fix: support Windows paths in media extraction

gateway/platforms/base.py

@@ -2413,7 +2413,7 @@ def extract_media(content: str) -> Tuple[List[Tuple[str, bool]], str]:
         # Extract MEDIA:<path> tags, allowing optional whitespace after the colon
         # and quoted/backticked paths for LLM-formatted outputs.
         media_pattern = re.compile(
-            r'''[`"']?MEDIA:\s*(?P<path>`[^`\n]+`|"[^"\n]+"|'[^'\n]+'|(?:~/|/)\S+(?:[^\S\n]+\S+)*?\.(?:png|jpe?g|gif|webp|mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a|flac|epub|pdf|zip|rar|7z|docx?|xlsx?|pptx?|txt|csv|apk|ipa)(?=[\s`"',;:)\]}]|$))[`"']?'''
+            r'''[`"']?MEDIA:\s*(?P<path>`[^`\n]+`|"[^"\n]+"|'[^'\n]+'|(?:~/|/|[A-Za-z]:[\\/])\S+(?:[^\S\n]+\S+)*?\.(?:png|jpe?g|gif|webp|mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a|flac|epub|pdf|zip|rar|7z|docx?|xlsx?|pptx?|txt|csv|apk|ipa)(?=[\s`"',;:)\]}]|$))[`"']?'''
         )
         for match in media_pattern.finditer(content):
             path = match.group("path").strip()
@@ -2477,9 +2477,9 @@ def extract_local_files(content: str) -> Tuple[List[str], str]:
 
         # (?<![/:\w.]) prevents matching inside URLs (e.g. https://…/img.png)
         #             and relative paths (./foo.png)
-        # (?:~/|/)    anchors to absolute or home-relative paths
+        # (?:~/|/|[A-Za-z]:[\\/]) anchors to absolute, home-relative, or Windows drive paths
         path_re = re.compile(
-            r'(?<![/:\w.])(?:~/|/)(?:[\w.\-]+/)*[\w.\-]+\.(?:' + ext_part + r')\b',
+            r'(?<![/:\w.])(?:~/|/|[A-Za-z]:[\\/])(?:[\w.\-]+[\\/])*[\w.\-]+\.(?:' + ext_part + r')\b',
             re.IGNORECASE,
         )
 

tests/gateway/test_extract_local_files.py

@@ -60,6 +60,18 @@ def test_tilde_path_image(self):
         assert paths == ["/home/user/photos/cat.jpg"]
         assert "~/photos/cat.jpg" not in cleaned
 
+    def test_windows_drive_path(self):
+        paths, cleaned = _extract("Report at D:/hermes-workspace/report.txt attached")
+        assert paths == ["D:/hermes-workspace/report.txt"]
+        assert "D:/hermes-workspace/report.txt" not in cleaned
+        assert "Report at" in cleaned
+
+    def test_windows_backslash_path(self):
+        text = r"Report at D:\hermes-workspace\report.txt attached"
+        paths, cleaned = _extract(text)
+        assert paths == [r"D:\hermes-workspace\report.txt"]
+        assert r"D:\hermes-workspace\report.txt" not in cleaned
+
     def test_video_extensions(self):
         for ext in (".mp4", ".mov", ".avi", ".mkv", ".webm"):
             text = f"Video at /tmp/clip{ext} here"
@@ -337,10 +349,10 @@ def test_path_with_spaces_not_matched(self):
         paths, _ = _extract("File at /tmp/my file.png here")
         assert paths == []
 
-    def test_windows_path_not_matched(self):
-        """Windows-style paths should not match."""
+    def test_windows_path_matched(self):
+        """Windows-style drive paths are supported for Windows hosts."""
         paths, _ = _extract("See C:\\Users\\test\\image.png")
-        assert paths == []
+        assert paths == ["C:\\Users\\test\\image.png"]
 
     def test_relative_path_not_matched(self):
         """Relative paths like ./image.png should not match."""

tests/gateway/test_platform_base.py

@@ -330,6 +330,19 @@ def test_media_tag_supports_unquoted_flac_paths_with_spaces(self):
         assert media == [("/tmp/Jane Doe/speech.flac", False)]
         assert cleaned == ""
 
+    def test_media_tag_supports_windows_drive_paths(self):
+        content = "Report attached\nMEDIA:D:/hermes-workspace/report.txt"
+        media, cleaned = BasePlatformAdapter.extract_media(content)
+        assert media == [("D:/hermes-workspace/report.txt", False)]
+        assert "MEDIA:" not in cleaned
+        assert "Report attached" in cleaned
+
+    def test_media_tag_supports_windows_backslash_paths(self):
+        content = r"MEDIA:D:\hermes-workspace\report.txt"
+        media, cleaned = BasePlatformAdapter.extract_media(content)
+        assert media == [(r"D:\hermes-workspace\report.txt", False)]
+        assert cleaned == ""
+
     def test_as_document_directive_stripped_from_cleaned_text(self):
         """[[as_document]] is a routing directive — strip it from
         user-visible text just like [[audio_as_voice]]. Callers detect the