Go to file

profit 17e410751c Phase 2: Production Bible — Character + Location bibles from scene data

Layer 3 implementation:
- Character Bible: canonical names, aliases, arcs, relationships, wardrobe
  states, emotional arcs, reference prompts — all grounded in scene evidence
- Location Bible: canonical names, variants, descriptions, types, features,
  mood associations, reference prompts — all grounded in scene evidence
- Combined Production Bible output for downstream layers
- Bible validator: duplicate detection, scene reference checks, hallucination
  detection, UNKNOWN field flagging
- Prompt contracts: L3_character_bible_v1, L3_location_bible_v1
- Named versioned output: character_bible_v1.json, location_bible_v1.json,
  production_bible_v1.json
- CLI: --phase 2 runs bible only, --phase omitted runs both phases
- OutputWriter: added write_named/write_named_raw for non-scene outputs

Tested on the_last_backup: 3 characters, 5 locations, 0 hallucinations,
3 warnings (UNKNOWN physical_description — correct behavior)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-06 16:51:55 -07:00

src

Phase 2: Production Bible — Character + Location bibles from scene data

2026-04-06 16:51:55 -07:00

test_scripts

Add Ollama backend + Qwen3 local inference support

2026-04-06 16:28:53 -07:00

.env.example

Phase 1 implementation: script ingestion + AI extraction pipeline

2026-04-06 15:49:43 -07:00

.gitignore

Phase 1 implementation: script ingestion + AI extraction pipeline