@mindstudio-ai/agent 0.1.164 → 0.1.166

package/CHANGELOG.md

@@ -4,6 +4,18 @@ What changed in `@mindstudio-ai/agent`, newest first, each version under its own
 
 Versions before 0.1.163 aren't recorded here.
 
+## 0.1.166
+
+### Changed behavior
+
+- `renderVideoFromHtmlComposition` renders with HyperFrames 0.8.148, and its usage notes and `llms.txt` say so. In it, an mp4 or mov keeps sound and picture in sync when the source's streams start apart, and a long render with many clips no longer stalls at 90%. Check: an app that pins HyperFrames' CLI or `@hyperframes/player` at the platform's version for authoring or previewing moves it to 0.8.148.
+
+## 0.1.165
+
+### New
+
+- The CLI can log what each call costs. When `MINDSTUDIO_USAGE_LOG` names a file, every billed call from an action, `batch` (a line per step) or `ask` appends one JSON line to it: `{ ts, action, billingCost, billingEvents?, durationMs }`, with `billingCost` in nano-dollars. It's for a tool that runs the CLI and keeps its own record of spend, whatever happens to the command's output. App code isn't affected.
+
 ## 0.1.164
 
 ### New

package/dist/cli.js

@@ -9,6 +9,31 @@ var __export = (target, all) => {
     __defProp(target, name, { get: all[name], enumerable: true });
 };
 
+// src/usageLog.ts
+import { appendFileSync } from "fs";
+function logUsage(entry) {
+  const file = process.env.MINDSTUDIO_USAGE_LOG;
+  if (!file || typeof entry.billingCost !== "number") {
+    return;
+  }
+  const line = {
+    ts: Date.now(),
+    action: entry.action,
+    billingCost: entry.billingCost,
+    ...entry.billingEvents?.length && { billingEvents: entry.billingEvents },
+    durationMs: Date.now() - entry.startedAt
+  };
+  try {
+    appendFileSync(file, JSON.stringify(line) + "\n");
+  } catch {
+  }
+}
+var init_usageLog = __esm({
+  "src/usageLog.ts"() {
+    "use strict";
+  }
+});
+
 // src/generated/metadata.ts
 var metadata_exports = {};
 __export(metadata_exports, {
@@ -795,7 +820,7 @@ var init_metadata = __esm({
       "renderVideoFromHtmlComposition": {
         stepType: "renderVideoFromHtmlComposition",
         description: "Render an HTML composition (HTML, CSS, media and seekable animation on a timeline) to a video file",
-        usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.143, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
+        usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.148, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
         inputSchema: { "type": "object", "properties": { "html": { "type": "string", "description": "The composition's HTML, up to 10 MB; give this or project" }, "project": { "type": "string", "description": "URL of a zip of the project's folder, or of one self-contained HTML file; give this or html" }, "entryFile": { "type": "string", "description": "The entry HTML inside the zip, relative to its root; index.html when omitted" }, "variables": { "type": "object", "properties": {}, "required": [], "description": "Values over the composition's declared variables" }, "fps": { "enum": [24, 30, 60], "type": "number", "description": "Frames per second: 24, 30 (default) or 60" }, "quality": { "enum": ["draft", "standard", "high"], "type": "string", "description": "Encode quality: draft, standard (default) or high" }, "format": { "enum": ["mp4", "webm", "mov", "gif"], "type": "string", "description": "mp4 (default), webm or mov (both keep transparency), or gif" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" } } },
         outputSchema: { "type": "object", "properties": { "videoUrl": { "type": "string", "description": "URL of the rendered video" }, "durationSec": { "type": "number", "description": "Its length in seconds" }, "frames": { "type": "number", "description": "How many frames it has" } }, "required": ["videoUrl", "durationSec", "frames"] }
       },
@@ -9307,6 +9332,7 @@ function summarizeInput(input) {
 async function cmdAsk(question, options) {
   try {
     let lineBuffer = "";
+    const startedAt = Date.now();
     const result = await runAsk(question, options, (event) => {
       switch (event.type) {
         case "text":
@@ -9336,6 +9362,12 @@ async function cmdAsk(question, options) {
     if (lineBuffer) {
       process.stderr.write(lineBuffer);
     }
+    logUsage({
+      action: "ask",
+      billingCost: result.billingCost,
+      billingEvents: result.billingEvents,
+      startedAt
+    });
     if (options.json) {
       process.stdout.write(
         JSON.stringify({
@@ -9360,6 +9392,7 @@ var init_ask = __esm({
   async "src/ask/index.ts"() {
     "use strict";
     await init_client();
+    init_usageLog();
     init_context2();
     init_sse();
     init_tools();
@@ -9434,7 +9467,7 @@ async function startMcpServer(options) {
           capabilities: { tools: {} },
           serverInfo: {
             name: "mindstudio-agent",
-            version: "0.1.164"
+            version: "0.1.166"
           },
           instructions: 'Welcome to MindStudio \u2014 a platform with 200+ AI models, 850+ third-party integrations, and pre-built agents.\n\nGetting started:\n1. Call `ask` with any question about the SDK \u2014 it knows every action, model, and connector and returns working code with real model IDs and config options. Examples: ask("generate an image with FLUX"), ask("what models support vision?"), ask("how do I send a Slack message?").\n2. Call `changeName` to set your display name \u2014 use your name or whatever your user calls you. This is how you\'ll appear in MindStudio request logs.\n3. If you have a profile picture, pass its public image URL to `changeProfilePicture`.\n4. For manual browsing, call `listActions` to discover all available actions.\n\nThen use the tools to generate text, images, video, audio, search the web, work with data sources, run agents, and more.\n\nImportant:\n- AI-powered actions (text generation, image generation, video, audio, etc.) cost money. Before running these, call `estimateActionCost` and confirm with the user before proceeding \u2014 unless they\'ve explicitly told you to go ahead.\n- Not all agents from `listAgents` are configured for API use. Do not try to run an agent just because it appears in the list \u2014 it will likely fail. Only run agents the user specifically asks you to run.'
         });
@@ -9885,6 +9918,7 @@ var init_mcp = __esm({
 });
 
 // src/cli.ts
+init_usageLog();
 import { parseArgs } from "util";
 import { execSync } from "child_process";
 import { readFileSync as readFileSync3 } from "fs";
@@ -10204,11 +10238,18 @@ async function cmdExec(method, input, options) {
 `);
     };
   }
+  const startedAt = Date.now();
   const result = await agent.executeStep(meta.stepType, input, {
     appId: options.appId,
     threadId: options.threadId,
     onLog
   });
+  logUsage({
+    action: camelToKebab(method),
+    billingCost: result.$billingCost,
+    billingEvents: result.$billingEvents,
+    startedAt
+  });
   if (options.outputKey) {
     const val = result[options.outputKey];
     if (typeof val === "string") {
@@ -10384,10 +10425,18 @@ Example: mindstudio batch '[{"stepType":"generateImage","step":{"prompt":"a cat"
     return { stepType: item.stepType, step: item.step };
   });
   const agent = await createAgent(options);
+  const startedAt = Date.now();
   const result = await agent.executeStepBatch(steps, {
     appId: options.appId,
     threadId: options.threadId
   });
+  for (const step of result.results) {
+    logUsage({
+      action: `batch:${step.stepType}`,
+      billingCost: step.billingCost,
+      startedAt
+    });
+  }
   if (options.noMeta) {
     process.stdout.write(JSON.stringify(result.results, null, 2) + "\n");
   } else {
@@ -10458,7 +10507,7 @@ function isNewerVersion(current, latest) {
   return false;
 }
 async function checkForUpdate() {
-  const currentVersion = "0.1.164";
+  const currentVersion = "0.1.166";
   if (!currentVersion || process.env.MINDSTUDIO_NO_UPDATE_CHECK) {
     return null;
   }
@@ -10493,7 +10542,7 @@ async function checkForUpdate() {
   }
 }
 function printUpdateNotice(latestVersion) {
-  const currentVersion = "0.1.164";
+  const currentVersion = "0.1.166";
   process.stderr.write(
     `
   ${ansi2.cyanBright("Update available")} ${ansi2.gray(currentVersion + " \u2192")} ${ansi2.cyanBold(latestVersion)}
@@ -10506,7 +10555,7 @@ function isStandaloneBinary() {
   return !argv1.includes("node_modules");
 }
 async function cmdUpdate() {
-  const currentVersion = "0.1.164";
+  const currentVersion = "0.1.166";
   process.stderr.write(
     `  ${ansi2.gray("Current version:")} ${currentVersion}
 `
@@ -10647,7 +10696,7 @@ async function cmdLogin(options) {
   process.stderr.write("\n");
   printLogo();
   process.stderr.write("\n");
-  const ver = "0.1.164";
+  const ver = "0.1.166";
   process.stderr.write(
     `  ${ansi2.bold("MindStudio Agent")} ${ver ? " " + ansi2.gray("v" + ver) : ""}
 `
@@ -10975,7 +11024,7 @@ async function main() {
   const updatePromise = command !== "mcp" && command !== "login" && command !== "update" ? checkForUpdate() : Promise.resolve(null);
   try {
     if (command === "version" || command === "-v") {
-      process.stdout.write("0.1.164\n");
+      process.stdout.write("0.1.166\n");
       return;
     }
     if (command === "login") {

package/dist/index.d.ts

@@ -11159,7 +11159,7 @@ interface StepMethods {
      * Render an HTML composition (HTML, CSS, media and seekable animation on a timeline) to a video file
      *
      * @remarks
-     * - Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.143, in Chrome off the app's own sandbox; author for that version
+     * - Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.148, in Chrome off the app's own sandbox; author for that version
      * - Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL
      * - `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`
      * - Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL

package/dist/index.js

@@ -5102,7 +5102,7 @@ var stepMetadata = {
   "renderVideoFromHtmlComposition": {
     stepType: "renderVideoFromHtmlComposition",
     description: "Render an HTML composition (HTML, CSS, media and seekable animation on a timeline) to a video file",
-    usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.143, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
+    usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.148, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
     inputSchema: { "type": "object", "properties": { "html": { "type": "string", "description": "The composition's HTML, up to 10 MB; give this or project" }, "project": { "type": "string", "description": "URL of a zip of the project's folder, or of one self-contained HTML file; give this or html" }, "entryFile": { "type": "string", "description": "The entry HTML inside the zip, relative to its root; index.html when omitted" }, "variables": { "type": "object", "properties": {}, "required": [], "description": "Values over the composition's declared variables" }, "fps": { "enum": [24, 30, 60], "type": "number", "description": "Frames per second: 24, 30 (default) or 60" }, "quality": { "enum": ["draft", "standard", "high"], "type": "string", "description": "Encode quality: draft, standard (default) or high" }, "format": { "enum": ["mp4", "webm", "mov", "gif"], "type": "string", "description": "mp4 (default), webm or mov (both keep transparency), or gif" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" } } },
     outputSchema: { "type": "object", "properties": { "videoUrl": { "type": "string", "description": "URL of the rendered video" }, "durationSec": { "type": "number", "description": "Its length in seconds" }, "frames": { "type": "number", "description": "How many frames it has" } }, "required": ["videoUrl", "durationSec", "frames"] }
   },