@mindstudio-ai/agent 0.0.2 → 0.0.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -20,25 +20,25 @@ import { MindStudioAgent } from '@mindstudio-ai/agent';
20
20
  const agent = new MindStudioAgent({ apiKey: 'your-api-key' });
21
21
 
22
22
  // Generate an image
23
- const { output } = await agent.generateImage({
23
+ const { imageUrl } = await agent.generateImage({
24
24
  prompt: 'A mountain landscape at sunset',
25
25
  mode: 'background',
26
26
  });
27
- console.log(output.imageUrl);
27
+ console.log(imageUrl);
28
28
 
29
29
  // Send a message to an AI model
30
- const { output: chat } = await agent.userMessage({
30
+ const { content } = await agent.userMessage({
31
31
  message: 'Summarize this article: ...',
32
32
  source: 'user',
33
33
  });
34
- console.log(chat.content);
34
+ console.log(content);
35
35
 
36
36
  // Search Google
37
- const { output: search } = await agent.searchGoogle({
37
+ const { results } = await agent.searchGoogle({
38
38
  query: 'TypeScript best practices 2025',
39
39
  exportType: 'json',
40
40
  });
41
- console.log(search.results);
41
+ console.log(results);
42
42
  ```
43
43
 
44
44
  Every method is fully typed — your editor will autocomplete available parameters, show enum options, and infer the output shape.
@@ -70,7 +70,7 @@ Resolution order: constructor `apiKey` > `MINDSTUDIO_API_KEY` env > `CALLBACK_TO
70
70
 
71
71
  ## Thread persistence
72
72
 
73
- Steps execute within threads. Pass `threadId` and `appId` from a previous call to maintain state across calls:
73
+ Steps execute within threads. Pass `$threadId` and `$appId` from a previous call to maintain state across calls:
74
74
 
75
75
  ```typescript
76
76
  const r1 = await agent.userMessage({
@@ -81,7 +81,7 @@ const r1 = await agent.userMessage({
81
81
  // The model remembers the conversation
82
82
  const r2 = await agent.userMessage(
83
83
  { message: 'What is my name?', source: 'user' },
84
- { threadId: r1.threadId, appId: r1.appId },
84
+ { threadId: r1.$threadId, appId: r1.$appId },
85
85
  );
86
86
  ```
87
87