fix:chatcmpl.py del content <think>,in the ppiochatcmpl.py and modelsopechatcmpl.py fun _closure_stream stream logic

pkg/provider/modelmgr/requesters/ppiochatcmpl.py

@@ -112,24 +112,32 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
                         del me['image_base64']
 
         args['messages'] = messages
-
-        current_content = ''
         args['stream'] = True
-        chunk_idx = 0
-        is_think = False
+
         tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        accumulated_reasoning = ''  # 仅用于判断何时结束思维链
         async for chunk in self._req_stream(args, extra_body=extra_args):
-            # 处理流式消息
-            if hasattr(chunk, 'choices'):
-                # 完整响应模式
-                if chunk.choices:
-                    choice = chunk.choices[0]
-                    delta = choice.delta.model_dump() if hasattr(choice, 'delta') else choice.message.model_dump()
-                else:
-                    continue
+            # 解析 chunk 数据
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+                finish_reason = getattr(choice, 'finish_reason', None)
             else:
-                # 流式chunk模式
-                delta = chunk.delta.model_dump() if hasattr(chunk, 'delta') else {}
+                delta = {}
+                finish_reason = None
+
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            # reasoning_content = delta.get('reasoning_content', '')
+
             if remove_think:
                 if delta['content'] is not None:
                     if '<think>' in delta['content']:
@@ -141,30 +149,46 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
                     elif is_think or delta['content'] == '\n\n':
                         continue
 
-            delta_message = await self._make_msg_chunk(delta, chunk_idx)
-            # 处理流式消息
-            if delta_message.content:
-                current_content += delta_message.content
-                delta_message.content = current_content
-                # delta_message.all_content = current_content
-            if delta_message.tool_calls:
-                for tool_call in delta_message.tool_calls:
-                    if tool_call.id not in tool_calls_map:
-                        tool_calls_map[tool_call.id] = llm_entities.ToolCall(
-                            id=tool_call.id,
-                            type=tool_call.type,
-                            function=llm_entities.FunctionCall(
-                                name=tool_call.function.name if tool_call.function else '', arguments=''
-                            ),
-                        )
-                    if tool_call.function and tool_call.function.arguments:
-                        # 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
-                        tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
+            delta_tool_calls = None
+            if delta.get('tool_calls'):
+                delta_tool_calls = []
+                for tool_call in delta['tool_calls']:
+                    tc_id = tool_call.get('id')
+                    if tc_id:
+                        if tc_id not in tool_calls_map:
+                            # 新的工具调用
+                            tool_calls_map[tc_id] = llm_entities.ToolCall(
+                                id=tc_id,
+                                type=tool_call.get('type', 'function'),
+                                function=llm_entities.FunctionCall(
+                                    name=tool_call.get('function', {}).get('name', ''),
+                                    arguments=tool_call.get('function', {}).get('arguments', ''),
+                                ),
+                            )
+                            delta_tool_calls.append(tool_calls_map[tc_id])
+                        else:
+                            # 追加函数参数
+                            func_args = tool_call.get('function', {}).get('arguments', '')
+                            if func_args:
+                                tool_calls_map[tc_id].function.arguments += func_args
+                                # 返回更新后的完整工具调用
+                                delta_tool_calls.append(tool_calls_map[tc_id])
 
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content  and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+
+                # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta_tool_calls if delta_tool_calls else None,
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
             chunk_idx += 1
-            chunk_choices = getattr(chunk, 'choices', None)
-            if chunk_choices and getattr(chunk_choices[0], 'finish_reason', None):
-                delta_message.is_final = True
-                delta_message.content = current_content
-
-            yield delta_message