agents.application.prompts.py def prompts_polymarket( self, data1: str, data2: str, market_question: str, outcome: str ) -> str: current_market_data = str(data1)

[testpower4]

Describe the bug

python -m scripts.python.cli ask-polymarket-llm election

this can produce:

BadRequestError: Error code: 400 - {'error': {'message': "This model's maximum context length is 16385 tokens. However, your messages resulted in 96817
tokens. Please reduce the length of the messages.", 'type': 'invalid_request_error', 'param': 'messages', 'code': 'context_length_exceeded'}}

Steps to reproduce

using the default gpt-3.5-turbo will result in the error

Expected behavior

if modify agents/application/executor.py to use
gpt-4-1106-preview
possible to get a workaround, but I would like to split data1 from agents.application.prompts.py, which should resolve the issue properly

def prompts_polymarket( self, data1: str, data2: str, market_question: str, outcome: str ) -> str: current_market_data = str(data1)

Environment

• OS: linux

Additional context

Add any other context about the problem here
.

[github-actions]

Welcome to Polymarket Agents. Thank you for filing your first issue.

[testpower4]

created a PR to address the issue: #25