- anthropic.ts: use model.api instead of hardcoding 'anthropic-messages'
- openai-responses.ts: use model.api instead of hardcoding 'openai-responses'
- gitlab-duo: simplify to use actual model IDs, export MODELS array
- Extensions register providers via pendingProviderRegistrations
- These were only applied in bindCore() during AgentSession creation
- But model resolution in main.ts happens before session creation
- Fix: apply pending registrations immediately after loading extensions
- Also fix gitlab-duo to pass Authorization header instead of apiKey
- Delegates to pi-ai's built-in Anthropic/OpenAI streaming
- OAuth support with GitLab's bundled client ID
- Direct access token caching (25 min TTL)
- Models: duo-chat-opus/sonnet/haiku-4-5, duo-chat-gpt-5-1/mini/codex
- No external dependencies beyond pi-ai
- Move custom-provider.ts to custom-provider/index.ts
- Add package.json with @anthropic-ai/sdk dependency
- Extension now requires npm install before use
- Add resetApiProviders() to clear and re-register built-in providers
- Add createAssistantMessageEventStream() factory for extensions
- Add streamSimple support in ProviderConfig for custom API implementations
- Call resetApiProviders() on /reload to clean up extension providers
- Add custom-provider.md documentation
- Add custom-provider.ts example with full Anthropic implementation
- Update extensions.md with streamSimple config option
The TUI only re-renders changed lines. During agent streaming, the
conversation lines above DOSBox change but DOSBox lines stay the same.
This caused the image to stay at its old position while text scrolled.
Fix: Add invisible timestamp to image line to force TUI to see it as
changed every render, ensuring the image is always re-rendered at the
correct position.
bundle.extract() uses XMLHttpRequest which doesn't exist in Node.js.
Reverted to writing files directly to Emscripten FS after DOSBox init.
jsdos mounts C: to /home/web_user by default.
The previous approach of writing files to Emscripten FS after DOSBox
started didn't work because the C: drive mount was pointing elsewhere.
Now we create a proper zip archive of QBasic files and include it in
the jsdos bundle using the extract() API with a data URL. The bundle
extracts to the C: drive root on startup.
- DOSBox now starts at session_start and persists in background
- /dosbox command attaches UI to running instance (Ctrl+Q detaches)
- Added dosbox tool with actions: send_keys, screenshot, read_text
- Bundled QuickBASIC 4.5 files, mounted at C:\QB on startup
- Agent can interact with DOSBox programmatically via tool
Use: pi -e ./examples/extensions/pi-dosbox
Then: /dosbox to view, or let agent use the dosbox tool
- allocateImageId() now returns random IDs instead of sequential
- Static images no longer auto-allocate IDs (transient display)
- Only explicit imageId usage (like DOSBox) gets tracked IDs
- Suppress emulators exit logging in DOSBox dispose
Fixes image replacement bug when extension and main app both
allocated sequential IDs starting at 1.
- Add allocateImageId() to generate unique image IDs
- Add deleteKittyImage() and deleteAllKittyImages() functions
- Image component now tracks its ID and has dispose() method
- renderImage() returns imageId for tracking
- DOSBox: reuse single image ID for all frames, delete on dispose
Fixes image accumulation hitting terminal quota and lingering
images after component close.
- Render DOSBox framebuffer as images in terminal via emulators package
- Support keyboard input with js-dos key codes
- Push Kitty enhanced mode for proper key press/release events
- Standalone app (npm start) and pi extension entry point
- Exit with Ctrl+Q
- Classic gameplay with 5x11 alien formation
- 3 alien types, destructible shields, level progression
- Uses Kitty keyboard protocol for smooth movement
- Saves game state on pause, tracks high score
Adds a new extension that generates images via Google Antigravity's
image models (gemini-3-pro-image, imagen-3). Features:
- Returns images as tool result attachments for inline terminal rendering
- Configurable save modes: none, project, global, custom
- Supports env vars (PI_IMAGE_SAVE_MODE, PI_IMAGE_SAVE_DIR) and config files
- Configurable aspect ratios (1:1, 16:9, etc.)
Requires OAuth login via /login for google-antigravity provider.
* feat(extensions): add inline-bash example for expanding !{command} in prompts
Adds an example extension that expands inline bash commands within user
prompts before sending to the agent. Uses the `input` event to transform
patterns like `!{pwd}` or `!{git status}` into their output.
Preserves existing `!command` whole-line bash behavior.
* docs(extensions): add inline-bash to README
* chore: fix stupid bug
- Add Focusable interface for components that need hardware cursor positioning
- Add CURSOR_MARKER (APC escape sequence) for marking cursor position in render output
- Editor and Input components implement Focusable and emit marker when focused
- TUI extracts cursor position from rendered output and positions hardware cursor
- Track hardwareCursorRow separately from cursorRow for differential rendering
- visibleWidth() and extractAnsiCode() now handle APC sequences
- Update overlay-test.ts example to demonstrate Focusable usage
- Add documentation for Focusable interface in docs/tui.md
Closes#719, closes#525
The Editor component now accepts TUI as the first constructor parameter,
enabling it to query terminal dimensions. When content exceeds available
height, the editor scrolls vertically keeping the cursor visible.
Features:
- Max editor height is 30% of terminal rows (minimum 5 lines)
- Page Up/Down keys scroll by page size
- Scroll indicators show lines above/below: ─── ↑ 5 more ───
Breaking change: Editor constructor signature changed from
new Editor(theme)
to
new Editor(tui, theme)
fixes#732
* feat(coding-agent): add input event for extension input interception
Extensions can now intercept, transform, or handle user input before the
agent processes it. Three result types: continue (pass through), transform
(modify text/images), handled (respond without LLM). Handlers chain
transforms and short-circuit on handled. Source field identifies origin.
* fix: make source public, use if/else over ternary
* fix: remove response field, extension handles own UI
Shift+P conflicts with typing capital P. Ctrl+Alt+P is cross-platform
safe and doesn't conflict with common shortcuts like:
- Ctrl+Shift+P (command palette on Windows/VS Code)
- Shift+Alt+P (types π on macOS)
