BREAKING CHANGE: AssistantMessage now uses content array instead of separate fields
- Changed AssistantMessage.content from string to array of content blocks
- Removed separate thinking, toolCalls, and signature fields
- Content blocks can be TextContent, ThinkingContent, or ToolCall types
- Updated streaming events to include start/end events for text and thinking
- Fixed multiTurn test to handle new content structure
Note: Currently only Anthropic provider is updated to work with new API
Other providers need to be updated to match the new interface
- Added contentSignature tracking for assistant messages
- Fixed message format in convertToResponsesFormat (output_text instead of input_text)
- Properly preserve message IDs for multi-turn conversations
- Added proper ResponseOutputMessage type satisfaction
- Updated tests to cover more providers and multi-turn scenarios
- Added dangerouslyAllowBrowser: true to OpenAI client initialization
- Allows usage of the library in browser environments
- Applies to both OpenAICompletionsLLM and OpenAIResponsesLLM
- Added @mariozechner/pi-ai package to the structure
- Updated features to include unified LLM API
- Expanded supported providers list
- Updated tech stack with multiple SDKs
- Added architecture details for AI package
- Updated version numbers to current 0.5.12
- Added testing information for AI package (Vitest)
- Included all packages in build order example
- Moved completed AI package implementation task to done folder
- Task successfully implemented the unified AI API (@mariozechner/pi-ai)
- Package renamed, documentation improved, and published as v0.5.12
- Added note that library only includes tool-calling capable models
- Added Model Discovery section showing how to enumerate models
- Added examples for finding models with specific capabilities
- Added cache read/write costs to model capabilities display
- Clarified that models are auto-fetched from APIs at build time
- Changed package name from @mariozechner/ai to @mariozechner/pi-ai
- Fixed generate-models.ts to fetch from models.dev API instead of local file
- Completely rewrote README with practical examples:
- Image input with base64 encoding
- Proper tool calling with context management
- Streaming with completion indicators
- Abort signal usage
- Provider-specific options (reasoning/thinking)
- Custom model definitions for local/self-hosted LLMs
- Environment variables explanation
- Bumped version to 0.5.9 and published
- Added image tests to OpenAI Completions (gpt-4o-mini)
- Added image tests to Anthropic (claude-sonnet-4-0)
- Added image tests to Google (gemini-2.5-flash)
- Tests verify models can process and describe the red circle test image
- Change ImageContent to simple { type, data, mimeType } structure
- Remove URL and file path support from core interface
- Simplify provider converters to work with base64 data only
- Update validation and implementation considerations
- Clarify that preprocessing is user's responsibility
- Document image support for Anthropic, Google GenAI, OpenAI APIs
- Include format requirements, size limits, and API examples
- Propose unified abstraction layer for cross-provider image handling
- Add implementation examples for format conversion and validation
- Track input/output token costs for all providers
- Calculate costs based on Model pricing information
- Include cost information in AssistantMessage responses
- Add Usage interface with detailed cost breakdown
- Implement calculateCost utility function for cost calculations
- LLM constructors now take Model objects instead of string IDs
- Added provider field to AssistantMessage interface
- Updated getModel function with type-safe model ID autocomplete
- Fixed Anthropic model ID mapping for proper API aliases
- Added baseUrl to Model interface for provider-specific endpoints
- Updated all tests to use getModel for model instantiation
- Removed deprecated models.json in favor of generated models
- Add proper Anthropic model aliases (claude-opus-4-1, claude-sonnet-4-0, etc.)
- Deduplicate models when same ID appears in both models.dev and OpenRouter
- models.dev takes priority over OpenRouter for duplicate IDs
- Fix test to use correct claude-3-5-haiku-latest alias
- Reduces Anthropic models from 11 to 10 (removed duplicate)
- Generated from OpenRouter API and models.dev
- Includes models from Google, OpenAI, Anthropic, xAI, Groq, Cerebras, OpenRouter
- Provides type-safe model selection with autocomplete
- Add Model interface to types.ts with normalized structure
- Create type-safe generic createLLM function with provider-specific model constraints
- Generate models from OpenRouter API and models.dev data
- Strip provider prefixes for direct providers (google, openai, anthropic, xai)
- Keep full model IDs for OpenRouter-proxied models
- Clean separation: types.ts (Model interface), models.ts (factory logic), models.generated.ts (data)
- Remove old model scripts and unused dependencies
- Rename GeminiLLM to GoogleLLM for consistency
- Add tests for new providers (xAI, Groq, Cerebras, OpenRouter)
- Support 181 tool-capable models across 7 providers with full type safety
- Switch from Node.js test runner to Vitest for better DX
- Add test suites for Grok, Groq, Cerebras, and OpenRouter providers
- Add Ollama test suite with automatic server lifecycle management
- Include thinking mode and multi-turn tests for all providers
- Remove example files (consolidated into test suite)
- Add VS Code test configuration
- Generate models.generated.ts from models.json with proper types
- Categorize providers: OpenAI (Responses), OpenAI-compatible, Anthropic, Gemini
- Create createLLM() factory with TypeScript overloads for type safety
- Auto-detect base URLs and environment variables for providers
- Support 353 models across 39 providers with full autocompletion
- Exclude generated file from git (rebuilt on npm build)
- Remove catch-all [key: string]: any from ModelInfo
- Make all required fields non-optional (attachment, reasoning, etc.)
- Add proper union types for modalities (text, image, audio, video, pdf)
- Mark only cost and knowledge fields as optional
- Export ModalityInput and ModalityOutput types
- Add models script to download latest model information
- Create models.ts module to query model capabilities
- Include models.json in package distribution
- Export utilities to check model features (reasoning, tools)
- Update build process to copy models.json to dist
- Add examples for Cerebras, Groq, Ollama, and OpenRouter
- Update OpenAI Completions provider to handle base URL properly
- Simplify README formatting
- All examples use the same OpenAICompletionsLLM provider with different base URLs
- Replace planned features with actual working code examples
- Add clear provider comparison table
- Show real imports and usage patterns
- Include streaming, thinking, and tool calling examples
- Update supported models to match current implementation
- Add multi-turn test to verify thinking and tool calling work together
- Test thinkingSignature handling for proper multi-turn context
- Fix Gemini provider to generate base64 thinkingSignature when needed
- Handle multiple rounds of tool calls in tests (Gemini behavior)
- Make thinking tests more robust for model-dependent behavior
- All 18 tests passing across 4 providers
- Added thinkingConfig with includeThoughts and thinkingBudget support
- Use part.thought boolean flag to detect thinking content per API docs
- Capture and preserve thought signatures for multi-turn function calling
- Added supportsThinking() check for Gemini 2.5 series models
- Updated example to demonstrate thinking configuration
- Handle SDK type limitations with proper type assertions
- Added GeminiLLM provider implementation with GoogleGenerativeAI SDK
- Supports streaming with text/thinking content and completion signals
- Handles Gemini's parts-based content system (text, thought, functionCall)
- Implements tool/function calling with proper format conversion
- Maps between unified types and Gemini-specific formats (model vs assistant role)
- Added test example matching other provider patterns
- Fixed typo in AssistantMessage type (stopResaon -> stopReason) across all providers
- Update LLMOptions interface to include completion boolean parameter
- Modify all providers to signal when text/thinking blocks are complete
- Update examples to handle the completion parameter
- Move documentation files to docs/ directory
- Implement OpenAICompletionsLLM for Chat Completions API with streaming
- Implement OpenAIResponsesLLM for Responses API with reasoning support
- Update types to use LLM/Context instead of AI/Request
- Add support for reasoning tokens, tool calls, and streaming
- Create test examples for both OpenAI providers
- Update Anthropic provider to match new interface
- Define clean API with complete() method and callbacks for streaming
- Add comprehensive type system for messages, tools, and usage
- Implement AnthropicAI provider with full feature support:
- Thinking/reasoning with signatures
- Tool calling with parallel execution
- Streaming via callbacks (onText, onThinking)
- Proper error handling and stop reasons
- Cache tracking for input/output tokens
- Add working test/example demonstrating tool execution flow
- Support for system prompts, temperature, max tokens
- Proper message role types: user, assistant, toolResult
- Set up @mariozechner/ai package structure following monorepo patterns
- Install OpenAI, Anthropic, and Google Gemini SDK dependencies
- Document comprehensive API investigation for all three providers
- Design minimal unified API with streaming-first architecture
- Add models.dev integration for pricing and capabilities
- Implement automatic caching strategy for all providers
- Update project documentation with package creation guide
- Implemented new renderLineBased method that properly handles scrollback boundaries
- Fixed ANSI code preservation in MarkdownComponent line wrapping
- Added comprehensive test to reproduce and verify the fix
- Root cause: PARTIAL rendering strategy couldn't position cursor in scrollback
- Solution: Component-agnostic line comparison with proper viewport boundary handling
Fixed the interrupt mechanism to show "[Interrupted by user]" message when ESC is pressed:
- Removed duplicate UI cleanup from ESC key handler that interfered with event processing
- Added centralized interrupted event emission in exception handler when abort signal is detected
- Removed duplicate event emissions from API call methods to prevent multiple messages
- Added abort signal support to preflight reasoning check for proper cancellation
- Simplified abort detection to only check signal state, not error messages
Fixed rendering artifact where duplicate bottom borders appeared when components
dynamically shifted positions (e.g., Ctrl+C in agent clearing status container).
Root cause: Container wasn't reporting as "changed" when cleared (0 children),
causing differential renderer to skip re-rendering that area.
Solution: Container now tracks previousChildCount and reports changed when
child count changes, ensuring proper re-rendering when containers are cleared.
- Added comprehensive test reproducing the layout shift artifact
- Fixed Container to track and report child count changes
- All tests pass including new layout shift artifact test
- Add header with slash command and file autocomplete instructions
- Add initial welcome message with detailed feature descriptions
- Import TextComponent for the header
- Make it clearer how to use all the demo features
The demos were not showing any output until user input because:
- Components were added before ui.start() was called
- addChild calls requestRender() but it returns early if \!isStarted
- So no initial render happened until user input triggered one
Now ui.start() triggers an initial render if components exist.
- Move chat application example to test/chat-app.ts
- Move multi-component layout example to test/multi-layout.ts
- Update README to reference example files instead of inline code
- Add proper exit handlers (Ctrl+C) to all examples
- Simplify README by reducing inline code examples
- Add surgical differential rendering as the main feature
- Document the three rendering strategies (surgical, partial, full)
- Add performance metrics documentation
- Simplify component examples to be more concise
- Add comprehensive testing section with VirtualTerminal API
- Include testing best practices and performance testing guidance
- Remove duplicate TextEditor documentation section
- New renderDifferentialSurgical method with three strategies:
- SURGICAL: Only update specific changed lines (1-2 lines per render)
- PARTIAL: Clear and re-render from first change when line counts change
- FULL: Clear scrollback and re-render all when changes above viewport
- Preserves all content in scrollback buffer correctly
- Reduces redraws from ~14 lines to ~1.3 lines for common updates
- All 24 tests pass including scrollback preservation tests
- Massive performance improvement: 90% reduction in unnecessary redraws
- renderDifferential now correctly handles content that exceeds viewport
- When changes are above viewport, do full re-render with scrollback clear
- When changes are in viewport, do partial re-render from change point
- All tests pass, correctly preserves 100 items in scrollback
- Issue: Still re-renders too much (entire tail from first change)
