fix(qqbot): support HTML entities in media tags (< >) (#60493)

* fix(qqbot): 支持媒体标签中的 HTML 实体（< >）

* fix(qqbot): support HTML entities in media tags

* test(qqbot): add unit tests for media tag regex with HTML entities

* test(qqbot): export regex constants to enable unit tests

* fix(qqbot): reset regex lastIndex in tests to avoid state pollution

* test(qqbot): add .js extension to import in media-tags.test.ts

* fix(qqbot): support HTML entities in media tags (#60493) (thanks @ylc0919)

---------

Co-authored-by: sliverp <870080352@qq.com>

CHANGELOG.md

@@ -10,6 +10,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- QQBot/media-tags: support HTML entity-encoded angle brackets (`&lt;`/`&gt;`) in media-tag regexes so entity-escaped `<qqimg>` tags from upstream are correctly parsed and normalized. (#60493) Thanks @ylc0919.
 - Slack/media: preserve bearer auth across same-origin `files.slack.com` redirects while still stripping it on cross-origin Slack CDN hops, so `url_private_download` image attachments load again. (#62960) Thanks @vincentkoc.
 - Control UI: guard stale session-history reloads during fast session switches so the selected session and rendered transcript stay in sync. (#62975) Thanks @scoootscooob.
 

extensions/qqbot/src/utils/media-tags.test.ts

@@ -0,0 +1,32 @@
+import { describe, it, expect } from 'vitest';
+import { FUZZY_MEDIA_TAG_REGEX, SELF_CLOSING_TAG_REGEX } from './media-tags.js';
+
+describe('media-tags with HTML entities', () => {
+  it('extracts URL from entity-encoded fuzzy tag', () => {
+    const input = '<qqimg>https://example.com/a.png</qqimg>';
+    FUZZY_MEDIA_TAG_REGEX.lastIndex = 0; 
+    const match = FUZZY_MEDIA_TAG_REGEX.exec(input);
+    expect(match?.[2]).toBe('https://example.com/a.png');
+  });
+
+  it('extracts URL from mixed entity+plain tag', () => {
+    const input = '&lt;qqimg&gt;https://example.com/b.png</qqimg>';
+    FUZZY_MEDIA_TAG_REGEX.lastIndex = 0; 
+    const match = FUZZY_MEDIA_TAG_REGEX.exec(input);
+    expect(match?.[2]).toBe('https://example.com/b.png');
+  });
+
+  it('extracts file from entity-encoded self-closing tag', () => {
+    const input = '&lt;qqmedia file="https://example.com/c.zip" /&gt;';
+    SELF_CLOSING_TAG_REGEX.lastIndex = 0;
+    const match = SELF_CLOSING_TAG_REGEX.exec(input);
+    expect(match?.[2]).toBe('https://example.com/c.zip');
+  });
+
+  it('does not match invalid input', () => {
+    const input = 'no tag here';
+    FUZZY_MEDIA_TAG_REGEX.lastIndex = 0; 
+    const match = FUZZY_MEDIA_TAG_REGEX.exec(input);
+    expect(match).toBeNull();
+  });
+});

extensions/qqbot/src/utils/media-tags.ts

@@ -49,10 +49,12 @@ ALL_TAG_NAMES.sort((a, b) => b.length - a.length);
 
 const TAG_NAME_PATTERN = ALL_TAG_NAMES.join("|");
 
+const LEFT_BRACKET = "(?:[<＜<]|&lt;)";
+const RIGHT_BRACKET = "(?:[>＞>]|&gt;)";
 /** Match self-closing media-tag syntax with file/src/path/url attributes. */
-const SELF_CLOSING_TAG_REGEX = new RegExp(
+export const SELF_CLOSING_TAG_REGEX = new RegExp(
   "`?" +
-    "[<＜<]\\s*(" +
+    LEFT_BRACKET + "\\s*(" +
     TAG_NAME_PATTERN +
     ")" +
     "(?:\\s+(?!file|src|path|url)[a-z_-]+\\s*=\\s*[\"']?[^\"'/>＞>]*?[\"']?)*" +
@@ -62,23 +64,23 @@ const SELF_CLOSING_TAG_REGEX = new RegExp(
     "[\"']?" +
     "(?:\\s+[a-z_-]+\\s*=\\s*[\"']?[^\"'/>＞>]*?[\"']?)*" +
     "\\s*/?" +
-    "\\s*[>＞>]" +
+    "\\s*" + RIGHT_BRACKET +
     "`?",
   "gi",
 );
 
 /** Match malformed wrapped media tags that should be normalized. */
-const FUZZY_MEDIA_TAG_REGEX = new RegExp(
+export const FUZZY_MEDIA_TAG_REGEX = new RegExp(
   "`?" +
-    "[<＜<]\\s*(" +
+    LEFT_BRACKET + "\\s*(" +
     TAG_NAME_PATTERN +
-    ")\\s*[>＞>]" +
+    ")\\s*" + RIGHT_BRACKET +
     "[\"']?\\s*" +
     "([^<＜<＞>\"'`]+?)" +
     "\\s*[\"']?" +
-    "[<＜<]\\s*/?\\s*(?:" +
+    LEFT_BRACKET + "\\s*/?\\s*(?:" +
     TAG_NAME_PATTERN +
-    ")\\s*[>＞>]" +
+    ")\\s*" + RIGHT_BRACKET +
     "`?",
   "gi",
 );
@@ -94,13 +96,13 @@ function resolveTagName(raw: string): (typeof VALID_TAGS)[number] {
 
 /** Match wrapped tags whose bodies need newline and tab cleanup. */
 const MULTILINE_TAG_CLEANUP = new RegExp(
-  "([<＜<]\\s*(?:" +
+  "(" + LEFT_BRACKET + "\\s*(?:" +
     TAG_NAME_PATTERN +
-    ")\\s*[>＞>])" +
+    ")\\s*" + RIGHT_BRACKET + ")" +
     "([\\s\\S]*?)" +
-    "([<＜<]\\s*/?\\s*(?:" +
+    "(" + LEFT_BRACKET + "\\s*/?\\s*(?:" +
     TAG_NAME_PATTERN +
-    ")\\s*[>＞>])",
+    ")\\s*" + RIGHT_BRACKET + ")",
   "gi",
 );