v2.1.303
Bug fixes and reliability improvements
Read the official notes →Official release notes for AI coding tools, in one place. Release notes from Cursor, Claude Code, OpenAI Codex CLI, GitHub Copilot, Gemini CLI, Aider, pulled from each vendor's official feed and linked back to the source.
Updated 2026-10-19 14:53 UTC · last 7 days: GitHub Copilot 7 · Claude Code 5 · Cursor 2 · OpenAI Codex CLI 1 · Gemini CLI 1
Bug fixes and reliability improvements
Read the official notes →Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode • Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle…
Read the official notes →@GitHub in Slack and Teams now supports working across multiple repositories in a single conversation. Whether you’re creating issues, opening pull requests, or investigating bugs, you can work across repositories…
Read the official notes →Cloud agents can now build and share interactive canvases. The Environments API is available in beta, environments support up to 300 repos, and large environments load 5x faster.
Read the official notes →New Features: Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. (#52990, #53429) • Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code…
Read the official notes →We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on November 16th, 2026: Model Deprecation date…
Read the official notes →Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting • Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace…
Read the official notes →Agentic autofix for code scanning alerts is now generally available. It remediates alerts by working across your codebase the way a developer would: it explores relevant files, proposes a fix,…
Read the official notes →HydraFusion has an updated model pool, improved orchestration workflows, and introduces HydraFusion Max. Both HydraFusion and HydraFusion Max are available across VS Code, the GitHub Copilot app, and GitHub Copilot…
Read the official notes →Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt • Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime • Added…
Read the official notes →Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents • Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its…
Read the official notes →refactor(a2a-server): implement V1 to V2 settings migration logic • fix(acp): bridge PromptResponse.usage and emit usage_update notifications (#29389) • Changelog for v0.63.0-preview.0 • fix(cli): propagate resolved folder trust state in headless mode (#29031) • chore(release)…
Read the official notes →Gemini 4 Argon, Google’s newest frontier model, is now generally available in GitHub Copilot. It is designed for complex coding, agentic, and reasoning tasks. In early testing, Gemini 4 Argon…
Read the official notes →Enterprise administrators can now require supported GitHub Copilot clients to retrieve current server-managed settings at startup instead of relying on a cached policy. We are also adding minimum client version…
Read the official notes →Origin integrates with over 20 apps for deployments, CI, code review, security, monitoring, and project management, and the marketplace is now open to public submissions.
Read the official notes →Enterprise administrators can now use telemetry in managed settings to attribute GitHub Copilot activity to a user without collecting their prompts, responses, or tool content. The telemetry.capture.identity setting adds three…
Read the official notes →This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and account controls, and…
Read the official notes →This week’s updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot Claude Haiku…
Read the official notes →Bug Fixes: Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. (#51866) • Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults.…
Read the official notes →Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode • Added autoCompactWindow to subagent frontmatter and --agents definitions, so a…
Read the official notes →Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through • Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code…
Read the official notes →This release adds new billing and license controls for Copilot code review admins: Billing: Organization owners can bill Copilot code reviews from members with a Copilot license to the organization’s…
Read the official notes →New Features: Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. (#50148) • Pin tasks in the agent Command Center with p and keep them in a shared Pinned group when supported by the server. (#51500)…
Read the official notes →Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block • Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely…
Read the official notes →Claude Haiku 5.5, Anthropic’s newest lightweight model, is now generally available in GitHub Copilot. It is designed for fast, high-volume work like subagents, quick edits, and terminal tasks. In early…
Read the official notes →Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) • Added agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apart • Added…
Read the official notes →Secret protection should keep pace with the way you build software, whether you write code yourself or work with an AI agent. With our new purpose-built model, we’re bringing context-aware…
Read the official notes →New Features: GPT-6.1 Sol is now the default model in the bundled and Amazon Bedrock catalogs. (#49318, #49339) • Amazon Bedrock supports multi-agent V2 and Ultra reasoning on compatible models; Bedrock Mantle also accepts AWS GovCloud regions. (#49345, #49813) • Sign in to MCP…
Read the official notes →Local sandboxing for GitHub Copilot is now generally available in GitHub Copilot CLI, the GitHub Copilot app, and VS Code sessions using Agent Host. Local sandboxes give developers a secure…
Read the official notes →GitHub Copilot CLI makes it easier to choose a local model without leaving your existing workflow. Starting in CLI version 1.0.94-0, use /model to discover supported models from a running…
Read the official notes →If your Copilot usage metrics have shown agent activity or agent lines of code falling while Copilot usage kept growing, we’ve found the cause, and a fix is rolling out…
Read the official notes →fix(cli): display retry progress indicator during connection recovery (#28340) • Changelog for v0.61.0-preview.1 • Changelog for v0.61.0 • fix(cli): distinguish missing MCP enablement config from malformed JSON • fix(cli): restore paused stdin after capability detection…
Read the official notes →Added --marketplace to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it • Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for…
Read the official notes →Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission prompts • Fixed a regression in 2.1.288 where the last messages of a session could be lost when quitting
Read the official notes →See and reply to the local agents running on your computer from the Cursor iOS app.
Read the official notes →Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end • Added agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main…
Read the official notes →Bug Fixes: Preserve SYSTEMROOT, TEMP, and TMP when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment. • #51121: Backport Windows remote MCP environment preservation…
Read the official notes →Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines • Fixed the terminal freezing on short code blocks with many unclosed
Read the official notes →Added $.ui.selection() for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row • Added a built-in gh api to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters…
Read the official notes →You can now request a GitHub Copilot code review through the REST and GraphQL APIs and set the review effort level for each request. Balanced is also now the default…
Read the official notes →As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model…
Read the official notes →This week, put Copilot to work with new models, reusable workflows and desktop app automation, plus Azure canvases and VS Code improvements. GitHub Copilot Claude Sonnet 5.5 is available to…
Read the official notes →New Features: Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106) • Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112) • Start sessions outside a project with…
Read the official notes →Computer use is now available in public preview in GitHub Copilot CLI and the GitHub Copilot app on macOS and Windows. Copilot can interact with desktop applications on your behalf…
Read the official notes →This changelog covers VS Code v1.136 through v1.140, shipped throughout September 2026. September’s releases streamline agent-driven development from implementation through pull request merge. Automations handle repeatable tasks, agent merge helps…
Read the official notes →Added Claude Mods: plugins may now modify deeper behavior • Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with /plugin enable cc-plugin-you-should-know@builtin (for first-party sessions with…
Read the official notes →New Features: Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. (#49744) Full Changelog: #49744 [0.159] Backport account security setup reminders for 0.159.3 @andrewgu-oai
Read the official notes →Added a count such as "2 of 5" to the permission prompt when several permission requests stack up • Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states • Fixed several Claude Code…
Read the official notes →Bug Fixes: Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. (#49385) Full Changelog: #49385 [0.159] Backport Windows console suppression for 0.159.2 @andrewgu-oai
Read the official notes →fix(a2a-server): add early return on unsupported store in tasks metadata endpoint • Changelog for v0.61.0-preview.0 • Changelog for v0.60.0 • fix(core,acp): format MCP tool call titles as structured signatures and segregate explanations • chore(release): bump version to…
Read the official notes →New Features: Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. (#49323, #49342) Full Changelog: #49323 [0.159] Prepare 0.159.1 release backports @andrewgu-oai • #49342 [0.159] Backport GPT-6.1 Sol Bedrock catalogs…
Read the official notes →Added CLAUDE_CODE_DISABLE_WEB_FETCH environment variable to turn off the WebFetch tool • Added claude --desktop to open the Claude desktop app on the current directory, or on a session with --continue / --resume • Added claude plugin configure to show a plugin's options and…
Read the official notes →New Features: Opt-in instant_interrupt lets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141) • New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)…
Read the official notes →Added Claude Sonnet 5.5 (claude-sonnet-5-5), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads • Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you…
Read the official notes →New Features: Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. (#47639, #47896, #48118) • Connect to MCP servers that require pre-registered OAuth client secrets, including through codex mcp add…
Read the official notes →Chores: Release highlights could not be determined: the supplied PR index is empty, and the GitHub tag comparison returned 404. Full Changelog:
Read the official notes →