Update documentation and add README synchronization

.gitignore

@@ -33,3 +33,5 @@ go.work.sum
 
 node_modules/
 dist/
+
+__pycache__/

README.md

@@ -2,7 +2,7 @@
 
 ![Build and Release](https://github.com/lordmathis/llamactl/actions/workflows/release.yaml/badge.svg) ![Go Tests](https://github.com/lordmathis/llamactl/actions/workflows/go_test.yaml/badge.svg) ![WebUI Tests](https://github.com/lordmathis/llamactl/actions/workflows/webui_test.yaml/badge.svg)
 
-**Unified management and routing for llama.cpp and MLX models with web dashboard.**
+**Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.**
 
 ## Features
 
@@ -12,7 +12,7 @@
 - **State Persistence**: Ensure instances remain intact across server restarts
 
 ### 🔗 Universal Compatibility
-- **OpenAI API Compatible**: Drop-in replacement - route requests by model name
+- **OpenAI API Compatible**: Drop-in replacement - route requests by instance name
 - **Multi-Backend Support**: Native support for llama.cpp, MLX (Apple Silicon optimized), and vLLM
 
 ### 🌐 User-Friendly Interface

docs/index.md

@@ -1,24 +1,16 @@
 # Llamactl Documentation
 
-Welcome to the Llamactl documentation! **Management server and proxy for multiple llama.cpp and MLX instances with OpenAI-compatible API routing.**
+Welcome to the Llamactl documentation!  
 
 ![Dashboard Screenshot](images/dashboard.png)
 
 ## What is Llamactl?
 
-Llamactl is designed to simplify the deployment and management of llama-server and MLX instances. It provides a modern solution for running multiple large language models with centralized management and multi-backend support.
+**{{HEADLINE}}**
 
 ## Features
 
-🚀 **Multiple Model Serving**: Run different models simultaneously (7B for speed, 70B for quality)
+{{FEATURES}}  
-🔗 **OpenAI API Compatible**: Drop-in replacement - route requests by model name
-🍎 **Multi-Backend Support**: Native support for both llama.cpp and MLX (Apple Silicon optimized)
-🌐 **Web Dashboard**: Modern React UI for visual management (unlike CLI-only tools)
-🔐 **API Key Authentication**: Separate keys for management vs inference access
-📊 **Instance Monitoring**: Health checks, auto-restart, log management
-⚡ **Smart Resource Management**: Idle timeout, LRU eviction, and configurable instance limits
-💡 **On-Demand Instance Start**: Automatically launch instances upon receiving OpenAI-compatible API requests
-💾 **State Persistence**: Ensure instances remain intact across server restarts  
 
 ## Quick Links
 

docs/readme_sync.py

@@ -0,0 +1,59 @@
+"""
+MkDocs hook to sync content from README.md to docs/index.md
+"""
+import re
+import os
+
+
+def on_page_markdown(markdown, page, config, **kwargs):
+    """Process markdown content before rendering"""
+    # Only process the index.md file
+    if page.file.src_path != 'index.md':
+        return markdown
+
+    # Get the path to README.md (relative to mkdocs.yml)
+    readme_path = os.path.join(os.path.dirname(config['config_file_path']), 'README.md')
+
+    if not os.path.exists(readme_path):
+        print(f"Warning: README.md not found at {readme_path}")
+        return markdown
+
+    try:
+        with open(readme_path, 'r', encoding='utf-8') as f:
+            readme_content = f.read()
+    except Exception as e:
+        print(f"Error reading README.md: {e}")
+        return markdown
+
+    # Extract headline (the text in bold after the title)
+    headline_match = re.search(r'\*\*(.*?)\*\*', readme_content)
+    headline = headline_match.group(1) if headline_match else 'Management server for llama.cpp and MLX instances'
+
+    # Extract features section - everything between ## Features and the next ## heading
+    features_match = re.search(r'## Features\n(.*?)(?=\n## |\Z)', readme_content, re.DOTALL)
+    if features_match:
+        features_content = features_match.group(1).strip()
+        # Just add line breaks at the end of each line for proper MkDocs rendering
+        features_with_breaks = add_line_breaks(features_content)
+    else:
+        features_with_breaks = "Features content not found in README.md"
+
+    # Replace placeholders in the markdown
+    markdown = markdown.replace('{{HEADLINE}}', headline)
+    markdown = markdown.replace('{{FEATURES}}', features_with_breaks)
+
+    return markdown
+
+
+def add_line_breaks(content):
+    """Add two spaces at the end of each line for proper MkDocs line breaks"""
+    lines = content.split('\n')
+    processed_lines = []
+
+    for line in lines:
+        if line.strip():  # Only add spaces to non-empty lines
+            processed_lines.append(line.rstrip() + '  ')
+        else:
+            processed_lines.append(line)
+
+    return '\n'.join(processed_lines)

docs/user-guide/api-reference.md

@@ -310,7 +310,7 @@ POST /v1/reranking
 The server routes requests to the appropriate instance based on the `model` field in the request body. Instances with on-demand starting enabled will be automatically started if not running. For configuration details, see [Managing Instances](managing-instances.md).
 
 **Error Responses:**
-- `400 Bad Request`: Invalid request body or missing model name
+- `400 Bad Request`: Invalid request body or missing instance name
 - `503 Service Unavailable`: Instance is not running and on-demand start is disabled
 - `409 Conflict`: Cannot start instance due to maximum instances limit
 

mkdocs.yml

@@ -67,6 +67,9 @@ plugins:
       javascript_dir: js
       canonical_version: null
 
+hooks:
+  - docs/readme_sync.py
+
 extra:
   version:
     provider: mike

pkg/server/handlers.go

@@ -551,7 +551,7 @@ func (h *Handler) OpenAIListInstances() http.HandlerFunc {
 // @Accept json
 // @Produces json
 // @Success 200 "OpenAI response"
-// @Failure 400 {string} string "Invalid request body or model name"
+// @Failure 400 {string} string "Invalid request body or instance name"
 // @Failure 500 {string} string "Internal Server Error"
 // @Router /v1/ [post]
 func (h *Handler) OpenAIProxy() http.HandlerFunc {
@@ -564,7 +564,7 @@ func (h *Handler) OpenAIProxy() http.HandlerFunc {
 		}
 		r.Body.Close()
 
-		// Parse the body to extract model name
+		// Parse the body to extract instance name
 		var requestBody map[string]any
 		if err := json.Unmarshal(bodyBytes, &requestBody); err != nil {
 			http.Error(w, "Invalid request body", http.StatusBadRequest)
@@ -573,11 +573,11 @@ func (h *Handler) OpenAIProxy() http.HandlerFunc {
 
 		modelName, ok := requestBody["model"].(string)
 		if !ok || modelName == "" {
-			http.Error(w, "Model name is required", http.StatusBadRequest)
+			http.Error(w, "Instance name is required", http.StatusBadRequest)
 			return
 		}
 
-		// Route to the appropriate inst based on model name
+		// Route to the appropriate inst based on instance name
 		inst, err := h.InstanceManager.GetInstance(modelName)
 		if err != nil {
 			http.Error(w, "Failed to get instance: "+err.Error(), http.StatusInternalServerError)