On Oct 14, OpenAI retired GPT-5.5 from ChatGPT, ChatGPT Work, and Codex on every plan; the OpenAI API is unaffected. Codex users on ChatGPT sign-in should replace gpt-5.5 with gpt-6-sol (Plus/Pro/Business/Enterprise/Edu) or gpt-6-luna (Free/Go desktop), including config.toml, custom agents, and scheduled tasks.
Chainguard opened GA for enterprise on four OAuth MCP servers— cg oci , cg apk , cg versions , and cg api —so agents in Claude Code, Cursor, and other MCP clients can verify image tags, Wolfi package equivalents, EOL status, and org policy before shipping deps. Connect via each server URL with browser OAuth, or headless with chainctl auth login audience=<server…
The gh actions lock CLI extension writes .github/workflows/actions.lock , pinning every action (transitive ones included) to a reviewed commit, so a moved or hijacked tag can't swap in new code; Dependabot updates the lock in the same PR. It's in preview for GitHub Enterprise Cloud, with an optional Require lockfile policy for admins…
Vani Code Agent (preview, code install extension AhuraSense.vani code ) reads and edits your workspace with per edit diffs, runs commands only after you approve, and offers Ask, Accept edits, or Plan modes with .env , .git , and CI workflows protected by default. The extension is free; usage bills to your Vani API key, and desktop apps plus a CLI are next…
Vercel’s Oct 13 changelog puts Google’s Gemini 4 Argon on AI Gateway as google/gemini 4 argon (1M context, thinking levels low/medium/high, provider pricing with no markup). Run vercel ai gateway setup , then pick it in Claude Code, Codex, or Cursor…
Chainguard opened a beta for Workspaces: Chainguard hardened microVMs where developers and agents work via chainctl develop , with working tree sync, warm snapshots, host side short lived credential injection, and optional egress policies—so agents never touch local corporate secrets. Claude is supported today; pairs optionally with Chainguard Checks as a CI gate before PRs…
Spotted something we missed? Start a thread.