@mindstudio-ai/agent 0.1.16 → 0.1.17

package/llms.txt

@@ -9,8 +9,8 @@ This file is the complete API reference. No other documentation is needed to use
 There are 150+ actions available. Do NOT try to read or load them all at once. Follow this discovery flow:
 
 1. **Identify yourself** — Call `changeName` to set your display name (use your name or whatever your user calls you). If you have a profile picture or icon, call `uploadFile` to upload it, then `changeProfilePicture` with the returned URL. This helps users identify your requests in their logs.
-2. **Discover** — Call `listActions` (MCP tool) or `mindstudio list-actions --summary` (CLI) to get a compact `{ action: description }` map of everything available (~3k tokens).
-3. **Drill in** — Once you identify the right action, look up its full signature in the reference below, or call `mindstudio info <action>` (CLI) for parameter details.
+2. **Ask** — Use `mindstudio ask "your question"` (CLI) or the `ask` MCP tool for SDK guidance. It knows every action, model, and connector and returns working TypeScript code with real model IDs and config options. Examples: `mindstudio ask "generate an image with FLUX"`, `mindstudio ask "what models support vision?"`, `mindstudio ask "how do I send a Slack message?"`.
+3. **Browse** — For manual discovery, call `listActions` (MCP tool) or `mindstudio list-actions --summary` (CLI) to get a compact `{ action: description }` map of everything available (~3k tokens). Call `mindstudio info <action>` (CLI) for parameter details.
 4. **Call it** — Invoke the action with the required parameters. All actions share the same calling convention (see below).
 
 For specific use cases:
@@ -466,6 +466,14 @@ Send a message to an AI model and return the response, or echo a system message.
 - Source "system" echoes the message content directly (no AI call).
 - Mode "background" saves the result to a variable. Mode "foreground" streams it to the user (not available in direct execution).
 - Structured output (JSON/CSV) can be enforced via structuredOutputType and structuredOutputExample.
+- When executed inside a v2 app method (managed sandbox or local dev tunnel),
+LLM token output can be streamed to the frontend in real time via an SSE
+side-channel. The frontend opts in by passing { stream: true } to the method
+invocation via @mindstudio-ai/interface. Tokens are published to Redis
+pub/sub as they arrive and forwarded as SSE events on the invoke response.
+The method code itself is unchanged — streaming is transparent to the
+developer. See V2ExecutionService.ts and the invoke handler in V2Apps for
+the server-side plumbing.
 - Input: `{ message: string, source?: "user" | "system", modelOverride?: { model: string, temperature: number, maxResponseTokens: number, ignorePreamble?: boolean, userMessagePreprocessor?: { dataSource?: string, messageTemplate?: string, maxResults?: number, enabled?: boolean, shouldInherit?: boolean }, preamble?: string, multiModelEnabled?: boolean, editResponseEnabled?: boolean, config?: object }, structuredOutputType?: "text" | "json" | "csv", structuredOutputExample?: string, chatHistoryMode?: "include" | "exclude" }`
 - Output: `{ content: string }`
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/agent",
-  "version": "0.1.16",
+  "version": "0.1.17",
   "description": "TypeScript SDK for MindStudio direct step execution",
   "type": "module",
   "main": "./dist/index.js",