feat: prompt AI to use ReadMediaFile for video attachments instead of Python frame extraction#627
Open
bj456736 wants to merge 1 commit into
Open
Conversation
… Python frame extraction
|
commit: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
When users upload videos as attachments, the system renders them as
<video path="...">tags in the prompt. Previously, the system prompt only provided general guidance about "use proper tools or shell commands or Python packages to process... multimedia files", which often led the AI to write Python scripts to extract frames manually instead of using the built-inReadMediaFiletool.This was reported as feedback Q-0266: Kimi CLI 视频分析希望默认调用 ReadMediaFile 而不是写 Python 切帧.
Solution
Added an explicit instruction in the default system prompt (
packages/agent-core/src/profile/default/system.md):Why this approach
ReadMediaFilealready fully supports video files via thevideo_incapability andvideoUploader.ReadMediaFilerather than Python frame extraction.