Who's using Claude Code Action for PR reviews—what's your workflow/prompt? The first suggestion completely hallucinated.
Really thinking of just using @greptile
English
Andrei Bobkov
55 posts
Andrei Bobkov
@ctoofeverything
21. Building https://t.co/b2wSZMFfMw
Berlin, Germany Katılım Haziran 2014
127 Takip Edilen45 Takipçiler
English
@ctoofeverything @whoiskatrin @zlxndr aight I'll work on that
wanna open an issue with problems you faced so I know to include it?
English
we just shipped one of our biggest Agents SDK updates in a while! 🎈
- 15+ new docs with more examples
- interval scheduling with scheduleEvery()
- custom routing
- callable timeouts
- state validation hooks
- MCP options api and so much more!
go build cool stuff!
English
English
@threepointone @whoiskatrin @zlxndr Really need the authentication guide for the agents. Still didn’t manage to set up with with AIChatAgent and useChat:(
English
@whoiskatrin @zlxndr yup see here github.com/cloudflare/age… hoping to land in main docs by tomorrow
English
As software gets easier to make, the products that stand out will be the ones crafted with uncommon care.
If that's the kind of work you want to do, I'm sharing everything I know:
interfacecraft.dev
English
@inngest function execution is down, all runs are queued but not picked up by runners…
Status page is green
English
@artzkaizen @jonathan_wilke @ViktorB01 RHF also supports async validation (at least with zod)
Reusability can indeed be improved though, I’m sticking to some TS hacks for now, like FieldPathByValue
Haven’t tried tanstack yet
English
@jonathan_wilke @ViktorB01 Personally I think either choice is great. tanstack has a few avatars tho
- async validation
- you can create reusable components and bind them to the useAppform hook.
English
Developers, I need your opinion:
🩷 react-hook-form
or
💛 Tanstack Form
English
@pufferkeefer @kitlangton Of course not. I’m genuinely excited for this course and open to changing my mind, that’s all. And I really do want Effect to be a useful tool, just don’t see how yet.
English
I’ve seen a lot of excitement around @EffectTS_ but their selling points don’t look like they’re worth the trade-offs:
- Typed errors: just use catch & instanceof, with custom error classes if needed
- dependency injection: function arguments
Anything else I’m missing?
Charlie Lamb@charlietlamb
The winning tech for fast paced projects going into 2026: - @nextjs lots of noise about tanstack start atm but next is still king imo - @EffectTS_ the best way to write typescript - @better_auth authentication is literally solved now - @autumnpricing payments are literally solved now - @cubic_dev_ or @greptile both great picks for ai code review, no reason for ai to not be reviewing your code in 2026 - @useblacksmith for github actions on steroids - @cursor_ai and @claudeai are still clear when it comes to writing code - @mintlify or fumadocs by @fuma_nama for documentation, depends on your use case - @convex or @supabase if you want to quickly spin up a backend - @neondatabase for free plan, @PlanetScale for when things get serious - @vercel /@Railway /@render save time and let these guys handle your devops - @aisdk: you don't need python to call an llm, ai sdk is the best way to do this - @shadcn obviously
English
@artzkaizen @Baconbrix I’m using Expo Updates but I’m genuinely terrified of this limit
Luckily the protocol that powers expo-updates is open source, and there’s an official example from Expo team of a custom server: github.com/expo/custom-ex…
It does mean though creating your “own version of EAS”
English
I really want to understand the rationale behind expo charging for ota updates based on MAU's
I love expo but this is huge deal breaker, most apps have well over 1k users
@Baconbrix
English
@zirkelc_ I use it a lot it in tests, much more convenient than afterEach hook—no need to remember the cleanup
English
I rarely see code with `await using` despite being available for some time
It automatically disposes resources when they go out of scope, like closing database connections after the function ends
This is especially useful on Lambda where hanging connections are a common issue
English
Bun and Node.js docs have conflicting info about the node:vm module.
Bun claims it to be suitable for untrusted code execution, while official Node.js docs explicitly say in red that it cannot be used for untrusted code execution.
So what’s up with node:vm in Bun? @jarredsumner
English
I came to a similar conclusion when developing an MCP for one ERP system. 2 biggest problems were the huge amount of data and LLM’s math accuracy. I solved both by giving it a “computer”-a sandbox by @CloudflareDev to safely execute generated code and retrieve only necessary data
AI SDK@aisdk
With programmatic tool calling, Claude can call your tools from a code execution environment, keeping intermediate results out of context. It can significantly reduce token usage and cost.
English
@jarredsumner Please fix the test isolation and module.mock restoration! We beg you
It's been an issue for 2 years that has huge impact on Bun.test users (including our company):
github.com/oven-sh/bun/is…
English
informal bun roadmap:
bun process manager:
- `bun start <package.json script or file>`
- `bun stop <package.json script or file>`
- `bun logs <package.json script or file>`
- `bun deploy` to deploy frontend/backend to any hosting
- observability & node compatibility & bugfixes
English
