mirror of https://github.com/hanzoai/video.git synced 2026-10-30 18:18:27 +00:00

Files

T

calesthio 355fd2b7d6 Implementation spec: governance, decision intelligence, theme system, and E2E bug fixes

Implements the 2026-04-02 transformation spec (Phases 1-8) and fixes all
critical bugs found during 5-pipeline E2E testing.

Governance & Decision Intelligence:
- Pipeline-specific stage order in checkpoint (replaces global STAGES list)
- Provider scoring engine (lib/scoring.py) with 7-dimension weighted ranking
- Decision log artifact enforced at proposal/idea stage across all 10 pipelines
- Delivery promise classifier prevents silent motion-to-still downgrades
- Structured shot language in scene_plan schema (camera, lens, lighting, DOF)
- Variation checker and slideshow risk scorer block samey output before render
- Creative intake, capability extension, and creative-intake meta skills
- Final self-review artifact with 5 mandatory checks before presenting output
- Source media review contract for user-supplied footage

Render & Theme System:
- Remotion AnimatedBackground now derives colors from playbook (no more hardcoded
  dark blue fintech gradient on every video)
- video_compose builds custom ThemeConfig from playbook YAML colors/fonts —
  custom playbooks flow through to Remotion automatically
- Explainer component wires theme to all child components (charts, cards, etc.)
- resolveAsset() handles absolute paths on Windows/Unix via file:// URIs
- RENDERER_FAMILY_MAP synced with actual Remotion compositions

Critical Bug Fixes:
- Windows npx subprocess: run_command() resolves .cmd wrappers via shutil.which()
- Silent renderer downgrade: Remotion failure now returns explicit error with
  options instead of silently falling back to FFmpeg
- .env inline comment parsing strips trailing # comments from API keys
- concat_path UnboundLocalError in video_compose finally block
- audio_mixer and showcase_card capture=True kwarg bug
- Selector estimate_cost() calls fixed (_select_tool -> _select_best_tool)
- asset_manifest schema expanded with provider, license, subtype fields
- screen-demo subtitle_gen moved from required to optional tools
- Duration drift detection in post-render final review (>25% warns)

2026-04-03 09:35:09 -07:00

2.0 KiB

Raw Permalink Blame History

Script Director - Localization Dub Pipeline

When To Use

Turn the approved localization brief into a transcript-backed, reviewable script package for every target language. This stage should create text truth before any dubbing audio is generated.

Reference Inputs

docs/localization-dubbing-best-practices.md
skills/creative/storytelling.md

Process

1. Build Source Transcript Truth

Start with the source transcript and fix obvious errors in:

names,
terminology,
speaker allocation,
numbers,
CTA phrasing.

2. Produce Reviewable Target Copy

For each target language, generate text that can be reviewed before synthesis. Record where terms should remain unchanged.

3. Preserve Structure Where Practical

Keep section timing and sequence aligned to the source unless the translation clearly needs a different pacing strategy.

4. Use Metadata For Localization Control

Recommended metadata keys:

source_transcript_status
target_language_sections
glossary_terms
protected_terms
pronunciation_notes
review_status_by_language

5. Quality Gate

the source transcript is strong enough to trust,
target-language copy exists for every planned deliverable,
glossary terms are preserved,
the script package can be reviewed before audio generation.

Mid-Production Fact Verification

If you encounter uncertainty during script writing:

Use web_search to verify factual claims before committing them to the script
Use web_search to find reference images for visual accuracy
Log verification in the decision log: category="visual_accuracy_check"

Every factual claim in the script should be traceable to the research_brief. If you make a claim that isn't in the research, do additional research and add the source. Do not invent statistics, dates, or attributions.

Common Pitfalls

Generating audio from an unreviewed transcript.
Letting product names drift across languages.
Treating translation text as final timing without acknowledging length drift.

2.0 KiB Raw Permalink Blame History