Commands Being Sent To Prompt Include Full List Not Only Enabled

[Electrofried]

Description

When sending prompts through to the provider (tested with Ooga, none others) the full list of commands is being sent through, not just those that are enabled.

Steps to Reproduce the Bug

Start task with a subset of commands enabled.
Check prompt being sent to API.
See all commands on the list, not just the enabled ones.

Expected Behavior

Only Enabled commands should be added to the prompt.

Actual Behavior

All commands are added even disabled ones.

Additional Context / Screenshots

No response

Operating System

• Microsoft Windows
• Apple MacOS
• Linux
• Android
• iOS
• Other

Python Version

• Python <= 3.9
• Python 3.10
• Python 3.11

Environment Type - Connection

• Local
• Remote

Environment Type - Container

• Using Docker
• Not Using Docker

Acknowledgements

• My issue title is concise, descriptive, and in title casing.
• I have searched the existing issues to make sure this bug has not been reported yet.
• I am using the latest version of Agent-LLM.
• I have provided enough information for the maintainers to reproduce and diagnose the issue.

[Josh-XT]

Fixed in #207 for instruct at least, still an issue?

[Josh-XT]

Found was still broken in execution agent and fixed there too in #220