feat(server): add wait and custom code tools

packages/browseros-agent/apps/server/src/agent/prompt.ts

@@ -138,6 +138,7 @@ You control a Chromium browser. Key tool categories:
 - \`get_dom\` / \`search_dom\` → raw HTML (use for precise CSS/XPath queries)
 - \`take_screenshot\` → visual capture (use for verification or saving)
 - \`evaluate_script\` → run JS on the page (use for dynamic data extraction)
+- \`browser_run_code\` → run custom async page code when predefined tools are insufficient
 - \`get_console_logs\` → browser console output (use for debugging)
 
 **Interaction** — act on page elements:
@@ -152,6 +153,7 @@ You control a Chromium browser. Key tool categories:
 **Navigation**:
 - \`navigate_page\` → go to URL, back, forward, reload
 - \`new_page\` → open new tab (only when user explicitly asks)
+- \`wait_for\` → wait for text/selectors to appear or disappear, or pause briefly
 - \`close_page\` → close a tab
 
 **Bookmarks**: \`get_bookmarks\`, \`create_bookmark\`, \`remove_bookmark\`, \`update_bookmark\`, \`move_bookmark\`, \`search_bookmarks\`
@@ -315,6 +317,7 @@ function getToolSelection(
 | Looking for specific links | \`get_page_links\` |
 | Need exact HTML or CSS selectors | \`get_dom\` or \`search_dom\` |
 | Need runtime data (JS variables, computed values) | \`evaluate_script\` |
+| Need custom async page logic | \`browser_run_code\` |
 | Something isn't working, need to debug | \`get_console_logs\` |
 | Need visual proof or to save an image | \`take_screenshot\` or \`save_screenshot\` |
 
@@ -417,7 +420,7 @@ function getErrorRecovery(
 ## Error Recovery
 
 ### Browser interaction errors
-- Element not found → \`scroll(page, "down")\`, \`wait_for(page, text)\`, then \`take_snapshot(page)\` to re-fetch elements
+- Element not found → \`scroll(page, "down")\`, \`wait_for(page, { text })\`, then \`take_snapshot(page)\` to re-fetch elements
 - Click/fill failed → \`scroll(page, "down", element)\` into view, retry once
 - Page didn't load → check URL, try \`navigate_page\` with reload
 - After 2 failed attempts → describe the blocking issue, request guidance

packages/browseros-agent/apps/server/src/browser/browser.ts

@@ -657,13 +657,19 @@ export class Browser {
 
   async waitFor(
     page: number,
-    opts: { text?: string; selector?: string; timeout: number },
+    opts: {
+      text?: string
+      textGone?: string
+      selector?: string
+      selectorGone?: string
+      timeout: number
+    },
   ): Promise<boolean> {
     const session = await this.resolveSession(page)
     const deadline = Date.now() + opts.timeout
     const interval = 500
 
-    while (Date.now() < deadline) {
+    while (Date.now() <= deadline) {
       if (opts.text) {
         const result = await session.Runtime.evaluate({
           expression: `document.body?.innerText?.includes(${JSON.stringify(opts.text)}) ?? false`,
@@ -672,6 +678,14 @@ export class Browser {
         if (result.result?.value === true) return true
       }
 
+      if (opts.textGone) {
+        const result = await session.Runtime.evaluate({
+          expression: `!(document.body?.innerText?.includes(${JSON.stringify(opts.textGone)}) ?? false)`,
+          returnByValue: true,
+        })
+        if (result.result?.value === true) return true
+      }
+
       if (opts.selector) {
         const result = await session.Runtime.evaluate({
           expression: `!!document.querySelector(${JSON.stringify(opts.selector)})`,
@@ -680,7 +694,17 @@ export class Browser {
         if (result.result?.value === true) return true
       }
 
-      await new Promise((r) => setTimeout(r, interval))
+      if (opts.selectorGone) {
+        const result = await session.Runtime.evaluate({
+          expression: `!document.querySelector(${JSON.stringify(opts.selectorGone)})`,
+          returnByValue: true,
+        })
+        if (result.result?.value === true) return true
+      }
+
+      const remaining = deadline - Date.now()
+      if (remaining <= 0) break
+      await new Promise((r) => setTimeout(r, Math.min(interval, remaining)))
     }
 
     return false
@@ -941,6 +965,42 @@ export class Browser {
     }
   }
 
+  async runCode(
+    page: number,
+    code: string,
+    args?: Record<string, unknown>,
+  ): Promise<{
+    value?: unknown
+    error?: string
+    description?: string
+  }> {
+    const session = await this.resolveSession(page)
+    const expression = `(
+      async (args) => {
+        ${code}
+      }
+    )(${JSON.stringify(args ?? {})})`
+
+    const result = await session.Runtime.evaluate({
+      expression,
+      returnByValue: true,
+      awaitPromise: true,
+    })
+
+    if (result.exceptionDetails) {
+      return {
+        error:
+          result.exceptionDetails.exception?.description ??
+          result.exceptionDetails.text,
+      }
+    }
+
+    return {
+      value: result.result?.value,
+      description: result.result?.description,
+    }
+  }
+
   async getDom(page: number, opts?: { selector?: string }): Promise<string> {
     const session = await this.resolveSession(page)
     const doc = await session.DOM.getDocument({ depth: 0 })

packages/browseros-agent/apps/server/src/tools/navigation.ts

@@ -299,13 +299,29 @@ export const close_page = defineNavigationTool({
 export const wait_for = defineNavigationTool({
   name: 'wait_for',
   description:
-    'Wait for text or a CSS selector to appear on the page. Polls periodically up to a timeout.',
+    'Wait for text or a CSS selector to appear or disappear on the page, or wait for a fixed time. Polls periodically up to a timeout.',
   input: z.object({
     page: pageParam,
     text: z.string().optional().describe('Text to wait for on the page'),
+    textGone: z
+      .string()
+      .optional()
+      .describe('Text to wait for to disappear from the page'),
     selector: z.string().optional().describe('CSS selector to wait for'),
+    selectorGone: z
+      .string()
+      .optional()
+      .describe('CSS selector to wait for to disappear from the page'),
+    time: z
+      .number()
+      .min(0)
+      .max(120000)
+      .optional()
+      .describe('Fixed wait time in milliseconds'),
     timeout: z
       .number()
+      .min(0)
+      .max(120000)
       .default(10000)
       .describe('Maximum wait time in milliseconds'),
   }),
@@ -316,40 +332,76 @@ export const wait_for = defineNavigationTool({
     timeout: z.number(),
   }),
   handler: async (args, ctx, response) => {
-    if (!args.text && !args.selector) {
-      response.error('Provide either text or selector to wait for.')
+    const timeout = args.timeout ?? 10_000
+    const target =
+      args.text !== undefined
+        ? `text "${args.text}"`
+        : args.textGone !== undefined
+          ? `text "${args.textGone}" to disappear`
+          : args.selector !== undefined
+            ? `selector "${args.selector}"`
+            : args.selectorGone !== undefined
+              ? `selector "${args.selectorGone}" to disappear`
+              : args.time !== undefined
+                ? `${args.time}ms`
+                : ''
+
+    if (
+      !args.text &&
+      !args.textGone &&
+      !args.selector &&
+      !args.selectorGone &&
+      args.time === undefined
+    ) {
+      response.error(
+        'Provide text, textGone, selector, selectorGone, or time to wait for.',
+      )
+      return
+    }
+
+    if (
+      args.time !== undefined &&
+      !args.text &&
+      !args.textGone &&
+      !args.selector &&
+      !args.selectorGone
+    ) {
+      await new Promise((resolve) => setTimeout(resolve, args.time))
+      response.text(`Waited ${args.time}ms.`)
+      response.data({
+        page: args.page,
+        found: true,
+        target,
+        timeout: args.time,
+      })
       return
     }
 
     const found = await ctx.browser.waitFor(args.page, {
       text: args.text,
+      textGone: args.textGone,
       selector: args.selector,
-      timeout: args.timeout,
+      selectorGone: args.selectorGone,
+      timeout,
     })
 
     if (found) {
-      const target = args.text
-        ? `text "${args.text}"`
-        : `selector "${args.selector}"`
       response.text(`Found ${target} on page.`)
       response.data({
         page: args.page,
         found,
         target,
-        timeout: args.timeout,
+        timeout,
       })
       response.includeSnapshot(args.page)
     } else {
-      const target = args.text
-        ? `text "${args.text}"`
-        : `selector "${args.selector}"`
       response.data({
         page: args.page,
         found,
         target,
-        timeout: args.timeout,
+        timeout,
       })
-      response.error(`Timed out after ${args.timeout}ms waiting for ${target}.`)
+      response.error(`Timed out after ${timeout}ms waiting for ${target}.`)
     }
   },
 })

packages/browseros-agent/apps/server/src/tools/registry.ts

@@ -43,12 +43,12 @@ import {
   new_hidden_page,
   new_page,
   show_page,
-  // biome-ignore lint/correctness/noUnusedImports: temporarily disabled
   wait_for,
 } from './navigation'
 import { suggest_app_connection, suggest_schedule } from './nudges'
 import { download_file, save_pdf, save_screenshot } from './page-actions'
 import {
+  browser_run_code,
   evaluate_script,
   get_page_content,
   get_page_links,
@@ -73,7 +73,7 @@ import {
 } from './windows'
 
 export const registry = createRegistry([
-  // Navigation (8)
+  // Navigation (9)
   get_active_page,
   list_pages,
   navigate_page,
@@ -82,9 +82,9 @@ export const registry = createRegistry([
   show_page,
   move_page,
   close_page,
-  // wait_for, // temporarily disabled
+  wait_for,
 
-  // Observation (9)
+  // Observation (10)
   take_snapshot,
   take_enhanced_snapshot,
   get_page_content,
@@ -93,6 +93,7 @@ export const registry = createRegistry([
   search_dom,
   take_screenshot,
   evaluate_script,
+  browser_run_code,
   get_console_logs,
 
   // Input (17)

packages/browseros-agent/apps/server/src/tools/snapshot.ts

@@ -246,3 +246,52 @@ export const evaluate_script = defineScriptTool({
     })
   },
 })
+
+export const browser_run_code = defineScriptTool({
+  name: 'browser_run_code',
+  description:
+    'Execute async custom JavaScript code in the page context. The code runs as an async function body with a serializable args object available and may use return to produce a result.',
+  input: z.object({
+    page: pageParam,
+    code: z
+      .string()
+      .describe(
+        'JavaScript function body to run in the page context. Use return to provide output.',
+      ),
+    args: z
+      .record(z.unknown())
+      .optional()
+      .describe('Serializable arguments available to the code as args'),
+  }),
+  output: z.object({
+    text: z.string(),
+    value: z.unknown().optional(),
+    description: z.string().optional(),
+  }),
+  handler: async (args, ctx, response) => {
+    const result = await ctx.browser.runCode(args.page, args.code, args.args)
+
+    if (result.error) {
+      response.error(`Code error: ${result.error}`)
+      return
+    }
+
+    const val = result.value
+    let text: string
+    if (val === undefined) {
+      text = result.description ?? 'undefined'
+      response.text(text)
+    } else if (typeof val === 'string') {
+      text = val
+      response.text(text)
+    } else {
+      text = JSON.stringify(val, null, 2)
+      response.text(text)
+    }
+    response.data({
+      text,
+      value: result.value,
+      description: result.description,
+    })
+  },
+})

packages/browseros-agent/apps/server/src/tools/tool-label-registry.ts

@@ -20,6 +20,7 @@ const VERB_OVERRIDES: Record<string, string> = {
   get_active_page: 'Got active tab',
   move_page: 'Moved tab',
   group_tabs: 'Grouped tabs',
+  wait_for: 'Waited for page state',
 
   // Page reading
   take_snapshot: 'Captured page snapshot',
@@ -47,6 +48,7 @@ const VERB_OVERRIDES: Record<string, string> = {
 
   // Console / scripts
   evaluate_script: 'Ran script',
+  browser_run_code: 'Ran custom page code',
   get_console_logs: 'Read console logs',
 
   // History / bookmarks
@@ -292,12 +294,9 @@ function canonicalName(rawName: string): string {
 function humanizeToolName(rawName: string): string {
   const stripped = canonicalName(rawName)
   const words = stripped.split(/[_-]/).filter((w) => w.length > 0)
-  if (words.length === 0) return rawName
-  const first = words[0]!
-  return [
-    first.charAt(0).toUpperCase() + first.slice(1),
-    ...words.slice(1),
-  ].join(' ')
+  const [first, ...rest] = words
+  if (!first) return rawName
+  return [first.charAt(0).toUpperCase() + first.slice(1), ...rest].join(' ')
 }
 
 /**