fix(dingtalk): don't let richText re-derivation clobber VOICE classification

The msg_type_str == "richText" branch reset msg_type to PHOTO/TEXT after
the rich-text item scan had already promoted it (e.g. a native voice item
→ VOICE), dropping voice notes from the auto-STT path. Only re-derive when
the scan left the type at TEXT.

Ports the root-cause analysis from PR #38276 (stale, targeted the deleted
gateway/platforms/dingtalk.py) onto the live plugin adapter, with
regression tests.

Refs #38211 #38219 #38276

plugins/platforms/dingtalk/adapter.py

@@ -920,11 +920,15 @@ class DingTalkAdapter(BasePlatformAdapter):
         if msg_type_str == "picture" and not media_urls:
             msg_type = MessageType.PHOTO
         elif msg_type_str == "richText":
-            msg_type = (
-                MessageType.PHOTO
-                if any("image" in t for t in media_types)
-                else MessageType.TEXT
-            )
+            # Only re-derive the type when the rich-text scan above left it
+            # at TEXT. The scan may already have promoted it to VOICE/AUDIO/
+            # VIDEO/DOCUMENT for embedded media items — resetting those here
+            # dropped native voice notes back to TEXT and skipped STT
+            # (#38211, #38219; analysis from #38276).
+            if msg_type == MessageType.TEXT and any(
+                "image" in t for t in media_types
+            ):
+                msg_type = MessageType.PHOTO
         elif msg_type_str == "audio":
             # Voice message — DingTalk already provides recognition text.
             # Do NOT add media_urls here: if audio_paths is non-empty,

tests/gateway/test_dingtalk.py

@@ -735,6 +735,40 @@ class TestExtractMedia:
         assert urls == ["dl_voice_abc"]
         assert mtypes == ["audio"]
 
+    def test_richtext_reset_does_not_clobber_voice(self):
+        """A richText envelope containing a native voice item must stay
+        VOICE — the ``msg_type_str == "richText"`` re-derivation used to
+        reset it to TEXT, dropping the voice note from the STT path
+        (#38211, #38219)."""
+        from plugins.platforms.dingtalk.adapter import DingTalkAdapter
+        from gateway.platforms.base import MessageType
+
+        msg = self._msg_with_rich_text(
+            [{"type": "voice", "downloadCode": "dl_voice_rt"}]
+        )
+        msg.message_type = "richText"
+        msg_type, urls, mtypes = DingTalkAdapter._extract_media(
+            DingTalkAdapter, msg
+        )
+        assert msg_type == MessageType.VOICE
+        assert urls == ["dl_voice_rt"]
+        assert mtypes == ["audio"]
+
+    def test_richtext_with_image_still_photo(self):
+        """richText with only an embedded image keeps the PHOTO promotion."""
+        from plugins.platforms.dingtalk.adapter import DingTalkAdapter
+        from gateway.platforms.base import MessageType
+
+        msg = self._msg_with_rich_text(
+            [{"type": "picture", "downloadCode": "dl_img_rt"}]
+        )
+        msg.message_type = "richText"
+        msg_type, urls, mtypes = DingTalkAdapter._extract_media(
+            DingTalkAdapter, msg
+        )
+        assert msg_type == MessageType.PHOTO
+        assert urls == ["dl_img_rt"]
+
     def test_audio_rich_text_item_stays_audio(self):
         """Generic audio uploads (e.g. an mp3 the user attached) must NOT
         be auto-transcribed — they stay MessageType.AUDIO."""