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

- Replace planned features with actual working code examples
- Add clear provider comparison table
- Show real imports and usage patterns
- Include streaming, thinking, and tool calling examples
- Update supported models to match current implementation

packages/ai/README.md

@@ -1,18 +1,6 @@
 # @mariozechner/ai
 
-Unified API for OpenAI, Anthropic, and Google Gemini LLM providers. This package provides a common interface for working with multiple LLM providers, handling their differences transparently while exposing a consistent, minimal API.
+Unified API for OpenAI, Anthropic, and Google Gemini LLM providers with streaming, tool calling, and thinking support.
-
-## Features (Planned)
-
-- **Unified Interface**: Single API for OpenAI, Anthropic, and Google Gemini
-- **Streaming Support**: Real-time response streaming with delta events
-- **Tool Calling**: Consistent tool/function calling across providers
-- **Reasoning/Thinking**: Support for reasoning tokens where available
-- **Session Management**: Serializable conversation state across providers
-- **Token Tracking**: Unified token counting (input, output, cached, reasoning)
-- **Interrupt Handling**: Graceful cancellation of requests
-- **Provider Detection**: Automatic configuration based on endpoint
-- **Caching Support**: Provider-specific caching strategies
 
 ## Installation
 
@@ -20,38 +8,75 @@ Unified API for OpenAI, Anthropic, and Google Gemini LLM providers. This package
 npm install @mariozechner/ai
 ```
 
-## Quick Start (Coming Soon)
+## Quick Start
 
 ```typescript
-import { createClient } from '@mariozechner/ai';
+import { AnthropicLLM } from '@mariozechner/ai/providers/anthropic';
+import { OpenAICompletionsLLM } from '@mariozechner/ai/providers/openai-completions';
+import { GeminiLLM } from '@mariozechner/ai/providers/gemini';
 
-// Automatically detects provider from configuration
+// Pick your provider - same API for all
-const client = createClient({
+const llm = new AnthropicLLM('claude-3-5-sonnet-20241022');
-  provider: 'openai',
+// const llm = new OpenAICompletionsLLM('gpt-4o');
-  apiKey: process.env.OPENAI_API_KEY,
+// const llm = new GeminiLLM('gemini-2.0-flash-exp');
-  model: 'gpt-4'
+
+// Basic completion
+const response = await llm.complete({
+  messages: [{ role: 'user', content: 'Hello!' }]
+});
+console.log(response.content);
+
+// Streaming with thinking
+const streamResponse = await llm.complete({
+  messages: [{ role: 'user', content: 'Explain quantum computing' }]
+}, {
+  onText: (chunk) => process.stdout.write(chunk),
+  onThinking: (chunk) => process.stderr.write(chunk),
+  thinking: { enabled: true }
 });
 
-// Same API works for all providers
+// Tool calling
-const response = await client.complete({
+const tools = [{
-  messages: [
+  name: 'calculator',
-    { role: 'user', content: 'Hello!' }
+  description: 'Perform calculations',
-  ],
+  parameters: {
-  stream: true
+    type: 'object',
+    properties: {
+      expression: { type: 'string' }
+    },
+    required: ['expression']
+  }
+}];
+
+const toolResponse = await llm.complete({
+  messages: [{ role: 'user', content: 'What is 15 * 27?' }],
+  tools
 });
 
-for await (const event of response) {
+if (toolResponse.toolCalls) {
-  if (event.type === 'content') {
+  for (const call of toolResponse.toolCalls) {
-    process.stdout.write(event.text);
+    console.log(`Tool: ${call.name}, Args:`, call.arguments);
   }
 }
 ```
 
-## Supported Providers
+## Features
 
-- **OpenAI**: GPT-3.5, GPT-4, o1, o3 models
+- **Unified Interface**: Same API across OpenAI, Anthropic, and Gemini
-- **Anthropic**: Claude models via native SDK
+- **Streaming**: Real-time text and thinking streams with completion signals
-- **Google Gemini**: Gemini models with thinking support
+- **Tool Calling**: Consistent function calling with automatic ID generation
+- **Thinking Mode**: Access reasoning tokens (o1, Claude, Gemini 2.0)
+- **Token Tracking**: Input, output, cache, and thinking token counts
+- **Error Handling**: Graceful fallbacks with detailed error messages
+
+## Providers
+
+| Provider | Models | Thinking | Tools | Streaming |
+|----------|--------|----------|-------|-----------|
+| OpenAI Completions | gpt-4o, gpt-4o-mini | ❌ | ✅ | ✅ |
+| OpenAI Responses | o1, o3, gpt-5 | ✅ | ✅ | ✅ |
+| Anthropic | claude-3.5-sonnet, claude-3.5-haiku | ✅ | ✅ | ✅ |
+| Gemini | gemini-2.0-flash, gemini-2.0-pro | ✅ | ✅ | ✅ |
 
 ## Development