Claude Code bug: automatic git reset destroys uncommitted changes every 10 minutes

Bug Details
Claude Code performs git fetch origin + git reset --hard origin/main on the user's project repository every 10 minutes via programmatic git operations (no external git binary spawned). This silently destroys all uncommitted changes to tracked files. Untracked files survive, and git worktrees are immune to this behavior.
Environment and Evidence
Affected version: Claude Code 2.1.87 (Homebrew cask, compiled Bun binary)
OS: macOS 15.4 (Darwin 25.3.0, arm64)
Evidence from investigation:
- Git reflog shows 95+ entries at exact 10-minute intervals with entries like
reset: moving to origin/main - Live reproduction confirmed modified tracked files are silently reverted at the 10-minute mark
fswatchcaptured the file operations pattern matching git fetch + reset- Only the Claude Code CLI process (PID 70111,
claude --dangerously-skip-permissions) was found with CWD in the affected repo - No external git processes spawned - operations are programmatic within Claude Code (likely libgit2)
Technical Analysis
Binary analysis of the compiled binary at /opt/homebrew/Caskroom/claude-code/2.1.87/claude revealed:
hg1()function does["fetch","origin"]viat_(C8(), _)without explicit CWD, defaulting toprocess.cwd()io1()function is a git pull wrapper logginggit pull: cwd=${H} ref=${_??"default"}fileHistorystate tracks{snapshots: [], trackedFiles: new Set, snapshotSequence: 0}
What Was Ruled Out
The investigation eliminated: git hooks, Claude Code user hooks, plugin marketplace updater, macOS cloud sync (iCloud, Dropbox, Syncthing, Synology, Google Drive), cron/LaunchAgents, Vite/SvelteKit dev servers, IDEs/editors, Time Machine, and external file watchers.
📖 Read the full source: HN AI Agents
👀 See Also

Claude Code v2.1.77 Release: Token Limits, Sandbox Controls, and Bug Fixes
Claude Code v2.1.77 increases default maximum output token limits for Claude Opus 4.6 to 64k tokens and adds an allowRead sandbox filesystem setting. The release includes over 30 fixes for issues ranging from memory management to terminal UI behavior.

Alibaba Launches Wukong AI Platform for Enterprise Automation
Alibaba has launched Wukong, an AI platform that coordinates multiple agents to handle complex business tasks like document editing, spreadsheet updates, meeting transcription, and research. It's currently in invitation-only beta testing.
The Mundane Risk: Why AI Safety's Biggest Threats Are Boring, Not Dramatic
An essay argues that mundane AI failures are already causing damage at scale, current alignment approaches depend too heavily on sandboxed environments, and capability convergence makes accidental open-world exposure increasingly plausible.

Google Chrome Silently Downloads 4GB Gemini Nano Model Without Consent
Chrome automatically downloads a 4GB Gemini Nano model (weights.bin) to user devices without consent or opt-out, and re-downloads it if deleted. This raises legal (ePrivacy/GDPR) and environmental concerns at Chrome's billion-device scale.