feat: Expanded WeCom message parsing to capture msgtype, inline voice/video… (#1843)

* Expanded WeCom message parsing to capture msgtype, inline voice/video/file/link data, bounded base64 downloads, and richer mixed-message attachments (src/langbot/libs/wecom_ai_bot_api/api.py); added event accessors for new fields (src/langbot/libs/wecom_ai_bot_api/wecombotevent.py).
Converter now maps richer WeCom payloads (text, images, files, voice, video, links) into platform message chain with fallbacks when nothing parsable is present (src/langbot/pkg/platform/sources/wecombot.py).
Preprocessor now turns voice inputs into file URLs for downstream runners (src/langbot/pkg/pipeline/preproc/preproc.py).
Dify runner uploads all incoming files (images/audio/video/docs) after downloading or decoding data URLs, infers MIME types, and passes typed file descriptors into chat/workflow calls (src/langbot/pkg/provider/runners/difysvapi.py).

* Update src/langbot/pkg/platform/sources/wecombot.py

Fixed the issue of duplicate text in the comments.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/langbot/libs/wecom_ai_bot_api/api.py

Modify the way you approach challenges.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/langbot/pkg/platform/sources/wecombot.py

Changing the variable names makes more sense.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* feat: use from_base64 for the voice file converting

---------

Co-authored-by: tabriswang <tabriswang@finecomn.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
This commit is contained in:
Yaguang.Wang
2025-12-05 22:33:15 +08:00
committed by GitHub
parent 45e61befac
commit cb7c9af25c
6 changed files with 400 additions and 65 deletions
@@ -111,6 +111,12 @@ class PreProcessor(stage.PipelineStage):
):
if me.base64 is not None:
content_list.append(provider_message.ContentElement.from_image_base64(me.base64))
elif isinstance(me, platform_message.Voice):
# 转成文件链接,让下游 runner 上传到目标模型
if me.base64:
content_list.append(provider_message.ContentElement.from_file_base64(me.base64, 'voice.silk'))
elif me.url:
content_list.append(provider_message.ContentElement.from_file_url(me.url, 'voice'))
elif isinstance(me, platform_message.File):
# if me.url is not None:
content_list.append(provider_message.ContentElement.from_file_url(me.url, me.name))