-
Notifications
You must be signed in to change notification settings - Fork 1.5k
feat: add dynamic status verbs #269
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: dev
Are you sure you want to change the base?
Conversation
- Add generateStatusVerb function with Haiku/GPT-4o-mini fallback - Add /session_generate_verb endpoint - Generate contextual verbs based on user input with safety filters
- Add CurrentStatusVerb, VerbHistory, and VerbCycleIndex fields - Implement AddVerbToHistory with 10-item limit - Add CycleToNextVerb for reverse chronological cycling - Add GenerateStatusVerb client method
- Add verb generation with 800ms debouncing while typing - Add VerbCycleMsg for 2-second cycling during AI processing - Prevent duplicate verb generation on message submit - Add status line display with generated verbs
b4f5d96
to
a317ffc
Compare
- Replace CurrentStatusVerb and VerbHistory with PromptVerbs and VerbIndex - Implement AddPromptVerb, ResetPromptVerbs, and CycleToNextVerb methods - Adjust editor component to utilize new prompt verb management
…ompt - Move verb prompt text to a new file `verb.txt` - Update `SystemPrompt` to include a function for retrieving the verb prompt - Refactor `index.ts` to use the new verb prompt function
- Introduce verbText field to track the current verb text - Optimize verb generation logic to prevent unnecessary calls - Clean up lastProcessedText references and ensure clarity in state management
Whilst I like the personality this change provides, I'm not convinced I'd want to burn tokens on this for every message by default - even though it does only use the small models. If this is added it ideally would have a configuration option to enable/disable it - disabled by default. Perhaps the option could have a "local-only" setting, that would only run if you had a local model configured, which could also be a a safe default. |
## Summary This PR implements dual model support (main + turbo) for cost-optimized operations and adds model sorting functionality. ### Key Changes #### Dual Model Support - Added `turbo_model` and `turbo_cost_threshold` config options - New dual-pane model selector (Tab to switch panes) - Visual indicators: ⚡ (turbo), 🧠 (reasoning), 🔧 (tools) - Smart turbo model selection with fallback logic - Fixed Anthropic auth showing incorrect turbo status #### Model Sorting - Added `release_date` and `last_updated` fields to model schema - Press 'S' to cycle through sort modes: Name, Last Updated, Release Date - Stable multi-level sorting with consistent ordering - Helps discover newest models and track updates ### Impact Enables cost optimization for PRs sst#269 (status verbs) and sst#275 (window titles) to use configured turbo models instead of hardcoded ones. ### Demo https://github.com/user-attachments/assets/d076e840-d790-4e23-8cf7-a179282d1f0b
## Summary This PR implements dual model support (main + turbo) for cost-optimized operations and adds model sorting functionality. ### Key Changes #### Dual Model Support - Added `turbo_model` and `turbo_cost_threshold` config options - New dual-pane model selector (Tab to switch panes) - Visual indicators: ⚡ (turbo), 🧠 (reasoning), 🔧 (tools) - Smart turbo model selection with fallback logic - Fixed Anthropic auth showing incorrect turbo status #### Model Sorting - Added `release_date` and `last_updated` fields to model schema - Press 'S' to cycle through sort modes: Name, Last Updated, Release Date - Stable multi-level sorting with consistent ordering - Helps discover newest models and track updates ### Impact Enables cost optimization for PRs sst#269 (status verbs) and sst#275 (window titles) to use configured turbo models instead of hardcoded ones. ### Demo https://github.com/user-attachments/assets/d076e840-d790-4e23-8cf7-a179282d1f0b
## Summary This PR implements dual model support (main + turbo) for cost-optimized operations and adds model sorting functionality. ### Key Changes #### Dual Model Support - Added `turbo_model` and `turbo_cost_threshold` config options - New dual-pane model selector (Tab to switch panes) - Visual indicators: ⚡ (turbo), 🧠 (reasoning), 🔧 (tools) - Smart turbo model selection with fallback logic - Fixed Anthropic auth showing incorrect turbo status #### Model Sorting - Added `release_date` and `last_updated` fields to model schema - Press 'S' to cycle through sort modes: Name, Last Updated, Release Date - Stable multi-level sorting with consistent ordering - Helps discover newest models and track updates ### Impact Enables cost optimization for PRs sst#269 (status verbs) and sst#275 (window titles) to use configured turbo models instead of hardcoded ones. ### Demo https://github.com/user-attachments/assets/d076e840-d790-4e23-8cf7-a179282d1f0b
Summary
Test plan
CleanShot.2025-06-20.at.23.53.35.mp4