fix(gateway): tighten MEDIA extraction regex + silent skip on file-not-found

Three related fixes for the MEDIA:<path> extraction pipeline that
caused 'file not found' noise in platform channels:

1. run.py — tighten tool-result MEDIA regex from \S+ (any non-
   whitespace) to require a path pattern with known extensions.
   Prevents LLM-generated placeholder paths like
   'MEDIA:/path/to/example.mp4' from being captured as real media.

2. base.py — remove the |\S+ fallback in extract_media() that
   catches anything non-whitespace as a potential MEDIA path.
   This was the primary cause of false positives — strings like
   '' in tool output were captured as MEDIA: paths.

3. mattermost.py — replace the file-not-found error message sent
   to the channel with a silent logger.warning() skip. When a
   path extracted by MEDIA doesn't exist on disk, the channel
   no longer gets a noisy '(file not found: ...)' message.

Impact: eliminates the persistent 'file not found' spam in
Mattermost channels caused by over-broad MEDIA regex patterns
matching non-path text in tool output.
This commit is contained in:
colin-chang 2026-05-18 20:07:36 -07:00 committed by Teknium
parent 09b6dcc4f3
commit ea49b38625
3 changed files with 20 additions and 5 deletions

View file

@ -2137,7 +2137,7 @@ class BasePlatformAdapter(ABC):
# 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`"',;:)\]}]|$)|\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|apk|ipa)(?=[\s`"',;:)\]}]|$))[`"']?'''
)
for match in media_pattern.finditer(content):
path = match.group("path").strip()

View file

@ -471,9 +471,10 @@ class MattermostAdapter(BasePlatformAdapter):
p = Path(file_path)
if not p.exists():
return await self.send(
chat_id, f"{caption or ''}\n(file not found: {file_path})", reply_to
logger.warning(
"Mattermost: local file not found, skipping: %s", file_path
)
return SendResult(success=True, message_id=None)
fname = file_name or p.name
ct = mimetypes.guess_type(fname)[0] or "application/octet-stream"

View file

@ -15778,7 +15778,14 @@ class GatewayRunner:
if _hm.get("role") in {"tool", "function"}:
_hc = _hm.get("content", "")
if "MEDIA:" in _hc:
for _match in re.finditer(r'MEDIA:(\S+)', _hc):
_TOOL_MEDIA_RE = re.compile(
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))',
re.IGNORECASE
)
for _match in _TOOL_MEDIA_RE.finditer(_hc):
_p = _match.group(1).strip().rstrip('",}')
if _p:
_history_media_paths.add(_p)
@ -16067,7 +16074,14 @@ class GatewayRunner:
if msg.get("role") in {"tool", "function"}:
content = msg.get("content", "")
if "MEDIA:" in content:
for match in re.finditer(r'MEDIA:(\S+)', content):
_TOOL_MEDIA_RE = re.compile(
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))',
re.IGNORECASE
)
for match in _TOOL_MEDIA_RE.finditer(content):
path = match.group(1).strip().rstrip('",}')
if path and path not in _history_media_paths:
media_tags.append(f"MEDIA:{path}")