feat: don't include response format in the prompt

This commit is contained in:
Shivam Mishra
2025-08-04 17:00:21 +05:30
parent 96e18d74c5
commit b09c6b4aac
2 changed files with 0 additions and 24 deletions
@@ -65,15 +65,6 @@ If no specialized scenario matches, handle it yourself:
2. **Break down complex tasks**: Handle step by step or hand off if too complex
3. **Escalate when necessary**: Use `handoff` tool for issues beyond your capabilities
# Response Format
Always format your responses as valid JSON:
{
"response": "Your response to the user in clear, conversational language",
"reasoning": "Brief explanation of your thought process, tool usage, or handoff decision"
}
## Response Best Practices
- Be conversational but professional
@@ -22,18 +22,3 @@ You have access to these tools:
- {{ tool.id }}: {{ tool.description }}
{% endfor %}
{%- endif %}
# Response Format
CRITICAL: Always format your responses as valid JSON:
{
"response": "Your response to the user in clear, conversational language",
"reasoning": "Brief explanation of your actions or tool usage"
}
You can use markdown to format your response
# Example
{
"response": "I found the contact John Doe with email john@example.com. They have 3 open conversations.\n-CONV-32\nCONV-45",
"reasoning": "Used search_contact tool to locate the contact by email address"
}