Fetching from the wire…
Tools2026-09-16 · source-backed
Published September 16, it turns on modal editing via /vim, adds /settings options to opt into context management tools for agents and subagents, adds transcriptView: "concise" grouping tool activity into expandable summaries, and adds GPT-6 Astra support. The subagent toggle is opt-in, so existing installs don't get it. The same release adds per-host sandbox network allow/deny rules that layer on top of a configured upstream proxy rather than replacing it, and fixes a Windows bypass where a policy-blocked write forced you to disable the sandbox for the whole session.
Each link below shares sources, entities, or timing with this story.
rust-v0.153.1 backports the GPT-6-Astra model catalog so the model can be configured through the API without changing the default or appearing in the picker. rust-v0.153.2, 2 hours 51 minutes later, corrects the Astra Fast tier description from "1.5x" to "2x speed, increased u...
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...
Published September 7, it puts OpenAI Codex in the agent picker with a copy-ready ~/.codex/config.toml panel pointing Codex CLI and Desktop at Manifest over the Responses API (GitHub). Two compatibility fixes make it work: Responses-API role: "developer" instruction messages f...
5.8k stars, Rust, macOS, ~40 MB versus ~67 MB upstream, keeping full Lua customization. Command-failure recovery with suggested fixes applied via Cmd + Shift + E, natural-language-to-command via # <description>, preconfigured integration for Claude Code, Codex, Gemini CLI, and...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
Triple-stream retrieval (BM25 keyword, vector embeddings, knowledge-graph traversal) fused via Reciprocal Rank Fusion on the iii engine, with SQLite for state and an in-memory vector index, no external database. The economic claim: ~170K tokens/year (~$10) versus ~650K tokens...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.