3 people af775d48c0 feat(fidelity): preserve dropped modifiers + full list transcription (#86) (#137) ...

Closes #111, #112, #113.

- Resolver recovers leading modifiers dropped by the head-noun reduction as
  <modifier> <head-noun> compounds (open white shirt -> white shirt + open
  shirt). KB-only, deterministic, no bare-word invention; goldens unchanged.
- Analyzer system prompt instructs full list transcription; a deterministic
  post-parse check warns SC0021 when a tag-list yields fewer concepts than items.
- Data-driven fidelity regression suite locks both failure modes.

Co-authored-by: kunail0804 <kunail0804@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-13 15:59:00 +02:00

..

__init__.py

chore: initialize repository structure and tooling (#1) (#45)

2026-07-07 16:59:32 +02:00

test_ollama_backend.py

fix(analyzer): escalate temperature on retries to self-recover malformed JSON (#81)

2026-07-10 21:18:41 +02:00

test_response_parser.py

fix(compiler): recover lost scene detail via 16.4k Danbooru KB + harden analyzer (#79)

2026-07-10 19:45:32 +02:00

test_scene_analyzer.py

feat(fidelity): preserve dropped modifiers + full list transcription (#86) (#137)

2026-07-13 15:59:00 +02:00

test_system_prompt.py

feat(analyzer): add the official Analyzer system prompt (#16) (#60)

2026-07-08 13:51:21 +02:00