fix(security): extract shared stripHtmlToText() utility (fixes #18-24)

- Create src/utils/stripHtml.ts with he-based HTML-to-text conversion
- Replace bingAdapter's inline regex+decodeHtmlEntities with stripHtmlToText()
- Replace WebBrowserTool's inline regex chain with stripHtmlToText()
- Add stripHtml.test.ts with 6 test cases
- Update bingAdapter test expectation for whitespace normalization

Test: 3068 pass, 0 fail

packages/builtin-tools/src/tools/WebBrowserTool/WebBrowserTool.ts

@@ -2,6 +2,7 @@ import { z } from 'zod/v4'
 import type { ToolResultBlockParam } from 'src/Tool.js'
 import { buildTool } from 'src/Tool.js'
 import { lazySchema } from 'src/utils/lazySchema.js'
+import { stripHtmlToText } from 'src/utils/stripHtml.js'
 
 const WEB_BROWSER_TOOL_NAME = 'WebBrowser'
 
@@ -117,12 +118,7 @@ Use this for:
         const title = titleMatch?.[1]?.trim() ?? ''
 
         // Extract text content (strip HTML tags, scripts, styles)
-        let textContent = html
-          .replace(/<script[\s\S]*?<\/script>/gi, '')
-          .replace(/<style[\s\S]*?<\/style>/gi, '')
-          .replace(/<[^>]+>/g, ' ')
-          .replace(/\s+/g, ' ')
-          .trim()
+        let textContent = stripHtmlToText(html)
 
         // Truncate to reasonable size
         if (textContent.length > 50_000) {

packages/builtin-tools/src/tools/WebSearchTool/__tests__/bingAdapter.test.ts

@@ -244,7 +244,7 @@ describe('extractBingResults', () => {
     `
     const results = extractBingResults(html)
     expect(results).toHaveLength(1)
-    expect(results[0].title).toBe('Whitespace  Title')
+    expect(results[0].title).toBe('Whitespace Title')
   })
 
   test('handles snippet with HTML entities', () => {

packages/builtin-tools/src/tools/WebSearchTool/adapters/bingAdapter.ts

@@ -6,6 +6,7 @@
 import axios from 'axios'
 import he from 'he'
 import { AbortError } from 'src/utils/errors.js'
+import { stripHtmlToText } from 'src/utils/stripHtml.js'
 import type { SearchResult, SearchOptions, WebSearchAdapter } from './types.js'
 
 const FETCH_TIMEOUT_MS = 30_000
@@ -137,7 +138,7 @@ export function extractBingResults(html: string): SearchResult[] {
     const url = resolveBingUrl(rawUrl)
     if (!url) continue
 
-    const title = decodeHtmlEntities(titleHtml.replace(/<[^>]+>/g, '').trim())
+    const title = stripHtmlToText(titleHtml)
 
     // Extract snippet: try b_lineclamp → b_caption <p> → b_caption fallback
     const snippet = extractSnippet(block)
@@ -153,7 +154,7 @@ function extractSnippet(block: string): string | undefined {
   const lineclampRegex = /<p[^>]*class="b_lineclamp[^"]*"[^>]*>([\s\S]*?)<\/p>/i
   let match = lineclampRegex.exec(block)
   if (match) {
-    return decodeHtmlEntities(match[1].replace(/<[^>]+>/g, '').trim())
+    return stripHtmlToText(match[1])
   }
 
   // 2. Try <p> inside b_caption
@@ -161,7 +162,7 @@ function extractSnippet(block: string): string | undefined {
     /<div[^>]*class="b_caption[^"]*"[^>]*>[\s\S]*?<p[^>]*>([\s\S]*?)<\/p>/i
   match = captionPRegex.exec(block)
   if (match) {
-    return decodeHtmlEntities(match[1].replace(/<[^>]+>/g, '').trim())
+    return stripHtmlToText(match[1])
   }
 
   // 3. Fallback: any text inside b_caption <div>
@@ -169,8 +170,8 @@ function extractSnippet(block: string): string | undefined {
     /<div[^>]*class="b_caption[^"]*"[^>]*>([\s\S]*?)<\/div>/i
   const fallbackMatch = fallbackRegex.exec(block)
   if (fallbackMatch) {
-    const text = fallbackMatch[1].replace(/<[^>]+>/g, '').trim()
-    if (text) return decodeHtmlEntities(text)
+    const text = stripHtmlToText(fallbackMatch[1])
+    if (text) return text
   }
 
   return undefined

src/utils/__tests__/stripHtml.test.ts

@@ -0,0 +1,30 @@
+import { describe, expect, test } from 'bun:test'
+import { stripHtmlToText } from '../stripHtml.js'
+
+describe('stripHtmlToText', () => {
+  test('removes HTML tags', () => {
+    expect(stripHtmlToText('<p>Hello <b>world</b></p>')).toBe('Hello world')
+  })
+
+  test('decodes HTML entities', () => {
+    expect(stripHtmlToText('&lt;script&gt;alert(1)&lt;/script&gt;')).toBe(
+      '<script>alert(1)</script>',
+    )
+  })
+
+  test('removes script blocks', () => {
+    expect(stripHtmlToText('<script>evil()</script>safe')).toBe('safe')
+  })
+
+  test('removes style blocks', () => {
+    expect(stripHtmlToText('<style>body{}</style>text')).toBe('text')
+  })
+
+  test('handles empty input', () => {
+    expect(stripHtmlToText('')).toBe('')
+  })
+
+  test('collapses excess whitespace', () => {
+    expect(stripHtmlToText('a   b\n\n\nc')).toBe('a b\n\nc')
+  })
+})

src/utils/stripHtml.ts

@@ -0,0 +1,27 @@
+/**
+ * Strip HTML tags and decode entities, producing plain text.
+ * Uses the `he` library for entity decoding (already a dependency).
+ */
+import he from 'he'
+
+export function stripHtmlToText(html: string): string {
+  return (
+    he
+      .decode(
+        html
+          // Remove script/style blocks and their content
+          .replace(/<script[\s\S]*?<\/script>/gi, '')
+          .replace(/<style[\s\S]*?<\/style>/gi, '')
+          // Replace <br>, <p>, <li>, <tr> with newlines
+          .replace(/<(br|p|li|tr)\b[^>]*\/?>/gi, '\n')
+          // Replace </p>, </li>, </tr>, </div>, </h[1-6]> with newlines
+          .replace(/<\/(p|li|tr|div|h[1-6])>/gi, '\n')
+          // Remove remaining HTML tags
+          .replace(/<[^>]*>/g, ''),
+      )
+      // Collapse multiple whitespace/newlines
+      .replace(/\n{3,}/g, '\n\n')
+      .replace(/[ \t]{2,}/g, ' ')
+      .trim()
+  )
+}