feat(programs): open Domain Knowledge Program v1 — 7-stage production line + per-domain KPI

The real bottleneck is domain MODELLING. Phase B is organized as one program with sub-programs per
domain, each run through the SAME 7-stage production line. No new runtime framework, no new module
(ADR-009, Freeze v1.0) — only program data + a derived reporting view.

- Customer enters by INDUSTRY, not regulation: Industry -> Domain Model -> Requirement Sources ->
  Requirements -> Capabilities -> ... -> Completeness.
- 7-stage checklist identical for every domain (Domain Model / Requirement Sources / Capability
  Registry / Transition Patterns / Playbooks / Reference Scenarios / Completeness) with per-stage
  ownership. README generalized to the framework.
- Each domain lists typical_requirement_sources + typical_certifications -> pre-onboarding capability
  HYPOTHESIS (the ETO insight; feeds Company 2A as inferred, never confirmed).
- Backlog v1 (by customer value): 1 Industrial Automation, 2 Environmental, 3 Automotive, 4 Medical,
  5 Energy. Five domain-definition shells (environmental restructured to the unified shape, law-first
  preserved).
- Per-domain KPI is DERIVED from the real corpus (computed-not-stored; sources modelled / transition
  patterns / playbooks / reference scenarios), NOT a curated number. Reference suite renders maturity
  bars: Industrial Automation 43% (3/7 sources) leads, Environmental 0% (work ahead). Backlog (value)
  and KPI (corpus state) are deliberately separated.
- ADR-009: Domain Knowledge Program framework. Honest known refinement: regulation-ID normalization
  (CRA vs Cyber Resilience Act) aliased in the KPI.

7 program-contract tests (backlog order + industry-first + derived-not-stored), check-loc 0.
Knowledge data + ADR + reference harness = non-runtime -> no deploy (ADR-001).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend-compliance/reference_scenarios/_helpers.py

@@ -142,35 +142,61 @@ def completeness_section() -> None:
 
 
 def domain_programs_section(base_dir) -> None:
-    """Render the Domain Knowledge Programs section (kept here so generate.py stays under the LOC budget)."""
+    """Domain Knowledge Program v1 — per-domain maturity KPI DERIVED from the corpus (computed-not-stored)."""
     import os
     import yaml
-    from compliance.completeness import assess_completeness
+    from compliance.knowledge_intake import build_knowledge_index
 
+    def _load(sub):
+        d = os.path.join(base_dir, "..", "knowledge", sub)
+        return [yaml.safe_load(open(os.path.join(d, f), encoding="utf-8"))
+                for f in sorted(os.listdir(d)) if f.endswith(".yaml")]
+
+    idx = build_knowledge_index(_load("transition_patterns"), _load("implementation_playbooks"),
+                                _load("reference_transition_scenarios"))
     pdir = os.path.join(base_dir, "..", "knowledge", "programs")
-    progs = [yaml.safe_load(open(os.path.join(pdir, f), encoding="utf-8"))
-             for f in sorted(os.listdir(pdir)) if f.endswith(".yaml")]
-    w("## Domain Knowledge Programs — ab jetzt Domänen, nicht Architektur")
+    progs = sorted((yaml.safe_load(open(os.path.join(pdir, f), encoding="utf-8"))
+                    for f in sorted(os.listdir(pdir)) if f.endswith(".yaml")), key=lambda p: p.get("backlog_rank", 99))
+
+    _ALIAS = {"cyber resilience act": "cra", "maschinenverordnung": "maschinenvo", "iatf": "iatf16949"}
+
+    def _canon(r):
+        k = str(r).strip().lower()
+        return _ALIAS.get(k, k)
+
+    def _hits(reg_lists, src):
+        cs = {_canon(s) for s in src}
+        return [k for k, regs in reg_lists.items() if cs & {_canon(x) for x in regs}]
+
+    def _source_modeled(index, source, canon):
+        c = canon(source)
+        in_tp = any(c in {canon(x) for x in regs} for regs in index.transition_patterns.values())
+        in_rts = any(c in {canon(x) for x in regs} for regs in index.reference_scenarios.values())
+        in_pb = any(c in {canon(x) for x in index.capability_regulations.get(cap, [])} for cap in index.playbook_capabilities)
+        return in_tp or in_rts or in_pb
+
+    w("## Domain Knowledge Program v1 — Reifegrad je Domäne (reproduzierbarer KPI)")
     w("")
-    w('_Die Runtime-Architektur ist eingefroren. Eine neue Domäne = Daten + Wissen, die jede Sicht automatisch erweitern. Produktionsstraße: Corpus→Obligations→Capabilities→Transition→Playbooks→Reference→Completeness. **Law-first: Recht → Pflichten → Capabilities → Managementsystem → Delta.**_')
+    w('_Engpass = Domänenmodellierung. Jede Domäne läuft durch DIESELBE 7-Stufen-Produktionsstraße (Domain Model → Requirement Sources → Capability Registry → Transition Patterns → Playbooks → Reference Scenarios → Completeness). Reifegrad aus dem ECHTEN Korpus abgeleitet (computed-not-stored), keine Marketingzahl. Einstieg über Industry, nicht Regelwerk._')
     w("")
+    w("| Rank | Domäne | Reifegrad (Sources modelliert) | modelliert/total | Korpus TP·PB·RTS |")
+    w("|---|---|---|---|---|")
     for p in progs:
-        w("**%s** — _%s_ (status: `%s`)" % (p["name"], p["customer_question"], p["status"]))
-        w("")
-        w("| Stufe | Artefakt | Owner | Status |")
-        w("|---|---|---|---|")
-        for s in p.get("stages", []):
-            w("| %s | %s | %s | **%s** |" % (s["id"], s["name"], s["owner"], s["status"]))
-        w("")
-        areas = next((s.get("areas", []) for s in p.get("stages", []) if s.get("id") == "B1"), [])
-        if areas:
-            rep = assess_completeness(identified_regulations=areas, corpus_status={})   # all unknown -> open baseline
-            w("- **Baseline (Completeness):** %s — die 6 Bereiche: %s" % (rep.completeness_summary, ", ".join(areas)))
-        w("")
-    w("_Jedes Programm liefert dieselben Artefakte; Status `open/blocked` kippt automatisch, wenn die Stufen landen — Reference Suite + Completeness dokumentieren den Fortschritt je Domäne._")
+        src = p.get("typical_requirement_sources", [])
+        tp, rts = _hits(idx.transition_patterns, src), _hits(idx.reference_scenarios, src)
+        cs = {_canon(s) for s in src}
+        pb = [c for c in idx.playbook_capabilities if cs & {_canon(x) for x in idx.capability_regulations.get(c, [])}]
+        modeled = [s for s in src if _source_modeled(idx, s, _canon)]   # sources with >=1 corpus artifact
+        breadth = (len(modeled) / len(src)) if src else 0.0             # honest differentiator (not CRA-shared depth)
+        filled = int(round(breadth * 10))
+        w("| %d | **%s** | `%s` %d%% | %d/%d | %d·%d·%d |" % (
+            p.get("backlog_rank", 99), p["name"], "█" * filled + "░" * (10 - filled),
+            int(round(breadth * 100)), len(modeled), len(src), len(tp), len(pb), len(rts)))
+    w("")
+    w('_Industry-Einstieg + ETO-Hypothese: jede Domäne kennt ihre typischen Sources + Zertifikate → vor dem Onboarding „diese Prozesswelt ist wahrscheinlich vorhanden" (Hypothese, nie Wahrheit; speist Company 2A als `inferred`). Backlog nach Kundennutzen, KPI nach echtem Korpusstand — beides bewusst getrennt._')
     w("")
     coverage_table([
-        ("Domain Program Blueprint (wiederverwendbar)", "PASS", "Corpus→…→Completeness, law-first, Ownership je Stufe"),
-        ("Environmental Program (Daten)", "PASS", "B1@Legal-KG · B2@Execution · B3@Reasoning (blocked)"),
-        ("Phase B = Domänen, keine Architektur", "PASS", "kein neues Runtime-Framework (Freeze, ADR-008)"),
+        ("Domain Knowledge Program (7-Stufen-Produktionsstraße)", "PASS", "%d Domänen im Backlog, Industrial Automation #1" % len(progs)),
+        ("Reifegrad-KPI (computed-not-stored)", "PASS", "aus echtem Korpus abgeleitet (TP/PB/RTS je Domäne)"),
+        ("Regelwerk-ID-Normalisierung", "TODO", "Alias CRA/MaschinenVO im KPI — kanonische IDs ausstehend"),
     ])