LLMS
Claude Code v2.1.68
RESUMEN
What's changed - Opus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with `/model` - Re-introduced the "ultrathink" keyword to enable high effort for the nex
Descripción Detallada
What's changed - Opus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with `/model` - Re-introduced the "ultrathink" keyword to enable high effort for the next turn - Removed Opus 4 and 4.1 from Claude Code on the first-party API — users with these models pinned are automatically moved to Opus 4.6
Actualización de Claude Code que cambia el modelo por defecto y elimina versiones anteriores.
- Opus 4.6 ahora es el modelo por defecto para suscriptores Max y Team, con esfuerzo medio.
- Se reintrodujo la palabra clave 'ultrathink' para alto esfuerzo en la siguiente interacción.
- Se eliminaron Opus 4 y 4.1 del API, migrando automáticamente a los usuarios a Opus 4.6.
A quién le importa
Solo si usas versiones anteriores de Opus o necesitas ajustar el esfuerzo del modelo.
Generado por IA · puede contener errores
Releases Relacionados
LLMS
Claude Code v2.1.179
## What's changed - Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool" - Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172) - Fixed a sandbox `denyR
LLMS
Claude Code v2.1.178
## What's changed - Added `Tool(param:value)` syntax for permission rules to match a tool's input parameters (with `*` wildcard), e.g. `Agent(model:opus)` to block Opus subagents - Skills in nested `.claude/skills` directories now load when working on files there; on a name clash, the nested skill