AI Coding Live News

Anthropic published Claude Code v2.1.314 on GitHub at 01:06 UTC on Oct 30. The official CHANGELOG lists 119 entries, more than half of them fixes. The new features lean enterprise: permissions.blockWritesOutsideWorkingDirectories makes Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode; Claude apps gateway upstreams can be limited to IdP groups, and Bedrock upstreams can log which guardrail fired; idle compaction now also runs in VS Code and the Code tab of Claude Desktop. It also fixes sessions failing repeatedly when an admin caps effort, and claude -p exiting 0 with no output when startup failed.

MiniMax officially open-sourced MiniMax Code CLI v0.4.12 under MIT for developers worldwide. It is a terminal coding agent that works with MiniMax accounts or bring-your-own models, plus search, plugins, and multimodal tools. On FrontierHarness Eval it claims SOTA pass rate, fastest average task completion, and second-lowest token usage; open-sourcing aims to let teams inspect tool calls and permissions for reliable enterprise apps.

Cursor upgraded its Projects multi-agent architecture with native sandbox security probes. The probes continuously analyze code diffs, permissions, and dependencies before and after subagents commit changes, actively thwarting unintended privilege escalation and security regressions.

Perplexity says two engineers worked with hundreds of AI coding agents to build CobbleDB, a custom Rust database replacing DynamoDB reads in its search stack. The case shows coding agents contributing at real infrastructure scale while keeping production execution outside the agents’ permissions.

Google Home opened early access to a Model Context Protocol (MCP) server for US Google Home Premium Advanced subscribers. Any MCP-capable agent—Claude, Hermes, OpenClaw, ChatGPT, Google Antigravity—can securely connect to the Home ecosystem: review camera summaries, monitor activity, control Nest doorbells/thermostats and Matter lights, and build custom dashboards. Setup means creating a Google Cloud project, configuring Home MCP, then handing the config to an agent for sign-in and permissions. It covers Google Home and Works with Google Home / Matter devices, rolling out over coming weeks.

The unofficial-but-tolerated Claude Code Changelog bot (@ClaudeCodeLog) posted 2.1.274 with 108 CLI changes. Highlights: a visible critical-memory warning with safe free/restart steps; sessions no longer loop forever on unexpected tool_use_id 400s (transcripts self-heal when possible, else a clear /rewind error ends the loop); MCP 403 insufficient_scope now names missing permissions and points to /mcp re-auth; CLAUDE_CODE_MCP_STARTUP_WAIT_MS bounds how long the first non-interactive turn waits for MCP servers. Many more MCP/stream, /goal resume, self-hosted runner 401, VS Code, and cloud session/routine fixes. Source: anthropics/claude-code CHANGELOG #21274.

ClaudeDevs shipped a Claude Code weekly batch aimed at startup latency, token observability, and mobile remote control. The CLI no longer waits for the sandbox and MCP servers before accepting input; the Linux x64 download is about 4.5x smaller at roughly 75 MB, and native builds use 40–70 MB less memory per session. /cost now shows a prompt-cache line, /usage breaks down /loop runs and tokens so teams can see which loops burn quota, and /tasks lists each subagent's model and effort level. An Auto mode tab in /permissions exposes default allow/block rules and custom additions without hand-editing ~/.claude/settings.json. Remote Control reconnects after a server-side disconnect instead of exiting, surfaces permission prompts and new messages on phone after reconnect, and lets you watch a foreground subagent's tool calls live. Anthropic asked users to run claude update.

ClaudeDevs shipped a Claude Code weekly batch: the CLI no longer waits for sandbox and MCP servers before accepting input, the Linux x64 download is about 4.5x smaller at ~75 MB, and native builds use 40–70 MB less memory per session. /cost now shows a prompt-cache line, /usage breaks down /loop runs and tokens, and /tasks lists each subagent's model and effort. An Auto mode tab in /permissions exposes defaults and custom rules without editing ~/.claude/settings.json. Remote Control reconnects after a server-side disconnect, surfaces permission prompts on phone, and lets you watch foreground subagent tool calls live. Run claude update.

LM Studio introduced Bionic Auto Review for automated agent shell tool permissions, combining AST parsing and deterministic command matching to auto-approve 82% of safe terminal requests.