- 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
Add comprehensive audio and video support across the agent pipeline:
- Generalize media placeholder system: _strip_image_content → _strip_media_content,
_media_placeholder with type-specific labels, unified across providers
- Add detect_audio_mime with magic-byte detection and filename fallback
- Add _AUDIO_FORMAT_MAP for correct MIME-to-API-format conversion
- Add InputLimitsConfig with count limits (max_input_audios/videos) and byte limits
- Support input_audio blocks in context builder with OpenAI-compatible format
- Support video_url blocks with base64 inline data
- Add audio/video passthrough in Codex provider, placeholder fallback in Anthropic provider
- Thread supports_vision/audio/video capability flags through AgentLoop
- Unify placeholder format: [audio: path]/[video: path] instead of generic [file: path]
- Optimize file I/O: single read_bytes() instead of header+full double reads
- Extract _STRIP_MEDIA_TYPES as class constant to avoid per-call allocation
