hokusai/bulkgen
Konstantin Fickel 0ecf1f0f9e
All checks were successful
Continuous Integration / Build Package (push) Successful in 48s
Continuous Integration / Lint, Check & Test (push) Successful in 1m1s
refactor: use project-named state file and store prompt/params directly
- State filename now derives from config: cards.bulkgen.yaml produces
  .cards.bulkgen-state.yaml instead of .bulkgen.state.yaml
- Store resolved prompt text and extra params directly in state file
  instead of hashing them, making state files human-readable
- Only file input contents remain hashed (SHA-256)
- Thread project_name through builder and CLI
- Remove hash_string() and _extra_hash() helpers
- Update .gitignore pattern to .*.bulkgen-state.yaml
2026-02-15 13:56:12 +01:00
..
providers feat: add OpenAI as provider for text and image generation 2026-02-15 13:48:06 +01:00
__init__.py feat: scaffold project structure with package dirs and mistralai dependency 2026-02-13 20:07:08 +01:00
builder.py refactor: use project-named state file and store prompt/params directly 2026-02-15 13:56:12 +01:00
cli.py refactor: use project-named state file and store prompt/params directly 2026-02-15 13:56:12 +01:00
config.py refactor: move model definitions into providers and extract resolve module 2026-02-15 11:03:57 +01:00
graph.py feat: support multiple reference images with model-aware API mapping 2026-02-14 17:19:54 +01:00
resolve.py refactor: move model definitions into providers and extract resolve module 2026-02-15 11:03:57 +01:00
state.py refactor: use project-named state file and store prompt/params directly 2026-02-15 13:56:12 +01:00