<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": "GetReminders", "description": "Get a list of reminders.", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": null},
    {"name": "GetTodos", "description": "Get todos.", "parameters": {"type": "object", "properties": {"filter": {"type": "string"}}, "required": []}, "responses": null}
]
```<|END_TEXT|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|><|START_TEXT|>Look up reminders and todos.<|END_TEXT|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I'll call both tools in parallel.<|END_THINKING|><cofl:tool_calls><cofl:tool_call id="0" name="GetReminders"></cofl:tool_call><cofl:tool_call id="1" name="GetTodos"><cofl:tool_param name="filter" string="true">open</cofl:tool_param></cofl:tool_call></cofl:tool_calls><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><cofl:tool_results><cofl:tool_result id="0" is_error="false"><cofl:tool_result_item index="0">{"reminder": "A"}</cofl:tool_result_item></cofl:tool_result><cofl:tool_result id="1" is_error="false"><cofl:tool_result_item index="0">{"todo": "B"}</cofl:tool_result_item></cofl:tool_result></cofl:tool_results><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>