Preserve model rate-limit error messages

Constraint: Users need the original provider error text in AG-UI RUN_ERROR.message while still normalizing retry metadata.\nRejected: Keep fixed Chinese rate-limit copy | It hides the actionable upstream model error from clients.\nConfidence: high\nScope-risk: narrow\nDirective: Keep RATE_LIMITED code and retry fields stable, but do not replace message with generic copy.\nTested: uv run --extra server pytest tests/unittests/server/test_error_utils.py tests/unittests/server/test_invoker.py tests/unittests/server/test_agui_protocol.py tests/unittests/integration/test_langgraph_events.py tests/unittests/integration/test_langgraph_to_agent_event.py -q; uv run ruff check targeted files; git diff --check; uvicorn local harness for status 429/throttling/false-positive 429.\nNot-tested: GitHub CI not yet read back after this commit.

Change-Id: I5a1b893d34dd936bf172ca980d3e7d3a496a60d4
Co-developed-by: Codex <noreply@openai.com>
Signed-off-by: congxiao.wxx <congxiao.wxx@alibaba-inc.com>

Author: congxiao-wxx

agentrun/utils/error_utils.py

@@ -4,7 +4,6 @@
 from typing import Any, Dict, Optional
 
 RATE_LIMITED_CODE = "RATE_LIMITED"
-RATE_LIMITED_MESSAGE = "模型当前请求过多，请稍后再试"
 RATE_LIMITED_RETRY_AFTER_MS = 2000
 
 _RATE_LIMIT_CODES = {
@@ -52,7 +51,7 @@ def build_error_event_data(
         return {"message": fallback_message, "code": fallback_code}
 
     data: Dict[str, Any] = {
-        "message": RATE_LIMITED_MESSAGE,
+        "message": fallback_message,
         "code": RATE_LIMITED_CODE,
         "retryable": True,
         "retryAfterMs": RATE_LIMITED_RETRY_AFTER_MS,

tests/unittests/integration/test_langgraph_events.py

@@ -842,7 +842,7 @@ def test_on_llm_error_rate_limited(self):
 
         assert len(results) == 1
         assert results[0].event == EventType.ERROR
-        assert results[0].data["message"] == "模型当前请求过多，请稍后再试"
+        assert results[0].data["message"] == "LLM error: RuntimeError: API rate limit exceeded"
         assert results[0].data["code"] == "RATE_LIMITED"
         assert results[0].data["retryable"] is True
         assert results[0].data["retryAfterMs"] == 2000

tests/unittests/integration/test_langgraph_to_agent_event.py

@@ -840,7 +840,7 @@ def test_on_llm_error_rate_limited(self):
 
         assert len(results) == 1
         assert results[0].event == EventType.ERROR
-        assert results[0].data["message"] == "模型当前请求过多，请稍后再试"
+        assert results[0].data["message"] == "LLM error: RuntimeError: API rate limit exceeded"
         assert results[0].data["code"] == "RATE_LIMITED"
         assert results[0].data["retryable"] is True
         assert results[0].data["retryAfterMs"] == 2000

tests/unittests/server/test_agui_protocol.py

@@ -163,7 +163,7 @@ def invoke_agent(request: AgentRequest):
             event for event in events if event.get("type") == "RUN_ERROR"
         )
         assert "RUN_FINISHED" not in types
-        assert run_error["message"] == "模型当前请求过多，请稍后再试"
+        assert run_error["message"] == "model overloaded"
         assert run_error["code"] == "RATE_LIMITED"
         assert run_error["retryable"] is True
         assert run_error["retryAfterMs"] == 2000

tests/unittests/server/test_invoker.py

@@ -208,7 +208,7 @@ async def invoke_agent(req: AgentRequest) -> str:
         error_event = next(
             item for item in items if item.event == EventType.ERROR
         )
-        assert error_event.data["message"] == "模型当前请求过多，请稍后再试"
+        assert error_event.data["message"] == "model overloaded"
         assert error_event.data["code"] == "RATE_LIMITED"
         assert error_event.data["retryable"] is True
         assert error_event.data["retryAfterMs"] == 2000