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.
This release resolves several MCP integration failures — including schema validation errors and timeout drops on long-running tools — that previously blocked OpenAI-compatible and Cloudflare AI Gateway users from reliably running MCP-powered workflows.
Teams running Claude Code on large sessions or multi-server MCP setups should upgrade to `v2.1.116` immediately — both for the meaningful speed gains and the security fix that prevents sandbox auto-allow from bypassing critical directory protections.