@mindstudio-ai/agent 0.1.81 → 0.1.83

package/llms.txt

@@ -19,7 +19,7 @@ For specific use cases:
 - **Pre-built agents**: Call `listAgents()` to see what's available → `runAgent({ appId })` to execute one. **Important:** Not all agents are configured for API use. Do not try to run an agent just because it appears in the list — only run agents the user specifically asks you to run.
 - **Model selection**: Call `listModelsSummary()` or `listModelsSummaryByType("llm_chat")` to browse models, then pass the model ID as `modelOverride.model` to actions like `generateText`. Use the summary endpoints (not `listModels`) to keep token usage low.
 - **Cost estimation**: AI-powered actions (text generation, image generation, video, audio, etc.) cost money. Call `estimateStepCost(stepType, stepInput)` before running these and confirm with the user before proceeding — unless they've explicitly given permission to go ahead. Non-AI actions (data lookups, OAuth connectors, etc.) are generally free.
-- **Task agents**: For multi-step tasks that need autonomous tool use (research, content creation, data enrichment), use `runTask()`. Provide a prompt, input, SDK action names as tools, a structured output example, and a tool-use model id. The platform runs a tool-use loop — calling the model, executing actions, feeding results back — until structured output is produced. Example: `runTask({ prompt: "Find info about this restaurant", input: { name: "Tartine" }, tools: ["searchGoogle", "fetchUrl"], structuredOutputExample: '{"name":"...","url":"..."}', model: yourModelId })`. Pass a current tool-use model id (call `listModels` or ask). Don't hardcode one.
+- **Task agents**: For multi-step tasks that need autonomous tool use (research, content creation, data enrichment), use `runTask()`. Provide a prompt, input, tools, a structured output example, and a tool-use model id. The platform runs a tool-use loop — calling the model, executing tools, feeding results back — until structured output is produced. Tools are SDK action names and/or your own app methods, written as `{ appMethod: "saveVendor", description: "when to use it" }`. App methods run as the user who invoked the method that started the task, with their roles, so the agent can read and write app state on their behalf. Example: `runTask({ prompt: "Research this restaurant and save it", input: { name: "Tartine" }, tools: ["searchGoogle", "fetchUrl", { appMethod: "saveRestaurant", description: "Persist the researched restaurant." }], structuredOutputExample: '{"name":"...","url":"..."}', model: yourModelId })`. Pass a current tool-use model id (call `listModels` or ask). Don't hardcode one.
 
 ## Install
 
@@ -731,21 +731,21 @@ Extract text, HTML, or structured content from one or more web pages.
 - Output format controls the result shape: "text" returns markdown, "html" returns raw HTML, "json" returns structured scraper data.
 - Can optionally capture a screenshot of each page.
 - Input: `{ url: string, service?: "default" | "firecrawl", autoEnhance?: boolean, outputFormat?: "text" | "json" | "html", pageOptions?: { onlyMainContent: boolean, screenshot: boolean, waitFor: number, replaceAllPathsWithAbsolutePaths: boolean, headers: object, removeTags: string[], mobile: boolean } }`
-- Output: `{ content: string | string[] | { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string } } | { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string } }[], screenshot?: string }`
+- Output: `{ content: string | string[] | { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string }, error?: { code: string, message: string } } | { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string }, error?: { code: string, message: string } }[], screenshot?: string | string[] }`
 
 #### scrapeXPost
 Scrape data from a single X (Twitter) post by URL.
 - Returns structured post data (text, html, optional json/screenshot/metadata).
 - Optionally saves the text content to a variable.
 - Input: `{ url: string }`
-- Output: `{ post: { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string } } }`
+- Output: `{ post: { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string }, error?: { code: string, message: string } } }`
 
 #### scrapeXProfile
 Scrape public profile data from an X (Twitter) account by URL.
 - Returns structured profile data.
 - Optionally saves the result to a variable.
 - Input: `{ url: string }`
-- Output: `{ profile: { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string } } }`
+- Output: `{ profile: { text: string, html: string, json?: object, screenshotUrl?: string, metadata?: { title: string, description: string, url: string, image: string }, error?: { code: string, message: string } } }`
 
 #### screenshotUrl
 Capture a screenshot of a web page as a PNG image.
@@ -808,6 +808,9 @@ Send an email to one or more recipient addresses.
 - Use the "to" field to send to one or more specific recipient email addresses directly. Allowed recipients depend on the sender: when the app sends from a domain it owns (a verified custom domain or its <slug>.madewithremy.com subdomain) any recipient is allowed; when it falls back to the shared Remy address, recipients must be verified app users or members of the app's organization. (v1 apps cannot use a direct "to" — they must resolve recipients via a connection.)
 - Alternatively, recipient email addresses can be resolved from OAuth connections configured by the app creator via connectionId. The user running the workflow does not specify the recipient directly.
 - Use "cc" and "bcc" to add visible / hidden recipients (a string or an array). They are subject to the same recipient rules as "to".
+- "to" is optional only in the sense that recipients can come from elsewhere — omit it and supply "cc"/"bcc" for a hidden-list send, or omit all three and recipients are resolved from an OAuth connection. Naming nobody at all is an error.
+- Bcc-only sends are supported: with no "to" or "cc", the To: header is addressed to the app's own sender address (the standard "undisclosed recipients" pattern) so recipients can't see each other. The returned "recipients" reflects that auto-filled address.
+- Every recipient counts toward the app's daily outbound cap, including cc and bcc.
 - The sender defaults automatically: v2 apps send from the app's own identity — its verified custom domain if set, else its platform subdomain (noreply@<slug>.madewithremy.com), else the default Remy address.
 - Optionally set "from" to a custom handle, but ONLY if the app has a custom domain or subdomain: a bare handle ("support" → support@<app-domain>), a full "support@your-domain.com", or "Name <support@your-domain.com>". The domain must be one the app owns, or the step fails.
 - If the body is a URL to a hosted HTML file on the CDN, the HTML is fetched and used as the email body.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/agent",
-  "version": "0.1.81",
+  "version": "0.1.83",
   "description": "TypeScript SDK for MindStudio direct step execution",
   "type": "module",
   "main": "./dist/index.js",