Anthropic ships Claude Code v2.1.219 with Opus 5 as the default model and 1M context
ashwin-ant · ghdev · 2026-07-25
Anthropic shipped Claude Code v2.1.219 with several notable changes:
- Claude Opus 5 (claude-opus-5) is now the default Opus model, with 1M context and fast mode priced at $10 / $50 per Mtok.
- Added tighter sandbox controls via sandbox.network.strictAllowlist to block non-allowlisted hosts without prompting.
- Added a DirectoryAdded hook for mid-session working-directory registration, plus better MCP error surfacing and startup warnings.
- Fixed several session, permission, runner, and output bugs, including claude -p dropping answers after mid-stream API errors.
The release also improves nested subagent forwarding, structured failure categories for self-hosted runners, and a few UI/status edge cases in the model picker and MCP commands.
More from coding & agent
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11
- How Do You Catch Behavioral Regressions in LLM Agents Between Releases? — Beautiful_Belt_601 · 2026-09-11
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- ARRM targets silent economic regressions in AI agents that functional tests miss — Beautiful_Belt_601 · 2026-09-11