Improve agent loop tracking and make concurrent limit configurable

[rbren]

This PR improves how we track and manage concurrent agent loops:

• Add max_concurrent_conversations to AppConfig (default: 3)
• Add start_time tracking to Session class
• Use accurate start time to determine oldest session when limit is reached

Previously, when the limit of concurrent agent loops was reached, the system would try to guess which was the oldest by reversing the list of session IDs. This was inaccurate. Now we track the actual start time of each session and use that to accurately determine which session is the oldest when we need to close one.

The limit of 3 concurrent conversations has also been moved from a hardcoded constant to a configurable value in AppConfig.

---

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:6eaa039-nikolaik   --name openhands-app-6eaa039   docker.all-hands.dev/all-hands-ai/openhands:6eaa039