← Back to all releases

v2.1.3 Claude Code Release Notes

Claude's Analysisby Sonnet 4.6
Full Analysis

New /config release-channel toggle and /doctor permission warnings land alongside sub-agent model fixes and hook timeout bumped from 60s to 10 minutes.

Changes
13
Total Changes (vs Average)
0.6×
Version Type
Patch
Release Focus
Mixed
Day Since Prior Release
1
Release # This Month
#5 of 26
Bug Fix Ratio
46%
Post-Release Edits
—
How does this release compare? Release pace, fix share and issue trends since April 2025.See all-time statistics
Change Category
Ecosystem Impact
Plugins/Skills appears in 5 of the last 10 releases; this version's command/skills unification marks a conceptual consolidation of that sustained focus. Terminals also at 5 of 10, with continued rendering and cursor-state stability improvements.
Key Themes
2New /config and /doctor Commands|2Sub-Agent Model Selection Fixed|2Hooks Get More Room to Run|2Slash Commands and Skills Unified|1VS Code: Permission Destination Control
May Help If You've Noticed
Sub-agents run the wrong model during long conversations or when using web search
Tool hooks time out before finishing builds, tests, or other slow operations
Hooks don't seem to activate even after you accepted the trust dialog
You're unsure whether to update immediately or stay on a stable release channel
Permission settings accidentally apply globally when you only wanted project-level scope

Changes in Claude Code v2.1.3

Added3 changes

  • •Added release channel (stable or latest) toggle to /config
  • •Added detection and warnings for unreachable permission rules, with warnings in /doctor and after saving rules that include the source of each rule and actionable fix guidance
  • •[VSCode] Added clickable destination selector for permission requests, allowing you to choose where settings are saved (this project, all projects, shared with team, or session only)

Improved2 changes

  • •Improved terminal rendering stability by preventing uncontrolled writes from corrupting cursor state
  • •Improved slash command suggestion readability by truncating long descriptions to 2 lines

Fixed6 changes

  • •Fixed plan files persisting across /clear commands, now ensuring a fresh plan file is used after clearing a conversation
  • •Fixed false skill duplicate detection on filesystems with large inodes (e.g., ExFAT) by using 64-bit precision for inode values
  • •Fixed mismatch between background task count in status bar and items shown in tasks dialog
  • •Fixed sub-agents using the wrong model during conversation compaction
  • •Fixed web search in sub-agents using incorrect model
  • •Fixed trust dialog acceptance when running from the home directory not enabling trust-requiring features like hooks during the session

Changed2 changes

  • •Merged slash commands and skills, simplifying the mental model with no change in behavior
  • •Changed tool hook execution timeout from 60 seconds to 10 minutes