tools/base_tool.py now auto-loads .env at import time so API keys are
available even when tools are imported directly (fixes silent zero-key
fallback in subagents). Added LUMINA bioluminescent terrarium product
ad embed to README. Two new demo compositions: 37 Trillion (one-key
narrated explainer) and LUMINA (music-driven product ad, no narration).
Prove that adding one API key (OPENAI_API_KEY) to the zero-key foundation
produces dramatically better videos for ~$0.69 each. Two compositions built:
The Abyss (deep ocean visual essay) and VOID (neural interface product ad).
New tools:
- audio_probe: ffprobe wrapper with probe_duration() helper
- composition_validator: pre-render checks (asset existence, audio-video sync)
- pixabay_music: royalty-free music scraper (no API key needed)
- freesound_music: Freesound API search + download
Remotion upgrades:
- BackgroundImageLayer: AI images behind data scenes with ken-burns + dark overlay
- Gradient support: all 9 components changed from backgroundColor to background CSS
- CaptionOverlay: word spacing fix, WhisperX word-level subtitles
- HeroTitle: reduced overlay opacity so background images show through
Process codified in agent skills:
- compose-director: audio acquisition flow (present user with voice/music/subtitle
options), mandatory pre-render validation, post-render self-review (extract
frames + transcribe + inspect + present findings to user)
- scene-director: narration duration budgeting (word budget from video duration)
- remotion skill: pre-render validation section
- TTS tool: now returns audio_duration_seconds in result
README updated with VOID product ad video embed.
- Fix Kling URL format: text_to_video → text-to-video (hyphens)
- Fix Kling, MiniMax, Veo: switch from sync fal.run to queue API with polling
- Add Rule Zero to AGENT_GUIDE: all production must go through pipelines
- Make Layer 3 skill reading mandatory before calling generation tools
- Add explicit do-nots: no ad-hoc scripts, no skipping director skills
Two new provider tools following the BaseTool pattern with auto-discovery:
- google_imagen: Imagen 4 image generation via Generative Language REST API
- google_tts: Google Cloud TTS with 700+ voices across 50+ languages
Both share GOOGLE_API_KEY env var. Selectors auto-discover them — no
selector code changes needed. Docs and contract tests updated.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
calesthio