Claude Code (Anthropic)

Version 2.1.169 (June 2026)
  • Added --safe-mode flag and CLAUDE_CODE_SAFE_MODE env var to start with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting.
  • Added /cd command to move a session to a new working directory without breaking the prompt cache.
  • Added disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS env var to hide bundled skills, workflows, and built‑in slash commands from the model.
  • Fixed Up/Down arrows jumping to command history past wrapped lines; now move through each visual row first.
  • Fixed enterprise‑managed MCP policies (allowedMcpServers/deniedMcpServers) not being enforced on reconnect, IDE‑typed configs, --mcp-config servers during first session after install, or before remote settings loaded; also fixed slow cold starts for orgs without remote settings.
  • Fixed a ~30‑50 ms UI stall at the start of each turn for macOS users logged in with claude.ai credentials.
  • Fixed claude -p being slow or appearing to hang on Windows while waiting for the slash‑command/skill scan (regression in 2.1.161).
  • Fixed Remote Control getting stuck on “reconnecting” after resuming a session when an OAuth token refresh happened simultaneously.
  • Fixed Git Credential Manager’s “Connect to GitHub” popup appearing on Windows at startup when background git commands ran without cached credentials.
  • Fixed footer hints (e.g. “esc to interrupt”) not showing for users with a custom statusline.
  • Fixed stale permission and dialog prompts reappearing every time you reattached to a remote session whose worker had died while waiting on them.
  • Fixed claude agents --json omitting blocked and just‑dispatched background sessions; added --all to include completed sessions, plus new id and state fields.
  • Fixed agents view leaving a stale/garbled frame after navigating back from an agent on WSL in Windows Terminal.
  • Fixed background agents ignoring project‑level settings env values (e.g. ANTHROPIC_MODEL) when dispatched onto a pre‑warmed worker.
  • Fixed MCPB plugin cache being spuriously invalidated on Windows, causing unnecessary re‑extraction.
  • Fixed plugin .in_use PID lock files accumulating without bound; stale markers from crashed sessions are now swept once per day.
  • Fixed untrusted project settings being able to set OTEL client‑certificate paths without trust confirmation.
  • /workflows now opens immediately even while a turn is in progress.
  • Improved TaskCreate reliability: malformed inputs are repaired automatically and validation errors for unloaded tools include the schema.
  • Improved error message shown when your organization has disabled API key authentication, with guidance based on where the active API key comes from.
  • Reduced CPU usage while responses stream and during spinner animations.
  • Restored a default 5‑minute idle timeout on Vertex/Foundry so a stalled stream aborts instead of hanging indefinitely; set API_FORCE_IDLE_TIMEOUT=0 to opt out.
  • Remote‑managed settings with an invalid entry now apply their remaining valid policies and surface the validation error, instead of silently dropping the whole payload.
  • Background sessions now preserve --ide, --chrome, --bare, --remote‑control, and other flags across retire→wake, and respawn state validation was hardened.
  • Background sessions are now told that shared‑checkout edits are blocked until they enter a worktree, avoiding a wasted rejected edit before EnterWorktree.
  • The “CLAUDE.md is too long” warning threshold now scales with the model's context window.
  • Auto‑updater on Windows now stops retrying within a session once claude.exe is held by another process.
  • Improved color contrast for skill tags in the slash‑command menu.
  • Promo credit claims for Apple/Google‑billed subscribers without a payment method now explain where to add one.
  • Added a tip suggesting claude agents when running multiple concurrent sessions.
  • Version 2.1.168 / 2.1.167: Bug fixes and reliability improvements.
  • Version 2.1.166: Added fallbackModel setting (up to three fallback models), glob pattern support in deny‑rule tool‑name position, hardened cross‑session messaging, MAX_THINKING_TOKENS=* disables thinking, Claude Code now retries a turn once on fallback model when API rejects unexpected non‑retryable error.

Claude API / Platform

  • Claude Opus upgraded to version 4.8, with improvements in coding, agentic skills, and reasoning over Opus 4.7.

  • Deprecation of Claude Opus 4.1 model announced; retirement scheduled for August 5, 2026 on the Claude API.

  • Release notes: <https://support.claude.com/en/articles/12138966-release-notes>

OpenAI Codex CLI

June 2026 Updates
  • New codex resume command to resume sessions where you left off.
  • Context compaction automatically summarizes the session as it approaches the context window limit.
  • Ability to use supported OpenAI models via Amazon Bedrock (June 1).
  • Terminal placement controls: set default terminal location in General settings (June 1).
  • Build and deploy websites with Sites now available in preview in the Codex app (June 2).
  • ChatGPT for iOS updates: optional Face ID/passcode lock, fixed reconnecting/archiving/loading tasks/host connections (June 2).
  • Codex app updates: activity insights, share cards, performance improvements, bug fixes (June 4).
  • Full changelog: <https://developers.openai.com/codex/changelog>

OpenCode (opencode‑ai/opencode)

Release v1.16.2 (June 5, 2026) Core
  • Reasoning summaries now only run on providers that support them, avoiding GPT‑5 request failures on compatible backends.
  • Edit operations now refuse loose matches that could overwrite the wrong code or replace an existing file by mistake.
  • Fixed Bedrock sessions hanging before a model response starts.
  • Diff viewer now supports next and previous hunk navigation.
  • Terminal themes now refresh after live terminal reloads without stale colors or broken highlighting.
  • Running subagents can now be sent to the background so you can keep working.
  • Sessions now persist system context updates during long‑running conversations.
  • Added Snowflake Cortex provider support.
TUI
  • Fixed the external editor fallback so attach‑mode sessions still open when the original project path is unavailable locally.
  • Permission replies now route through the correct session directory.
  • /mo now prefers the models command in slash autocomplete.
  • Fixed crashes from malformed path or diff metadata in permission and session views.
Desktop
  • Fixed titlebar tab overflow clipping.
  • Fixed overflowed titlebar tabs so scrolling and drag regions behave correctly.
  • Improved tab closing and navigation so the next tab is selected more reliably.
  • Improved multi‑server desktop support with per‑server home state and session tabs.
Release v1.16.0 (same day)
  • Added managed workspace cloning that keeps dirty and untracked files.
  • Added moving sessions between workspaces and directories.
  • Added proper OpenAI model support through AWS Bedrock.
  • Added skill discovery and file‑based agent loading.
  • Updated GitHub Copilot usage tracking for token‑based billing.
  • Added run --replay for interactive session replay.
  • Improved startup time.
  • Added Vue syntax highlighting.
  • Restored full ACP session replay when loading saved sessions.
  • Fixed shell cancellation races.
  • Fixed SAP AI Core OpenAI reasoning variants.
  • Fixed delegated tasks losing their selected reasoning variant.
  • Fixed OpenAI websocket sessions getting stuck idle.
  • Fixed Windows path normalization in migrated storage.
  • Fixed prompt corruption when pasting near wide characters.
  • Fixed ACP cancel so it aborts the active run.
  • Fixed SAP AI Core Anthropic Opus 4.7+ adaptive reasoning.
Changelog: <https://opencode.ai/changelog>

---
AI Coding Intelligence • Leaniverse News