* feat!: collapse pipeline — Resolver emits a flat prompt, drop categories (v1.1) BREAKING CHANGE: the Category Splitter and Prompt Builder stages and nodes are removed. The Resolver is now the translator from Scene JSON to prompt: it resolves concepts to Knowledge Base tags and joins them into one flat comma-separated prompt string, in resolution order (which naturally leads with character concepts). Resolver node outputs are now (prompt, warnings, errors, json) — the json being the traceable resolved tags so a translation problem is inspectable. Node count drops from 8 to 6. The CategoryMap/PromptOutput models and their schemas are removed; the `category` field remains on entries and resolved tags for traceability only. Debug Viewer simplified to scene/warnings/errors. Goldens, example scenes/workflow, integration/performance/repo-layout/release tests, benchmark script, and the docs (README + wiki) are updated to the flat prompt. Version bumped to 1.1.0. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * build: drop removed splitter/builder packages from pyproject Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: kunail0804 <kunail0804@gmail.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Golden files & the regression convention
This directory holds the golden outputs for the ten reference scenes
(MASTER_SPEC §26.8): the exact prompt outputs each scene compiles to. The golden
tests (tests/regression/test_golden.py) assert exact equality, guarding
determinism — the same input, Knowledge Base, and configuration must always
produce identical output.
The reference scenes themselves are defined in
tests/regression/golden_scenes.py.
Regenerating goldens (deliberate only)
Goldens are never regenerated automatically. When a change is intended to alter compiler output — for example a Knowledge Base edit or a formatting change — regenerate them explicitly and review the diff before committing:
python scripts/regenerate_goldens.py
git diff tests/regression/golden/
If the golden tests fail and the change was not intended to alter output, that is a real regression — fix the code, do not regenerate.
Regression convention
Every fixed bug adds a permanent regression test that is never removed. Put scene-level regressions here (a new reference scene plus its golden) and unit-level regressions in the relevant stage's test module. Regression tests are part of the long-term validation suite and only grow.