Luca Chang

cc: @mikekistler

> The main change here is that neither end can be associated with a Promise/CompletableFuture anymore. Instead, they must be associated with some kind of Emitter, which supports multiple values....

Do you have a branch somewhere I could look at? I assume that's just the polymorphic part - interested in seeing the exact diff for this. --- Also linking the...

I might be willing to sponsor this, depending on the specifics, but I likely won't be able to directly contribute that much right now due to having several other large...

Discussing in parallel with @cliffhall and @scottslewis - the Primitives WG is planning to introduce a unified proposal for filtering across the protocol after the new Groups proposal (addressing feedback)...

@He-Pin Discord is [here](https://discord.gg/6CSzBmMkjX), linked in the governance documentation [here](https://modelcontextprotocol.io/community/communication#discord). Check the `#primitive-grouping-wg` channel. --- Also linking Agents WG notes on this from two days ago for discoverability for others:...

Can you elaborate on this? I'm not sure what this is, exactly (and this appears to be a mockup).

LGTM, left some thoughts on the batching note but beyond that I think this is more than ready for other eyes on it 👀

> Because tool invocations are [model controlled](https://modelcontextprotocol.io/specification/2025-03-26/server), when should the model decide to search on tools as opposed to just consider using an available tool directly? The way I've been...

> > this is meant as a tool that LLMs can invoke to search for a tool. > > i think this is the issue. unless it changes the semantics...