Update AGENT_USAGE.md

AGENT_USAGE.md

@@ -19,12 +19,19 @@ All endpoints below are relative to this base URL.
 - **Path**: `/chat`
 - **Description**: General chat/completions endpoint, similar to OpenAI Chat Completions.
 
-**Request JSON:**
+**Request JSON (with optional system prompt):**
 
 ```json
 {
   "messages": [
-    { "role": "user", "content": "Your question here" }
+    {
+      "role": "system",
+      "content": "You are a helpful assistant that answers briefly."
+    },
+    {
+      "role": "user",
+      "content": "Your question here"
+    }
   ],
   "temperature": 1.0,
   "top_p": 1.0,
@@ -34,7 +41,8 @@ All endpoints below are relative to this base URL.
 
 - `messages`:
   - Array of objects with `role` (`"user"`, `"assistant"`, `"system"`) and `content` (string).
-  - The agent should include conversation history if it wants the model to be aware of context.
+  - Include one or more **`system` messages at the start** to control behavior (system prompting).
+  - Append `user` and `assistant` messages to maintain conversation history.
 - `temperature`, `top_p`, `max_tokens` are optional; if omitted, defaults are used.
 
 **Response JSON:**