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
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16
- lemire: AI's real impact on coding is expanding the engineer's 'cognitive radius', not speed — lemire · 2026-11-16