Skip to content

Agent Zero AI framework

fix: response tool examples were wrong for researcher and developer agents (#607)

ehl0wr0ld38f390a13c0d
diff --git a/prompts/developer/agent.system.main.communication.md b/prompts/developer/agent.system.main.communication.md
index 694aa5cf2..6c53f73dc 100644
--- a/prompts/developer/agent.system.main.communication.md
+++ b/prompts/developer/agent.system.main.communication.md
@@ -75,7 +75,7 @@ Exactly one JSON object per response cycle.
"headline": "Asking for additional information",
"tool_name": "response",
"tool_args": {
- "message": "I'll architect and implement a distributed task queue system. To ensure I deliver exactly what you need, please clarify:\n\n1. **Scale Requirements**: Expected tasks/second, peak loads, growth projections?\n2. **Message Guarantees**: At-most-once, at-least-once, or exactly-once delivery?\n3. **Technology Stack**: Preferred languages, existing infrastructure, cloud/on-premise?\n4. **Persistence Needs**: Task durability requirements, retention policies?\n5. **Integration Points**: Existing systems to connect, API requirements?\n6. **Performance Targets**: Latency budgets, throughput requirements?\n\nAny specific aspects like priority queues, scheduled tasks, or monitoring requirements to emphasize?"
+ "text": "I'll architect and implement a distributed task queue system. To ensure I deliver exactly what you need, please clarify:\n\n1. **Scale Requirements**: Expected tasks/second, peak loads, growth projections?\n2. **Message Guarantees**: At-most-once, at-least-once, or exactly-once delivery?\n3. **Technology Stack**: Preferred languages, existing infrastructure, cloud/on-premise?\n4. **Persistence Needs**: Task durability requirements, retention policies?\n5. **Integration Points**: Existing systems to connect, API requirements?\n6. **Performance Targets**: Latency budgets, throughput requirements?\n\nAny specific aspects like priority queues, scheduled tasks, or monitoring requirements to emphasize?"
}
}
~~~
diff --git a/prompts/researcher/agent.system.main.communication.md b/prompts/researcher/agent.system.main.communication.md
index d6df445a2..13761ee5b 100644
--- a/prompts/researcher/agent.system.main.communication.md
+++ b/prompts/researcher/agent.system.main.communication.md
@@ -87,7 +87,7 @@ Avoid ** markdown emphasis syntax to prevent rendering conflicts with JSON strin
"headline": "Asking for additional information",
"tool_name": "response",
"tool_args": {
- "message": "I'll conduct a comprehensive competitive analysis of the enterprise CRM market. To ensure I deliver exactly what you need, please clarify:\n\n1. **Geographic Scope**: Global analysis or specific regions/countries?\n2. **Company Size**: Fortune 500, mid-market, or all enterprise segments?\n3. **Competitor Focus**: Specific vendors (Salesforce, Microsoft, Oracle) or comprehensive landscape?\n4. **Time Horizon**: Current state only or include 3-5 year projections?\n5. **Analysis Depth**: Executive summary or detailed technical/feature comparison?\n6. **Output Format**: Presentation deck, written report, or comparison matrices?\n\nAny specific aspects like pricing analysis, integration capabilities, or industry-specific solutions to emphasize?"
+ "text": "I'll conduct a comprehensive competitive analysis of the enterprise CRM market. To ensure I deliver exactly what you need, please clarify:\n\n1. **Geographic Scope**: Global analysis or specific regions/countries?\n2. **Company Size**: Fortune 500, mid-market, or all enterprise segments?\n3. **Competitor Focus**: Specific vendors (Salesforce, Microsoft, Oracle) or comprehensive landscape?\n4. **Time Horizon**: Current state only or include 3-5 year projections?\n5. **Analysis Depth**: Executive summary or detailed technical/feature comparison?\n6. **Output Format**: Presentation deck, written report, or comparison matrices?\n\nAny specific aspects like pricing analysis, integration capabilities, or industry-specific solutions to emphasize?"
}
}
~~~
diff --git a/python/tools/response.py b/python/tools/response.py
index 73d9d42d3..629b56815 100644
--- a/python/tools/response.py
+++ b/python/tools/response.py
@@ -4,7 +4,7 @@ from python.helpers.tool import Tool, Response
class ResponseTool(Tool):
async def execute(self, **kwargs):
- return Response(message=self.args["text"], break_loop=True)
+ return Response(message=self.args["message"] if "message" in self.args else self.args["text"], break_loop=True)
async def before_execution(self, **kwargs):
# self.log = self.agent.context.log.log(type="response", heading=f"{self.agent.agent_name}: Responding", content=self.args.get("text", ""))