#selectQuery

1 messages ยท Page 1 of 1 (latest)

rapid timber
#

@charred quiver I'm lacking some context about how/if selectQuery is relevant in the context of multi object

#

my impression that even after selecting a tool, the LLM should still have access to all the previous known objects. Trying to understand a bit more where/how the losing track of Query happens.

charred quiver
#

the problem is that Query is a special case - it's not an object, there's no QueryID etc

#

which is why it has a special API, LLM.withQuery, which sets it as the initially selected object, even though that's kind of a lie (it's an object, but it has a nil ID)

#

i'm not sure how to square this with the new Environments API, either

atomic orchid
#

separately from that, the word "query" is meaningless to the LLM

#

and confusing to the caller

#

so there's pending bikeshedding on that

charred quiver
#

yeah exactly

#

"root"?

rapid timber
atomic orchid
#

Well I think we can be even more specific. It's really about privileges to 1) access the core API 2) access the caller module's context

#

we could take it even further and make it about each core API subsystem, like "ability to create a container", "ability to create a directory", "ability to access the host" (kind of a big one) etc

#

@charred quiver we were just talking about the need to manually curate what core functions are masked etc

rapid timber
#

@atomic orchid questions:

  1. Everything (selectQuery + privileged) seems to be related to the Environments API, shall we scope this discussion under that issue / thread?

  2. There's a current limitation to build agents which is to lose track of the root context / core api / etc. Shall we provide a stopgap in the meantime?

  3. Can we push the privileges discussion a bit further down the road? Or we should start designing this scopes based on that?

#

Also 3, re permission model: MCP has adopted OAuth as their authentication protocol. I'd assume that will inherently affect the permission model MCP servers adopt. I guess we might want to take that into account while designing our permission model to at least make sure we can make them compatible eventually?

atomic orchid
atomic orchid
#

Can we push the privileges discussion a bit further down the road? Or we should start designing this scopes based on that?

at the moment there's an argument to dag.LLM() called withQuery. It won't make sense to anyone. So no we can't push back the design of it. Otherwise we'll need to support it forever

rapid timber
rapid timber
#

Keep track of core API issue

atomic orchid
rapid timber
atomic orchid
#

Honestly it's not user-facing, so purely MCP implementation detail I think

#

(in other words, whichever performs best)

#

Separately I care about the user-facing API for this, ie. dag.LLM(withQuery: Bool!)

rapid timber
atomic orchid
#

selectQuery

rapid timber
#

I've synced with Alex and we'll go with the selectQuery tool given the trade-offs. Will try to get something working tomorrow morning ๐Ÿ™

charred quiver