feat: Add deployment configs and API documentation

.gitignore

@@ -4,8 +4,12 @@ cli-proxy-api
 
 # Configuration
 config.yaml
+config.prod.yaml
 .env
 
+# Auth credentials (sensitive)
+auth-credentials/
+
 # Generated content
 bin/*
 logs/*

API_DOCUMENTATION.md

@@ -0,0 +1,1012 @@
+# CLIProxyAPI - Complete API Documentation
+
+> **Last Updated:** December 31, 2025
+
+---
+
+## 🌐 API Endpoint
+
+```
+https://creative-magic-production-22f0.up.railway.app
+```
+api key: sk-cItvhSBsi7KWnTDZqfFX5gzuVURodOL8pPj1CbyJreAk3HYG
+
+✅ **This is a permanent URL** - Your API is deployed to Fly.io and runs 24/7!
+
+**Local Endpoint (for development):**
+```
+http://localhost:8317
+```
+
+---
+
+## 🔐 Authentication
+
+All API requests require an API key in the `Authorization` header.
+
+### Available API Keys
+
+| API Key | Description |
+|---------|-------------|
+| `test-api-key-1` | Primary test key |
+| `test-api-key-2` | Secondary test key |
+| `test-api-key-3` | Tertiary test key |
+| `new-test-key` | Additional test key |
+
+### Authentication Header
+
+```
+Authorization: Bearer YOUR_API_KEY
+```
+
+---
+
+## 📚 API Endpoints
+
+### 1. List Models
+
+Returns a list of all available models.
+
+**Endpoint:** `GET /v1/models`
+
+**Example:**
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/models \
+  -H "Authorization: Bearer test-api-key-1"
+```
+
+**Response:**
+```json
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "gemini-2.5-pro",
+      "object": "model",
+      "created": 1750118400,
+      "owned_by": "google"
+    },
+    ...
+  ]
+}
+```
+
+---
+
+### 2. Chat Completions
+
+Create a chat completion with any available model.
+
+**Endpoint:** `POST /v1/chat/completions`
+
+**Request Body:**
+```json
+{
+  "model": "model-name",
+  "messages": [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Your message here"}
+  ],
+  "max_tokens": 1000,
+  "temperature": 0.7,
+  "stream": false
+}
+```
+
+**Parameters:**
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `model` | string | ✅ | Model ID to use |
+| `messages` | array | ✅ | Array of message objects |
+| `max_tokens` | integer | ❌ | Maximum tokens in response |
+| `temperature` | float | ❌ | Sampling temperature (0-2) |
+| `stream` | boolean | ❌ | Enable streaming responses |
+| `top_p` | float | ❌ | Nucleus sampling parameter |
+
+---
+
+## 🤖 Available Models (35 Total)
+
+---
+
+## Google Models
+
+### gemini-2.5-pro
+**Provider:** Google | **Type:** Chat/Reasoning
+
+The flagship Gemini 2.5 Pro model with advanced reasoning capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-2.5-pro",
+    "messages": [{"role": "user", "content": "Explain quantum computing in simple terms"}],
+    "max_tokens": 1000
+  }'
+```
+
+**Python Example:**
+```python
+import requests
+
+response = requests.post(
+    "https://creative-magic-production-22f0.up.railway.app/v1/chat/completions",
+    headers={
+        "Authorization": "Bearer test-api-key-1",
+        "Content-Type": "application/json"
+    },
+    json={
+        "model": "gemini-2.5-pro",
+        "messages": [{"role": "user", "content": "Explain quantum computing in simple terms"}],
+        "max_tokens": 1000
+    }
+)
+print(response.json())
+```
+
+---
+
+## Antigravity Models
+
+### gemini-2.5-flash
+**Provider:** Antigravity | **Type:** Fast Chat
+
+Fast and efficient Gemini 2.5 Flash model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-2.5-flash",
+    "messages": [{"role": "user", "content": "Write a haiku about coding"}],
+    "max_tokens": 100
+  }'
+```
+
+---
+
+### gemini-2.5-flash-lite
+**Provider:** Antigravity | **Type:** Lightweight Chat
+
+Lightweight version of Gemini 2.5 Flash for cost-effective usage.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-2.5-flash-lite",
+    "messages": [{"role": "user", "content": "What is 2+2?"}],
+    "max_tokens": 50
+  }'
+```
+
+---
+
+### gemini-2.5-computer-use-preview-10-2025
+**Provider:** Antigravity | **Type:** Computer Use
+
+Gemini model with computer use capabilities for automation tasks.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-2.5-computer-use-preview-10-2025",
+    "messages": [{"role": "user", "content": "Describe how to automate a web form submission"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### gemini-3-pro-preview
+**Provider:** Antigravity | **Type:** Next-Gen Chat
+
+Preview of the next-generation Gemini 3 Pro model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-3-pro-preview",
+    "messages": [{"role": "user", "content": "Write a complex algorithm to solve the traveling salesman problem"}],
+    "max_tokens": 2000
+  }'
+```
+
+---
+
+### gemini-3-flash-preview
+**Provider:** Antigravity | **Type:** Next-Gen Fast Chat
+
+Preview of the next-generation Gemini 3 Flash model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-3-flash-preview",
+    "messages": [{"role": "user", "content": "Summarize the benefits of renewable energy"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### gemini-3-pro-image-preview
+**Provider:** Antigravity | **Type:** Vision/Image
+
+Gemini 3 Pro with image generation and understanding capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-3-pro-image-preview",
+    "messages": [{"role": "user", "content": "Describe what an AI-generated landscape would look like"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### gemini-claude-sonnet-4-5
+**Provider:** Antigravity | **Type:** Hybrid Chat
+
+Hybrid model combining Gemini and Claude Sonnet 4.5 capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-claude-sonnet-4-5",
+    "messages": [{"role": "user", "content": "Write a professional email to a client"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### gemini-claude-sonnet-4-5-thinking
+**Provider:** Antigravity | **Type:** Hybrid Reasoning
+
+Hybrid model with extended thinking/reasoning capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-claude-sonnet-4-5-thinking",
+    "messages": [{"role": "user", "content": "Solve this logic puzzle: If all bloops are razzles and all razzles are lazzles, are all bloops lazzles?"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### gemini-claude-opus-4-5-thinking
+**Provider:** Antigravity | **Type:** Premium Hybrid Reasoning
+
+Premium hybrid model with Opus-level reasoning capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-claude-opus-4-5-thinking",
+    "messages": [{"role": "user", "content": "Analyze the philosophical implications of artificial consciousness"}],
+    "max_tokens": 2000
+  }'
+```
+
+---
+
+### gpt-oss-120b-medium
+**Provider:** Antigravity | **Type:** Open Source LLM
+
+120 billion parameter open-source style model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-oss-120b-medium",
+    "messages": [{"role": "user", "content": "Explain the difference between supervised and unsupervised learning"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+## Qwen Models
+
+### qwen3-32b
+**Provider:** IFlow | **Type:** Chat
+
+Qwen 3 32B parameter model for general chat.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-32b",
+    "messages": [{"role": "user", "content": "Translate this to Chinese: Hello, how are you?"}],
+    "max_tokens": 100
+  }'
+```
+
+---
+
+### qwen3-235b
+**Provider:** IFlow | **Type:** Large Chat
+
+Qwen 3 235B parameter flagship model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-235b",
+    "messages": [{"role": "user", "content": "Write a detailed business plan for a tech startup"}],
+    "max_tokens": 2000
+  }'
+```
+
+---
+
+### qwen3-235b-a22b-instruct
+**Provider:** IFlow | **Type:** Instruction-Tuned
+
+Qwen 3 235B with instruction tuning for better task following.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-235b-a22b-instruct",
+    "messages": [
+      {"role": "system", "content": "You are a helpful coding assistant."},
+      {"role": "user", "content": "Write a Python function to calculate factorial"}
+    ],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### qwen3-235b-a22b-thinking-2507
+**Provider:** IFlow | **Type:** Reasoning
+
+Qwen 3 235B with enhanced thinking/reasoning capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-235b-a22b-thinking-2507",
+    "messages": [{"role": "user", "content": "Solve step by step: What is 17 * 23 + 45 / 9?"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### qwen3-max
+**Provider:** IFlow | **Type:** Maximum Performance
+
+Qwen 3 Max - highest performance configuration.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-max",
+    "messages": [{"role": "user", "content": "Write a comprehensive essay on climate change"}],
+    "max_tokens": 3000
+  }'
+```
+
+---
+
+### qwen3-max-preview
+**Provider:** IFlow | **Type:** Preview
+
+Preview version of Qwen 3 Max with latest features.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-max-preview",
+    "messages": [{"role": "user", "content": "What are the latest trends in AI?"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### qwen3-vl-plus
+**Provider:** IFlow | **Type:** Vision-Language
+
+Qwen 3 Vision-Language model for multimodal tasks.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-vl-plus",
+    "messages": [{"role": "user", "content": "Describe how image recognition works"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### qwen3-coder-plus
+**Provider:** Qwen | **Type:** Code Generation
+
+Specialized coding model for advanced programming tasks.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-coder-plus",
+    "messages": [
+      {"role": "system", "content": "You are an expert programmer."},
+      {"role": "user", "content": "Write a REST API in Python using FastAPI with CRUD operations"}
+    ],
+    "max_tokens": 2000
+  }'
+```
+
+---
+
+### qwen3-coder-flash
+**Provider:** Qwen | **Type:** Fast Code Generation
+
+Fast coding model for quick code generation tasks.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "qwen3-coder-flash",
+    "messages": [{"role": "user", "content": "Write a JavaScript function to reverse a string"}],
+    "max_tokens": 300
+  }'
+```
+
+---
+
+### vision-model
+**Provider:** Qwen | **Type:** Vision
+
+Dedicated vision model for image understanding.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "vision-model",
+    "messages": [{"role": "user", "content": "Explain computer vision techniques"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+## DeepSeek Models
+
+### deepseek-r1
+**Provider:** IFlow | **Type:** Reasoning
+
+DeepSeek R1 reasoning model for complex problem solving.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-r1",
+    "messages": [{"role": "user", "content": "Prove that the square root of 2 is irrational"}],
+    "max_tokens": 1500
+  }'
+```
+
+---
+
+### deepseek-v3
+**Provider:** IFlow | **Type:** Chat
+
+DeepSeek V3 general chat model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-v3",
+    "messages": [{"role": "user", "content": "Explain blockchain technology"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### deepseek-v3.1
+**Provider:** IFlow | **Type:** Improved Chat
+
+DeepSeek V3.1 with improved capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-v3.1",
+    "messages": [{"role": "user", "content": "Compare SQL and NoSQL databases"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### deepseek-v3.2
+**Provider:** IFlow | **Type:** Latest Chat
+
+DeepSeek V3.2 latest version with enhanced performance.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-v3.2",
+    "messages": [{"role": "user", "content": "Write a microservices architecture design"}],
+    "max_tokens": 1500
+  }'
+```
+
+---
+
+### deepseek-v3.2-chat
+**Provider:** IFlow | **Type:** Conversational
+
+DeepSeek V3.2 optimized for conversational interactions.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-v3.2-chat",
+    "messages": [
+      {"role": "user", "content": "Hi! Can you help me learn Python?"},
+      {"role": "assistant", "content": "Of course! I would be happy to help you learn Python. Where would you like to start?"},
+      {"role": "user", "content": "Let us start with variables and data types"}
+    ],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### deepseek-v3.2-reasoner
+**Provider:** IFlow | **Type:** Advanced Reasoning
+
+DeepSeek V3.2 with specialized reasoning capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "deepseek-v3.2-reasoner",
+    "messages": [{"role": "user", "content": "A farmer has 17 sheep. All but 9 die. How many are left?"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+## Kimi Models
+
+### kimi-k2
+**Provider:** IFlow | **Type:** Chat
+
+Kimi K2 general purpose model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "kimi-k2",
+    "messages": [{"role": "user", "content": "Write a poem about the ocean"}],
+    "max_tokens": 300
+  }'
+```
+
+---
+
+### kimi-k2-0905
+**Provider:** IFlow | **Type:** Updated Chat
+
+Kimi K2 September 2025 update with improvements.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "kimi-k2-0905",
+    "messages": [{"role": "user", "content": "Summarize the key features of Python 3.12"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### kimi-k2-thinking
+**Provider:** IFlow | **Type:** Reasoning
+
+Kimi K2 with extended thinking capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "kimi-k2-thinking",
+    "messages": [{"role": "user", "content": "If I have 3 boxes, each containing 2 red balls and 3 blue balls, what is the probability of drawing a red ball from a randomly chosen box?"}],
+    "max_tokens": 800
+  }'
+```
+
+---
+
+## MiniMax Models
+
+### minimax-m2
+**Provider:** IFlow | **Type:** Chat
+
+MiniMax M2 efficient chat model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "minimax-m2",
+    "messages": [{"role": "user", "content": "Write a short story about a robot"}],
+    "max_tokens": 500
+  }'
+```
+
+---
+
+### minimax-m2.1
+**Provider:** IFlow | **Type:** Improved Chat
+
+MiniMax M2.1 with enhanced capabilities.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "minimax-m2.1",
+    "messages": [{"role": "user", "content": "Explain machine learning to a 10-year-old"}],
+    "max_tokens": 400
+  }'
+```
+
+---
+
+## GLM Models
+
+### glm-4.6
+**Provider:** IFlow | **Type:** Chat
+
+GLM 4.6 chat model from Zhipu AI.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "glm-4.6",
+    "messages": [{"role": "user", "content": "What is the history of artificial intelligence?"}],
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+### glm-4.7
+**Provider:** IFlow | **Type:** Latest Chat
+
+GLM 4.7 latest version with improved performance.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "glm-4.7",
+    "messages": [{"role": "user", "content": "Design a database schema for an e-commerce platform"}],
+    "max_tokens": 1500
+  }'
+```
+
+---
+
+## Other Models
+
+### tstars2.0
+**Provider:** IFlow | **Type:** Specialized
+
+TStars 2.0 specialized model.
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "tstars2.0",
+    "messages": [{"role": "user", "content": "What are best practices for software testing?"}],
+    "max_tokens": 800
+  }'
+```
+
+---
+
+## 🔄 Streaming Responses
+
+Enable streaming for real-time token-by-token responses:
+
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gemini-2.5-pro",
+    "messages": [{"role": "user", "content": "Write a long story about space exploration"}],
+    "max_tokens": 2000,
+    "stream": true
+  }'
+```
+
+**Python Streaming Example:**
+```python
+import requests
+
+response = requests.post(
+    "https://creative-magic-production-22f0.up.railway.app/v1/chat/completions",
+    headers={
+        "Authorization": "Bearer test-api-key-1",
+        "Content-Type": "application/json"
+    },
+    json={
+        "model": "gemini-2.5-pro",
+        "messages": [{"role": "user", "content": "Write a long story"}],
+        "stream": True
+    },
+    stream=True
+)
+
+for line in response.iter_lines():
+    if line:
+        print(line.decode('utf-8'))
+```
+
+---
+
+## 🐍 Python SDK Example
+
+```python
+import openai
+
+# Configure the client
+client = openai.OpenAI(
+    api_key="test-api-key-1",
+    base_url="https://creative-magic-production-22f0.up.railway.app/v1"
+)
+
+# Chat completion
+response = client.chat.completions.create(
+    model="gemini-2.5-pro",
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Hello!"}
+    ]
+)
+
+print(response.choices[0].message.content)
+```
+
+---
+
+## 📦 Node.js Example
+
+```javascript
+import OpenAI from 'openai';
+
+const client = new OpenAI({
+    apiKey: 'test-api-key-1',
+    baseURL: 'https://creative-magic-production-22f0.up.railway.app/v1'
+});
+
+async function main() {
+    const response = await client.chat.completions.create({
+        model: 'gemini-2.5-pro',
+        messages: [
+            { role: 'system', content: 'You are a helpful assistant.' },
+            { role: 'user', content: 'Hello!' }
+        ]
+    });
+    
+    console.log(response.choices[0].message.content);
+}
+
+main();
+```
+
+---
+
+## 🔧 cURL Quick Reference
+
+### Basic Chat
+```bash
+curl -X POST https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "MODEL_NAME", "messages": [{"role": "user", "content": "YOUR_MESSAGE"}]}'
+```
+
+### With System Prompt
+```bash
+curl -X POST https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "MODEL_NAME",
+    "messages": [
+      {"role": "system", "content": "You are a helpful assistant."},
+      {"role": "user", "content": "YOUR_MESSAGE"}
+    ]
+  }'
+```
+
+### With Temperature Control
+```bash
+curl -X POST https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "MODEL_NAME",
+    "messages": [{"role": "user", "content": "YOUR_MESSAGE"}],
+    "temperature": 0.7,
+    "max_tokens": 1000
+  }'
+```
+
+---
+
+## 📊 Model Summary Table
+
+| Model | Provider | Type | Best For |
+|-------|----------|------|----------|
+| `gemini-2.5-pro` | Google | Reasoning | Complex tasks, analysis |
+| `gemini-2.5-flash` | Antigravity | Fast | Quick responses |
+| `gemini-2.5-flash-lite` | Antigravity | Lightweight | Cost-effective |
+| `gemini-2.5-computer-use-preview-10-2025` | Antigravity | Computer Use | Automation |
+| `gemini-3-pro-preview` | Antigravity | Next-Gen | Latest features |
+| `gemini-3-flash-preview` | Antigravity | Next-Gen Fast | Fast + latest |
+| `gemini-3-pro-image-preview` | Antigravity | Vision | Image tasks |
+| `gemini-claude-sonnet-4-5` | Antigravity | Hybrid | Writing, chat |
+| `gemini-claude-sonnet-4-5-thinking` | Antigravity | Hybrid Reasoning | Complex reasoning |
+| `gemini-claude-opus-4-5-thinking` | Antigravity | Premium Reasoning | Maximum capability |
+| `gpt-oss-120b-medium` | Antigravity | Open Source | General tasks |
+| `qwen3-32b` | IFlow | Chat | General chat |
+| `qwen3-235b` | IFlow | Large | Complex tasks |
+| `qwen3-235b-a22b-instruct` | IFlow | Instruction | Task following |
+| `qwen3-235b-a22b-thinking-2507` | IFlow | Reasoning | Math, logic |
+| `qwen3-max` | IFlow | Maximum | Best performance |
+| `qwen3-max-preview` | IFlow | Preview | Latest Qwen |
+| `qwen3-vl-plus` | IFlow | Vision-Language | Multimodal |
+| `qwen3-coder-plus` | Qwen | Coding | Advanced coding |
+| `qwen3-coder-flash` | Qwen | Fast Coding | Quick code |
+| `vision-model` | Qwen | Vision | Image understanding |
+| `deepseek-r1` | IFlow | Reasoning | Math proofs |
+| `deepseek-v3` | IFlow | Chat | General |
+| `deepseek-v3.1` | IFlow | Improved | Better performance |
+| `deepseek-v3.2` | IFlow | Latest | Best DeepSeek |
+| `deepseek-v3.2-chat` | IFlow | Conversational | Dialogue |
+| `deepseek-v3.2-reasoner` | IFlow | Reasoning | Logic puzzles |
+| `kimi-k2` | IFlow | Chat | Creative writing |
+| `kimi-k2-0905` | IFlow | Updated | September update |
+| `kimi-k2-thinking` | IFlow | Reasoning | Problem solving |
+| `minimax-m2` | IFlow | Chat | Efficient |
+| `minimax-m2.1` | IFlow | Improved | Better MiniMax |
+| `glm-4.6` | IFlow | Chat | Chinese/English |
+| `glm-4.7` | IFlow | Latest | Best GLM |
+| `tstars2.0` | IFlow | Specialized | Testing focus |
+
+---
+
+## ❌ Error Handling
+
+### Common Errors
+
+| Status Code | Error | Solution |
+|-------------|-------|----------|
+| 401 | Unauthorized | Check your API key |
+| 404 | Not Found | Check endpoint URL |
+| 429 | Rate Limited | Wait and retry |
+| 500 | Server Error | Retry or try different model |
+| 503 | Service Unavailable | Model temporarily unavailable |
+
+### Error Response Format
+```json
+{
+  "error": {
+    "type": "error_type",
+    "message": "Error description"
+  }
+}
+```
+
+---
+
+## 🚀 Quick Start
+
+1. **Test the connection:**
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/models \
+  -H "Authorization: Bearer test-api-key-1"
+```
+
+2. **Make your first chat:**
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "gemini-2.5-flash", "messages": [{"role": "user", "content": "Hello!"}]}'
+```
+
+3. **Try a coding model:**
+```bash
+curl https://creative-magic-production-22f0.up.railway.app/v1/chat/completions \
+  -H "Authorization: Bearer test-api-key-1" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "qwen3-coder-plus", "messages": [{"role": "user", "content": "Write hello world in 5 languages"}]}'
+```
+
+---
+
+**Happy coding! 🎉**

Dockerfile

@@ -16,20 +16,22 @@ RUN CGO_ENABLED=0 GOOS=linux go build -ldflags="-s -w -X 'main.Version=${VERSION
 
 FROM alpine:3.22.0
 
-RUN apk add --no-cache tzdata
+RUN apk add --no-cache tzdata ca-certificates
 
-RUN mkdir /CLIProxyAPI
+RUN mkdir -p /CLIProxyAPI/auth-credentials
 
 COPY --from=builder ./app/CLIProxyAPI /CLIProxyAPI/CLIProxyAPI
 
-COPY config.example.yaml /CLIProxyAPI/config.example.yaml
+# Copy production config as config.yaml
+COPY config.prod.yaml /CLIProxyAPI/config.yaml
+
+# Copy auth credentials
+COPY auth-credentials/ /CLIProxyAPI/auth-credentials/
 
 WORKDIR /CLIProxyAPI
 
 EXPOSE 8317
 
-ENV TZ=Asia/Shanghai
-
-RUN cp /usr/share/zoneinfo/${TZ} /etc/localtime && echo "${TZ}" > /etc/timezone
+ENV TZ=UTC
 
-CMD ["./CLIProxyAPI"]
+CMD ["./CLIProxyAPI"]

Dockerfile.bak

@@ -0,0 +1,37 @@
+FROM golang:1.24-alpine AS builder
+
+WORKDIR /app
+
+COPY go.mod go.sum ./
+
+RUN go mod download
+
+COPY . .
+
+ARG VERSION=dev
+ARG COMMIT=none
+ARG BUILD_DATE=unknown
+
+RUN CGO_ENABLED=0 GOOS=linux go build -ldflags="-s -w -X 'main.Version=${VERSION}' -X 'main.Commit=${COMMIT}' -X 'main.BuildDate=${BUILD_DATE}'" -o ./CLIProxyAPI ./cmd/server/
+
+FROM alpine:3.22.0
+
+RUN apk add --no-cache tzdata ca-certificates
+
+RUN mkdir -p /CLIProxyAPI/auth-credentials
+
+COPY --from=builder ./app/CLIProxyAPI /CLIProxyAPI/CLIProxyAPI
+
+# Copy production config as config.yaml
+COPY config.prod.yaml /CLIProxyAPI/config.yaml
+
+# Copy auth credentials
+COPY auth-credentials/ /CLIProxyAPI/auth-credentials/
+
+WORKDIR /CLIProxyAPI
+
+EXPOSE 8317
+
+ENV TZ=UTC
+
+CMD ["./CLIProxyAPI"]

Dockerfile.fly

@@ -0,0 +1,37 @@
+FROM golang:1.24-alpine AS builder
+
+WORKDIR /app
+
+COPY go.mod go.sum ./
+
+RUN go mod download
+
+COPY . .
+
+ARG VERSION=dev
+ARG COMMIT=none
+ARG BUILD_DATE=unknown
+
+RUN CGO_ENABLED=0 GOOS=linux go build -ldflags="-s -w -X 'main.Version=${VERSION}' -X 'main.Commit=${COMMIT}' -X 'main.BuildDate=${BUILD_DATE}'" -o ./CLIProxyAPI ./cmd/server/
+
+FROM alpine:3.22.0
+
+RUN apk add --no-cache tzdata ca-certificates
+
+RUN mkdir -p /CLIProxyAPI/auth-credentials
+
+COPY --from=builder ./app/CLIProxyAPI /CLIProxyAPI/CLIProxyAPI
+
+# Copy production config as config.yaml
+COPY config.prod.yaml /CLIProxyAPI/config.yaml
+
+# Copy auth credentials
+COPY auth-credentials/ /CLIProxyAPI/auth-credentials/
+
+WORKDIR /CLIProxyAPI
+
+EXPOSE 8317
+
+ENV TZ=UTC
+
+CMD ["./CLIProxyAPI"]

README_HF.md

@@ -0,0 +1,8 @@
+---
+title: CLIProxy API
+emoji: 🚀
+colorFrom: blue
+colorTo: purple
+sdk: docker
+app_port: 8317
+---

fly.toml

@@ -0,0 +1,24 @@
+# fly.toml app configuration file generated for cliproxy-api on 2025-12-31T21:57:30+02:00
+#
+# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
+#
+
+app = 'cliproxy-api'
+primary_region = 'ams'
+
+[build]
+  dockerfile = 'Dockerfile.fly'
+
+[http_service]
+  internal_port = 8317
+  force_https = true
+  auto_stop_machines = 'stop'
+  auto_start_machines = true
+  min_machines_running = 0
+  processes = ['app']
+
+[[vm]]
+  memory = '256mb'
+  cpu_kind = 'shared'
+  cpus = 1
+  memory_mb = 256

internal/util/gemini_schema_test.go

@@ -20,14 +20,20 @@ func TestCleanJSONSchemaForAntigravity_ConstToEnum(t *testing.T) {
 		}
 	}`
 
+	// Note: The placeholder "_" property is added because the schema has properties but no required fields
+	// This is needed for Claude VALIDATED mode
 	expected := `{
 		"type": "object",
 		"properties": {
 			"kind": {
 				"type": "string",
 				"enum": ["InsightVizNode"]
+			},
+			"_": {
+				"type": "boolean"
 			}
-		}
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)
@@ -120,6 +126,7 @@ func TestCleanJSONSchemaForAntigravity_AnyOfFlattening_SmartSelection(t *testing
 		}
 	}`
 
+	// Note: The placeholder "_" property is added because the schema has properties but no required fields
 	expected := `{
 		"type": "object",
 		"properties": {
@@ -127,10 +134,14 @@ func TestCleanJSONSchemaForAntigravity_AnyOfFlattening_SmartSelection(t *testing
 				"type": "object",
 				"description": "Accepts: null | object",
 				"properties": {
-					"kind": { "type": "string" }
-				}
-			}
-		}
+					"kind": { "type": "string" },
+					"_": { "type": "boolean" }
+				},
+				"required": ["_"]
+			},
+			"_": { "type": "boolean" }
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)
@@ -150,14 +161,17 @@ func TestCleanJSONSchemaForAntigravity_OneOfFlattening(t *testing.T) {
 		}
 	}`
 
+	// Note: The placeholder "_" property is added because the schema has properties but no required fields
 	expected := `{
 		"type": "object",
 		"properties": {
 			"config": {
 				"type": "string",
 				"description": "Accepts: string | integer"
-			}
-		}
+			},
+			"_": { "type": "boolean" }
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)
@@ -213,6 +227,7 @@ func TestCleanJSONSchemaForAntigravity_RefHandling(t *testing.T) {
 	}`
 
 	// After $ref is converted to placeholder object, empty schema placeholder is also added
+	// Note: The top-level also gets "_" placeholder because it has properties but no required fields
 	expected := `{
 		"type": "object",
 		"properties": {
@@ -226,8 +241,10 @@ func TestCleanJSONSchemaForAntigravity_RefHandling(t *testing.T) {
 					}
 				},
 				"required": ["reason"]
-			}
-		}
+			},
+			"_": { "type": "boolean" }
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)
@@ -254,6 +271,7 @@ func TestCleanJSONSchemaForAntigravity_RefHandling_DescriptionEscaping(t *testin
 	}`
 
 	// After $ref is converted, empty schema placeholder is also added
+	// Note: The top-level also gets "_" placeholder because it has properties but no required fields
 	expected := `{
 		"type": "object",
 		"properties": {
@@ -267,8 +285,10 @@ func TestCleanJSONSchemaForAntigravity_RefHandling_DescriptionEscaping(t *testin
 					}
 				},
 				"required": ["reason"]
-			}
-		}
+			},
+			"_": { "type": "boolean" }
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)
@@ -562,14 +582,17 @@ func TestCleanJSONSchemaForAntigravity_AnyOfFlattening_PreservesDescription(t *t
 		}
 	}`
 
+	// Note: The top-level also gets "_" placeholder because it has properties but no required fields
 	expected := `{
 		"type": "object",
 		"properties": {
 			"config": {
 				"type": "string",
 				"description": "Parent desc (Child desc) (Accepts: string | integer)"
-			}
-		}
+			},
+			"_": { "type": "boolean" }
+		},
+		"required": ["_"]
 	}`
 
 	result := CleanJSONSchemaForAntigravity(input)

internal/util/gemini_thinking.go

@@ -275,9 +275,9 @@ func ApplyDefaultThinkingIfNeeded(model string, body []byte) []byte {
 	}
 	// Gemini 3 models use thinkingLevel instead of thinkingBudget
 	if IsGemini3Model(model) {
-		// Don't set a default - let the API use its dynamic default ("high")
-		// Only set includeThoughts
-		updated, _ := sjson.SetBytes(body, "generationConfig.thinkingConfig.includeThoughts", true)
+		// Set xhigh as the default thinking level for Gemini 3 Pro models
+		updated, _ := sjson.SetBytes(body, "generationConfig.thinkingConfig.thinkingLevel", "xhigh")
+		updated, _ = sjson.SetBytes(updated, "generationConfig.thinkingConfig.includeThoughts", true)
 		return updated
 	}
 	// Gemini 2.5 and other models use thinkingBudget

render.yaml

@@ -0,0 +1,10 @@
+services:
+  - type: web
+    name: cliproxy-api
+    runtime: docker
+    dockerfilePath: ./Dockerfile.fly
+    plan: free
+    envVars:
+      - key: TZ
+        value: UTC
+    healthCheckPath: /v1/models

start-public-tunnel.ps1

@@ -0,0 +1,33 @@
+# Start CLIProxyAPI with Cloudflare Tunnel
+# This script exposes your API publicly via Cloudflare Tunnel
+
+Write-Host "Starting CLIProxyAPI with Cloudflare Tunnel..." -ForegroundColor Cyan
+Write-Host ""
+
+# Cloudflared executable path
+$cloudflared = "C:\Program Files (x86)\cloudflared\cloudflared.exe"
+
+# Check if cloudflared exists
+if (-not (Test-Path $cloudflared)) {
+    Write-Host "ERROR: cloudflared not found at $cloudflared" -ForegroundColor Red
+    Write-Host "Please install it with: winget install Cloudflare.cloudflared" -ForegroundColor Yellow
+    exit 1
+}
+
+# Start the tunnel
+Write-Host "Creating Cloudflare Tunnel to http://localhost:8317..." -ForegroundColor Green
+Write-Host "The public URL will be displayed below. Use it with your API keys:" -ForegroundColor Green
+Write-Host ""
+Write-Host "API Keys configured in config.yaml:" -ForegroundColor Yellow
+Write-Host "  - test-api-key-1" -ForegroundColor White
+Write-Host "  - test-api-key-2" -ForegroundColor White
+Write-Host "  - test-api-key-3" -ForegroundColor White
+Write-Host "  - new-test-key" -ForegroundColor White
+Write-Host ""
+Write-Host "Example usage:" -ForegroundColor Yellow
+Write-Host '  curl https://<YOUR-TUNNEL-URL>/v1/models -H "Authorization: Bearer test-api-key-1"' -ForegroundColor White
+Write-Host ""
+Write-Host "Press Ctrl+C to stop the tunnel." -ForegroundColor Cyan
+Write-Host "==========================================" -ForegroundColor Cyan
+
+& $cloudflared tunnel --url http://localhost:8317 --protocol http2