Implement real normalize stage

README.md

@@ -9,8 +9,7 @@ Implemented now:
 - strict config loading/validation (`pipeline.yml` and `session.yml`)
 - local workspace/session layout, locking, and manifest persistence
 - resumable stage control (`run`, `plan`, `resume`, `run-stage`, `status`)
-- real `prepare`, `transcribe`, `merge`, `polish`, `trim`, and `analyze` stages
-- placeholder `normalize` stage
+- real `prepare`, `transcribe`, `merge`, `polish`, `normalize`, `trim`, and `analyze` stages
 - real WhisperX, Seriatim, and Audita adapters
 - real Scriptorium subprocess adapter
 - optional Scriptorium render diagnostics (`render_debug`)
@@ -47,7 +46,7 @@ YAML decoding is strict (`KnownFields(true)`), so unknown fields fail fast.
 
 - `transcripts/merged.json`: canonical deterministic merged transcript from Seriatim merge
 - `transcripts/processed.json`: full polished transcript from Audita polish
-- `transcripts/normalized.json`: placeholder normalized transcript (Seriatim schema pass-through for now)
+- `transcripts/normalized.json`: Seriatim-normalized transcript from the normalize stage
 - `transcripts/trimmed.json`: gameplay-only polished transcript from trim stage
 
 ## Normalize Configuration