, raw: str) -> dict[str, dict]: + import json + + try: + data = json.loads(raw) + except ValueError as exc: + raise ValueError(f"LLM_PROVIDERS is not valid JSON: {exc}") from exc + if not isinstance(data, dict): + raise ValueError("LLM_PROVIDERS JSON must be an object keyed by provider name") + profiles: dict[str, dict] = {} + for key, spec in data.items(): + name = str(key).strip().lower() + if not name or not isinstance(spec, dict): + continue + base_url = str(spec.get("base_url", "")) + api_key = str(spec.get("api_key", "")) + model = str(spec.get("model", "")) + if not (base_url and api_key and model): + continue + extra_body = spec.get("extra_body", "") + if isinstance(extra_body, dict): + extra_body = json.dumps(extra_body, ensure_ascii=False) + temperature = spec.get("temperature") + profiles[name] = { + "base_url": base_url, + "api_key": api_key, + "model": model, + "timeout_seconds": float(spec.get("timeout_seconds", 30)), + "max_retries": int(spec.get("max_retries", 2)), + "temperature": float(temperature) if temperature is not None else None, + "extra_body": str(extra_body), + } + return profiles + + @classmethod + def _profiles_from_prefixed(cls, raw: str) -> dict[str, dict]: + profiles: dict[str, dict] = {} + for name in cls._declared_provider_names(): + prefix = f"LLM_{name.upper()}_" + base_url = os.getenv(prefix + "BASE_URL", "") + api_key = os.getenv(prefix + "API_KEY", "") + model = os.getenv(prefix + "MODEL", "") + if not (base_url and api_key and model): + continue + temperature = os.getenv(prefix + "TEMPERATURE") + profiles[name] = { + "base_url": base_url, + "api_key": api_key, + "model": model, + "timeout_seconds": float(os.getenv(prefix + "TIMEOUT_SECONDS", "30")), + "max_retries": int(os.getenv(prefix + "MAX_RETRIES", "2")), + "temperature": float(temperature) if temperature else None, + "extra_body": os.getenv(prefix + "EXTRA_BODY", ""), + } + return profiles + + @classmethod + def llm_profile(cls, name: str) -> dict | None: + return cls.llm_profiles().get(name.strip().lower()) @classmethod def validate(cls): @@ -41,16 +133,21 @@ class Config: raise ValueError( f"AGENT_BACKEND must be 'fastgpt' or 'langgraph', got {cls.AGENT_BACKEND!r}" ) - if cls.AGENT_LLM_PROVIDER not in ("fake", "openai"): + profiles = cls.llm_profiles() # JSON 非法时在此抛出明确错误 + incomplete = [n for n in cls._declared_provider_names() if n not in profiles] + if incomplete: raise ValueError( - "AGENT_LLM_PROVIDER must be 'fake' or 'openai', " - f"got {cls.AGENT_LLM_PROVIDER!r}" + "LLM providers missing BASE_URL/API_KEY/MODEL: " + + ", ".join(incomplete) ) - if cls.AGENT_LLM_PROVIDER == "openai" and ( - not cls.LLM_API_KEY or not cls.LLM_BASE_URL + if ( + cls.LLM_PROVIDER + and cls.LLM_PROVIDER != "fake" + and cls.LLM_PROVIDER.strip().lower() not in profiles ): raise ValueError( - "AGENT_LLM_PROVIDER=openai requires LLM_API_KEY and LLM_BASE_URL" + f"Unknown LLM_PROVIDER {cls.LLM_PROVIDER!r}; " + f"configured: {sorted(profiles)}" ) if cls.AGENT_BACKEND != "fastgpt": return