WHY you should care
Two API-level additions in v2.1.218 affect how you build with Managed Agents in production:
-
effort parameter on agent create — BetaManagedAgentsModelConfigParams now accepts effort: "low" | "medium" | "high" | "xhigh" | "max". Control reasoning depth per-agent at creation time. Useful for cost/latency tuning.
-
dreaming-2026-04-21 beta header — New accepted beta on agent create/update. What it enables is unclear yet, but it's live. Worth watching.
Other notable changes
- 🚀
/code-review runs as a background subagent — no longer floods conversation context
- 🐛 Windows path fix —
C:\Users\... paths with \u-prefixed segments were silently corrupting to CJK characters
- 🐛 Left-arrow no longer silently discards conversations
/deep-research won't auto-launch anymore — manual onlycontext: fork skills background by default
Source PR
thevibeworks/claude-code-docs#1084
/cc @lroolle
WHY you should care
Two API-level additions in v2.1.218 affect how you build with Managed Agents in production:
effortparameter on agent create —BetaManagedAgentsModelConfigParamsnow acceptseffort: "low" | "medium" | "high" | "xhigh" | "max". Control reasoning depth per-agent at creation time. Useful for cost/latency tuning.dreaming-2026-04-21beta header — New accepted beta on agent create/update. What it enables is unclear yet, but it's live. Worth watching.Other notable changes
/code-reviewruns as a background subagent — no longer floods conversation contextC:\Users\...paths with\u-prefixed segments were silently corrupting to CJK characters/deep-researchwon't auto-launch anymore — manual onlycontext: forkskills background by defaultSource PR
thevibeworks/claude-code-docs#1084
/cc @lroolle