feat(backends): map LLM auth/rate-limit errors to backend-neutral errors

Closes the error-code gap between LangGraph and FastGPT backends: the
endpoint's 401/429 branches previously could never trigger under the
LangGraph backend because all provider failures collapsed into LLMAPIError
(500).

- agent/llm: LLMAuthError / LLMRateLimitError as LLMAPIError subclasses;
  OpenAILLMService raises them from openai AuthenticationError (401, no
  retry) and RateLimitError (429, after bounded retries exhausted)
- backends/langgraph: _complete_turn translates LLMAuthError ->
  ChatBackendAuthenticationError and LLMRateLimitError ->
  ChatBackendRateLimitError; stream reuses complete() so the mapping
  applies to both paths; other errors (timeout etc.) propagate unchanged
- endpoint untouched: existing 401/429 response branches now fire for
  both backends

Verified: 212 unit tests (7 new error-mapping tests)

src/agent/llm.py

@@ -27,6 +27,16 @@ class LLMAPIError(LLMError):
     """provider 返回错误或无效响应。"""
 
 
+class LLMAuthError(LLMAPIError):
+    """provider 拒绝凭证（401）。不可重试，需区分上报（对照
+    FastGPT 后端的 ChatBackendAuthenticationError 语义）。"""
+
+
+class LLMRateLimitError(LLMAPIError):
+    """provider 限流（429）。重试耗尽后抛出，需区分上报（对照
+    FastGPT 后端的 ChatBackendRateLimitError 语义）。"""
+
+
 class LLMService(Protocol):
     """节点依赖的最小 LLM 接口。"""
 
@@ -128,7 +138,12 @@ class OpenAILLMService:
     ) -> str:
         import asyncio
 
-        from openai import APIConnectionError, APITimeoutError, RateLimitError
+        from openai import (
+            APIConnectionError,
+            APITimeoutError,
+            AuthenticationError,
+            RateLimitError,
+        )
 
         client = self._get_client()
         messages = [
@@ -163,7 +178,15 @@ class OpenAILLMService:
                     retries += 1
                     await asyncio.sleep(min(2 ** retries, 10))
                     continue
+                if isinstance(exc, RateLimitError):
+                    # 限流耗尽：区分上报，API 层映射为 429（两后端错误码等价）
+                    raise LLMRateLimitError(
+                        f"LLM provider 限流（重试 {self._max_retries} 次后仍失败）"
+                    ) from exc
                 raise LLMAPIError(f"LLM provider 不可用：{type(exc).__name__}") from exc
+            except AuthenticationError as exc:
+                # 401 鉴权失败：不可重试，区分上报，API 层映射为 401
+                raise LLMAuthError("LLM provider 认证失败") 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

src/backends/langgraph.py

@@ -15,8 +15,11 @@
 from collections.abc import AsyncIterator
 
 from ..agent.graph import GraphDeps, build_graph, workflow_fake_llm
+from ..agent.llm import LLMAuthError, LLMRateLimitError
 from .chat import (
     ChatBackend,
+    ChatBackendAuthenticationError,
+    ChatBackendRateLimitError,
     ChatInput,
     ChatResult,
     ChatStreamEvent,
@@ -49,6 +52,20 @@ class LangGraphBackend(ChatBackend):
         - 本阶段不处理 ``need_form_update`` 的真实表单差量
           （作业 6 起实现）。
         """
+        result = await self._complete_turn(chat_input)
+        return ChatResult(
+          content = result["response_text"],
+          status_code = None,
+          form_update = result.get("turn_patch") or {}
+        )
+
+    async def _complete_turn(self, chat_input: ChatInput) -> dict:
+        """执行一轮图，把 LLM 层错误翻译为后端中立错误。
+
+        错误码等价（对照 FastGPT 后端）：
+        LLMAuthError -> ChatBackendAuthenticationError（API 层 401）；
+        LLMRateLimitError -> ChatBackendRateLimitError（API 层 429）。
+        """
         graph_input: dict = {
             "session_id": chat_input.session_id,
             "input_text": chat_input.text,
@@ -58,16 +75,16 @@ class LangGraphBackend(ChatBackend):
         # 使 set_info 写入后本轮 chat 立即可见（输入覆盖 checkpoint 同键）。
         if chat_input.injected_fields:
             graph_input.update(chat_input.injected_fields)
-        result = await self._graph.ainvoke(
-            graph_input,
-            config={"configurable": {"thread_id": chat_input.session_id}},
-            context=GraphDeps(llm=self._llm),
-        )
-        return ChatResult(
-          content = result["response_text"],
-          status_code = None,
-          form_update = result.get("turn_patch") or {}
-        )
+        try:
+            return await self._graph.ainvoke(
+                graph_input,
+                config={"configurable": {"thread_id": chat_input.session_id}},
+                context=GraphDeps(llm=self._llm),
+            )
+        except LLMAuthError as exc:
+            raise ChatBackendAuthenticationError(str(exc)) from exc
+        except LLMRateLimitError as exc:
+            raise ChatBackendRateLimitError(str(exc)) from exc
 
     async def stream(self, chat_input: ChatInput) -> AsyncIterator[ChatStreamEvent]:
         """流式：产生中立流事件。