Releasebot
Create account

AI Coding Assistants Release Notes

Release notes for AI-powered coding assistants, editors and agents

Get this feed: RSS Email API

Products (11)

Latest AI Coding Assistants Updates

  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 6, 2026
    Cline logo

    Cline

    3.71.0

    Cline releases GPT-5.4 models for ChatGPT subscribers, adds a Notification hook for attention and completion boundaries, and fixes MCP reconnects.

    Added

    • Added GPT-5.4 models for ChatGPT subscription users
    • Hooks: Added a Notification hook for attention and completion boundaries

    Fixed

    • Handle streamable HTTP MCP reconnects more reliably after disconnects
    Original source Report a problem
  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 6, 2026
    Anthropic logo

    Claude Code by Anthropic

    2.1.70

    Anthropic rolls out a comprehensive stability and UX release, fixing API 400s, prompt and tool search quirks, and edge-case responses while boosting performance. It adds VS Code session visuals, document views, MCP management, and smarter startup behavior, signaling broad product maintenance and polish.

    • Fixed API 400 errors when using ANTHROPIC_BASE_URL with a third-party gateway — tool search now correctly detects proxy endpoints and disables tool_reference blocks

    • Fixed API Error: 400 This model does not support the effort parameter when using custom Bedrock inference profiles or other model identifiers not matching standard Claude naming patterns

    • Fixed empty model responses immediately after ToolSearch — the server renders tool schemas with system-prompt-style tags at the prompt tail, which could confuse models into stopping early

    • Fixed prompt-cache bust when an MCP server with instructions connects after the first turn

    • Fixed Enter inserting a newline instead of submitting when typing over a slow SSH connection

    • Fixed clipboard corrupting non-ASCII text (CJK, emoji) on Windows/WSL by using PowerShell Set-Clipboard

    • Fixed extra VS Code windows opening at startup on Windows when running from the VS Code integrated terminal

    • Fixed voice mode failing on Windows native binary with "native audio module could not be loaded"

    • Fixed push-to-talk not activating on session start when voiceEnabled: true was set in settings

    • Fixed markdown links containing #NNN references incorrectly pointing to the current repository instead of the linked URL

    • Fixed repeated "Model updated to Opus 4.6" notification when a project's .claude/settings.json has a legacy Opus model string pinned

    • Fixed plugins showing as inaccurately installed in /plugin

    • Fixed plugins showing "not found in marketplace" errors on fresh startup by auto-refreshing after marketplace installation

    • Fixed /security-review command failing with unknown option merge-base on older git versions

    • Fixed /color command having no way to reset back to the default color — /color default, /color gray, /color reset, and /color none now restore the default

    • Fixed a performance regression in the AskUserQuestion preview dialog that re-ran markdown rendering on every keystroke in the notes input

    • Fixed feature flags read during early startup never refreshing their disk cache, causing stale values to persist across sessions

    • Fixed permissions.defaultMode settings values other than acceptEdits or plan being applied in Claude Code Remote environments — they are now ignored

    • Fixed skill listing being re-injected on every --resume (~600 tokens saved per resume)

    • Fixed teleport marker not rendering in VS Code teleported sessions

    • Improved error message when microphone captures silence to distinguish from "no speech detected"

    • Improved compaction to preserve images in the summarizer request, allowing prompt cache reuse for faster and cheaper compaction

    • Improved /rename to work while Claude is processing, instead of being silently queued

    • Reduced prompt input re-renders during turns by ~74%

    • Reduced startup memory by ~426KB for users without custom CA certificates

    • Reduced Remote Control /poll rate to once per 10 minutes while connected (was 1–2s), cutting server load ~300×. Reconnection is unaffected — transport loss immediately wakes fast polling.

    • [VSCode] Added spark icon in VS Code activity bar that lists all Claude Code sessions, with sessions opening as full editors

    • [VSCode] Added full markdown document view for plans in VS Code, with support for adding comments to provide feedback

    • [VSCode] Added native MCP server management dialog — use /mcp in the chat panel to enable/disable servers, reconnect, and manage OAuth authentication without switching to the terminal

    Original source Report a problem

  • All of your release notes in one feed

    Join Releasebot and get updates from Cline and hundreds of other software products.

    Create account
  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 5, 2026
    Anthropic logo

    Claude Code by Anthropic

    2.1.69

    Claude Code update adds the Claude API skill, new session naming, keypad support, remote-control name option, multi-language voice STT, and agent/worksphere UI improvements. Plus plugin, worktree, and startup prompts. Dozens of fixes boost security, stability, and performance across platforms.

    Release Notes

    • Added the /claude-api skill for building applications with the Claude API and Anthropic SDK
    • Added Ctrl+U on an empty bash prompt (!) to exit bash mode, matching escape and backspace
    • Added numeric keypad support for selecting options in Claude's interview questions (previously only the number row above QWERTY worked)
    • Added optional name argument to /remote-control and claude remote-control (/remote-control My Project or --name "My Project") to set a custom session title visible in claude.ai/code
    • Added Voice STT support for 10 new languages (20 total) — Russian, Polish, Turkish, Dutch, Ukrainian, Greek, Czech, Danish, Swedish, Norwegian
    • Added effort level display (e.g., "with low effort") to the logo and spinner, making it easier to see which effort setting is active
    • Added agent name display in terminal title when using claude --agent
    • Added sandbox.enableWeakerNetworkIsolation setting (macOS only) to allow Go programs like gh, gcloud, and terraform to verify TLS certificates when using a custom MITM proxy with httpProxyPort
    • Added includeGitInstructions setting (and CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS env var) to remove built-in commit and PR workflow instructions from Claude's system prompt
    • Added /reload-plugins command to activate pending plugin changes without restarting
    • Added a one-time startup prompt suggesting Claude Code Desktop on macOS and Windows (max 3 showings, dismissible)
    • Added ${CLAUDE_SKILL_DIR} variable for skills to reference their own directory in SKILL.md content
    • Added InstructionsLoaded hook event that fires when CLAUDE.md or .claude/rules/*.md files are loaded into context
    • Added agent_id (for subagents) and agent_type (for subagents and --agent) to hook events
    • Added worktree field to status line hook commands with name, path, branch, and original repo directory when running in a --worktree session
    • Added pluginTrustMessage in managed settings to append organization-specific context to the plugin trust warning shown before installation
    • Added policy limit fetching (e.g., remote control restrictions) for Team plan OAuth users, not just Enterprise
    • Added pathPattern to strictKnownMarketplaces for regex-matching file/directory marketplace sources alongside hostPattern restrictions
    • Added plugin source type git-subdir to point to a subdirectory within a git repo
    • Added oauth.authServerMetadataUrl config option for MCP servers to specify a custom OAuth metadata discovery URL when standard discovery fails
    • Fixed a security issue where nested skill discovery could load skills from gitignored directories like node_modules
    • Fixed trust dialog silently enabling all .mcp.json servers on first run. You'll now see the per-server approval dialog as expected
    • Fixed claude remote-control crashing immediately on npm installs with "bad option: --sdk-url" (anthropics/claude-code#28334)
    • Fixed --model claude-opus-4-0 and --model claude-opus-4-1 resolving to deprecated Opus versions instead of current
    • Fixed macOS keychain corruption when using multiple OAuth MCP servers. Large OAuth metadata blobs could overflow the security -i stdin buffer, silently leaving stale credentials behind and causing repeated /login prompts.
    • Fixed .credentials.json losing subscriptionType (showing "Claude API" instead of "Claude Pro"/"Claude Max") when the profile endpoint transiently fails during token refresh (anthropics/claude-code#30185)
    • Fixed ghost dotfiles (.bashrc, HEAD, etc.) appearing as untracked files in the working directory after sandboxed Bash commands on Linux
    • Fixed Shift+Enter printing [27;2;13~ instead of inserting a newline in Ghostty over SSH
    • Fixed stash (Ctrl+S) being cleared when submitting a message while Claude is working
    • Fixed ctrl+o (transcript toggle) freezing for many seconds in long sessions with lots of file edits
    • Fixed plan mode feedback input not supporting multi-line text entry (backslash+Enter and Shift+Enter now insert newlines)
    • Fixed cursor not moving down into blank lines at the top of the input box
    • Fixed /stats crash when transcript files contain entries with missing or malformed timestamps
    • Fixed a brief hang after a streaming error on long sessions (the transcript was being fully rewritten to drop one line; it is now truncated in place)
    • Fixed --setting-sources user not blocking dynamically discovered project skills
    • Fixed duplicate CLAUDE.md, slash commands, agents, and rules when running from a worktree nested inside its main repo (e.g. claude -w)
    • Fixed plugin Stop/SessionEnd/etc hooks not firing after any /plugin operation
    • Fixed plugin hooks being silently dropped when two plugins use the same ${CLAUDE_PLUGIN_ROOT}/... command template
    • Fixed memory leak in long-running SDK/CCR sessions where conversation messages were retained unnecessarily
    • Fixed API 400 errors in forked agents (autocompact, summarization) when resuming sessions that were interrupted mid-tool-batch
    • Fixed "unexpected tool_use_id found in tool_result blocks" error when resuming conversations that start with an orphaned tool result
    • Fixed teammates accidentally spawning nested teammates via the Agent tool's name parameter
    • Fixed CLAUDE_CODE_MAX_OUTPUT_TOKENS being ignored during conversation compaction
    • Fixed /compact summary rendering as a user bubble in SDK consumers (Claude Code Remote web UI, VSCode extension)
    • Fixed voice space bar getting stuck after a failed voice activation (module loading race, cold GrowthBook)
    • Fixed worktree file copy on Windows
    • Fixed global .claude folder detection on Windows
    • Fixed symlink bypass where writing new files through a symlinked parent directory could escape the working directory in acceptEdits mode
    • Fixed sandbox prompting users to approve non-allowed domains when allowManagedDomainsOnly is enabled in managed settings — 1 non-allowed domains are now blocked automatically with no bypass
    • Fixed interactive tools (e.g., AskUserQuestion) being silently auto-allowed when listed in a skill's allowed-tools, bypassing the permission prompt and running with empty answers
    • Fixed multi-GB memory spike when committing with large untracked binary files in the working tree
    • Fixed Escape not interrupting a running turn when the input box has draft text. Use Up arrow to pull queued messages back for editing, or Ctrl+U to clear the input line.
    • Fixed Android app crash when running local slash commands (/voice, /cost) in Remote Control sessions
    • Fixed a memory leak where old message array versions accumulated in React Compiler memoCache over long sessions
    • Fixed a memory leak where REPL render scopes accumulated over long sessions (~35MB over 1000 turns)
    • Fixed memory retention in in-process teammates where the parent's full conversation history was pinned for the teammate's lifetime, preventing GC after /clear or auto-compact
    • Fixed a memory leak in interactive mode where hook events could accumulate unboundedly during long sessions
    • Fixed hang when --mcp-config points to a corrupted file
    • Fixed slow startup when many skills/plugins are installed
    • Fixed cd <outside-dir> && <cmd> permission prompt to surface the chained command instead of only showing "Yes, allow reading from /"
    • Fixed conditional .claude/rules/*.md files (with paths: frontmatter) and nested CLAUDE.md files not loading in print mode (claude -p)
    • Fixed /clear not fully clearing all session caches, reducing memory retention in long sessions
    • Fixed terminal flicker caused by animated elements at the scrollback boundary
    • Fixed UI frame drops on macOS when using MCP servers with OAuth (regression from 2.1.x)
    • Fixed occasional frame stalls during typing caused by synchronous debug log flushes
    • Fixed TeammateIdle and TaskCompleted hooks to support {"continue": false, "stopReason": "..."} to stop the teammate, matching Stop hook behavior
    • Fixed WorktreeCreate and WorktreeRemove plugin hooks being silently ignored
    • Fixed skill descriptions with colons (e.g., "Triggers include: X, Y, Z") failing to load from SKILL.md frontmatter
    • Fixed project skills without a description: frontmatter field not appearing in Claude's available skills list
    • Fixed /context showing identical token counts for all MCP tools from a server
    • Fixed literal nul file creation on Windows when the model uses CMD-style 2>nul redirection in Git Bash
    • Fixed extra blank lines appearing below each tool call in the expanded subagent transcript view (Ctrl+O)
    • Fixed Tab/arrow keys not cycling Settings tabs when /config search box is focused but empty
    • Fixed service key OAuth sessions (CCR containers) spamming [ERROR] logs with 403s from profile-scoped endpoints
    • Fixed inconsistent color for "Remote Control active" status indicator
    • Fixed Voice waveform cursor covering the first suffix letter when dictating mid-input
    • Fixed Voice input showing all 5 spaces during warmup instead of capping at ~2 (aligning with the "keep holding6666" hint)
    • Improved spinner performance by isolating the 50ms animation loop from the surrounding shell, reducing render and CPU overhead during turns
    • Improved UI rendering performance in native binaries with React Compiler
    • Improved --worktree startup by eliminating a git subprocess on the startup path
    • Improved macOS startup by eliminating redundant settings-file reloads when managed settings resolve
    • Improved macOS startup for Claude.ai enterprise/team users by skipping an unnecessary keychain lookup
    • Improved MCP -p startup by pipelining claude.ai config fetch with local connections and using a concurrency pool instead of sequential batching
    • Improved voice startup by removing imperceptible warmup pulse animations that were causing re-render stutter
    • Improved MCP binary content handling: tools returning PDFs, Office documents, or audio now save decoded bytes to disk with the correct file extension instead of dumping raw base64 into the conversation context. WebFetch also saves binary responses alongside its summary.
    • Improved memory usage in long sessions by stabilizing onSubmit across message updates
    • Improved LSP tool rendering and memory context building to no longer read entire files
    • Improved session upload and memory sync to avoid reading large files into memory before size/binary checks
    • Improved file operation performance by avoiding reading file contents for existence checks (6 sites)
    • Improved documentation to clarify that --append-system-prompt-file and --system-prompt-file work in interactive mode (the docs previously said print mode only)
    • Reduced baseline memory by ~16MB by deferring Yoga WASM preloading
    • Reduced memory footprint for SDK and CCR sessions using stream-json output
    • Reduced memory usage when resuming large sessions (including compacted history)
    • Reduced token usage on multi-agent tasks with more concise subagent final reports
    • Changed Sonnet 4.5 users on Pro/Max/Team Premium to be automatically migrated to Sonnet 4.6
    • Changed the /resume picker to show your most recent prompt instead of the first one. This also resolves some titles appearing as (session).
    • Changed claude.ai MCP connector failures to show a notification instead of silently disappearing from the tool list
    • Changed example command suggestions to be generated deterministically instead of calling Haiku
    • Changed resuming after compaction to no longer produce a preamble recap before continuing
    • [SDK] Changed task creation to no longer require the activeForm field 1 the spinner falls back to the task subject
    • [VSCode] Added compaction display as a collapsible "Compacted chat" card with the summary inside
    • [VSCode] The permission mode picker now respects permissions.disableBypassPermissionsMode from your effective Claude Code settings (including managed/policy settings) 1 when set to disable, bypass permissions mode is hidden from the picker
    • [VSCode] Fixed RTL text (Arabic, Hebrew, Persian) rendering reversed in the chat panel (regression in v2.1.63)
    Original source Report a problem
  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 5, 2026
    Cline logo

    Cline

    3.70.0

    New Cline API docs released with Getting Started and SDK examples. Hooks now expose model.provider and model.slug, and token updates occur in real time as usage chunks arrive. Reliability fixes and docs updates enhance subagent behavior and error handling.

    Added

    • New Cline API docs: Getting Started, Auth, Chat Completions, Models, Errors, and SDK Examples
    • Hook payloads now include model.provider and model.slug
    • Token/cost updates now happen immediately as usage chunks arrive, not after tool execution

    Fixed

    • Improve subagent context compaction logic
    • Subagent stream retry delay increased to reduce noise from transient failures
    • State serialization errors are now caught and logged instead of crashing
    • Removed incorrect max_tokens from OpenRouter requests

    Changed

    • Windows test cleanup now retries on locked files and applies per-test timeouts
    • Updated hooks docs
    Original source Report a problem
  • Mar 5, 2026
    • Date parsed from source:
      Mar 5, 2026
    • First seen by Releasebot:
      Mar 6, 2026
    Cursor logo

    Cursor

    Build agents that run automatically

    Cursor unveils Automations to run always-on agents triggered by Slack, Linear, GitHub, PagerDuty or custom webhooks. Agents spin up cloud sandboxes, learn over time, and cover security reviews, incident response, weekly digests, and more, turning code workflows into a factory.

    We're introducing Cursor Automations to build always-on agents.

    These agents run on schedules or are triggered by events like a sent Slack message, a newly created Linear issue, a merged GitHub PR, or a PagerDuty incident. In addition to these built-in integrations, you can configure your own custom events with webhooks.

    “I love that automations work for both quick wins and more complex workflows. I can schedule the obvious stuff in seconds, but I still have full flexibility to catch any webhook or plug into custom MCPs when I need to.”

    Trent Haines
    Software Engineer, Decagon

    Upgrading the software engineering pipeline

    With the rise of coding agents, every engineer is able to produce much more code. But code review, monitoring, and maintenance haven’t sped up to the same extent yet. At Cursor, we’ve been using automations to help scale these other parts of the development lifecycle.

    When invoked, the automated agent spins up a cloud sandbox, follows your instructions using the MCPs and models you've configured, and verifies its own output. Agents also have access to a memory tool that lets them learn from past runs and improve with repetition.

    As we’ve run more automated agents on our own codebase at Cursor over the past several weeks, two categories of automations have emerged.

    Review and monitoring

    Automations are great for reviewing changes. They can catch and fix everything from style nits and inconsistencies to security vulnerabilities and performance regressions.

    In fact, Bugbot is in many ways the original automation! It runs when a PR is opened or updated, gets triggered thousands of times a day, and has caught millions of bugs since we first launched it. Automations allow you to customize all kinds of review agents for different purposes. Here are three we use at Cursor:

    • Security review
      Our security review automation is triggered on every push to main. This way, the agent can work for longer to find more nuanced issues without blocking the PR. It audits the diff for security vulnerabilities, skips issues already discussed in the PR, and posts high-risk findings to Slack. This automation has caught multiple vulnerabilities and critical bugs at Cursor.

    • Agentic codeowners
      On every PR open or push, this automation classifies risk based on blast radius, complexity, and infrastructure impact. Low-risk PRs get auto-approved. Higher-risk PRs get up to two reviewers assigned based on contribution history. Decisions are summarized in Slack and logged to a Notion database via MCP so we can audit the agent’s work and tweak the instructions.

    • Incident response
      When triggered by a PagerDuty incident, this automation kicks off an agent that uses the Datadog MCP to investigate the logs and looks at the codebase for recent changes. It then sends a message in a Slack channel to our on-call engineers, with the corresponding monitor message and a PR containing the proposed fix. This has significantly reduced our incident response time.

    Chores

    We’ve also found automations useful for everyday tasks and knowledge work that require stitching together information across different tools.

    • Weekly summary of changes
      This automation posts a weekly Slack digest summarizing meaningful changes to the repository in the last seven days. The agent highlights major merged PRs, bug fixes, technical debt, and security or dependency updates.

    • Test coverage
      Every morning, an automated agent reviews recently merged code and identifies areas that need test coverage. It follows existing conventions when adding tests and only alters production behavior when necessary. The agent then runs relevant test targets before opening a PR.

    • Bug report triage
      When a bug report lands in a Slack channel, this automation checks for duplicates and creates an issue using Linear MCP. The agent then investigates the root cause in the codebase, attempts a fix, and replies in the original thread with a summary.

    How Rippling uses automations

    Teams outside Cursor have already started building automations. Abhishek Singh at Rippling set up a personal assistant. He dumps meeting notes, action items, TODOs, and Loom links into a Slack channel throughout the day. A cron agent runs every two hours, reads everything alongside his GitHub PRs, Jira issues, and Slack mentions, deduplicates across sources, and posts a clean dashboard.

    He also runs Slack-triggered automations for creating Jira issues from threads and summarizing discussions in Confluence. Singh and Rippling have extended their use of automations to handle tasks like incident triage, weekly status reports, on-call handoff, and more. The most useful automations get shared across the team.

    “Automations have made the repetitive aspects of my work easy to offload. By making automations to round up tasks, deal with doc updates, and respond to Slack messages, I can focus on the things that matter. Anything can be an automation!”

    Tim Fall
    Senior Staff Software Engineer, Rippling

    The factory that creates your software

    All of these automations are powered by cloud agents that use their own computers to build, test, and demo their work. Now you can build the factory that creates your software by configuring agents to continuously monitor and improve your codebase.

    “We built our software factory using Cursor Automations with Runlayer MCP and plugins. We move faster than teams five times our size because our agents have the right tools, the right context, and the right guardrails.”

    Tal Peretz
    Co-founder, Runlayer

    Try creating an automation at cursor.com/automations, or start from a template. Learn more in the docs.

    Original source Report a problem
  • Mar 5, 2026
    • Date parsed from source:
      Mar 5, 2026
    • First seen by Releasebot:
      Mar 6, 2026
    Cursor logo

    Cursor

    Automations

    Cursor unveils automations for always-on agents with triggers and schedules across Slack, GitHub, and more.

    Cursor automations

    Cursor now supports automations for building always-on agents that run based on triggers and instructions you define.

    Automations run on schedules or are triggered by events from Slack, Linear, GitHub, PagerDuty, and webhooks.

    When invoked, the agent spins up a cloud sandbox and follows your instructions using the MCPs and models you've configured. Agents also have access to a memory tool that lets them learn from past runs and improve with repetition.

    Create automations at cursor.com/automations, or start from a template. Read more in our announcement.

    Original source Report a problem
  • Mar 5, 2026
    • Date parsed from source:
      Mar 5, 2026
    • First seen by Releasebot:
      Mar 6, 2026
    GitHub logo

    Copilot CLI by GitHub

    0.0.422-1

    New release adds personal hooks loading, auto copy in alt mode, startup prompts, plan approval protocol, and startup prompts. It boosts reliability with persisted session metrics, reduced alt-screen memory, clearer git and plugin UX, LSP/CLI improvements, and broader URL/UI fixes for calmer, smoother sessions.

    Added

    • Load personal hooks from ~/.copilot/hooks in addition to repo-level .github/hooks
    • Add copy_on_select config option to auto-copy selected text to clipboard in alt screen mode
    • Add exitPlanMode.request protocol method for SDK plan approval support
    • Automatic notifications when background shell commands and agents complete
    • Press Ctrl+R to search command history with reverse incremental search (like Bash)
    • Add startup prompt hooks to auto-submit prompts or slash commands when a session starts
    • Support enabledPlugins in config for automatic plugin installation at startup
    • Support installing plugins from ssh:// URLs
    • Session usage metrics (requests, tokens, code changes) are now persisted to events.jsonl after each session ends

    Improved

    • Show a clear, actionable error message when git is not installed and a remote plugin or marketplace is used
    • Text selection persists after copying to clipboard in alt screen
    • Reduce memory usage in alt-screen mode for long sessions
    • @-mention file completion always reflects the current state of the working directory
    • Links in alt-screen mode are rendered with underline styling for better visibility
    • /delegate prompts for a target remote in multi-remote repositories and clarifies confirmation text
    • Hide noisy todo bookkeeping queries and show dependency details in timeline
    • Rename launch_messages config setting to companyAnnouncements
    • Show a waiting message when the terminal is handed to an external editor
    • Rename repository config from .github/copilot/config.json to settings.json

    Fixed

    • Plugin cache automatically recovers from a corrupted or incomplete clone without manual intervention
    • IME candidate windows appear at correct cursor position in CJK input
    • Opening links on Windows correctly handles URLs with & query parameters
    • ESC key to cancel works correctly in tmux and other non-kitty terminals
    • GitHub MCP server stays enabled in repositories that have both Azure DevOps and GitHub remotes
    • Colons in inline code render correctly inside markdown tables
    • Plugin-contributed LSP servers are now loaded, started, and shown in /lsp show
    • Pressing Enter in required enum field now selects the highlighted option
    • CLI no longer hangs for minutes when working in a directory with a large number of files
    • GitHub MCP server connection status is accurately tracked and counted in the status indicator
    • Ctrl+K joins lines when cursor is at end of line, matching standard Emacs/terminal behavior
    • Escape sequences split across input chunks no longer leak into text input
    Original source Report a problem
  • Mar 5, 2026
    • Date parsed from source:
      Mar 5, 2026
    • First seen by Releasebot:
      Mar 5, 2026
    • Modified by Releasebot:
      Mar 6, 2026
    GitHub logo

    Copilot CLI by GitHub

    0.0.422

    A large release boosts stability and UX across alt-screen, diff, and shell integration, adds GPT-5.4 model support, plugin cache auto-recovery, improved error messages, and richer session telemetry. New /lsp, copy commands, JSONL output, and multi-remote handling enhance automation and collaboration.

    2026-03-05

    • Display request ID in authentication and authorization error messages to aid troubleshooting
    • Load personal hooks from ~/.copilot/hooks in addition to repo-level .github/hooks
    • Timeline now shows the question in a box and displays 'Making best guess on autopilot' when ask_user is auto-responded
    • Add support for GPT-5.4 model
    • Plugin cache automatically recovers from a corrupted or incomplete clone without manual intervention
    • Show a clear, actionable error message when git is not installed and a remote plugin or marketplace is used
    • Text selection persists after copying to clipboard in alt screen
    • Scroll view no longer jumps to earlier messages when scrolling during response streaming or with popups open
    • Add copy_on_select config option to auto-copy selected text to clipboard in alt screen mode
    • IME candidate windows appear at correct cursor position in CJK input
    • Add mouse scroll support to /diff in alt-screen mode
    • Reduce memory usage in alt-screen mode for long sessions
    • Diff mode now works correctly when git color.diff=always is configured
    • Opening links on Windows correctly handles URLs with & query parameters
    • @-mention file completion always reflects the current state of the working directory
    • ESC key to cancel works correctly in tmux and other non-kitty terminals
    • Click in the prompt input to reposition the text cursor
    • Add /copy command to copy the last response to clipboard
    • Links in alt-screen mode are rendered with underline styling for better visibility
    • /delegate prompts for a target remote in multi-remote repositories and clarifies confirmation text
    • GitHub MCP server stays enabled in repositories that have both Azure DevOps and GitHub remotes
    • Colons in inline code render correctly inside markdown tables
    • Pressing Ctrl+C on the help dialog now dismisses it cleanly
    • Plugin-contributed LSP servers are now loaded, started, and shown in /lsp show
    • Pressing Enter in required enum field now selects the highlighted option
    • Hide noisy todo bookkeeping queries and show dependency details in timeline
    • CLI no longer hangs for minutes when working in a directory with a large number of files
    • Add --output-format json flag to emit JSONL in prompt mode for programmatic integrations
    • Add exitPlanMode.request protocol method for SDK plan approval support
    • Automatic notifications when background shell commands and agents complete
    • GitHub MCP server connection status is accurately tracked and counted in the status indicator
    • Press Ctrl+R to search command history with reverse incremental search (like Bash)
    • Long diff lines no longer overflow and wrap in the diff view
    • Add startup prompt hooks to auto-submit prompts or slash commands when a session starts
    • Ctrl+K joins lines when cursor is at end of line, matching standard Emacs/terminal behavior
    • Escape sequences split across input chunks no longer leak into text input
    • Rename launch_messages config setting to companyAnnouncements
    • Show a waiting message when the terminal is handed to an external editor
    • Support enabledPlugins in config for automatic plugin installation at startup
    • Improve key bindings in reverse history search: Ctrl+J to accept, Ctrl+G to cancel
    • Rename repository config from .github/copilot/config.json to settings.json
    • Support installing plugins from ssh:// URLs
    • Session usage metrics (requests, tokens, code changes) are now persisted to events.jsonl after each session ends
    Original source Report a problem
  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 4, 2026
    Anthropic logo

    Claude Code by Anthropic

    2.1.68

    • Opus 4.6 now defaults to medium effort for Max and Team subscribers. Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness. You can change this anytime with /model

    • Re-introduced the "ultrathink" keyword to enable high effort for the next turn

    • Removed Opus 4 and 4.1 from Claude Code on the first-party API — users with these models pinned are automatically moved to Opus 4.6

    Original source Report a problem
  • March 2026
    • No date parsed from source.
    • First seen by Releasebot:
      Mar 4, 2026
    Anthropic logo

    Claude Code by Anthropic

    2.1.66

    Release Notes

    • Reduced spurious error logging
    Original source Report a problem