Proposal: Agent healthcheck endpoint to advance production-readiness of deployed agents about agent-protocol HOT 2 OPEN

That's an interesin

I'm curious what your thoughts are on the info endpoint, I posted a potential schema for it here in Issue #39.

It didn't go over a health check for readiness and liveliness, but I think that it could be added there technically. Or some other type of standardized status message.

The schema we were considering does include a version for both the Agent Protocol and the Agent itself, which would be useful for clients.

That's an interesting proposal @jzanecook. I have some thoughts about that info proposal that are distinctly different form this one, but I believe they are and should be separate concerns. I think it's worthwhile deciding earlier rather than later how prescriptive the agent protocol needs to be. For what it's worth, I prefer open/extensible protocols rather than restrictive ones, and I also believe a mechanism in the protocol for Agent metadata is valuable but is a separate concern from liveness or readiness.

I would find a lot of value in being able to GET liveness with a 200 response as good enough to detect liveness of an Agent. I think the readiness check is distinctly different because it indicates that dependent resources are also alive and responsive. Agent metadata is also valuable but a GET for info/metadata should be different than a GET for a factor of health. My preference in RESTful architectures (since this protocol appears to assume HTTP so far) is always to keep separate endpoints for separate resources.

from agent-protocol.

I'm curious what your thoughts are on the info endpoint, I posted a potential schema for it here in Issue #39.

It didn't go over a health check for readiness and liveliness, but I think that it could be added there technically. Or some other type of standardized status message.

The schema we were considering does include a version for both the Agent Protocol and the Agent itself, which would be useful for clients.

from agent-protocol.