- Add 'aborted' as a distinct stop reason separate from 'error'
- Change AssistantMessage.error to errorMessage for clarity
- Update error event to include reason field ('error' | 'aborted')
- Map provider-specific safety/refusal reasons to 'error' stop reason
- Reorganize utility functions into utils/ directory
- Rename agent.ts to agent-loop.ts for better clarity
- Fix error handling in all providers to properly distinguish abort from error
- Added partial-json package for parsing incomplete JSON during streaming
- Tool call arguments now contain partially parsed JSON during toolcall_delta events
- Enables progressive UI updates (e.g., showing file paths before content is complete)
- Arguments are always valid objects (minimum empty {}), never undefined
- Full validation still occurs at toolcall_end when arguments are complete
- Updated all providers (Anthropic, OpenAI Completions/Responses) to use parseStreamingJson
- Added comprehensive documentation and examples in README
- Added test to verify arguments are always defined during streaming
- Switch from Zod to TypeBox for tool parameter schemas
- TypeBox schemas can be serialized/deserialized as JSON
- Use AJV for runtime validation instead of Zod's parse
- Add StringEnum helper for Google API compatibility (avoids anyOf/const patterns)
- Export Type and Static from main package for convenience
- Update all tests and documentation to reflect TypeBox usage
- Reduce default max tokens for Anthropic to 1/3 of model max
- Fix Google provider to properly handle empty tools array
- Ensure toolConfig is undefined when no tools are present
- Replace JSON Schema with Zod schemas for tool parameter definitions
- Add runtime validation for all tool calls at provider level
- Create shared validation module with detailed error formatting
- Update Agent API with comprehensive event system
- Add agent tests with calculator tool for multi-turn execution
- Add abort test to verify proper handling of aborted requests
- Update documentation with detailed event flow examples
- Rename generate.ts to stream.ts for clarity
- Add 'zai' as a KnownProvider type
- Add ZAI_API_KEY environment variable mapping
- Generate 4 zAI models (glm-4.5-air, glm-4.5v, etc.) using anthropic-messages API
- Add comprehensive test coverage for zAI provider in generate.test.ts and empty.test.ts
- Models support reasoning/thinking capabilities and tool calling
- Google provider sometimes returns duplicate or missing tool call IDs
- Added counter to ensure unique IDs for each tool call
- Check for duplicates and generate new ID when needed
- Fixes issues with multiple tool calls having the same ID
- Anthropic API requires tool call IDs to match pattern ^[a-zA-Z0-9_-]+$
- OpenAI Responses API generates IDs with pipe character (|) which breaks Anthropic
- Added sanitizeToolCallId() to replace invalid characters with underscores
- Fixes cross-provider handoffs from OpenAI Responses to Anthropic
- Added test to verify the fix works
- Replace createLLM with getModel/getModels/getProviders functions
- Rename PROVIDERS to MODELS (internal only, not exposed)
- Add streamSimple/completeSimple for unified reasoning interface
- Update README with new API examples and comprehensive documentation
- Remove model registration (models are now fixed from build time)
- Add proper TypeScript typing for provider-specific options
- Document context serialization, cross-provider handoffs, and browser usage
- Implement QueuedGenerateStream class that extends AsyncIterable with finalMessage() method
- Add new types: GenerateStream, GenerateOptions, GenerateOptionsUnified, GenerateFunction
- Create generateAnthropic function-based implementation replacing class-based approach
- Add comprehensive test suite for the new generate API
- Support streaming events with text, thinking, and tool call deltas
- Map ReasoningEffort to provider-specific options
- Include apiKey in options instead of constructor parameter
- Test handling of empty content arrays
- Test handling of empty string content
- Test handling of whitespace-only content
- All providers handle these edge cases gracefully
- Updated generate-models.ts to fetch these providers directly from models.dev API
- OpenRouter now only used for xAI and other third-party providers
- Fixed test model IDs to match new model names from models.dev
- Removed unused import from google.ts
- Add getApi() method to all providers to identify the API type
- Add api field to AssistantMessage to track which API generated it
- Update transformMessages to check API compatibility instead of model
- Fixes issue where OpenAI Responses API failed when switching models
- Preserves thinking blocks and signatures when staying within same API
- Required header for browser-based access to Anthropic API
- Added to both OAuth and regular API key authentication
- Ensures full browser compatibility
- Add transformMessages utility to handle cross-provider compatibility
- Convert thinking blocks to <thinking> tagged text when switching providers
- Preserve native thinking blocks when staying with same provider/model
- Add comprehensive handoff tests verifying all provider combinations
- Fix OpenAI Completions to return partial results on abort
- Update tool call ID format for Anthropic compatibility
- Document cross-provider handoff capabilities in README
- Anthropic, Google, and OpenAI Responses providers now return partial results when aborted
- Restructured streaming to accumulate content blocks incrementally
- Prevents submission of thinking/toolCall blocks from aborted completions in multi-turn conversations
- Makes UI development easier by providing partial content even when requests are interrupted
- Add inlineSources: true to embed TypeScript source in source maps
- Keeps source maps in separate files (inlineSourceMap: false)
- Enables proper debugging and breakpoints when using packages from npm
- Emit start event with model and provider info after creating stream
- Add abort signal tests for all providers
- Update README abort signal section to reflect non-throwing API
- Fix model references in README examples
- Add 'start' event with model/provider info
- Add 'done' event with stop reason and usage stats
- Add 'error' event handling
- Show more detailed event data in examples
- Add API changes section explaining v0.5.15+ changes
- Update Quick Start example to show content array usage
- Update Tool Calling example to filter tool calls from content blocks
- Update Streaming example to use new onEvent callback
- Fix model IDs in provider-specific examples
- Collect complete output items during streaming instead of building blocks incrementally
- Handle reasoning summary parts with proper newline separation
- Support refusal content in message outputs
- Preserve full reasoning items and message IDs for multi-turn resubmission
- Emit proper streaming events for text and thinking deltas
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
Mario Zechner