持续追踪核心框架、最新模型规格与重要系统接口的更新迭代轨迹。
### Added - Offer `meta/muse-spark-1.2-contributor` on the Cline provider, alongside a refreshed model catalog. ### Fixed - Attribute error telemetry to the model actually in use for a run, so failures are no longer reported against the wrong model.
### Added - 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. ### Changed - 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.
### Added - 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. ### Changed - 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, and package installs are refused. ### Fixed - ...
### Fixed - 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 consume the shared refresh token, producing spurious "Unauthorized" / re-authenticate prompts and unexpected sign-outs. Promoted legacy windows now keep working on their current session and offer a one-time Reload Window prompt instead. - Fall back to the default Cline model when migrating a setup that references a model id the new extension doesn't recognize, instead ...
### Changed - 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.
### Added - 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.
### Added - Add GPT-5.6 ChatGPT subscription models. ### Changed - Soften and shorten the message shown when Cline hits the consecutive mistake limit. ### Fixed - Handle cumulative usage snapshots from OpenAI-compatible providers so token counts are no longer over-reported. - Load skills from files saved as UTF-8 with a byte-order mark (BOM).
### Added - Add telemetry to track when Cline reaches the consecutive mistake limit.
### Added - Add Claude Opus 5 across the Anthropic, Claude Code, Bedrock, Vertex, Cline, and OpenRouter providers, including 1M context window variants. - Add Moonshot Kimi K3 support. - Include the host plugin version in telemetry events. ### Fixed - Correct pricing for the Claude Opus 1M context variants, which overstated costs for requests above 200k tokens. - Enable native tool calling for Kimi K3 models, fixing empty responses.
### Added - Add support for free Cline models, shown as "(free)" in the model picker, with a dedicated error card that includes the reset time when the free limit is reached. ### Fixed - Keep Claude Code responses that were already streamed when the CLI exits with a max-turns error, instead of discarding a valid response.
### Changed - Convert the stable extension to a combined A/B package: one VSIX containing both the current (legacy) extension and the new SDK-based extension, plus a loader that activates exactly one per window via a staged remote rollout. For nearly all users nothing changes — the loader activates the same extension as 4.0.12; a small percentage (starting at 1%) is gradually opted into the SDK-based extension. If the new extension fails to activate, the loader falls back to the current one in the same window. Settings and credentials are shared between the two.
### Added - Add the SDK-backed VS Code extension runtime. Cline now runs tasks through the shared Cline SDK session layer for agent turns, tools, Plan/Act mode coordination, MCP, checkpoints, telemetry, provider changes, compaction, mistake limits, and task history. - Add ClinePass to the VS Code extension, including onboarding, provider selection, signup and subscription handoff, live model lists, entitlement and organization error states, out-of-credit prompts, and clearer ClinePass auth/error handling. - Add the Customize marketplace for discovering and managing Skills, MCP servers, and Plu...
### Fixed - Complete the fix for the Anthropic provider on VS Code 1.123 and later by upgrading the bundled Anthropic SDK to a release compatible with the Node 24 runtime. - Update the Vertex AI provider to a compatible Anthropic Vertex SDK release so it works with the upgraded Anthropic SDK.
### Fixed - Restore the Anthropic provider on VS Code 1.123 and later, where the updated Node 24 runtime broke the bundled Anthropic SDK. - Handle the DeepSeek V4 reasoning format.
### Added - Add Claude Fable 5 model support. ### Fixed - Fix MiniMax M3 thinking controls across gateways. ### Changed - Clean up the Codex model list.
### Added - Add a debug section in settings for Cline testers. ### Fixed - Include the walkthrough markdown files in the VS Code extension package so the first-run walkthrough steps load correctly.
### Added - Add the latest Fireworks AI serverless models and update the default Fireworks model to Kimi K2.6. ### Fixed - Fix MCP server delete/add flows so settings writes do not cause the MCP server list to be emptied by the file watcher. - Remove stale Fireworks AI models and correct Fireworks model metadata and cache pricing. ### Changed - Always use the upstream Cline recommended models endpoint instead of gating it behind a feature flag.
### Added - Add MiniMax M3 model support. ### Fixed - Update VS Code extension dependencies to resolve security issues in `@xmldom/xmldom`, `basic-ftp`, `axios`, `undici`, and other direct/transitive packages.
### Fixed - Fix `@` file mentions and workspace file search on VS Code 1.122+ by resolving the new bundled `@vscode/ripgrep-universal` per-platform binary layout before falling back to legacy ripgrep paths.
### Fixed - Fix `@` file mentions failing to find files in some environments (notably VS Code Remote SSH, and after certain VS Code updates) by keeping the file-search fallback alive when the workspace index or bundled ripgrep binary is unavailable.
### Added - Add Claude Opus 4.8 provider support, including 1M-context variants where available. - Add Moonshot Kimi K2.6 model support. ### Fixed - Show prompt-cache support for Qwen 3.7 Max in the Cline provider. - Fix the VS Code nightly publish workflow startup permissions. ### Changed - Move the VS Code extension project into `apps/vscode`.
### Added - Add GPT-5.5 support to SAP AI Core. - Add DeepSeek V4 Flash and Pro models. - Add Gemini 3.5 Flash to Gemini and Vertex providers. - Add `/lg-task` URI webhook integration for LG dashboard flows. ### Fixed - Fix Vertex AI global endpoint handling for Claude models. - Route Poolside Laguna models through next-gen prompts and native tool calling. ### Changed - Update `diff` and `protobufjs` dependencies.
### Added - Add SAP AI Core support for additional hosted models ### Fixed - Disable the MCP "Restart Server" button when a server is toggled off. ### Changed - Remove the Cline Kanban launch modal and bundled demo media from the VS Code extension startup flow.
### Fixed - Show a clear "Searching..." state in the @-mention file picker - Improve @-mention file search performance - Allow `write_to_file` to create or overwrite files with empty content. - Fix validation failures for MCP servers that require an object. - Enable OpenRouter prompt cache control for Qwen models. - Update Axios and SAP Connectivity dependencies ### Changed - Use the VS Code-specific `README.marketplace.md` when packaging and publishing the VS Code extension - Add telemetry to @-mention search to help diagnose local, remote, and multi-root workspace search behavior.
### Added - Restore VS Code foreground terminal support and settings. - Add latest OpenAI, SAP AI Core, and Z AI models. ### Fixed - Fix hook template JSON escaping. - Improve ripgrep file search error handling. ### Changed - Remove hardcoded model lists from docs.
### Added - Add GPT-5.5 model support for OpenAI Codex subscription users. ### Fixed - Remove hardcoded "What’s New" fallback items in webview; only remote-configured welcome banners are shown. ### Changed - Improve cline-core memory diagnostics used by the extension runtime: - enable near-heap-limit heap snapshots - add periodic memory usage logging - log discovered heap snapshots on abnormal exits for easier OOM debugging
### Added - Wire up remote `globalSkills` from enterprise remote config with full UI, toggle support, and system prompt integration — enterprise-managed skills now appear under a dedicated "Enterprise Skills" section and support `alwaysEnabled` enforcement - Onboarding flow now uses dynamically fetched recommended models instead of a hardcoded list, with a fallback to the welcome view on failure - Add dedicated "Quota Exceeded" error message in the chat error UI when Cline account spend caps are hit ### Fixed - Fix OOM crashes during long conversations by setting `--max-old-space-size=8192` fo...
### Added - Add Claude Opus 4.7 model support - Add Azure Blob Storage as a storage provider - Add `globalSkills` to remote config - Inline value reuse in user-level remote-config discovery ### Fixed - Fix cache reflection for Cline and Vercel API handlers - Fix stuck `command_output` ask when terminal command ends unexpectedly - Add `use_subagents` to system prompt for GLM, Hermes, and XS models - Fix action injection security risk ### Changed - Remove deprecated evals tool
### Added - Add a dedicated "Spend Limit Reached" error UI when spend caps are hit - Docs updates ### Fixed - Show actual `read_file` line ranges in chat UI
### Added - Added W&B Inference by CoreWeave as a new API provider with 17 models - Improved parallel tool calling support for OpenRouter and Cline providers ### Fixed - Claude Code Provider: handle rate limit events, empty content arrays, error results, and unknown content types without crashing - Tool handlers (`read_file`, `list_files`, `list_code_definition_names`, `search_files`) now return graceful errors instead of crashing
### Added - Implement dynamic free model detection for Cline API - Add file read deduplication cache to prevent repeated reads - Add feature tips tooltip during thinking state ### Fixed - Replace error message when not logged in to Cline - Align ClineRulesToggleModal padding with ServersToggleModal - Skip WebP for GLM and Devstral models running through llama.cpp - Respect user-configured context window in LiteLLM getModel() - Honor explicit model IDs outside static catalog in W&B provider - Add missing Fireworks serverless models and pricing
### Added - Latency improvements for remote workspaces ### Fixed - Stabilize flaky hooks tests ### Changed - Remove example hooks in favor of reading the docs
### Added - Add Cline Kanban launch modal in webview; CLI now launches Kanban by default with a migration view - Add toggle to disable feature tips in chat - Add repeated tool call loop detection to prevent infinite loops wasting tokens ### Fixed - Fix CLI Kanban spawn on Windows by enabling shell mode for `npx.cmd`
### Added - Add "Lazy Teammate Mode" experimental toggle - `read_file` tool now supports chunked reading for targeted file access ### Fixed - Exclude `new_task` tool from system prompt in yolo/headless mode - Fix Kanban demo video formatting ### Changed - Polish `Notification` hook functionality