Merge branch 'main' into release/2.0-rc

backend/packages/harness/deerflow/models/factory.py

@@ -56,6 +56,7 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
             "supports_thinking",
             "supports_reasoning_effort",
             "when_thinking_enabled",
+            "when_thinking_disabled",
             "thinking",
             "supports_vision",
         },
@@ -72,21 +73,24 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
             raise ValueError(f"Model {name} does not support thinking. Set `supports_thinking` to true in the `config.yaml` to enable thinking.") from None
         if effective_wte:
             model_settings_from_config.update(effective_wte)
-    if not thinking_enabled and has_thinking_settings:
-        if effective_wte.get("extra_body", {}).get("thinking", {}).get("type"):
+    if not thinking_enabled:
+        if model_config.when_thinking_disabled is not None:
+            # User-provided disable settings take full precedence
+            model_settings_from_config.update(model_config.when_thinking_disabled)
+        elif has_thinking_settings and effective_wte.get("extra_body", {}).get("thinking", {}).get("type"):
             # OpenAI-compatible gateway: thinking is nested under extra_body
             model_settings_from_config["extra_body"] = _deep_merge_dicts(
                 model_settings_from_config.get("extra_body"),
                 {"thinking": {"type": "disabled"}},
             )
             model_settings_from_config["reasoning_effort"] = "minimal"
-        elif disable_chat_template_kwargs := _vllm_disable_chat_template_kwargs(effective_wte.get("extra_body", {}).get("chat_template_kwargs") or {}):
+        elif has_thinking_settings and (disable_chat_template_kwargs := _vllm_disable_chat_template_kwargs(effective_wte.get("extra_body", {}).get("chat_template_kwargs") or {})):
             # vLLM uses chat template kwargs to switch thinking on/off.
             model_settings_from_config["extra_body"] = _deep_merge_dicts(
                 model_settings_from_config.get("extra_body"),
                 {"chat_template_kwargs": disable_chat_template_kwargs},
             )
-        elif effective_wte.get("thinking", {}).get("type"):
+        elif has_thinking_settings and effective_wte.get("thinking", {}).get("type"):
             # Native langchain_anthropic: thinking is a direct constructor parameter
             model_settings_from_config["thinking"] = {"type": "disabled"}
     if not model_config.supports_reasoning_effort:

backend/packages/harness/deerflow/models/openai_codex_provider.py

@@ -48,6 +48,10 @@ class CodexChatModel(BaseChatModel):
 
     model_config = {"arbitrary_types_allowed": True}
 
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        return True
+
     @property
     def _llm_type(self) -> str:
         return "codex-responses"
@@ -216,18 +220,48 @@ class CodexChatModel(BaseChatModel):
     def _stream_response(self, headers: dict, payload: dict) -> dict:
         """Stream SSE from Codex API and collect the final response."""
         completed_response = None
+        streamed_output_items: dict[int, dict[str, Any]] = {}
 
         with httpx.Client(timeout=300) as client:
             with client.stream("POST", f"{CODEX_BASE_URL}/responses", headers=headers, json=payload) as resp:
                 resp.raise_for_status()
                 for line in resp.iter_lines():
                     data = self._parse_sse_data_line(line)
-                    if data and data.get("type") == "response.completed":
+                    if not data:
+                        continue
+
+                    event_type = data.get("type")
+                    if event_type == "response.output_item.done":
+                        output_index = data.get("output_index")
+                        output_item = data.get("item")
+                        if isinstance(output_index, int) and isinstance(output_item, dict):
+                            streamed_output_items[output_index] = output_item
+                    elif event_type == "response.completed":
                         completed_response = data["response"]
 
         if not completed_response:
             raise RuntimeError("Codex API stream ended without response.completed event")
 
+        # ChatGPT Codex can emit the final assistant content only in stream events.
+        # When response.completed arrives, response.output may still be empty.
+        if streamed_output_items:
+            merged_output = []
+            response_output = completed_response.get("output")
+            if isinstance(response_output, list):
+                merged_output = list(response_output)
+
+            max_index = max(max(streamed_output_items), len(merged_output) - 1)
+            if max_index >= 0 and len(merged_output) <= max_index:
+                merged_output.extend([None] * (max_index + 1 - len(merged_output)))
+
+            for output_index, output_item in streamed_output_items.items():
+                existing_item = merged_output[output_index]
+                if not isinstance(existing_item, dict):
+                    merged_output[output_index] = output_item
+
+            completed_response = dict(completed_response)
+            completed_response["output"] = [item for item in merged_output if isinstance(item, dict)]
+
         return completed_response
 
     @staticmethod

backend/packages/harness/deerflow/models/patched_deepseek.py

@@ -23,6 +23,14 @@ class PatchedChatDeepSeek(ChatDeepSeek):
     request payload.
     """
 
+    @classmethod
+    def is_lc_serializable(cls) -> bool:
+        return True
+
+    @property
+    def lc_secrets(self) -> dict[str, str]:
+        return {"api_key": "DEEPSEEK_API_KEY", "openai_api_key": "DEEPSEEK_API_KEY"}
+
     def _get_request_payload(
         self,
         input_: LanguageModelInput,