Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-06-28 · source-backed
Week 26 (June 22 to 26, v2.1.185 to 192) added claude mcp login for shell-based MCP auth, /rewind support to resume from before a /clear, shell mode that reacts to command output, and background subagents that now surface permission prompts instead of silently auto-denying (Releasebot). The June 27 release added fullscreen mouse controls and, importantly, fixed hook matchers with hyphenated identifiers like code-reviewer and mcp__brave-search that were accidentally substring-matching. They now exact-match (Releasebot). If your hooks were firing on the wrong tools and you couldn't figure out why, that's the bug. Background agents also stopped telling the model to "end your response," so the parent keeps working while a subagent runs.
Each link below shares sources, entities, or timing with this story.
It patches leaks that only bite over time: MCP stdio server stderr accumulating unbounded, LSP documents staying open indefinitely, and pasted images retained in the agent view (Releasebot). On top of that, background agents now commit, push, and open a draft PR on completion...
Buried in the notes: several 2.1.232 changes covering Cygwin symlink handling and shell input redirections were rolled back, with a narrower version planned (Releasebot). 2.1.233 also fixed idle-session CPU burn on Linux and MCP stream handling. If you are on Windows with Cygw...
MCP servers can now request structured user input mid-task via interactive dialogs. Two new hooks — Elicitation and ElicitationResult — let developers intercept and override responses programmatically. The -n / --name flag sets session display names for monitoring multi-sessio...
Two things in one release, and only one of them is in the security section. CLAUDE_CODE_SUBAGENT_MODEL used to override the model for every subagent. In 2.1.251 it sets the default instead. An agent definition's model: frontmatter now wins, and so does an explicit per-spawn mo...
The v2.1.205 release turned /doctor into a full setup audit that flags unused skills, MCP, and plugins against their context cost, deduplicates local vs checked-in CLAUDE.md, and flags slow hooks (Releasebot). A typical 5-server, 58-tool MCP setup burns ~55k tokens before your...
Cursor 3 launched on April 2. Not an update. A full rebuild. The editor is now secondary to what they're calling an agent orchestration workspace. You can run unlimited parallel agents, locally or in the cloud, launch them from your phone or Slack or Linear, and manage them in...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.