mateclaw/mateclaw-server/src/main
matevip 62b94b522f fix(dingtalk): make inbound images visible to vision model and chat UI
Three knots untangled so an image sent from DingTalk lands in both the
LLM's multimodal prompt and the chat history bubble:

- Prefer MessageContent.downloadCode (universal, used by the new
  api.dingtalk.com messageFiles/download) over pictureDownloadCode
  (legacy oapi field). Sending the legacy code to the new API got
  HTTP 500 unknownError, which was the original 'image not recognized'.
- After fetching bytes, persist to ~/.mateclaw/media/dingtalk/ so vision
  can read via FileSystemResource, AND stuff the same bytes into
  GeneratedFileCache so the UI gets an /api/v1/files/generated/{id} URL
  to render. Without the URL the message bubble showed an empty card.
- Carry filename / contentType / size on the MessageContentPart so the
  chat history doesn't fall back to the 'unknown' caption.

Same treatment applied to the richText branch (inline images from the
PC client) and threaded through the Stream SDK path.

Bundles in the prerequisite ChannelManager wiring of GeneratedFileCache
into DingTalkChannelAdapter and the new DingTalkMediaUploader used by
the outbound attachment flow that this work depends on.

Known limit: GeneratedFileCache TTL is 10 min — fresh refreshes work,
but viewing the image after a JVM restart needs a stable on-disk
serving endpoint, which is intentionally out of scope here.
2026-04-28 14:59:59 +08:00
..
java/vip/mate fix(dingtalk): make inbound images visible to vision model and chat UI 2026-04-28 14:59:59 +08:00
resources feat(channels): localize seeded channel names to Chinese on zh-CN installs 2026-04-28 11:10:44 +08:00