@mindstudio-ai/agent 0.1.48 → 0.1.49

package/llms.txt

@@ -104,24 +104,21 @@ MCP client config (standalone binary — recommended):
 
 ## Setup
 
+Inside MindStudio apps (auth is automatic):
 ```typescript
-import { MindStudioAgent } from '@mindstudio-ai/agent';
+import { mindstudio, db, auth, Roles, stream } from '@mindstudio-ai/agent';
 
-// With API key (or set MINDSTUDIO_API_KEY env var)
-const agent = new MindStudioAgent({ apiKey: 'your-key' });
+const { imageUrl } = await mindstudio.generateImage({ prompt: 'a sunset' });
 ```
 
-Your MindStudio API key authenticates all requests. MindStudio routes to the correct AI provider (OpenAI, Google, Anthropic, etc.) server-side — you do NOT need separate provider API keys.
-
-Constructor options:
+External usage (API key required):
 ```typescript
-new MindStudioAgent({
-  apiKey?: string,     // Auth token. Falls back to MINDSTUDIO_API_KEY env var.
-  baseUrl?: string,    // API base URL. Defaults to "https://v1.mindstudio-api.com".
-  maxRetries?: number, // Retries on 429 rate limit (default: 3). Uses Retry-After header for delay.
-})
+import { MindStudioAgent } from '@mindstudio-ai/agent';
+const agent = new MindStudioAgent({ apiKey: 'your-key' });
 ```
 
+Your MindStudio API key authenticates all requests. MindStudio routes to the correct AI provider (OpenAI, Google, Anthropic, etc.) server-side — you do NOT need separate provider API keys.
+
 ## Models
 
 Direct access to 200+ AI models from every major provider — all through a single API key, billed at cost with no markups.
@@ -129,10 +126,10 @@ Direct access to 200+ AI models from every major provider — all through a sing
 Use `listModels()` or `listModelsByType()` for full model details, or `listModelsSummary()` / `listModelsSummaryByType()` for a lightweight list (id, name, type, tags) suitable for LLM context windows. Pass a model ID to `modelOverride.model` in methods like `generateText` to select a specific model:
 
 ```typescript
-const { models } = await agent.listModelsByType('llm_chat');
+const { models } = await mindstudio.listModelsByType('llm_chat');
 const model = models.find(m => m.name.includes("Gemini"));
 
-const { content } = await agent.generateText({
+const { content } = await mindstudio.generateText({
   message: 'Hello',
   modelOverride: {
     model: model.id,
@@ -146,7 +143,7 @@ const { content } = await agent.generateText({
 
 Every method has the signature:
 ```typescript
-agent.methodName(input: InputType, options?: { appId?: string, threadId?: string }): Promise<OutputType & StepExecutionMeta>
+mindstudio.methodName(input: InputType, options?: { appId?: string, threadId?: string }): Promise<OutputType & StepExecutionMeta>
 ```
 
 The first argument is the step-specific input object. The optional second argument controls thread/app context.
@@ -154,10 +151,10 @@ The first argument is the step-specific input object. The optional second argume
 **Results are returned flat** — output fields are spread at the top level alongside metadata:
 
 ```typescript
-const { content } = await agent.generateText({ message: 'Hello' });
+const { content } = await mindstudio.generateText({ message: 'Hello' });
 
 // Full result shape for any method:
-const result = await agent.generateText({ message: `Hello` });
+const result = await mindstudio.generateText({ message: `Hello` });
 result.content;              // step-specific output field
 result.$appId;               // string — app ID for this execution
 result.$threadId;            // string — thread ID for this execution
@@ -171,8 +168,8 @@ result.$billingEvents;       // object[] | undefined — itemized billing events
 Pass `$appId`/`$threadId` from a previous result to maintain conversation state, variable state, or other context across calls:
 
 ```typescript
-const r1 = await agent.generateText({ message: 'My name is Alice' });
-const r2 = await agent.generateText(
+const r1 = await mindstudio.generateText({ message: 'My name is Alice' });
+const r2 = await mindstudio.generateText(
   { message: 'What is my name?' },
   { threadId: r1.$threadId, appId: r1.$appId },
 );
@@ -186,7 +183,7 @@ All errors throw `MindStudioError`:
 import { MindStudioError } from '@mindstudio-ai/agent';
 
 try {
-  await agent.generateImage({ prompt: '...' });
+  await mindstudio.generateImage({ prompt: '...' });
 } catch (err) {
   if (err instanceof MindStudioError) {
     err.message; // Human-readable error message
@@ -203,7 +200,7 @@ try {
 
 For action types not covered by generated methods:
 ```typescript
-const result = await agent.executeStep('stepType', { ...params });
+const result = await mindstudio.executeStep('stepType', { ...params });
 ```
 
 ## Batch execution
@@ -212,7 +209,7 @@ Execute multiple steps in parallel in a single request. Maximum 50 steps per bat
 Individual step failures do not affect other steps — partial success is possible.
 
 ```typescript
-const result = await agent.executeStepBatch([
+const result = await mindstudio.executeStepBatch([
   { stepType: 'generateImage', step: { prompt: 'a sunset' } },
   { stepType: 'textToSpeech', step: { text: 'hello world' } },
 ], { appId?, threadId? });
@@ -393,8 +390,9 @@ Extract audio MP3 from a video file
 - Output: `{ audioUrl: string }`
 
 #### extractText
-Download a file from a URL and extract its text content. Supports PDFs, plain text files, and other document formats.
+Download a file from a URL and extract its text content. Supports PDFs (including scanned/image-based PDFs via OCR), plain text files, and other document formats.
 - Best suited for PDFs and raw text/document files. For web pages, use the scrapeUrl step instead.
+- Handles both text-layer PDFs and image-based/scanned PDFs (e.g. Figma/Canva exports, scanned documents). Image-based PDFs are processed with OCR automatically — there is no need to convert PDF pages to images first.
 - Accepts a single URL, a comma-separated list of URLs, or a JSON array of URLs.
 - Files are rehosted on the MindStudio CDN before extraction.
 - Maximum file size is 50MB per URL.
@@ -1595,7 +1593,7 @@ Output:
 Estimate the cost of executing a step before running it. Pass the same step config you would use for execution.
 
 ```typescript
-const estimate = await agent.estimateStepCost('generateText', { message: 'Hello' });
+const estimate = await mindstudio.estimateStepCost('generateText', { message: 'Hello' });
 ```
 
 - `stepType`: string — The action name (e.g. `"generateText"`).
@@ -1621,14 +1619,14 @@ Output:
 Update the display name of the authenticated agent. Useful for agents to set their own name after connecting.
 
 ```typescript
-await agent.changeName('My Agent');
+await mindstudio.changeName('My Agent');
 ```
 
 #### `changeProfilePicture(profilePictureUrl)`
 Update the profile picture of the authenticated agent. Useful for agents to set their own avatar after connecting.
 
 ```typescript
-await agent.changeProfilePicture('https://example.com/avatar.png');
+await mindstudio.changeProfilePicture('https://example.com/avatar.png');
 ```
 
 #### `uploadFile(content, options)`
@@ -1636,7 +1634,7 @@ Upload a file to the MindStudio CDN. Gets a signed upload URL, PUTs the file con
 
 ```typescript
 import { readFileSync } from 'fs';
-const { url } = await agent.uploadFile(readFileSync('photo.png'), { extension: 'png', type: 'image/png' });
+const { url } = await mindstudio.uploadFile(readFileSync('photo.png'), { extension: 'png', type: 'image/png' });
 ```
 
 - `content`: `Buffer | Uint8Array` — The file content.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/agent",
-  "version": "0.1.48",
+  "version": "0.1.49",
   "description": "TypeScript SDK for MindStudio direct step execution",
   "type": "module",
   "main": "./dist/index.js",