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 olderv2.1.48 v2.1.50newer

Claude Code v2.1.49

1 entries read diff v2.1.48 → v2.1.49 Markdown

This is a minor maintenance release that temporarily disables HTTP hooks functionality. Users who have configured HTTP hooks in their Claude Code settings will see those hooks return "not yet supported" instead of executing. Bash hooks remain fully functional.

Find
Pick an entry · j / k steps through
1 entry

Changesopen

HTTP Hooks Temporarily Disabled#

What

HTTP hooks defined in your configuration will no longer execute. Instead, they return immediately with a "HTTP hooks are not yet supported" message.

Impact:

  • If you have configured HTTP hooks (using type: "http" in your hooks configuration), they will not execute in this version
  • The hook will be skipped rather than failing the operation—your workflow will continue without the HTTP call
  • Bash hooks (type: "bash") continue to work normally

Example log output when an HTTP hook is encountered:

Hooks: skipping HTTP hook https://example.com/hook — HTTP hooks are not yet supported

Workaround: If you rely on HTTP hooks, you can convert them to bash hooks that use curl to make the HTTP request:

{
  "type": "bash",
  "command": "curl -X POST -H 'Content-Type: application/json' -d '$HOOK_PAYLOAD' https://example.com/hook"
}
Evidence

Hook execution skips HTTP hooks with message (search for "HTTP hooks are not yet supported")

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

1 entry

Notesopen

#

This appears to be a temporary change—the HTTP hook schema and configuration parsing remain intact, only the execution is disabled. The previous implementation supported POST requests with configurable headers and environment variable substitution in header values. This functionality may return in a future release once stability or security concerns are addressed.

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.49. 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.

  • Improved MCP OAuth authentication with step-up auth support and discovery caching, reducing redundant network requests during server connections
  • Added --worktree (-w) flag to start Claude in an isolated git worktree
  • Subagents support isolation: "worktree" for working in a temporary git worktree
  • Added Ctrl+F keybinding to kill background agents (two-press confirmation)
  • Agent definitions support background: true to always run as a background task
  • Plugins can ship settings.json for default configuration
  • Fixed file-not-found errors to suggest corrected paths when the model drops the repo folder
  • Fixed Ctrl+C and ESC being silently ignored when background agents are running and the main thread is idle. Pressing twice within 3 seconds now kills all background agents.
  • Fixed prompt suggestion cache regression that reduced cache hit rates.
  • Fixed plugin enable and plugin disable to auto-detect the correct scope when --scope is not specified, instead of always defaulting to user scope
  • Simple mode (CLAUDE_CODE_SIMPLE) now includes the file edit tool in addition to the Bash tool, allowing direct file editing in simple mode.
  • Permission suggestions are now populated when safety checks trigger an ask response, enabling SDK consumers to display permission options
  • Sonnet 4.5 with 1M context is being removed from the Max plan in favor of our frontier Sonnet 4.6 model, which now has 1M context. Please switch in /model.
  • Fixed verbose mode not updating thinking block display when toggled via /config — memo comparators now correctly detect verbose changes
  • Fixed unbounded WASM memory growth during long sessions by periodically resetting the tree-sitter parser
  • Fixed potential rendering issues caused by stale yoga layout references
  • Improved performance in non-interactive mode (-p) by skipping unnecessary API calls during startup
  • Improved performance by caching authentication failures for HTTP and SSE MCP servers, avoiding repeated connection attempts to servers requiring auth
  • Fixed unbounded memory growth during long-running sessions caused by Yoga WASM linear memory never shrinking
  • SDK model info now includes supportsEffort, supportedEffortLevels, and supportsAdaptiveThinking fields so consumers can discover model capabilities.
  • Added ConfigChange hook event that fires when configuration files change during a session, enabling enterprise security auditing and optional blocking of settings changes.
  • Improved startup performance by caching MCP auth failures to avoid redundant connection attempts
  • Improved startup performance by reducing HTTP calls for analytics token counting
  • Improved startup performance by batching MCP tool token counting into a single API call
  • Fixed disableAllHooks setting to respect managed settings hierarchy — non-managed settings can no longer disable managed hooks set by policy (#26637)
  • Fixed --resume session picker showing raw XML tags for sessions that start with commands like /clear. Now correctly falls through to the session ID fallback.
  • Improved permission prompts for path safety and working directory blocks to show the reason for the restriction instead of a bare prompt with no context
System prompt

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