feat(llm): support incremental Responses WebSocket transport

artemis/llm/router.py

@@ -17,7 +17,7 @@
 from enum import StrEnum
 import hashlib
 import os
-from typing import Any
+from typing import Any, Literal
 
 from langchain_core.language_models.chat_models import BaseChatModel
 from pydantic import BaseModel, Field
@@ -40,6 +40,9 @@ class ModelEndpoint(BaseModel):
     model_name: str = Field(default_factory=lambda: settings.OPENAI_MODEL)
     api_key: str | None = Field(default=None, repr=False)
     api_base: str | None = None
+    transport: Literal["http", "websocket"] = Field(
+        default_factory=lambda: settings.OPENAI_TRANSPORT
+    )
     temperature: float | None = None
     max_tokens: int | None = Field(default=None, gt=0)
     timeout_seconds: float = Field(default_factory=lambda: settings.OPENAI_TIMEOUT_SECONDS, gt=0)
@@ -63,6 +66,7 @@ class ModelEndpoint(BaseModel):
             self.enable_grounding,
             self.api_base or settings.OPENAI_BASE_URL,
             settings.OPENAI_USE_SYSTEM_PROXY,
+            self.transport,
             hashlib.sha256(key.encode()).hexdigest(),
         )
 
@@ -119,13 +123,32 @@ class ModelFactory:
             "http_client": DefaultHttpxClient(
                 timeout=endpoint.timeout_seconds, **model_http_options()
             ),
-            "http_async_client": DefaultAsyncHttpxClient(
+        }
+        if endpoint.transport == "websocket":
+            import httpx
+
+            from artemis.llm.websocket import ResponsesWebSocketTransport
+
+            # Disable HTTP proxy mounts on this facade: they would bypass the
+            # WebSocket transport. Each actual transport owns its proxy policy.
+            kwargs["http_async_client"] = httpx.AsyncClient(
+                timeout=endpoint.timeout_seconds,
+                trust_env=False,
+                transport=ResponsesWebSocketTransport(
+                    timeout=endpoint.timeout_seconds, use_proxy=settings.OPENAI_USE_SYSTEM_PROXY
+                ),
+                event_hooks={
+                    "request": [observe_request_headers],
+                    "response": [observe_response_headers],
+                },
+            )
+        else:
+            kwargs["http_async_client"] = DefaultAsyncHttpxClient(
                 timeout=endpoint.timeout_seconds,
                 **model_http_options(),
                 event_hooks={
                     "request": [observe_request_headers],
                     "response": [observe_response_headers],
                 },
-            ),
-        }
+            )
         return ChatOpenAI(**{k: v for k, v in kwargs.items() if v is not None})