Claude Code 2.1.74 patches memory, OAuth stalls

// 74d agoPRODUCT UPDATE

Claude Code 2.1.74 patches memory, OAuth stalls

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

Anthropic shipped back-to-back Claude Code v2.1.73 and v2.1.74 updates focused on reliability, memory handling, and workflow controls. The latest release fixes unbounded Node.js RSS growth, MCP OAuth hangs/refresh edge cases, model override handling, and multiple VS Code and CLI regressions.

// ANALYSIS

This is a high-signal stability release that matters more than flashy features for teams running Claude Code daily.

–The memory leak fix targets generator cleanup on streaming responses, addressing long-session RAM blowups that can cripple CLI workflows.
–MCP OAuth fixes remove a painful auth deadlock class (port conflicts and silent refresh failures), which should reduce brittle enterprise integrations.
–`/context` suggestions and `autoMemoryDirectory` add practical control over context bloat and memory persistence, improving repeatability across large codebases.
–VS Code and Windows fixes (terminal rendering, LSP URI handling, session UI bugs) show continued hardening beyond the core CLI path.

// TAGS

claude-codeai-codingclidevtoolmcpopen-source

DISCOVERED

74d ago

2026-03-14

PUBLISHED

74d ago

2026-03-14

RELEVANCE

9/ 10

AUTHOR

DIY Smart Code

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE1h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE2h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE5h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.