Update environment configuration to switch OpenAI model from gpt-5.4 to gpt-4o-mini. Introduce _effective_llm_route_from_request function in api_server.py to determine the effective LLM routing based on service keys and model compatibility. Update chat event handling to include LLM routing information in response data. Enhance logging for better traceability of API interactions.
This commit is contained in:
陈辅元
@@ -13,8 +13,8 @@ MODEL_PRIMARY=deepseek-chat
|
||||
|
||||
OPENAI_API_KEY=sk-proj-FEb2ChHZK5Llm0tBkmNIT3BlbkFJbu0b0zQpTW8762yD6HDv
|
||||
OPENAI_BASE_URL=http://113.192.49.54:9080/v1
|
||||
OPENAI_MODEL=gpt-5.4
|
||||
# OPENAI_CHAT_MODEL=gpt-4o-mini
|
||||
OPENAI_MODEL=gpt-4o-mini
|
||||
# OPENAI_CHAT_MODEL=
|
||||
|
||||
# 模型配置
|
||||
# 主生成模型
|
||||
|
||||
Binary file not shown.
@@ -275,6 +275,36 @@ def _conversation_nl_dict(reply: str) -> Dict[str, Any]:
|
||||
}
|
||||
|
||||
|
||||
def _effective_llm_route_from_request(request: NLChatRequest) -> Dict[str, Any]:
|
||||
"""
|
||||
计算“本次请求实际使用的 LLM 路由信息”（用于前端联调回显）。
|
||||
注意：此处仅回显路由结果，不包含密钥等敏感信息。
|
||||
"""
|
||||
model = _normalize_model_label(request.model)
|
||||
sc = _infer_service_code(request.service_code, model)
|
||||
|
||||
sc2 = sc
|
||||
if sc2 == "deepseek" and not _has_deepseek_key():
|
||||
if _has_openai_key():
|
||||
sc2 = "openai"
|
||||
if sc2 == "openai" and not _has_openai_key():
|
||||
if _has_deepseek_key():
|
||||
sc2 = "deepseek"
|
||||
|
||||
# 与 _maybe_override_orch_llm 保持一致：网关不兼容时丢弃 model 覆盖，让下游走默认模型
|
||||
effective_model = model
|
||||
if effective_model is not None:
|
||||
if (sc2 or "").strip().lower() == "openai" and "deepseek" in effective_model.strip().lower():
|
||||
effective_model = None
|
||||
elif (sc2 or "").strip().lower() == "deepseek" and effective_model.strip().lower().startswith("gpt"):
|
||||
effective_model = None
|
||||
|
||||
return {
|
||||
"service_code": sc2,
|
||||
"model": effective_model,
|
||||
}
|
||||
|
||||
|
||||
def _normalize_lang_code(code: Optional[str]) -> str:
|
||||
raw = (code or "auto").strip()
|
||||
if not raw:
|
||||
@@ -670,6 +700,7 @@ async def _chat_stream_events(request: NLChatRequest) -> AsyncIterator[bytes]:
|
||||
async for pkt in _sse_stream_text_chunks("chat", reply):
|
||||
yield pkt
|
||||
data_dict = _conversation_nl_dict(reply)
|
||||
data_dict["llm"] = _effective_llm_route_from_request(request)
|
||||
yield _sse_data({"code": 200, "msg": "success", "data": data_dict})
|
||||
await _append_session_if_needed(request, text, data_dict)
|
||||
return
|
||||
@@ -760,6 +791,7 @@ async def _chat_stream_events(request: NLChatRequest) -> AsyncIterator[bytes]:
|
||||
pass
|
||||
|
||||
data_dict = _nl_dict_from_generation(result)
|
||||
data_dict["llm"] = _effective_llm_route_from_request(request)
|
||||
msg = "success" if result.valid else "partial"
|
||||
yield _sse_data({"code": 200, "msg": msg, "data": data_dict})
|
||||
await _append_session_if_needed(request, text, data_dict)
|
||||
@@ -846,6 +878,7 @@ async def nl_chat(request: NLChatRequest):
|
||||
reply = _localized_conversation_reply(lang)
|
||||
logger.info("[API/chat] 对话意图: conversation（跳过 Text2SQL）")
|
||||
data_dict = _conversation_nl_dict(reply)
|
||||
data_dict["llm"] = _effective_llm_route_from_request(request)
|
||||
await _append_session_if_needed(request, text, data_dict)
|
||||
return {"code": 200, "msg": "success", "data": data_dict}
|
||||
|
||||
@@ -866,6 +899,7 @@ async def nl_chat(request: NLChatRequest):
|
||||
pass
|
||||
|
||||
data_dict = _nl_dict_from_generation(result)
|
||||
data_dict["llm"] = _effective_llm_route_from_request(request)
|
||||
response_data = NLChatSuccessData.model_validate(data_dict)
|
||||
msg = "success" if result.valid else "partial"
|
||||
if result.valid:
|
||||
|
||||
@@ -105,3 +105,71 @@ ORDER BY m.ValueDate;
|
||||
2026-04-16 13:48:13 INFO [agents.orchestrator] orchestrator.py:754 _validate_sql() | [validate] 程序+探针+LLM 汇总: valid=True err_count=0 warn_count=0 db_execution_status=0 sql_chars=494
|
||||
2026-04-16 13:48:13 INFO [agents.orchestrator] orchestrator.py:921 generate() | [OK] SQL生成与验证通过（1次尝试）
|
||||
2026-04-16 13:48:13 INFO [__main__] api_server.py:776 _chat_stream_events() | [API/stream] Text2SQL 完成: valid=True attempts=1 tables_used=['TSBTransferInstruction', 'VSBTransferInstruction', 'VSBHKRpt0431', 'VSBHKRpt0430', 'TSBAccountInstrumentMovement'] sql_chars=494 sql_head="-- 查询所有客户账户间股票转移记录\n-- 使用 TSBAccountInstrumentMovement，MovementType='T' 表示账户间转移\nSELECT \n m.MovementID,\n m.AccountID AS FromAccountID,\n m.TransferToAccountID,\n m.InstrumentID,\n i.Name AS InstrumentSymbol,\n m.MovementType,\n m.Quantity AS TransferQuantity,\n m.ValueDate AS TransferDate\nFROM TSBAccountInstrumentMovement m\nLEFT JOIN MCInstrument i ON m.InstrumentID = i.InstrumentID\nWHERE m.MovementType = 'T'\n AND m.ValueDate = CAST(GETDATE() AS DATE)\nORDER BY m.ValueDate;"
|
||||
2026-04-16 14:40:07 INFO [uvicorn.access] httptools_impl.py:483 send() | 192.168.3.210:53090 - "POST /g3sb/api/nl/chat/stream HTTP/1.1" 200
|
||||
2026-04-16 14:50:35 INFO [__main__] api_server.py:668 _chat_stream_events() | [API/stream] 开始: user_id='ACCOUNT' visitor_biz_id=None session_id='a68b69c0-d945-4553-869f-3538d42900f9' service_code='openai' model=None lang_code='zh' msg_chars=3 preview='123' dialog_context_chars=0 last_turn_was_data_query=False
|
||||
2026-04-16 14:50:38 INFO [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-5.4, base_url=http://113.192.49.54:9080/v1
|
||||
2026-04-16 14:50:38 INFO [uvicorn.error] server.py:272 shutdown() | Shutting down
|
||||
2026-04-16 14:50:38 ERROR [asyncio] base_events.py:1820 default_exception_handler() | Exception in callback BaseProactorEventLoop._start_serving.<locals>.loop(<_OverlappedF...210', 55004))>) at D:\conda\Lib\asyncio\proactor_events.py:843
|
||||
handle: <Handle BaseProactorEventLoop._start_serving.<locals>.loop(<_OverlappedF...210', 55004))>) at D:\conda\Lib\asyncio\proactor_events.py:843>
|
||||
Traceback (most recent call last):
|
||||
File "D:\conda\Lib\asyncio\events.py", line 88, in _run
|
||||
self._context.run(self._callback, *self._args)
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 858, in loop
|
||||
self._make_socket_transport(
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 647, in _make_socket_transport
|
||||
return _ProactorSocketTransport(self, sock, protocol, waiter,
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 613, in __init__
|
||||
super().__init__(loop, sock, protocol, waiter, extra, server)
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 189, in __init__
|
||||
super().__init__(loop, sock, protocol, waiter, extra, server)
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 335, in __init__
|
||||
super().__init__(*args, **kw)
|
||||
File "D:\conda\Lib\asyncio\proactor_events.py", line 66, in __init__
|
||||
self._server._attach()
|
||||
File "D:\conda\Lib\asyncio\base_events.py", line 296, in _attach
|
||||
assert self._sockets is not None
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
AssertionError
|
||||
2026-04-16 14:50:38 INFO [uvicorn.error] server.py:102 _serve() | Finished server process [37328]
|
||||
2026-04-16 14:50:38 ERROR [uvicorn.error] on.py:134 send() | Traceback (most recent call last):
|
||||
File "D:\conda\Lib\asyncio\runners.py", line 194, in run
|
||||
return runner.run(main)
|
||||
^^^^^^^^^^^^^^^^
|
||||
File "D:\conda\Lib\asyncio\runners.py", line 118, in run
|
||||
return self._loop.run_until_complete(task)
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
File "D:\conda\Lib\asyncio\base_events.py", line 674, in run_until_complete
|
||||
self.run_forever()
|
||||
File "D:\conda\Lib\asyncio\windows_events.py", line 322, in run_forever
|
||||
super().run_forever()
|
||||
File "D:\conda\Lib\asyncio\base_events.py", line 641, in run_forever
|
||||
self._run_once()
|
||||
File "D:\conda\Lib\asyncio\base_events.py", line 1986, in _run_once
|
||||
handle._run()
|
||||
File "D:\conda\Lib\asyncio\events.py", line 88, in _run
|
||||
self._context.run(self._callback, *self._args)
|
||||
File "C:\Users\24019\AppData\Roaming\Python\Python312\site-packages\uvicorn\server.py", line 78, in serve
|
||||
with self.capture_signals():
|
||||
^^^^^^^^^^^^^^^^^^^^^^
|
||||
File "D:\conda\Lib\contextlib.py", line 144, in __exit__
|
||||
next(self.gen)
|
||||
File "C:\Users\24019\AppData\Roaming\Python\Python312\site-packages\uvicorn\server.py", line 339, in capture_signals
|
||||
signal.raise_signal(captured_signal)
|
||||
File "D:\conda\Lib\asyncio\runners.py", line 157, in _on_sigint
|
||||
raise KeyboardInterrupt()
|
||||
KeyboardInterrupt
|
||||
|
||||
During handling of the above exception, another exception occurred:
|
||||
|
||||
Traceback (most recent call last):
|
||||
File "C:\Users\24019\AppData\Roaming\Python\Python312\site-packages\starlette\routing.py", line 645, in lifespan
|
||||
await receive()
|
||||
File "C:\Users\24019\AppData\Roaming\Python\Python312\site-packages\uvicorn\lifespan\on.py", line 137, in receive
|
||||
return await self.receive_queue.get()
|
||||
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||
File "D:\conda\Lib\asyncio\queues.py", line 158, in get
|
||||
await getter
|
||||
asyncio.exceptions.CancelledError
|
||||
|
||||
2026-04-16 14:50:43 INFO [utils.dialog_classifier] dialog_classifier.py:211 _classify_dialog_llm() | [dialog] intent=conversation (LLM) reply_chars=51 reply_preview='请具体说明你想查询什么数据，例如时间范围、品种、账户或指标。仅输入“123”我还无法判断你的查询需求。'
|
||||
|
||||
Reference in New Issue
Block a user