promptgun 1.4.1 → 1.4.3

package/README.md

@@ -117,6 +117,32 @@ You can also avoid writing a file altogether and get the byte array directly:
 const byteArray = await ai.image('A black hole')
 ```
 
+## System and User Prompts
+
+By default, `.chat()` with a string creates a user message. To add system instructions, pass message objects:
+
+```typescript
+const response = await ai
+  .chat(
+    {system: 'You are a helpful assistant that speaks like a pirate'},
+    {user: 'Tell me about the weather'}
+  )
+```
+
+This works with structured output too:
+
+```typescript
+const response = await ai
+  .chat(
+    {system: 'You are a JSON API that returns restaurant data'},
+    {user: 'I want Italian restaurants in Rome'}
+  )
+  .getObject(o => o
+    .hasString('name')
+    .hasString('address')
+  )
+```
+
 ## Conversations
 With `ai.createConversation()` you can create a dedicated client
 for a single conversation. Every prompt you do gets appended
@@ -300,14 +326,15 @@ const user = await ai
 
 ## Model Selection
 
-Switch models using either a string or the `AiModel` enum:
-
+By default, Promptgun uses GPT-5. Switch models using either a string:
 ```typescript
 // Using a string
 const result = await ai
   .chat('Hello')
   .model('gpt-5')
-
+```
+or the `AiModel` enum:
+```typescript
 // Using the enum - get in-place documentation!
 const result = await ai
   .chat('Hello')

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "promptgun",
-	"version": "1.4.1",
+	"version": "1.4.3",
 	"type": "module",
 	"exports": "./build/index.js",
 	"types": "./build/index.d.ts",