Claude Code v2.1.76
Released Mar 14, 2026 (5 months ago).
⚠ Elevated report volume. This build drew 425 issue reports —
more than double the typical release (160 median). That can mean a regression, or simply
that many users happened to be on this build. Skim the reports below before deciding to upgrade.
425 issues reference this build
8 still open
417 resolved (98%)
"References this build" means the issue body mentions running 2.1.76 (from the
bug-report template). It reflects report volume, not a proven defect count — an issue may mention a
version without being caused by it. First-party data from the anthropics/claude-code tracker.
Top issues reported on v2.1.76
Ranked by community engagement (reactions and comments).
- [BUG] Remote Control: automatic reconnection doesn't work -- connection drops silently with no recovery
- [BUG] "Request too large (max 20MB)" error on small files (99KB PNG)
- [BUG] API Error: Rate limit reached
- [BUG] Skill `model:` frontmatter triggers 429 "Extra usage required" on 2.1.76 when session uses opus[1m]
- [BUG] Terminal scrolls to top during agent execution (Windows Terminal + PowerShell)
- Scroll position resets to top of session while processing
- [Bug] Scroll position resets to top during agent execution
- [BUG] Opus 4.6 with 1M context is not available on Max 5x plan
- [BUG] Slash commands with Skill() in allowed-tools trigger rate limit on minimal diffs (regression)
- [Bug][Urgent] Claude Code API responses extremely slow with Claude 4.6 Sonnet/Opus (5+ minute latency)
- [Bug] Anthropic API Error: Internal Server Error (500)
- PreToolUse/PostToolUse hooks do not fire for subagent (Agent tool) tool calls
- [BUG] [1M] Opus 4.6 1M context unavailable on Max 5x — works on another machine with same account
- Tool output is fully expanded by default and the collapse toggle (▸) is non-functional
- Image processing failure silently passes oversized images into context, bricking sessions
- [BUG] Agent Teams teammates lose [1m] context window suffix — root cause: tmux spawn hardcodes model without variant
- [BUG] Agent Teams: teammates intermittently stop receiving SendMessage after extended polling (default mode, not tmux)
- [MODEL] Explore subagent system prompt has contradictory instructions for Bash vs built-in tool usage
- [BUG] Rate limit reached without any usage spent
- [BUG] Slack MCP plugin fails with invalid_scope during OAuth
- [BUG] API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"},"request_id"
- [BUG] Agent/Explore subagent crashes with "Cannot read properties of undefined (reading 'input_tokens')"
- [BUG] Worktree branches created by Claude track origin/main as upstream
- WebFetch summarizer emits <system-reminder> blocks in tool output, violating harness trust boundary
- [Bug] Session feedback prompt conflicts with numbered list selections
- [BUG] ~20 sessions lost, only 11 survived - 2 months of work I paid for - gone
- [Bug] Anthropic API Error: Internal Server Error (500)
- context: fork and agent frontmatter silently ignored for plugin-loaded skills
- [BUG] I cannot enter oauth token
- Tool calls (WebFetch) can hang indefinitely with no timeout, causing permanent process stall
Changelog
What's changed
- Added MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL)
- Added new
ElicitationandElicitationResulthooks to intercept and override responses before they're sent back - Added
-n/--name <name>CLI flag to set a display name for the session at startup - Added
worktree.sparsePathssetting forclaude --worktreein large monorepos to check out only the directories you need via git sparse-checkout - Added
PostCompacthook that fires after compaction completes - Added
/effortslash command to set model effort level - Added session quality survey — enterprise admins can configure the sample rate via the
feedbackSurveyRatesetting - Fixed deferred tools (loaded via
ToolSearch) losing their input schemas after conversation compaction, causing array and number parameters to be rejected with type errors - Fixed slash commands showing "Unknown skill"
- Fixed plan mode asking for re-approval after the plan was already accepted
- Fixed voice mode swallowing keypresses while a permission dialog or plan editor was open
- Fixed
/voicenot working on Windows when installed via npm - Fixed spurious "Context limit reached" when invoking a skill with
model:frontmatter on a 1M-context session - Fixed "adaptive thinking is not supported on this model" error when using non-standard model strings
- Fixed
Bash(cmd:*)permission rules not matching when a quoted argument contains# - Fixed "don't ask again" in the Bash permission dialog showing the full raw command for pipes and compound commands
- Fixed auto-compaction retrying indefinitely after consecutive failures — a circuit breaker now stops after 3 attempts
- Fixed MCP reconnect spinner persisting after successful reconnection
- Fixed LSP plugins not registering servers when the LSP Manager initialized before marketplaces were reconciled
- Fixed clipboard copying in tmux over SSH — now attempts both direct terminal write and tmux clipboard integration
- Fixed
/exportshowing only the filename instead of the full file path in the success message - Fixed transcript not auto-scrolling to new messages after selecting text
- Fixed Escape key not working to exit the login method selection screen
- Fixed several Remote Control issues: sessions silently dying when the server reaps an idle environment, rapid messages being queued one-at-a-time instead of batched, and stale work items causing redelivery after JWT refresh
- Fixed bridge sessions failing to recover after extended WebSocket disconnects
- Fixed slash commands not found when typing the exact name of a soft-hidden command
- Improved
--worktreestartup performance by reading git refs directly and skipping redundantgit fetchwhen the remote branch is already available locally - Improved background agent behavior — killing a background agent now preserves its partial results in the conversation context
- Improved model fallback notifications — now always visible instead of hidden behind verbose mode, with human-friendly model names
- Improved blockquote readability on dark terminal themes — text is now italic with a left bar instead of dim
- Improved stale worktree cleanup — worktrees left behind after an interrupted parallel run are now automatically cleaned up
- Improved Remote Control session titles — now derived from your first prompt instead of showing "Interactive session"
- Improved
/voiceto show your dictation language on enable and warn when yourlanguagesetting isn't supported for voice input - Updated
--plugin-dirto only accept one path to support subcommands — use repeated--plugin-dirfor multiple directories - [VSCode] Fixed gitignore patterns containing commas silently excluding entire filetypes from the @-mention file picker