- Add KIMI_MODEL_ADAPTIVE_THINKING environment variable and matching adaptive_thinking model-alias field to force adaptive thinking on or off, overriding Anthropic model-name version inference
- Add /provider command for managing AI providers with support for custom registry imports
- Introduce a tabbed model selector in the UI
- Render scheduled reminders distinctly in the TUI
- Expose cron fired events to SDK clients
- Report cron fire times with local timezone offsets
- Include match count in truncation messages
- Report truncated compaction summaries clearly
- Apply valid completion token budgets across supported providers
- Polish TUI visual interaction
- Clarify Kimi Platform API key login labels and prompt details
- Fix glob pattern backslash escaping
Minor Changes
-
#232
a24bfb1- AddKIMI_MODEL_ADAPTIVE_THINKING(and a matchingadaptive_thinkingmodel-alias field) to force adaptive thinking (thinking: { type: 'adaptive' }) on or off, overriding the Anthropic model-name version inference. This lets custom-named staff endpoints that back an adaptive-capable model opt in even when the model name does not encode a parseable Claude version. -
#264
42bb914- Add/providercommand for managing AI providers, support custom registry imports, and introduce a tabbed model selector. -
#204
ee69d0a- Render scheduled reminders distinctly in the TUI, expose cron fired events to SDK clients, and report cron fire times with local timezone offsets.
Patch Changes
-
#282
a580cd3- Fix glob pattern backslash escaping and include match count in truncation messages. -
#267
e2e1728- Report truncated compaction summaries clearly and apply valid completion token budgets across supported providers. -
#274
a1dfbfe- Clarify Kimi Platform API key login labels and prompt details.