genesis facing token limit for usage tier 1 openai accounts - suggesting having configurable model setting

[ofir-barkay]

for newly created openai accounts, the usage tier for gpt-4o is 30K TPM, which Genesis usually exceeds during new agencies creation process.
my hot fix was to switch to gpt-4o-mini by editing the model parameter in the framework's agent.py file.
I think it would be a nice addition to have the model as a configurable agency parameter (for both Genesis and all other agencies)
(+changing to mini could help one reduce testing and experimenting costs..)

[github-actions]

This issue is stale because it has been open for 30 days with no activity. Please upgrade to the latest version and test it again.

[Cass0wary]

+1 would be nice if agent-swarm could catch the Rate limit reached error and pause for x number of seconds before trying again instead of terminating.

Traceback (most recent call last):
  File "/Users/username/Documents/AIAgents/venv/bin/agency-swarm", line 8, in <module>
    sys.exit(main())
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/cli.py", line 51, in main
    agency.run_demo()
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/agency/agency.py", line 797, in run_demo
    self.get_completion_stream(message=text, event_handler=TermEventHandler, recipient_agent=recipient_agent)
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/agency/agency.py", line 236, in get_completion_stream
    next(res)
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/threads/thread.py", line 184, in get_completion
    yield from handle_output(tool_call, output)
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/threads/thread.py", line 148, in handle_output
    item = next(output)
  File "/Users/username/Documents/AIAgents/venv/lib/python3.10/site-packages/agency_swarm/threads/thread.py", line 253, in get_completion
    raise Exception("OpenAI Run Failed. Error: ", self.run.last_error.message)
Exception: ('OpenAI Run Failed. Error: ', 'Rate limit reached for gpt-4o-mini in organization org-xxxxxx on requests per min (RPM): Limit 3, Used 3, Requested 1. Please try again in 20s. Visit https://platform.openai.com/account/rate-limits to learn more. You can increase your rate limit by adding a payment method to your account at https://platform.openai.com/account/billing.')

[phact]

Addressed by #173

[github-actions]

This issue is stale because it has been open for 30 days with no activity. Please upgrade to the latest version and test it again.

[desperad0s]

This is still an issue. Very discouraging for new users, after spending many hours refining my prompt and having a conversation with Genesis, and it then bouncing and failing due to rate-limit and never being able to pickup again and every time retrying, running into the same issues again.

I will try the hot fix, otherwise I might jsut try the from scratch with my prompt.

[github-actions]

This issue is stale because it has been open for 30 days with no activity. Please upgrade to the latest version and test it again.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale. If the issue still persists, please reopen.