Add Claude Opus 5 across the Anthropic, Claude Code, Bedrock, Vertex, Cline, and OpenRouter providers, including 1M context window variants. · Add Moonshot Kimi K3 support. · Include the host plugin version in telemetry events. · Correct pricing for the Claude Opus 1M context variants, which overstated costs for requests above 200k tokens. · Enable native tool calling for Kimi K3 models, fixing empty responses.
Primary source ↗Start chatting without opening a project folder — the app now supports workspace-free chat sessions. · New first-run onboarding flow to get you set up on launch. · Drag and drop files directly onto the chat to attach them. · Image attachments now display inline in the chat transcript. · Schedule one-time routines (not just recurring ones), with navigation to jump to a routine's run.
Primary source ↗The reasoning section in the chat transcript now reads simply "Thinking" — dropped the redundant status text and brain icon. · **Full Changelog**: https://github.com/cline/cline/compare/desktop-v0.0.2...desktop-v0.0.3
Primary source ↗Rolling release backing the desktop app auto-updater. The latest.json asset points at the newest desktop-vX.Y.Z release. Do not delete.
Primary source ↗First public release of Cline Code for macOS: a desktop app for running and inspecting Cline agent sessions, signed and notarized for Apple Silicon and Intel. · Automatic updates: the app checks on launch and every 2 hours, downloads new versions in the background, and prompts for a one-click restart. Ignored updates apply on the next launch. · Download the DMG once from GitHub Releases — every future release arrives automatically.
Primary source ↗Add telemetry to track when Cline reaches the consecutive mistake limit. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.9...v4.0.10
Primary source ↗Fixed out-of-credits detection so the CLI reliably recognizes the Cline API's real `insufficient_credits` (402) error and shows the "add credits" card instead of a generic error · **Full Changelog**: https://github.com/cline/cline/compare/cli-v3.0.45...cli-v3.0.46
Primary source ↗Smaller install: the Claude Code and Codex providers are now optional and loaded on demand, cutting `npm i -g cline` from ~640MB to ~285MB (from SDK v0.0.65) · Kimi K3 is now available as a ClinePass model (from SDK v0.0.65) · Runs now retry once after refreshing expired OAuth credentials (from SDK v0.0.65) · Team runs: the spawn tool is no longer exposed to teammates, and errored teammate runs now report as failed instead of completed (from SDK v0.0.65) · Hub status output now includes version
Primary source ↗Claude Code and Codex provider SDKs are now optional peer dependencies loaded on demand, dramatically cutting install size · Added Kimi K3 to the bundled ClinePass model fallback · Runs now retry once after refreshing expired OAuth credentials · Team runs: the spawn tool is no longer exposed to teammate agents · Team runs: errored teammate runs now report as failed instead of completed
Primary source ↗Improved max output token handling across providers (gateway routing, OpenAI vendor, and reasoning models) (from SDK v0.0.64) · Frontmatter and configuration files that start with a UTF-8 byte order mark (e.g. saved by Windows editors) now parse correctly (from SDK v0.0.64) · **Full Changelog**: https://github.com/cline/cline/compare/cli-v3.0.43...cli-v3.0.44
Primary source ↗Improved max output token handling across providers (gateway routing, OpenAI vendor, and reasoning models) · Frontmatter and user-instruction files that start with a UTF-8 byte order mark (e.g. saved by Windows editors) now parse correctly · **Full Changelog**: https://github.com/cline/cline/compare/sdk/sdk/v0.0.63...sdk/sdk/v0.0.64
Primary source ↗The CLI now automatically trusts your operating system's certificate store, so it works behind corporate proxies and TLS-inspecting firewalls without manually setting `NODE_EXTRA_CA_CERTS` (fixes "unable to get local issuer certificate" errors, including Windows intermediate CA stores) · **Full Changelog**: https://github.com/cline/cline/compare/cli-v3.0.42...cli-v3.0.43
Primary source ↗The session runtime now emits `task.mistake_limit_reached` telemetry when the consecutive-mistake limit is hit, so every host (CLI, VS Code extension, hub daemon) captures it — including auto-stops when no host prompt is configured · **Full Changelog**: https://github.com/cline/cline/compare/sdk/sdk/v0.0.62...sdk/sdk/v0.0.63
Primary source ↗Add GPT-5.6 ChatGPT subscription models. · Soften and shorten the message shown when Cline hits the consecutive mistake limit. · Handle cumulative usage snapshots from OpenAI-compatible providers so token counts are no longer over-reported. · Load skills from files saved as UTF-8 with a byte-order mark (BOM). · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.8...v4.0.9
Primary source ↗Fixed Ollama native API routing so context window and timeout settings work again · **Full Changelog**: https://github.com/cline/cline/compare/cli-v3.0.41...cli-v3.0.42
Primary source ↗Fixed Ollama native API routing so context window and timeout settings work again · Telemetry is no longer attached to hub tool contexts · **Full Changelog**: https://github.com/cline/cline/compare/sdk/sdk/v0.0.61...sdk/sdk/v0.0.62
Primary source ↗Compaction now shows progress status in the TUI · Model IDs are now suggested from OpenAI-compatible endpoints when configuring a provider · Workspace git info (branch/remote) is now persisted and refreshed across sessions · Compaction no longer runs during an active turn · Fixed a crash when the terminal title was updated during TUI teardown
Primary source ↗Context compaction now reports progress status while it runs · Workspace git info (branch/remote) is now persisted and refreshed across sessions · Fixed benign git states being reported as workspace initialization errors · Plan/Act mode guidance added to the system prompt, with nudges when switching modes · Editor diff view restored for SDK edit tools
Primary source ↗Added a manual API key escape hatch for Cline OAuth providers, so you can enter a key by hand from settings · Fixed provider config not reloading when switching models · Fixed auto-update failing to detect Bun global installs after symlink resolution · Fixed unexpected logouts caused by transient network or server errors during token refresh · The ClinePass usage-limit error is now surfaced clearly when you hit the limit
Primary source ↗Add more models to the GCP Vertex provider, plus a free-form entry option in the model dropdown for specifying custom Vertex models. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.7...v4.0.8
Primary source ↗You can now select Cline free models on the ClinePass provider in the model picker · Removed the retired ClinePass GLM 5.1 model · Fixed OpenAI Codex model metadata under the GPT Subscription provider · `str_replace` edits now report accurate diffs · Fixed context compaction so canonical session history is preserved
Primary source ↗Add a ClinePass limit-reached error with a one-click option to switch to Cline usage-based billing. · Allow selecting Cline free models on the ClinePass provider, organized into Subscribed and Free tabs with model descriptions. · Refine ClinePass onboarding and provider settings copy, and open the "learn more" link via the in-app URL handler. · Remove the Cline model picker recommendation copy. · Remove all references to GLM 5.1.
Primary source ↗New plan/act accent palette: act mode is now blue (`#79b8ff`) and plan mode amber, replacing the old cyan/yellow — applied across dialogs, the model selector, config, onboarding, markdown, and syntax highlighting, with light-theme variants tuned for contrast · Restyled chat input: a minimal frame with full-width horizontal rules and a bold accent prompt glyph instead of the tinted background, plus slimmer user-message bubbles · Assistant markdown accents are now tinted by the mode (plan/act) the
Primary source ↗Weaker models (e.g. DeepSeek) that emit malformed tool calls — wrong argument types or truncated JSON — are now handled gracefully and run instead of erroring out · Plan/act mode switches are now visible to the model, so it knows when you change modes mid-session · Fixed plan/act mode notices being dropped from prompts sent to the model · Fixed a race where switching modes in an empty session could trigger an unexpected restart · **Full Changelog**: https://github.com/cline/cline/compare/cli-v3.
Primary source ↗Fixed plan mode's `switch_to_act_mode` tool not taking effect until the end of the turn: the model would keep running with plan-mode tools (no file editor) and fall back to editing files through shell commands. Switching to act mode now ends the plan-mode run and automatically continues with the approved plan using the full act-mode toolset. A Tab mode toggle racing a completing turn can no longer auto-start plan execution you didn't approve. · **Full Changelog**: https://github.com/cline/cline/
Primary source ↗ClinePass is now enabled for all CLI users · Recover missing interactive sessions when reading messages · Format structured commands in history export · Add the subscription promo code when linking to the dashboard subscription page · Add Tencent TokenHub as a provider (from SDK v0.0.55)
Primary source ↗Generalize the model capability warning so it applies more broadly. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.5...v4.0.6
Primary source ↗Add support for Claude Sonnet 5 across the Anthropic, Bedrock, Vertex, Claude Code, SAP AI Core, OpenRouter, and Vercel AI Gateway providers, including model picker and recommended-model updates. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.4...v4.0.5
Primary source ↗Fully remove the ClinePass feature flag so ClinePass is available everywhere in the UI — onboarding, settings, the welcome promo banner, and the credit-limit "Switch to ClinePass" action. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.3...v4.0.4
Primary source ↗Enable the ClinePass provider for all users by removing the feature-flag gate that previously fell back to the standard Cline provider. · **Full Changelog**: https://github.com/cline/cline/compare/v4.0.2...v4.0.3
Primary source ↗### Added Add the SDK-backed VS Code extension runtime. Cline now runs tasks through the shared Cline SDK session layer for agent turns, tools, Plan/Act mode coordination, MCP, checkpoints, telemetry, provider changes, compaction, mistake limits, and task history. Add ClinePass to the VS Code extension, including onboarding, provider selection, signup and subscription handoff, live model lists, en
Primary source ↗### Fixed Complete the fix for the Anthropic provider on VS Code 1.123 and later by upgrading the bundled Anthropic SDK to a release compatible with the Node 24 runtime. Update the Vertex AI provider to a compatible Anthropic Vertex SDK release so it works with the upgraded Anthropic SDK.
Primary source ↗### Fixed Restore the Anthropic provider on VS Code 1.123 and later, where the updated Node 24 runtime broke the bundled Anthropic SDK. Handle the DeepSeek V4 reasoning format.
Primary source ↗### Added Add Claude Fable 5 model support. ### Fixed
Primary source ↗### Added Add a debug section in settings for Cline testers. ### Fixed
Primary source ↗### Added Add the latest Fireworks AI serverless models and update the default Fireworks model to Kimi K2.6. ### Fixed
Primary source ↗### Added Add MiniMax M3 model support. ### Fixed
Primary source ↗### Fixed Fix `@` file mentions and workspace file search on VS Code 1.122+ by resolving the new bundled `@vscode/ripgrep-universal` per-platform binary layout before falling back to legacy ripgrep paths.
Primary source ↗### Fixed Fix `@` file mentions failing to find files in some environments (notably VS Code Remote SSH, and after certain VS Code updates) by keeping the file-search fallback alive when the workspace index or bundled ripgrep binary is unavailable.
Primary source ↗### Added Add Claude Opus 4.8 provider support, including 1M-context variants where available. Add Moonshot Kimi K2.6 model support.
Primary source ↗[github-releases] GitHub Releases
github_releases · every 120m
https://github.com/cline/cline/releases[changelog-md] CHANGELOG.md
markdown_changelog · every 180m
https://raw.githubusercontent.com/cline/cline/main/CHANGELOG.md