feat: prefer ReadMediaFile over manual frame extraction for video analysis#485
Open
bj456736 wants to merge 1 commit into
Open
feat: prefer ReadMediaFile over manual frame extraction for video analysis#485bj456736 wants to merge 1 commit into
bj456736 wants to merge 1 commit into
Conversation
…ual frame extraction Adds explicit guidance in system prompt to prefer ReadMediaFile tool over writing Python/ffmpeg scripts when analyzing video content. This prevents inefficient manual frame extraction and leverages built-in multimodal capabilities. - Modified system.md General Guidelines for Research and Data Processing - Target task: Kimi CLI 视频分析希望默认调用 ReadMediaFile 而不是写 Python 切帧
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds explicit guidance in the system prompt to prefer the
ReadMediaFiletool over writing Python/ffmpeg scripts when analyzing video content.Problem
When users share video files with Kimi Code CLI, the AI may default to writing Python scripts or ffmpeg commands to extract frames manually. This is inefficient and fails to leverage the built-in multimodal
video_incapability.Solution
Modified
system.mdin the General Guidelines for Research and Data Processing section to explicitly state:Changes
packages/agent-core/src/profile/default/system.md: updated one line in the multimedia processing guideline.Testing
prompt-placeholders.test.ts: 4 tests passagent-profile-loader.test.ts: 6 tests passRelated Task
Kimi CLI 视频分析希望默认调用 ReadMediaFile 而不是写 Python 切帧 (P0)