Cline

• The hub's durable event log is now capped at 64 MiB on disk. Event envelopes carrying full session snapshots could previously accumulate to tens of gigabytes, since row and time retention alone did not bound file size and deletes never shrink a SQLite file. Oldest events are dropped first and the file is vacuumed to return the space, and pruning now also runs after every 16 MiB appended instead of waiting for the hourly sweep
• Fixed task.completed telemetry being dropped for most interactive sessions. The event is now emitted from every session teardown path, exactly once per session
• Refreshed the model catalog. Adds two providers (AgentRouter and Opper) and updates model lists and pricing across providers. The resolved default model changes for Aki.io and NanoGPT, so if you use one of those without pinning a model you will get a different default

Full Changelog: https://github.com/cline/cline/compare/sdk/sdk/v0.0.78...sdk/sdk/v0.0.79

Everything here lands through the SDK bundle, so it applies to windows running that bundle.

Added

• 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 3.5 Lightning, and Thinking Machines' Inkling models.

Fixed

• 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 now reports it exactly once.

Full Changelog: https://github.com/cline/cline/compare/v4.1.13...v4.1.14

• Added cline hub drain, which stops a hub from accepting new mutating work while it finishes what it is already running, and cline hub drain --off to lift it
• Added cline hub upgrade, which drains the hub, waits for it to go idle, stops it, and starts a fresh one on the current build. An aborted upgrade lifts the drain again, so the hub is never left refusing work
• Sessions now survive a hub restart. A reconnecting client replays the events it missed while disconnected, deduped by event id so nothing is delivered twice
• Fixed tool calling being silently disabled 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 the request
• Langfuse traces now carry session and client identity for hub-backed and delegated-agent runs, instead of arriving without their session grouping or client version
• Refreshed the model catalog, which updates model lists and pricing across providers and changes the resolved default model for several of them (DeepSeek, Crof, CrossModel, Eden AI, Kilo, and NanoGPT)

• The hub can now be drained and upgraded without losing work. A draining hub refuses new mutating work while it finishes what it is running, a durable event log lets a reconnecting client replay everything it missed, and durable runs are queued rather than dropped. Replayed events are deduped by event id, so an event that arrives on both the replay and the live stream is delivered once
• Fixed tool calling being silently disabled for custom OpenAI-Compatible models whose capability list was synthesized from convenience flags like supportsReasoning. An inferred list read as an authoritative denial and stripped every tool from the request; explicitly authored capability lists still decide
• Langfuse traces now carry session and client identity for hub-backed and delegated-agent runs. Hub sessions rebuild client name and version from request headers, and delegated agents group under their parent session instead of appearing as unattributed traces
• Refreshed the model catalog, which updates model lists and pricing across providers and changes the resolved default model for several of them (DeepSeek, Crof, CrossModel, Eden AI, Kilo, and NanoGPT). If you use one of those providers

• The agent can now be handed off between Hub instances without losing work: a Hub that is restarting refuses new work while it finishes what it is running, and the app replays anything it missed while disconnected instead of dropping it
• Fixed tool calling being silently disabled for custom OpenAI-Compatible models whose capability list was inferred from convenience flags like supportsReasoning
• Refreshed the model catalog, which updates model lists and pricing across providers and changes the resolved default model for several of them (DeepSeek, Crof, CrossModel, Eden AI, Kilo, and NanoGPT)
• The app now honors server-side feature flags, refreshing them when your account changes

Full Changelog: https://github.com/cline/cline/compare/desktop-v0.0.15...desktop-v0.0.16

Everything here lands through the SDK bundle, so it applies to windows running that bundle.

Fixed

• 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 the request; an explicitly authored capability list still decides.
• 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.

Full Changelog: https://github.com/cline/cline/compare/v4.1.12...v4.1.13

• Beta: your typed prompt is no longer lost when a cloud handoff starts — the live draft carries into the handoff and is restored if it fails.
• Beta: fixed a closed model popover blocking clicks in the composer.
• Beta: cleaned up visual regressions in provider settings, notifications, and the avatar overlay from the previous sync.
• Includes the 0.0.16-track main updates: the redesigned first-run onboarding with an interactive welcome graphic, centralized tool availability, hook fixes (PostToolUse output and context changes now reach the model), and the fix for checkpoint restore staying locked after queued turns.

Full Changelog: https://github.com/cline/cline/compare/desktop-v0.0.15-beta.1...desktop-v0.0.16-beta.1

• The app is now called Cline, renamed from Cline Code. Your settings, sessions, and credentials carry over untouched — only the name and icon change
• Refreshed app icons and branding
• Reskinned the first-run onboarding, with an interactive welcome graphic
• Plugins, MCP servers, and Skills are now one Plugins hub with a dedicated Marketplace page
• The composer's model selector now leads with Recommended and Free tiers (Subscribed and Free on ClinePass), labeled by display name with descriptions, instead of an alphabetized list of raw model ids. Provider settings show the same badges and descriptions
• Agents can now create and manage durable todos and one-time or recurring schedules
• Fixed checkpoint restore wedging permanently. Sessions that were never prompted — and persistence-only updates — reported a bogus "running" status, so anything gated on an active turn stayed blocked forever
• Fixed "No sessions found" flashing while session history was still loading
• Fixed the work summary undercounting elapsed time when thinking before a tool call attached to the answer instead of the run
• Fixed the settings gear keeping its hover state while the Account screen is open

Everything here lands through the SDK bundle, so it applies to windows running that bundle — except the last section, which is a legacy-bundle fix.

Added

• Let models that support it generate images during a task. Generated images render inline in the conversation.

Fixed

• 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.

• Models that support image generation can now produce media during a turn. The TUI saves each generated file to a temporary path and prints it so you can open it with your usual tools, HTML session exports embed images inline, and ACP clients receive generated images as image content
• Skill slash commands now load through the skills tool instead of expanding into your message. History and resume show the /command you typed instead of the whole skill body, and the instructions reach the model once instead of twice. Workflows still expand, as does zen mode, whose preset has no skills tool
• Image, voice, and other non-chat models are no longer offered in the onboarding and model pickers or ACP model listings, and are rejected for --model
• Fixed TUI dialog colors not following theme changes live
• Fixed the account dialog's selection chevron so it matches the other dialogs
• Fixed provider-executed tool activity — every tool the Claude Code provider runs inside its own session — being dropped instead of shown as a tool card

• Added model-driven image generation. Models that support it can generate images during a turn, and generated images are persisted in session history and exports
• Agents can now create and manage scheduled tasks and a durable todo agenda. Schedules are scoped to the workspace that registered them
• Skill slash commands now load through the skills tool instead of being pasted into the user message. The persisted transcript records what you typed (/my-skill ...) rather than the whole SKILL.md body, and skill instructions arrive once instead of twice. Workflows keep textual expansion
• Fixed provider-executed tool activity being dropped entirely — every tool the Claude Code provider ran inside its own session modified the workspace with no tool activity in runtime events, transcripts, or the UI. These now surface as observational tool events
• Fixed PreToolUse hook contextModification never reaching the model on the next engine; it is delivered again as a <hook_context> block stamped with the tool name and call id, hidden from user-facing transcripts

• Beta: hand off a local session to Cline Cloud with /handoff — the conversation, attached images, and an optional follow-up command move to a cloud workspace that keeps working after you close the app. A preflight confirms the repository, branch, and commit are pushed; the composer shows handoff progress and finishes with a receipt linking to the cloud session.
• Beta: Cloud now lives in the existing Local / Remote environment menu. It is selectable when the Cloud sessions feature flag is on and shows as "Coming soon" otherwise. The separate Local / Cloud toggle is gone; repository and branch controls are unchanged.
• If a handoff is interrupted — the app restarts, the network drops, or the branch moves mid-transfer — reopening the session recovers or cleanly retries it, and your typed draft and attachments are restored.
• Includes the 0.0.14 stable release and everything on main since: the unified Plugins hub with a Marketplace page, recommended and free model tiers in the model picker, scheduled tasks for agents, and the app rename to "Cline" (this beta is now "Cline Beta").