The `uncertain` mapping isn't clean. DASP treats it as terminal: the host can't prove whether effects occurred, so it must not retry. A2A's `TASK_STATE_UNSPECIFIED` is indeterminate, but not terminal. The adapter must preserve the DASP outcome in metadata and map it conservatively, likely to `FAILED`.
https://dasp-protocol.github.io/dasp/
Hey HNI'm the author of Jido, an Elixir Actor & Agent SDK. I was building out an Elixir Durable Actor/Agent server and hit a wall regarding communication protocols. I reviewed all the existing protocols; A2A, ACP, AHP and nothing met my needs.I wanted a language agnostic durable actor session protocol. Agent Host Protocol (AHP) from Microsoft was close, but was centered around "chat".The...
https://jido.run/blog/jido-assembly-slack-clone
Hi HN!We put together a showcase on a group chat application in pure Elixir that includes the following:* Hologram UI* Jido Agents* Jido Messaging (bridging chat to Telegram/Discord)The authoring experience is pure Elixir on both the front end and back end. This showcase demonstrates the potency of this stack.
I came to similar conclusions - what does valuable agentic software look like? It's not OpenClaw (yet)
The game theory then, in my opinion, is to focus on the knowable frontier - implement tools we can trust - and continue working and sharing that work.
I am holding onto the optimistic case - valuable use cases beyond coding agents will emerge.
This will be solved - and I hope that Jido can be a meaningful participant in that wider conversation.
Actions can enforce an output schema: https://hexdocs.pm/jido_action/schemas-validation.html#outpu...
Agents can as well - but it can be implemented a few different ways.
Jido core has zero LLM support for this reason.
There's nearing 40+ years of "Agent" research in CompSci, LLM's came along and we threw out all of it. I didn't like that so I spent time researching this history to do my best at considering it with Jido.
That said, I love LLM's - but they belong in the Jido AI package.
There’s a growing community showcase and I have a list of private/commercial references as well depending on your goals
I used Claude to learn & refine the patterns, but it couldn’t write this level of OTP code at that time.
As models got better, I used them to find bugs and simplify - but the bones are roughly the same from that original design.
The future is going to be wild
As LLM API's evolved, I needed more and built ReqLLM which is now embedded deeply into Jido.
Agree on operational boundaries - it took a long time to land where we did with the 2.0 release
Too much to say about this in a comment, but take a look at the "Concepts: Executor" section - it digs into the model here
https://hex.pm/packages/req_llm
ReqLLM is baked into the heart of Jido now - we don't support anything else
It's use-case specific though - security is a much bigger topic then just "agents in containers"
The point of Jido isn't to solve this directly - it's to give you the tools to solve it for your needs.