Fetching from the wire…
Infra2026-08-21 · source-backed
The sandbox firewall forwards requests to a v0 proxy using a per-sandbox certificate authority, so the proxy reads the traffic, verifies the sandbox's OIDC token, resolves the chat session, and fetches a fresh credential server-side. Critically, it injects credentials only into protocol-defined fields (the Authorization bearer header, the login request's token field) and rejects any request where the placeholder appears elsewhere, because blind substitution would leak the token back through query results. Vercel First 15 days: ~13,000 requests, zero placeholder-misuse rejections. If you're generating code that calls authenticated APIs, this is the pattern to copy rather than invent.
Each link below shares sources, entities, or timing with this story.
Now on all plans and in v0. Instead of storing provider secrets in env vars, a deployment authenticates with its existing Vercel OIDC identity and calls getToken() for a task-scoped credential the platform refreshes and expires. Covers 100+ integrations including managed conne...
Server-managed settings that terminate sandbox TLS, route sandbox traffic through your proxy, inject credentials, or weaken isolation all need approval before applying. ANTHROPIC_CUSTOM_HEADERS from managed or project settings needs approval when it sets a credential, org/tena...
Vercel added ChatGPT accounts as an authentication option for both Vercel and v0. The interesting part isn't convenience, it's direction: OpenAI is being wired in as an OAuth identity provider on a major developer platform, the role Google and GitHub have held for a decade. If...
Martin Alderson's essay "The upcoming AI margin collapse, part 1: GLM 5.2" hit 675 points and 462 comments on Hacker News, and it's the rare HN chart-topper that's actually about spreadsheet math instead of vibes. The argument is simple. Z.ai's GLM 5.2 delivers frontier-adjace...
I've been saying for months that the missing piece in agentic coding isn't smarter models. It's that agents can't provision anything. They can write code all day but the moment they need a database, an auth provider, or a hosting account, a human has to step in, click through...
NanoNets' Graft builds a persistent graph of linked markdown nodes describing subsystems, APIs and concepts, then injects ranked context per prompt through hooks instead of letting the agent re-explore the repo. A 162-run sweep across two repos reports 8,070 to 4,650 tokens, 4...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.