feat(opt): three efficiency levers for NL→SQL workflow

Lever 1: Join-graph via FK logics in annotations + suggest-fks command
  - TableAnnotation.foreign_keys field stores curated logical FKs (DWH has no FK constraints)
  - tht schema suggest-fks: mine from approved SQL, heuristics (time_key → dim_time),
    same-name discovery + explicit --assume flag for multi-owner PKs
  - mschema renders 【Foreign keys】 section populated; validation in merge.py
  - SKILL.md F4 now reads FKs from mschema-text, no custom data_time_key logic

Lever 2: Context-pack consolidation at kickoff (tht search pack)
  - Single embedding of question, reused for schema + evidence + solved searches
  - One command: tht search pack <question> --session <id> → retrieval_pack.md
  - Graceful degradation when Ollama/vector store unreachable (exit 0, empty sections)
  - SKILL.md F1 prescribes as first call; reduces model thinking turns via pre-retrieval

Lever 3: Phase-summary recap v2 auto-construction from session ledger
  - tht session show --json includes full decisions ledger
  - tht phase meta --json exports 'emits' (substantive decision types per phase)
  - Gate appends deterministic 【Decisioni registrate in questa fase】 section (appendLedgerSection)
  - Model authors only summary + checks; recap table comes from persisted state (exact by construction)
  - SKILL.md Disciplina 6: brief model output, gate fills the rest

Tests: 358 Python (including 10 FK + 3 pack + 1 session-ledger tests) + 111 JS gate tests, all pass.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

harness/.pi/extensions/tht-gate.js

@@ -42,6 +42,7 @@ import {
 	buildCteResultV2,
 	enrichCteResultColumns,
 	enrichPhaseSummaryV2,
+	appendLedgerSection,
 } from "./gate/enrich.js";
 import { isReserved } from "./reserved-labels.mjs";
 
@@ -898,11 +899,26 @@ export default function (pi) {
 						"Riepilogo di fase v2 non valido:\n- " + v.errors.join("\n- "),
 					);
 				}
-				const enriched = enrichPhaseSummaryV2(
+				let enriched = enrichPhaseSummaryV2(
 					data,
 					phaseMetaForNum(ctx, curNum),
 					makeGetColumns(ctx),
 				);
+				// Recap deterministico: appende la sezione "decisioni di questa fase"
+				// dal ledger (best-effort: un errore di lettura non blocca il gate).
+				try {
+					const show = JSON.parse(
+						tht(ctx, ["session", "show", session, "--json"]),
+					);
+					const meta = phaseMeta(ctx).phases.find((p) => p.num === curNum);
+					enriched = appendLedgerSection(
+						enriched,
+						show.decisions,
+						meta ? meta.emits : [],
+					);
+				} catch {
+					// ledger non leggibile: il riepilogo resta quello del modello
+				}
 				artifact = { ...artifact, data: enriched };
 			}