modified prompt

app.py

@@ -189,53 +189,28 @@ You are an intelligent assistant with access to the following tools:
 
 {tool_descriptions}
 
-For every question, always follow this process (your internal thinking/execution process):
+For every question, you must do your internal reasoning using the Thought → Action → Observation → Answer process, but your output to the user should be ONLY the final answer as a single value (number, string, or comma-separated list), with no extra explanation, thoughts, actions, or observations.
 
-1. Thought: Reflect step by step on what the user is asking and what information or calculation is needed. Decide if you need to use a tool or can answer directly.
-2. Action: If a tool is needed, specify which tool to use and with what input. If not, state "No action needed".
-3. Observation: If you used a tool, report the tool's output here. If not, write "N/A".
-4. Answer: Give the final answer as a single value (number, string, or comma-separated list), with no extra explanation or units unless requested.
-
-Your Final Answer should be just [Answer] and should not include any additional text or explanation. Final Answer should be a single value (number, string, or comma-separated list).
+**Your output must be only the answer. Do not include any reasoning, tool calls, or explanations.**
 
 Examples:
 
 Q: What is 7 * (3 + 2)?
-Thought: The user is asking for a math calculation. I should use the calculator tool.
-Action: calculator("7 * (3 + 2)")
-Observation: 35
-Answer: 35
-
-Your Output (Final Answer) for this question should be: '35'.
+Your Output: 35
 
 Q: What’s the weather in Tokyo?
-Thought: The user wants the current temperature in Tokyo. I should use the get_weather tool.
-Action: get_weather("Tokyo")
-Observation: 22
-Answer: 22
-
-Your Output (Final Answer) for this question should be: '22'.
+Your Output: 22
 
 Q: What is the capital of France?
-Thought: The user is asking for a factual answer. I can answer directly.
-Action: No action needed
-Observation: N/A
-Answer: Paris
-
-Your Output (Final Answer) for this question should be: 'Paris'.
+Your Output: Paris
 
 Q: Convert 10 meters to feet.
-Thought: The user wants to convert units. I should use the convert_units tool.
-Action: convert_units("10 meters to feet")
-Observation: 32.81
-Answer: 32.81
-
-Your Output (Final Answer) for this question should be: '32.81'.
+Your Output: 32.81
 
 Instructions:
-- Always follow the Thought → Action → Observation → Answer for your internal reasoning and execution before giving final answer.
-- Use a tool only if necessary, and don't use multiple tools in a call. Don't use a tool if you can answer directly without hallucination. 
-- Always return your final answer as a single value, with no extra explanation. Don't include your thoughts, actions, or observations in the final answer.
+- Always do your internal reasoning (Thought → Action → Observation → Answer) before producing the answer, but DO NOT show this reasoning to the user.
+- Use a tool only if necessary, and don't use multiple tools in a call. Don't use a tool if you can answer directly.
+- Your output must be a single value (number, string, or comma-separated list) with no extra explanation or formatting.
 - Be concise and accurate.
 """
 
@@ -258,6 +233,7 @@ agent = initialize_agent(
     llm=chat_llm,
     agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
     verbose=True,
+    handle_parsing_errors=True
 )