<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TEXT|>Note that both your responses and reflections can be grounded. Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".

# Available Tools
```json
[
    {"name": "get_weather", "description": "gets the weather of a given location", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "the location to get the weather, example: San Francisco."}}, "required": ["location"]}, "responses": null},
    {"name": "get_capital_city", "description": "gets the capital city of a given country", "parameters": {"type": "object", "properties": {"country": {"type": "string", "description": "the country to get the capital city for"}}, "required": ["country"]}, "responses": null}
]
```<|END_TEXT|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TEXT|>This is a developer instruction<|END_TEXT|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|><|START_TEXT|>How are you?<|END_TEXT|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>