pi-reasoning - automatic reasoning levels

# pi-reasoning - pi.dev extension Automatic reasoning level management for [pi.dev](https://pi.dev). Sets the thinking/reasoning level based on the selected model with sensible defaults for all major models. No more manually adjusting reasoning every time you switch models - `pi-reasoning` does it for you. ## Features - **🧠 Auto-reasoning** - Model change β†’ optimal thinking level applied instantly - **πŸ“‹ Sensible defaults** - Covers Claude, GPT, Gemini, DeepSeek, Llama, Mistral, Kimi, o-series - **βš™οΈ `/reasoning` command** - Manual override, auto re-apply, or check current level (`/effort` is an alias) - **πŸ“Š Status bar indicator** - Colored dot + level always visible - **πŸ”Œ Zero config** - Install and go ## Install ```bash pi install npm:@pixu1980/pi-reasoning ``` Requires **Node.js β‰₯ 22** (uses `--experimental-strip-types`). ## How it works When you switch models (via `/model`, `Ctrl+P`, or session restore), the extension: 1. Checks if the new model supports reasoning 2. Looks up the model in its internal mapping table 3. Applies the corresponding thinking level 4. Updates the status bar with the current level Non-reasoning models are handled by pi's built-in clamping (always `off`). ### Default mappings | Model family | Thinking level | |---|---| | Claude Opus 4/3, o3, o4, DeepSeek R1 | `max` | | Claude Sonnet 4/4.5, GPT-5, Gemini 2.5/3, DeepSeek, Kimi, QwQ | `high` | | Claude 3 Sonnet, GPT-4o/4.1/4, Gemini 2.0 Pro, Llama 3/4, Mistral Large | `medium` | | Claude Haiku/3 Haiku, GPT-4o-mini, Gemini 2.0 Flash, Mistral Small | `low` | | GPT-4.1-mini | `minimal` | | GPT-4.1-nano, GPT-4-mini | `off` | Models not in the map get a heuristic guess based on their name (`nano` β†’ off, `mini`/`flash` β†’ low, `large`/`pro` β†’ high, else medium). ### Native pi.dev `thinkingLevelMap` support The extension fully respects each model's native `thinkingLevelMap` as defined by pi.dev. This means: - **Available levels** are determined by the model's actual capabilities, not by the extension's mapping table. - **`xhigh` and `max`** are opt-in levels: they only appear in the menu for models that explicitly declare them in their `thinkingLevelMap` (e.g. `claude-opus-4-7`, `claude-fable-5`). - **Missing `thinkingLevelMap`**: when a model doesn't declare one, only standard levels through `high` are offered - `xhigh`/`max` are hidden. - **Auto-apply clamping**: if the extension's recommended level isn't supported by the model, it automatically falls back to the highest available level. ## Usage ### `/reasoning` - Show or set reasoning level `/effort` is an alias: it is the same command under both names. ``` /reasoning Show current level (interactive menu) /reasoning auto Re-apply auto-reasoning for current model /reasoning high Set specific level (off/minimal/low/medium/high/xhigh/max) /reasoning reset Restore default model mappings /reasoning map Show active modelβ†’level mappings /effort Alias for /reasoning (all arguments identical) ``` Every menu entry, status line and notification renders a level as `emoji + level` with a per-level separator: one space for `off`/`minimal`/`low`/`medium`/`max` (`βšͺ off`, `πŸ”₯ max`), two spaces for `high`/`xhigh` (`❀️ high`, `❀️‍πŸ”₯ xhigh`). ### Examples ```bash # Check current level /reasoning # β†’ select menu: βšͺ off / πŸ’š minimal / πŸ’› low / 🧑 medium / ❀️ high / βš™οΈ auto # Switch to a reasoning model /model claude-sonnet-4-20250514 # β†’ Status bar: ❀️ claude-sonnet-... # Override manually (either name works) /reasoning max # β†’ "Reasoning level β†’ πŸ”₯ max" /effort low # β†’ "Reasoning level β†’ πŸ’› low" # Re-apply auto after manual override /reasoning auto # β†’ "Auto-reasoning β†’ ❀️ high (anthropic/claude-sonnet-4-20250514)" # See all mappings /reasoning map # β†’ "Active mappings (24): # claude-opus-4 β†’ max # claude-sonnet-4-5 β†’ high # ..." ``` ### Status bar indicator The extension adds a status bar entry showing the current model and level: | Indicator | Level | |-----------|-------| | βšͺ model | off | | πŸ’š model | minimal | | πŸ’› model | low | | 🧑 model | medium | | ❀️ model | high | | ❀️‍πŸ”₯ model | xhigh | | πŸ”₯ model | max | The status updates automatically on model change and level change. ## Customization Want different mappings? The extension is designed for easy modification. Edit `modelMap` in `index.ts` to add your own patterns, or use the `/reasoning reset` command to restore defaults after experimenting. ### Pattern matching rules - Patterns are matched as **case-insensitive substrings** against the model ID - Entries are checked **in order** - first match wins - Put more specific patterns before broader ones - Optionally filter by **provider** (e.g. `providers: ["anthropic"]`) ### Example custom entries ```typescript // Custom provider filter { pattern: "my-custom-model", level: "high", providers: ["my-provider"] }, // Broad family match (caught by more specific entries first) { pattern: "gpt", level: "medium" }, ``` ## Development ```bash # From monorepo root cd packages/pi-reasoning pi -e . # Test locally ``` ### Files | File | Role | |------|------| | `index.ts` | Extension entry - model map, event handlers, /reasoning + /effort command | | `package.json` | Package metadata, peer deps | | `README.md` | This file | ## How it integrates The extension uses two pi.dev lifecycle hooks: 1. **`model_select`** - Fired when the model changes. We look up the new model in our mapping and apply the corresponding thinking level. 2. **`thinking_level_select`** - Fired when the thinking level changes (from any source). We keep the status bar in sync. The `pi.setThinkingLevel()` API handles clamping to model capabilities, so a `max` setting on a non-reasoning model is safely ignored. ## Related - [pi.dev extensions documentation](https://pi.dev/docs/extensions) - [pi.dev models documentation](https://pi.dev/docs/models) ## License MIT