feat(config): named LLM provider list via env vars, runtime selection

- Config.llm_profiles: LLM_PROVIDERS declares names, each group defined by
  LLM_<NAME>_BASE_URL/_API_KEY/_MODEL (required) and optional _TIMEOUT_SECONDS/
  _MAX_RETRIES/_TEMPERATURE/_EXTRA_BODY; JSON-dict form of LLM_PROVIDERS also
  supported. LLM_PROVIDER selects the active group at runtime; empty/fake =
  offline scripted model
- removed fixed openai/kimi groups (AGENT_LLM_PROVIDER, KIMI_LLM_*)
- validate(): incomplete groups and unknown LLM_PROVIDER fail fast with
  the configured-name list
- OpenAILLMService: http client trust_env from LLM_HTTP_TRUST_ENV (default
  False - local gateways must bypass the Windows system proxy)
- build_llm_service(provider): explicit name or LLM_PROVIDER default
- .env/.env.example: deepseek + kimi groups side by side, switch by
  LLM_PROVIDER=kimi (thinking off via EXTRA_BODY reasoning_effort=none)
- eval probe scripts updated to the new config interface

Verified: 172 unit tests; live calls succeed on both providers
(deepseek 28s, kimi 6.6s, both emitting valid <state> prefixes)

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,
+    )