Document changes for Micro-Agents and some formatting changes

[mamoodi]

End-user friendly description of the problem this fixes or functionality that this introduces

• Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below

• Adding an Overview for Micro-Agents
• Removed persist data since that's the default now
• Removed table of contents for configuration options and used headers for auto table on the right side
• Formatting changes

---

Give a summary of what the PR does, explaining any non-trivial design decisions

---

Link of any specific issues this addresses

---

To run this PR locally, use the following command:

docker run -it --rm   -p 3000:3000   -v /var/run/docker.sock:/var/run/docker.sock   --add-host host.docker.internal:host-gateway   -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:5d898d5-nikolaik   --name openhands-app-5d898d5   docker.all-hands.dev/all-hands-ai/openhands:5d898d5

[mamoodi]

@rbren I tried to follow your comment from the other PR and wrote this in the overview. Not sure what else to add. In its current state is it providing any value?

[mamoodi]

I'm leaning towards removing this right now unless you have ideas on how to add more value here.

[rbren]

Yeah there is a bunch of stuff we can put here about the YAML header options. Especially the way triggers work right now

I've also been trying to standardize on Microagent as the way this is stylized

[mamoodi]

I need to get back to this PR later. I think this Micro-Agents section needs a lot of love :D

[mamoodi]

Rejigged it.

[enyst]

Just a small detail: we talk about Repository Agents in two sections, first documenting them, then the contributing section. Then at the end of contributing, we say repo microagents should stay in their own repo 😅.

Suggestions:

• remove them from Contributing completely
• slightly reorder them to be first, in the other section. It's extremely reasonable to guess it's the first thing that people want to adapt.

[mamoodi]

Just a small detail: we talk about Repository Agents in two sections, first documenting them, then the contributing section. Then at the end of contributing, we say repo microagents should stay in their own repo 😅.

Suggestions:

• remove them from Contributing completely
• slightly reorder them to be first, in the other section. It's extremely reasonable to guess it's the first thing that people want to adapt.

I'll reorder the Repository to be first.

Can you elaborate on the first bit. Where does it mention the Repository Agents in the contributing section? Can you point me to it please so I can remove it.

[enyst]

Oh, I didn't hallucinate it 😅, it was in their readme, sorry
https://github.com/All-Hands-AI/OpenHands/tree/main/microagents

[mamoodi]

I tried to keep the format consistent between both Micro-Agents:

• Overview
• Creating the Micro-Agent
  • Best Practices
  • Steps
  • Example

[mamoodi]

I've tried to consolidate all the docs we have in these documentation. Including the README. My suggestion is if this is approved, we just link the README to the docs as to avoid redundancy and having to update documentation in two places.

If you are good with that, I can go ahead with this as well.

[rbren]

Can we standardize on microagent (no hyphen)?

[mamoodi]

Yes

[mamoodi]

Done!

[enyst]

Sorry, I read on the run, but did we give up task type microagents?

[mamoodi]

Sorry, I read on the run, but did we give up task type microagents?

I swear I read somewhere that those are not fully implemented yet...However, if they are, probably need someone to explain them to me so they can be added.