100%

07 — Functional Acceptance + Coherence Sweep

Goal

Prove it on the real production path: run the redesigned system on the representative grind target via the autopilot loop and assert the plan-wide functional criteria; finish with a plan-agnostic audit + full test + binding-parity sweep.

Implementation Sketch

  • drive /continue-roadmap —autopilot on the grind target; let trigger->generate->verify->attempt->ratify run.
  • run evolution_metrics.py; assert the three plan-wide functional criteria.
  • run the plan-agnostic audit (grep generic runtime for plan-name/domain hard-coding), full pytest sweep, binding-parity check, 24-entries-valid.

Spec References

  • .claude/rules/skill-control-contract.md §Autopilot Mode (the real loop)
  • script-first.md §11 plan-agnostic audit; scripts/ledger_evolution_runtime/tests/
  • learning-ledger.md §5 append-only (24 historical entries stay valid)

Work Items

  • Run the redesigned system end-to-end on the representative grind target via the /continue-roadmap —autopilot loop (trigger -> generate -> verify -> attempt -> ratify) — the REAL production entry point, not a seam-injected stub.
  • Functional acceptance: evolution_metrics.py on the grind target satisfies the plan-wide functional criteria (ratified >= 1, measurement_rate > 0.25, coverage >= 2).
  • Coherence sweep: plan-agnostic/domain-agnostic audit (script-first.md §11 — no plan-name/domain term hard-coding in generic runtime), full scripts/ledger_evolution_runtime/tests/ pytest sweep, v2/v7 binding parity, and confirm the 24 historical entries remain valid.

Fresh intel (regenerated)

{ “schema_version”: 1, “target”: { “kind”: “plan-section”, “ref”: “evolution-empirical-redesign/s-183969d9” }, “generated_at”: “2026-06-20T00:56:03.109288+00:00”, “graph_state”: { “head_sha”: “e4b7c39a”, “last_code_import_at”: “2026-06-20T00:50:59.91Z”, “embedding_stale”: false, “insights_stale”: false, “cpg_stale”: false }, “surfaces”: {}, “summary”: “intel-package[plan-section:evolution-empirical-redesign/s-183969d9] agent-authored dossier”, “degraded”: false, “dossier”: { “objective_symbols”: [], “tiers”: {}, “agent_authored”: true, “difficulty”: { “class”: “routine”, “research_online”: false, “research_mode”: “auto”, “signals”: [], “plan_dir”: “/home/eric/projects/ori_lang/plans/evolution-empirical-redesign” } } }

(full dossier: acceptance-coherence—s-183969d9.intel.json)