Support microagents in CLI and Headless

[rbren]

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
  CHANGELOG: custom microagents are now supported in headless and CLI modes

---

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

Main goal was to set up custom microagents, but I took a minute to DRY this code out a bit. We could probably do the same with the agent set up in the server, but leaving that alone for now for stability

---

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:075bfec-nikolaik   --name openhands-app-075bfec   docker.all-hands.dev/all-hands-ai/openhands:075bfec

[rbren]

OK verified things seem to be working well for both CLI and headless

[enyst]

I merged main here, because dummy agent job was stuck again. So it has the latest fixes there.

[enyst]

I ran one eval instance, it looks as expected (it did get the micro agent, Xingyao's PR fixes that)