fix(multimodal): support HTML image tags in document extraction and chat responses

- Replace plain image URLs with `<img src="..." data-url="...">` HTML tags in multimodal and document extractor services
- Propagate citations from workflow end events to client responses
- Update system prompts to instruct LLMs to render images using Markdown `![alt](url)` with strict UUID-preserving URL copying
This commit is contained in:
Timebomb2018
2026-04-27 17:56:58 +08:00
parent 3d9882643e
commit 531d785629
6 changed files with 27 additions and 12 deletions

View File

@@ -296,7 +296,7 @@ async def chat(
}
)
# 多 Agent 非流式返回
# workflow 非流式返回
result = await app_chat_service.workflow_chat(
message=payload.message,