Claude Code (Anthropic)
Version 2.1.169 (June 2026)- Added
--safe-modeflag andCLAUDE_CODE_SAFE_MODEenv var to start with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting.
- Added
/cdcommand to move a session to a new working directory without breaking the prompt cache.
- Added
disableBundledSkillssetting andCLAUDE_CODE_DISABLE_BUNDLED_SKILLSenv 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-configservers 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 -pbeing 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 --jsonomitting blocked and just‑dispatched background sessions; added--allto include completed sessions, plus newidandstatefields.
- 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
envvalues (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_usePID 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.
/workflowsnow opens immediately even while a turn is in progress.
- Improved
TaskCreatereliability: 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=0to 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.exeis 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 agentswhen running multiple concurrent sessions.
- Version 2.1.168 / 2.1.167: Bug fixes and reliability improvements.
- Version 2.1.166: Added
fallbackModelsetting (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 resumecommand 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.
- 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.
/monow prefers the models command in slash autocomplete.
- Fixed crashes from malformed path or diff metadata in permission and session views.
- 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.
- 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 --replayfor 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.
---
AI Coding Intelligence • Leaniverse News