Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The auto-mode safety guardrails directly prevent the agent from executing irreversible git and infrastructure teardown operations without explicit user intent, reducing the risk of accidental data or state loss during autonomous sessions.
The release resolves a startup regression from `2.1.169`, file-corruption bugs on network and cloud-synced drives, and unbounded subagent nesting — all of which directly affected reliability in common development environments.
The `Tool(param:value)` permission syntax gives operators the first parameter-level control over which tool inputs are allowed or blocked, closing a gap that previously required coarser tool-level rules.
The release pairs access to Anthropic's most capable generally available model to date with a fix for a session-continuity regression that affected VS Code integrated terminal users.
The release closes a security gap in enterprise MCP policy enforcement that left access controls unenforced during reconnects and first-install sessions, while also adding a `--safe-mode` escape hatch and `/cd` command that improve day-to-day troubleshooting and session management.
Audit your Claude Code setup after upgrading — persistent `/config` settings, parallel MCP connections, and expanded `--from-pr` platform support meaningfully change how configuration, integrations, and PR-based workflows behave.