Claude Code v2.1.217 adds emoji autocomplete and fixes transcript, Windows update, and MCP bugs
ashwin-ant · ghdev · 2026-07-22
Claude Code v2.1.217 adds prompt-input emoji shortcode autocomplete, transcript-write warnings, and fixes for several reliability and security issues.
Highlights
- Emoji shortcode autocomplete in the prompt box, with a toggle to disable it.
- Better visibility into transcript write failures and disabled session saving.
- Memory leak fix for truncated MCP tool outputs.
- Windows auto-update recovery now restores the preserved executable if an update fails.
- Fixes for workspace isolation, /compact, mTLS/TLS/OAuth/proxy handling, screen reader startup, telemetry endpoint routing, malformed transcript resume crashes, Remote Control permission prompts, background shell stoppages, and brace-expansion OOMs at startup.
More from coding & agent
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- Tokyo Agent Forge hackathon shipped production-ready AI agents in one day — DavidBennett__ · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A VS Code extension adds Markdown-style highlighting to Alchemy string templates — samgoodwin89 · 2026-07-27
- Claude’s Stripe MCP connector is being called unusable after repeated disconnects — evielync · 2026-07-27