Cline v4.1.23
Changed If a model's response ends without a recognized finish reason, Cline asks it to continue once instead of treating the response as complete. Refreshed the model catalog. The Cline recommended list adds GPT-6.1…
github.com·tool·219 items·last fetched
Changed If a model's response ends without a recognized finish reason, Cline asks it to continue once instead of treating the response as complete. Refreshed the model catalog. The Cline recommended list adds GPT-6.1…
Mermaid diagrams in chat now render inline as interactive diagrams, with copy, download, fullscreen, and pan/zoom. Links inside a diagram go through the same confirmation dialog as other links, showing the real…
MCP servers launched with `npx` or `uvx` on Windows now load. They often took longer than the 3-second startup limit and were silently dropped, so their tools never showed up. The default is now 10 seconds Claude…
Responses that end with a missing or unrecognized finish reason are no longer treated as successful completions. `AgentModelFinishReason` gains `unknown` (the AI SDK adapter maps unified `other` and missing reasons to…
Existing users get a one-time What's new dialog introducing Connectors, with connector logos, a clickable example prompt, and an Open Connectors button. You can replay it from Settings → About → Show what's new Full…
New `/compact` slash command. It summarizes the conversation so far to free up context. The summary uses your session's provider settings and is not sent to the model as a prompt Connectors is now the first and default…
Cloud sessions can now use the same models as Cline on the web. The model picker lists Cline Usage-Billing, ClinePass, and ClineFree models (organization accounts don't get ClinePass), instead of only Cline. A new…
Agent teams stay fast in long sessions and while teammates are streaming. Every streamed chunk used to re-save the whole team state, so team runs got slower over time and `~/.cline/data/db/teams.db` could grow to…
Agent teams no longer slow down as a session runs or while a teammate is streaming. Every streamed chunk and 2-second heartbeat used to re-save the whole team state, including every finished teammate's full transcript…
Custom providers added with Add Provider now work when you run a task. They showed up in the provider and model pickers but failed with `Unknown or disabled provider` New chats remember whether you last used Cloud or…
When an MCP tool returns more output than fits in context, the agent can now read the rest. It gets a preview plus a link it can page through with `read_files`, so the output past the cutoff is no longer lost Custom…
Oversized MCP and Composio tool results can now be recovered in full. Core caches the oversized output in a per-session in-memory cache and sends the model a bounded preview plus a `cline://cache/...` URI that…
On Linux with the proprietary NVIDIA driver, the app window no longer opens blank. The app now turns off WebKitGTK's DMA-BUF renderer when it detects the NVIDIA driver. To keep that renderer on (for example, on a…
Added New providers: Bee (by HEOSSI) and Pareto Inference (`PARETO_API_KEY`). Changed Direct Anthropic requests now use Anthropic's server-side refusal fallback. On OpenRouter and Cline, Anthropic models can fail over…
Linux on ARM is now supported: each release ships arm64 `.deb` and `.rpm` packages alongside the x64 ones, and they auto-update like the others Web search settings moved from General to Customize → Tools, next to the…
The CLI binaries are now built with Bun 1.4.2. macOS 27 no longer kills them at launch, and the x64 builds run on CPUs without AVX2 The hub now starts on Windows machines with a system proxy (Clash, v2ray, corporate…
Direct Anthropic requests now ask the Claude API for its recommended server-side refusal fallback (`anthropic.fallbacks: "default"`), and OpenRouter and Cline requests for Anthropic models set…
The hub now starts reliably on Windows machines with a system proxy. Bun's fetch sends loopback requests through `HTTP(S)_PROXY` with no localhost bypass, so on machines that export those variables (Clash, v2ray…
Settings has a new About page. It shows your version and channel, has Check for updates and Restart to update buttons, and lists the release notes for recent versions with links to each GitHub release and the full…
The app now starts on machines that set a system HTTP(S) proxy, such as Clash, v2ray, or a corporate proxy. Before, the backend sent its local connection checks through the proxy, so it couldn't find its own hub and…
Added New provider: ai&, an OpenAI-compatible endpoint serving open-weight models from Japan. Changed Refreshed the model catalog to 6,386 models across 209 providers. The resolved default model changes for 19…
Cline Desktop now runs on Linux. Each release ships x64 `.deb` and `.rpm` packages alongside the macOS and Windows builds. Open folder… uses the native GTK picker, and updates download in the background and install…
Long sessions on local models no longer die mid-answer at the output-token limit. llama.cpp, Ollama, and LM Studio cap generation at whatever context is left, whatever output budget you set, so a text-only reply could…
A text-only turn truncated at the output-token limit now gets one compact-and-retry attempt per run before the existing nudge-and-retry recovery. Local OpenAI-compatible servers (llama.cpp, Ollama, LM Studio) cap…
Composio connectors now load all their tools, not just the first 20. Google Calendar, for example, showed only 20 of its 47 tools, and the Installed view wrongly said "20/20." The full list is now fetched and the tool…
Changed Sub-agents spawned in the same step now run their tool calls at the same time rather than one after another. Tools that must run in order still do, and the parent still waits for every result before its next…
Start a task in its own git worktree. The welcome screen's “Work in” switch (next to the folder and branch chips) now offers Local or Worktree; pick Worktree and the first prompt of a new thread cuts a fresh `cline/`…
Runs no longer die when a model turn hits its output-token limit before making a tool call. A reasoning-heavy or oversized response could spend the whole output allowance and end the run with an output-token-limit…
A turn that hits the model's output-token limit without producing a usable tool call is now retried instead of failing the run. Reasoning or a large response could consume the whole output allowance before the agent…
Context compaction no longer silently degrades to truncation partway through a long session on OAuth providers. The summarizer kept the access token resolved when the session started while the main agent loop refreshed…
Concurrent feature-flag polls for the same account now share one in-flight request. The cache was marked fresh before its network request finished, so a caller that raced the initial poll returned immediately with the…
Cline starts again after updating. In 0.0.31 the app could fail at launch with "desktop backend exited before publishing its endpoint" and never reach the workspace picker. Cline runs its own copy of the Cline Hub in…
Cline can now work on a remote machine over SSH, with the app itself staying local. Add and test a host under Settings → Remote, then pick it from the environment selector beside the workspace picker on the welcome…
Added Images attached to a model that cannot read them are now flagged instead of silently discarded. Thumbnails get a warning badge and the composer explains that the images will be ignored, with a button to switch to…
Windows updates no longer fail with "Error opening file for writing". The installer hook meant to stop the running backend never terminated anything: Tauri ships a 32-bit NSIS installer, so its PowerShell ran under…
Queued messages can now be sent into the running turn with Enter. While the agent is working, pressing Enter with an empty composer steers the first message in the queue, so it is picked up at the next turn boundary…
The app no longer gets stuck on "Desktop backend unavailable" when the backend is slow to start. The window asked for the backend's address exactly once and the shell stops waiting after about 15 seconds, so on a…
Introducing Cline Desktop: a native app for working with open-weight models, with task import from Claude Code and Codex, scheduled runs, web search and voice input, and a marketplace for plugins, MCP servers, and…
Hub-managed Agent Plugins. Packages under `~/.agents/plugins/*` on the hub host are discovered and validated from their root `plugin.json`; valid skills under `skills/` are exposed through the skills tool as…
An expired Cline sign-in now produces one actionable error instead of two dead ends. A turn that fails before the runtime takes the prompt was reported twice — the hub's detail-less `run.failed` appended a bubble, then…
The composer now shows the current branch's GitHub pull request — PR number, merge status, changed-line totals, and CI checks. Click through to open it in your browser, or expand CI to inspect individual checks and…
ChatGPT Subscription (Codex) now lists only the models your plan can actually use. Two separate paths filled the picker from the shared OpenAI catalog, so GPT-4o, GPT-4.1, and `chatgpt-image-latest` showed up alongside…
Fixed the live chat stream doubling text and dropping messages mid-turn. The sidecar has two Hub sockets that both receive a session's events — ClineCore's own client and the observer client — and a session that…
Agent Plugins are now discovered and run by the shared Hub. Packages under `~/.agents/plugins` are validated from their `plugin.json`, their valid Agent Skills become available to the agent, and their stdio /…
Beta: configure and opt in to image generation under Customize → Tools. Provider credentials stay server-side, and generated images remain available in session history. Scheduled runs are grouped within their runtime…
Everything here lands through the SDK bundle, so it applies to windows running that bundle. Added ClinePass is now surfaced across the app: a card on the account page describing what the plan covers, a hint in provider…
Import your history from Claude Code, Codex, and opencode. An Import button in the Sessions header (and a row in Settings → General) scans your local stores from all three tools and turns the conversations you pick…
Cline now handles a running Hub that is older than your CLI. Instead of quietly talking to a hub executing stale code, you get a prompt showing how many active sessions a replacement would interrupt, with…
Fixed tool calling being silently disabled for gateway models whose catalog entry declares no capabilities. Three separate producers built gateway model definitions with their own hand-written capability translations…
Beta: Composio connectors now register tools directly in the packaged desktop runtime for eligible internal accounts, with safer OAuth revocation and more resilient connect, disconnect, and reconciliation behavior. Web…