release: v0.8.0 — smart zoom, render metadata, frame descriptions#4
Merged
release: v0.8.0 — smart zoom, render metadata, frame descriptions#4
Conversation
…r context First release since v0.4.2. Adds OpenAI vision-powered video analysis and LLM-generated metadata for rendered clips. Smart zoom — analyze extracted video frames via OpenAI vision API to identify action areas for dynamic crop panning. Per-frame fallback on API failure. Render metadata — LLM-generated titles and descriptions for rendered clips via POST_RENDER hook. Frame descriptions from vision API cached on plugin instance and fed as context. Player name, assists, event type, and team level extracted from hook data for richer prompts. Frame descriptions — multi-frame vision analysis generating per-frame descriptions and overall play summary. Renamed short_metadata → render_metadata for platform-agnostic output. Writes to context.shared["render_metadata"] instead of Google-specific path. Consolidated changelog for single v0.8.0 release. Updated CLAUDE.md module table and hook documentation. Co-Authored-By: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
First release since v0.4.2. Adds three OpenAI vision-powered capabilities:
zoom.py,ON_FRAMES_EXTRACTEDhook)render_metadata.py,POST_RENDERhook), with frame descriptions and player/event context fed as template variablesframes.py)Also includes: consolidated changelog, updated CLAUDE.md, renamed
short_metadata→render_metadatafor platform-agnostic output.Test plan
make checkpasses — lint, mypy, 225 tests, 100% line + branch coveragev0.8.0triggers PyPI release via GitHub Actionsreeln render short --smart --zoom-frames 16withrender_metadata_enabled: trueandframe_description_enabled: true🤖 Generated with Claude Code