Claude Code 2.1.307 emits an OpenTelemetry event each time a safety layer stops, prompts or sends back a tool call
For the first time, an agent's blocked actions can flow into your own monitoring. What's new, plus a fix to how MCP calls are retried.
// Key points
- New claude_code.safety_event fires for each tool call that a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back.
- New /claude-api api-version moves Claude API code to API version 2026-10-21.
- Unparseable tool calls are retried up to twice before the turn ends with an error.
- Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; only read-only or idempotent tools are now retried.
Builder's takeBuilding on the OpenTelemetry export that entered beta on October 14, I'd count safety_event by rule: a rule that prompts constantly is too tight, one that never fires may be doing nothing, which is the same point as my post on scaling agent autonomy with reversibility. If you run your own MCP server, like the one behind AI Interview, make write tools idempotent or mark them clearly instead of relying on the client to deduplicate.
// Background · from #Coding agents
Full timeline →- Oct 22 GitHub CLI v2.103.0 can use expiring, auto-refreshing OAuth tokens, so a leaked token stops working within hours
- Oct 21 GitHub package firewall enters public preview, screening npm traffic between coding agents, CI and the registry
- Oct 21 Cloudflare and VoidZero introduce tsrs, a Rust port of the TypeScript compiler up to 8x faster than TypeScript 7.0 with about 70% less memory