docs(claude-code): mark subscription mode broken on macOS

PR #12 shipped oauthToken support with optimistic framing, but testing revealed @anthropic-ai/claude-agent-sdk has a macOS-specific bug: the SDK isolates CLAUDE_CONFIG_DIR per invocation and tries to copy ~/.claude/.credentials.json, which doesn't exist on macOS (creds live in the Keychain). The OAuth token gets misclassified as an API key and requests are billed against API credits instead of the subscription — subscribers without API credits see "Credit balance is too low" errors. Direct `claude -p` works fine, so the upstream SDK is the broken layer. Changes: - README Claude Code section: lead with the macOS status note and point subscribers at ClaudeProvider + ANTHROPIC_API_KEY as the current workaround. - JSDoc on ClaudeCodeProvider: same status note. - billing_error message: explain the bug and recommend the workaround so users can self-diagnose from the error alone. No code removal — when the SDK fix lands upstream, oauthToken users will Just Work without any code changes here.
Merge pull request 'fix(claude-code): add oauthToken config for subscription SDK auth' (#12 ) from fix/claude-code-oauth-token into main
2026-05-21 22:05:48 +02:00 · 2026-05-21 12:56:28 +00:00 · 2026-05-21 14:56:14 +02:00 · 2026-05-21 14:39:36 +02:00 · 2026-05-21 12:38:05 +00:00 · 2026-05-21 14:37:33 +02:00
14 changed files with 1262 additions and 971 deletions
--- a/README.md
+++ b/README.md
@@ -1,35 +1,10 @@
 # Simple AI Provider
-A professional, type-safe TypeScript package that provides a unified interface for multiple AI providers. Currently supports **Claude (Anthropic)**, **OpenAI**, **Google Gemini**, and **OpenWebUI** with a consistent API across all providers.
+A type-safe TypeScript library with a single API surface for **Claude (Anthropic)**, **OpenAI**, **Google Gemini**, **OpenWebUI**, and **Claude Code** (subscription-friendly via local CLI).
-## ✨ Features
+The same `complete()` / `stream()` interface works across every provider, with consistent error types, streaming, and optional structured (typed JSON) output.
- 🔗 **Unified Interface**: Same API for Claude, OpenAI, Gemini, and OpenWebUI
+## Install
 - 🎯 **Type Safety**: Full TypeScript support with comprehensive type definitions  
 - 🚀 **Streaming Support**: Real-time response streaming for all providers
 - 🛡️ **Error Handling**: Standardized error types with provider-specific details
 - 🏭 **Factory Pattern**: Easy provider creation and management
 - 🔧 **Configurable**: Extensive configuration options for each provider
 - 📦 **Zero Dependencies**: Lightweight with minimal external dependencies
 - 🌐 **Local Support**: OpenWebUI integration for local/private AI models
 - 🎨 **Structured Output**: Define custom response types for type-safe AI outputs
 - 🏗️ **Provider Registry**: Dynamic provider registration and creation system
 - ✅ **Comprehensive Testing**: Full test coverage with Bun test framework
 - 🔍 **Advanced Validation**: Input validation with detailed error messages
 ## 🏗️ Architecture
 The library is built on solid design principles:
 - **Template Method Pattern**: Base provider defines the workflow, subclasses implement specifics
 - **Factory Pattern**: Clean provider creation and management
 - **Strategy Pattern**: Unified interface across different AI providers
 - **Type Safety**: Comprehensive TypeScript support throughout
 - **Error Normalization**: Consistent error handling across all providers
 - **Validation First**: Input validation before processing
 - **Extensibility**: Easy to add new providers via registry system
 ## 🚀 Quick Start
 ```bash
 npm install simple-ai-provider
@@ -37,37 +12,14 @@ npm install simple-ai-provider
 bun add simple-ai-provider
 ```
-### Basic Usage
+Requires Node ≥ 18 (or Bun). TypeScript ≥ 5 is recommended as a peer dependency.
 ## Quick start
 ```typescript
-import { ClaudeProvider, OpenAIProvider, GeminiProvider, OpenWebUIProvider } from 'simple-ai-provider';
+import { ClaudeProvider } from 'simple-ai-provider';
-// Claude
+const claude = new ClaudeProvider({ apiKey: process.env.ANTHROPIC_API_KEY! });
 const claude = new ClaudeProvider({
  apiKey: process.env.ANTHROPIC_API_KEY!,
  defaultModel: 'claude-3-5-sonnet-20241022'
 });
 // OpenAI  
 const openai = new OpenAIProvider({
  apiKey: process.env.OPENAI_API_KEY!,
  defaultModel: 'gpt-4o'
 });
 // Google Gemini
 const gemini = new GeminiProvider({
  apiKey: process.env.GOOGLE_AI_API_KEY!,
  defaultModel: 'gemini-1.5-flash'
 });
 // OpenWebUI (local)
 const openwebui = new OpenWebUIProvider({
  apiKey: 'ollama', // Often not required
  baseUrl: 'http://localhost:3000',
  defaultModel: 'llama2'
 });
 // Initialize and use any provider
 await claude.initialize();
 const response = await claude.complete({
@@ -75,183 +27,107 @@ const response = await claude.complete({
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain TypeScript in one sentence.' }
  ],
-  maxTokens: 100,
+  maxTokens: 200
  temperature: 0.7
 });
 console.log(response.content);
 console.log(response.usage);   // { promptTokens, completionTokens, totalTokens }
 ```
-## 🏭 Factory Functions
+Every provider follows the same pattern: construct, `initialize()`, then `complete()` or `stream()`.
-Create providers using factory functions for cleaner code:
+## Providers
 ### Claude (Anthropic API)
 ```typescript
-import { createProvider, createClaudeProvider, createOpenAIProvider, createGeminiProvider, createOpenWebUIProvider } from 'simple-ai-provider';
+import { ClaudeProvider } from 'simple-ai-provider';
-// Method 1: Specific factory functions
+const claude = new ClaudeProvider({
-const claude = createClaudeProvider('your-key', { defaultModel: 'claude-3-5-sonnet-20241022' });
+  apiKey: process.env.ANTHROPIC_API_KEY!,
-const openai = createOpenAIProvider('your-key', { defaultModel: 'gpt-4o' });
+  defaultModel: 'claude-3-5-sonnet-20241022', // optional
-const gemini = createGeminiProvider('your-key', { defaultModel: 'gemini-1.5-flash' });
+  version: '2023-06-01',                       // optional
-const openwebui = createOpenWebUIProvider({ apiKey: 'your-key', baseUrl: 'http://localhost:3000' });
+  timeout: 30_000,                             // optional, ms
-
+  maxRetries: 3                                // optional
 // Method 2: Generic factory
 const provider = createProvider('claude', { apiKey: 'your-key' });
 ```
 ### Provider Registry
 For dynamic provider creation and registration:
 ```typescript
 import { ProviderRegistry, ClaudeProvider } from 'simple-ai-provider';
 // Register a custom provider
 ProviderRegistry.register('my-claude', ClaudeProvider);
 // Create provider dynamically
 const provider = ProviderRegistry.create('my-claude', { apiKey: 'your-key' });
 // Check available providers
 const availableProviders = ProviderRegistry.getRegisteredProviders();
 console.log(availableProviders); // ['claude', 'openai', 'gemini', 'openwebui', 'my-claude']
 ```
 ## 🎨 Structured Response Types
 Define custom response types for type-safe, structured AI outputs. The library automatically parses the AI's response into your desired type.
 ```typescript
 import { createResponseType, createClaudeProvider } from 'simple-ai-provider';
 // 1. Define your response type
 interface ProductAnalysis {
  productName: string;
  priceRange: 'budget' | 'mid-range' | 'premium';
  pros: string[];
  cons: string[];
  overallRating: number; // 1-10 scale
  recommendation: 'buy' | 'consider' | 'avoid';
 }
 // 2. Create a ResponseType object
 const productAnalysisType = createResponseType<ProductAnalysis>(
  'A comprehensive product analysis with pros, cons, rating, and recommendation'
 );
 // 3. Use with any provider
 const claude = createClaudeProvider({ apiKey: 'your-key' });
 await claude.initialize();
 const response = await claude.complete<ProductAnalysis>({
  messages: [
    { role: 'user', content: 'Analyze the iPhone 15 Pro from a consumer perspective.' }
  ],
  responseType: productAnalysisType,
  maxTokens: 800
 });
 // 4. Get the fully typed and parsed response
 const analysis = response.content;
 console.log(`Product: ${analysis.productName}`);
 console.log(`Recommendation: ${analysis.recommendation}`);
 console.log(`Rating: ${analysis.overallRating}/10`);
 ```
-### Key Benefits
+### Claude Code (via local CLI)
- **Automatic Parsing**: The AI's JSON response is automatically parsed into your specified type.
+`ClaudeCodeProvider` wraps `@anthropic-ai/claude-agent-sdk`, which spawns the local `claude` CLI under the hood.
 - **Type Safety**: Get fully typed responses from AI providers with IntelliSense.
 - **Automatic Prompting**: System prompts are automatically generated to guide the AI.
 - **Validation**: Built-in response validation and parsing logic.
 - **Consistency**: Ensures AI outputs match your expected format.
 - **Developer Experience**: Catch errors at compile-time instead of runtime.
-### Streaming with Response Types
+> **Honest status:** the **API-key mode** (Mode B below) works reliably. The **subscription mode** (Mode A) is currently broken on macOS due to an upstream bug in `@anthropic-ai/claude-agent-sdk` — the SDK isolates `CLAUDE_CONFIG_DIR` per invocation and tries to copy a `~/.claude/.credentials.json` file that doesn't exist on macOS (Claude Code stores credentials in the Keychain). The provider misidentifies the OAuth token and bills it as an API key, so subscribers without API credits hit "Credit balance is too low".
 >
 > If you have a Pro/Max subscription and need programmatic access today: use the direct [`ClaudeProvider`](#claude-anthropic-api) with an API key, or wait for the upstream SDK fix. The `oauthToken` field is wired up and ready for when Anthropic fixes the Keychain handling.
-You can also use response types with streaming. The raw stream provides real-time text, and you can parse the final string once the stream is complete.
+**Mode A — Claude Pro/Max subscription** *(see status note above)*:
 ```typescript
 import { parseAndValidateResponseType } from 'simple-ai-provider';
 const stream = claude.stream({
  messages: [{ role: 'user', content: 'Analyze the Tesla Model 3.' }],
  responseType: productAnalysisType,
  maxTokens: 600
 });
 let fullResponse = '';
 for await (const chunk of stream) {
  if (!chunk.isComplete) {
    process.stdout.write(chunk.content);
    fullResponse += chunk.content;
  } else {
    console.log('\n\nStream complete!');
    // Validate the complete streamed response
    try {
      const analysis = parseAndValidateResponseType(fullResponse, productAnalysisType);
      console.log('Validation successful!');
      console.log(`Product: ${analysis.productName}`);
    } catch (e) {
      console.error('Validation failed:', (e as Error).message);
    }
  }
 }
 ```
 ## 📝 Environment Variables
 Set up your API keys:
 ```bash
-# Required for respective providers
+# One-time: install the CLI, then mint a long-lived OAuth token.
-export ANTHROPIC_API_KEY="your-claude-api-key"
+# `claude login` alone is NOT enough — Anthropic gates SDK use behind setup-token.
-export OPENAI_API_KEY="your-openai-api-key"  
+claude setup-token
 export GOOGLE_AI_API_KEY="your-gemini-api-key"
 # OpenWebUI Bearer Token (get from Settings > Account in OpenWebUI)
 export OPENWEBUI_API_KEY="your-bearer-token"
 ```
 ## 🔧 Provider-Specific Configuration
 ### Claude Configuration
 ```typescript
-const claude = new ClaudeProvider({
+import { ClaudeCodeProvider } from 'simple-ai-provider';
-  apiKey: 'your-api-key',
+
-  defaultModel: 'claude-3-5-sonnet-20241022',
+const claude = new ClaudeCodeProvider({
-  version: '2023-06-01',
+  oauthToken: process.env.CLAUDE_CODE_OAUTH_TOKEN  // from `claude setup-token`
  maxRetries: 3,
  timeout: 30000
 });
 ```
-### OpenAI Configuration
+**Mode B — Console API key** (billed per-token, works reliably):
 ```typescript
 const claude = new ClaudeCodeProvider({
  apiKey: process.env.ANTHROPIC_API_KEY
 });
 ```
 If both are present, `oauthToken` wins. Either field can also be picked up from the environment (`CLAUDE_CODE_OAUTH_TOKEN` / `ANTHROPIC_API_KEY`) without being passed explicitly.
 Optional config:
 ```typescript
 new ClaudeCodeProvider({
  apiKey: '...',
  defaultModel: 'sonnet',  // 'sonnet' | 'opus' | 'haiku' | 'inherit' | full model ID
  maxTurns: 1,             // 1 for plain completion; raise for agent/tool loops
  allowedTools: [],        // tool names to enable (default: none)
  cwd: process.cwd()       // working directory for the agent
 });
 ```
 **Trade-offs even when it works:**
 - Requires `claude` CLI installed on the host. Not ideal for typical server deployments.
 - Higher latency than the direct API (spawns a CLI process per request).
 - Streaming yields text as the SDK emits successive assistant messages, not token-by-token deltas.
 - If you have an API key, [`ClaudeProvider`](#claude-anthropic-api) is the simpler, faster choice.
 ### OpenAI
 ```typescript
 import { OpenAIProvider } from 'simple-ai-provider';
 const openai = new OpenAIProvider({
-  apiKey: 'your-api-key',
+  apiKey: process.env.OPENAI_API_KEY!,
  defaultModel: 'gpt-4o',
-  organization: 'your-org-id',
+  organization: 'org-...',     // optional
-  project: 'your-project-id',
+  project: 'proj-...'          // optional
  maxRetries: 3,
  timeout: 30000
 });
 ```
-### Gemini Configuration
+`baseUrl` is supported for OpenAI-compatible endpoints.
 ### Gemini (Google)
 ```typescript
 import { GeminiProvider } from 'simple-ai-provider';
 const gemini = new GeminiProvider({
-  apiKey: 'your-api-key',
+  apiKey: process.env.GOOGLE_AI_API_KEY!,
-  defaultModel: 'gemini-1.5-flash',
+  defaultModel: 'gemini-2.5-flash',
-  safetySettings: [
+  safetySettings: [/* SafetySetting[] from @google/genai */],
    {
      category: 'HARM_CATEGORY_HARASSMENT',
      threshold: 'BLOCK_MEDIUM_AND_ABOVE'
    }
  ],
  generationConfig: {
    temperature: 0.7,
    topP: 0.8,
@@ -261,441 +137,198 @@ const gemini = new GeminiProvider({
 });
 ```
-### OpenWebUI Configuration
+Backed by `@google/genai` (the successor to the deprecated `@google/generative-ai`).
 ### OpenWebUI (local / self-hosted)
 ```typescript
 import { OpenWebUIProvider } from 'simple-ai-provider';
 const openwebui = new OpenWebUIProvider({
-  apiKey: 'your-bearer-token', // Get from OpenWebUI Settings > Account
+  apiKey: 'your-bearer-token',          // from Settings > Account in OpenWebUI
-  baseUrl: 'http://localhost:3000', // Your OpenWebUI instance
+  baseUrl: 'http://localhost:3000',
-  defaultModel: 'llama3.1',
+  defaultModel: 'llama3.1:latest',
-  useOllamaProxy: false, // Use OpenWebUI's chat API (recommended)
+  useOllamaProxy: false,                // false: OpenWebUI chat API (default)
-  // useOllamaProxy: true, // Use Ollama API proxy for direct model access
+                                        // true:  direct Ollama proxy
-  dangerouslyAllowInsecureConnections: true, // For local HTTPS
+  dangerouslyAllowInsecureConnections: true
  timeout: 60000, // Longer timeout for local inference
  maxRetries: 2
 });
 ```
-## 🌊 Streaming Support
+`useOllamaProxy` flips between two internal strategies — the OpenAI-compatible chat completions endpoint and the direct Ollama generate endpoint.
-All providers support real-time streaming:
+## Streaming
 Identical shape across providers:
 ```typescript
-const stream = provider.stream({
+for await (const chunk of provider.stream({ messages, maxTokens: 200 })) {
  messages: [{ role: 'user', content: 'Count from 1 to 10' }],
  maxTokens: 100
 });
 for await (const chunk of stream) {
  if (!chunk.isComplete) {
    process.stdout.write(chunk.content);
  } else {
-    console.log('\nDone! Usage:', chunk.usage);
+    console.log('\n', chunk.usage);
  }
 }
 ```
-## 🔀 Multi-Provider Usage
+## Structured output
-Use multiple providers seamlessly:
+Ask any provider for a typed JSON response. The library injects a system prompt describing the expected shape and parses the result.
 ```typescript
-const providers = {
+import { createResponseType } from 'simple-ai-provider';
  claude: new ClaudeProvider({ apiKey: process.env.ANTHROPIC_API_KEY! }),
  openai: new OpenAIProvider({ apiKey: process.env.OPENAI_API_KEY! }),
  gemini: new GeminiProvider({ apiKey: process.env.GOOGLE_AI_API_KEY! }),
  openwebui: new OpenWebUIProvider({ 
    apiKey: 'ollama', 
    baseUrl: 'http://localhost:3000'
  })
 };
-// Initialize all providers
+interface UserProfile {
-await Promise.all(Object.values(providers).map(p => p.initialize()));
+  name: string;
-
+  age: number;
-// Use the same interface for all
+  hobbies: string[];
 const prompt = { 
  messages: [{ role: 'user', content: 'Hello!' }],
  maxTokens: 50 
 };
 for (const [name, provider] of Object.entries(providers)) {
  try {
    const response = await provider.complete(prompt);
    console.log(`${name}: ${response.content}`);
  } catch (error) {
    console.log(`${name} failed: ${error.message}`);
  }
 }
 const profileType = createResponseType<UserProfile>(
  'A user profile with name, age, and hobbies',
  { name: 'Alice', age: 30, hobbies: ['climbing', 'photography'] }
 );
 const response = await claude.complete({
  messages: [{ role: 'user', content: 'Generate a fictional user profile.' }],
  responseType: profileType
 });
 // response.content is typed as UserProfile
 // response.rawContent is the original string
 console.log(response.content.name);
 ```
-## 📊 Provider Comparison
+This also works with `stream()` — chunks deliver text, then the final chunk parses.
-| Provider | Context Length | Streaming | Vision | Function Calling | Local Execution | Best For |
+## Factory functions
 |----------|---------------|-----------|--------|------------------|-----------------|----------|
 | **Claude** | 200K tokens | ✅ | ✅ | ✅ | ❌ | Reasoning, Analysis, Code Review |
 | **OpenAI** | 128K tokens | ✅ | ✅ | ✅ | ❌ | General Purpose, Function Calling |
 | **Gemini** | 1M tokens | ✅ | ✅ | ✅ | ❌ | Large Documents, Multimodal |
 | **OpenWebUI** | 32K tokens | ✅ | ❌ | ❌ | ✅ | Privacy, Custom Models, Local |
-### Detailed Capabilities
+If you prefer a single entry point:
 Each provider offers unique capabilities:
 #### Claude (Anthropic)
 - Advanced reasoning and analysis
 - Excellent code review capabilities
 - Strong safety features
 - System message support
 #### OpenAI
 - Broad model selection
 - Function calling support
 - JSON mode for structured outputs
 - Vision capabilities
 #### Gemini (Google)
 - Largest context window (1M tokens)
 - Multimodal capabilities
 - Cost-effective pricing
 - Strong multilingual support
 #### OpenWebUI
 - Complete privacy (local execution)
 - Custom model support
 - No API costs
 - RAG (Retrieval Augmented Generation) support
 ## 🎯 Model Selection
 ### Getting Available Models
 Instead of maintaining a static list, you can programmatically get available models:
 ```typescript
-// Get provider information including available models
+import { createProvider } from 'simple-ai-provider';
 const info = provider.getInfo();
 console.log('Available models:', info.models);
-// Example output:
+const claude    = createProvider('claude',      { apiKey: '…' });
-// Claude: ['claude-3-5-sonnet-20241022', 'claude-3-5-haiku-20241022', ...]
+const openai    = createProvider('openai',      { apiKey: '…' });
-// OpenAI: ['gpt-4o', 'gpt-4o-mini', 'gpt-4-turbo', ...]
+const gemini    = createProvider('gemini',      { apiKey: '…' });
-// Gemini: ['gemini-1.5-flash', 'gemini-1.5-pro', ...]
+const openwebui = createProvider('openwebui',   { apiKey: '…', baseUrl: '…' });
-// OpenWebUI: ['llama3.1:latest', 'mistral:latest', ...]
+const claudeCode = createProvider('claude-code', {});
 ```
-### Model Selection Guidelines
+Per-provider shortcut factories also exist: `createClaudeProvider`, `createOpenAIProvider`, `createGeminiProvider`, `createOpenWebUIProvider`, `createClaudeCodeProvider`.
-**For Claude (Anthropic):**
+## Error handling
 - Check [Anthropic's model documentation](https://docs.anthropic.com/claude/docs/models-overview) for latest models
-**For OpenAI:**
+Every error thrown by the library is an `AIProviderError` with a typed `.type` and optional `.statusCode`:
 - Check [OpenAI's model documentation](https://platform.openai.com/docs/models) for latest models
 **For Gemini (Google):**
 - Check [Google AI's model documentation](https://ai.google.dev/docs/models) for latest models
 **For OpenWebUI:**
 - Models depend on your local installation
 - Check your OpenWebUI instance for available models
 ## 🚨 Error Handling
 The package provides comprehensive, standardized error handling with detailed error types:
 ```typescript
 import { AIProviderError, AIErrorType } from 'simple-ai-provider';
 try {
-  const response = await provider.complete({ 
+  await provider.complete({ messages: [...] });
    messages: [{ role: 'user', content: 'Hello' }] 
  });
 } catch (error) {
  if (error instanceof AIProviderError) {
    switch (error.type) {
-      case AIErrorType.AUTHENTICATION:
+      case AIErrorType.AUTHENTICATION:   /* bad API key, expired token */ break;
-        console.log('Invalid API key or authentication failed');
+      case AIErrorType.RATE_LIMIT:       /* slow down */ break;
-        break;
+      case AIErrorType.MODEL_NOT_FOUND:  /* wrong model name */ break;
-      case AIErrorType.RATE_LIMIT:
+      case AIErrorType.INVALID_REQUEST:  /* bad input */ break;
-        console.log('Rate limited, try again later');
+      case AIErrorType.NETWORK:          /* transient connectivity */ break;
-        break;
+      case AIErrorType.TIMEOUT:          /* slow request */ break;
-      case AIErrorType.MODEL_NOT_FOUND:
+      case AIErrorType.UNKNOWN:          /* fall back */ break;
        console.log('Model not available or not found');
        break;
      case AIErrorType.INVALID_REQUEST:
        console.log('Invalid request parameters');
        break;
      case AIErrorType.NETWORK:
        console.log('Network/connection issue');
        break;
      case AIErrorType.TIMEOUT:
        console.log('Request timed out');
        break;
      case AIErrorType.UNKNOWN:
        console.log('Unknown error:', error.message);
        break;
      default:
        console.log('Error:', error.message);
    }
-    
+    console.error(error.statusCode, error.originalError);
    // Access additional error details
    console.log('Status Code:', error.statusCode);
    console.log('Original Error:', error.originalError);
  }
 }
 ```
-### Error Types
+## Configuration reference
- **AUTHENTICATION**: Invalid API keys or authentication failures
+All providers share these base options:
 - **RATE_LIMIT**: API rate limits exceeded
 - **INVALID_REQUEST**: Malformed requests or invalid parameters
 - **MODEL_NOT_FOUND**: Requested model is not available
 - **NETWORK**: Connection issues or server errors
 - **TIMEOUT**: Request timeout exceeded
 - **UNKNOWN**: Unclassified errors
-## 🔧 Advanced Usage
+| Option       | Type     | Default   | Notes                                  |
 |--------------|----------|-----------|----------------------------------------|
 | `apiKey`     | `string` | required¹ | ¹ Optional for `ClaudeCodeProvider`    |
 | `baseUrl`    | `string` | provider default | Custom or self-hosted endpoint  |
 | `timeout`    | `number` | `30000`   | Request timeout in ms                  |
 | `maxRetries` | `number` | `3`       | SDK-level retry attempts               |
-### Custom Base URLs
+Each provider adds its own config (see the sections above).
-```typescript
+## TypeScript
 // OpenAI-compatible endpoint
 const customOpenAI = new OpenAIProvider({
  apiKey: 'your-key',
  baseUrl: 'https://api.custom-provider.com/v1'
 });
-// Custom OpenWebUI instance
+Full type definitions ship with the package. The main types you'll use:
 const remoteOpenWebUI = new OpenWebUIProvider({
  apiKey: 'your-key',
  baseUrl: 'https://my-openwebui.example.com',
  apiPath: '/api/v1'
 });
 ```
 ### Provider Information
 ```typescript
 const info = provider.getInfo();
 console.log(`Provider: ${info.name} v${info.version}`);
 console.log(`Models: ${info.models.join(', ')}`);
 console.log(`Max Context: ${info.maxContextLength} tokens`);
 console.log(`Supports Streaming: ${info.supportsStreaming}`);
 console.log('Capabilities:', info.capabilities);
 ```
 ### OpenWebUI-Specific Features
 OpenWebUI offers unique advantages for local AI deployment:
 ```typescript
 const openwebui = new OpenWebUIProvider({
  apiKey: 'your-bearer-token', // Get from OpenWebUI Settings > Account
  baseUrl: 'http://localhost:3000',
  defaultModel: 'llama3.1',
  useOllamaProxy: false, // Use chat completions API (recommended)
  // Longer timeout for local inference
  timeout: 120000,
  // Allow self-signed certificates for local development
  dangerouslyAllowInsecureConnections: true
 });
 // Test connection and list available models
 try {
  await openwebui.initialize();
  console.log('Connected to local OpenWebUI instance');
  // Use either chat completions or Ollama proxy
  const response = await openwebui.complete({
    messages: [{ role: 'user', content: 'Hello!' }],
    maxTokens: 100
  });
 } catch (error) {
  console.log('OpenWebUI not available:', error.message);
  // Gracefully fallback to cloud providers
 }
 ```
 **OpenWebUI API Modes:**
 - **Chat Completions** (`useOllamaProxy: false`): OpenWebUI's native API with full features
 - **Ollama Proxy** (`useOllamaProxy: true`): Direct access to Ollama API for raw model interaction
 ## 📦 TypeScript Support
 Full TypeScript support with comprehensive type definitions:
 ```typescript
 import type {
  AIMessage,
  CompletionParams,
  CompletionResponse,
  CompletionChunk,
  TokenUsage,
  ProviderInfo,
  ResponseType,
  // Per-provider config interfaces
  ClaudeConfig,
  ClaudeCodeConfig,
  OpenAIConfig,
  GeminiConfig,
-  OpenWebUIConfig,
+  OpenWebUIConfig
  AIMessage,
  ResponseType,
  TokenUsage
 } from 'simple-ai-provider';
 // Type-safe configuration
 const config: ClaudeConfig = {
  apiKey: 'your-key',
  defaultModel: 'claude-3-5-sonnet-20241022',
  // TypeScript will validate all options
 };
 // Type-safe responses
 const response: CompletionResponse = await provider.complete(params);
 // Type-safe messages with metadata
 const messages: AIMessage[] = [
  { 
    role: 'user', 
    content: 'Hello',
    metadata: { timestamp: Date.now() }
  }
 ];
 // Type-safe response types
 interface UserProfile {
  name: string;
  age: number;
 }
 const responseType: ResponseType<UserProfile> = createResponseType(
  'A user profile with name and age',
  { name: 'John', age: 30 }
 );
 ```
-### Advanced Type Features
+`CompletionResponse<T>` is generic — when you pass `responseType`, `content` is `T` (and the original string is preserved on `rawContent`).
- **Generic Response Types**: Type-safe structured outputs
+## Provider metadata
 - **Message Metadata**: Support for custom message properties
 - **Provider-Specific Configs**: Type-safe configuration for each provider
 - **Error Types**: Comprehensive error type definitions
 - **Factory Functions**: Type-safe provider creation
-## 🧪 Testing
+Every provider exposes `getInfo()`:
-The package includes comprehensive tests using Bun test framework:
+```typescript
-
+const info = provider.getInfo();
-```bash
+//   { name, version, models, maxContextLength, supportsStreaming, capabilities }
 # Run all tests
 bun test
 # Run tests for specific provider
 bun test tests/claude.test.ts
 bun test tests/openai.test.ts
 bun test tests/gemini.test.ts
 bun test tests/openwebui.test.ts
 # Run tests with coverage
 bun test --coverage
 ```
-### Test Coverage
+Model lists in `info.models` are example values — refer to each vendor's docs for the current authoritative list. The library accepts any model string the underlying SDK supports.
- ✅ Provider initialization and configuration
+## Architecture (brief)
 - ✅ Message validation and conversion
 - ✅ Error handling and normalization
 - ✅ Response formatting
 - ✅ Streaming functionality
 - ✅ Structured response types
 - ✅ Factory functions
 - ✅ Provider registry
-## 🛠️ Development
+The library uses a template-method base class (`BaseAIProvider`) that owns the public lifecycle (`initialize`, `complete`, `stream`), input validation, response-type parsing, and error normalization. Each provider supplies:
-### Prerequisites
+- `doInitialize()` / `doComplete()` / `doStream()` — the actual SDK calls
 - `getModelNamePatterns()` — regexes for naming-convention warnings
 - `sendValidationProbe()` — minimal request used during `initialize()`
 - `mapProviderError()` / `providerErrorMessages()` — provider-specific error translation
- Node.js 18.0.0 or higher
+`OpenWebUIProvider` additionally uses an internal strategy split (`OpenWebUIChatStrategy` vs `OpenWebUIOllamaStrategy`) selected by `useOllamaProxy`.
 - Bun (recommended) or npm/yarn
 - TypeScript 5.0 or higher
-### Setup
+## Development
 ```bash
 # Clone the repository
 git clone https://gitea.jleibl.net/jleibl/simple-ai-provider.git
 cd simple-ai-provider
 # Install dependencies
 bun install
 # Build the project
 bun run build
 ```
-# Run tests
+Examples live in `examples/`:
 bun test
-# Run examples
+```bash
 bun run examples/basic-usage.ts
 bun run examples/structured-response-types.ts
 bun run examples/multi-provider.ts
 bun run examples/structured-response-types.ts
 ```
-### Project Structure
+Tests in `tests/` use Bun's test runner (`bun test`). Note: post-refactor some tests need updating before they pass cleanly.
-```text
+## License
 src/
 ├── index.ts              # Main entry point
 ├── types/
 │   └── index.ts          # Type definitions and utilities
 ├── providers/
 │   ├── base.ts           # Abstract base provider
 │   ├── claude.ts         # Claude provider implementation
 │   ├── openai.ts         # OpenAI provider implementation
 │   ├── gemini.ts         # Gemini provider implementation
 │   ├── openwebui.ts      # OpenWebUI provider implementation
 │   └── index.ts          # Provider exports
 └── utils/
    └── factory.ts        # Factory functions and registry
-examples/
+MIT — see [LICENSE](LICENSE).
 ├── basic-usage.ts        # Basic usage examples
 ├── structured-response-types.ts  # Structured output examples
 └── multi-provider.ts     # Multi-provider examples
-tests/
+## Links
 ├── claude.test.ts        # Claude provider tests
 ├── openai.test.ts        # OpenAI provider tests
 ├── gemini.test.ts        # Gemini provider tests
 └── openwebui.test.ts     # OpenWebUI provider tests
 ```
 ## 🤝 Contributing
 Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
 ### Development Guidelines
 1. **Code Style**: Follow the existing TypeScript patterns
 2. **Testing**: Add tests for new features
 3. **Documentation**: Update README for new features
 4. **Type Safety**: Maintain comprehensive type definitions
 5. **Error Handling**: Use standardized error types
 ## 📄 License
 MIT License - see the [LICENSE](LICENSE) file for details.
 ## 🔗 Links
 - [Anthropic Claude API](https://docs.anthropic.com/claude/reference/)
 - [Claude Code SDK](https://docs.anthropic.com/claude/docs/claude-code-sdk)
 - [OpenAI API](https://platform.openai.com/docs/)
- [Google Gemini API](https://ai.google.dev/)
+- [Google Gen AI SDK](https://ai.google.dev/)
 - [OpenWebUI](https://openwebui.com/)
- [Gitea Repository](https://gitea.jleibl.net/jleibl/simple-ai-provider)
+- [Repository](https://gitea.jleibl.net/jleibl/simple-ai-provider)
 ---
 ⭐ **Star this repo if you find it helpful!**
--- a/bun.lock
+++ b/bun.lock
@@ -4,6 +4,7 @@
    "": {
      "name": "simple-ai-provider",
      "dependencies": {
        "@anthropic-ai/claude-agent-sdk": "^0.3.146",
        "@anthropic-ai/sdk": "^0.97.0",
        "@google/genai": "^2.5.0",
        "openai": "^6.0.0",
@@ -19,12 +20,34 @@
    },
  },
  "packages": {
    "@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/claude-agent-sdk@0.3.146", "", { "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.3.146", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.3.146", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.3.146", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.3.146", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.3.146", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.3.146", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.3.146", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.3.146" }, "peerDependencies": { "@anthropic-ai/sdk": ">=0.93.0", "@modelcontextprotocol/sdk": "^1.29.0", "zod": "^4.0.0" } }, "sha512-hK9/Ng+hOyexUemTxdIUsSWJ9o2LFi2YNWzHwz8/YMCohUYOnFMZkBiENvUAb0WIc5hieOyBZrOIlg5OewuJMg=="],
    "@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/claude-agent-sdk-darwin-arm64@0.3.146", "", { "os": "darwin", "cpu": "arm64" }, "sha512-0IIvlEaenq2CRSVx5Bo5BaCtHQXS87GancM35WKEYveGVLn6DI+5G7ikYuTE4AKRPkMnogFtY4BJt6LulWGj+A=="],
    "@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/claude-agent-sdk-darwin-x64@0.3.146", "", { "os": "darwin", "cpu": "x64" }, "sha512-Dk5xJ03Ff1JXbMRP1t2wc/TyfY6xF/2Ysp31wMhFPjoNiKSPHMWaIg242+T3CHdxLWmJ8plWHL1HL5cyZ/LCkw=="],
    "@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/claude-agent-sdk-linux-arm64@0.3.146", "", { "os": "linux", "cpu": "arm64" }, "sha512-mzBXDDWWBAC/vDtAYpO1G/dq5QvJtYSPXsqcb+sNdcDhiuf4IYnYp7ytRncYlsUNDkLmX6Gk2jkWAHUUA2Lozg=="],
    "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/claude-agent-sdk-linux-arm64-musl@0.3.146", "", { "os": "linux", "cpu": "arm64" }, "sha512-QlCid0ucdrmhUAOewfQjaofN2wlokWcfFTxSFePTSj1umk35JO7TDFP700F7jU49r1fPWIdvJpPwWGyB0DeFPA=="],
    "@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/claude-agent-sdk-linux-x64@0.3.146", "", { "os": "linux", "cpu": "x64" }, "sha512-B2baXU1tCBT5CVlD7jJMKjpC4xdO45NUIWpqImmwuOfKvlM/PITjyTXyTY662mGZf1dBmdqBBsqirwFH/jhi8Q=="],
    "@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/claude-agent-sdk-linux-x64-musl@0.3.146", "", { "os": "linux", "cpu": "x64" }, "sha512-E3coK1ThQT08KIX80RLcsq7DWXFllCKOzoOe32it/bdtY56TBgPY9xemwXhIJ+cVBHTI9/MpBSIlKBcFCt+yQA=="],
    "@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/claude-agent-sdk-win32-arm64@0.3.146", "", { "os": "win32", "cpu": "arm64" }, "sha512-CIwQxGX2r/yWpjCJ6ahB3smKXhghWgGTxL98+LGW52TUwqTiBnlNrH9DPqqgv1/+Hyquw6xfLrKU+StyfMgiLw=="],
    "@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/claude-agent-sdk-win32-x64@0.3.146", "", { "os": "win32", "cpu": "x64" }, "sha512-qmxrsyaqA8s4HShqJls7ZCRjdoqN66Jo/hbjQNB3uHepD8tEO1iD19aPV4+osdLT7feMkhDBfLT07Q30R2NB5w=="],
    "@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.97.1", "", { "dependencies": { "json-schema-to-ts": "^3.1.1", "standardwebhooks": "^1.0.0" }, "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["zod"], "bin": { "anthropic-ai-sdk": "bin/cli" } }, "sha512-wOf7AUeJPitcVpvKO4UMu63mWH5SaVipkGd7OOQJt/G6VYGlV8D2Gp9dLxOrttDJh/9gqPqdaBwDGcBevumeAg=="],
    "@babel/runtime": ["@babel/runtime@7.29.2", "", {}, "sha512-JiDShH45zKHWyGe4ZNVRrCjBz8Nh9TMmZG1kh4QTK8hCBTWBi8Da+i7s1fJw7/lYpM4ccepSNfqzZ/QvABBi5g=="],
    "@google/genai": ["@google/genai@2.5.0", "", { "dependencies": { "google-auth-library": "^10.3.0", "p-retry": "^4.6.2", "protobufjs": "^7.5.4", "ws": "^8.18.0" }, "peerDependencies": { "@modelcontextprotocol/sdk": "^1.25.2" }, "optionalPeers": ["@modelcontextprotocol/sdk"] }, "sha512-qDi3LLh9I3llJK0f9uV8kZ8EdT9oHPxGJJ9yOJ/i5YXYrVwRCs8jHo9x4e99uOeKYDvD3TZwT70p/H/LS3BixQ=="],
    "@hono/node-server": ["@hono/node-server@1.19.14", "", { "peerDependencies": { "hono": "^4" } }, "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw=="],
    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.29.0", "", { "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.2.1", "express-rate-limit": "^8.2.1", "hono": "^4.11.4", "jose": "^6.1.3", "json-schema-typed": "^8.0.2", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.25 || ^4.0", "zod-to-json-schema": "^3.25.1" }, "peerDependencies": { "@cfworker/json-schema": "^4.1.1" }, "optionalPeers": ["@cfworker/json-schema"] }, "sha512-zo37mZA9hJWpULgkRpowewez1y6ML5GsXJPY8FI0tBBCd77HEvza4jDqRKOXgHNn867PVGCyTdzqpz0izu5ZjQ=="],
    "@protobufjs/aspromise": ["@protobufjs/aspromise@1.1.2", "", {}, "sha512-j+gKExEuLmKwvz3OgROXtrJ2UG2x8Ch2YZUxahh+s1F2HZ+wAceUNLkvy6zKCPVRkU++ZWQrdxsUeQXmcg4uoQ=="],
    "@protobufjs/base64": ["@protobufjs/base64@1.1.2", "", {}, "sha512-AZkcAA5vnN/v4PDqKyMR5lx7hZttPDgClv83E//FMNhR2TMcLUhfRUBHCmSl0oi9zMgDDqRUJkSxO3wm85+XLg=="],
@@ -53,80 +76,256 @@
    "@types/retry": ["@types/retry@0.12.0", "", {}, "sha512-wWKOClTTiizcZhXnPY4wikVAwmdYHp8q6DmC+EJUzAMsycb7HB32Kh9RN4+0gExjmPmZSAQjgURXIGATPegAvA=="],
    "accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],
    "agent-base": ["agent-base@7.1.4", "", {}, "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ=="],
    "ajv": ["ajv@8.20.0", "", { "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", "json-schema-traverse": "^1.0.0", "require-from-string": "^2.0.2" } }, "sha512-Thbli+OlOj+iMPYFBVBfJ3OmCAnaSyNn4M1vz9T6Gka5Jt9ba/HIR56joy65tY6kx/FCF5VXNB819Y7/GUrBGA=="],
    "ajv-formats": ["ajv-formats@3.0.1", "", { "dependencies": { "ajv": "^8.0.0" } }, "sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ=="],
    "base64-js": ["base64-js@1.5.1", "", {}, "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA=="],
    "bignumber.js": ["bignumber.js@9.3.1", "", {}, "sha512-Ko0uX15oIUS7wJ3Rb30Fs6SkVbLmPBAKdlm7q9+ak9bbIeFf0MwuBsQV6z7+X768/cHsfg+WlysDWJcmthjsjQ=="],
    "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="],
    "buffer-equal-constant-time": ["buffer-equal-constant-time@1.0.1", "", {}, "sha512-zRpUiDwd/xk6ADqPMATG8vc9VPrkck7T07OIx0gnjmJAnHnTVXNQG3vfvWNuiZIkwu9KrKdA1iJKfsfTVxE6NA=="],
    "bun-types": ["bun-types@1.3.14", "", { "dependencies": { "@types/node": "*" } }, "sha512-4N0ig0fEomHt5R0KCFWjovxow98rIoRwKolrYdCcknNwMekCXRnWEUvgu5soYV8QXtVsrUD8B95MBOZGPvr6KQ=="],
    "bytes": ["bytes@3.1.2", "", {}, "sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg=="],
    "call-bind-apply-helpers": ["call-bind-apply-helpers@1.0.2", "", { "dependencies": { "es-errors": "^1.3.0", "function-bind": "^1.1.2" } }, "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ=="],
    "call-bound": ["call-bound@1.0.4", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "get-intrinsic": "^1.3.0" } }, "sha512-+ys997U96po4Kx/ABpBCqhA9EuxJaQWDQg7295H4hBphv3IZg0boBKuwYpt4YXp6MZ5AmZQnU/tyMTlRpaSejg=="],
    "content-disposition": ["content-disposition@1.1.0", "", {}, "sha512-5jRCH9Z/+DRP7rkvY83B+yGIGX96OYdJmzngqnw2SBSxqCFPd0w2km3s5iawpGX8krnwSGmF0FW5Nhr0Hfai3g=="],
    "content-type": ["content-type@1.0.5", "", {}, "sha512-nTjqfcBFEipKdXCv4YDQWCfmcLZKm81ldF0pAopTvyrFGVbcR6P/VAAd5G7N+0tTr8QqiU0tFadD6FK4NtJwOA=="],
    "cookie": ["cookie@0.7.2", "", {}, "sha512-yki5XnKuf750l50uGTllt6kKILY4nQ1eNIQatoXEByZ5dWgnKqbnqmTrBE5B4N7lrMJKQ2ytWMiTO2o0v6Ew/w=="],
    "cookie-signature": ["cookie-signature@1.2.2", "", {}, "sha512-D76uU73ulSXrD1UXF4KE2TMxVVwhsnCgfAyTg9k8P6KGZjlXKrOLe4dJQKI3Bxi5wjesZoFXJWElNWBjPZMbhg=="],
    "cors": ["cors@2.8.6", "", { "dependencies": { "object-assign": "^4", "vary": "^1" } }, "sha512-tJtZBBHA6vjIAaF6EnIaq6laBBP9aq/Y3ouVJjEfoHbRBcHBAHYcMh/w8LDrk2PvIMMq8gmopa5D4V8RmbrxGw=="],
    "cross-spawn": ["cross-spawn@7.0.6", "", { "dependencies": { "path-key": "^3.1.0", "shebang-command": "^2.0.0", "which": "^2.0.1" } }, "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA=="],
    "data-uri-to-buffer": ["data-uri-to-buffer@4.0.1", "", {}, "sha512-0R9ikRb668HB7QDxT1vkpuUBtqc53YyAwMwGeUFKRojY/NWKvdZ+9UYtRfGmhqNbRkTSVpMbmyhXipFFv2cb/A=="],
    "debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
    "depd": ["depd@2.0.0", "", {}, "sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw=="],
    "dunder-proto": ["dunder-proto@1.0.1", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.1", "es-errors": "^1.3.0", "gopd": "^1.2.0" } }, "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A=="],
    "ecdsa-sig-formatter": ["ecdsa-sig-formatter@1.0.11", "", { "dependencies": { "safe-buffer": "^5.0.1" } }, "sha512-nagl3RYrbNv6kQkeJIpt6NJZy8twLB/2vtz6yN9Z4vRKHN4/QZJIEbqohALSgwKdnksuY3k5Addp5lg8sVoVcQ=="],
    "ee-first": ["ee-first@1.1.1", "", {}, "sha512-WMwm9LhRUo+WUaRN+vRuETqG89IgZphVSNkdFgeb6sS/E4OrDIN7t48CAewSHXc6C8lefD8KKfr5vY61brQlow=="],
    "encodeurl": ["encodeurl@2.0.0", "", {}, "sha512-Q0n9HRi4m6JuGIV1eFlmvJB7ZEVxu93IrMyiMsGC0lrMJMWzRgx6WGquyfQgZVb31vhGgXnfmPNNXmxnOkRBrg=="],
    "es-define-property": ["es-define-property@1.0.1", "", {}, "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g=="],
    "es-errors": ["es-errors@1.3.0", "", {}, "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw=="],
    "es-object-atoms": ["es-object-atoms@1.1.1", "", { "dependencies": { "es-errors": "^1.3.0" } }, "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA=="],
    "escape-html": ["escape-html@1.0.3", "", {}, "sha512-NiSupZ4OeuGwr68lGIeym/ksIZMJodUGOSCZ/FSnTxcrekbvqrgdUxlJOMpijaKZVjAJrWrGs/6Jy8OMuyj9ow=="],
    "etag": ["etag@1.8.1", "", {}, "sha512-aIL5Fx7mawVa300al2BnEE4iNvo1qETxLrPI/o05L7z6go7fCw1J6EQmbK4FmJ2AS7kgVF/KEZWufBfdClMcPg=="],
    "eventsource": ["eventsource@3.0.7", "", { "dependencies": { "eventsource-parser": "^3.0.1" } }, "sha512-CRT1WTyuQoD771GW56XEZFQ/ZoSfWid1alKGDYMmkt2yl8UXrVR4pspqWNEcqKvVIzg6PAltWjxcSSPrboA4iA=="],
    "eventsource-parser": ["eventsource-parser@3.0.8", "", {}, "sha512-70QWGkr4snxr0OXLRWsFLeRBIRPuQOvt4s8QYjmUlmlkyTZkRqS7EDVRZtzU3TiyDbXSzaOeF0XUKy8PchzukQ=="],
    "express": ["express@5.2.1", "", { "dependencies": { "accepts": "^2.0.0", "body-parser": "^2.2.1", "content-disposition": "^1.0.0", "content-type": "^1.0.5", "cookie": "^0.7.1", "cookie-signature": "^1.2.1", "debug": "^4.4.0", "depd": "^2.0.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "etag": "^1.8.1", "finalhandler": "^2.1.0", "fresh": "^2.0.0", "http-errors": "^2.0.0", "merge-descriptors": "^2.0.0", "mime-types": "^3.0.0", "on-finished": "^2.4.1", "once": "^1.4.0", "parseurl": "^1.3.3", "proxy-addr": "^2.0.7", "qs": "^6.14.0", "range-parser": "^1.2.1", "router": "^2.2.0", "send": "^1.1.0", "serve-static": "^2.2.0", "statuses": "^2.0.1", "type-is": "^2.0.1", "vary": "^1.1.2" } }, "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw=="],
    "express-rate-limit": ["express-rate-limit@8.5.2", "", { "dependencies": { "ip-address": "^10.2.0" }, "peerDependencies": { "express": ">= 4.11" } }, "sha512-5Kb34ipNX694DH48vN9irak1Qx30nb0PLYHXfJgw4YEjiC3ZEmZJhwOp+VfiCYwFzvFTdB9QkArYS5kXa2cx2A=="],
    "extend": ["extend@3.0.2", "", {}, "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g=="],
    "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],
    "fast-sha256": ["fast-sha256@1.3.0", "", {}, "sha512-n11RGP/lrWEFI/bWdygLxhI+pVeo1ZYIVwvvPkW7azl/rOy+F3HYRZ2K5zeE9mmkhQppyv9sQFx0JM9UabnpPQ=="],
    "fast-uri": ["fast-uri@3.1.2", "", {}, "sha512-rVjf7ArG3LTk+FS6Yw81V1DLuZl1bRbNrev6Tmd/9RaroeeRRJhAt7jg/6YFxbvAQXUCavSoZhPPj6oOx+5KjQ=="],
    "fetch-blob": ["fetch-blob@3.2.0", "", { "dependencies": { "node-domexception": "^1.0.0", "web-streams-polyfill": "^3.0.3" } }, "sha512-7yAQpD2UMJzLi1Dqv7qFYnPbaPx7ZfFK6PiIxQ4PfkGPyNyl2Ugx+a/umUonmKqjhM4DnfbMvdX6otXq83soQQ=="],
    "finalhandler": ["finalhandler@2.1.1", "", { "dependencies": { "debug": "^4.4.0", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "on-finished": "^2.4.1", "parseurl": "^1.3.3", "statuses": "^2.0.1" } }, "sha512-S8KoZgRZN+a5rNwqTxlZZePjT/4cnm0ROV70LedRHZ0p8u9fRID0hJUZQpkKLzro8LfmC8sx23bY6tVNxv8pQA=="],
    "formdata-polyfill": ["formdata-polyfill@4.0.10", "", { "dependencies": { "fetch-blob": "^3.1.2" } }, "sha512-buewHzMvYL29jdeQTVILecSaZKnt/RJWjoZCF5OW60Z67/GmSLBkOFM7qh1PI3zFNtJbaZL5eQu1vLfazOwj4g=="],
    "forwarded": ["forwarded@0.2.0", "", {}, "sha512-buRG0fpBtRHSTCOASe6hD258tEubFoRLb4ZNA6NxMVHNw2gOcwHo9wyablzMzOA5z9xA9L1KNjk/Nt6MT9aYow=="],
    "fresh": ["fresh@2.0.0", "", {}, "sha512-Rx/WycZ60HOaqLKAi6cHRKKI7zxWbJ31MhntmtwMoaTeF7XFH9hhBp8vITaMidfljRQ6eYWCKkaTK+ykVJHP2A=="],
    "function-bind": ["function-bind@1.1.2", "", {}, "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA=="],
    "gaxios": ["gaxios@7.1.4", "", { "dependencies": { "extend": "^3.0.2", "https-proxy-agent": "^7.0.1", "node-fetch": "^3.3.2" } }, "sha512-bTIgTsM2bWn3XklZISBTQX7ZSddGW+IO3bMdGaemHZ3tbqExMENHLx6kKZ/KlejgrMtj8q7wBItt51yegqalrA=="],
    "gcp-metadata": ["gcp-metadata@8.1.2", "", { "dependencies": { "gaxios": "^7.0.0", "google-logging-utils": "^1.0.0", "json-bigint": "^1.0.0" } }, "sha512-zV/5HKTfCeKWnxG0Dmrw51hEWFGfcF2xiXqcA3+J90WDuP0SvoiSO5ORvcBsifmx/FoIjgQN3oNOGaQ5PhLFkg=="],
    "get-intrinsic": ["get-intrinsic@1.3.0", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "es-define-property": "^1.0.1", "es-errors": "^1.3.0", "es-object-atoms": "^1.1.1", "function-bind": "^1.1.2", "get-proto": "^1.0.1", "gopd": "^1.2.0", "has-symbols": "^1.1.0", "hasown": "^2.0.2", "math-intrinsics": "^1.1.0" } }, "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ=="],
    "get-proto": ["get-proto@1.0.1", "", { "dependencies": { "dunder-proto": "^1.0.1", "es-object-atoms": "^1.0.0" } }, "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g=="],
    "google-auth-library": ["google-auth-library@10.6.2", "", { "dependencies": { "base64-js": "^1.3.0", "ecdsa-sig-formatter": "^1.0.11", "gaxios": "^7.1.4", "gcp-metadata": "8.1.2", "google-logging-utils": "1.1.3", "jws": "^4.0.0" } }, "sha512-e27Z6EThmVNNvtYASwQxose/G57rkRuaRbQyxM2bvYLLX/GqWZ5chWq2EBoUchJbCc57eC9ArzO5wMsEmWftCw=="],
    "google-logging-utils": ["google-logging-utils@1.1.3", "", {}, "sha512-eAmLkjDjAFCVXg7A1unxHsLf961m6y17QFqXqAXGj/gVkKFrEICfStRfwUlGNfeCEjNRa32JEWOUTlYXPyyKvA=="],
    "gopd": ["gopd@1.2.0", "", {}, "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg=="],
    "has-symbols": ["has-symbols@1.1.0", "", {}, "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ=="],
    "hasown": ["hasown@2.0.3", "", { "dependencies": { "function-bind": "^1.1.2" } }, "sha512-ej4AhfhfL2Q2zpMmLo7U1Uv9+PyhIZpgQLGT1F9miIGmiCJIoCgSmczFdrc97mWT4kVY72KA+WnnhJ5pghSvSg=="],
    "hono": ["hono@4.12.21", "", {}, "sha512-uV63apnb0kyPtAUwoWgaGh9HyIFcv8lgmzPZSiTBQAFOFGIzka5EZ1dZocmGnn0XdX0+XTqJ6Tqv7selMuGLRQ=="],
    "http-errors": ["http-errors@2.0.1", "", { "dependencies": { "depd": "~2.0.0", "inherits": "~2.0.4", "setprototypeof": "~1.2.0", "statuses": "~2.0.2", "toidentifier": "~1.0.1" } }, "sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ=="],
    "https-proxy-agent": ["https-proxy-agent@7.0.6", "", { "dependencies": { "agent-base": "^7.1.2", "debug": "4" } }, "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw=="],
    "iconv-lite": ["iconv-lite@0.7.2", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-im9DjEDQ55s9fL4EYzOAv0yMqmMBSZp6G0VvFyTMPKWxiSBHUj9NW/qqLmXUwXrrM7AvqSlTCfvqRb0cM8yYqw=="],
    "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
    "ip-address": ["ip-address@10.2.0", "", {}, "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA=="],
    "ipaddr.js": ["ipaddr.js@1.9.1", "", {}, "sha512-0KI/607xoxSToH7GjN1FfSbLoU0+btTicjsQSWQlh/hZykN8KpmMf7uYwPW3R+akZ6R/w18ZlXSHBYXiYUPO3g=="],
    "is-promise": ["is-promise@4.0.0", "", {}, "sha512-hvpoI6korhJMnej285dSg6nu1+e6uxs7zG3BYAm5byqDsgJNWwxzM6z6iZiAgQR4TJ30JmBTOwqZUw3WlyH3AQ=="],
    "isexe": ["isexe@2.0.0", "", {}, "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="],
    "jose": ["jose@6.2.3", "", {}, "sha512-YYVDInQKFJfR/xa3ojUTl8c2KoTwiL1R5Wg9YCydwH0x0B9grbzlg5HC7mMjCtUJjbQ/YnGEZIhI5tCgfTb4Hw=="],
    "json-bigint": ["json-bigint@1.0.0", "", { "dependencies": { "bignumber.js": "^9.0.0" } }, "sha512-SiPv/8VpZuWbvLSMtTDU8hEfrZWg/mH/nV/b4o0CYbSxu1UIQPLdwKOCIyLQX+VIPO5vrLX3i8qtqFyhdPSUSQ=="],
    "json-schema-to-ts": ["json-schema-to-ts@3.1.1", "", { "dependencies": { "@babel/runtime": "^7.18.3", "ts-algebra": "^2.0.0" } }, "sha512-+DWg8jCJG2TEnpy7kOm/7/AxaYoaRbjVB4LFZLySZlWn8exGs3A4OLJR966cVvU26N7X9TWxl+Jsw7dzAqKT6g=="],
    "json-schema-traverse": ["json-schema-traverse@1.0.0", "", {}, "sha512-NM8/P9n3XjXhIZn1lLhkFaACTOURQXjWhV4BA/RnOv8xvgqtqpAX9IO4mRQxSx1Rlo4tqzeqb0sOlruaOy3dug=="],
    "json-schema-typed": ["json-schema-typed@8.0.2", "", {}, "sha512-fQhoXdcvc3V28x7C7BMs4P5+kNlgUURe2jmUT1T//oBRMDrqy1QPelJimwZGo7Hg9VPV3EQV5Bnq4hbFy2vetA=="],
    "jwa": ["jwa@2.0.1", "", { "dependencies": { "buffer-equal-constant-time": "^1.0.1", "ecdsa-sig-formatter": "1.0.11", "safe-buffer": "^5.0.1" } }, "sha512-hRF04fqJIP8Abbkq5NKGN0Bbr3JxlQ+qhZufXVr0DvujKy93ZCbXZMHDL4EOtodSbCWxOqR8MS1tXA5hwqCXDg=="],
    "jws": ["jws@4.0.1", "", { "dependencies": { "jwa": "^2.0.1", "safe-buffer": "^5.0.1" } }, "sha512-EKI/M/yqPncGUUh44xz0PxSidXFr/+r0pA70+gIYhjv+et7yxM+s29Y+VGDkovRofQem0fs7Uvf4+YmAdyRduA=="],
    "long": ["long@5.3.2", "", {}, "sha512-mNAgZ1GmyNhD7AuqnTG3/VQ26o760+ZYBPKjPvugO8+nLbYfX6TVpJPseBvopbdY+qpZ/lKUnmEc1LeZYS3QAA=="],
    "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],
    "media-typer": ["media-typer@1.1.0", "", {}, "sha512-aisnrDP4GNe06UcKFnV5bfMNPBUw4jsLGaWwWfnH3v02GnBuXX2MCVn5RbrWo0j3pczUilYblq7fQ7Nw2t5XKw=="],
    "merge-descriptors": ["merge-descriptors@2.0.0", "", {}, "sha512-Snk314V5ayFLhp3fkUREub6WtjBfPdCPY1Ln8/8munuLuiYhsABgBVWsozAG+MWMbVEvcdcpbi9R7ww22l9Q3g=="],
    "mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
    "mime-types": ["mime-types@3.0.2", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A=="],
    "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
    "negotiator": ["negotiator@1.0.0", "", {}, "sha512-8Ofs/AUQh8MaEcrlq5xOX0CQ9ypTF5dl78mjlMNfOK08fzpgTHQRQPBxcPlEtIw0yRpws+Zo/3r+5WRby7u3Gg=="],
    "node-domexception": ["node-domexception@1.0.0", "", {}, "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ=="],
    "node-fetch": ["node-fetch@3.3.2", "", { "dependencies": { "data-uri-to-buffer": "^4.0.0", "fetch-blob": "^3.1.4", "formdata-polyfill": "^4.0.10" } }, "sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA=="],
    "object-assign": ["object-assign@4.1.1", "", {}, "sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg=="],
    "object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
    "on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
    "once": ["once@1.4.0", "", { "dependencies": { "wrappy": "1" } }, "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w=="],
    "openai": ["openai@6.38.0", "", { "peerDependencies": { "ws": "^8.18.0", "zod": "^3.25 || ^4.0" }, "optionalPeers": ["ws", "zod"], "bin": { "openai": "bin/cli" } }, "sha512-AoMplt2UalrpgUDMh3L09QWjNRlgJPipclQvA6sYAaeF6nHNBMgmikAZGmcYLn8on4d9sQY9Q8bOLfrBS7Lc8g=="],
    "p-retry": ["p-retry@4.6.2", "", { "dependencies": { "@types/retry": "0.12.0", "retry": "^0.13.1" } }, "sha512-312Id396EbJdvRONlngUx0NydfrIQ5lsYu0znKVUzVvArzEIt08V1qhtyESbGVd1FGX7UKtiFp5uwKZdM8wIuQ=="],
    "parseurl": ["parseurl@1.3.3", "", {}, "sha512-CiyeOxFT/JZyN5m0z9PfXw4SCBJ6Sygz1Dpl0wqjlhDEGGBP1GnsUVEL0p63hoG1fcj3fHynXi9NYO4nWOL+qQ=="],
    "path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="],
    "path-to-regexp": ["path-to-regexp@8.4.2", "", {}, "sha512-qRcuIdP69NPm4qbACK+aDogI5CBDMi1jKe0ry5rSQJz8JVLsC7jV8XpiJjGRLLol3N+R5ihGYcrPLTno6pAdBA=="],
    "pkce-challenge": ["pkce-challenge@5.0.1", "", {}, "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ=="],
    "protobufjs": ["protobufjs@7.6.0", "", { "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", "@protobufjs/codegen": "^2.0.5", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.1", "@protobufjs/float": "^1.0.2", "@protobufjs/inquire": "^1.1.2", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", "@protobufjs/utf8": "^1.1.1", "@types/node": ">=13.7.0", "long": "^5.3.2" } }, "sha512-LtESOsMPTZgyYtwxhvdgdjGL0HmXEaRA/hVD6sol4zA60hVXXXP/SGmxnqDbgGE8gy7pYex7cym+5vYPcmaXBQ=="],
    "proxy-addr": ["proxy-addr@2.0.7", "", { "dependencies": { "forwarded": "0.2.0", "ipaddr.js": "1.9.1" } }, "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg=="],
    "qs": ["qs@6.15.2", "", { "dependencies": { "side-channel": "^1.1.0" } }, "sha512-Rzq0KEyX/w/tEybncDgdkZrJgVUsUMk3xjh3t5bv3S1HTAtg+uOYt72+ZfwiQwKdysThkTBdL/rTi6HDmX9Ddw=="],
    "range-parser": ["range-parser@1.2.1", "", {}, "sha512-Hrgsx+orqoygnmhFbKaHE6c296J+HTAQXoxEF6gNupROmmGJRoyzfG3ccAveqCBrwr/2yxQ5BVd/GTl5agOwSg=="],
    "raw-body": ["raw-body@3.0.2", "", { "dependencies": { "bytes": "~3.1.2", "http-errors": "~2.0.1", "iconv-lite": "~0.7.0", "unpipe": "~1.0.0" } }, "sha512-K5zQjDllxWkf7Z5xJdV0/B0WTNqx6vxG70zJE4N0kBs4LovmEYWJzQGxC9bS9RAKu3bgM40lrd5zoLJ12MQ5BA=="],
    "require-from-string": ["require-from-string@2.0.2", "", {}, "sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw=="],
    "retry": ["retry@0.13.1", "", {}, "sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg=="],
    "router": ["router@2.2.0", "", { "dependencies": { "debug": "^4.4.0", "depd": "^2.0.0", "is-promise": "^4.0.0", "parseurl": "^1.3.3", "path-to-regexp": "^8.0.0" } }, "sha512-nLTrUKm2UyiL7rlhapu/Zl45FwNgkZGaCpZbIHajDYgwlJCOzLSk+cIPAnsEqV955GjILJnKbdQC1nVPz+gAYQ=="],
    "safe-buffer": ["safe-buffer@5.2.1", "", {}, "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ=="],
    "safer-buffer": ["safer-buffer@2.1.2", "", {}, "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg=="],
    "send": ["send@1.2.1", "", { "dependencies": { "debug": "^4.4.3", "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "etag": "^1.8.1", "fresh": "^2.0.0", "http-errors": "^2.0.1", "mime-types": "^3.0.2", "ms": "^2.1.3", "on-finished": "^2.4.1", "range-parser": "^1.2.1", "statuses": "^2.0.2" } }, "sha512-1gnZf7DFcoIcajTjTwjwuDjzuz4PPcY2StKPlsGAQ1+YH20IRVrBaXSWmdjowTJ6u8Rc01PoYOGHXfP1mYcZNQ=="],
    "serve-static": ["serve-static@2.2.1", "", { "dependencies": { "encodeurl": "^2.0.0", "escape-html": "^1.0.3", "parseurl": "^1.3.3", "send": "^1.2.0" } }, "sha512-xRXBn0pPqQTVQiC8wyQrKs2MOlX24zQ0POGaj0kultvoOCstBQM5yvOhAVSUwOMjQtTvsPWoNCHfPGwaaQJhTw=="],
    "setprototypeof": ["setprototypeof@1.2.0", "", {}, "sha512-E5LDX7Wrp85Kil5bhZv46j8jOeboKq5JMmYM3gVGdGH8xFpPWXUMsNrlODCrkoxMEeNi/XZIwuRvY4XNwYMJpw=="],
    "shebang-command": ["shebang-command@2.0.0", "", { "dependencies": { "shebang-regex": "^3.0.0" } }, "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA=="],
    "shebang-regex": ["shebang-regex@3.0.0", "", {}, "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A=="],
    "side-channel": ["side-channel@1.1.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3", "side-channel-list": "^1.0.0", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw=="],
    "side-channel-list": ["side-channel-list@1.0.1", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.4" } }, "sha512-mjn/0bi/oUURjc5Xl7IaWi/OJJJumuoJFQJfDDyO46+hBWsfaVM65TBHq2eoZBhzl9EchxOijpkbRC8SVBQU0w=="],
    "side-channel-map": ["side-channel-map@1.0.1", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "get-intrinsic": "^1.2.5", "object-inspect": "^1.13.3" } }, "sha512-VCjCNfgMsby3tTdo02nbjtM/ewra6jPHmpThenkTYh8pG9ucZ/1P8So4u4FGBek/BjpOVsDCMoLA/iuBKIFXRA=="],
    "side-channel-weakmap": ["side-channel-weakmap@1.0.2", "", { "dependencies": { "call-bound": "^1.0.2", "es-errors": "^1.3.0", "get-intrinsic": "^1.2.5", "object-inspect": "^1.13.3", "side-channel-map": "^1.0.1" } }, "sha512-WPS/HvHQTYnHisLo9McqBHOJk2FkHO/tlpvldyrnem4aeQp4hai3gythswg6p01oSoTl58rcpiFAjF2br2Ak2A=="],
    "standardwebhooks": ["standardwebhooks@1.0.0", "", { "dependencies": { "@stablelib/base64": "^1.0.0", "fast-sha256": "^1.3.0" } }, "sha512-BbHGOQK9olHPMvQNHWul6MYlrRTAOKn03rOe4A8O3CLWhNf4YHBqq2HJKKC+sfqpxiBY52pNeesD6jIiLDz8jg=="],
    "statuses": ["statuses@2.0.2", "", {}, "sha512-DvEy55V3DB7uknRo+4iOGT5fP1slR8wQohVdknigZPMpMstaKJQWhwiYBACJE3Ul2pTnATihhBYnRhZQHGBiRw=="],
    "toidentifier": ["toidentifier@1.0.1", "", {}, "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA=="],
    "ts-algebra": ["ts-algebra@2.0.0", "", {}, "sha512-FPAhNPFMrkwz76P7cdjdmiShwMynZYN6SgOujD1urY4oNm80Ou9oMdmbR45LotcKOXoy7wSmHkRFE6Mxbrhefw=="],
    "type-is": ["type-is@2.1.0", "", { "dependencies": { "content-type": "^2.0.0", "media-typer": "^1.1.0", "mime-types": "^3.0.0" } }, "sha512-faYHw0anBbc/kWF3zFTEnxSFOAGUX9GFbOBthvDdLsIlEoWOFOtS0zgCiQYwIskL9iGXZL3kAXD8OoZ4GmMATA=="],
    "typescript": ["typescript@6.0.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-y2TvuxSZPDyQakkFRPZHKFm+KKVqIisdg9/CZwm9ftvKXLP8NRWj38/ODjNbr43SsoXqNuAisEf1GdCxqWcdBw=="],
    "undici-types": ["undici-types@7.24.6", "", {}, "sha512-WRNW+sJgj5OBN4/0JpHFqtqzhpbnV0GuB+OozA9gCL7a993SmU+1JBZCzLNxYsbMfIeDL+lTsphD5jN5N+n0zg=="],
    "unpipe": ["unpipe@1.0.0", "", {}, "sha512-pjy2bYhSsufwWlKwPc+l3cN7+wuJlK6uz0YdJEOlQDbl6jo/YlPi4mb8agUkVC8BF7V8NuzeyPNqRksA3hztKQ=="],
    "vary": ["vary@1.1.2", "", {}, "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg=="],
    "web-streams-polyfill": ["web-streams-polyfill@3.3.3", "", {}, "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw=="],
    "which": ["which@2.0.2", "", { "dependencies": { "isexe": "^2.0.0" }, "bin": { "node-which": "./bin/node-which" } }, "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA=="],
    "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],
    "ws": ["ws@8.20.1", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-It4dO0K5v//JtTXuPkfEOaI3uUN87iYPnqo/ZzqCoG3g8uhA66QUMs/SrM0YK7/NAu+r4LMh/9dq2A7k+rHs+w=="],
    "zod": ["zod@4.4.3", "", {}, "sha512-ytENFjIJFl2UwYglde2jchW2Hwm4GJFLDiSXWdTrJQBIN9Fcyp7n4DhxJEiWNAJMV1/BqWfW/kkg71UDcHJyTQ=="],
    "zod-to-json-schema": ["zod-to-json-schema@3.25.2", "", { "peerDependencies": { "zod": "^3.25.28 || ^4" } }, "sha512-O/PgfnpT1xKSDeQYSCfRI5Gy3hPf91mKVDuYLUHZJMiDFptvP41MSnWofm8dnCm0256ZNfZIM7DSzuSMAFnjHA=="],
    "bun-types/@types/node": ["@types/node@24.12.4", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GUUEShf+PBCGW2KaXwcIt3Yk+e3pkKwWKb9GSyM9WQVE+ep2jzmHdGsHzu4wgcZy5fN9FBdVzjpBQsYlpfpgLA=="],
    "type-is/content-type": ["content-type@2.0.0", "", {}, "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ=="],
    "bun-types/@types/node/undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
  }
 }
--- a/examples/claude-code.ts
+++ b/examples/claude-code.ts
@@ -0,0 +1,61 @@
 /**
 * Quick smoke test for ClaudeCodeProvider.
 *
 * Prereqs (pick one):
 *  - Claude Pro/Max subscription: run `claude setup-token`, then set
 *    CLAUDE_CODE_OAUTH_TOKEN=<the token it prints> in your environment
 *    (or pass it as `oauthToken` below).
 *  - Console API key: set ANTHROPIC_API_KEY (or pass `apiKey`).
 *
 * `claude login` alone is NOT sufficient for SDK use — Anthropic gates
 * non-interactive (`claude -p`) invocations behind a separate token.
 *
 * Run:  bun run examples/claude-code.ts
 */
 import { ClaudeCodeProvider } from '../src/index.js';
 async function main() {
  const claude = new ClaudeCodeProvider({
    defaultModel: 'sonnet',
    oauthToken: process.env.CLAUDE_CODE_OAUTH_TOKEN
  });
  console.log('Initializing…');
  await claude.initialize();
  console.log('Ready.\n');
  // ── Non-streaming completion ───────────────────────────────────────────
  console.log('--- complete() ---');
  const response = await claude.complete({
    messages: [
      { role: 'system', content: 'You are concise. Reply in one sentence.' },
      { role: 'user', content: 'What is the capital of Japan?' }
    ],
    maxTokens: 100
  });
  console.log(response.content);
  console.log(`tokens: ${response.usage.totalTokens} | cost: $${response.metadata?.costUsd ?? '?'}\n`);
  // ── Streaming ──────────────────────────────────────────────────────────
  console.log('--- stream() ---');
  let totalTokens = 0;
  for await (const chunk of claude.stream({
    messages: [{ role: 'user', content: 'Count from 1 to 5, one per line.' }],
    maxTokens: 100
  })) {
    if (!chunk.isComplete) {
      process.stdout.write(chunk.content);
    } else {
      totalTokens = chunk.usage?.totalTokens ?? 0;
    }
  }
  console.log(`\ntokens: ${totalTokens}`);
 }
 main().catch(err => {
  console.error('Failed:', err.message);
  if (err.type) console.error('Type:', err.type);
  process.exit(1);
 });
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
  "name": "simple-ai-provider",
-  "version": "2.0.1",
+  "version": "2.1.0",
  "description": "A simple and extensible AI provider package for easy integration of multiple AI services",
  "main": "dist/index.js",
  "module": "dist/index.mjs",
@@ -21,8 +21,8 @@
    "build": "bun run build:clean && bun run build:types && bun run build:esm && bun run build:cjs",
    "build:clean": "rm -rf dist",
    "build:types": "tsc --project tsconfig.build.json",
-    "build:esm": "bun build src/index.ts --outfile dist/index.mjs --format esm",
+    "build:esm": "bun build src/index.ts --outfile dist/index.mjs --format esm --target node",
-    "build:cjs": "bun build src/index.ts --outfile dist/index.js --format cjs",
+    "build:cjs": "bun build src/index.ts --outfile dist/index.js --format cjs --target node",
    "dev": "bun run src/index.ts",
    "test": "bun test",
    "prepublishOnly": "bun run build"
@@ -52,6 +52,7 @@
    "url": "https://gitea.jleibl.net/jleibl/simple-ai-provider.git"
  },
  "dependencies": {
    "@anthropic-ai/claude-agent-sdk": "^0.3.146",
    "@anthropic-ai/sdk": "^0.97.0",
    "@google/genai": "^2.5.0",
    "openai": "^6.0.0"
--- a/src/constants.ts
+++ b/src/constants.ts
@@ -16,7 +16,8 @@ export const DEFAULT_MODELS = {
  claude: 'claude-3-5-sonnet-20241022',
  openai: 'gpt-4o',
  gemini: 'gemini-2.5-flash',
-  openwebui: 'llama3.1:latest'
+  openwebui: 'llama3.1:latest',
  'claude-code': 'sonnet'
 } as const;
 export const DEFAULT_OPENWEBUI_BASE_URL = 'http://localhost:3000';
--- a/src/index.ts
+++ b/src/index.ts
@@ -38,6 +38,7 @@ export { ClaudeProvider, type ClaudeConfig } from './providers/claude.js';
 export { OpenAIProvider, type OpenAIConfig } from './providers/openai.js';
 export { GeminiProvider, type GeminiConfig } from './providers/gemini.js';
 export { OpenWebUIProvider, type OpenWebUIConfig } from './providers/openwebui.js';
 export { ClaudeCodeProvider, type ClaudeCodeConfig } from './providers/claude-code.js';
 // Factory utilities
 export {
@@ -46,6 +47,7 @@ export {
  createOpenAIProvider,
  createGeminiProvider,
  createOpenWebUIProvider,
  createClaudeCodeProvider,
  type ProviderType,
  PROVIDER_REGISTRY
 } from './utils/factory.js';
@@ -53,9 +55,9 @@ export {
 /**
 * List of all supported providers
 */
-export const SUPPORTED_PROVIDERS = ['claude', 'openai', 'gemini', 'openwebui'] as const;
+export const SUPPORTED_PROVIDERS = ['claude', 'openai', 'gemini', 'openwebui', 'claude-code'] as const;
 /**
 * Package version
 */
-export const VERSION = '2.0.1';
+export const VERSION = '2.1.0';
--- a/src/providers/claude-code.ts
+++ b/src/providers/claude-code.ts
@@ -0,0 +1,413 @@
 /**
 * Claude Code Provider
 *
 * Wraps `@anthropic-ai/claude-agent-sdk` so consumers can use a local
 * Claude Code installation through the same BaseAIProvider interface
 * as the other providers.
 *
 * Status:
 * - apiKey mode: works reliably.
 * - oauthToken (subscription) mode: currently broken on macOS due to an
 *   upstream SDK bug. The SDK isolates CLAUDE_CONFIG_DIR per invocation
 *   and tries to copy ~/.claude/.credentials.json, which doesn't exist on
 *   macOS (creds live in the Keychain). The OAuth token gets misclassified
 *   as an API key by the SDK, so requests are billed against API credits
 *   instead of the subscription. Subscribers without API credits will see
 *   "Credit balance is too low" errors. The oauthToken field is wired up
 *   and will work as expected once the SDK fix lands upstream.
 *
 * Other tradeoffs:
 * - Requires `claude` CLI installed on the host.
 * - Higher latency (spawns a CLI process per request).
 * - Designed for agent workflows, but used here in single-turn mode
 *   (maxTurns: 1, no tools) for plain text completion.
 * - If you have an API key, prefer the direct ClaudeProvider for simpler,
 *   lower-latency access.
 *
 * @see https://docs.anthropic.com/claude/docs/claude-code-sdk
 */
 import { query } from '@anthropic-ai/claude-agent-sdk';
 import type {
  AIMessage,
  AIProviderConfig,
  CompletionChunk,
  CompletionParams,
  CompletionResponse,
  ProviderInfo
 } from '../types/index.js';
 import { BaseAIProvider } from './base.js';
 import { AIProviderError, AIErrorType } from '../types/index.js';
 import { DEFAULT_MODELS } from '../constants.js';
 /**
 * Configuration for the Claude Code provider.
 *
 * Authentication options, in priority order:
 *
 *  1. `oauthToken` — long-lived subscription token generated by
 *     `claude setup-token` (recommended for Pro/Max subscribers using
 *     the SDK programmatically). Billed against the subscription.
 *  2. `apiKey` — standard Anthropic console API key. Billed per-token.
 *  3. Environment fallback — the SDK reads `CLAUDE_CODE_OAUTH_TOKEN` or
 *     `ANTHROPIC_API_KEY` from the environment if neither field is set.
 *
 * Note: `claude login` alone is not sufficient for SDK use because
 * Anthropic gates non-interactive (`claude -p`) invocations behind a
 * separate token. Run `claude setup-token` once to mint one.
 */
 export interface ClaudeCodeConfig extends Omit<AIProviderConfig, 'apiKey'> {
  /**
   * Long-lived OAuth token from `claude setup-token`. This is the
   * supported path for Claude Pro/Max subscribers to use the SDK
   * programmatically — billed against the subscription instead of
   * per-token.
   */
  oauthToken?: string;
  /** Standard Anthropic console API key. Mutually compatible with oauthToken (oauthToken takes precedence). */
  apiKey?: string;
  /**
   * Default model. Accepts SDK aliases (`'sonnet'`, `'opus'`, `'haiku'`,
   * `'inherit'`) or any full Claude model ID.
   * @default 'sonnet'
   */
  defaultModel?: string;
  /**
   * Working directory for the Claude Code session.
   * @default process.cwd()
   */
  cwd?: string;
  /**
   * Tool names the model is allowed to call. Defaults to none, which
   * makes the provider behave as a pure text completion endpoint.
   */
  allowedTools?: string[];
  /**
   * Maximum agent turns. Defaults to 1 for plain completion; raise this
   * if you also pass `allowedTools` and want tool-use loops.
   * @default 1
   */
  maxTurns?: number;
 }
 export class ClaudeCodeProvider extends BaseAIProvider {
  private readonly defaultModel: string;
  private readonly cwd: string | undefined;
  private readonly allowedTools: string[];
  private readonly maxTurns: number;
  private readonly oauthToken: string | undefined;
  constructor(config: ClaudeCodeConfig) {
    super(config as AIProviderConfig);
    this.defaultModel = config.defaultModel || DEFAULT_MODELS['claude-code'];
    this.cwd = config.cwd;
    this.allowedTools = config.allowedTools ?? [];
    this.maxTurns = config.maxTurns ?? 1;
    this.oauthToken = config.oauthToken;
  }
  /**
   * apiKey is optional for this provider — the SDK reads
   * ANTHROPIC_API_KEY from the environment or falls back to the local
   * Claude Code credentials. We override the base validator to skip the
   * non-empty apiKey requirement.
   */
  protected override validateAndNormalizeConfig(config: AIProviderConfig): AIProviderConfig {
    if (!config) {
      throw new AIProviderError(
        'Configuration object is required',
        AIErrorType.INVALID_REQUEST
      );
    }
    if (config.apiKey !== undefined && typeof config.apiKey !== 'string') {
      throw new AIProviderError(
        'API key, when provided, must be a string',
        AIErrorType.INVALID_REQUEST
      );
    }
    const oauthToken = (config as ClaudeCodeConfig).oauthToken;
    if (oauthToken !== undefined && typeof oauthToken !== 'string') {
      throw new AIProviderError(
        'oauthToken, when provided, must be a string',
        AIErrorType.INVALID_REQUEST
      );
    }
    return {
      ...config,
      apiKey: config.apiKey ?? '',
      timeout: config.timeout,
      maxRetries: config.maxRetries
    };
  }
  protected async doInitialize(): Promise<void> {
    // The SDK lazy-spawns the CLI per query; no connection probe is
    // necessary (and a probe would cost a real billed turn). We defer
    // auth/model errors to the first complete()/stream() call.
    if (this.oauthToken) {
      process.env.CLAUDE_CODE_OAUTH_TOKEN = this.oauthToken;
    }
    if (this.config.apiKey) {
      process.env.ANTHROPIC_API_KEY = this.config.apiKey;
    }
  }
  protected async doComplete(params: CompletionParams): Promise<CompletionResponse<string>> {
    const { systemPrompt, prompt } = this.buildPrompt(params.messages);
    const model = params.model || this.defaultModel;
    let collectedText = '';
    let sessionId = '';
    let usage = { promptTokens: 0, completionTokens: 0, totalTokens: 0 };
    for await (const message of query({
      prompt,
      options: this.buildOptions(model, systemPrompt)
    })) {
      if (message.type === 'system' && message.subtype === 'init') {
        sessionId = message.session_id;
        continue;
      }
      if (message.type === 'assistant') {
        if (message.error) {
          throw this.errorForSdkAssistantError(message.error);
        }
        collectedText += extractText(message.message.content);
        continue;
      }
      if (message.type === 'result') {
        usage = {
          promptTokens: message.usage?.input_tokens ?? 0,
          completionTokens: message.usage?.output_tokens ?? 0,
          totalTokens: (message.usage?.input_tokens ?? 0) + (message.usage?.output_tokens ?? 0)
        };
        if (message.subtype !== 'success') {
          throw new AIProviderError(
            `Claude Code session ended without a successful result: ${message.subtype}`,
            AIErrorType.UNKNOWN
          );
        }
        return {
          content: collectedText || message.result,
          model,
          usage,
          id: sessionId || message.uuid,
          metadata: {
            costUsd: message.total_cost_usd,
            durationMs: message.duration_ms,
            numTurns: message.num_turns,
            stopReason: message.stop_reason
          }
        };
      }
    }
    throw new AIProviderError(
      'Claude Code stream ended without a result message',
      AIErrorType.UNKNOWN
    );
  }
  protected async *doStream<T = any>(
    params: CompletionParams<T>
  ): AsyncIterable<CompletionChunk> {
    const { systemPrompt, prompt } = this.buildPrompt(params.messages);
    const model = params.model || this.defaultModel;
    let sessionId = '';
    let yieldedText = '';
    for await (const message of query({
      prompt,
      options: this.buildOptions(model, systemPrompt)
    })) {
      if (message.type === 'system' && message.subtype === 'init') {
        sessionId = message.session_id;
        continue;
      }
      if (message.type === 'assistant') {
        if (message.error) {
          throw this.errorForSdkAssistantError(message.error);
        }
        const fullText = extractText(message.message.content);
        const delta = fullText.slice(yieldedText.length);
        if (delta) {
          yield { content: delta, isComplete: false, id: sessionId };
          yieldedText = fullText;
        }
        continue;
      }
      if (message.type === 'result') {
        const usage = {
          promptTokens: message.usage?.input_tokens ?? 0,
          completionTokens: message.usage?.output_tokens ?? 0,
          totalTokens: (message.usage?.input_tokens ?? 0) + (message.usage?.output_tokens ?? 0)
        };
        if (message.subtype !== 'success') {
          throw new AIProviderError(
            `Claude Code session ended without a successful result: ${message.subtype}`,
            AIErrorType.UNKNOWN
          );
        }
        yield { content: '', isComplete: true, id: sessionId, usage };
        return;
      }
    }
  }
  public getInfo(): ProviderInfo {
    return {
      name: 'Claude Code',
      version: '1.0.0',
      models: ['sonnet', 'opus', 'haiku', 'inherit'],
      maxContextLength: 200000,
      supportsStreaming: true,
      capabilities: {
        vision: true,
        functionCalling: true,
        systemMessages: true,
        reasoning: true,
        codeGeneration: true,
        subscriptionAuth: true,
        requiresLocalCli: true
      }
    };
  }
  protected override mapProviderError(error: any): AIProviderError | null {
    if (!error) return null;
    const message: string = error.message || '';
    if (message.includes('ENOENT') && message.toLowerCase().includes('claude')) {
      return new AIProviderError(
        'Claude Code CLI not found. Install it from https://docs.anthropic.com/claude/docs/claude-code and run `claude login` for subscription accounts.',
        AIErrorType.INVALID_REQUEST,
        undefined,
        error
      );
    }
    if (message.includes('not logged in') || message.includes('authentication')) {
      return new AIProviderError(
        'Claude Code is not authenticated. Run `claude login` or set ANTHROPIC_API_KEY in the environment.',
        AIErrorType.AUTHENTICATION,
        undefined,
        error
      );
    }
    return null;
  }
  private buildPrompt(messages: AIMessage[]): { systemPrompt: string | undefined; prompt: string } {
    let systemPrompt: string | undefined;
    const turns: AIMessage[] = [];
    for (const msg of messages) {
      if (msg.role === 'system') {
        systemPrompt = systemPrompt ? `${systemPrompt}\n\n${msg.content}` : msg.content;
      } else {
        turns.push(msg);
      }
    }
    if (turns.length === 0) {
      throw new AIProviderError(
        'At least one user or assistant message is required',
        AIErrorType.INVALID_REQUEST
      );
    }
    // Single user turn: pass the content directly. Multi-turn history is
    // flattened with role labels — the Agent SDK doesn't accept a
    // messages array in stateless mode, so this is the simplest faithful
    // representation of the conversation.
    if (turns.length === 1 && turns[0]!.role === 'user') {
      return { systemPrompt, prompt: turns[0]!.content };
    }
    const flattened = turns
      .map(t => `${t.role === 'assistant' ? 'Assistant' : 'Human'}: ${t.content}`)
      .join('\n\n');
    return { systemPrompt, prompt: `${flattened}\n\nAssistant:` };
  }
  private buildOptions(model: string, systemPrompt: string | undefined) {
    const options: Record<string, unknown> = {
      model,
      maxTurns: this.maxTurns,
      allowedTools: this.allowedTools
    };
    if (systemPrompt) options.systemPrompt = systemPrompt;
    if (this.cwd) options.cwd = this.cwd;
    return options as any;
  }
  private errorForSdkAssistantError(code: string): AIProviderError {
    const map: Record<string, { type: AIErrorType; message: string }> = {
      authentication_failed: {
        type: AIErrorType.AUTHENTICATION,
        message: 'Claude Code authentication failed. For subscriptions run `claude setup-token` and pass the result as `oauthToken`. Otherwise set ANTHROPIC_API_KEY or pass `apiKey`.'
      },
      oauth_org_not_allowed: {
        type: AIErrorType.AUTHENTICATION,
        message: 'Your organization is not allowed by the Claude Code OAuth policy.'
      },
      billing_error: {
        type: AIErrorType.AUTHENTICATION,
        message: 'Billing error from Claude Code SDK. If you are a Pro/Max subscriber on macOS, this is likely the upstream @anthropic-ai/claude-agent-sdk Keychain bug — the SDK misclassifies the OAuth token as an API key. Workaround: use ClaudeProvider directly with an ANTHROPIC_API_KEY instead.'
      },
      rate_limit: {
        type: AIErrorType.RATE_LIMIT,
        message: 'Rate limit exceeded.'
      },
      invalid_request: {
        type: AIErrorType.INVALID_REQUEST,
        message: 'Invalid request to Claude Code.'
      },
      model_not_found: {
        type: AIErrorType.MODEL_NOT_FOUND,
        message: 'Requested model is not available to this Claude Code installation.'
      },
      server_error: {
        type: AIErrorType.NETWORK,
        message: 'Claude Code server error. Try again shortly.'
      },
      max_output_tokens: {
        type: AIErrorType.INVALID_REQUEST,
        message: 'Response exceeded the configured maxOutputTokens.'
      }
    };
    const entry = map[code] ?? { type: AIErrorType.UNKNOWN, message: `Claude Code error: ${code}` };
    return new AIProviderError(entry.message, entry.type);
  }
 }
 function extractText(content: unknown): string {
  if (!Array.isArray(content)) return '';
  let out = '';
  for (const block of content) {
    if (block && typeof block === 'object' && (block as any).type === 'text') {
      out += (block as any).text ?? '';
    }
  }
  return out;
 }
--- a/src/providers/index.ts
+++ b/src/providers/index.ts
@@ -8,3 +8,4 @@ export { ClaudeProvider, type ClaudeConfig } from './claude.js';
 export { OpenAIProvider, type OpenAIConfig } from './openai.js';
 export { GeminiProvider, type GeminiConfig } from './gemini.js';
 export { OpenWebUIProvider, type OpenWebUIConfig } from './openwebui.js';
 export { ClaudeCodeProvider, type ClaudeCodeConfig } from './claude-code.js';
--- a/src/utils/factory.ts
+++ b/src/utils/factory.ts
@@ -6,13 +6,15 @@ import { ClaudeProvider, type ClaudeConfig } from '../providers/claude.js';
 import { OpenAIProvider, type OpenAIConfig } from '../providers/openai.js';
 import { GeminiProvider, type GeminiConfig } from '../providers/gemini.js';
 import { OpenWebUIProvider, type OpenWebUIConfig } from '../providers/openwebui.js';
 import { ClaudeCodeProvider, type ClaudeCodeConfig } from '../providers/claude-code.js';
 import { BaseAIProvider } from '../providers/base.js';
 export const PROVIDER_REGISTRY = {
  claude: ClaudeProvider,
  openai: OpenAIProvider,
  gemini: GeminiProvider,
-  openwebui: OpenWebUIProvider
+  openwebui: OpenWebUIProvider,
  'claude-code': ClaudeCodeProvider
 } as const;
 export type ProviderType = keyof typeof PROVIDER_REGISTRY;
@@ -22,6 +24,7 @@ export interface ProviderConfigMap {
  openai: OpenAIConfig;
  gemini: GeminiConfig;
  openwebui: OpenWebUIConfig;
  'claude-code': ClaudeCodeConfig;
 }
 export function createProvider<T extends ProviderType>(
@@ -59,3 +62,9 @@ export function createGeminiProvider(
 export function createOpenWebUIProvider(config: OpenWebUIConfig): OpenWebUIProvider {
  return new OpenWebUIProvider(config);
 }
 export function createClaudeCodeProvider(
  options: Partial<ClaudeCodeConfig> = {}
 ): ClaudeCodeProvider {
  return new ClaudeCodeProvider(options);
 }
--- a/tests/claude-code.test.ts
+++ b/tests/claude-code.test.ts
@@ -0,0 +1,178 @@
 /**
 * Tests for ClaudeCodeProvider
 *
 * The provider shells out to the local Claude Code CLI via
 * @anthropic-ai/claude-agent-sdk. Tests cover the public surface and the
 * provider-specific hooks; full integration is not exercised because it
 * would spawn a real CLI process.
 */
 import { describe, it, expect, beforeEach } from 'bun:test';
 import { ClaudeCodeProvider } from '../src/providers/claude-code.js';
 import { AIProviderError, AIErrorType } from '../src/types/index.js';
 describe('ClaudeCodeProvider', () => {
  let provider: ClaudeCodeProvider;
  beforeEach(() => {
    provider = new ClaudeCodeProvider({ apiKey: 'test-key' });
  });
  describe('Constructor', () => {
    it('should accept empty config (subscription mode)', () => {
      const p = new ClaudeCodeProvider({});
      expect(p).toBeInstanceOf(ClaudeCodeProvider);
    });
    it('should accept apiKey override', () => {
      const p = new ClaudeCodeProvider({ apiKey: 'sk-...' });
      expect(p).toBeInstanceOf(ClaudeCodeProvider);
    });
    it('should accept custom defaults', () => {
      const p = new ClaudeCodeProvider({
        defaultModel: 'opus',
        maxTurns: 5,
        allowedTools: ['Read', 'Bash'],
        cwd: '/tmp/agent'
      });
      expect(p).toBeInstanceOf(ClaudeCodeProvider);
    });
    it('should reject non-string apiKey', () => {
      expect(() => new ClaudeCodeProvider({ apiKey: 123 as any }))
        .toThrow(AIProviderError);
    });
  });
  describe('getInfo', () => {
    it('should advertise subscriptionAuth capability', () => {
      const info = provider.getInfo();
      expect(info.name).toBe('Claude Code');
      expect(info.supportsStreaming).toBe(true);
      expect(info.capabilities).toMatchObject({
        subscriptionAuth: true,
        requiresLocalCli: true,
        systemMessages: true
      });
      expect(info.models).toContain('sonnet');
      expect(info.models).toContain('opus');
    });
  });
  describe('Error mapping', () => {
    const mapError = (err: any) => (provider as any).mapProviderError(err);
    it('should detect missing CLI', () => {
      const err = new Error('spawn claude ENOENT');
      const mapped = mapError(err);
      expect(mapped).toBeInstanceOf(AIProviderError);
      expect(mapped.type).toBe(AIErrorType.INVALID_REQUEST);
      expect(mapped.message).toContain('CLI');
    });
    it('should detect missing authentication', () => {
      const err = new Error('not logged in');
      const mapped = mapError(err);
      expect(mapped).toBeInstanceOf(AIProviderError);
      expect(mapped.type).toBe(AIErrorType.AUTHENTICATION);
    });
    it('should return null for unrelated errors', () => {
      expect(mapError(new Error('something else'))).toBeNull();
    });
  });
  describe('SDK assistant error mapping', () => {
    const mapSdkError = (code: string) => (provider as any).errorForSdkAssistantError(code);
    it('should map authentication_failed', () => {
      const err = mapSdkError('authentication_failed');
      expect(err.type).toBe(AIErrorType.AUTHENTICATION);
    });
    it('should map rate_limit', () => {
      const err = mapSdkError('rate_limit');
      expect(err.type).toBe(AIErrorType.RATE_LIMIT);
    });
    it('should map model_not_found', () => {
      const err = mapSdkError('model_not_found');
      expect(err.type).toBe(AIErrorType.MODEL_NOT_FOUND);
    });
    it('should map server_error to NETWORK', () => {
      const err = mapSdkError('server_error');
      expect(err.type).toBe(AIErrorType.NETWORK);
    });
    it('should fall back to UNKNOWN for unrecognized codes', () => {
      const err = mapSdkError('weird_new_code');
      expect(err.type).toBe(AIErrorType.UNKNOWN);
    });
  });
  describe('Prompt building', () => {
    const build = (messages: any[]) => (provider as any).buildPrompt(messages);
    it('should pass single user turn through unchanged', () => {
      const result = build([{ role: 'user', content: 'Hello' }]);
      expect(result.prompt).toBe('Hello');
      expect(result.systemPrompt).toBeUndefined();
    });
    it('should combine multiple system messages', () => {
      const result = build([
        { role: 'system', content: 'Be brief' },
        { role: 'system', content: 'Use British spelling' },
        { role: 'user', content: 'Hi' }
      ]);
      expect(result.systemPrompt).toBe('Be brief\n\nUse British spelling');
      expect(result.prompt).toBe('Hi');
    });
    it('should flatten multi-turn conversation with role labels', () => {
      const result = build([
        { role: 'user', content: 'What is 2+2?' },
        { role: 'assistant', content: '4' },
        { role: 'user', content: 'Why?' }
      ]);
      expect(result.prompt).toContain('Human: What is 2+2?');
      expect(result.prompt).toContain('Assistant: 4');
      expect(result.prompt).toContain('Human: Why?');
      expect(result.prompt.endsWith('Assistant:')).toBe(true);
    });
    it('should reject empty turn list', () => {
      expect(() => build([{ role: 'system', content: 'only system' }]))
        .toThrow(AIProviderError);
    });
  });
  describe('Validation', () => {
    it('should require initialization before complete()', async () => {
      await expect(
        provider.complete({ messages: [{ role: 'user', content: 'test' }] })
      ).rejects.toThrow('Provider must be initialized before use');
    });
    it('should validate temperature range when initialized', async () => {
      (provider as any).initialized = true;
      await expect(
        provider.complete({
          messages: [{ role: 'user', content: 'test' }],
          temperature: 1.5
        })
      ).rejects.toThrow(/temperature must be at most 1/);
    });
  });
 });
--- a/tests/claude.test.ts
+++ b/tests/claude.test.ts
@@ -51,7 +51,7 @@ describe('ClaudeProvider', () => {
          messages: [{ role: 'user', content: 'test' }],
          temperature: 1.5
        })
-      ).rejects.toThrow('Temperature must be a number between 0.0 and 1.0');
+      ).rejects.toThrow(/temperature must be at most 1/);
    });
    it('should validate message format', async () => {
@@ -79,17 +79,18 @@ describe('ClaudeProvider', () => {
      const error = new Error('Unauthorized');
      (error as any).status = 401;
-      const providerError = (provider as any).handleAnthropicError(error);
+      const providerError = (provider as any).normalizeError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.AUTHENTICATION);
      expect(providerError.statusCode).toBe(401);
    });
    it('should handle rate limit errors', () => {
      const error = new Error('Rate limited');
      (error as any).status = 429;
-      const providerError = (provider as any).handleAnthropicError(error);
+      const providerError = (provider as any).normalizeError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.RATE_LIMIT);
@@ -99,11 +100,21 @@ describe('ClaudeProvider', () => {
      const error = new Error('Model not found');
      (error as any).status = 404;
-      const providerError = (provider as any).handleAnthropicError(error);
+      const providerError = (provider as any).normalizeError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.MODEL_NOT_FOUND);
    });
    it('should route 400 with max_tokens to mapProviderError', () => {
      const error = new Error('max_tokens too large');
      (error as any).status = 400;
      const providerError = (provider as any).normalizeError(error);
      expect(providerError.type).toBe(AIErrorType.INVALID_REQUEST);
      expect(providerError.message).toMatch(/Max tokens/);
    });
  });
  describe('message conversion', () => {
--- a/tests/gemini.test.ts
+++ b/tests/gemini.test.ts
@@ -11,7 +11,7 @@ describe('GeminiProvider', () => {
  beforeEach(() => {
    provider = new GeminiProvider({
      apiKey: 'test-api-key',
-      defaultModel: 'gemini-1.5-flash'
+      defaultModel: 'gemini-2.5-flash'
    });
  });
@@ -54,11 +54,11 @@ describe('GeminiProvider', () => {
      const info = provider.getInfo();
      expect(info.name).toBe('Gemini');
-      expect(info.version).toBe('1.0.0');
+      expect(info.version).toBe('2.0.0');
      expect(info.supportsStreaming).toBe(true);
-      expect(info.models).toContain('gemini-1.5-flash');
+      expect(info.models).toContain('gemini-2.5-flash');
      expect(info.models).toContain('gemini-2.5-pro');
      expect(info.models).toContain('gemini-1.5-pro');
      expect(info.models).toContain('gemini-1.0-pro');
      expect(info.maxContextLength).toBe(1048576);
      expect(info.capabilities).toHaveProperty('vision', true);
      expect(info.capabilities).toHaveProperty('functionCalling', true);
@@ -79,7 +79,7 @@ describe('GeminiProvider', () => {
          messages: [{ role: 'user', content: 'test' }],
          temperature: 1.5
        })
-      ).rejects.toThrow('Temperature must be a number between 0.0 and 1.0');
+      ).rejects.toThrow(/temperature must be at most 1/);
    });
    it('should validate top_p range', async () => {
@@ -92,7 +92,7 @@ describe('GeminiProvider', () => {
          messages: [{ role: 'user', content: 'test' }],
          topP: 1.5
        })
-      ).rejects.toThrow('Top-p must be a number between 0.0 (exclusive) and 1.0 (inclusive)');
+      ).rejects.toThrow(/topP must be at most 1/);
    });
    it('should validate message format', async () => {
@@ -129,10 +129,12 @@ describe('GeminiProvider', () => {
  });
  describe('error handling', () => {
    const mapError = (err: any) => (provider as any).normalizeError(err);
    it('should handle authentication errors', () => {
      const error = new Error('API key invalid');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.AUTHENTICATION);
@@ -142,7 +144,7 @@ describe('GeminiProvider', () => {
    it('should handle rate limit errors', () => {
      const error = new Error('quota exceeded');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.RATE_LIMIT);
@@ -152,7 +154,7 @@ describe('GeminiProvider', () => {
    it('should handle model not found errors', () => {
      const error = new Error('model not found');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.MODEL_NOT_FOUND);
@@ -162,7 +164,7 @@ describe('GeminiProvider', () => {
    it('should handle invalid request errors', () => {
      const error = new Error('invalid length request parameters');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.INVALID_REQUEST);
@@ -171,7 +173,7 @@ describe('GeminiProvider', () => {
    it('should handle network errors', () => {
      const error = new Error('network connection failed');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.NETWORK);
@@ -180,7 +182,7 @@ describe('GeminiProvider', () => {
    it('should handle timeout errors', () => {
      const error = new Error('request timeout');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.TIMEOUT);
@@ -189,7 +191,7 @@ describe('GeminiProvider', () => {
    it('should handle unknown errors', () => {
      const error = new Error('Unknown error');
-      const providerError = (provider as any).handleGeminiError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.UNKNOWN);
@@ -266,7 +268,7 @@ describe('GeminiProvider', () => {
        stopSequences: ['STOP', 'END']
      };
-      const result = (provider as any).buildGenerationConfig(params);
+      const result = (provider as any).buildConfig(params);
      expect(result.temperature).toBe(0.8);
      expect(result.topP).toBe(0.9);
@@ -279,20 +281,29 @@ describe('GeminiProvider', () => {
        messages: [{ role: 'user' as const, content: 'test' }]
      };
-      const result = (provider as any).buildGenerationConfig(params);
+      const result = (provider as any).buildConfig(params);
      expect(result.temperature).toBe(0.7);
      expect(result.maxOutputTokens).toBe(1000);
    });
    it('should attach systemInstruction when passed', () => {
      const params = { messages: [{ role: 'user' as const, content: 'test' }] };
      const result = (provider as any).buildConfig(params, 'be helpful');
      expect(result.systemInstruction).toBe('be helpful');
    });
  });
  describe('response formatting', () => {
    // The @google/genai SDK exposes `text` as a getter on GenerateContentResponse,
    // so the mock provides it directly rather than reconstructing the candidate->parts tree.
    it('should format completion response correctly', () => {
      const mockResponse = {
        text: 'Hello there!',
        candidates: [{
          content: {
            parts: [{ text: 'Hello there!' }]
          },
          finishReason: 'STOP',
          safetyRatings: [],
          citationMetadata: null
@@ -304,42 +315,19 @@ describe('GeminiProvider', () => {
        }
      };
-      const result = (provider as any).formatCompletionResponse(mockResponse, 'gemini-1.5-flash');
+      const result = (provider as any).formatCompletionResponse(mockResponse, 'gemini-2.5-flash');
      expect(result.content).toBe('Hello there!');
-      expect(result.model).toBe('gemini-1.5-flash');
+      expect(result.model).toBe('gemini-2.5-flash');
      expect(result.usage.promptTokens).toBe(10);
      expect(result.usage.completionTokens).toBe(20);
      expect(result.usage.totalTokens).toBe(30);
      expect(result.metadata.finishReason).toBe('STOP');
    });
    it('should handle multiple text parts', () => {
      const mockResponse = {
        candidates: [{
          content: {
            parts: [
              { text: 'Hello ' },
              { text: 'there!' },
              { functionCall: { name: 'test' } } // Non-text part should be filtered
            ]
          },
          finishReason: 'STOP'
        }],
        usageMetadata: {
          promptTokenCount: 5,
          candidatesTokenCount: 10,
          totalTokenCount: 15
        }
      };
      const result = (provider as any).formatCompletionResponse(mockResponse, 'gemini-1.5-flash');
      expect(result.content).toBe('Hello there!');
    });
    it('should throw error for empty response', () => {
      const mockResponse = {
        text: '',
        candidates: [],
        usageMetadata: {
          promptTokenCount: 5,
@@ -349,8 +337,8 @@ describe('GeminiProvider', () => {
      };
      expect(() => {
-        (provider as any).formatCompletionResponse(mockResponse, 'gemini-1.5-flash');
+        (provider as any).formatCompletionResponse(mockResponse, 'gemini-2.5-flash');
-      }).toThrow('No candidates found in Gemini response');
+      }).toThrow('No text content found in Gemini response');
    });
  });
--- a/tests/openai.test.ts
+++ b/tests/openai.test.ts
@@ -73,7 +73,7 @@ describe('OpenAIProvider', () => {
          messages: [{ role: 'user', content: 'test' }],
          temperature: 1.5
        })
-      ).rejects.toThrow('Temperature must be a number between 0.0 and 1.0');
+      ).rejects.toThrow(/temperature must be at most 1/);
    });
    it('should validate top_p range', async () => {
@@ -85,7 +85,7 @@ describe('OpenAIProvider', () => {
          messages: [{ role: 'user', content: 'test' }],
          topP: 1.5
        })
-      ).rejects.toThrow('Top-p must be a number between 0.0 (exclusive) and 1.0 (inclusive)');
+      ).rejects.toThrow(/topP must be at most 1/);
    });
    it('should validate message format', async () => {
@@ -120,22 +120,24 @@ describe('OpenAIProvider', () => {
  });
  describe('error handling', () => {
    const mapError = (err: any) => (provider as any).normalizeError(err);
    it('should handle authentication errors', () => {
      const error = new Error('Unauthorized');
      (error as any).status = 401;
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.AUTHENTICATION);
-      expect(providerError.message).toContain('Authentication failed');
+      expect(providerError.message).toContain('OpenAI API key');
    });
    it('should handle rate limit errors', () => {
      const error = new Error('Rate limited');
      (error as any).status = 429;
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.RATE_LIMIT);
@@ -146,7 +148,7 @@ describe('OpenAIProvider', () => {
      const error = new Error('Model not found');
      (error as any).status = 404;
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.MODEL_NOT_FOUND);
@@ -157,7 +159,7 @@ describe('OpenAIProvider', () => {
      const error = new Error('Bad request');
      (error as any).status = 400;
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.INVALID_REQUEST);
@@ -167,7 +169,7 @@ describe('OpenAIProvider', () => {
      const error = new Error('Internal server error');
      (error as any).status = 500;
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.NETWORK);
@@ -176,11 +178,21 @@ describe('OpenAIProvider', () => {
    it('should handle unknown errors', () => {
      const error = new Error('Unknown error');
-      const providerError = (provider as any).handleOpenAIError(error);
+      const providerError = mapError(error);
      expect(providerError).toBeInstanceOf(AIProviderError);
      expect(providerError.type).toBe(AIErrorType.UNKNOWN);
    });
    it('should route 429 with quota to quota-specific message', () => {
      const error = new Error('quota exceeded');
      (error as any).status = 429;
      const providerError = mapError(error);
      expect(providerError.type).toBe(AIErrorType.RATE_LIMIT);
      expect(providerError.message).toContain('Usage quota exceeded');
    });
  });
  describe('message conversion', () => {
--- a/tests/openwebui.test.ts
+++ b/tests/openwebui.test.ts
@@ -1,5 +1,11 @@
 /**
 * Tests for OpenWebUI provider implementation
 *
 * The R3 refactor split message conversion, response formatting, and the
 * HTTP client into openwebui-strategies.ts and openwebui-http.ts. Tests for
 * those helpers should live alongside those files. This file covers the
 * provider's public surface and the error-mapping hooks it adds on top of
 * BaseAIProvider.
 */
 import { describe, it, expect, beforeEach, jest } from 'bun:test';
@@ -14,7 +20,7 @@ describe('OpenWebUIProvider', () => {
    mockConfig = {
      apiKey: 'test-bearer-token',
      baseUrl: 'http://localhost:3000',
-      defaultModel: 'llama3.1'
+      defaultModel: 'llama3.1:latest'
    };
  });
@@ -26,31 +32,32 @@ describe('OpenWebUIProvider', () => {
    });
    it('should use default values when not specified', () => {
-      const minimalConfig: OpenWebUIConfig = { apiKey: 'test' };
+      provider = new OpenWebUIProvider({ apiKey: 'test' });
      provider = new OpenWebUIProvider(minimalConfig);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
-    it('should handle custom configuration', () => {
+    it('should accept Ollama proxy mode', () => {
-      const config: OpenWebUIConfig = {
+      provider = new OpenWebUIProvider({
        apiKey: 'test',
        baseUrl: 'http://localhost:8080',
        defaultModel: 'mistral:7b',
        useOllamaProxy: true
-      };
+      });
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
-    it('should handle trailing slash in baseUrl', () => {
+    it('should normalize trailing slash in baseUrl', () => {
-      const config: OpenWebUIConfig = {
+      provider = new OpenWebUIProvider({
        apiKey: 'test',
-        baseUrl: 'http://localhost:3000/',
+        baseUrl: 'http://localhost:3000/'
-        defaultModel: 'llama3.1'
+      });
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
    it('should reject malformed baseUrl', () => {
      expect(() => new OpenWebUIProvider({ apiKey: 'test', baseUrl: 'not a url' }))
        .toThrow(AIProviderError);
    });
  });
  describe('getInfo', () => {
@@ -62,7 +69,7 @@ describe('OpenWebUIProvider', () => {
      const info = provider.getInfo();
      expect(info.name).toBe('OpenWebUI');
-      expect(info.version).toBe('1.0.0');
+      expect(info.version).toBe('2.0.0');
      expect(info.supportsStreaming).toBe(true);
      expect(info.maxContextLength).toBe(32768);
      expect(Array.isArray(info.models)).toBe(true);
@@ -77,338 +84,113 @@ describe('OpenWebUIProvider', () => {
      expect(info.models).toContain('gemma:latest');
    });
-    it('should have correct capabilities', () => {
+    it('should expose capabilities', () => {
      const info = provider.getInfo();
-      expect(info.capabilities).toEqual({
+      expect(info.capabilities).toMatchObject({
        vision: false,
        functionCalling: false,
        jsonMode: false,
        systemMessages: true,
-        reasoning: true,
+        localDeployment: true
        codeGeneration: true,
        localDeployment: true,
        multiModel: true
      });
    });
  });
-  describe('Error Handling', () => {
+  describe('Error mapping', () => {
    const mapError = (err: any) => (provider as any).normalizeError(err);
    beforeEach(() => {
      provider = new OpenWebUIProvider(mockConfig);
    });
-    it('should handle connection refused errors', () => {
+    it('should map ECONNREFUSED to NETWORK', () => {
-      const mockError = new Error('connect ECONNREFUSED') as any;
+      const error = new Error('connect ECONNREFUSED') as any;
      mockError.code = 'ECONNREFUSED';
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.NETWORK);
      expect(aiError.message).toContain('Network error connecting to OpenWebUI');
    });
-    it('should handle hostname resolution errors', () => {
+    it('should map ENOTFOUND to NETWORK', () => {
-      const mockError = new Error('getaddrinfo ENOTFOUND') as any;
+      const error = new Error('getaddrinfo ENOTFOUND') as any;
      mockError.code = 'ENOTFOUND';
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
-      expect(aiError).toBeInstanceOf(AIProviderError);
+      expect(aiError.type).toBe(AIErrorType.NETWORK);
      expect(aiError.type).toBe(AIErrorType.UNKNOWN);
      expect(aiError.message).toContain('OpenWebUI error');
    });
-    it('should handle 404 model not found errors', () => {
+    it('should map 404 with "model" in message to MODEL_NOT_FOUND', () => {
-      const mockError = new Error('model not available') as any;
+      const error = new Error('model not available') as any;
-      mockError.status = 404;
+      error.status = 404;
      mockError.message = 'model not available';
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.MODEL_NOT_FOUND);
      expect(aiError.message).toContain('OpenWebUI');
    });
-    it('should handle 404 endpoint not found errors', () => {
+    it('should map 404 without "model" in message to MODEL_NOT_FOUND with endpoint message', () => {
-      const mockError = new Error('Not found') as any;
+      const error = new Error('Not found') as any;
-      mockError.status = 404;
+      error.status = 404;
      mockError.message = 'endpoint not found';
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
-      expect(aiError).toBeInstanceOf(AIProviderError);
+      expect(aiError.type).toBe(AIErrorType.MODEL_NOT_FOUND);
-      expect(aiError.type).toBe(AIErrorType.INVALID_REQUEST);
+      expect(aiError.message).toContain('endpoint');
      expect(aiError.message).toContain('OpenWebUI endpoint not found');
    });
-    it('should handle timeout errors', () => {
+    it('should map timeout errors to TIMEOUT', () => {
-      const mockError = new Error('Request timeout') as any;
+      const error = new Error('Request timeout') as any;
      mockError.code = 'ETIMEDOUT';
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.TIMEOUT);
    });
-    it('should handle rate limit errors', () => {
+    it('should map 429 to RATE_LIMIT', () => {
-      const mockError = new Error('Rate limit exceeded') as any;
+      const error = new Error('Rate limit exceeded') as any;
-      mockError.status = 429;
+      error.status = 429;
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.RATE_LIMIT);
    });
-    it('should handle server errors', () => {
+    it('should map 500 to NETWORK', () => {
-      const mockError = new Error('Internal server error') as any;
+      const error = new Error('Internal server error') as any;
-      mockError.status = 500;
+      error.status = 500;
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.NETWORK);
    });
-    it('should handle authentication errors', () => {
+    it('should map 401 to AUTHENTICATION with OpenWebUI hint', () => {
-      const mockError = new Error('Unauthorized') as any;
+      const error = new Error('Unauthorized') as any;
-      mockError.status = 401;
+      error.status = 401;
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.AUTHENTICATION);
-      expect(aiError.message).toContain('Authentication failed with OpenWebUI');
+      expect(aiError.message).toContain('OpenWebUI');
    });
-    it('should handle unknown errors', () => {
+    it('should map unrecognized errors to UNKNOWN', () => {
-      const mockError = new Error('Unknown error');
+      const error = new Error('Unknown error');
-      const aiError = (provider as any).handleOpenWebUIError(mockError);
+      const aiError = mapError(error);
      expect(aiError).toBeInstanceOf(AIProviderError);
      expect(aiError.type).toBe(AIErrorType.UNKNOWN);
    });
  });
  describe('Message Conversion', () => {
    beforeEach(() => {
      provider = new OpenWebUIProvider(mockConfig);
    });
    it('should convert messages correctly for chat API', () => {
      const messages = [
        { role: 'system' as const, content: 'You are helpful' },
        { role: 'user' as const, content: 'Hello' },
        { role: 'assistant' as const, content: 'Hi there!' }
      ];
      const converted = (provider as any).convertMessages(messages);
      expect(converted).toHaveLength(3);
      expect(converted[0]).toEqual({ role: 'system', content: 'You are helpful' });
      expect(converted[1]).toEqual({ role: 'user', content: 'Hello' });
      expect(converted[2]).toEqual({ role: 'assistant', content: 'Hi there!' });
    });
    it('should convert messages to prompt for Ollama API', () => {
      const messages = [
        { role: 'system' as const, content: 'You are helpful' },
        { role: 'user' as const, content: 'Hello' },
        { role: 'assistant' as const, content: 'Hi there!' }
      ];
      const prompt = (provider as any).convertMessagesToPrompt(messages);
      expect(prompt).toBe('System: You are helpful\n\nHuman: Hello\n\nAssistant: Hi there!\n\nAssistant: ');
    });
  });
  describe('Response Formatting', () => {
    beforeEach(() => {
      provider = new OpenWebUIProvider(mockConfig);
    });
    it('should format chat completion response correctly', () => {
      const mockResponse = {
        id: 'test-id',
        object: 'chat.completion',
        created: 1234567890,
        model: 'llama3.1',
        choices: [{
          index: 0,
          message: { role: 'assistant', content: 'Hello there!' },
          finish_reason: 'stop'
        }],
        usage: {
          prompt_tokens: 10,
          completion_tokens: 5,
          total_tokens: 15
        }
      };
      const response = (provider as any).formatChatResponse(mockResponse);
      expect(response.content).toBe('Hello there!');
      expect(response.model).toBe('llama3.1');
      expect(response.id).toBe('test-id');
      expect(response.usage.promptTokens).toBe(10);
      expect(response.usage.completionTokens).toBe(5);
      expect(response.usage.totalTokens).toBe(15);
      expect(response.metadata?.finishReason).toBe('stop');
      expect(response.metadata?.created).toBe(1234567890);
    });
    it('should format Ollama response correctly', () => {
      const mockResponse = {
        model: 'llama3.1',
        created_at: '2024-01-01T00:00:00Z',
        response: 'Hello there!',
        done: true,
        prompt_eval_count: 10,
        eval_count: 5,
        total_duration: 1000000,
        eval_duration: 500000
      };
      const response = (provider as any).formatOllamaResponse(mockResponse);
      expect(response.content).toBe('Hello there!');
      expect(response.model).toBe('llama3.1');
      expect(response.usage.promptTokens).toBe(10);
      expect(response.usage.completionTokens).toBe(5);
      expect(response.usage.totalTokens).toBe(15);
      expect(response.metadata?.created).toBe(1704067200000);
      expect(response.metadata?.totalDuration).toBe(1000000);
    });
    it('should handle response without content', () => {
      const mockResponse = {
        id: 'test-id',
        object: 'chat.completion',
        created: 1234567890,
        model: 'llama3.1',
        choices: [{
          index: 0,
          message: { role: 'assistant' }, // Message without content
          finish_reason: 'stop'
        }],
        usage: { prompt_tokens: 5, completion_tokens: 0, total_tokens: 5 }
      };
      expect(() => {
        (provider as any).formatChatResponse(mockResponse);
      }).toThrow(AIProviderError);
    });
    it('should handle missing usage information', () => {
      const mockResponse = {
        id: 'test-id',
        object: 'chat.completion',
        created: 1234567890,
        model: 'llama3.1',
        choices: [{
          index: 0,
          message: { role: 'assistant', content: 'Hello there!' },
          finish_reason: 'stop'
        }]
        // No usage information
      };
      const response = (provider as any).formatChatResponse(mockResponse);
      expect(response.content).toBe('Hello there!');
      expect(response.usage.promptTokens).toBe(0);
      expect(response.usage.completionTokens).toBe(0);
      expect(response.usage.totalTokens).toBe(0);
    });
  });
  describe('Configuration Options', () => {
    it('should handle custom baseUrl', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        baseUrl: 'https://my-openwebui.com'
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
    it('should handle custom default model', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        defaultModel: 'mistral:7b'
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
    it('should handle Ollama proxy mode', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        useOllamaProxy: true
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
    it('should handle SSL verification settings', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        dangerouslyAllowInsecureConnections: false
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
  });
  describe('Request Generation', () => {
    beforeEach(() => {
      provider = new OpenWebUIProvider(mockConfig);
    });
    it('should generate correct headers', () => {
      const headers = (provider as any).makeRequest('http://test.com', 'GET');
      // Note: This would need to be mocked in a real test environment
      expect(typeof headers).toBe('object');
    });
  });
  describe('API Mode Selection', () => {
    it('should use chat API by default', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        useOllamaProxy: false
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
    it('should use Ollama proxy when configured', () => {
      const config: OpenWebUIConfig = {
        apiKey: 'test',
        useOllamaProxy: true
      };
      provider = new OpenWebUIProvider(config);
      expect(provider).toBeInstanceOf(OpenWebUIProvider);
    });
  });
  describe('Validation', () => {
    beforeEach(() => {
      provider = new OpenWebUIProvider(mockConfig);
    });
-    it('should validate provider is initialized before use', async () => {
+    it('should require initialization before use', async () => {
      const params: CompletionParams = {
        messages: [{ role: 'user', content: 'Hello' }]
      };
@@ -417,31 +199,31 @@ describe('OpenWebUIProvider', () => {
    });
  });
-  describe('structured responses', () => {
+  describe('Structured responses', () => {
-    it('should handle structured responses correctly', async () => {
+    it('should parse JSON content into typed responses', async () => {
-      const provider = new OpenWebUIProvider({ apiKey: 'test-key' });
+      const p = new OpenWebUIProvider({ apiKey: 'test-key' });
      const mockResponse = {
        content: JSON.stringify({ name: 'John Doe', age: 30 }),
-        model: 'llama3.1',
+        model: 'llama3.1:latest',
        usage: { promptTokens: 10, completionTokens: 20, totalTokens: 30 },
        id: 'test-id'
      };
-      (provider as any).doComplete = jest.fn().mockResolvedValue(mockResponse);
+      (p as any).doComplete = jest.fn().mockResolvedValue(mockResponse);
-      (provider as any).initialized = true;
+      (p as any).initialized = true;
-      const responseType = createResponseType<{ name: string; age: number }>
+      const responseType = createResponseType<{ name: string; age: number }>(
-        (`{ name: string; age: number }`,
+        `{ name: string; age: number }`,
        'A user profile'
      );
-      const response = await provider.complete<{ name: string; age: number }>({ 
+      const response = await p.complete<{ name: string; age: number }>({
        messages: [{ role: 'user', content: 'test' }],
        responseType
      });
      expect(response.content).toEqual({ name: 'John Doe', age: 30 });
      expect(response.rawContent).toBe(JSON.stringify({ name: 'John Doe', age: 30 }));
-      expect((provider as any).doComplete).toHaveBeenCalled();
+      expect((p as any).doComplete).toHaveBeenCalled();
    });
  });
 });
Author	SHA1	Message	Date
Jan-Marlon Leibl	956ca21f54	docs(claude-code): mark subscription mode broken on macOS PR #12 shipped oauthToken support with optimistic framing, but testing revealed @anthropic-ai/claude-agent-sdk has a macOS-specific bug: the SDK isolates CLAUDE_CONFIG_DIR per invocation and tries to copy ~/.claude/.credentials.json, which doesn't exist on macOS (creds live in the Keychain). The OAuth token gets misclassified as an API key and requests are billed against API credits instead of the subscription — subscribers without API credits see "Credit balance is too low" errors. Direct `claude -p` works fine, so the upstream SDK is the broken layer. Changes: - README Claude Code section: lead with the macOS status note and point subscribers at ClaudeProvider + ANTHROPIC_API_KEY as the current workaround. - JSDoc on ClaudeCodeProvider: same status note. - billing_error message: explain the bug and recommend the workaround so users can self-diagnose from the error alone. No code removal — when the SDK fix lands upstream, oauthToken users will Just Work without any code changes here.	2026-05-21 22:05:48 +02:00
jleibl	b99707c629	Merge pull request 'fix(claude-code): add oauthToken config for subscription SDK auth' (#12 ) from fix/claude-code-oauth-token into main Reviewed-on: #12	2026-05-21 12:56:28 +00:00
Jan-Marlon Leibl	b935209142	fix(claude-code): add oauthToken config for subscription SDK auth `claude login` alone does not authorize SDK / non-interactive (`claude -p`) usage. Anthropic gates that behind a separate long-lived token minted by `claude setup-token`. Without it, subscription users hit `billing_error` from the SDK even though interactive Claude Code works fine. Changes: - ClaudeCodeConfig.oauthToken: new optional field. When set, the provider exports it as CLAUDE_CODE_OAUTH_TOKEN before invoking the SDK, which makes the SDK bill against the user's Pro/Max subscription instead of API credits. - apiKey continues to work for users with a console API key. If both are present, oauthToken takes precedence. - billing_error / authentication_failed messages now point users at `claude setup-token` so the fix is obvious from the error alone. - README: rewrite the Claude Code section to document both modes and the `claude setup-token` step explicitly. - examples/claude-code.ts: read CLAUDE_CODE_OAUTH_TOKEN from env so the smoke test actually works for subscribers.	2026-05-21 14:56:14 +02:00
Jan-Marlon Leibl	d4871d22fe	chore(release): 2.1.0 Minor release adding the ClaudeCodeProvider for Claude Pro/Max subscription users (PR #10) along with a rewritten README (PR #10) and a repaired test suite (PR #11). New public exports: - ClaudeCodeProvider, ClaudeCodeConfig - createClaudeCodeProvider - 'claude-code' added to PROVIDER_REGISTRY and SUPPORTED_PROVIDERS No breaking changes.	2026-05-21 14:39:36 +02:00
jleibl	9cb7ee8f9e	Merge pull request 'test: repair test suite after R1-R3 refactors and add Claude Code tests' (#11 ) from chore/test-suite-repair into main Reviewed-on: #11	2026-05-21 12:38:05 +00:00
Jan-Marlon Leibl	a0d181787c	test: repair test suite after R1-R3 refactors and add Claude Code tests The R1-R3 refactors removed the per-provider handle*Error methods, consolidated validators into validateNumberInRange, renamed Gemini's buildGenerationConfig to buildConfig, and split OpenWebUI's message conversion and response formatting into openwebui-strategies.ts. 44 of 91 existing tests broke as a result. Changes: claude.test.ts (8 -> 13 passing) - Switch error mapping tests from handleAnthropicError to the base normalizeError method. - Update temperature error-message expectation to match the new validateNumberInRange wording. openai.test.ts (16 -> 22 passing) - Same handleOpenAIError -> normalizeError switch. - Add a regression test for the 429+"quota" path that goes through mapProviderError instead of the base mapping. gemini.test.ts (17 -> 27 passing) - Update getInfo expectations to the new default model (gemini-2.5) and provider version 2.0.0. - Switch to normalizeError. - Rename buildGenerationConfig -> buildConfig (renamed during R2). - Update formatCompletionResponse mocks: the @google/genai SDK exposes response.text as a getter rather than walking candidates[0].content.parts. openwebui.test.ts (4 -> 19 passing) - Drop tests for convertMessages / convertMessagesToPrompt / formatChatResponse / formatOllamaResponse / makeRequest: these moved into openwebui-strategies.ts and openwebui-http.ts during R3 and warrant their own test files. - Add error-mapping tests covering the new mapProviderError + providerErrorMessages plumbing. claude-code.test.ts (new, 18 tests) - Constructor accepts subscription mode (empty config). - getInfo advertises subscriptionAuth + requiresLocalCli. - mapProviderError catches ENOENT and "not logged in". - errorForSdkAssistantError covers each documented SDK error code. - buildPrompt handles single-turn pass-through, multi-system combination, multi-turn flattening with role labels, and rejects empty turn lists. Full suite: 100 pass / 0 fail across 5 files.	2026-05-21 14:37:33 +02:00
jleibl	93ef2611c0	Merge pull request 'feat: add ClaudeCodeProvider for subscription users' (#10 ) from feat/claude-code-provider into main Reviewed-on: #10	2026-05-21 12:25:34 +00:00
Jan-Marlon Leibl	c8c579da8b	docs: rewrite README Full rewrite focused on what consumers actually need: install, a working snippet per provider, and the public API surface. Changes vs the previous version: - Document ClaudeCodeProvider, including the subscription-via-CLI auth path that the new provider enables. - Remove the ProviderRegistry section (the class was removed in R1). - Drop the stale Provider Comparison and Detailed Capabilities tables; vendor capabilities and model lists move too fast for a README to track. - Remove the inaccurate Zero Dependencies and Comprehensive Testing claims (post-refactor 44/91 tests need updating). - Refresh default models (Gemini 1.5 -> 2.5) and the package list to match the current build. - Add a brief Architecture note covering the base hooks introduced in R2 and the OpenWebUI strategy split from R3. README is 315 lines (was 701).	2026-05-21 14:25:01 +02:00
Jan-Marlon Leibl	e10ce7f53a	feat: add ClaudeCodeProvider for subscription users Wraps @anthropic-ai/claude-agent-sdk so Claude Pro/Max subscribers (who do not have a console API key) can use this library by authenticating through the local `claude` CLI. Subscribers run `claude login` once and the provider picks up the credentials automatically. Provider behavior: - query() is invoked in single-turn mode (maxTurns: 1, allowedTools: []) to behave as plain text completion by default. Both knobs are configurable for agentic use cases. - Conversation history is flattened to a single prompt with role labels. - doStream() emits text deltas as the SDK yields successive assistant messages. doComplete() accumulates and returns the final result. - SDKAssistantMessageError codes (authentication_failed, billing_error, rate_limit, model_not_found, ...) map to AIErrorType variants. - ClaudeCodeConfig.apiKey is optional — when omitted the SDK falls back to ANTHROPIC_API_KEY or local subscription credentials. The base validator is overridden to allow this. Tradeoffs: - Requires the `claude` CLI installed and logged in on the host. This is not suitable for typical server-side production deployments; it is the official path for subscription accounts. - Higher latency (CLI process spawn) than the direct Anthropic API. - The agent SDK is heavy. Bundle grows ~750KB; bun build now uses --target node so the SDK's Node built-in imports resolve correctly. Wired into PROVIDER_REGISTRY ('claude-code'), createClaudeCodeProvider, SUPPORTED_PROVIDERS, and re-exported from the package entry.	2026-05-21 14:16:11 +02:00