Cline changelog
The last 25 stable releases of Cline, newest first, with the lines that remove, rename or deprecate something pulled out on top. Taken from the GitHub releases every morning.
Breaking changes and deprecations
None of these releases removes, renames or deprecates a flag, command or setting.
Latest releases
-
- Cloud 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.
- Refreshed the model catalog. Adds the CommandCode, Reflection, Liquid Inference and Munito AI providers and drops CrofAI, iFlow and Llama. The Cline free list adds Reflection Beam, Nemotron 3.5 Lightning and Laguna S…
- GPT-6 models (such as gpt-6-sol and gpt-6.1-sol) work on OpenAI and Azure OpenAI-compatible endpoints, and SAP AI Core no longer rejects requests with "Unsupported parameter: 'max_tokens'". Both now get max_completion…
- Gemini API keys (the gemini provider) no longer send native Google Search. Free-tier keys failed every turn with a 429 quota error on Gemini 3+, and on Gemini 2.x every Cline tool was dropped.
- Toggling Plan/Act while a task is starting no longer drops your first prompt, and the session no longer keeps running with the other mode's tools.
-
- 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, 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.
- When a provider error interrupts a response mid-stream, Cline retries it up to 3 times before failing the turn.
- In JetBrains, the Run task card stays above the Auto-approve bar.
- Auto Compact and its strategy setting sit together again in Feature settings.
-
- 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 model, v0-1.5-md, an…
- Turning reasoning off no longer fails with a 400 error on GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5 or Claude Opus 5.5, and now works on every provider. Level-only Gemini models no longer reject the request with a thin…
- An MCP server or hook that exits before reading all of its input no longer crashes the extension host about 3 seconds later.
- A 404 from a stale or retired model id is no longer shown as a sign-in problem. Cline shows the real error instead of the logged-out card.
- Errors in the Cline output log keep their details. Production builds used to drop them, so a line like "Cline OAuth login failed:" showed no reason.
- Deleting a slash command from the input keeps the spacing of the text around it.
- Screenshots and other images no longer inflate the token estimate, which made auto-compaction run long before the conversation was near its limit.
- Auto-compaction uses the selected model's context window when the catalog entry has none.
-
- 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.IO, Blue Claw, C…
- Generate Commit Message now follows your .clinerules, so conventions like language, format, and ticket references apply to commit messages too.
- Claude through a custom Anthropic base URL (Azure AI Foundry, corporate gateways) no longer fails with a 400 error. 4.1.22 started sending an option only Anthropic's own API accepts.
- Kimi K3 and other models that only accept certain reasoning levels no longer reject requests. Cline picks the closest level the model supports.
- When an MCP tool returns more output than fits in context, Cline 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.
- Approve and Reject on a tool approval work right away, even while the panel is still updating. A late update failure no longer rejects a later, unrelated approval.
- Old tasks no longer show leftover Focus Chain checklist rows when reopened.
-
- New providers: Bee (by HEOSSI) and Pareto Inference (PARETO_API_KEY).
- 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".
- Refreshed the model catalog. GPT-6.1 Sol becomes the default model for OpenAI, OpenRouter, GitHub Copilot, Cortecs, Eden AI, Kilo Gateway, both LLM Gateway providers, NanoGPT, OpenCode Zen, and Requesty. Vercel AI Gat…
- After an API error you can type and send a new message instead of only using Retry. A /compact (or /smol, /newtask) typed during recovery stays in the composer instead of being sent to the model as text.
- If a new task fails Cline sign-in, signing in and submitting a revised prompt now starts the task with that prompt. Before, nothing happened.
- Reset Code is now disabled when a message has no checkpoint, and no longer stays disabled for a message whose checkpoint exists (seen on slow disks). Changing the Checkpoints setting now applies to the active task, an…
- Canceling right after sending a message now stops the task. A cancel that landed while the turn was still being set up was ignored, and the task kept running.
- Reasoning tokens are no longer counted twice in token usage. Cost is unchanged.
- Amazon Bedrock: GPT-6 and GPT-5.6 route through inference profiles, and India regions (ap-south-1, ap-south-2) resolve the in. profile. OpenAI models behind inference profiles get the reasoning effort setting they sup…
-
- New provider: ai&, an OpenAI-compatible endpoint serving open-weight models from Japan.
- Refreshed the model catalog to 6,386 models across 209 providers. The resolved default model changes for 19 providers that do not pin one, 11 of them to Claude Opus 5.5 (including GitHub Copilot and Vertex). If you us…
- Raised the minimum js-yaml version to 4.3.2 to pick up a security fix in the parser used to read rule and skill frontmatter.
- Long replies on local models (llama.cpp, Ollama, LM Studio) that hit the output-token limit now compact the conversation and retry once instead of ending the task. These servers cap generation at whatever context is l…
- Reopening a task that failed now shows the error with the retry option, instead of presenting it as a completed task.
- A command that prints nothing no longer shows a raw JSON blob like [{"query":"git add -A","result":"","success":true}] as its output.
- On Windows, @-mention search results now show the right file names. Nested files such as a subfolder's README rendered as /README.md, and the same open file could appear twice.
- Canceling a request while it waits to retry an empty model response now takes effect right away, instead of after the backoff finishes.
-
- 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 turn.
- Models that advertise a large output limit now get a bigger default output budget — 30% of the limit rather than a flat 32,000 tokens, whichever is larger. Nothing changes for models under roughly 107k output tokens;…
- Refreshed the model catalog: 203 to 209 providers and 6,079 to 6,237 models. Kimi For Coding splits into separate kimi.com and kimi.ai providers, and AI21 Labs, ainetcafe, Inco, OCI Generative AI, Tempr, and Vispark a…
- UserPromptSubmit and TaskStart hooks can inject context again. What those hooks returned as contextModification was being dropped — only cancel survived — so a hook meant to add repository facts or house rules to a ta…
- Unsent text in the composer survives Retry. Retry sent no composer content but still ran the same cleanup as approval actions, deleting the only copy of anything typed while a request was in flight. Text, quote contex…
- Output from background commands now streams into the command row while the command runs, instead of appearing only when it finishes.
- The Azure API version configured for a provider is now honored in tasks and mirrored to providers.json.
- Rules are found and shown consistently. The Rules panel listed only .clinerules and the Documents global folder, so rules loaded from .cline/rules, ~/.cline/rules, or ~/Cline/Rules were applied to the model but missin…
- Deleting a task from history now actually removes it. A task whose index entry was missing but whose file on disk survived was reported as deleted and then reappeared on the next refresh.
- Sub-agents you configure yourself no longer ask you to approve their individual tool calls after you have already approved the delegation.
-
- 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 an i…
- Cline's logo and icons have been refreshed throughout the extension, including the activity bar and panel icons.
- The W&B Inference provider is now listed as CoreWeave, with its sign-up and API-key links updated to match CoreWeave's current documentation.
- Long tasks now compact when they actually need to rather than running out of room. The trigger compared a character-based estimate of the conversation (~3 characters per token) against the model's context limit, so co…
- On Windows, opening a repository that contains a file named rg.exe, git.exe, or powershell.exe no longer runs that file in place of the real program. Bare program names were resolved through the workspace directory be…
- A model turn that fails mid-stream with a transient provider error is now retried up to three times with backoff instead of ending the task. A single rate-limit response forwarded by a gateway previously surfaced as a…
- Terminal commands that succeed without printing anything (git add -A on a clean tree, for example) are now reported as empty output. They were treated as a shell-integration failure, which fed the model a snapshot of…
- Checkpoints no longer re-hash every untracked file on each message. In workspaces holding large untracked directories this delayed every message by seconds to minutes; a persistent per-task index now lets git skip fil…
- run_commands no longer hangs until its timeout after a command that backgrounds a child process. The command had finished, but the backgrounded process held the output pipes open.
- apply_patch no longer silently overwrites an existing file when the model uses "Add File" on a path that already exists. The file's contents were replaced with no error and no record of what was lost.
-
- ClinePass is now surfaced across the app: a card on the account page describing what the plan covers, a hint in provider settings, and a banner on the home screen. Dismissed banners stay dismissed.
- Fixed the background Hub process ballooning in memory during long sessions. Session status updates broadcast a full copy of the conversation transcript to every connected client, so on a large task each status change…
- Hook scripts that fail to spawn no longer crash the extension's core process and take the running task down with them.
- Fixed a chat render crash on malformed api_req payloads.
- Cost estimates no longer appear in task history for subscription-billed tasks (ClinePass, ChatGPT via Codex, and Claude Code), matching the task header.
- Pasted provider API keys are now stripped of the invisible characters clipboards smuggle in (newlines, zero-width spaces, BOM). A key corrupted that way was hidden by the masked field and rejected by the provider with…
- Signing in to OpenAI Codex (ChatGPT subscription) now fails with a clear "port in use" error when callback port 1455 is occupied. Previously the button opened a browser to a flow whose callback could never arrive, and…
- A transient network failure while refreshing OpenAI Codex or OpenAI-compatible-account tokens no longer signs you out. Only a genuinely rejected refresh token now requires re-authentication.
- Fixed tool calling being silently disabled for Dify, SAP AI Core, opencode, and Codex CLI models. Their catalog entries declare no capabilities, and the empty list was read as an authoritative denial that stripped eve…
- Fixed images being dropped from file reads on models whose capability list is empty.
-
- Cost estimates are no longer shown for providers billed by a flat-rate subscription (ClinePass, ChatGPT via Codex, and Claude Code). The task header and model pricing rows rendered API-rate dollar figures that read as…
- Signing back in no longer moves your last-used provider off ClinePass on credential refresh.
- Hooks now resolve their workspace from the VS Code window instead of shared global state in ~/.cline. With a second window open on another project, a workspace's .clinerules/hooks scripts were never discovered, and ho…
- New files are now created with your platform's native line endings.
- Fixed the codebase search tool crashing on files containing a single enormous line.
- Credentials embedded in git remote URLs are now redacted from the workspace information sent to the model, which also now carries richer workspace metadata.
- Installing an MCP server from the marketplace no longer misreads the catalog's -- separator as part of the server command.
- The hub's event log can no longer grow until it fills your disk.
- The per-tool MCP auto-approve checkboxes are hidden. MCP auto-approval is governed solely by the global "Use MCP servers" toggle — the per-tool checkboxes were no-ops that implied granularity the approval path does no…
-
- Auto-approve every MCP tool call while the "Use MCP servers" toggle is on. The toggle only took effect on tools that had also been opted in individually, so turning it on appeared to do nothing; it now governs all MCP…
-
- Refresh the built-in model catalog. New entries include Claude Fable 5, Grok 4.6 on Vertex, several DeepSeek V4 Flash variants (including the vision preview), MiMo v2.5, Qwen3.8 27B, Gemma 4 26B, LongCat 2.0, Nemotron…
- Restore task completion telemetry for interactive sessions. A share of interactive stops routed through a teardown path that never reported completion after 4.1.11 changed how session status is tracked; every session…
-
- Restore tool calling for custom OpenAI-Compatible models whose capability list was inferred from convenience flags like supportsReasoning. The inferred list read as an authoritative denial and stripped every tool from…
- Keep Hub-backed sessions intact across a Hub restart or upgrade. Clients replay the events they missed while disconnected, and the same event is no longer delivered twice when the replay and live streams overlap.
- Carry session and client identity into Langfuse traces for Hub-backed and delegated-agent runs, which previously arrived without their session grouping or client version.
-
- Enforce enterprise MCP controls on the Customize marketplace. MCP entries are now hidden when remote config disables the marketplace, and limited to allowedMCPServers when an allowlist is configured.
- Restore tool calling for custom OpenAI-Compatible models whose stored capability list was empty.
-
- Let models that support it generate images during a task. Generated images render inline in the conversation.
- Fix code actions failing with "command not found" on VS Code 1.134.
- Fix @ file mentions breaking on paths that contain spaces.
- Show the diff edit view for multi-line edits in files with CRLF line endings.
- Continue the surviving session when resuming a task, instead of rebuilding it from the original task text.
- Clear the task-scoped settings overlay when the task view is cleared or switched, so one task's overrides no longer leak into the next.
- Honor the classic truncation range when migrating legacy tasks.
- Preserve LiteLLM input token limits instead of overwriting them with catalog values.
- Restore custom base URLs for Gemini, and normalize legacy host-root values so they keep working.
- Point provider signup links at each provider's API key page instead of a generic landing page.
-
- Let models that support it search the web during a task, with a toggle in Feature Settings to turn it on. Search calls and their results appear in the conversation and persist across reloads.
- Stop two Cline installations on different builds from shutting each other's Hub daemon down in a loop, which killed live sessions with an abnormal socket close. Build identity is now compared through a total order, so…
- Leave a Hub that is still serving sessions in place instead of replacing it mid-handshake; the swap happens once it goes idle.
- Reclaim idle plugin sandbox processes instead of leaving them running for the life of the session.
- Refresh the model catalog, which adds Crusoe as a provider and updates model lists and per-provider default models across the board.
-
- Use the editor's foreground color for diff block text, so diffs stay legible in themes where the previous hardcoded color washed them out.
- Switch the interface to Inter and Geist Mono.
- Don't discard a successfully refreshed Cline token when the old one was already past expiry, which made the first request after a long idle period fail despite valid credentials.
- Stop the legacy-task migration backlog from spamming telemetry, and record a migration outcome only once the seeded session actually persists, so a failed migration is no longer reported as a success.
- Report involuntary Cline logouts (a rejected refresh token) instead of clearing credentials silently.
- Fix the Claude Code provider being unusable for agentic work: it now runs its own native tools instead of receiving tool definitions it cannot bridge, anchors the session on your workspace directory, and loads ~/.clau…
- Reject truncated tool-call JSON instead of silently "repairing" it into wrong arguments.
- Fix strict providers rejecting a turn with "user message must have content" when a message's content held only empty text parts.
- Fix a mid-turn crash on streamed tool calls with non-zero or non-contiguous indexes, hit through LiteLLM's Anthropic passthrough.
- Report disjoint per-request token buckets instead of re-counting the whole cached conversation on every request, which inflated per-task totals roughly 5x on cache-heavy sessions.
-
- Enter any Vertex model ID by hand, including models the catalog doesn't list yet.
- Support Fable 5 on Vertex.
- Show the full model catalog for every Vertex region instead of filtering the picker down to a hardcoded list of global-endpoint models, which lagged behind every model launch. Picking a model the region doesn't serve…
- Report Fable 5 cost on Vertex as unknown rather than applying Anthropic's list price, which understated what Vertex actually bills — its rates are region-dependent.
- Make the auto-approve menu the single source of truth for unattended runs and remove the Yolo Mode toggle, which was cosmetic: nothing in the approval path read it. Setups that had Yolo Mode (or auto-approve-all) turn…
- Respect your configured max output tokens when the compaction summarizer requests a summary.
- Remove the stale "Double-Check Completion" feature tip.
-
- Restore the "View Changes" button on completion rows, backed by SDK checkpoints, so you can review everything a task touched from the completion card.
- Bring back a copy button on turn-final response rows.
- Support pre-registered OAuth clients for remote MCP servers, for setups where dynamic client registration isn't available.
- Fade the "View Changes" button until changes since the last message are confirmed, and hide it entirely when there is nothing to show.
- Centralize plugin settings and contributions, with host-aware snapshots and atomic plugin toggles.
- Carry execution context in scheduled run reports — readable headers, schedule metadata, durations, and lifecycle error details.
- Preserve prompts queued during a turn when that turn is interrupted: they survive aborts, are drained after a turn aborts itself, and the stop is surfaced instead of the queue being silently dropped.
- Keep session context durable across aborts and hub restarts, so an interrupted session resumes with the state it had.
- Settle the turn phase when a mode switch aborts a running turn.
- Report queued-turn failures as run.failed instead of letting them complete silently.
-
- Offer meta/muse-spark-1.2-contributor on the Cline provider, alongside a refreshed model catalog.
- Attribute error telemetry to the model actually in use for a run, so failures are no longer reported against the wrong model.
-
- Explain when a free model promotion ends. Requests to a retired free model now show a dedicated notice with a button to pick another model, instead of a generic error with nothing but a Retry prompt.
- Map reasoning settings onto a shared path across AI SDK providers, so effort levels and enable/disable toggles behave consistently (including on Ollama) instead of relying on per-provider overrides.
-
- Recognize Chutes as a provider.
- Show skills alongside workflows in the slash command menu, and disambiguate commands that share a name instead of letting one shadow the other.
- Remove model-initiated plan-to-act switching. Switching out of plan mode is now driven by you, not by the model deciding mid-turn.
- Hard-block file-editing shell commands in plan mode instead of relying on prompting alone. Read-only investigation still works, but file manipulation, in-place editors, redirection to files, mutating git subcommands,…
- Stop treating a turn that completes with a plan as a failed turn when a plan-blocked command was its only tool call. The turn no longer ends in the error state with a Retry footer, and toggling to Act correctly re-run…
- Show tool paths relative to the workspace in the chat view instead of absolute paths.
- Reset pending attachments when starting a new task, so images from the previous task no longer carry over.
- Surface a clear error when the selected provider has no API key configured, instead of a generic failure.
- Refresh MCP tool and resource lists when a server sends a list_changed notification, instead of only showing a toast.
- Show installed plugins under their real package names instead of all appearing as "index".
-
- Stop the two bundles of the combined rollout package from invalidating each other's Cline account session. A still-open legacy window that refreshed its token after the machine was promoted to the new extension would…
- Fall back to the default Cline model when migrating a setup that references a model id the new extension doesn't recognize, instead of leaving the provider unconfigured.
- Restore reliable checkpoints: checkpoints are created consistently, and restoring one now rewinds the whole workspace rather than a subset of files.
- Keep settings edits that are made before the provider config finishes loading — base URLs, API keys, and the Qwen/Moonshot API line are no longer silently discarded.
- Stop losing keystrokes in custom base URL fields, and keep the custom URL checkbox state after a failed clear.
- Use the AskSage custom API URL at inference time instead of ignoring it.
- Settle a pending tool approval when an edited message replaces the session, so the task no longer hangs waiting on a prompt that is gone.
- Drop attachments from messages that have been edited.
- Complete terminal commands when the shell execution ends, so tasks no longer stall on commands that already finished.
- Include untracked files when generating commit messages.
-
- Show which extension variant is active — "Legacy" or "Next" — next to the version in the settings About page, in both bundles of the combined rollout package.
-
- Remove vestigial MCP server-key machinery from McpHub — native MCP tool calls now route by server name instead of a random in-memory uid, so routing survives restarts and server list changes.
Other agents
Claude CodeCodex CLIGemini CLICopilot CLIopencodeHermes AgentQwen CodeKimi CLIGooseMistral VibeCrushAider All agents →
Run Cline next to the other agents and see when one needs you: AgentVera keeps them in one window on Mac, Windows and Linux, and on your phone.
Bring your agents to one desk.
Download, pick a project, open your first agent. Your installed CLIs are ready to go.