Claude Code v2.1.158: Auto Mode Now on Bedrock, Vertex, Foundry for Opus 4.7/4.8
Claude Code v2.1.158 extends auto mode to Bedrock, Vertex, and Foundry deployments running Opus 4.7 or Opus 4.8. Auto mode allows the agent to automatically determine when to run commands, edit files, or ask for clarification without requiring manual approval for each step.
Key Details
- New platforms: Bedrock, Vertex AI, and Foundry (in addition to existing support)
- Models: Opus 4.7 and Opus 4.8
- Opt-in: Set environment variable
CLAUDE_CODE_ENABLE_AUTO_MODE=1
To enable, launch Claude Code with the environment variable set:
CLAUDE_CODE_ENABLE_AUTO_MODE=1 claude codeOnce enabled, the agent will autonomously execute actions like file edits and shell commands, reducing user interaction overhead. This is particularly useful for long-running multi-step tasks where manual confirmation would break flow.
No other changes were included in this patch release.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Anthropic Policy Update Bans Third-Party Tools for Claude Pro/Max Users
Anthropic updated their policy in February 2026 to explicitly ban any script, wrapper, or third-party tool usage with Claude Pro or Max plans, resulting in lifetime bans for users who violate this policy. High-tier Max plan users engaging in heavy coding sessions are being targeted in a March 2026 enforcement wave.
OpenClaw 2026.3.24: Bridge Config Removed, Heartbeat Token Savings, Loop Detection
OpenClaw 2026.3.24 removes the deprecated bridge configuration section from openclaw.json, adds isolatedSession: true to heartbeat config to reduce token costs from ~100K to 2-5K per run, and introduces new features including imageGenerationModel, tools.loopDetection, channels.modelByChannel, built-in model aliases, and pdfModel.
Anthropic files lawsuit to prevent Pentagon blacklisting over AI restrictions
Anthropic has filed a lawsuit seeking to block the Pentagon from blacklisting the company over restrictions on AI use, according to a Reuters report shared on Hacker News.
Meta OpenEnv AI Hackathon in India Offers Direct Interviews and $30K Prize Pool
Meta is hosting India's first OpenEnv AI Hackathon in collaboration with Hugging Face and PyTorch, where developers build reinforcement learning environments for AI agents. Top teams get direct interviews with Meta and Hugging Face AI teams, plus a $30,000 prize pool.