chore(runner): add runner options for save tracing

docs/docs/agent.md

@@ -93,7 +93,7 @@ from veadk.tools.demo_tools import get_city_weather
 session_id = "..."
 prompt = "..."
 
-# define three agents, one for planner, two for write poem and polish
+# 定义三个智能体，分别为天气预报智能体、穿衣建议智能体以及一个Planner智能体
 weather_reporter = Agent(
     name="weather_reporter",
     description="A weather reporter agent to report the weather.",

docs/docs/tracing.md

@@ -4,17 +4,28 @@ VeADK 提供可观测（Tracing）的能力，用于记录 Agent 执行过程中
 
 ## 本地观测
 
-通过如下方式开启本地观测，并且将运行时数据保存至本地：
+通过如下方式开启本地观测，并且在 `runner` 的运行函数中指定 `save_tracing_data=True` 来将运行时数据保存至本地：
 
 ```python
+import asyncio
+
+from veadk import Agent, Runner
+from veadk.memory.short_term_memory import ShortTermMemory
 from veadk.tracing.telemetry.opentelemetry_tracer import OpentelemetryTracer
 
 tracer = OpentelemetryTracer()
 agent = Agent(tracers=[tracer])
 
-# ... run agent ...
 
-# the data will be automatically saved to local
+session_id = "session_id"
+
+runner = Runner(agent=agent, short_term_memory=ShortTermMemory())
+
+prompt = "How is the weather like in Beijing? Besides, tell me which tool you invoked."
+
+# 设置 `save_tracing_data` 来保存运行时的 Tracing 数据
+asyncio.run(runner.run(messages=prompt, session_id=session_id, save_tracing_data=True))
+
 print(f"Tracing file path: {tracer._trace_file_path}")
 ```
 

veadk/runner.py

@@ -145,6 +145,7 @@ async def run(
         messages: RunnerMessage,
         session_id: str,
         stream: bool = False,
+        save_tracing_data: bool = False,
     ):
         converted_messages: list = self._convert_messages(messages)
 
@@ -159,7 +160,8 @@ async def run(
             final_output = await self._run(session_id, converted_message, stream)
 
         # try to save tracing file
-        self.save_tracing_file(session_id)
+        if save_tracing_data:
+            self.save_tracing_file(session_id)
 
         return final_output
 
@@ -173,6 +175,7 @@ def save_tracing_file(self, session_id: str) -> str:
             return ""
 
         if not self.agent.tracers:
+            logger.warning("No tracer is configured in the agent.")
             return ""
 
         try: