Since Oct 26, Copilot CLI (/permissions, then assisted), the Copilot app and VS Code can have an LLM review each command, file path or URL request, running clearly safe ones and asking you about the rest. Enterprise admins can block Allow All while keeping Assisted, or turn Assisted off separately; it's still no substitute for a sandbox.
Released Oct 27, the stable build adds a banner saying the CLI isn't yet tuned for Gemini 4, opt in private network endpoints for MCP OAuth, and a keys array in keybindings.json . Its git and shell environments now skip interactive credential and SSH prompts while keeping your /.gitconfig , and flicker and lost scrollback in the terminal UI are fixed…
Augment's agent workspace now lets you run Codex or Claude Code under named profiles, each with its own env vars (say, a separate work account), and mark some as backups so Intent switches to the next one when a profile hits quota, including Claude Code's weekly and session limits. Queued PRs also show their GitHub merge queue position and ETA…
Released Oct 27, Write now makes Claude read a very large CLAUDE.md, rules or @ included file in full (or edit in place) instead of clobbering it after seeing only the start, and prompt and agent hooks run at most 24 at a time per session, subagents included. On Bedrock, Vertex, Foundry and Mantle, unrecognized model names like custom deployments now get the shorter system prompt; set CLAUDE CODE SIMPLE SYSTEM PROMPT=0 to keep the full one…
Announced Oct 26, the cloud delivered FortiGuard Inline AI Security Service scans prompts, model responses and MCP tool lists, calls and responses in both directions, redacting 35 types of PII and enforcing per team model permissions, budgets and rate limits. If your company runs FortiGate, expect your agents' MCP traffic to start hitting policy checks you didn't write…
Since v2.1.311, setting CLAUDE CODE EVEN MORE DANGEROUSLY SKIP PERMISSIONS=1 lifts the short blocklist (like rm rf ) that dangerously skip permissions still prompts for, and Anthropic's Daisy Hollman confirmed it's not a joke. Managed policy settings still apply on top, so if you run unattended agents, keep limits enforced outside the prompt…
Spotted something we missed? Start a thread.
