Source Intelligence

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 olderv1.0.58 v1.0.60newer

Claude Code v1.0.59

6 entries read diff v1.0.58 → v1.0.59 Markdown
Find
Pick an entry · j / k steps through
6 entries

Changesopen

New Features#

Checkpointing System 🆕

Claude Code now automatically saves checkpoints of your work during sessions, providing a safety net for your changes.

  • Automatic checkpoint creation: Claude Code creates incremental snapshots of your codebase as you work
  • Shadow Git repository: Checkpoints are stored in .claude/checkpoints/ using Git for efficient version tracking
  • Opt-out option: Disable checkpointing by setting the environment variable CLAUDE_CODE_DISABLE_CHECKPOINTING
  • Configuration: New checkpointingEnabled setting (enabled by default)

Usage: Checkpoints are created automatically in the background. No user action required.

# To disable checkpointing:
export CLAUDE_CODE_DISABLE_CHECKPOINTING=true
claude

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Improvements#

Performance Optimizations

  • Removed duplicate import statements for Node.js streams
  • Streamlined internal Zod library usage
  • Improved Git operations with core.untrackedcache for better performance

UI Simplification

  • Removed agent color index management system for a cleaner interface
  • Simplified how parallel agents are displayed

Bug Fixes#

  • Fixed internal error handling structures
  • Improved checkpoint initialization error recovery
  • Enhanced configuration validation

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Internal Changes#

  • Added cryptographic utilities for checkpoint directory hashing
  • Updated internal agent management functions
  • Refined memory usage tracking
  • Structural code improvements (98.7% similarity to previous version)

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Configuration#

New configuration option added:

{
  "checkpointingEnabled": true  // Enable/disable checkpoint feature
}

Notes#

  • The checkpointing feature operates transparently in the background
  • Checkpoint data is stored locally in your project's .claude/checkpoints/ directory
  • Each project gets its own unique checkpoint directory based on SHA-256 hash
  • The feature adds minimal overhead to your workflow while providing recovery options

This release focuses on improving reliability and safety with the new checkpointing system while maintaining the familiar Claude Code experience.

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v1.0.59. 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.

  • SDK: Added tool confirmation support with canUseTool callback
  • SDK: Allow specifying env for spawned process
  • Hooks: Exposed PermissionDecision to hooks (including "ask")
  • Hooks: UserPromptSubmit now supports additionalContext in advanced JSON output
  • Fixed issue where some Max users that specified Opus would still see fallback to Sonnet
System prompt

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