What caught our eye this week across JavaScript Weekly #795, React Status #483, and Node Weekly #634 — and what it means for the Aliz stack.

TypeScript 7.0 shipped on July 8, 2026. The compiler is now written in Go — a line-by-line port of the existing TypeScript codebase (codename "Corsa"), not a from-scratch rewrite. The result is 8–12x faster builds, dramatically faster editor responsiveness, and a language server that crashes far less often. This is the single biggest performance improvement in TypeScript's 12-year history. But it comes with real breaking changes, a missing programmatic API, and a migration path that rewards patience over haste.

shadcn/ui launched on Radix in January 2023, and for three years Radix was the primitive layer under every component you copied into your repo. As of July 2026, that default has changed: new shadcn projects now scaffold on Base UI. This isn't a forced migration or a deprecation — Radix stays fully supported, and both libraries keep getting new components. The signal worth paying attention to is why the default moved: people running shadcn create were already picking Base UI over Radix roughly 2-to-1, so the default simply caught up to what teams were already choosing.

Claude Fable is the most capable model Anthropic has shipped — above Opus class, frontier reasoning, genuinely impressive on hard problems. It's also the fastest way to burn through your token budget if you haven't built the discipline to use it correctly. Most developers will reach for it because it's the best, use it for tasks Haiku could handle, and wonder why their costs exploded. This post is about earning the right to use Fable by mastering the cheaper models first.

AI coding agents waste a remarkable number of tokens just figuring out how your code connects. They open file after file, read imports, chase type definitions, and slowly build a mental model of architecture — burning through context windows and money in the process. @ttsc/graph takes a different approach: it hands the agent a compiler-resolved architecture graph upfront, so it can navigate by structure instead of reading source. It's early (v0.16), requires TypeScript v7 rc, and the benchmarks are vendor-supplied — but the idea is sharp enough to be worth knowing about. The author is Jeongho Nam (samchon), known for typia and nestia, which adds some credibility to the execution.

V0 is Vercel's AI-powered development platform that lets you generate, edit, and deploy full-stack web applications through natural language prompts. Since its launch as a UI component generator, it has evolved dramatically in the first half of 2026 — growing into a full-stack development environment with git integration, a terminal, merge conflict resolution, and enterprise features. What started as "generate a landing page from a prompt" now looks more like a cloud IDE competing with Cursor and Windsurf. This post traces the arc of that transformation and identifies the strategic bets Vercel is making.

You already use Zod to validate API responses. Now it's the contract layer between your app and LLMs. One schema gives you runtime validation, TypeScript inference, AND guaranteed structured output from GPT, Gemini, and Claude. Without it you're calling JSON.parse() on free text and praying the model didn't sneak in a markdown fence or an apologetic preamble.

AG-UI (Agent User Interaction Protocol) is an open, event-based protocol that standardizes how AI agents communicate with user-facing applications. Created by CopilotKit and adopted by Microsoft, Google, AWS, LangChain, and CrewAI, it fills the gap between MCP (agent↔tools) and A2A (agent↔agent) by defining the agent↔UI layer. It's MIT licensed with 14.4k GitHub stars and 50+ framework integrations.

The Model Context Protocol specification release candidate (locked May 21, stable July 28, 2026) makes the protocol fully stateless — no handshakes, no session IDs, no sticky routing. Alongside that headline change, it graduates the extensions framework to first-class status, introduces MCP Apps for server-rendered UI, formalizes the Tasks extension for long-running work, adds production-grade observability headers, upgrades to full JSON Schema 2020-12, and hardens OAuth 2.0 authorization through multiple SEPs. Three features — Roots, Sampling, and Logging — are deprecated under a new lifecycle policy with a one-year sunset window.

AI coding tools are great at boilerplate, but they still hallucinate web API details, browser support, and even whether a feature exists at all. MDN's new MCP Server tackles that problem by letting MCP-compatible editors and agents pull current MDN documentation and browser compatibility data straight from the source.