feat: Trino federation + Hadoop external tables + LLM data catalog

Trino Federation tab (3 sub-views):
- Federated: catalog landscape + a single cross-source SQL that joins
  PostgreSQL + MySQL + MongoDB (region scorecard) — the federation proof,
  computed in the background and cached (large full scans take ~2 min).
- Hadoop Lake: all federated business data materialized as external Iceberg
  tables on HDFS (iceberg.hadoop.*_ext, ~120k rows each) with live, fast
  business analytics (revenue by region/channel, top customers, HR by
  department, supply by type, telemetry averages). Includes a one-click
  "rebuild external tables" job.
- Data Dictionary: every business table + column with masked / visible PII
  badges and categories.

Backend trino_federated.py: /catalogs, /marquee(+refresh), /lake,
/materialize(+status), /dictionary. Name-based PII detection flags raw PII
in derived/lake tables as visible vs physically-masked curated layer.

LLM context: platform_context now emits a full BUSINESS DATA CATALOG section
(tables, columns, types, source row counts, federated scorecard) with exact
per-column masked/visible status, so the assistant knows the data in detail
and what is masked vs not.

api/platform_context.py

@@ -132,13 +132,84 @@ def build_masking_section() -> str:
     return "\n".join(lines)
 
 
+def build_business_data_section() -> str:
+    """Detailed inventory of the actual business data — tables, columns, types,
+    row counts and per-column masked/visible status — so the assistant knows the
+    data in detail and exactly what is masked vs not."""
+    lines: list[str] = ["=== BUSINESS DATA CATALOG (live, every detail) ==="]
+
+    # source row totals (cheap estimates)
+    try:
+        import sql_console as s
+        totals = {
+            "PostgreSQL sales_orders": s._table_row_count("postgres", "public.sales_orders"),
+            "MySQL employee_events": s._table_row_count("mysql", "hr.employee_events"),
+            "MongoDB supplychain.events": s._table_row_count("mongodb", "supplychain.events"),
+        }
+        lines.append("Source volumes (live row counts):")
+        for k, v in totals.items():
+            lines.append(f"  - {k}: {v:,} rows" if isinstance(v, int) else f"  - {k}: ~")
+    except Exception:
+        pass
+
+    # full column dictionary + masking per column
+    try:
+        from trino_federated import build_dictionary
+        d = build_dictionary()
+        summ = d.get("summary", {})
+        lines.append(
+            f"Catalogued tables: {summ.get('tables', 0)} — columns: {summ.get('columns', 0)}, "
+            f"PII columns: {summ.get('pii_columns', 0)} ({summ.get('masked_columns', 0)} masked)."
+        )
+        for t in d.get("tables", []):
+            lines.append(f"\n{t['engine']} · {t['fqn']} — {t['desc']}")
+            for c in t.get("columns", []):
+                flag = ""
+                if c.get("masked"):
+                    flag = f"  [MASKED · {c.get('category')}]"
+                elif c.get("pii"):
+                    flag = f"  [PII visible · {c.get('category')}]"
+                lines.append(f"    · {c['name']} ({c['type']}){flag}")
+    except Exception as exc:
+        lines.append(f"(data dictionary unavailable: {exc})")
+
+    # federated cross-source marquee (region scorecard), if computed
+    try:
+        from trino_federated import _marquee, _load_marquee
+        if _marquee.get("data") is None:
+            _load_marquee()
+        m = _marquee.get("data")
+        if m and m.get("rows"):
+            lines.append("\nFederated region scorecard (one Trino SQL across PostgreSQL+MySQL+MongoDB):")
+            for r in m["rows"][:8]:
+                rev = r.get("revenue")
+                rev_s = f"€{rev:,.0f}" if isinstance(rev, (int, float)) else "?"
+                lines.append(
+                    f"  - {r.get('region')}: orders={r.get('orders')}, revenue={rev_s}, "
+                    f"hr_events={r.get('hr_events')}, supply_events={r.get('supply_events')}"
+                )
+    except Exception:
+        pass
+
+    lines.append(
+        "\nData is also materialized into the Hadoop lake as external Iceberg tables "
+        "(iceberg.hadoop.*_ext) and exposed through one federated Trino engine "
+        "(catalogs: postgres_sales, mysql_hr, mongodb_supplychain, cassandra_telemetry, iceberg, kafka)."
+    )
+    return "\n".join(lines)
+
+
 def build_llm_addendum() -> str:
     try:
         platform = build_platform_section()
     except Exception as exc:
         platform = f"(platform section error: {exc})"
+    try:
+        business = build_business_data_section()
+    except Exception as exc:
+        business = f"(business data section error: {exc})"
     try:
         masking = build_masking_section()
     except Exception as exc:
         masking = f"(masking section error: {exc})"
-    return "\n\n".join([platform, masking])
+    return "\n\n".join([platform, business, masking])