- Convert thinking blocks with missing/empty signatures to text blocks
- Prevents 400 error: 'Invalid signature in thinking block'
- Occurs when stream is aborted mid-thinking and message is resubmitted
- Add NO_IMAGE to error finish reasons in Google provider
- Fix non-null assertion after optional chaining in Anthropic provider
- Migrate biome config to 2.3.5
- Ignore Tailwind CSS file from biome checks
- Bump all packages to version 0.6.0
Tool results now use content blocks and can include both text and images.
All providers (Anthropic, Google, OpenAI Completions, OpenAI Responses)
correctly pass images from tool results to LLMs.
- Update ToolResultMessage type to use content blocks
- Add placeholder text for image-only tool results in Google/Anthropic
- OpenAI providers send tool result + follow-up user message with images
- Fix Anthropic JSON parsing for empty tool arguments
- Add comprehensive tests for image-only and text+image tool results
- Update README with tool result content blocks API
- Add handling for message_start event to capture initial token usage
- Fix message_delta to use assignment (=) instead of addition (+=)
since Anthropic sends cumulative token counts, not incremental
- Add comprehensive tests for all providers (Google, OpenAI Completions,
OpenAI Responses, Anthropic)
- Document OpenAI limitation: token stats only available at stream end
Fixes issue where aborted streams had zero token counts despite
Anthropic sending input tokens in the initial message_start event.
Fixes issue where unpaired Unicode surrogates in tool results cause JSON serialization errors in API providers, particularly Anthropic.
- Add sanitizeSurrogates() utility function to remove unpaired surrogates
- Apply sanitization in all provider convertMessages() functions:
- User message text content (string and text blocks)
- Assistant message text and thinking blocks
- Tool result output
- System prompts
- Valid emoji (properly paired surrogates) are preserved
- Add comprehensive test suite covering all 8 providers
Previously only Google and Groq handled unpaired surrogates correctly.
Now all providers (Anthropic, OpenAI Completions/Responses, Google, xAI, Groq, Cerebras, zAI) sanitize text before API submission.
Storage Architecture:
- New pluggable storage system with backends (LocalStorage, ChromeStorage, IndexedDB)
- SettingsRepository for app settings (proxy config, etc.)
- ProviderKeysRepository for API key management
- AppStorage with global accessors (getAppStorage, setAppStorage, initAppStorage)
Transport Refactoring:
- Renamed DirectTransport → ProviderTransport (calls LLM providers with optional CORS proxy)
- Renamed ProxyTransport → AppTransport (uses app server with user auth)
- Updated TransportMode: "direct" → "provider", "proxy" → "app"
CORS Proxy Integration:
- ProviderTransport checks proxy.enabled/proxy.url from storage
- When enabled, modifies model baseUrl to route through proxy: {proxyUrl}/?url={originalBaseUrl}
- ProviderKeyInput test function also honors proxy settings
- Settings dialog with Proxy tab (Switch toggle, URL input, explanatory description)
Anthropic Prompt Caching:
- System prompt cached with cache_control markers (both OAuth and regular API keys)
- Last user message cached to cache conversation history
- Saves 90% on input tokens for cached content (10x cost reduction)
Settings Dialog Improvements:
- Configurable tab system with SettingsTab base class
- ApiKeysTab and ProxyTab as custom elements
- Switch toggle for proxy enable (instead of Checkbox)
- Explanatory paragraphs for each tab
- ApiKeyPromptDialog reuses ProviderKeyInput component
Removed:
- Deprecated ApiKeysDialog (replaced by ProviderKeyInput in SettingsDialog)
- Old storage-adapter and key-store (replaced by new storage architecture)
- 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
- 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
- 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
- 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
- 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
- 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 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
- 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 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
- 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
- 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
