langchain-ai/deepagents · error · ChannelMediaError

unsupported media mime type: {mime}

Error message

unsupported media mime type: {mime}

What it means

`_media_type` only accepts files whose guessed MIME type starts with `image/` or `video/`. Any other recognized MIME type (audio, documents, archives, etc.) is rejected with `ChannelMediaError` so channels never forward non-image/non-video attachments to the agent.

Source

Thrown at libs/talon/deepagents_talon/channels/base.py:492

    window = text[:limit]
    for delimiter in ("\n\n", "\n", " "):
        index = window.rfind(delimiter)
        if index > 0:
            return index + len(delimiter)
    return limit


def _media_type(path: Path) -> str:
    mime, _ = mimetypes.guess_type(path)
    if mime is None:
        msg = f"unsupported media file type: {path}"
        raise ChannelMediaError(msg)
    if mime.startswith("image/"):
        return "image"
    if mime.startswith("video/"):
        return "video"
    msg = f"unsupported media mime type: {mime}"
    raise ChannelMediaError(msg)


_RETRYABLE_ERROR_FRAGMENTS = frozenset(
    {
        "connectionerror",
        "connectionreset",
        "connectionrefused",
        "connecttimeout",
        "timeout",
        "broken pipe",
        "remotedisconnected",
        "eoferror",
        "network",
        "transient",
    }
)

View on GitHub (pinned to a1af029e6e)

Solutions

1. Send only image or video files; convert other content to an image/video if needed.
2. Filter attachments by MIME type before calling `validate_media` and skip or flag unsupported types.
3. If document support is required, request/extend the channel's media handling rather than bypassing validation.

Example fix

# before
validate_media(Path('voice_note.ogg'))  # audio/ogg -> ChannelMediaError
# after
if (mime := mimetypes.guess_type('voice_note.ogg')[0]) and mime.startswith(('image/', 'video/')):
    validate_media(Path('voice_note.ogg'))

import mimetypes
from pathlib import Path
def is_image_or_video(path: Path) -> bool:
    mime, _ = mimetypes.guess_type(path)
    return bool(mime) and (mime.startswith("image/") or mime.startswith("video/"))

if not is_image_or_video(attachment):
    skip(attachment)

def is_supported_mime(mime: str | None) -> bool:
    return mime is not None and mime.startswith(("image/", "video/"))

try:
    validate_media(path)
except ChannelMediaError as exc:
    notify_sender(f"Attachment not supported (images/videos only): {exc}")

When it happens

Trigger: Calling `validate_media` on a file with a known but unsupported MIME type, e.g. `.mp3` (audio/mpeg), `.pdf` (application/pdf), `.zip`, or `.txt`.

Common situations: Users send voice notes, documents, or compressed archives over Telegram and the pipeline tries to attach them; automation forwards arbitrary files into the channel media directory.

Related errors

• unsupported media file type: {path}
• media file type {detected!r} does not match requested type {
• media file is too large: {size} bytes exceeds {max_bytes}
• {media.media_type} media is too large: {size} bytes exceeds
• unsupported outbound media file type: {path}

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/def3a32f36b5a6d0. Report an issue: GitHub.