Epic: Structural Segmentation & Role Topology Aggregation

[seonghobae]

Description

Replace the mock section extractor and part-graph topologies with real song boundary detection.

Tasks

• Implement self-similarity matrix (SSM) or novelty-curve based segmentation to identify structural boundaries (Intro, Verse, Chorus, Bridge, etc.).
• Implement logic to detect which stems (roles) are active within each detected boundary to build the real PartGraphNode handoffs.
• Fuse the temporal grid, chords, and lyrics (if available) into the final RehearsalSong IPC payload.
• Replace the hardcoded demo song generation in api.py with the integrated pipeline output.

Definition of Done

The analysis engine outputs a fully populated, reality-based JSON payload matching the IPC schema, dynamically adapting to the length, structure, and instrumentation of the input audio.

[coderabbitai]

🔗 Related PRs

#37 - feat: add shared rehearsal contract baseline [merged]
#85 - feat: complete section extraction pipeline [merged]
#86 - feat: implement role extraction target and part graph (closes #34) [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!