Skip to content

fix(gateway): deliver .json and .md files sent via MEDIA: tags #33089

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ZMGID wants to merge 3 commits into from
Closed

fix(gateway): deliver .json and .md files sent via MEDIA: tags #33089

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c43dd41
fix(gateway): add json|md to MEDIA tag extension whitelist
ZMGID May 27, 2026
36774e9
test(gateway): cover json|md MEDIA tag extraction
ZMGID May 27, 2026
f7f0628
fix(gateway): add html|htm to MEDIA tag extension whitelist
ZMGID May 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion gateway/platforms/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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]+'|(?:~/|/)\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|json|md|html?|apk|ipa)(?=[\s`"',;:)\]}]|$))[`"']?'''
)
for match in media_pattern.finditer(content):
path = match.group("path").strip()
Expand Down
4 changes: 2 additions & 2 deletions gateway/run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16853,7 +16853,7 @@ def _clarify_callback_sync(question: str, choices) -> str:
r'MEDIA:((?:/|~\/)\S+\.(?:png|jpe?g|gif|webp|'
r'mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a|'
r'flac|epub|pdf|zip|rar|7z|docx?|xlsx?|pptx?|'
r'txt|csv|apk|ipa))',
r'txt|csv|json|md|html?|apk|ipa))',
re.IGNORECASE
)
for _match in _TOOL_MEDIA_RE.finditer(_hc):
Expand Down Expand Up @@ -17159,7 +17159,7 @@ def _approval_notify_sync(approval_data: dict) -> None:
r'MEDIA:((?:/|~\/)\S+\.(?:png|jpe?g|gif|webp|'
r'mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a|'
r'flac|epub|pdf|zip|rar|7z|docx?|xlsx?|pptx?|'
r'txt|csv|apk|ipa))',
r'txt|csv|json|md|html?|apk|ipa))',
re.IGNORECASE
)
for match in _TOOL_MEDIA_RE.finditer(content):
Expand Down
15 changes: 15 additions & 0 deletions tests/gateway/test_platform_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,6 +330,21 @@ 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_json_and_md_documents(self):
# Regression: .json and .md were missing from the extension whitelist,
# so these tags were never extracted and got delivered as raw text.
for path in ("/tmp/data.json", "/tmp/notes.md"):
media, cleaned = BasePlatformAdapter.extract_media(f"MEDIA:{path}")
assert media == [(path, False)]
assert cleaned == ""

def test_media_tag_supports_html_documents(self):
# Regression: .html/.htm were missing from the extension whitelist.
for path in ("/tmp/report.html", "/tmp/page.htm"):
media, cleaned = BasePlatformAdapter.extract_media(f"MEDIA:{path}")
assert media == [(path, 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
Expand Down