feature: 增加 OpenAI 兼容模型适配器

- 新增 openai_adapter 目录，按模型拆分 DeepSeek 与 Hunyuan
  的特殊适配逻辑
- 保持 OpenAIModel 主流程兼容，避免将特定模型逻辑继续堆叠在主实现中
- 适配 DeepSeek v4 的 thinking、response_format、reasoning_content 与
  token usage 处理
- 为 hy3-preview 增加 ToolPrompt 文本工具调用解析与流式输出过滤
- 修复 ToolPrompt 流式解析多个工具调用时只保留最后一个的问题
- 优化 thinking 示例，仅在 hy3-preview 下启用
  add_tools_to_prompt，并区分展示思考、工具调用和最终回复
- 更新示例 prompt，避免模型在工具返回前编造结果或过度展开推理

Author: raychen911

examples/llmagent_with_thinking/agent/agent.py

@@ -11,7 +11,7 @@
 from trpc_agent_sdk.tools import FunctionTool
 from trpc_agent_sdk.types import GenerateContentConfig
 from trpc_agent_sdk.types import ThinkingConfig
-
+from trpc_agent_sdk.types import HttpOptions
 from .config import get_model_config
 from .prompts import INSTRUCTION
 from .tools import get_weather_forecast
@@ -32,8 +32,9 @@ def _create_model() -> LLMModel:
         #    if the LLM model service fails to return the JSON format of tool calls, you can also enable ToolPrompt.
         #    This will prompt the LLM model to output the special text for tool calling in the main content,
         #    thereby increasing the probability of successful tool invocation.
-        # You can uncomment the code below to use ToolPrompt.
-        # add_tools_to_prompt=True,
+        # Thinking models may emit tool calls as text. ToolPrompt lets the
+        # framework parse those text calls back into executable FunctionCalls.
+        add_tools_to_prompt=model_name.lower() == "hy3-preview",  # Enable ToolPrompt for Hy3-preview model
     )
     return model
 
@@ -45,6 +46,9 @@ def create_agent():
     weather_tool = FunctionTool(get_weather_report)
     forecast_tool = FunctionTool(get_weather_forecast)
 
+    # Set reasoning effort to high for Hy3-preview model
+    http_options=HttpOptions(extra_body={"chat_template_kwargs": {"reasoning_effort": "high"}})
+
     return LlmAgent(
         name="weather_agent",
         description=
@@ -54,7 +58,7 @@ def create_agent():
         instruction=INSTRUCTION,
         tools=[weather_tool, forecast_tool],
         # Note: thinking_budget must be less than max_output_tokens
-        generate_content_config=GenerateContentConfig(max_output_tokens=10240, ),
+        generate_content_config=GenerateContentConfig(max_output_tokens=10240, http_options=http_options),
         # The model must be a thinking model to use this Planner; this configuration will not take effect for non-thinking models.
         planner=BuiltInPlanner(thinking_config=ThinkingConfig(
             include_thoughts=True,

examples/llmagent_with_thinking/agent/prompts.py

@@ -18,13 +18,21 @@
 - Provide clear, useful weather information and suggestions
 
 **Available tools:**
-1. `get_weather`: Get current weather information
+1. `get_weather_report`: Get current weather information
 2. `get_weather_forecast`: Get multi-day weather forecast
 
 **Tool usage guide:**
-- When the user asks about the current weather, use `get_weather`
+- When the user asks about the current weather, use `get_weather_report`
 - When the user asks about the weather for the next few days, use `get_weather_forecast`
 - If the query is not clear, you can use both tools at the same time
+- Do not answer with weather data before the required tool result is available
+- Do not guess, simulate, or invent tool results
+- If a tool is needed, call the tool first and wait for the tool result before giving the final answer
+
+**Thinking guidance:**
+- Keep reasoning concise and focused on choosing the right tool and city
+- Do not repeat the tool usage rules or tool schema in your reasoning
+- Do not draft the final answer in reasoning; use reasoning only to decide the next action
 
 **Reply format:**
 - Provide accurate weather information

examples/llmagent_with_thinking/run_agent.py

@@ -30,7 +30,7 @@ async def run_weather_agent():
     demo_queries = [
         "What's the weather like today?",
         "What's the current weather in Guangzhou?",
-        "What will the weather be like in Shanghai for the next three days?",
+        "Please check both the current weather in Guangzhou and the three-day weather forecast for Shanghai.",
     ]
 
     for query in demo_queries:
@@ -51,23 +51,78 @@ async def run_weather_agent():
 
         user_content = Content(parts=[Part.from_text(text=query)])
 
-        print("🤖 Assistant: ", end="", flush=True)
+        printed_thinking = False
+        printed_assistant = False
+        in_thinking = False
+        thinking_line_start = False
+        assistant_text_started = False
+
+        def print_assistant_header() -> None:
+            nonlocal printed_assistant
+            if printed_assistant:
+                return
+            if printed_thinking:
+                print("\n")
+            print("🤖 Assistant: ", end="", flush=True)
+            printed_assistant = True
+
+        def print_thinking_header() -> None:
+            nonlocal in_thinking, printed_thinking, thinking_line_start
+            if in_thinking:
+                return
+            print("\n  💭 Thinking: ", end="", flush=True)
+            in_thinking = True
+            printed_thinking = True
+            thinking_line_start = False
+
+        def print_thinking_text(text: str) -> None:
+            nonlocal thinking_line_start
+            for line in text.splitlines(keepends=True):
+                if thinking_line_start:
+                    print("  ", end="", flush=True)
+                print(line, end="", flush=True)
+                thinking_line_start = line.endswith("\n")
+
+        def close_thinking_section() -> None:
+            nonlocal in_thinking, thinking_line_start
+            if in_thinking:
+                if not thinking_line_start:
+                    print()
+                print("  💭 End Thinking")
+                in_thinking = False
+                thinking_line_start = False
+
         async for event in runner.run_async(user_id=user_id, session_id=current_session_id, new_message=user_content):
             if not event.content or not event.content.parts:
                 continue
 
             if event.partial:
                 for part in event.content.parts:
                     if part.text:
-                        print(part.text, end="", flush=True)
+                        if part.thought:
+                            if assistant_text_started:
+                                continue
+                            print_thinking_header()
+                            print_thinking_text(part.text)
+                        else:
+                            close_thinking_section()
+                            print_assistant_header()
+                            assistant_text_started = True
+                            print(part.text, end="", flush=True)
                 continue
 
             for part in event.content.parts:
-                if part.thought:
-                    continue
-                if part.function_call:
+                if part.thought and part.text and not printed_thinking and not assistant_text_started:
+                    print_thinking_header()
+                    print_thinking_text(part.text)
+                elif part.function_call:
+                    close_thinking_section()
+                    print_assistant_header()
                     print(f"\n🔧 [Invoke Tool:: {part.function_call.name}({part.function_call.args})]")
                 elif part.function_response:
+                    close_thinking_section()
+                    printed_thinking = False
+                    print_assistant_header()
                     print(f"📊 [Tool Result: {part.function_response.response}]")
                 # elif part.text:
                 #     print(f"\n✅ {part.text}")