feat(learning): graduated gate — panel-consensus style lessons auto-flow to writer (P0)
All checks were successful
G12 Leak-Guard / leak-guard (pull_request) Successful in 4s
Lint — undefined names / undefined-names (pull_request) Successful in 10s

The voice-learning panel produced 81 vetted style lessons — all stuck at
review_status='proposed' with 0 ever approved — so the writer (which reads only
'approved') received NONE of them. The system captured learning but never let it
flow. Chair decision (2026-06-28): a GRADUATED gate by content risk.

- STYLE lessons (categories style/structure/lexicon/tabular) the 2/2 panel kept →
  created as review_status='approved' → flow to the writer immediately, reversibly
  (chair vetoes in /training). The deepseek+gemini panel only emits style_method
  and only on 2/2 consensus, so this is exactly the gate's criterion; substance is
  already filtered out and skipped, and routes through the strict halacha gate.
- SUBSTANCE (halacha/precedent/fact) stays a HARD chair gate — unchanged.

style_lesson_panel.py: _review_status_for(category) sets the gate explicitly
(approved for _STYLE_CATEGORIES, else proposed); the apply loop passes it to
db.add_decision_lesson (which already accepts review_status — no DB change).

Spec: INV-LRN1 rewritten as the graduated gate (hard for substance; reversible
auto-flow for consensus style — still "under user control" via veto, per
NCSC/CEPEJ); §0.6 updated to match.

A one-time backfill of the 81 existing panel style lessons to 'approved' runs
separately (DB, post-merge).

Invariants: INV-LRN1 (amended — graduated), INV-LRN5 (style-only, substance never
auto-flows), G10 (human control preserved as reversible veto).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-28 21:45:56 +00:00
parent 4de555367d
commit 044de2c0f0
2 changed files with 29 additions and 11 deletions

View File

@@ -110,6 +110,19 @@ def _category(change: dict) -> str:
return "style"
# Graduated gate (INV-LRN1, chair decision 2026-06-28): a STYLE lesson the panel
# kept by 2/2 consensus flows straight to the writer (review_status='approved'),
# reversibly — the chair can veto it in /training. SUBSTANCE (halacha/precedent/
# fact) never reaches here (it's filtered to `substance` and skipped, and routes
# through the strict 3-judge halacha gate), so every category this panel emits is
# style and auto-approves. The constant keeps the gate explicit and future-proof.
_STYLE_CATEGORIES = frozenset({"style", "structure", "lexicon", "tabular"})
def _review_status_for(category: str) -> str:
return "approved" if category in _STYLE_CATEGORIES else "proposed"
# ── two judges, one signature: (system, user) -> dict|None ──
async def judge_deepseek(client: httpx.AsyncClient, system: str, user: str) -> dict | None:
@@ -323,18 +336,24 @@ async def main(args: argparse.Namespace) -> int:
_lesson_text(r["_change"])])
written = 0
approved = 0
for r in fresh:
cat = _category(r["_change"])
rs = _review_status_for(cat)
await db.add_decision_lesson(
UUID(corpus_id),
lesson_text=_lesson_text(r["_change"]),
category=_category(r["_change"]),
category=cat,
source="panel:deepseek+gemini",
created_by="panel",
review_status=rs,
)
written += 1
approved += (rs == "approved")
chair = cc["split"] + cc["incomplete"]
print(f"\nAPPLIED (reversible): wrote {written} decision_lesson proposals "
print(f"\nAPPLIED (reversible): wrote {written} decision_lessons "
f"({approved} auto-approved style → writer; graduated gate) "
f"(source=panel:deepseek+gemini) · {skipped_dup} כפילויות דולגו · "
f"{chair} escalated to chair · {len(substance)} substance skipped")
print(f"backup → {backup}")