feat(llm): support incremental Responses WebSocket transport

apps/admin_console/services/model_settings_service.py

@@ -22,6 +22,7 @@ class ModelSettingsUpdate(BaseModel):
     api_key: SecretStr | None = None  # Omitted/blank keeps the existing key.
     timeout_seconds: float = Field(default=300, gt=0, le=3600)
     max_retries: int = Field(default=5, ge=0, le=10)
+    transport: Literal["http", "websocket"] | None = None
     retry_interval_seconds: float = Field(default=10, ge=0, le=300)
     rate_limit_retry_seconds: float | None = Field(default=None, ge=0, le=3600)
     tool_fallback_model: str | None = Field(default=None, min_length=1, max_length=200)
@@ -72,6 +73,7 @@ def get_model_settings() -> dict:
         "api_key_configured": bool(settings.OPENAI_API_KEY),
         "timeout_seconds": settings.OPENAI_TIMEOUT_SECONDS,
         "max_retries": settings.OPENAI_MAX_RETRIES,
+        "transport": settings.OPENAI_TRANSPORT,
         "retry_interval_seconds": settings.OPENAI_RETRY_INTERVAL_SECONDS,
         "rate_limit_retry_seconds": settings.OPENAI_RATE_LIMIT_RETRY_SECONDS,
         "tool_fallback_model": settings.OPENAI_TOOL_FALLBACK_MODEL,
@@ -102,6 +104,7 @@ def save_model_settings(update: ModelSettingsUpdate) -> dict:
         "OPENAI_REASONING_EFFORT": update.reasoning_effort,
     }
     optional_settings = {
+        "transport": ("OPENAI_TRANSPORT", str),
         "rate_limit_retry_seconds": ("OPENAI_RATE_LIMIT_RETRY_SECONDS", float),
         "tool_fallback_model": ("OPENAI_TOOL_FALLBACK_MODEL", str),
         "tool_fallback_reasoning_effort": ("OPENAI_TOOL_FALLBACK_REASONING_EFFORT", str),
@@ -261,10 +264,19 @@ async def test_model_settings(update: ModelSettingsUpdate) -> dict:
         api_base=update.base_url,
         timeout_seconds=update.timeout_seconds,
         max_retries=0,
+        transport=update.transport or settings.OPENAI_TRANSPORT,
         reasoning_effort=None if update.reasoning_effort == "default" else update.reasoning_effort,
     )
     model = ModelFactory.create_model(endpoint)
-    result = await model.ainvoke([HumanMessage(content="Reply with OK only.")])
+    try:
+        result = await model.ainvoke([HumanMessage(content="Reply with OK only.")])
+    finally:
+        await model.http_async_client.aclose()
+        model.http_client.close()
     if not result.content:
         raise ValueError("Responses 接口返回空内容，请检查模型配置")
-    return {"success": True, "message": "Responses 连接测试成功", "model": update.model}
+    return {
+        "success": True,
+        "message": f"Responses {endpoint.transport.upper()} 连接测试成功",
+        "model": update.model,
+    }