Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-08-27 · source-backed
Released August 26, the Agents window defaults to a single-pane side layout with session state surfaced as pills above the chat input showing changes, pull requests and artifacts. It now lists recent Copilot or Claude sessions started in other applications, two by default, tunable via chat.agentSessions.showExternal (VS Code). Two smaller items matter if you meter agent runs: the experimental /rubber-duck command asks a complementary model for a second opinion on the agent's work, and hovering the response footer gives a per-model breakdown of input, cached input and output tokens for that turn.
Each link below shares sources, entities, or timing with this story.
Released July 16, the agent host runs coding agents (Copilot, Claude, Codex) in their own process via a new Agent Host Protocol, so a session lives independently and renders across multiple windows. Agents can list sessions, read conversations, spawn sub-task sessions, and sen...
Shipped August 12 on the Agent Host Protocol: the same agent session attaches from multiple VS Code windows, and the model picker exposes both Anthropic and Copilot options, switchable between turns and billed to the respective service. An experimental chat.agentHost.allowSign...
The July 2026 update (v1.127-v1.131) runs each agent session against an isolated checkout, and it spans all three agents rather than being Copilot-only. Also: redesigned Agents window with side-by-side code review and chat, subagent tracking showing model, elapsed time and act...
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...
43.3% on Frontier-Bench v0.1. Opus 4.8 scored 18.7%. That's not an incremental bump, that's the same benchmark with a different shape of answer. Anthropic released Claude Opus 5 on July 24 at $5/$25 per million input/output tokens, exactly half of Fable 5's $10/$50, while matc...
wanshuiyin/HERO-Anti-OverDefense went from creation to 68 stars in a single day. HERO is Hashing, Edge cases, Rubrics, Overbuild, and the claim is that agent over-engineering isn't diffuse but falls into four recognizable shapes suppressible with a portable prompt contract acr...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.