Peter Edmonds

founder for educators @

[Peter Edmonds @peteredm0]

@thdxr the #1 most annoying thing with oc right now is stale lsp diagnostics. this happens basically on every edit:

> agent adds import
> lsp: "Error [78:10] Cannot find name 'foobar'."
> agent goes crazy looking through dts files trying to debug

is this a known issue?

[Peter Edmonds @peteredm0]

@tim_smart what’s “lalph”?

[Peter Edmonds @peteredm0]

@mitsuhiko probably...durable sandboxes?

opencode is great but doesn't have a solution for non-fs persistence (yet? @thdxr) which makes it a non-starter for building widely used agents on top of it.

basically just want something like opencode but in an actor.

[Peter Edmonds @peteredm0]

@RhysSullivan @dillon_mulroy nice! i first saw this in @ethanniser's code, but i'm sure many have rediscovered it.

[Peter Edmonds @peteredm0]

@dillon_mulroy @hugorcd @boristane what does evlog in the effect ecosystem look like?

just Effect.annotateLogs, or is there something more?

[Peter Edmonds @peteredm0]

@theo good day to be @useblacksmith i suppose.

[Peter Edmonds @peteredm0]

@adamdotdev my instinct is to save messages/parts on our end and treat each request as a new session, but aware that cache breakpoints are a delicate beast.

don't want to lose all my cache inputs by mismanaging the part format

[Peter Edmonds @peteredm0]

@adamdotdev for people building on top of opencode server ala Ramp Inspect, is there a suggested path to session persistence?

[Peter Edmonds @peteredm0]

@vercel code review bot is great. just caught a niche FE resource leak that no other reviewers (human or llm!) noticed.

integration into existing workflows needs some work though. would love a cli version so my agents can use it w/o visiting _yet_ another dash cc/@cramforce

[Peter Edmonds @peteredm0]

@thdxr cool will take a look this week!

for people building on top of opencode server ala ramp's inspect, is there a suggested path to session persistence?

my instinct is to save thread data on our end and treat each request as a new session.

wdyt?

[Peter Edmonds @peteredm0]

@zeeg First project I've seen based on the Anthropic Agents SDK!

How did you land on that vs Vercel SDK, OpenCode SDK, or others?

[Peter Edmonds @peteredm0]

@chaliy @jerrickhakim @vercel @blackboxai @roocode no, sandboxes don't support Docker.

all sandboxes run on al'23.

snapshots are analogous docker images in that you use them to spawn reproducible instances.

[Peter Edmonds @peteredm0]

@zeeg > using neon

[Peter Edmonds @peteredm0]

@sqs @AmpCode skills.

[Peter Edmonds @peteredm0]

what michael and jude (@vercel) are *correctly* reporting is that, while progressive disclosure is a useful pattern, the implementation doesn't matter.

i'd still benefit from a public implementation for Effect, whether "skills" or "indexed markdown". are these public @MichaelArnaldi ?

[Peter Edmonds @peteredm0]

@grinich @kushalbyatnal brilliant. i'll give it a swing this weekend.

[Peter Edmonds @peteredm0]

@MichaelArnaldi for encoding best practices and stylistic choices, like "prefer Effect.Service"

there's many ways to achieve the same thing in effect. from my experience, a small amount of guidance on preference helps a ton.

[Peter Edmonds @peteredm0]

@a1zhang @daytonaio why should subagents not share a sandbox?

isn't it important for a subagent to say "i've written the results to /results" or similar?