Claude Code v2.1.284 ships Sonnet 5.5, dollar-based spend display, one-shot MCP reconnect
ashwin-ant · ghdev · 2026-09-29
anthropics/claude-code released v2.1.284. Highlights:
- Adds Claude Sonnet 5.5 (claude-sonnet-5-5), now the default Sonnet model on the Anthropic API: 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads
- Auto mode gains a "yes, but ask again next time" option for reads outside working directories
- /usage and the status line now show dollar amounts against the gateway spend limit (e.g. "$271.40 / $500.00 spent this month"), with usedusd/limitusd/period fields
- The /effort slider's keys are rebindable via keybindings., plus a toggleUltracode action
- New /mcp reconnect all retries every failed or unauthenticated MCP server at once
- Claude apps gateway: managed-policy warnings, telemetry forwarding to Google Cloud OTLP, privatekeyjwt certificate auth
- Fixes corrupted response streams leaking raw JSON errors or the word "undefined" into answers
A maintenance release bundling the new model with spend transparency and MCP reliability fixes.
More from coding & agent
- Dagger founder: the Great CI Bottleneck of 2026 is a software problem, not hardware — msharmas · 2026-09-29
- Sonnet 5.5 lands in Factory: early tests show 'High' is the strong default — matanSF · 2026-09-29
- Full Browser Fallout Game Built With Claude Opus 5.5, Zero Texture or Sound Files — chrisfirst · 2026-09-29
- Clixad Bets on Ad-Funded AI Coding Credits Instead of $20/Month Subscriptions — Glass-Interaction972 · 2026-09-29
- Databricks: Opus 5.5 cuts coding costs 20%, GPT-6 Luna is 20x cheaper per task — pwendell · 2026-09-29
- Hindsight: Letting Your Agent Learn Without Breaking Policy — nishithreddy · 2026-09-29