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)

test/agent/test_llm_error_mapping.py

@@ -0,0 +1,134 @@
+"""LLM 错误分类测试：鉴权/限流可区分上报（两后端错误码等价的关键）。
+
+对照 FastGPT 后端：401 -> ChatBackendAuthenticationError、
+429 -> ChatBackendRateLimitError（endpoint 已有对应响应分支）。
+LangGraph 链路由 OpenAILLMService 抛出可区分子类、
+LangGraphBackend 翻译为 ChatBackend* 错误。
+"""
+
+from types import SimpleNamespace
+from unittest.mock import AsyncMock
+
+import httpx
+import pytest
+from openai import AuthenticationError, RateLimitError
+
+from src.agent.llm import (
+    LLMAPIError,
+    LLMAuthError,
+    LLMRateLimitError,
+    OpenAILLMService,
+)
+from src.backends.chat import (
+    ChatBackendAuthenticationError,
+    ChatBackendRateLimitError,
+    ChatInput,
+)
+from src.backends.langgraph import LangGraphBackend
+
+
+def _status_error(cls, status: int) -> Exception:
+    request = httpx.Request("POST", "http://llm.local/v1/chat/completions")
+    response = httpx.Response(status, request=request)
+    return cls("error", response=response, body=None)
+
+
+def _service_with_failing_llm(exc: Exception, max_retries: int = 0):
+    """complete 固定抛 exc 的 OpenAILLMService（client 打桩）。"""
+    llm = OpenAILLMService(model="test", api_key="test", max_retries=max_retries)
+    create = AsyncMock(side_effect=exc)
+    llm._client = SimpleNamespace(
+        chat=SimpleNamespace(completions=SimpleNamespace(create=create))
+    )
+    return llm, create
+
+
+@pytest.mark.asyncio
+async def test_authentication_error_raises_llm_auth_error_without_retry():
+    llm, create = _service_with_failing_llm(
+        _status_error(AuthenticationError, 401), max_retries=2
+    )
+    with pytest.raises(LLMAuthError):
+        await llm.complete("系统", "输入")
+    # 401 不可重试：只调用一次
+    assert create.call_count == 1
+
+
+@pytest.mark.asyncio
+async def test_rate_limit_error_retries_then_raises_llm_rate_limit_error():
+    llm, create = _service_with_failing_llm(
+        _status_error(RateLimitError, 429), max_retries=2
+    )
+    with pytest.raises(LLMRateLimitError):
+        await llm.complete("系统", "输入")
+    assert create.call_count == 3   # 首次 + 2 次重试
+
+
+@pytest.mark.asyncio
+async def test_llm_error_subclasses_are_api_errors():
+    """子类兼容既有 LLMAPIError 捕获（不破坏现有 except 顺序）。"""
+    assert issubclass(LLMAuthError, LLMAPIError)
+    assert issubclass(LLMRateLimitError, LLMAPIError)
+
+
+class _GraphRaising:
+    """ainvoke 固定抛指定异常的图替身。"""
+
+    def __init__(self, exc: Exception):
+        self._exc = exc
+
+    async def ainvoke(self, *args, **kwargs):
+        raise self._exc
+
+
+@pytest.mark.asyncio
+async def test_langgraph_backend_maps_auth_error_to_backend_error():
+    backend = LangGraphBackend(
+        graph=_GraphRaising(LLMAuthError("bad key")),
+        llm=SimpleNamespace(),
+    )
+    with pytest.raises(ChatBackendAuthenticationError):
+        await backend.complete(
+            ChatInput(session_id="s1", text="你好", client_mode="direct")
+        )
+
+
+@pytest.mark.asyncio
+async def test_langgraph_backend_maps_rate_limit_to_backend_error():
+    backend = LangGraphBackend(
+        graph=_GraphRaising(LLMRateLimitError("限流")),
+        llm=SimpleNamespace(),
+    )
+    with pytest.raises(ChatBackendRateLimitError):
+        await backend.complete(
+            ChatInput(session_id="s1", text="你好", client_mode="direct")
+        )
+
+
+@pytest.mark.asyncio
+async def test_langgraph_backend_stream_propagates_mapped_errors():
+    """stream 经由 complete 实现，映射自动生效。"""
+    backend = LangGraphBackend(
+        graph=_GraphRaising(LLMAuthError("bad key")),
+        llm=SimpleNamespace(),
+    )
+    with pytest.raises(ChatBackendAuthenticationError):
+        async for _ in backend.stream(
+            ChatInput(session_id="s1", text="你好", client_mode="direct")
+        ):
+            pass
+
+
+@pytest.mark.asyncio
+async def test_langgraph_backend_other_llm_errors_still_raise_api_error():
+    """其余 LLM 错误保持原样上抛（endpoint 落 500 通用分支）。"""
+    from src.agent.llm import LLMAPIError, LLMTimeoutError
+
+    backend = LangGraphBackend(
+        graph=_GraphRaising(LLMTimeoutError("超时")),
+        llm=SimpleNamespace(),
+    )
+    with pytest.raises(LLMTimeoutError):
+        await backend.complete(
+            ChatInput(session_id="s1", text="你好", client_mode="direct")
+        )