Claude Code v2.1.212: /fork Becomes Background Session Copy + Runaway Loop Guards
Anthropic shipped Claude Code v2.1.212 with a behavioral change to /fork and new safeguards against runaway search and delegation loops. Here are the details.
Key Changes
- /fork now copies your conversation into a new background session (appears as its own row in
claude agents). The old behavior — launching an in-session subagent — is now/subtask. - Auto-mode reset:
claude auto-mode resetrestores the default auto-mode configuration. Use--yesto skip the confirmation prompt. - WebSearch limit: New session-wide cap of 200 WebSearch tool calls (default). Tune via
CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION. - Subagent cap: Per-session limit of 200 subagent spawns. Override with
CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION. Running/clearresets the budget. - MCP auto-background: MCP tool calls exceeding 2 minutes automatically move to the background. Configure the threshold (in ms) or disable via
CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS. - Improved
/resume: Typing/resumein the agent view opens a picker of past sessions — including deleted ones — and resumes your pick as a background session.
Notable Fixes
- Plan mode no longer auto-runs file-modifying bash commands (e.g.,
touch,rm) without permission prompt or SDKcanUseToolcallback. - Fixed worktree creation following a repository-committed symlink at
.claude/worktreesthat could create files outside the repository. - SIGTERM during a running Bash tool in print/SDK mode now aborts the turn, kills the process tree, and exits with code 143.
- Windows fix:
/backgroundandclaude --bgno longer fail when Group Policy blocks PowerShell 5.1; the daemon now prefers PowerShell 7. - Shell mode (
!) now executes commands containing file paths even while the path autocomplete popup is open. /ultrareviewnow accepts PR references like#123,PR 123, and pasted URLs; error hints name the command you typed. It also fetches branches from origin and suggests closest branch name on typos.- Hosted sessions no longer fail at startup when repository settings configure mTLS certs, extra CA bundles, or OAuth scopes — these transport settings are now ignored with a warning.
- Fixed diff previews losing line numbers and +/- markers in narrow layouts.
- Fixed false
"Command timed out"on exit code 143.
Full details in the release notes.
📖 Read the full source: GitHub Claude-Code
👀 See Also
OpenAI's Pentagon Contract Terms Allow 'Any Lawful Use' Including Potential Surveillance
OpenAI negotiated new terms with the Pentagon that include the phrase 'any lawful use,' which sources say allows the military to use OpenAI's technology for mass surveillance programs if they're technically legal. Anthropic was blacklisted for refusing to budge on two red lines: no mass surveillance of Americans and no lethal autonomous weapons.
Why Every Client Wants a Chatbot Now (And Why It's the New Carousel)
A developer chronicles the trend of clients demanding AI chatbots on websites, despite admitting they close them immediately — parallels to the carousel era.
CEOs Report Minimal AI Impact on Productivity and Employment in Recent Study
A study of 6,000 executives found 90% reported no AI impact on employment or productivity over three years, with average AI usage at 1.5 hours per week. Economists compare this to Solow's productivity paradox from the 1980s IT era.
ThermoQA: Open Benchmark for Engineering Thermodynamics Tests LLMs on 293 Calculation Problems
ThermoQA is an open benchmark with 293 engineering thermodynamics problems across three tiers, testing LLMs on exact numerical calculations. Claude Opus 4.6 leads with 94.1% composite score, while DeepSeek-R1 shows highest run-to-run variance at ±2.5%.