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 ←olderv2.1.45 v2.1.48newer→

Claude Code v2.1.47

20 entries read diff v2.1.45 → v2.1.47 Markdown

This release introduces Remote Control (/remote-control), enabling access to CLI sessions from claude.ai/code or the Claude app. It adds a new --thinking flag with adaptive thinking support for Opus 4.6+, enhanced dangerous command warnings with detailed notes, and the ability to kill background agents via ctrl+f. Plugin security improvements include automatic flagging of delisted plugins.

Find
Pick an entry · j / k steps through
16 entries

Changesopen

Remote Control#

What

Access your CLI session from the web (claude.ai/code) or the Claude app, continuing conversations across devices.

Usage
/remote-control
Details
  • Opens a secure connection to claude.ai
  • Shows "Remote Control active" status in the CLI
  • Reconnects automatically if connection drops
  • Run /remote-control again to disconnect remote access
  • Can be enabled for all sessions or just the current session
Evidence

Remote Control UI and SSETransport infrastructure (search for "/remote-control", "Remote Control lets you access")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Adaptive Thinking with --thinking Flag#

What

New --thinking flag provides semantic control over Claude's thinking/reasoning behavior, replacing the deprecated --max-thinking-tokens.

Usage
claude --thinking enabled   # Claude decides when and how much to think
claude --thinking disabled  # No extended thinking
claude --thinking 10000     # Fixed thinking token budget (older models)
Details
  • For Opus 4.6+, adaptive mode lets Claude autonomously decide thinking depth
  • Takes precedence over the deprecated maxThinkingTokens setting
  • The old --max-thinking-tokens flag is now deprecated with guidance to use --thinking instead
Evidence

Thinking mode options (search for "--thinking <mode>", "Claude decides when and how much to think (Opus 4.6+)")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Kill Background Agents#

What

Quickly terminate all running background agents with a keyboard shortcut.

Usage
  • Press ctrl+f once to open search
  • Press ctrl+f again to kill all background agents
Details
  • New chat:killAgents action bound to double ctrl+f
  • Shows "All background agents killed" confirmation
  • Also available via text commands: "kill agents", "kill all agents"
Evidence

Agent termination system (search for "All background agents killed", "chat:killAgents")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

SSH Connection Configuration#

What

Pre-configured SSH connections for remote environments, typically set by enterprise administrators.

Details
  • New sshConfigs setting for managed settings
  • Supports configuration of:
  • SSH host (user@hostname or alias from ~/.ssh/config)
  • SSH port (default: 22)
  • Display name for the connection
  • Path to SSH identity file (private key)
  • Unique identifier for matching configs across settings sources
Evidence

SSH config schema (search for "SSH connection configurations for remote environments")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Enhanced Dangerous Command Warnings#

What

Bash commands that may have destructive effects now show detailed warning notes explaining the potential impact.

Details
  • New warning notes for potentially dangerous commands:
  • Note: may delete Kubernetes resources
  • Note: may delete all rows from a database table
  • Note: may destroy Terraform infrastructure
  • Note: may discard all working tree changes
  • Note: may discard uncommitted changes
  • Note: may drop or truncate database objects
  • Note: may force-delete a branch
  • Note: may force-remove files
  • Note: may overwrite remote history
  • Note: may permanently delete untracked files
  • Note: may permanently remove stashed changes
  • Note: may recursively force-remove files
  • Note: may rewrite the last commit
  • Note: may skip safety hooks
  • Blocked commands show "Permission for this action was denied by the dangerous action safety classifier"
Evidence

Warning note strings (search for "Note: may delete", "dangerous action safety classifier")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Plugin Security System#

What

Automatic detection and handling of security-flagged plugins from the official marketplace.

Details
  • Fetches security messages from https://raw.githubusercontent.com/anthropics/claude-plugins-official/refs/heads/security/security.json
  • Auto-uninstalls delisted plugins when autoUninstallDelisted is enabled
  • Shows "Plugins flagged. Check /plugins" notification
  • New blocklist.json and flagged-plugins.json files for tracking
  • "Removed from marketplace" indicator with optional reason
Evidence

Plugin security infrastructure (search for "Fetching plugin security messages", "flagged-plugins.json")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

Version Manager Detection#

What

Automatic detection and logging of asdf and mise version manager installations.

Details
  • Logs "Detected asdf installation:" when asdf is found
  • Logs "Detected mise installation:" when mise is found
  • Helps diagnose shell environment issues
Evidence

Version manager detection (search for "Detected asdf installation")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

Plugin Settings from settings.json#

What

Plugins can now load settings from a settings.json file in addition to manifest settings.

Details
  • Looks for settings.json in plugin directory
  • Falls back to manifest settings if not found
  • Settings can specify agent configuration to merge when plugin is enabled
  • Logs which settings source was used
Evidence

Plugin settings loader (search for "Loaded settings from settings.json for plugin")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Improved Fast Mode Status Display#

What

Better messaging when fast mode encounters issues.

Details
  • "Fast mode overloaded and is temporarily unavailable" message
  • Shows reset time: "resets in X"
  • "· Fast mode ON" indicator
Evidence

Fast mode messages (search for "Fast mode overloaded")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

BMP Image Support in Clipboard#

What

Added BMP format support for clipboard image operations on Linux.

Details
  • Now detects image/bmp in clipboard alongside png, jpeg, gif, webp
  • Uses wl-paste --type image/bmp or xclip -selection clipboard -t image/bmp
Evidence

BMP handling (search for "image/bmp")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

Warp Terminal Native Shift+Enter Support#

What

Warp now supports Shift+Enter natively, removing previous workaround messaging.

Details
  • Updated tip: "Note: iTerm2, WezTerm, Ghostty, Kitty, and Warp support Shift+Enter natively."
  • Removed previous warnings about Warp not supporting custom Shift+Enter keybindings
  • Warp removed from the list of terminals requiring manual configuration
Evidence

Terminal compatibility notes (search for "Warp support Shift+Enter natively")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

Improved /rename Behavior Setting#

What

New setting to control whether /rename updates the terminal tab title.

Details
  • Setting: "Whether /rename updates the terminal tab title (defaults to true)"
  • Set to false to keep auto-generated topic titles
  • Replaces the previous inverse setting behavior
Evidence

Rename setting (search for "Whether /rename updates the terminal tab title")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

Permission Validation Improvements#

What

Invalid permission rules in configuration files are now validated and skipped with warnings.

Details
  • Non-string values in permission arrays are removed with warning
  • Invalid permission rules show specific error messages
  • Logs which file and path contained the invalid rule
Evidence

Permission validation (search for "Invalid permission rule", "was skipped")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Agent Worktree Cleanup#

What

Better management and cleanup of git worktrees created by agents.

Details
  • Detects when agent worktree has uncommitted changes: "Agent worktree has changes, keeping:"
  • Logs worktree removal: "Removed agent worktree at:"
  • Handles branch cleanup failures gracefully
Evidence

Worktree management (search for "Agent worktree has changes", "worktreePath:")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

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

In-Process Chrome MCP Server#

What

Chrome browser automation MCP server can now run in-process for better performance.

Details
  • Logs "In-process Chrome MCP server started" when initialized
  • Uses new SSE transport infrastructure
  • Cleaner shutdown handling
Evidence

Chrome MCP server (search for "In-process Chrome MCP server started")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Pure JavaScript Path Conversion on Windows#

What

Windows path conversion (Unix ↔ Windows) is now done in pure JavaScript, removing the dependency on cygpath.

Details
  • Handles /cygdrive/ prefix conversion
  • Converts forward/backslashes appropriately
  • Works with UNC paths (starting with // or \\)
Evidence

Path conversion logic (search for "/cygdrive/")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

1 entry

Bug Fixesopen

#

  • Fixed backslash-escaped whitespace warning for commands that could alter command parsing (search for "Command contains backslash-escaped whitespace")
  • Fixed plugin hooks reload to only trigger on actual enabledPlugins changes, not all policySettings changes (search for "Plugin hooks: skipping reload, enabledPlugins unchanged")
  • Fixed hook file reading errors to log properly: "Failed to read hook file" (search for "Failed to read hook file")
  • Added validation for parent directory existence: "Parent directory does not exist or is not accessible:" (search for "Parent directory does not exist")
1 entry

Notesopen

#

Deprecation: The --max-thinking-tokens flag is deprecated. Use --thinking <mode> instead for newer models. The flag still works for backward compatibility.

Removed Features: Delegate Mode infrastructure has been removed. References to TeammateTool, delegate mode, and team coordination are no longer present in the codebase.

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.47. 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.

  • Fixed FileWriteTool line counting to preserve intentional trailing blank lines instead of stripping them with trimEnd().
  • Fixed Windows terminal rendering bugs caused by os.EOL (\r\n) in display code — line counts now show correct values instead of always showing 1 on Windows.
  • Improved VS Code plan preview: auto-updates as Claude iterates, enables commenting only when the plan is ready for review, and keeps the preview open when rejecting so Claude can revise.
  • Fixed a bug where bold and colored text in markdown output could shift to the wrong characters on Windows due to \r\n line endings.
  • Fixed compaction failing when conversation contains many PDF documents by stripping document blocks alongside images before sending to the compaction API (anthropics/claude-code#26188)
  • Improved memory usage in long-running sessions by releasing API stream buffers, agent context, and skill state after use
  • Improved startup performance by deferring SessionStart hook execution, reducing time-to-interactive by ~500ms.
  • Fixed an issue where bash tool output was silently discarded on Windows when using MSYS2 or Cygwin shells.
  • Improved performance of @ file mentions - file suggestions now appear faster by pre-warming the index on startup and using session-based caching with background refresh.
  • Improved memory usage by trimming agent task message history after tasks complete
  • Improved memory usage during long agent sessions by eliminating O(n²) message accumulation in progress updates
  • Fixed the bash permission classifier to validate that returned match descriptions correspond to actual input rules, preventing hallucinated descriptions from incorrectly granting permissions
  • Fixed user-defined agents only loading one file on NFS/FUSE filesystems that report zero inodes (anthropics/claude-code#26044)
  • Fixed plugin agent skills silently failing to load when referenced by bare name instead of fully-qualified plugin name (anthropics/claude-code#25834)
  • Search patterns in collapsed tool results are now displayed in quotes for clarity
  • Windows: Fixed CWD tracking temp files never being cleaned up, causing them to accumulate indefinitely (anthropics/claude-code#17600)
  • Use ctrl+f to kill all background agents instead of double-pressing ESC. Background agents now continue running when you press ESC to cancel the main thread, giving you more control over agent lifecycle.
  • Fixed API 400 errors ("thinking blocks cannot be modified") that occurred in sessions with concurrent agents, caused by interleaved streaming content blocks preventing proper message merging.
  • Simplified teammate navigation to use only Shift+Down (with wrapping) instead of both Shift+Up and Shift+Down.
  • Fixed an issue where a single file write/edit error would abort all other parallel file write/edit operations. Independent file mutations now complete even when a sibling fails.
  • Added last_assistant_message field to Stop and SubagentStop hook inputs, providing the final assistant response text so hooks can access it without parsing transcript files.
  • Fixed custom session titles set via /rename being lost after resuming a conversation (anthropics/claude-code#23610)
  • Fixed collapsed read/search hint text overflowing on narrow terminals by truncating from the start.
  • Fixed an issue where bash commands with backslash-newline continuation lines (e.g., long commands split across multiple lines with \) would produce spurious empty arguments, potentially breaking command execution.
  • Fixed built-in slash commands (/help, /model, /compact, etc.) being hidden from the autocomplete dropdown when many user skills are installed (anthropics/claude-code#22020)
  • Fixed MCP servers not appearing in the MCP Management Dialog after deferred loading
  • Fixed session name persisting in status bar after /clear command (anthropics/claude-code#26082)
  • Fixed crash when a skill's name or description in SKILL.md frontmatter is a bare number (e.g., name: 3000) — the value is now properly coerced to a string (anthropics/claude-code#25837)
  • Fixed /resume silently dropping sessions when the first message exceeds 16KB or uses array-format content (anthropics/claude-code#25721)
  • Added chat:newline keybinding action for configurable multi-line input (anthropics/claude-code#26075)
  • Added added_dirs to the statusline JSON workspace section, exposing directories added via /add-dir to external scripts (anthropics/claude-code#26096)
  • Fixed claude doctor misclassifying mise and asdf-managed installations as native installs (anthropics/claude-code#26033)
  • Fixed zsh heredoc failing with "read-only file system" error in sandboxed commands (anthropics/claude-code#25990)
  • Fixed agent progress indicator showing inflated tool use count (anthropics/claude-code#26023)
  • Fixed image pasting not working on WSL2 systems where Windows copies images as BMP format (anthropics/claude-code#25935)
  • Fixed background agent results returning raw transcript data instead of the agent's final answer (anthropics/claude-code#26012)
  • Fixed Warp terminal incorrectly prompting for Shift+Enter setup when it supports it natively (anthropics/claude-code#25957)
  • Fixed CJK wide characters causing misaligned timestamps and layout elements in the TUI (anthropics/claude-code#26084)
  • Fixed custom agent model field in .claude/agents/*.md being ignored when spawning team teammates (anthropics/claude-code#26064)
  • Fixed plan mode being lost after context compaction, causing the model to switch from planning to implementation mode (anthropics/claude-code#26061)
  • Fixed alwaysThinkingEnabled: true in settings.json not enabling thinking mode on Bedrock and Vertex providers (anthropics/claude-code#26074)
  • Fixed tool_decision OTel telemetry event not being emitted in headless/SDK mode (anthropics/claude-code#26059)
  • Fixed session name being lost after context compaction — renamed sessions now preserve their custom title through compaction (anthropics/claude-code#26121)
  • Increased initial session count in resume picker from 10 to 50 for faster session discovery (anthropics/claude-code#26123)
  • Windows: fixed worktree session matching when drive letter casing differs (anthropics/claude-code#26123)
  • Fixed /resume <session-id> failing to find sessions whose first message exceeds 16KB (anthropics/claude-code#25920)
  • Fixed "Always allow" on multiline bash commands creating invalid permission patterns that corrupt settings (anthropics/claude-code#25909)
  • Fixed React crash (error #31) when a skill's argument-hint in SKILL.md frontmatter uses YAML sequence syntax (e.g., [topic: foo | bar]) — the value is now properly coerced to a string (anthropics/claude-code#25826)
  • Fixed crash when using /fork on sessions that used web search — null entries in search results from transcript deserialization are now handled gracefully (anthropics/claude-code#25811)
  • Fixed read-only git commands triggering FSEvents file watcher loops on macOS by adding --no-optional-locks flag (anthropics/claude-code#25750)
  • Fixed custom agents and skills not being discovered when running from a git worktree — project-level .claude/agents/ and .claude/skills/ from the main repository are now included (anthropics/claude-code#25816)
  • Fixed non-interactive subcommands like claude doctor and claude plugin validate being blocked inside nested Claude sessions (anthropics/claude-code#25803)
  • Windows: Fixed the same CLAUDE.md file being loaded twice when drive letter casing differs between paths (anthropics/claude-code#25756)
  • Fixed inline code spans in markdown being incorrectly parsed as bash commands (anthropics/claude-code#25792)
  • Fixed teammate spinners not respecting custom spinnerVerbs from settings (anthropics/claude-code#25748)
  • Fixed shell commands permanently failing after a command deletes its own working directory (anthropics/claude-code#26136)
  • Fixed hooks (PreToolUse, PostToolUse) silently failing to execute on Windows by using Git Bash instead of cmd.exe (anthropics/claude-code#25981)
  • Fixed LSP findReferences and other location-based operations returning results from gitignored files (e.g., node_modules/, venv/) (anthropics/claude-code#26051)
  • Moved config backup files from home directory root to ~/.claude/backups/ to reduce home directory clutter (anthropics/claude-code#26130)
  • Fixed sessions with large first prompts (>16KB) disappearing from the /resume list (anthropics/claude-code#26140)
  • Fixed shell functions with double-underscore prefixes (e.g., __git_ps1) not being preserved across shell sessions (anthropics/claude-code#25824)
  • Fixed spinner showing "0 tokens" counter before any tokens have been received (anthropics/claude-code#26105)
  • VSCode: Fixed conversation messages appearing dimmed while the AskUserQuestion dialog is open (anthropics/claude-code#26078)
  • Fixed background tasks failing in git worktrees due to remote URL resolution reading from worktree-specific gitdir instead of the main repository config (anthropics/claude-code#26065)
  • Fixed Right Alt key leaving visible [25~ escape sequence residue in the input field on Windows/Git Bash terminals (anthropics/claude-code#25943)
  • The /rename command now updates the terminal tab title by default (anthropics/claude-code#25789)
  • Fixed Edit tool silently corrupting Unicode curly quotes (\u201c\u201d \u2018\u2019) by replacing them with straight quotes when making edits (anthropics/claude-code#26141)
  • Fixed OSC 8 hyperlinks only being clickable on the first line when link text wraps across multiple terminal lines.
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 →