Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

promote Dev #105

Merged
merged 29 commits into from
Sep 19, 2024
Merged

promote Dev #105

merged 29 commits into from
Sep 19, 2024

Conversation

teaxio
Copy link
Collaborator

@teaxio teaxio commented Sep 19, 2024

  • Added capability to load skills from external directories.
  • Fixed a bug related to skill loading warnings.
  • Implemented end loop detection for smaller models.
  • Added configuration to make LLM settings available via API routes.
  • Introduced max chat rounds for planners and browser navigation agents.
  • Fixed bugs in planner chatter saving and test processor configuration.
  • Updated README with instructions for new environment variables and Windows-specific server commands.
  • Introduced more verbose logging for OpenAI and autogen.

teaxio and others added 29 commits August 26, 2024 17:46
Useful for smaller models
Windows-specific commands for running server locally
Sometimes LLMs can make mistake and ask for open_url when already in the page.
This can sometimes lead to reseting the page state (e.g. if certain text was already entered in the text fields, they get lost).
This change prevents this from happening
Make LLM config available in API route
API can set max chat rounds per agent
@teaxio teaxio requested a review from deepak-akkil September 19, 2024 14:27
@teaxio teaxio merged commit 06719a4 into master Sep 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants