Claude Code v2.1.142: New claude agents flags, Opus 4.7 default, and bug fixes

Anthropic released Claude Code v2.1.142 with significant updates to the claude agents subsystem, a default model change in fast mode, and a long list of bug fixes.
New claude agents flags
Eight new flags are available to configure dispatched background sessions:
--add-dir— additional directories--settings— settings file path--mcp-config— MCP configuration--plugin-dir— plugin directory--permission-mode— permission mode for the session--model— model override--effort— effort level--dangerously-skip-permissions— skip permission prompts
Previously these were only configurable via environment variables or the daemon configuration file; now they can be passed directly when starting a background agent.
Fast mode defaults to Opus 4.7
Fast mode now uses Opus 4.7 by default, replacing Opus 4.6. If you need to pin fast mode to Opus 4.6, set the environment variable:
CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1Plugin improvements
Plugins with a root-level SKILL.md and no skills/ subdirectory are now correctly surfaced as a skill. The /plugin details pane and claude plugin details command now display the LSP servers a plugin provides.
Notable bug fixes
- MCP_TOOL_TIMEOUT — fixed so it actually raises the per-request fetch timeout for remote HTTP and SSE MCP servers. Previously, tool calls were capped at 60 seconds regardless of the configured value.
- macOS sleep/wake — background sessions no longer disappear after sleep/wake. The daemon now detects clock jumps instead of treating them as elapsed idle time.
- Daemon upgrade — the daemon now exits cleanly after the binary is upgraded (e.g.,
brew upgrade), preventing dispatched agents from crash-looping on the deleted binary path. - Windows network drives — background agents no longer deadlock when working directories are on network drives; Ctrl+C now works during startup.
- Editor detection —
claude agents"v to open in editor" now uses your shell's$EDITOR/$VISUALinstead of the daemon's default editor. - Terminal color bleed — fixed background-color bleed when attaching to a session from Apple Terminal or other 256-color-only terminals.
- Permissions persistence —
claude --bg --dangerously-skip-permissionsnow persists across retire/wake cycles. - Plugin cache — no longer deletes the active plugin version directory when installation metadata is missing.
Other improvements
- Reactive compaction — the first summarize attempt now seeds from the original request's overflow size, avoiding a wasted near-full-context retry.
- Hook configuration — configuring a prompt- or agent-type hook for
SessionStart/Setup/SubagentStartnow shows a clear error suggesting to use a command-type hook instead. - Removed stale
/model claude-sonnet-4-20250514suggestion from Usage Policy refusal messages.
📖 Read the full source: GitHub Claude-Code
👀 See Also

LORE.md: An Open Standard for Extracting Structured Knowledge from AI Conversations
LORE.md is an open standard for extracting durable knowledge from AI conversations into a structured format. It captures decisions with rationale, insights, patterns, open questions, and next steps, with everything linking across sessions.

SynapsCAD: Open-Source Desktop App for OpenSCAD with Claude AI Integration
SynapsCAD is an open-source desktop application that combines an OpenSCAD code editor, real-time 3D viewport, and AI assistant. Built entirely in Rust with Bevy 0.15 and egui, it supports Claude API integration for natural language 3D CAD coding.

OpenClaw developer builds unified memory system for AI agents
A developer has built a 15-tool unified memory system for OpenClaw AI agents that combines structured facts, vector search, entity graphs, episode timelines, hierarchical compression, and event-driven coordination. The system runs locally without cloud dependencies or monthly fees.

Hawkeye Update Adds Swarm Orchestration, Remote Tasks, and Local Model Support
Hawkeye v1.0+ now supports multi-agent swarm orchestration, remote task queuing, and improved Ollama/LM Studio integration. The local-first AI agent flight recorder helps developers track what happens when agents work in repositories.