Saoud Rizwan
54aeba1fee
* feat: add double-check completion experimental feature When enabled, the first attempt_completion call in a task is rejected with a tool error that instructs the model to re-verify its work against the original task requirements. The rejection includes the initial task text for context. The second call proceeds normally. This is opt-in (default off) and available via: - Settings > Features > Experimental > Double-Check Completion - CLI flag: --double-check-completion - CLI TUI settings panel toggle Adds completionAttemptCount to TaskState, plumbs the setting through TaskConfig/ToolExecutor following existing patterns, and includes 9 unit tests. * chore: add cli:run script for quick CLI testing * fix: increase task preview to 8000 chars, revert unintended regex change * fix: preserve existing proto field numbers The auto-generator renumbered open_ai_headers (175->177) and openai_codex_oauth_credentials (46->48), and dropped the reserved 146 comment. Restore original field numbers to avoid breaking wire-format compatibility. * fix: remove partial completion_result message on double-check rejection During streaming, handlePartialBlock shows the completion_result in the chat view. When we reject the first attempt, we need to clean up that partial message so the user doesn't see a stale completion that was actually rejected. * refactor: switch from counter to boolean toggle for double-check Use a boolean pending flag instead of a counter so that every attempt_completion gets double-checked, not just the first one in a task. The flag toggles: reject (set pending), accept (clear pending), so if the model does more work and tries to complete again later, it gets double-checked again.
Cline
Meet Cline, an AI assistant that lives in your terminal.
Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support.
npm i -g cline
# cd into your project and run:
cline
Move your mouse around under the Cline icon for a surprise!
Use any API and Model
Cline supports API providers like ChatGPT, Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, GCP Vertex, Cerebras and Groq. You can also configure any OpenAI compatible API, or use a local model through LM Studio/Ollama. If you're using a Cline Account, you'll always have access to the newest models as soon as they're available.
Stay in Control with Human-in-the-Loop
Cline asks for your approval before running commands, editing files, or taking any action. Review each step and approve or reject as you go—or enable auto-approve to let Cline work autonomously to completion.
Plan & Act Modes
Toggle to Plan Mode to discuss implementation and architecture with Cline. He'll ask clarifying questions, explore your codebase, and present a plan for you to align on. Once you're satisfied, switch to Act Mode and let Cline execute the plan.
Enterprise
Get the same Cline experience with enterprise-grade controls: SSO (SAML/OIDC), global policies and configuration, observability with audit trails, private networking (VPC/private link), and self-hosted or on-prem deployments, and enterprise support. Learn more at our enterprise page or talk to us.