use original json|txt files

Signed-off-by: Vladislav Nosivskoy <[email protected]>

.pre-commit-config.yaml

@@ -64,6 +64,7 @@ repos:
   - id: mixed-line-ending
   - id: requirements-txt-fixer
   - id: trailing-whitespace
+    exclude: lib/llm/tests/data/deepseek-v3.2/.*\.txt$
 
 # NOTE: removing from pre commit
 # will move to gitlab ci to run in proper

lib/llm/tests/data/deepseek-v3.2/test_input.json

@@ -10,7 +10,7 @@
                     "properties": {
                         "timezone": {
                             "type": "string",
-                            "description": "The timezone, e.g. America/New_York, UTC"
+                            "description": "The timezone, e.g. Asia/Shanghai, UTC"
                         }
                     },
                     "required": ["timezone"]
@@ -27,7 +27,7 @@
                     "properties": {
                         "location": {
                             "type": "string",
-                            "description": "The city name, e.g. New York, San Francisco"
+                            "description": "The city name, e.g. Beijing, Hangzhou"
                         },
                         "date": {
                             "type": "string",
@@ -46,17 +46,17 @@
         },
         {
             "role": "user",
-            "content": "What's the weather tomorrow in San Francisco and New York?"
+            "content": "明天杭州和北京的天气怎么样？"
         },
         {
             "role": "assistant",
-            "reasoning_content": "User is asking about tomorrow's weather. I need to first get the current date to calculate tomorrow's date.",
+            "reasoning_content": "用户询问明天的天气，我需要先获取当前日期来计算明天的日期📅",
             "tool_calls": [
                 {
                     "id": "call_xK9mN3pL2qR8vT5wY6hZ1aB4",
                     "type": "function",
                     "function": {
-                        "arguments": "{\"timezone\": \"America/New_York\"}",
+                        "arguments": "{\"timezone\": \"Asia/Shanghai\"}",
                         "name": "get_datetime"
                     }
                 }
@@ -65,25 +65,25 @@
         {
             "tool_call_id": "call_xK9mN3pL2qR8vT5wY6hZ1aB4",
             "role": "tool",
-            "content": "{\"current_date\": \"2024-01-15\", \"current_time\": \"14:30:00\", \"timezone\": \"America/New_York\"}"
+            "content": "{\"current_date\": \"2024-01-15\", \"current_time\": \"14:30:00\", \"timezone\": \"Asia/Shanghai\"}"
         },
         {
             "role": "assistant",
-            "reasoning_content": "Now I know today is 2024-01-15, so tomorrow is 2024-01-16. Let me query the weather for San Francisco and New York.",
+            "reasoning_content": "现在知道今天是2024-01-15，明天就是2024-01-16。接下来查询杭州和北京明天的天气🌤️",
             "tool_calls": [
                 {
                     "id": "call_bN7kR9mX3pQ2wL5vY8jZ4cD6",
                     "type": "function",
                     "function": {
-                        "arguments": "{\"location\": \"San Francisco\", \"date\": \"2024-01-16\"}",
+                        "arguments": "{\"location\": \"Hangzhou\", \"date\": \"2024-01-16\"}",
                         "name": "get_weather"
                     }
                 },
                 {
                     "id": "call_dP9mL7kX5rT4yN3wZ2hV8eF1",
                     "type": "function",
                     "function": {
-                        "arguments": "{\"location\": \"New York\", \"date\": \"2024-01-16\"}",
+                        "arguments": "{\"location\": \"Beijing\", \"date\": \"2024-01-16\"}",
                         "name": "get_weather"
                     }
                 }
@@ -92,39 +92,39 @@
         {
             "tool_call_id": "call_bN7kR9mX3pQ2wL5vY8jZ4cD6",
             "role": "tool",
-            "content": "{\"location\": \"San Francisco\", \"date\": \"2024-01-16\", \"temperature_high\": \"65\", \"temperature_low\": \"55\", \"weather\": \"partly cloudy\", \"humidity\": \"70%\"}"
+            "content": "{\"location\": \"Hangzhou\", \"date\": \"2024-01-16\", \"temperature_high\": \"12\", \"temperature_low\": \"5\", \"weather\": \"多云\", \"humidity\": \"65%\"}"
         },
         {
             "tool_call_id": "call_dP9mL7kX5rT4yN3wZ2hV8eF1",
             "role": "tool",
-            "content": "{\"location\": \"New York\", \"date\": \"2024-01-16\", \"temperature_high\": \"28\", \"temperature_low\": \"15\", \"weather\": \"sunny\", \"humidity\": \"35%\"}"
+            "content": "{\"location\": \"Beijing\", \"date\": \"2024-01-16\", \"temperature_high\": \"-2\", \"temperature_low\": \"-8\", \"weather\": \"晴\", \"humidity\": \"30%\"}"
         },
         {
             "role": "assistant",
-            "reasoning_content": "Retrieved weather data for both cities. Now I'll format a nice response for the user.",
-            "content": "Based on the forecast, here's tomorrow's weather (January 16, 2024):\n\n**San Francisco**:\n- Weather: Partly cloudy\n- High: 65°F\n- Low: 55°F\n- Humidity: 70%\n\n**New York**:\n- Weather: Sunny\n- High: 28°F\n- Low: 15°F\n- Humidity: 35%\n\nSan Francisco will be mild and partly cloudy, while New York will be cold but sunny. If you're in New York, dress warmly!"
+            "reasoning_content": "已获取两个城市明天的天气信息，现在整理给用户✨",
+            "content": "根据查询结果，明天（2024年1月16日）的天气情况如下：\n\n**杭州**：\n- 天气：多云\n- 最高温度：12°C\n- 最低温度：5°C\n- 湿度：65%\n\n**北京**：\n- 天气：晴\n- 最高温度：-2°C\n- 最低温度：-8°C\n- 湿度：30%\n\n杭州明天会比较温暖但有些多云，而北京会很冷但是晴天。建议在北京的朋友要注意保暖！"
         },
         {
             "role": "user",
-            "content": "Thanks! What about the day after tomorrow?"
+            "content": "谢谢！那后天呢？"
         },
         {
             "role": "assistant",
-            "reasoning_content": "User is now asking about the day after tomorrow, which is 2024-01-17. I can query directly since I already know today's date.",
+            "reasoning_content": "用户现在问后天的天气，后天是2024-01-17，我可以直接查询（因为已知今天日期）🗓️",
             "tool_calls": [
                 {
                     "id": "call_fR3nK8mV7pL4xT2yW9jB5gH3",
                     "type": "function",
                     "function": {
-                        "arguments": "{\"location\": \"San Francisco\", \"date\": \"2024-01-17\"}",
+                        "arguments": "{\"location\": \"Hangzhou\", \"date\": \"2024-01-17\"}",
                         "name": "get_weather"
                     }
                 },
                 {
                     "id": "call_hT5pN2kY9rV6zL3wX1mD7jK8",
                     "type": "function",
                     "function": {
-                        "arguments": "{\"location\": \"New York\", \"date\": \"2024-01-17\"}",
+                        "arguments": "{\"location\": \"Beijing\", \"date\": \"2024-01-17\"}",
                         "name": "get_weather"
                     }
                 }
@@ -133,18 +133,17 @@
         {
             "tool_call_id": "call_fR3nK8mV7pL4xT2yW9jB5gH3",
             "role": "tool",
-            "content": "{\"location\": \"San Francisco\", \"date\": \"2024-01-17\", \"temperature_high\": \"68\", \"temperature_low\": \"58\", \"weather\": \"light rain\", \"humidity\": \"85%\"}"
+            "content": "{\"location\": \"Hangzhou\", \"date\": \"2024-01-17\", \"temperature_high\": \"15\", \"temperature_low\": \"8\", \"weather\": \"小雨\", \"humidity\": \"80%\"}"
         },
         {
             "tool_call_id": "call_hT5pN2kY9rV6zL3wX1mD7jK8",
             "role": "tool",
-            "content": "{\"location\": \"New York\", \"date\": \"2024-01-17\", \"temperature_high\": \"32\", \"temperature_low\": \"22\", \"weather\": \"cloudy\", \"humidity\": \"50%\"}"
+            "content": "{\"location\": \"Beijing\", \"date\": \"2024-01-17\", \"temperature_high\": \"0\", \"temperature_low\": \"-6\", \"weather\": \"多云\", \"humidity\": \"45%\"}"
         },
         {
             "role": "assistant",
-            "reasoning_content": "Got the weather data for the day after tomorrow. Let me format this for the user.",
-            "content": "Here's the forecast for the day after tomorrow (January 17, 2024):\n\n**San Francisco**:\n- Weather: Light rain\n- High: 68°F\n- Low: 58°F\n- Humidity: 85%\n\n**New York**:\n- Weather: Cloudy\n- High: 32°F\n- Low: 22°F\n- Humidity: 50%\n\nSan Francisco will have light rain with temperatures rising slightly, so bring an umbrella. New York will be a bit warmer but still cold and cloudy, so continue to bundle up."
+            "reasoning_content": "获取到后天的天气数据，整理回复给用户📝",
+            "content": "后天（2024年1月17日）的天气情况：\n\n**杭州**：\n- 天气：小雨\n- 最高温度：15°C\n- 最低温度：8°C\n- 湿度：80%\n\n**北京**：\n- 天气：多云\n- 最高温度：0°C\n- 最低温度：-6°C\n- 湿度：45%\n\n杭州后天会有小雨，温度略有回升，记得带伞。北京会稍微暖和一点，但依然很冷，请继续做好保暖措施。"
         }
     ]
 }
-

lib/llm/tests/data/deepseek-v3.2/test_output.txt

@@ -30,83 +30,83 @@ If the thinking_mode is enabled, then after function results you should strongly
 
 Here are the functions available in JSONSchema format:
 <functions>
-{"name": "get_datetime", "description": "Get the current date and time", "parameters": {"type": "object", "properties": {"timezone": {"type": "string", "description": "The timezone, e.g. America/New_York, UTC"}}, "required": ["timezone"]}}
-{"name": "get_weather", "description": "Get the weather for a specific date and location", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city name, e.g. New York, San Francisco"}, "date": {"type": "string", "description": "The date in YYYY-MM-DD format"}}, "required": ["location", "date"]}}
+{"name": "get_datetime", "description": "Get the current date and time", "parameters": {"type": "object", "properties": {"timezone": {"type": "string", "description": "The timezone, e.g. Asia/Shanghai, UTC"}}, "required": ["timezone"]}}
+{"name": "get_weather", "description": "Get the weather for a specific date and location", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city name, e.g. Beijing, Hangzhou"}, "date": {"type": "string", "description": "The date in YYYY-MM-DD format"}}, "required": ["location", "date"]}}
 </functions>
-<｜User｜>What's the weather tomorrow in San Francisco and New York?<｜Assistant｜></think>
+<｜User｜>明天杭州和北京的天气怎么样？<｜Assistant｜></think>
 
 <｜DSML｜function_calls>
 <｜DSML｜invoke name="get_datetime">
-<｜DSML｜parameter name="timezone" string="true">America/New_York</｜DSML｜parameter>
+<｜DSML｜parameter name="timezone" string="true">Asia/Shanghai</｜DSML｜parameter>
 </｜DSML｜invoke>
 </｜DSML｜function_calls><｜end▁of▁sentence｜>
 
 <function_results>
-<result>{"current_date": "2024-01-15", "current_time": "14:30:00", "timezone": "America/New_York"}</result>
+<result>{"current_date": "2024-01-15", "current_time": "14:30:00", "timezone": "Asia/Shanghai"}</result>
 </function_results>
 
 </think>
 
 <｜DSML｜function_calls>
 <｜DSML｜invoke name="get_weather">
-<｜DSML｜parameter name="location" string="true">San Francisco</｜DSML｜parameter>
+<｜DSML｜parameter name="location" string="true">Hangzhou</｜DSML｜parameter>
 <｜DSML｜parameter name="date" string="true">2024-01-16</｜DSML｜parameter>
 </｜DSML｜invoke>
 <｜DSML｜invoke name="get_weather">
-<｜DSML｜parameter name="location" string="true">New York</｜DSML｜parameter>
+<｜DSML｜parameter name="location" string="true">Beijing</｜DSML｜parameter>
 <｜DSML｜parameter name="date" string="true">2024-01-16</｜DSML｜parameter>
 </｜DSML｜invoke>
 </｜DSML｜function_calls><｜end▁of▁sentence｜>
 
 <function_results>
-<result>{"location": "San Francisco", "date": "2024-01-16", "temperature_high": "65", "temperature_low": "55", "weather": "partly cloudy", "humidity": "70%"}</result>
-<result>{"location": "New York", "date": "2024-01-16", "temperature_high": "28", "temperature_low": "15", "weather": "sunny", "humidity": "35%"}</result>
+<result>{"location": "Hangzhou", "date": "2024-01-16", "temperature_high": "12", "temperature_low": "5", "weather": "多云", "humidity": "65%"}</result>
+<result>{"location": "Beijing", "date": "2024-01-16", "temperature_high": "-2", "temperature_low": "-8", "weather": "晴", "humidity": "30%"}</result>
 </function_results>
 
-</think>Based on the forecast, here's tomorrow's weather (January 16, 2024):
+</think>根据查询结果，明天（2024年1月16日）的天气情况如下：
 
-**San Francisco**:
-- Weather: Partly cloudy
-- High: 65°F
-- Low: 55°F
-- Humidity: 70%
+**杭州**：
+- 天气：多云
+- 最高温度：12°C
+- 最低温度：5°C
+- 湿度：65%
 
-**New York**:
-- Weather: Sunny
-- High: 28°F
-- Low: 15°F
-- Humidity: 35%
+**北京**：
+- 天气：晴
+- 最高温度：-2°C
+- 最低温度：-8°C
+- 湿度：30%
 
-San Francisco will be mild and partly cloudy, while New York will be cold but sunny. If you're in New York, dress warmly!<｜end▁of▁sentence｜><｜User｜>Thanks! What about the day after tomorrow?<｜Assistant｜><think>User is now asking about the day after tomorrow, which is 2024-01-17. I can query directly since I already know today's date.</think>
+杭州明天会比较温暖但有些多云，而北京会很冷但是晴天。建议在北京的朋友要注意保暖！<｜end▁of▁sentence｜><｜User｜>谢谢！那后天呢？<｜Assistant｜><think>用户现在问后天的天气，后天是2024-01-17，我可以直接查询（因为已知今天日期）🗓️</think>
 
 <｜DSML｜function_calls>
 <｜DSML｜invoke name="get_weather">
-<｜DSML｜parameter name="location" string="true">San Francisco</｜DSML｜parameter>
+<｜DSML｜parameter name="location" string="true">Hangzhou</｜DSML｜parameter>
 <｜DSML｜parameter name="date" string="true">2024-01-17</｜DSML｜parameter>
 </｜DSML｜invoke>
 <｜DSML｜invoke name="get_weather">
-<｜DSML｜parameter name="location" string="true">New York</｜DSML｜parameter>
+<｜DSML｜parameter name="location" string="true">Beijing</｜DSML｜parameter>
 <｜DSML｜parameter name="date" string="true">2024-01-17</｜DSML｜parameter>
 </｜DSML｜invoke>
 </｜DSML｜function_calls><｜end▁of▁sentence｜>
 
 <function_results>
-<result>{"location": "San Francisco", "date": "2024-01-17", "temperature_high": "68", "temperature_low": "58", "weather": "light rain", "humidity": "85%"}</result>
-<result>{"location": "New York", "date": "2024-01-17", "temperature_high": "32", "temperature_low": "22", "weather": "cloudy", "humidity": "50%"}</result>
+<result>{"location": "Hangzhou", "date": "2024-01-17", "temperature_high": "15", "temperature_low": "8", "weather": "小雨", "humidity": "80%"}</result>
+<result>{"location": "Beijing", "date": "2024-01-17", "temperature_high": "0", "temperature_low": "-6", "weather": "多云", "humidity": "45%"}</result>
 </function_results>
 
-<think>Got the weather data for the day after tomorrow. Let me format this for the user.</think>Here's the forecast for the day after tomorrow (January 17, 2024):
+<think>获取到后天的天气数据，整理回复给用户📝</think>后天（2024年1月17日）的天气情况：
 
-**San Francisco**:
-- Weather: Light rain
-- High: 68°F
-- Low: 58°F
-- Humidity: 85%
+**杭州**：
+- 天气：小雨
+- 最高温度：15°C
+- 最低温度：8°C
+- 湿度：80%
 
-**New York**:
-- Weather: Cloudy
-- High: 32°F
-- Low: 22°F
-- Humidity: 50%
+**北京**：
+- 天气：多云
+- 最高温度：0°C
+- 最低温度：-6°C
+- 湿度：45%
 
-San Francisco will have light rain with temperatures rising slightly, so bring an umbrella. New York will be a bit warmer but still cold and cloudy, so continue to bundle up.<｜end▁of▁sentence｜>
+杭州后天会有小雨，温度略有回升，记得带伞。北京会稍微暖和一点，但依然很冷，请继续做好保暖措施。<｜end▁of▁sentence｜>