release: v0.7.0 — smart zoom, short metadata, frame descriptions#3
Merged
release: v0.7.0 — smart zoom, short metadata, frame descriptions#3
Conversation
… context Add OpenAI vision-powered features for video analysis and metadata generation across three new capabilities: **Smart zoom** — analyze extracted video frames via OpenAI vision API to identify action areas for dynamic crop panning. Per-frame fallback to center on API failure; no shared write when all frames fail. **Short metadata** — LLM-generated titles and descriptions for short video uploads via POST_RENDER hook. Frame descriptions from vision API are cached on plugin instance and fed as context to short metadata prompts. Writes to context.shared["uploads"]["google"] for Google plugin consumption. **Player context** — player name, assists, event type, and team level extracted from hook data and passed to short metadata prompts for richer AI-generated titles and descriptions. New modules: zoom.py, frames.py, short_metadata.py New config fields: smart_zoom_enabled, smart_zoom_model, short_metadata_enabled, frame_description_enabled, frame_description_model New prompt templates: smart_zoom_detect, frame_describe, short_title, short_description New hooks: ON_FRAMES_EXTRACTED, POST_RENDER 100% line + branch coverage (226 tests) Co-Authored-By: Claude <noreply@anthropic.com>
JRemitz
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
v0.7.0 adds three vision-powered capabilities to the OpenAI plugin:
zoom.py,ON_FRAMES_EXTRACTEDhook)short_metadata.py,frames.py,POST_RENDERhook), with frame descriptions fed as{{frame_summary}}context{{player}},{{assists}},{{event}},{{team_level}})New modules:
zoom.py,frames.py,short_metadata.pyNew hooks:
ON_FRAMES_EXTRACTED,POST_RENDERNew config fields:
smart_zoom_enabled,smart_zoom_model,short_metadata_enabled,frame_description_enabled,frame_description_modelTest plan
make checkpasses — lint, mypy, 226 tests, 100% line + branch coveragev0.7.0triggers PyPI release via GitHub Actions🤖 Generated with Claude Code