Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All releases Home ←olderv2.1.73 v2.1.75newer→

Claude Code v2.1.74

4 entries read diff v2.1.73 → v2.1.74 Markdown
Find
Pick an entry · j / k steps through
1 entry

Changesopen

#

The changelog for version 2.1.74 is complete. Key highlights include:

  • 6 new features: Context usage analysis system, custom auto-memory directories, AI-generated session titles, /stuck diagnostic skill, session-end hooks timeout config, and assistant-mode auto-backgrounding
  • 12 improvements: Flexible agent model IDs, improved auto-mode description, smarter memory selection, bidirectional text rendering, better command parsing, git submodule auto-init, and more
  • 8 bug fixes: OAuth error normalization, abort controller leaks, argument parsing edge cases, case-insensitive model matching, team cleanup, and system message preservation
  • 3 in-development features: Context collapse (Hawthorn), plugin dependency resolution (Orchid Trellis), and per-message budget persistence
Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.74. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.

  • Added actionable suggestions to /context command — identifies context-heavy tools, memory bloat, and capacity warnings with specific optimization tips
  • Added autoMemoryDirectory setting to configure a custom directory for auto-memory storage
  • Fixed memory leak where streaming API response buffers were not released when the generator was terminated early, causing unbounded RSS growth on the Node.js/npm code path
  • Fixed managed policy ask rules being bypassed by user allow rules or skill allowed-tools
  • Fixed full model IDs (e.g., claude-opus-4-5) being silently ignored in agent frontmatter model: field and --agents JSON config — agents now accept the same model values as --model
  • Fixed MCP OAuth authentication hanging when the callback port is already in use
  • Fixed MCP OAuth refresh never prompting for re-auth after the refresh token expires, for OAuth servers that return errors with HTTP 200 (e.g. Slack)
  • Fixed voice mode silently failing on the macOS native binary for users whose terminal had never been granted microphone permission — the binary now includes the audio-input entitlement so macOS prompts correctly
  • Fixed SessionEnd hooks being killed after 1.5 s on exit regardless of hook.timeout — now configurable via CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS
  • Fixed /plugin install failing inside the REPL for marketplace plugins with local sources
  • Fixed marketplace update not syncing git submodules — plugin sources in submodules no longer break after update
  • Fixed unknown slash commands with arguments silently dropping input — now shows your input as a warning
  • Fixed Hebrew, Arabic, and other RTL text not rendering correctly in Windows Terminal, conhost, and VS Code integrated terminal
  • Fixed LSP servers not working on Windows due to malformed file URIs
  • Changed --plugin-dir so local dev copies now override installed marketplace plugins with the same name (unless that plugin is force-enabled by managed settings)
  • [VSCode] Fixed delete button not working for Untitled sessions
  • [VSCode] Improved scroll wheel responsiveness in the integrated terminal with terminal-aware acceleration
Read it on GitHub →
System prompt

The system prompt was not captured for this release, so this page cannot say whether it moved.

Which releases were captured →