Cline

Context compaction now reports progress status while it runs

• Workspace git info (branch/remote) is now persisted and refreshed across sessions
• Fixed benign git states being reported as workspace initialization errors
• Plan/Act mode guidance added to the system prompt, with nudges when switching modes
• Editor diff view restored for SDK edit tools
• Model IDs are now suggested from OpenAI-compatible endpoints
• VS Code terminal reliability improvements (OSC 633 parsing, exit codes, timeout handling)
• Provider-specific request headers are now centralized in the LLM layer
• +2 more changes

Added a manual API key escape hatch for Cline OAuth providers, so you can enter a key by hand from settings

• Fixed provider config not reloading when switching models
• Fixed auto-update failing to detect Bun global installs after symlink resolution
• Fixed unexpected logouts caused by transient network or server errors during token refresh
• The ClinePass usage-limit error is now surfaced clearly when you hit the limit
• Session id is now preserved when continuing within the same session
• Hardened context compaction budget handling

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 image-capable model.
• Previously the thumbnail looked normal and the image was replaced with a text placeholder just before the request, so there was no way to tell it had been dropped.
• Model info and the attachment picker also report image support accurately for models that declare text-only input without listing capabilities.
• +49 more changes

Add more models to the GCP Vertex provider, plus a free-form entry option in the model dropdown for specifying custom Vertex models.

You can now select Cline free models on the ClinePass provider in the model picker

• Removed the retired ClinePass GLM 5.1 model
• Fixed OpenAI Codex model metadata under the GPT Subscription provider
• `str_replace` edits now report accurate diffs
• Fixed context compaction so canonical session history is preserved
• The detached hub daemon now emits telemetry, and telemetry identity now includes `user_id`
• Cline provider requests now send versioned client-identity headers

Add a ClinePass limit-reached error with a one-click option to switch to Cline usage-based billing.

• Allow selecting Cline free models on the ClinePass provider, organized into Subscribed and Free tabs with model descriptions.
• Refine ClinePass onboarding and provider settings copy, and open the "learn more" link via the in-app URL handler.
• Remove the Cline model picker recommendation copy.
• Remove all references to GLM 5.1.

New plan/act accent palette: act mode is now blue (`#79b8ff`) and plan mode amber, replacing the old cyan/yellow — applied across dialogs, the model selector, config, onboarding, markdown, and syntax highlighting, with light-theme variants tuned for contrast

• Restyled chat input: a minimal frame with full-width horizontal rules and a bold accent prompt glyph instead of the tinted background, plus slimmer user-message bubbles
• Assistant markdown accents are now tinted by the mode (plan/act) they were produced in
• Polished the status bar usage display and ClinePass model name
• +4 more changes

Weaker models (e.g.

• DeepSeek) that emit malformed tool calls — wrong argument types or truncated JSON — are now handled gracefully and run instead of erroring out
• Plan/act mode switches are now visible to the model, so it knows when you change modes mid-session
• Fixed plan/act mode notices being dropped from prompts sent to the model
• Fixed a race where switching modes in an empty session could trigger an unexpected restart

Fixed plan mode's `switch_to_act_mode` tool not taking effect until the end of the turn: the model would keep running with plan-mode tools (no file editor) and fall back to editing files through shell commands.

• Switching to act mode now ends the plan-mode run and automatically continues with the approved plan using the full act-mode toolset.
• A Tab mode toggle racing a completing turn can no longer auto-start plan execution you didn't approve.

ClinePass is now enabled for all CLI users

• Recover missing interactive sessions when reading messages
• Format structured commands in history export
• Add the subscription promo code when linking to the dashboard subscription page
• Add Tencent TokenHub as a provider (from SDK v0.0.55)
• Fix first-prompt truncation on high-output models (e.g.
• MiniMax M3) that could immediately auto-compact and cut the initial task down to just the input wrapper (from SDK v0.0.55)
• Use a curated default when migrating legacy provider settings (from SDK v0.0.55)
• +2 more changes

Generalize the model capability warning so it applies more broadly.

Add support for Claude Sonnet 5 across the Anthropic, Bedrock, Vertex, Claude Code, SAP AI Core, OpenRouter, and Vercel AI Gateway providers, including model picker and recommended-model updates.

Fully remove the ClinePass feature flag so ClinePass is available everywhere in the UI — onboarding, settings, the welcome promo banner, and the credit-limit "Switch to ClinePass" action.

Enable the ClinePass provider for all users by removing the feature-flag gate that previously fell back to the standard Cline provider.

Add reasoning effort support (including `xhigh`) for DeepSeek thinking models.

• Improve the ClinePass provider experience with clearer reasoning controls and model selection.
• Show reasoning effort controls for ClinePass models and align ClinePass model resolution with the rest of the provider.
• Prefer canonical Cline Z.ai model ids and polish ClinePass and Z.ai model metadata.
• Fix environment variable replacement in the webview.
• Default focus chain settings in webview state so the toggle reflects the correct value on load.