nanobot

mirror of https://github.com/HKUDS/nanobot.git synced 2026-05-20 08:32:25 +00:00

History

chengyongru c053f9eba8 fix(multimodal): image OOM guard, Feishu post media extraction, vision fallback

- Add file size pre-check via stat() before read_bytes() to prevent OOM
  on oversized images/audio/video
- Fix _extract_post_content to extract media tags (file_key) from Feishu
  post messages so videos are no longer silently dropped
- Add supports_vision=False guard to downgrade images to text placeholders
- Add video_mime_compat() for video format validation
- Use full file path in content_text so model read_file works if needed
- Pass input_limits to AgentLoop in nanobot.py facade
- Deduplicate _MEDIA_PLACEHOLDER_TYPES from LLMProvider constant
- Remove unused _extract_post_text legacy wrapper
- Add 14 new tests covering vision fallback, count limits, video compat

2026-04-09 01:13:40 +08:00

agent

fix(multimodal): image OOM guard, Feishu post media extraction, vision fallback

2026-04-09 01:13:40 +08:00

api

refactor: extract runtime response guards into utils runtime module

2026-04-02 13:54:40 +00:00

bus

fix: add from __future__ import annotations across codebase

2026-03-06 19:13:56 +08:00

channels

fix(multimodal): image OOM guard, Feishu post media extraction, vision fallback