The latest releases of Claude Code, Codex, Gemini CLI, Copilot CLI and 9 more coding agents, with breaking changes flagged. Updated every day from GitHub.https://agentvera.dev/enhttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.316https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.316Breaking: Deprecated fast mode for Opus 4.8 as of October 30, 2026; it will be removed on November 30, 2026. After removal, fast mode requests on Opus 4.8 return an error and do not fall back to standard Opus 4.8. Migrate to Op… Added CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword off Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's own limit, set with pooled_budget on the spend limits admin API Added CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP to keep system cross-certificates that certify each other in a loop, for servers whose private CA needs one Added CLAUDE_CODE_SUBAGENT_EFFORT to set the effort level subagents run at when nothing else names one, instead of inheriting the session's Added managed.policy_mode: layered to the Claude apps gateway: every policy that matches a developer applies, each merged over the ones listed below it, not only the first Added guardrail.input_tagging on Claude apps gateway Bedrock upstreams, which wraps prompts in the input tags that an Amazon Bedrock guardrail's prompt attacks filter needs; all_messages_and_system also tags the syste…Sat, 31 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.314https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.314Added permissions.blockWritesOutsideWorkingDirectories: Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode Added an optional groups list to Claude apps gateway upstreams: only developers in the listed IdP groups are sent to that upstream, on failover too Added guardrail_trace to Claude apps gateway Bedrock upstreams, to log which Amazon Bedrock guardrail filter fired on a request, without the matched text Added idle compaction to VS Code and Claude Desktop's Code tab: a 200K+ token conversation left idle is summarized, and the summary is used on your next message if the prompt cache has expired Fixed sessions failing turn after turn with "Invalid effort level" when an organization's admin caps a model's effort: Claude Code now lowers the effort, retries, and says which level it uses Fixed claude -p exiting with code 0 and no output when startup failed; it now prints the error and exits 1Fri, 30 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.5https://agentvera.dev/en/agent-changelog/opencode/#v2.2.5Worktree and Shell Mode Shortcuts: Press ⌘⌥O on macOS or Ctrl+Alt+O on Windows and Linux to choose a worktree, and ⌘⌥B or Ctrl+Alt+B to choose its base branch. ⌘⇧X or Ctrl+Shift+X now toggles shell mode in the composer. Send Quotes From the Comment Popup: Hold ⌘ or Ctrl in the quote popup to turn its checkmark into send, or press ⌘Enter or Ctrl+Enter, to send just that quote and comment while leaving the rest of the composer untouched. Percentage Compaction Buffer: Set "compaction": { "buffer": "20%" } in opencode.json to keep a share of each model's context window free, so one setting fits models with small and large windows. Token counts still work. compaction.buffer accepts a percentage of the model's context window, such as "20%", in addition to a token count. When read misses because a folder is missing, the error names that folder and the nearest one that exists. When edit can't find oldString, the error shows the file's closest lines, or says the change is already there.Fri, 30 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.4https://agentvera.dev/en/agent-changelog/opencode/#v2.2.4Persistent Desktop Terminals: Desktop terminals now belong to the session, survive server restarts with their scrollback, and stay synchronized with the TUI and other windows. Renamed terminals also keep their names a… Publish Interactive Artifacts: Enable "experimental": { "artifacts": true } in opencode.json to let agents publish, update, and serve HTML or static artifacts through the built-in local provider or plugin-provided sto… Guided Claude Agent Setup: Select Claude Agent from the provider picker to copy claude auth login, install Claude Code, and verify the connection before continuing to model selection. Choose a Base Branch Quickly: While creating a worktree, open Choose base branch with ⌘⌥. on macOS or Ctrl+Alt+. on Windows and Linux. The command is also available in the command palette and Settings › Shortcuts. Added opt-in artifacts with artifact_create, artifact_read, artifact_update, and artifact_delete, including a built-in local static-file provider. Made enabled schedules run under opencode serve and coordinated multiple server processes so a schedule fires only once. Schedules remain opt-in through experimental.schedules.Fri, 30 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.3https://agentvera.dev/en/agent-changelog/opencode/#v2.2.3Use Claude Code in OpenCode: Install Claude Code, run claude auth login, then select Claude Agent in /connect to use your Claude Code login and models. Faster Long Sessions in Desktop: Streaming replies and long conversations now do much less rendering work. Desktop Stability Fixes: Fixes side-panel tabs, repeated "Session not found" toasts, and Open file over HTTP. Added the built-in Claude Agent provider. Install Claude Code, run claude auth login, and select Claude Agent in /connect; OPENCODE_CLAUDE_PATH can override the Claude executable. Thanks @Tarquinen. Added Code Mode JavaScript checks to experimental schedules, including statically authorized tool calls, persistent state, and custom wake messages. Added separate managed-policy actions for connecting to integrations and using integrations, MCP servers, skills, and plugins.Fri, 30 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.4https://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.4/release-notes (alias /whatsnew) browses the release notes of every Vibe version in a searchable, full-screen view. Provider option preserve_api_base = true keeps a custom api_base that /whoami would otherwise overwrite (split-horizon / proxied deployments) VIBE_TERMINAL_KEY names the terminal --continue uses; an empty value makes it ignore the terminal Setup warns when an API key set in your shell overrides the key it saves. /whoami shows which credential source (shell, .env, or keyring) is in use. vibe -p --system-prompt-file PATH replaces Vibe's own instructions in the system prompt with the file's text.Fri, 30 Oct 2026 12:00:00 GMTMistral Vibehttps://agentvera.dev/en/agent-changelog/codex/#v0.166.0https://agentvera.dev/en/agent-changelog/codex/#v0.166.0Added keyboard-driven transcript selection with word, line, and page motions, integrated search, and configurable shortcuts. Rendered Markdown consistently in async questions, choices, answers, and transcript replies. Added GPT-6.1 Terra to the bundled, Vertex AI, and Amazon Bedrock model catalogs. Added codex queue --resume to resume unloaded threads after queueing a message. Added clearer safety-block explanations and selectable safer follow-up prompts in the TUI. Added codex doctor --network-only for focused configuration, connectivity, and WebSocket diagnostics.Thu, 29 Oct 2026 12:00:00 GMTCodex CLIhttps://agentvera.dev/en/agent-changelog/crush/#v0.99.0https://agentvera.dev/en/agent-changelog/crush/#v0.99.0completions: OpenAI-compatible APIs responses: OpenAI, or anything routed through it messages: Anthropic-compatible APIs --can-reason is now --thinking always|never|toggleable --max-attachments N is new Reasoning levels show friendly names in the picker, like "X-High"Thu, 29 Oct 2026 12:00:00 GMTCrushhttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.2https://agentvera.dev/en/agent-changelog/opencode/#v2.2.2Image Generation by Default: When a connected provider supports image models, agents can now use experimental_image_generate without additional configuration. Set its preferred model through experimental.image_generat… Faster Worktree Selection: On the new-session screen, click the current Git branch to open that project’s “Run session in” worktree picker directly. Unified Quotes and Annotations: Timeline quotes, terminal quotes, and browser annotations now share a compact optional-comment editor, while source highlights remain attached to local drafts. Enabled experimental_image_generate by default when an image-capable provider is connected. Recorded the start time of each session’s latest execution. Rejected persistent terminal requests whose working directory no longer exists.Thu, 29 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.1https://agentvera.dev/en/agent-changelog/opencode/#v2.2.1Breaking: Group experimental generated-client methods under client.experimental; previous locations remain as deprecated aliases until the next minor release. Keep Working Toward a Goal: Run /goal in the TUI or Desktop to let the session continue until a reviewer confirms the objective is met. Use /goal pause, /goal resume, or /goal clear to control it. Generate Images: Enable experimental.image_generate to let agents create or edit images with the new image_generate tool. You can optionally set its default model with experimental.image_generate.model. Inspect Background Shells: Click a running shell in the Desktop activity pill to see its live output and stop it without leaving the menu. New Default Model Picker: Search favorites, recent models, providers, and variants from the redesigned model picker, which is now the default in Desktop. The fal, Black Forest Labs, Replicate, and Stability providers are removed, along with their ./providers/fal, ./providers/black-forest-labs, ./providers/replicate, and ./providers/stability entry points. Five legacy entry points are removed. Import the nested paths instead, which 2.2.0 already exports: ./providers/amazon-bedrock-mantle → ./providers/amazon-bedrock/mantle, and ./providers/google-vertex-chat, -interacti…Thu, 29 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.4https://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.4feat(generated-ui): follow the host theme in generated views feat(ci): bound autofix takeover with a round budget feat(verify-pr): make "re-verify after update" a follow-up trigger feat(extensions): support unscoped npm installation and updates feat(web-shell): move no-workspace sessions beside workspaces feat(managed): add independent worktrees for main sessionsThu, 29 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.105https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.105Selecting Copilot Fusion High or Max in /model now works from long-context sessionsWed, 28 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/goose/#v1.57.0https://agentvera.dev/en/agent-changelog/goose/#v1.57.0Allowlist: require HTTPS and validate redirects, block on policy failure Allow callers to supply Goose session IDs Linux window icons restored in desktop app OpenRouter: resolve variant suffixes like :free and :nitro to the base model Use catalog_provider_id for vision lookup on custom providers Desktop: start the agent only once after a forkWed, 28 Oct 2026 12:00:00 GMTGoosehttps://agentvera.dev/en/agent-changelog/opencode/#v1.19.5https://agentvera.dev/en/agent-changelog/opencode/#v1.19.5Failed TUI worker requests now return an error instead of leaving the caller hanging. (@Nowaker) @Nowaker: fix(opencode): answer a failed TUI worker request instead of hangingWed, 28 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.3https://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.3Generated UI cards keep inputs and state across navigation and split views, show live views after initial calculation, and appear only for clients that can render MCP Apps. Persistent session Workflow mode can be enabled with --workflow-mode on, /workflows mode on, SDK, or ACP, and workflow switches now reach the CLI sandbox. Tool results shrink to remaining headroom before auto-compaction, and qwen-latest-series- or qwen4 aliases are detected with 1M-token context windows. Valid XML tool calls are recovered when parameters quote other call markup, malformed blocks are isolated, and quoted examples are not dispatched. ACP and daemon clients keep rewind identity consistent across retries, cancellations, checkpoints, recordings, and notifications, while SDK frames preserve subagent identity. /autofix-pr start stops when the PR head branch has unpushed commits or uncommitted changes, preventing the watch from overwriting unseen work.Wed, 28 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.312https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.312Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub, such as Microsoft Entra ID's oid Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place Fixed per-directory and paths: skills not being found after a Bash cd deeper into a git repository Fixed a rare case where the first reply after resuming a session in the terminal could be missing the next time the session was resumedTue, 27 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/codex/#v0.165.0https://agentvera.dev/en/agent-changelog/codex/#v0.165.0Added a built-in Google Cloud Vertex AI provider, configured with model_provider = "gcp". Added GPT-6.1 Terra to the model catalogs. Added a repository filter to the session picker and directory grouping to the agent command center, making it easier to navigate sessions across linked worktrees. Added experimental attached thread forks to the app-server API. Enabled reasoning effort changes during a conversation by default for supported models. Enabled memory v2 by default for fresh profiles and added support for importing external-agent memories into it.Tue, 27 Oct 2026 12:00:00 GMTCodex CLIhttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.104https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.104Breaking: When a saved Auto preference is no longer available, Auto falls back to its default preference instead of failing each turn Managed model "fusion" now starts sessions on Auto and applies fusionTier settings Interactive and SDK Autopilot sessions keep waiting for attached background tasks instead of stopping after COPILOT_TASK_WAIT_TIMEOUT_SECONDS; -p --autopilot still honors it When a saved Auto preference is no longer available, Auto falls back to its default preference instead of failing each turn Assisted Permissions are available without enabling experimental mode.Tue, 27 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/gemini-cli/#v0.66.0https://agentvera.dev/en/agent-changelog/gemini-cli/#v0.66.0Update ROADMAP.md to no longer reference outdated 2025 roadmap Changelog for v0.65.0-preview.0 chore(release): bump version to 0.66.0-nightly.20261013.g204db94ae Changelog for v0.64.0 fix(ui): implement synchronized output and isolate spinner rendering fix(ui): fix debug console height calculation and terminalBuffer flickeringTue, 27 Oct 2026 12:00:00 GMTGemini CLIhttps://agentvera.dev/en/agent-changelog/opencode/#v2.2.0https://agentvera.dev/en/agent-changelog/opencode/#v2.2.0Create, install and share Desktop plugins (experimental) Refreshed the desktop app experience Add experimental image and decision generation APIs to plugins and sdk, allowing image generation or decision model (think typesafe, clef, etc) workflows. Plugins can now attach and update keyed session instructions with ctx.session.instructions.entry.put/list/remove. Instead of editing the system prompt and busting the prompt cache, each change is added as a small upda… Restored the Todo tool in desktop via opt-in Add configurable prompt cache TTLs per provider/modelTue, 27 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.2https://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.2fix(managed-agent)!: simplify Web Shell controls and retire cwd submissions feat(managed): add session permission rules and Auto approval feat(core): add an experimental shared agent loop and run headless on it Adds X-DashScope-Source-Config to matching QwenCloud and Qianwen AI Platform requests to identify site and client, without changing authentication or retries. Resumed OpenTUI sessions now retain recorded text, images, tool results, and prompt identities, while rewind restores transcript, request, and draft. OpenTUI now captures complete checkpoints at edit approvals and restores them safely, preserving conversation metadata and blocking stale or cancelled owners.Tue, 27 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.311https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.311Added --hold-idle-file and --max-hold-min to self-hosted-runner, to keep an idle session while your host reports processes it left running Added a tip for the Explanatory output style, shown when you ask Claude for explanations Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues Fixed Write and Edit stalling for up to 5 seconds after they ran, and reporting 0 lines changed, when changing thousands of lines in a fileMon, 26 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/cline/#v4.1.26https://agentvera.dev/en/agent-changelog/cline/#v4.1.26Cloud tasks: Settings > API Configuration has a Local | Cloud toggle when cloud sessions are on. Cloud picks the Cline model new cloud tasks run on, saved separately from your local models. Clicking the model label in… Starting or resuming a cloud sandbox shows a progress card with the repo, branch and steps (start sandbox, clone repository, start agent). It collapses once the agent starts. Cloud sessions hide the Plan/Act toggle and the auto-approve bar instead of showing them disabled. With no model chosen, the Cline provider uses Claude Sonnet 5.5 again, which is back at the top of Cline's recommended list. Model requests retry at most 3 times instead of 5. Kimi K3 now gets max reasoning for Extra High and Max, instead of an xhigh setting it rejects.Mon, 26 Oct 2026 12:00:00 GMTClinehttps://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.3https://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.3Breaking: [Breaking — config] auto_compact_threshold = 0 is now a config error; set a positive threshold or remove it to use the model's default Breaking: [Breaking — models] A reply without token usage fails the turn; third-party model servers must support stream_options.include_usage Breaking: [Breaking — config] A model's max_output_tokens no longer caps replies; it is only sent to providers that require an output limit Breaking: [Breaking — sessions] Images in sessions saved by Vibe 3.0.2 reach a model without image input as [Image], without their file link Breaking: [Breaking — shell timeouts] Shell timeout settings that are invalid, set one without the other, or clash with the lean profile are now refused as config errors. An agent file with such a setting, or any other invalid… Skills added or edited on disk are picked up by running sessions without /reload The footer shows the active model and its thinking level next to the token counter, and updates after /model, /thinking or a resume. Clicking the model in the footer opens /model while no turn is running, keeping the prompt being typed. The / menu starts each skill's description with its scope (project, user or vibe), setting skills apart from built-in commands. post_agent hooks accept match to run only after a given agent, or after the main agent with match = "main". The post_agent hook payload includes agent_name, the configuration name of the agent that finished its turn.Mon, 26 Oct 2026 12:00:00 GMTMistral Vibehttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.1https://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.1fix(qqbot)!: restore per-group session isolation under thread scope Adds opt-in daemon token persistence: qwen daemon start --save-token stores the bearer token in an owner-only file, qwen daemon token manages it, and daemon stop removes it. Adds idle-only manual context compression for Workspace-bound Managed Sessions via public API and the WebShell context-usage popover, preserving audit history. Aligns OpenTUI input, editing, drafts, and /statusline behavior with Ink, adding configurable status lines and more predictable completion, queue, and cancel handling. feat(shell): remind the model to record files a command writes Managed Workspace recovery now waits for durable settlement before continuing, shows recovery reasons and valid actions in WebShell, and gates message sending.Sat, 24 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.310https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.310Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too Fixed requests failing behind some gateways and compatible servers that reject the effort-2025-11-24 beta value or mid-conversation system messages; Claude Code now retries without them Fixed background cleanup deleting some recent files, such as pasted images, when cleanupPeriodDays is set to a very large value Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again Fixed file read permission prompts not showing where a symbolic link leads Fixed a question's auto-continue timeout firing the moment the external editor closed after a long editFri, 23 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/codex/#v0.164.0https://agentvera.dev/en/agent-changelog/codex/#v0.164.0Save reusable prompts and slash commands in ten numbered /presets slots, with a keyboard menu for quick access. Set model, reasoning effort, speed, and permission profiles directly with inline /model and /permissions arguments. Preview viewed and generated images in the fullscreen transcript on terminals supporting Kitty or Sixel graphics. Authenticate enterprise MCP connections using eligible Codex account grants or dedicated sign-in, including OAuth clients requiring secrets. Mask credentials during supported remote Bash commands and Zsh snapshot sessions, including credentials from custom providers. The Amazon Bedrock setup wizard is now enabled by default, with API key entry grouped alongside other AWS sign-in methods when credentials are detected.Fri, 23 Oct 2026 12:00:00 GMTCodex CLIhttps://agentvera.dev/en/agent-changelog/crush/#v0.98.2https://agentvera.dev/en/agent-changelog/crush/#v0.98.2Fri, 23 Oct 2026 12:00:00 GMTCrushhttps://agentvera.dev/en/agent-changelog/goose/#v1.56.0https://agentvera.dev/en/agent-changelog/goose/#v1.56.0Automatic thinking level operation for improved model reasoning Resume failed or cancelled delegate subagents Subagent session link in UI with view-only subagent sessions Limit concurrent subagents with GOOSE_MAX_CONCURRENT_SUBAGENTS Report session status via OSC 7501 in CLI Windows NSIS installer for desktopFri, 23 Oct 2026 12:00:00 GMTGoosehttps://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.5https://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.5Microsoft Store app: updates through the Store. Desktop app installed from the installer (.exe / .dmg): no change in this release; it updates with the next bundled release. CLI: hermes update, or re-run the installer one-liner. Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).Fri, 23 Oct 2026 12:00:00 GMTHermes Agenthttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.309https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.309Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command Fixed macOS sandbox denyWrite glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with --mcp-config Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open Fixed Bash permission checks not prompting for some compound commands that change directory before running git when the cd is wrapped or prefixed, as they do for a plain cdThu, 22 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.308https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.308Bug fixes and reliability improvementsThu, 22 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.103https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.103Clicking a completed response code block copies its original code when enabled. ACP sessions now honor saved sandbox settings and --sandbox/--no-sandbox flags, including on resume. Cloud replies keep full text when the CLI reconnects after a dropped connection Sessions browser shows a session's recorded title instead of a generic Session N fallback when available Model-specific default Responses verbosity now applies correctly for GPT-5 models unless session verbosity is explicitly set Allow dnx commands to use existing .NET and NuGet sandbox grants when developer-tool access is enabledThu, 22 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/opencode/#v1.19.4https://agentvera.dev/en/agent-changelog/opencode/#v1.19.4Upgraded the bundled Bun runtime to 1.4.4, which includes security fixes for Brotli, TLS, HTTP/1.1, HTTP/2, HTTP/3, WebSocket, and fetch, and updates root certificates to NSS 3.131.1.Thu, 22 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.2https://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.2enable_mouse_capture setting (or VIBE_ENABLE_MOUSE_CAPTURE=false) to leave text selection and copy to your terminal; depending on the terminal, some other mouse interactions such as clicks are disabled too. Added max_subagents and max_concurrent_subagents settings to control how many subagents can be alive and running at once In VS Code, connectors that need no login, such as DeepWiki, show as Not connected and connect in one click, instead of asking an admin to set them up. An image sent to a model that does not support image input no longer fails the turn. The model gets the text "[image]" in place of the image, and the session continues. Shortened the copy hint so it fits in narrow terminals. The model's reasoning now shows by default, as a collapsible "Thought" row.Thu, 22 Oct 2026 12:00:00 GMTMistral Vibehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.307https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.307Added /claude-api api-version to move Claude API code to API version 2026-10-21 Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back Fixed requests failing with a model-not-found error when CLAUDE_CODE_DISABLE_1M_CONTEXT is set and the model is an alias with the [1m] suffix, such as opus[1m] Fixed the prompt-caching-scope beta header being sent behind custom ANTHROPIC_BASE_URL gateways and on Foundry, where it has no effect Fixed MCP servers showing "needs authentication" in claude -p on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in Fixed MCP servers being reported as timed out, and staying failed in headless runs, when a macOS or Linux computer went to sleep while they were connectingWed, 21 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.306https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.306Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP toolsWed, 21 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.102https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.102Prompt mode now honors managed Auto model selection for -p and piped stdin runs Subagents honor custom and MCP tool approvals, avoiding duplicate permission prompts and allowing inherited workflows to run Plugin marketplaces accept git-subdir sources and long plugin descriptions Fish shell completion works when aliases include option aliases like --effort Chats no longer get blocked by organization plugin preparation while sending messages Long-running sandboxed commands continue running reliably past 10 secondsWed, 21 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.4https://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.4Desktop no longer shows suggestion pills above the composer. The pills appeared for no clear reason, mostly nudging you to set up MCP servers. They and the helpers that only they used are gone. Plugins that install nothing skip the dependency consent step. A plugin that declares no dependencies, or whose pyproject.toml installs nothing, now enables without an empty consent prompt. Dashboard: WhatsApp can be safely re-paired after logging out. Desktop plugin review: the surface lint no longer flags prototype writes; reviewers check them by hand. Desktop: the approval-mode chip follows the active profile's mode. Release builds: the desktop bundle's pre-build check gets enough time to verify archived build inputs when storage is slow.Wed, 21 Oct 2026 12:00:00 GMTHermes Agenthttps://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.3https://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.3Microsoft Store app: updates through the Store. Desktop app installed from the installer (.exe / .dmg): no change in this release; it updates with the next bundled release. CLI: hermes update, or re-run the installer one-liner. Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).Wed, 21 Oct 2026 12:00:00 GMTHermes Agenthttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.0https://agentvera.dev/en/agent-changelog/qwen-code/#v0.26.0feat(daemon): support session-targeted Skill and Extension refresh feat(runtime-broker): Session-create warm for Workspace-isolated bound Sessions feat(managed-agent): ship a configuration template in the reference distribution feat(serve): run private CSI file turns through Hosted Harness feat(managed-agent): support local and SSH workspace file references Adds a read-only --check preflight that prints PASS, WARN, FAIL, or SKIP for managed-agent deployment checks and exits nonzero on failure.Wed, 21 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.305https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.305Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of --tools (a 2.1.304 regression): Clau… Fixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag Fixed new worktrees in a bare repository sometimes starting from local HEAD instead of the default branch, and unchanged subagent worktrees sometimes not being cleaned up Fixed Bash commands on a full disk failing with a raw ENOSPC file path: the error now says the disk is full and that nothing ranTue, 20 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.101https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.101Add native structured output for dynamic workflow subagents on supported models Add assistedApprovalInstructions setting to guide Assisted Permissions confirmation decisions Shell commands that create and then enter a directory now request path approval instead of being denied early. Headless and SDK sessions without an OAuth handler skip MCP connections when saved tokens require sign-in, while renewable grants still connect. macOS sandboxed commands can connect directly to localhost TCP services when local access is enabled and no host filters apply. Local models and loopback providers in providers.json no longer block Auto, your saved model or the default model when signed in to CopilotTue, 20 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/gemini-cli/#v0.65.0https://agentvera.dev/en/agent-changelog/gemini-cli/#v0.65.0fix(cli): enforce read-only workspace settings in untrusted folders fix(core): avoid duplicate tool response turns when resuming sessions fix(core): prevent deletion of resumed session history on quick exit Changelog for v0.64.0-preview.0 Changelog for v0.63.0 fix(core): align OAuth callback iss parameter validation with RFC 9207 metadataTue, 20 Oct 2026 12:00:00 GMTGemini CLIhttps://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.1https://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.1New enable_auto_approve setting: when the admin-managed config sets it to false, the auto-approve (YOLO) mode is forbidden — the auto-approve agent (and any custom agent with safety = "yolo") is hidden and --auto-appr… compaction_max_output_tokens (80000), compaction_thinking (unset), compaction_reasoning_limit_tokens (32000), output_limit_retries (6) and output_token_reserve (4096) settings tune compaction requests and recovery fro… The app server has experimental session/subagents/wait, session/subagents/interrupt and session/subagents/read methods: a client can wait for the subagents a turn left running, interrupt them, and read each one's stat… vibe -p waits for the subagents its turn left running before it exits; --time-limit and other stops interrupt them, and the --output-dir export lists each subagent with its status, model, usage, cost and steps, and co… Each subagent's cost is priced at its own model's rates; when its model is unknown, the root's rates price it and the row says so (pricingModel, pricingFallback) An --agent-socket server's tools/call names its caller, so the server can tell a subagent's call from the root'sTue, 20 Oct 2026 12:00:00 GMTMistral Vibehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.304https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.304Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only Added /auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled… Added /claude-api managed-agents-secure, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)Mon, 19 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.100https://agentvera.dev/en/agent-changelog/copilot-cli/#v1.0.100Add --disable-client-telemetry flag to turn off client telemetry uploads from the CLI Add --trust-folder for one-off prompt-mode sessions started with -p or piped stdin Install verified Skills and plugins from GitHub install links via copilot plugin install "ghapp://air/install?..." Open /share without arguments to view a full-screen action menu for sharing the current session Sandbox host-rule traffic now honors HTTPS_PROXY and HTTP_PROXY when no sandbox proxy is configured Voice dictation no longer inserts language markers like into transcript textMon, 19 Oct 2026 12:00:00 GMTCopilot CLIhttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.25.3https://agentvera.dev/en/agent-changelog/qwen-code/#v0.25.3Adds optional model-generated layouts to Test Failure Explorer, with validation and fallback to the fixed view The Web Shell mobile composer no longer shows the ↑ and ↓ history buttons, reducing clutter while keeping history search available. The Web Shell trajectory panel now includes a collapsible Recent executions section that shows live requests and tools with elapsed time and final durations. Managed sessions created from published AgentDefinitions can now load static Skills and pass pinned MCP server and Hook catalog selections to Hosted Runtimes. Files now offers New file and New folder actions, and folder Delete asks for a second confirmation before permanently removing the folder and its contents. Eligible legacy cancellations now require confirmation through the daemon or WebShell Continue flow before continuing, while explicitly user-cancelled work stays blocked.Mon, 19 Oct 2026 12:00:00 GMTQwen Codehttps://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.0https://agentvera.dev/en/agent-changelog/mistral-vibe/#v3.0.0Breaking: displayed_workdir, context_warnings and raise_on_compaction_failure are deprecated: they remain accepted in existing configs but have no effect on Unified execution. Breaking: Removed the retired legacy execution runtime while preserving Unified execution and read-only imports of Vibe 2.0+ session folders (meta.json and messages.jsonl). Vibe 1.x single-JSON sessions are no longer supported. The app-server reports each model's compaction threshold, so a client can show how full a session's context is before it compacts. Desktop can import projects and sessions from another coding agent during onboarding. Rust CLI: /leanstall and /unleanstall install and uninstall the Lean agent. With experimental_enable_model_catalog on, the model list includes Mistral's curated models, and your config can still override their settings. Rust CLI: Tool approval options, /thinking levels, /resume sessions and /log-level rows and badges can be clicked. Rust CLI: Option lists show a faint hover background under the mouse.Mon, 19 Oct 2026 12:00:00 GMTMistral Vibehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.303https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.303Bug fixes and reliability improvementsSun, 18 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.302https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.302Added 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 compaction now say how to turn it off Added a notice to /design-sync and /design-login that standalone Claude Design (claude.ai/design) closes by December 14, 2026 Fixed a "Prompt is too long" error when stopping a turn while the conversation was being compacted Fixed requests failing with "diagnostics: Extra inputs are not permitted" after switching to Vertex or Bedrock mid-session Fixed the Read tool loading an image file of any size, or a pipe or device named like an image, entirely into memory; image sources over 128 MB are now refusedFri, 16 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/cline/#v4.1.25https://agentvera.dev/en/agent-changelog/cline/#v4.1.25Cline Cloud sessions, rolling out gradually: run a task in a hosted sandbox on a GitHub repo and branch you pick. Turn it on in Settings. Cloud tasks show in Recent and History with their status, notify you when they… With no model chosen, the Cline provider now uses Gemini 4 Argon, the new first model in Cline's recommended list. OpenRouter stays on Claude Sonnet 5.5. Refreshed the model catalog. Adds the Boundless and Standard Compute providers, and SambaNova now comes from the catalog with MiniMax M3 as its default. The Cline recommended list adds Gemini 4 Argon and drops Grok 4.… Long requests to local models (LM Studio, Ollama) no longer fail after 5 minutes of silence with terminated: BodyTimeoutError while the server is still processing a large prompt. OpenAI Compatible base URLs are used exactly as entered. A host-only URL like https://abc.com used to get /v1 added silently. Host-only URLs saved by earlier versions get /v1 added once, so existing setups keep working. Images and files attached to an answer to one of Cline's questions now reach the model instead of being dropped.Fri, 16 Oct 2026 12:00:00 GMTClinehttps://agentvera.dev/en/agent-changelog/goose/#v1.55.0https://agentvera.dev/en/agent-changelog/goose/#v1.55.0AIgateway declarative provider Propagate W3C trace context from ACP prompts to MCP tool calls Surface provider x-request-id on responses and errors Honor supports_vision declared on custom provider models Use live model metadata for OpenAI reasoning and prefer the Responses API Cap auto-compaction at 225k tokens by defaultFri, 16 Oct 2026 12:00:00 GMTGoosehttps://agentvera.dev/en/agent-changelog/opencode/#v1.19.3https://agentvera.dev/en/agent-changelog/opencode/#v1.19.3Configure model reasoning options to generate reasoning variants, replacing catalog variants while preserving your configured variant overrides.Fri, 16 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/opencode/#v1.19.2https://agentvera.dev/en/agent-changelog/opencode/#v1.19.2OpenCode 1 now stays on the 1.x release line: update checks use only the npm opencode-ai latest version, so 1.x installs are never offered a 2.x build as a regular update. Upgrading to OpenCode 2 remains a separate, explicit choice through the 2.0 offer in /update or opencode upgrade --major. Fix upgrades for installs managed by yarn. Skip 1.x updates for Homebrew Core installs, which now track OpenCode 2, and check tap and Chocolatey availability before offering an update. The install script refuses to install 2.x versions.Fri, 16 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/claude-code/#v2.1.301https://agentvera.dev/en/agent-changelog/claude-code/#v2.1.301Added 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 destinations with the ant CLI Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rules Added classifier_category to OpenTelemetry tool_decision events, naming the built-in rule a classifier block matched, when OTEL_LOG_TOOL_DETAILS=1Thu, 15 Oct 2026 12:00:00 GMTClaude Codehttps://agentvera.dev/en/agent-changelog/codex/#v0.163.0https://agentvera.dev/en/agent-changelog/codex/#v0.163.0Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls. Configure a leader key in /keymap. The default is Ctrl+X, shortcut hints stay open until you choose or cancel, and voice mute moves to F9. Restart a managed background server from /daemon. Codex warns about work the restart could interrupt, then reconnects automatically. Codex can run independent read-only tools in parallel, including skill, memory, and conversation-history lookups. Daybreak is enabled by default for eligible accounts. codex exec can also select it with an OpenAI API key when the server offers access.Thu, 15 Oct 2026 12:00:00 GMTCodex CLIhttps://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.2https://agentvera.dev/en/agent-changelog/hermes-agent/#v0.22.2The gateway starts after a reboot again. After a restart, Linux can hand an early PID to an unrelated process, and the gateway could mistake it for a running gateway, so a supervised gateway (systemd, launchd, Docker)… Long local-model turns survive on laptops. Local requests always stream with prompt-reading progress (shown in the status line), stall timers skip time the machine was asleep, a recovered local server gets another try… Release: split the Microsoft Store bundle into its own windows-store lane (f9d8a740) — Agent: add nemotron super 3.5 default parameters (c59d2994) — Cli: add nemotron to NVIDIA NIM default model list (cc55270e) — Cli: add curated model list at the top in the model picker list (e6835fd3) —Thu, 15 Oct 2026 12:00:00 GMTHermes Agenthttps://agentvera.dev/en/agent-changelog/opencode/#v1.19.1https://agentvera.dev/en/agent-changelog/opencode/#v1.19.1Breaking: Session sharing has been discontinued. Existing share links and session-sharing commands are no longer available, and importing sessions from share URLs is unsupported. Session sharing has been discontinued. Existing share links and session-sharing commands are no longer available, and importing sessions from share URLs is unsupported.Thu, 15 Oct 2026 12:00:00 GMTopencodehttps://agentvera.dev/en/agent-changelog/qwen-code/#v0.25.2https://agentvera.dev/en/agent-changelog/qwen-code/#v0.25.2feat(managed-agent): H4e-b2 the lead's mailbox over Session messages A new private extension imports Vitest 3.2 JSON reports and exposes failures, errors, counts, and diagnostics through MCP tools with search and pagination. Opt-in headless Mods now support TypeScript authoring, relative imports, typed non-secret configuration, and dependency validation before startup. Adds a default-off option allowing authorized public REST and WebShell sessions to use foreground Shell with mandatory approval. feat(managed-agent): Introduce the EventTransport seam behind the after-commit publisher feat(managed-agent): Stop Hosted team members with request_shutdown (H4e-b3a)Thu, 15 Oct 2026 12:00:00 GMTQwen Code