Fetching from the wire…
Public story · 2026-07-30 · high
Claude Code cut Opus 4.7 from fast mode the same week, closing the same cost-saving path from the other side.
Why now: Zed shipped its change on July 29, the same week Claude Code removed Opus 4.7 from fast mode, per its v2.1.219 release notes.
Zed dropped Fast Mode for Opus 4.6 and 4.7 in its July 29 stable release, per the v1.13.1 changelog on GitHub.
Claude Code made the same call on Opus 4.7 that same week, per its v2.1.219 release notes. Two coding tools built by separate teams cut the same discount path off the same model generation within days of each other.
That matters if you've been running Opus 4.x through Fast Mode to hold down token costs. That option is gone now in both tools. You either pay full Opus pricing or move to a different model.
The rest of Zed's 1.13.1 release is routine. Tighter branch picker filtering, LSP log requests that now show duration, a fix for a Fcitx5 memory leak on KDE Wayland. None of it explains why Fast Mode went away for Opus 4.6 and 4.7 specifically. The changelog doesn't say if the change is permanent or whether it reaches any other model.
One tool dropping a feature is a product call. Two separate tools cutting the same discount off the same model in the same stretch of days reads differently. It looks like Anthropic narrowing what it subsidizes at the model level, and builders on Opus inherit that call either way. Worth watching whether the next Opus release gets a Fast Mode tier at all, or whether the discount disappears for the whole line.
Each link below shares sources, entities, or timing with this story.
Claude Code 2.1.229 shipped a config flag most people will scroll past: CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS. What it does is delay the launch of sibling agents that share a prompt prefix, so the second through Nth agents read the warm cache instead of each writing their own...
DeepClaude hit 470 points on Hacker News. It swaps Claude Code's API backend to DeepSeek V4 Pro while preserving the full agent loop: file editing, bash execution, git tooling, the whole workflow. DeepSeek V4 Pro scores 96.4% on LiveCodeBench at a fraction of Anthropic's prici...
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...
July 9, across VS Code, Visual Studio, Copilot CLI, the cloud agent, github.com, GitHub Mobile, JetBrains, Xcode, and Eclipse. Sol is the high-reasoning tier at $5/1M in, $30/1M out, gated to Pro+/Max/Business/Enterprise. Terra is the balanced default at $2.50/$15. Luna is fas...
Within five days of each other, both Claude Code (v2.1.158, May 31) and Cursor (3.6, May 29) shipped remarkably similar architectures for autonomous agent execution. Both use a classifier subagent that reviews each pending action against conversation context and decides: allow...
A GitHub repo cataloging Claude Code tips doesn't normally warrant a top story. But shanraisshan/claude-code-best-practice at 53.4K stars isn't a tips list anymore. It's the de facto reference for how an entire generation of developers is learning to work with AI coding agents...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.