feat(rnd): AutoGPT Agent wrapper for Agent Server

[kcze]

Changes 🏗️

Add AutoGPT Agent wrapper block for the Agent Server that allows running a temporary agent with full AutoGPT capabilities. You can limit components and commands it has access to, specify task and input data.

• Add autogpt and forge dependency to the autogpt_server
• Add AutoGPTAgentBlock that initializes and runs a single agent loop on execution
• Add BlockAgent that inherits from autogpt Agent and is a thin extension on the agent that allows to disable components
• Add OutputComponent that adds output command for the agent
• Add test with a custom graph AutoGPTAgentBlock --- PrintingBlock

PR Quality Scorecard ✨

• [x] Have you used the PR description template?   +2 pts
• [x] Is your pull request atomic, focusing on a single change?   +5 pts
• [ ] Have you linked the GitHub issue(s) that this PR addresses?   +5 pts
• [ ] Have you documented your changes clearly and comprehensively?   +5 pts
• [ ] Have you changed or added a feature?   -4 pts
  • [ ] Have you added/updated corresponding documentation?   +4 pts
  • [ ] Have you added/updated corresponding integration tests?   +5 pts
• [ ] Have you changed the behavior of AutoGPT?   -5 pts
  • [ ] Have you also run agbenchmark to verify that these changes do not regress performance?   +10 pts

[netlify[bot]]

✅ Deploy Preview for auto-gpt-docs ready!

Name	Link
🔨 Latest commit	f1eff550d05ef486c91afa3ef6474751dc05a72a
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/66926407e5de690009b7f4fd
😎 Deploy Preview	https://deploy-preview-7365--auto-gpt-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 0% with 1 line in your changes missing coverage. Please review.

Project coverage is 54.20%. Comparing base (bffb92b) to head (f1eff55). Report is 3 commits behind head on master.

Files	Patch %	Lines
autogpt/autogpt/agents/agent.py	0.00%	1 Missing :warning:

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #7365      +/-   ##
==========================================
- Coverage   54.21%   54.20%   -0.01%     
==========================================
  Files         122      122              
  Lines        6875     6876       +1     
  Branches      881      881              
==========================================
  Hits         3727     3727              
- Misses       3015     3016       +1     
  Partials      133      133              

Flag	Coverage Δ
Linux	53.95% <0.00%> (-0.01%)	:arrow_down:
Windows	54.53% <ø> (+3.79%)	:arrow_up:
autogpt-agent	33.99% <0.00%> (-0.03%)	:arrow_down:
forge	58.63% <ø> (ø)
macOS	53.25% <0.00%> (-0.01%)	:arrow_down:

Flags with carried forward coverage won't be shown. Click here to find out more.

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[ntindle]

Failure "fixed" by https://github.com/actions/toolkit/pull/1723 and caused by https://github.com/actions/upload-artifact/issues/485

[Torantulino]

If we have a choice @kcze then I much prefer better results slower (better LLM) than worse results quickly (fast LLM) by default.

[kcze]

If we have a choice @kcze then I much prefer better results slower (better LLM) than worse results quickly (fast LLM) by default.

There's a switch on the block now :) I just made it fast for the test, it's smart by default for the block.