agent/pi - pi - Penguin

fix(ai): Fix browser compatibility for Anthropic OAuth tokens

- Check if process exists before modifying process.env
- Prevents errors in browser environments
- Maintains OAuth token functionality in Node.js

Mario Zechner · 2025-09-01 21:46:22 +02:00

cf35215686

chore: Bump version to 0.5.20

Mario Zechner · 2025-09-01 18:44:15 +02:00

add1b76b6c

feat(ai): Add cross-provider message handoff support

- 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

Mario Zechner · 2025-09-01 18:43:49 +02:00

46b5800d36

refactor(ai): Update API to support partial results on abort

- 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

Mario Zechner · 2025-09-01 01:57:45 +02:00

bf1f410c2b

chore: Bump version to 0.5.19

Mario Zechner · 2025-08-31 23:56:58 +02:00

5d5cd7955b

fix(ai): Fix OpenAI Responses provider import order and cost calculation

Mario Zechner · 2025-08-31 23:56:39 +02:00

7db3068cee

chore: Bump version to 0.5.18

Mario Zechner · 2025-08-31 23:49:29 +02:00

f87ac359bb

chore: Bump version to 0.5.17

Mario Zechner · 2025-08-31 23:09:35 +02:00

683263ba27

feat(ai): Add start event emission to all providers

- 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

Mario Zechner · 2025-08-31 23:09:14 +02:00

a132b8140c

docs(ai): Add all event types to streaming example

- 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

Mario Zechner · 2025-08-31 22:38:13 +02:00

8d4edf6458

docs(ai): Remove 'now' language and fix model IDs in README

Mario Zechner · 2025-08-31 22:36:58 +02:00

8cca5597e4

docs(ai): Remove old API reference from README

Mario Zechner · 2025-08-31 22:35:23 +02:00

c960d36da1

chore: Bump version to 0.5.16

Mario Zechner · 2025-08-31 22:17:35 +02:00

8f4e96f207

docs(ai): Update README for new content blocks API

- 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

Mario Zechner · 2025-08-31 22:17:17 +02:00

80da49cd40

chore: Bump version to 0.5.15

Mario Zechner · 2025-08-31 22:11:50 +02:00

0f2eaa70e9

fix(ai): Fix OpenAI Responses provider multi-turn conversation support

- 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

Mario Zechner · 2025-08-31 22:11:08 +02:00

ee4c131873

refactor(ai): Update OpenAI Completions provider to new content block API

Mario Zechner · 2025-08-31 20:59:57 +02:00

a72e6d08d4

refactor(ai): Simplify Google provider with cleaner block handling

Mario Zechner · 2025-08-31 20:31:08 +02:00

7c8cdacc09

refactor(ai): Update API to support multiple thinking and text blocks

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

Mario Zechner · 2025-08-31 19:32:12 +02:00

f29752ac82

test(ai): Add image input test for Anthropic Haiku 3.5

- Added image handling test for Claude 3.5 Haiku
- Ensures vision capabilities are properly tested

Mario Zechner · 2025-08-30 23:00:30 +02:00

f8a81b9453

fix(ai): Fix OpenAI Responses provider multi-turn conversation support

- 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

Mario Zechner · 2025-08-30 22:55:29 +02:00

cff766d3e2

feat(ai): Enable browser support for OpenAI providers

- Added dangerouslyAllowBrowser: true to OpenAI client initialization
- Allows usage of the library in browser environments
- Applies to both OpenAICompletionsLLM and OpenAIResponsesLLM

Mario Zechner · 2025-08-30 22:29:14 +02:00

2e90f8f8bc

chore: Mark AI package implementation task as complete

- 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

Mario Zechner · 2025-08-30 21:53:23 +02:00

8b12312d72

docs(ai): Fix model names in README examples

- Changed gpt-4o-mini to gpt-5-mini in examples to match actual model names
- Minor formatting fixes

Mario Zechner · 2025-08-30 21:48:17 +02:00

889208dccd

docs(ai): Improve README with model discovery and capabilities documentation

- 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

Mario Zechner · 2025-08-30 21:46:54 +02:00

dae40167a3

feat(ai): Rename package to @mariozechner/pi-ai and improve documentation

- 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

Mario Zechner · 2025-08-30 21:41:22 +02:00

d46a98ec10

feat(ai): Add image input tests for vision-capable models

- 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

Mario Zechner · 2025-08-30 18:37:17 +02:00

796e48b80e

docs(ai): Simplify ImageContent interface to base64-only approach

- 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

Mario Zechner · 2025-08-30 18:12:36 +02:00

4ac0c6ea28

docs(ai): Add comprehensive image input documentation for all LLM providers

- 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

Mario Zechner · 2025-08-30 18:07:35 +02:00

0b50c3f36d

fix(ai): Fix OpenAI completions store field type issue

- Cast params to any for store field assignment
- Maintains compatibility with providers that don't support store field

Mario Zechner · 2025-08-30 01:08:08 +02:00

545d04fc5c

feat(ai): Add cost tracking to LLM implementations

- 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

Mario Zechner · 2025-08-30 00:45:08 +02:00

550da5e47c

refactor(ai): Update LLM implementations to use Model objects

- 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

Mario Zechner · 2025-08-30 00:21:03 +02:00

f9d688d577

fix(ai): Deduplicate models and add Anthropic aliases

- 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)

Mario Zechner · 2025-08-29 23:34:01 +02:00

d61d09b88d

feat(ai): Add models.generated.ts with 181 tool-capable models

- Generated from OpenRouter API and models.dev
- Includes models from Google, OpenAI, Anthropic, xAI, Groq, Cerebras, OpenRouter
- Provides type-safe model selection with autocomplete

Mario Zechner · 2025-08-29 23:20:53 +02:00

9c3f32b91e

refactor(ai): Implement unified model system with type-safe createLLM

- 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

Mario Zechner · 2025-08-29 23:19:47 +02:00

c7618db3f7

feat(ai): Migrate tests to Vitest and add provider test coverage

- 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

Mario Zechner · 2025-08-29 21:32:45 +02:00

3f36051bc6

feat(ai): Add auto-generated TypeScript models with factory function

- 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)

Mario Zechner · 2025-08-25 21:31:29 +02:00

da66a97ea7

fix(ai): Improve ModelInfo types based on actual data structure

- 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

Mario Zechner · 2025-08-25 20:18:34 +02:00

9b8ea585bd

feat(ai): Add models.dev data integration

- 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

Mario Zechner · 2025-08-25 20:10:54 +02:00

02a9b4f09f

feat(ai): Add OpenAI-compatible provider examples for multiple services

- 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

Mario Zechner · 2025-08-25 17:41:47 +02:00

4bb3a5ad02

docs(ai): Update README with working quick start examples

- 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

Mario Zechner · 2025-08-25 15:58:57 +02:00

6112029076

test(ai): Add comprehensive E2E tests for all AI providers

- 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

Mario Zechner · 2025-08-25 15:54:26 +02:00

7a6852081d

fix(ai): Correct Gemini thinking config structure

- Fixed thinkingConfig to be at top level, not nested under 'config'
- Matches Gemini API documentation structure

Mario Zechner · 2025-08-25 10:33:58 +02:00

289e60ab88

feat(ai): Add proper thinking support for Gemini 2.5 models

- 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

Mario Zechner · 2025-08-25 10:26:23 +02:00

3e1422d3d7

feat(ai): Implement Gemini provider with streaming and tool support

- 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

Mario Zechner · 2025-08-24 20:41:32 +02:00

a8ba19f0b4

refactor(ai): Add completion signal to onText/onThinking callbacks

- 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

Mario Zechner · 2025-08-24 20:33:26 +02:00

cb4c32faaa

feat(ai): Add OpenAI Completions and Responses API providers

- 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

Mario Zechner · 2025-08-24 20:18:10 +02:00

8364ecde4a

feat(ai): Implement unified AI API with Anthropic provider

- 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

Mario Zechner · 2025-08-17 23:30:20 +02:00

e5aedfed29

feat(ai): Create unified AI package with OpenAI, Anthropic, and Gemini support

- 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 · 2025-08-17 20:18:45 +02:00

f064ea0e14

fix: Remove unused imports and add biome-ignore for false positive

- Remove unused SlashCommand import from tui-renderer.ts
- Add biome-ignore comment for previousRenderCommands which is actually used

Mario Zechner · 2025-08-16 19:21:43 +02:00

2c03724862

79 Commits