1.5 KiB
1.5 KiB
This sprint passes only if all of the following are true:
- The live validation target is the already-open song.als project.
- Exact MCP calls and exact raw results are recorded for the validated live tool sequence.
- At least one real Arrangement edit is applied through the MCP path on the open project.
- At least one real Arrangement MIDI operation is applied on the open project, or the report proves the exact runtime limitation with raw evidence.
- Harmonic MIDI backbone exists in Arrangement as meaningful content over materially more of the song than before.
- Before and after project-audit metrics are captured from the real open project with exact values.
- The after state shows at least one concrete improvement in coherence metrics, such as fewer silence islands, fewer mirrored pairs, stronger harmonic coverage, or reduced repeated-source dominance.
- Snare selectivity is validated in the real selection path, not only described from source code.
- All changed Python files compile.
- Relevant tests for touched MCP/runtime/coherence code pass.
- The validation report is strict and honest about what was and was not validated live.
- Codex can reasonably return pass from repository evidence alone.
Automatic fail conditions:
- validation remains code-only
- no exact MCP call log exists
- no before/after metrics exist
- no live edit was applied to song.als
- the run validates against a new generated song or different session
- the report claims completion without runtime evidence