feat: replace separate provider/model fields with unified format

README.md

@@ -75,8 +75,7 @@ curl -X POST http://localhost:8080/providers \
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "Hello from Bifrost! 🌈"}
     ]

docs/mcp.md

@@ -33,8 +33,7 @@ Bifrost's Model Context Protocol integration enables AI models to seamlessly dis
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "List the files in the /tmp directory"}
     ]

docs/quickstart/http-transport.md

@@ -132,8 +132,7 @@ docker run -p 8080:8080 maximhq/bifrost
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Hello, Bifrost!"}]
   }'
 ```
@@ -242,12 +241,12 @@ export ANTHROPIC_API_KEY="your-anthropic-key"
 # Use OpenAI
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"provider": "openai", "model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello from OpenAI!"}]}'
+  -d '{"model": "openai/gpt-4o-mini", "messages": [{"role": "user", "content": "Hello from OpenAI!"}]}'
 
 # Use Anthropic
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"provider": "anthropic", "model": "claude-3-sonnet-20240229", "messages": [{"role": "user", "content": "Hello from Anthropic!"}]}'
+  -d '{"model": "anthropic/claude-3-sonnet-20240229", "messages": [{"role": "user", "content": "Hello from Anthropic!"}]}'
 ```
 
 ### **🔄 Add Automatic Fallbacks**
@@ -257,10 +256,9 @@ curl -X POST http://localhost:8080/v1/chat/completions \
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Hello!"}],
-    "fallbacks": [{"provider": "anthropic", "model": "claude-3-sonnet-20240229"}]
+    "fallbacks": ["anthropic/claude-3-sonnet-20240229"]
   }'
 ```
 
@@ -276,8 +274,7 @@ import requests
 response = requests.post(
     "http://localhost:8080/v1/chat/completions",
     json={
-        "provider": "openai",
-        "model": "gpt-4o-mini",
+        "model": "openai/gpt-4o-mini",
         "messages": [{"role": "user", "content": "Hello from Python!"}]
     }
 )
@@ -291,8 +288,7 @@ const response = await fetch("http://localhost:8080/v1/chat/completions", {
   method: "POST",
   headers: { "Content-Type": "application/json" },
   body: JSON.stringify({
-    provider: "openai",
-    model: "gpt-4o-mini",
+    model: "openai/gpt-4o-mini",
     messages: [{ role: "user", content: "Hello from Node.js!" }],
   }),
 });
@@ -306,8 +302,7 @@ response, err := http.Post(
     "http://localhost:8080/v1/chat/completions",
     "application/json",
     strings.NewReader(`{
-        "provider": "openai",
-        "model": "gpt-4o-mini",
+        "model": "openai/gpt-4o-mini",
         "messages": [{"role": "user", "content": "Hello from Go!"}]
     }`)
 )

docs/usage/errors.md

@@ -221,8 +221,7 @@ client = BifrostClient("http://localhost:8080")
 
 try:
     response = client.chat_completion({
-        "provider": "openai",
-        "model": "gpt-4o-mini",
+        "model": "openai/gpt-4o-mini",
         "messages": [{"role": "user", "content": "Hello!"}]
     })
     print("Success:", response)

docs/usage/http-transport/README.md

@@ -28,7 +28,7 @@ open http://localhost:8080
 # Make requests to any provider
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"provider": "openai", "model": "gpt-4o-mini", "messages": [...]}'
+  -d '{"model": "openai/gpt-4o-mini", "messages": [...]}'
 ```
 
 ---
@@ -171,10 +171,9 @@ const response = await openai.chat.completions.create({
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Hello!"}],
-    "fallbacks": [{"provider": "anthropic", "model": "claude-3-sonnet-20240229"}]
+    "fallbacks": ["anthropic/claude-3-sonnet-20240229"]
   }'
 
 # OpenAI-compatible endpoint

docs/usage/http-transport/configuration/mcp.md

@@ -209,8 +209,7 @@ Tools are automatically available in chat completions:
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "List the files in the current directory"}
     ]
@@ -269,8 +268,7 @@ When MCP is configured, Bifrost automatically adds available tools to requests.
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "Can you list the files in the /tmp directory?"}
     ]
@@ -337,8 +335,7 @@ curl -X POST http://localhost:8080/v1/mcp/tool/execute \
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "Can you list the files in the /tmp directory?"},
       {
@@ -394,8 +391,7 @@ Control which MCP tools are available per request using context:
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "List files and search web"}
     ],
@@ -407,8 +403,7 @@ curl -X POST http://localhost:8080/v1/chat/completions \
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "Help me with file operations"}
     ],
@@ -479,8 +474,7 @@ bifrost-http -config config.json -port 8080 -plugins maxim
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "What files are in this directory?"}
     ]
@@ -563,8 +557,7 @@ docker logs bifrost-container | grep MCP
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {
         "role": "user",

docs/usage/http-transport/configuration/providers.md

@@ -497,20 +497,18 @@ docker run -p 8080:8080 \
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Test message"}]
   }'
 
 # Test with fallbacks
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Test message"}],
     "fallbacks": [
-      {"provider": "anthropic", "model": "claude-3-sonnet-20240229"}
+      "anthropic/claude-3-sonnet-20240229"
     ]
   }'
 ```

docs/usage/http-transport/endpoints.md

@@ -31,8 +31,7 @@ Chat conversation endpoint supporting all providers.
 
 ```json
 {
-  "provider": "openai",
-  "model": "gpt-4o-mini",
+  "model": "openai/gpt-4o-mini",
   "messages": [
     {
       "role": "user",
@@ -43,12 +42,7 @@ Chat conversation endpoint supporting all providers.
     "temperature": 0.7,
     "max_tokens": 1000
   },
-  "fallbacks": [
-    {
-      "provider": "anthropic",
-      "model": "claude-3-sonnet-20240229"
-    }
-  ]
+  "fallbacks": ["anthropic/claude-3-sonnet-20240229"]
 }
 ```
 
@@ -83,8 +77,7 @@ Chat conversation endpoint supporting all providers.
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "What is the capital of France?"}
     ]
@@ -99,8 +92,7 @@ Text completion endpoint for simple text generation.
 
 ```json
 {
-  "provider": "openai",
-  "model": "gpt-4o-mini",
+  "model": "openai/gpt-4o-mini",
   "text": "The future of AI is",
   "params": {
     "temperature": 0.8,
@@ -254,12 +246,11 @@ bifrost_provider_errors_total{provider="openai",error_type="rate_limit"} 23
 
 ### **Common Parameters**
 
-| Parameter   | Type   | Description             | Example                       |
-| ----------- | ------ | ----------------------- | ----------------------------- |
-| `provider`  | string | AI provider to use      | `"openai"`                    |
-| `model`     | string | Model name              | `"gpt-4o-mini"`               |
-| `params`    | object | Model parameters        | `{"temperature": 0.7}`        |
-| `fallbacks` | array  | Fallback configurations | `[{"provider": "anthropic"}]` |
+| Parameter   | Type   | Description             | Example                                  |
+| ----------- | ------ | ----------------------- | ---------------------------------------- |
+| `model`     | string | Provider and model name | `"openai/gpt-4o-mini"`                   |
+| `params`    | object | Model parameters        | `{"temperature": 0.7}`                   |
+| `fallbacks` | array  | Fallback model names    | `["anthropic/claude-3-sonnet-20240229"]` |
 
 ### **Model Parameters**
 
@@ -315,8 +306,7 @@ MCP tools are automatically available in chat completions:
 curl -X POST http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "List files in the current directory"}
     ]
@@ -354,8 +344,7 @@ curl -X POST http://localhost:8080/v1/chat/completions \
 # Initial request
 curl -X POST http://localhost:8080/v1/chat/completions \
   -d '{
-    "provider": "openai",
-    "model": "gpt-4o-mini",
+    "model": "openai/gpt-4o-mini",
     "messages": [
       {"role": "user", "content": "Read the README.md file"},
       {