Add opt-in local transcription with managed installation, cache warm-up,
and a one-time backend choice while preserving native-caption priority.
Correct frame timing and coverage, caption provenance and download
ownership, configuration parsing, provider pairing, and partial reports.
Update cross-host instructions, packaging, and test-gated release CI.
Validate 198 isolated tests, real local English and Spanish inference,
network-denied warm-cache inference, live captions/media, and packaging.
Record platform and account-dependent acceptance limits separately.
Frame extraction now runs a perceptual dedup pass (default on, --no-dedup
to disable) that drops near-identical frames before the budget cap, so the
budget goes to distinct content instead of held slides/static recordings.
The Frames report line notes how many near-duplicates were dropped.
Whisper transcription splits audio over the 25 MB upload cap into evenly
sized chunks, transcribes each, shifts segment timestamps back into source
time, and tolerates partial failures (only fails if every chunk fails) —
length alone no longer fails transcription.
token-burner is exempt from the long-video sparse-scan warning since it
keeps every scene-change frame. README/SKILL.md updated. Adds test_dedup.py and test_whisper.py.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
