Claude Code v2.1.301 Ships Unattended Retry Watchdog, OTel Classifier Tracing and Bug Fixes
ashwin-ant · ghdev · 2026-10-16
anthropics/claude-code released v2.1.301 with notable changes:
- New CLAUDECODERETRYWATCHDOGMAXUSAGELIMITWAITMS so unattended retry mode ends requests when a usage limit reset is too far away
- OpenTelemetry tracing guidance in the claude-api skill, including trace destinations via the ant CLI
- Vim mode % motion for matching brackets; multi-line rows input for mods
- tooldecision OTel events now expose classifierverdict, permissionmode, and classifiercategory
- Fixes: worktree deletion on quit, Fable alias fallback retry, misleading login error on full disk, Grep/Glob false "no matches", workflow agents skipping steps yet reporting success, artifact updates blocked by PreToolUse hooks, and more
More from coding & agent
- Every publishes 8,000-word Codex oral history, agent-native so your AI can dig the raw interviews — danshipper · 2026-10-16
- Developer rebuilds GitHub in 4 days: Keel makes agents declare intent before changing code — threepointone · 2026-10-16
- Stop using small models as judges with overloaded context, dev warns — xeophon · 2026-10-16
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- Monid launches: one balance, pay-per-call access to 1,700+ tools for AI agents — HeyAmit_ · 2026-10-16
- OpenAI publishes Sites tutorial: build and share your first Site — OpenAIDevs · 2026-10-16