Cline

The reasoning section in the chat transcript now reads simply "Thinking" — dropped the redundant status text and brain icon.

ne Code desktop (auto-update feed)

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.

Add telemetry to track when Cline reaches the consecutive mistake limit.

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

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 numbers
• Updated the bundled model catalog (from SDK v0.0.65)

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
• Improved shell-command parsing to fix a Windows shell mismatch
• New `@cline/ui` agent chat components with Storybook and npm packaging
• Updated the bundled model catalog

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)

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

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)

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

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).
• ---
• _Manually created due to a GitHub API outage — the automated workflow published v4.0.9 to the VS Code Marketplace and Open VSX Registry successfully, but the GitHub API degradation caused its release-creation step to fail afterward._

Fixed Ollama native API routing so context window and timeout settings work again

Fixed Ollama native API routing so context window and timeout settings work again

• Telemetry is no longer attached to hub tool contexts

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
• The API key fallback hint is now highlighted for better visibility
• Benign git states are no longer reported as workspace initialization errors