Cline by Cline
Source: https://github.com/cline/cline/releases
Weekly digest: every breaking change, retirement and price change across 20+ coding agents, one email.
Form not loading? Subscribe here.
2026-10-16 · 5 changes · release
- Marketplace plugins such as goal load again. In 0.0.46 they failed with Cannot find module '@cline/sdk' because the packaged app didn't include the SDK packages plugins import
- The Cloud sessions toggle is gone from Settings. Cloud sessions are on wherever they are available
- When a provider error interrupts a response mid-stream, Cline retries it up to 3 times before failing the turn
2026-10-16 · 9 changes · release
- Cline 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, noti
- 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
2026-10-16 · 7 changes · release
- Plugins now run in a worker instead of directly inside the hub. If this build can't run plugins, Cline says so in cline config tools, cline hub plugins, and the session-start warnings instead of quiet
- When a provider error interrupts a response mid-stream, Cline retries it up to 3 times before failing the turn
- Failed model requests now log the provider's request id, which makes support tickets easier to trace
2026-10-16 · 9 changes · release
- Plugins now run only in worker threads (the default, CLINEPLUGINMODE=worker) or in the subprocess sandbox (sandbox). The inprocess mode is removed, along with its silent fallback. A host that ships no
- Provider errors that arrive after a model stream has started are retried up to 3 times, and the final failure is reported as an error in logs and Langfuse traces. Exhausted retries no longer also trig
- Model request failure logs include the provider's request id
2026-10-13 · 15 changes · release
- A new outline along the left edge of the conversation lists each prompt you sent. Hover a mark to preview the prompt, and click it to jump there
- Plugins that fail to load or error during a session now show a status line in the chat naming the plugin and the error, instead of silently losing their tools
- You can cancel a Cline Cloud sign-in while it is waiting for the browser
2026-10-13 · 13 changes · release
- With no model chosen, the Cline and OpenRouter providers now use Claude Sonnet 5.5. For Cline, that's the first model in Cline's recommended list.
- Selecting ai& shows its own API key and model picker, instead of the generic OpenAI-compatible form with base URL and custom headers.
- Refreshed the model catalog. Adds Claude Haiku 5.5 and the AI/ML API, LowRouter, and Prime Inference providers. The Cline free list adds Step 5 Preview. The v0 provider now offers only its default mod
2026-10-13 · 13 changes · release
- Plugins now load inside the hub instead of a separate node or bun process, so the CLI no longer needs a JavaScript runtime on your PATH to run plugins. A plugin that fails to load no longer silently l
- --thinking now applies in ACP mode (--acp). Before, ACP sessions always ran with reasoning off
- cline hook accepts agenterror events. Before, it exited with an error and no response
2026-10-13 · 13 changes · release
- Plugins load in-process through one registry per process instead of a node/bun subprocess, so the compiled CLI and its hub no longer need a runtime on PATH, and plugins can use the Bun global under th
- Turning reasoning off now works on every provider, not just a fixed list. Models whose catalog entry has no off option are sent nothing and keep their default, and models without a reasoning capabilit
- The cline provider's default model is the first entry of the Cline recommended-models list, falling back to anthropic/claude-sonnet-5.5. CLINEDEFAULTMODELID moves from Claude Sonnet 5 to Claude Sonnet
2026-10-08 · 7 changes · release
- SSH remotes start again. Since 0.0.38, connecting to an SSH environment failed with SyntaxError: Invalid character
- On SSH environments, the git branch label no longer opens two new SSH logins every 5 seconds. It checks every 30 seconds now, and switching branches from the picker still updates it right away
- Long model names in the composer show in full when the row has room, and only truncate when it runs out
2026-10-08 · 12 changes · release
- Commit message generation and tasks with reasoning off no longer fail with a 400 error on GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5 or Claude Opus 5.5
- Cline no longer exits about 3 seconds after an MCP server or hook quits before reading all of its input
- Settings migrated from the VS Code extension no longer add an empty SAP AI Core provider
2026-10-08 · 5 changes · release
- The AI SDK moves together to one release line: ai 7.0.120 and every @ai-sdk/ package on @ai-sdk/provider-utils 5.0.50 (previously ai 7.0.79 with packages bumped one by one). Turning reasoning off no l
- Stdio MCP clients handle EPIPE when a server exits before reading all of its input. Previously that raised an uncaught exception on the host process. The SAP AI Core provider also no longer installs w
- The legacy provider-settings migration no longer adds an empty sapaicore entry to providers.json. It used to do this for every migrated user, because the extension writes sapAiCoreUseOrchestrationMode
2026-10-07 · 8 changes · release
- 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 Sol, and the free list adds Solar Mini 4 and drops DeepSeek V4.1 Flash and space-bunny-alpha. Default models change for 302.AI, AKI
- Generate Commit Message now follows your .clinerules, so conventions like language, format, and ticket references apply to commit messages too.
2026-10-07 · 8 changes · release
- 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, showin
- If the Cline Hub connection drops mid-chat, the app now reconnects your session automatically for up to a minute instead of failing right away. Queued messages are sent once the session is back. If it
- Local and self-hosted providers that don't need an API key (LM Studio, Ollama, vLLM, LiteLLM, and custom OpenAI-compatible endpoints) can start sessions again. They failed every turn with "Missing API
2026-10-07 · 7 changes · release
- 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 second
- Claude through a custom Anthropic base URL (Azure AI Foundry, corporate gateways) no longer fails with a 400 error
- Kimi K3 and other models that only accept certain reasoning levels no longer reject requests. The CLI picks the closest level the model supports
2026-10-07 · 10 changes · release
- 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
- Stdio MCP servers get a 10s default initialize budget (was 3s). npx/uvx launchers through cmd.exe on Windows routinely took 3-6s and were silently dropped from the session. An explicit timeout still o
- The Anthropic provider sends the server-side refusal fallbacks option only to api.anthropic.com. Custom endpoints such as Azure AI Foundry rejected it with a 400. New isOfficialAnthropicEndpoint helpe
2026-10-02 · 1 changes · release
- 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
- Full Changelog: https://github.com/cline/cline/compare/desktop-v0.0.42...desktop-v0.0.43
2026-10-02 · 4 changes · release
- 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 tab in Customize. A new Browse section lists the full connector catalog in two columns with search, so you no longer need the Marketplace to find a connector. I
- Connectors now show their brand logo, both in Customize and in Marketplace rows
2026-10-02 · 8 changes · release
- 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
- An unsent prompt is no longer lost when you switch to another session and back. New in the sidebar returns to your unfinished draft; Cmd/Ctrl+N still starts a fresh session
- Sessions you start in the app are now highlighted in the sidebar while open, instead of only sessions reopened from history. They also no longer get marked unread by their own messages
2026-10-02 · 2 changes · release
- 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 cou
- Refreshed the model catalog. Default models change for DigitalOcean (GPT-6.1 Sol), GMI Cloud (Qwen 3.8 Flash), NanoGPT (Pareto 26.10 Preview), Nvidia (DeepSeek V4.1 Flash), and Ofox (GPT-6.1 Sol)
- Full Changelog: https://github.com/cline/cline/compare/cli-v3.0.67...cli-v3.0.68
2026-10-02 · 3 changes · release
- 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'
- Standalone provider requests made outside a session (such as commit message generation) can now resolve Cline surface headers. sessionId is optional in resolveProviderRequestHeaders, and X-Task-ID is
- Refreshed the model catalog. Default models change for DigitalOcean (GPT-6.1 Sol), GMI Cloud (Qwen 3.8 Flash), NanoGPT (Pareto 26.10 Preview), Nvidia (DeepSeek V4.1 Flash), and Ofox (GPT-6.1 Sol)
2026-09-30 · 7 changes · release
- 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 Local, and which Cloud model you picked, instead of always going back to Local. Switching a thread from Local to Cloud also opens on your remembered C
- Saving provider credentials no longer fails when the provider's model list can't be fetched, and the model list refreshes when you change a provider's API key or endpoint
2026-09-30 · 5 changes · release
- 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 readfiles, so the output past the cutoff is no longer
- Custom providers defined in providers.json/models.json now work when you run a task. They showed up in the provider and model pickers but failed with Unknown or disabled provider
- If saving provider credentials fails during onboarding or in the provider settings dialog, the error now shows in place instead of failing silently
2026-09-30 · 4 changes · release
- 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/... U
- Custom providers from providers.json/models.json now run on the agent path. They appeared in pickers but failed with Unknown or disabled provider "<id>", because createAgentModelFromConfig only regist
- Provider settings saves are more robust. Settings still save when model discovery fails, mutations are serialized, a failed catalog write restores the previous settings, and persistence errors propaga
2026-09-30 · 2 changes · release
- 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 e
- The Linux .deb and .rpm packages now include app info, so GNOME Software and KDE Discover show Cline's icon and description and list it under Installed
- Full Changelog: https://github.com/cline/cline/compare/desktop-v0.0.38...desktop-v0.0.39
2026-09-30 · 11 changes · release
- New providers: Bee (by HEOSSI) and Pareto Inference (PARETOAPIKEY).
- Direct Anthropic requests now use Anthropic's server-side refusal fallback. On OpenRouter and Cline, Anthropic models can fail over to another upstream provider instead of failing the request.
- When a response is blocked by a content filter, Cline now says so and suggests rephrasing, instead of "Model returned empty response".
2026-09-30 · 15 changes · release
- 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 other built-in tools. That page shows whether your provider supports search, and links to provider settings when it doesn't
- Connectors are labeled Beta, and opening the marketplace from Connectors now shows only connectors
2026-09-30 · 14 changes · release
- 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 proxies). Loopback discovery requests were sent through the proxy, so a healthy hub looked unreachable and startup f
- Pressing Esc right after sending a prompt now stops the turn. A stop that landed while the turn was still being set up was ignored, and the agent kept working in the background
2026-09-30 · 7 changes · release
- 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 provider.
- A Stop issued while a turn is still being prepared is no longer dropped. The agent runtime ignores abort() with no run in flight, so a Stop that landed between runTurn() entry and the run start (sessi
- Content-filtered turns are no longer reported as empty responses. content-filter is a new AgentModelFinishReason, mapped by both the AI SDK and ApiHandler adapters (including the compat round trip); t
2026-09-29 · 12 changes · release
- 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 (Clas
- The hub daemon log now records one line per socket close with the close code and reason, whether the heartbeat sweep dropped it for a missed pong, and whether the server was already shutting down. Whe
- Token usage no longer counts reasoning tokens twice. Providers report reasoning tokens as a subset of outputTokens, but normalizeUsage() returned the raw total alongside reasoningTokenCount, so sessio
2026-09-26 · 4 changes · release
- 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
- After an update, a one-time What's new dialog now catches you up on recent features. The first one covers SSH remotes, worktrees, pull request status in the composer, and parallel sub-agents. To see i
- On macOS, Help → Export Diagnostics… now opens the diagnostics export directly, so you don't have to find it in Settings