@mastra/agent-browser 0.2.2 → 0.3.0-alpha.1

package/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @mastra/agent-browser
 
+## 0.3.0-alpha.1
+
+### Minor Changes
+
+- Add `waitUntil` support to `browser_click`, `browser_press`, and `browser_select`. When provided, the tool waits for the page to reach the given load state (`load`, `domcontentloaded`, or `networkidle`) after the action completes, preventing the next `browser_snapshot` from capturing stale DOM when the interaction triggers navigation. The parameter is optional and behaviour is unchanged when omitted. ([#17426](https://github.com/mastra-ai/mastra/pull/17426))
+
+  Usage example:
+
+  ```ts
+  await browser_click({ ref: '@e1', waitUntil: 'domcontentloaded', timeout: 5000 });
+  ```
+
+  Fixes #17397.
+
+### Patch Changes
+
+- Updated dependencies [[`19a8658`](https://github.com/mastra-ai/mastra/commit/19a86589c788ef48bb6c1b0612cc82a201857379), [`a659a77`](https://github.com/mastra-ai/mastra/commit/a659a779bdebe3a52a518c56d2260592d0240fe0), [`3332be9`](https://github.com/mastra-ai/mastra/commit/3332be9701ecd77aba840959d9a1d1ce7aef02d3)]:
+  - @mastra/core@1.38.0-alpha.6
+
+## 0.3.0-alpha.0
+
+### Minor Changes
+
+- Added extensibility hooks for custom browser providers (e.g. Firecrawl Browser Sandbox). ([#15724](https://github.com/mastra-ai/mastra/pull/15724))
+  - New `createThreadManager` config option to inject a custom thread manager factory
+  - Exported `AgentBrowserThreadManager` class and related types (`AgentBrowserSession`, `AgentBrowserThreadManagerConfig`, `CreateAgentBrowserThreadManager`)
+  - Changed several internal members from `private` to `protected` to support subclassing
+
+### Patch Changes
+
+- Updated dependencies [[`8ace89d`](https://github.com/mastra-ai/mastra/commit/8ace89df77f762e622d3b9f7f65ad7524350d050), [`fa63872`](https://github.com/mastra-ai/mastra/commit/fa6387280954e6b667bec5714b55ba082bc627ff), [`f07b646`](https://github.com/mastra-ai/mastra/commit/f07b64604ab7d25391179790b7fd4823df9e2dff), [`d8838ae`](https://github.com/mastra-ai/mastra/commit/d8838ae80b69780361693d27098f7f6684af12fe), [`40f9297`](https://github.com/mastra-ai/mastra/commit/40f9297003b921c62373d3e8d3a4bda76c9f6de3), [`0f0d1ba`](https://github.com/mastra-ai/mastra/commit/0f0d1ba67bfcb2204e571401662f1eceefc03357), [`8c31bcd`](https://github.com/mastra-ai/mastra/commit/8c31bcdb00e597880d5939b1b7d7566fbe5dacae), [`95b14cd`](https://github.com/mastra-ai/mastra/commit/95b14cdd820e86d97ac05fe568424c513a252e31), [`aa36be2`](https://github.com/mastra-ai/mastra/commit/aa36be23aa513b7dc53cb8ca16b7fab8f20e43ad), [`212c635`](https://github.com/mastra-ai/mastra/commit/212c635203e61d036ab41db8ff86c3893dc795b3), [`d8838ae`](https://github.com/mastra-ai/mastra/commit/d8838ae80b69780361693d27098f7f6684af12fe), [`9aa5a73`](https://github.com/mastra-ai/mastra/commit/9aa5a73e7e110f6e9365eec69364a33d5f03bb56), [`f73c789`](https://github.com/mastra-ai/mastra/commit/f73c789e8ef21561580395d2c410119cab5848c8), [`8bd16da`](https://github.com/mastra-ai/mastra/commit/8bd16da73a4cb874d739373643dbd6a6e7f88684), [`c8630f8`](https://github.com/mastra-ai/mastra/commit/c8630f80d4f40cb5d22e60ab162b618b1907167a), [`47f71dc`](https://github.com/mastra-ai/mastra/commit/47f71dc6fbcbd12d71e21a979e676e20a02bd77d), [`50ceae2`](https://github.com/mastra-ai/mastra/commit/50ceae270878e2f8fb2b2c6c2faab09df0007c8a), [`8cdde58`](https://github.com/mastra-ai/mastra/commit/8cdde5875bbba6702d9df226f2b20232b8d75d6c), [`847ff1e`](https://github.com/mastra-ai/mastra/commit/847ff1e0d94368d94b2e173e4e0908e115568ef3), [`259d409`](https://github.com/mastra-ai/mastra/commit/259d409a514174299dbde1ff5e1121209b3ba850), [`9e16c68`](https://github.com/mastra-ai/mastra/commit/9e16c6818b6485ccb43df28aba6f3a2219d28662), [`cefca33`](https://github.com/mastra-ai/mastra/commit/cefca33ae666e69810c935fedf95a929c173d1d7), [`d00e8c5`](https://github.com/mastra-ai/mastra/commit/d00e8c50daebe5bce5bf2f48bde39c86fc3d2fe4), [`36fa7e2`](https://github.com/mastra-ai/mastra/commit/36fa7e24d14e58a1eb46147097b32f583e5b8775), [`87e9774`](https://github.com/mastra-ai/mastra/commit/87e97741c1e493cd6d62f478eb810b49bda4d57c), [`65a72e7`](https://github.com/mastra-ai/mastra/commit/65a72e70c25eedea8ff985a6624b96be2850236b), [`0f77241`](https://github.com/mastra-ai/mastra/commit/0f7724108806703799a8ba80ad0f09414afd5066), [`92ff509`](https://github.com/mastra-ai/mastra/commit/92ff5098ef8a990438ca038077021a5f7541ec1d), [`3fce5e7`](https://github.com/mastra-ai/mastra/commit/3fce5e70d011d289043e75003ef3336ed4aa43c3), [`a763592`](https://github.com/mastra-ai/mastra/commit/a763592c3db46963ef1011cfe16fe372816e775e), [`80c7737`](https://github.com/mastra-ai/mastra/commit/80c7737e32d7917b5f356957d67c169d01744fd3), [`3f1cf47`](https://github.com/mastra-ai/mastra/commit/3f1cf476f74c1e4cc2df908837e05853a5347e31)]:
+  - @mastra/core@1.38.0-alpha.3
+
 ## 0.2.2
 
 ### Patch Changes

package/dist/index.cjs

@@ -141,7 +141,9 @@ var clickInputSchema = zod.z.object({
   ref: zod.z.string().describe("Element ref from snapshot (e.g., @e5)"),
   button: zod.z.enum(["left", "right", "middle"]).optional().describe("Mouse button (default: left)"),
   clickCount: zod.z.number().optional().describe("Number of clicks (default: 1, use 2 for double-click)"),
-  modifiers: zod.z.array(zod.z.enum(["Alt", "Control", "Meta", "Shift"])).optional().describe("Modifier keys to hold")
+  modifiers: zod.z.array(zod.z.enum(["Alt", "Control", "Meta", "Shift"])).optional().describe("Modifier keys to hold"),
+  waitUntil: zod.z.enum(["load", "domcontentloaded", "networkidle"]).optional().describe("If the click triggers a navigation, wait for this page load state before returning"),
+  timeout: zod.z.number().nonnegative().optional().describe("Timeout in milliseconds for the click and optional waitUntil")
 });
 var typeInputSchema = zod.z.object({
   ref: zod.z.string().describe("Element ref from snapshot"),
@@ -151,13 +153,17 @@ var typeInputSchema = zod.z.object({
 });
 var pressInputSchema = zod.z.object({
   key: zod.z.string().describe("Key to press (e.g., Enter, Tab, Escape, Control+a)"),
-  modifiers: zod.z.array(zod.z.enum(["Alt", "Control", "Meta", "Shift"])).optional().describe("Modifier keys to hold")
+  modifiers: zod.z.array(zod.z.enum(["Alt", "Control", "Meta", "Shift"])).optional().describe("Modifier keys to hold"),
+  waitUntil: zod.z.enum(["load", "domcontentloaded", "networkidle"]).optional().describe("If the key press triggers a navigation, wait for this page load state before returning"),
+  timeout: zod.z.number().nonnegative().optional().describe("Timeout in milliseconds for the optional waitUntil")
 });
 var selectInputSchema = zod.z.object({
   ref: zod.z.string().describe("Select element ref from snapshot"),
   value: zod.z.string().optional().describe("Option value to select"),
   label: zod.z.string().optional().describe("Option label to select"),
-  index: zod.z.number().int().min(0).optional().describe("Option index to select (0-based)")
+  index: zod.z.number().int().min(0).optional().describe("Option index to select (0-based)"),
+  waitUntil: zod.z.enum(["load", "domcontentloaded", "networkidle"]).optional().describe("If the selection triggers a navigation, wait for this page load state before returning"),
+  timeout: zod.z.number().nonnegative().optional().describe("Timeout in milliseconds for the selection and optional waitUntil")
 }).superRefine((data, ctx) => {
   if (data.value === void 0 && data.label === void 0 && data.index === void 0) {
     ctx.addIssue({
@@ -293,7 +299,7 @@ function createBackTool(browser) {
 function createClickTool(browser) {
   return tools.createTool({
     id: BROWSER_TOOLS.CLICK,
-    description: "Click an element using its ref from a snapshot. Use clickCount: 2 for double-click.",
+    description: "Click an element using its ref from a snapshot. Use clickCount: 2 for double-click. Pass waitUntil when the click triggers navigation so the page settles before the next snapshot.",
     inputSchema: clickInputSchema,
     execute: async (input, { agent }) => {
       const threadId = agent?.threadId;
@@ -390,7 +396,7 @@ function createHoverTool(browser) {
 function createPressTool(browser) {
   return tools.createTool({
     id: BROWSER_TOOLS.PRESS,
-    description: "Press a keyboard key (e.g., Enter, Tab, Escape, Control+a).",
+    description: "Press a keyboard key (e.g., Enter, Tab, Escape, Control+a). Pass waitUntil when the keypress triggers navigation (e.g., Enter to submit a form) so the page settles before the next snapshot.",
     inputSchema: pressInputSchema,
     execute: async (input, { agent }) => {
       const threadId = agent?.threadId;
@@ -448,7 +454,7 @@ function createScrollTool(browser) {
 function createSelectTool(browser) {
   return tools.createTool({
     id: BROWSER_TOOLS.SELECT,
-    description: "Select an option from a dropdown by value, label, or index.",
+    description: "Select an option from a dropdown by value, label, or index. Pass waitUntil when the selection triggers navigation so the page settles before the next snapshot.",
     inputSchema: selectInputSchema,
     execute: async (input, { agent }) => {
       const threadId = agent?.threadId;
@@ -576,7 +582,7 @@ var AgentBrowser = class extends browser.MastraBrowser {
       this.defaultTimeout = config.timeout;
     }
     const effectiveScope = config.cdpUrl ? config.scope ?? "shared" : config.scope ?? "thread";
-    this.threadManager = new AgentBrowserThreadManager({
+    const threadManagerConfig = {
       scope: effectiveScope,
       browserConfig: { ...config, headless: this.headless },
       resolveCdpUrl: this.resolveCdpUrl.bind(this),
@@ -589,7 +595,9 @@ var AgentBrowser = class extends browser.MastraBrowser {
       onBrowserCreated: (manager, threadId) => {
         this.setupCloseListenerForThread(manager, threadId);
       }
-    });
+    };
+    const createTm = config.createThreadManager ?? ((opts) => new AgentBrowserThreadManager(opts));
+    this.threadManager = createTm(threadManagerConfig);
   }
   // ---------------------------------------------------------------------------
   // Thread Scope (delegated to ThreadManager)
@@ -1089,12 +1097,15 @@ var AgentBrowser = class extends browser.MastraBrowser {
           "Take a new snapshot to see the current page state and get fresh refs."
         );
       }
+      const timeout = input.timeout ?? this.defaultTimeout;
+      const navigation = input.waitUntil ? page.waitForNavigation({ waitUntil: input.waitUntil, timeout }) : void 0;
       await locator.click({
         button: input.button ?? "left",
         clickCount: input.clickCount ?? 1,
         modifiers: input.modifiers,
-        timeout: this.defaultTimeout
+        timeout
       });
+      await navigation;
       return {
         success: true,
         url: page.url(),
@@ -1163,7 +1174,10 @@ var AgentBrowser = class extends browser.MastraBrowser {
   async press(input, threadId) {
     try {
       const page = await this.getPage(threadId);
+      const timeout = input.timeout ?? this.defaultTimeout;
+      const navigation = input.waitUntil ? page.waitForNavigation({ waitUntil: input.waitUntil, timeout }) : void 0;
       await page.keyboard.press(input.key);
+      await navigation;
       return {
         success: true,
         url: page.url(),
@@ -1191,9 +1205,10 @@ var AgentBrowser = class extends browser.MastraBrowser {
       if (input.value) selectValue.value = input.value;
       if (input.label) selectValue.label = input.label;
       if (input.index !== void 0) selectValue.index = input.index;
-      const selected = await locator.selectOption(selectValue, {
-        timeout: this.defaultTimeout
-      });
+      const timeout = input.timeout ?? this.defaultTimeout;
+      const navigation = input.waitUntil ? page.waitForNavigation({ waitUntil: input.waitUntil, timeout }) : void 0;
+      const selected = await locator.selectOption(selectValue, { timeout });
+      await navigation;
       return {
         success: true,
         selected,
@@ -1687,6 +1702,7 @@ var AgentBrowser = class extends browser.MastraBrowser {
 };
 
 exports.AgentBrowser = AgentBrowser;
+exports.AgentBrowserThreadManager = AgentBrowserThreadManager;
 exports.BROWSER_TOOLS = BROWSER_TOOLS;
 exports.backInputSchema = backInputSchema;
 exports.browserSchemas = browserSchemas;