cli-v3.0.50
ClineSummary
This release introduces user-selectable color themes for the interactive TUI, allowing for a more personalized experience. It also enhances stability by fixing several bugs, including issues with git branch updates, Telegram commands, and connector launch collisions, while improving error handling for model responses and context management.
New Features
- Added user-selectable color themes to the interactive TUI, with options to pick themes via `/theme`, the command palette, or the Theme row in `/settings`, and live previews of each theme.
- Introduced auto-approval settings that now take precedence over ACP.
- Enabled connector tools by default for improved functionality.
- Added support for Claude 4.6+ and 5.x models, resolving previous rejection errors.
- Integrated Infomaniak and SCX.ai as new model providers.
- Switched Ollama to use the native AI SDK provider.
Bug Fixes
- Fixed an issue where the git branch shown below the prompt would not update when switching branches from another terminal or editor.
- Resolved an issue where Telegram slash commands like `/clear` were silently dropped due to interception by the Telegram library.
- Corrected a problem where racing connector launches could collide, ensuring instances are claimed before socket mode is opened.
- Fixed a bug where a turn ending with a completed plan was incorrectly rendered as failed if a plan-blocked command was its only tool call.
- Resolved an issue where running out of context would cause a failure with a raw provider error, now recovering by force-compacting and retrying.
- Fixed an issue where empty model responses were only retried on Ollama, now retrying on every provider including OpenRouter, Cline, and OpenAI-compatible endpoints.
- Restored Bedrock prompt caching functionality, which was previously not working due to an incorrect cache format.
- Fixed an issue where reasoning models on OpenAI-compatible endpoints were sent `max_tokens` instead of the supported `max_completion_tokens`.
- Resolved an issue where requests to models without image support would fail, now substituting image content instead.
Improvements
- The TUI now previews each selected theme live.
- The hub supervises connector processes, and `doctor`/`connect` now skip connectors that are already starting.
- The Slack greeting is no longer replayed on reconnect.
- Plan mode now hard-blocks file-editing shell commands instead of relying solely on prompting, while keeping `run_commands` available for read-only investigation.
- The model layer has been upgraded to AI SDK 7.
- Error telemetry no longer reports the same provider failure twice, and repeated failures from unattended retry loops are now rate-limited.