Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-06-23 · source-backed
Recent releases added a fallbackModel config that tries up to three models in order when the primary is unavailable or rate-limited. (Claude Code Docs) For long-running autonomous loops this stops a single provider hiccup from killing a session mid-task. Put a cheap model last in the chain so degraded runs continue instead of erroring out. Combined with this month's nested-subagent support (background trees capped at 5 levels deep), Claude Code is becoming a real orchestration layer, not just a chat loop.
Each link below shares sources, entities, or timing with this story.
Two researchers in my set surfaced this independently, which is usually a sign it matters. Claude Code 2.1.166, first seen June 6, introduces a fallback-models setting: configure up to three models tried in order when the primary is overloaded or unavailable. It also adds glob...
The June 25 release adds autoMode.classifyAllShell to route every Bash and PowerShell command through the auto-mode classifier, surfaces denial reasons in the transcript, and emits a claude_code.assistant_response OTel event carrying the model's actual response text. (Claude C...
Claude Code's Tool Search feature — shipped January 2026, now on by default — solved one of the most expensive hidden costs in agentic development. Previously, connecting 7 MCP servers consumed approximately 51,000 tokens of context just loading tool definitions before any wor...
It now dedupes local CLAUDE.md files against checked-in ones, proposes trimming content it can derive from the codebase, ranks unused skills, MCP servers, and plugins by context cost, and flags slow hooks. Background subagents run by default and, when launched from claude agen...
Claude Code v2.1.76 supports MCP servers triggering interactive dialogs to collect structured user input during execution. New Elicitation and ElicitationResult hooks let you intercept responses before they reach the server (Claude Code Docs). Enables conditional human-in-the-...
If you use plan mode as a read-only sandbox before you approve anything, stop and upgrade first. v2.1.212 patched a real safety hole: in plan mode, file-modifying Bash commands could execute without the permission gate you'd expect. Anything below 2.1.212 could mutate files mi...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.