[NOTICKET] feat(report): evidence tables for cluster, anomaly, descriptive, data-quality and forecast

src/agents/report/anchored.py

@@ -321,8 +321,92 @@ _TOOL_TABLES: dict[str, Any] = {
         ["column a", "column b", "correlation"],
         [[p.get("a"), p.get("b"), p.get("corr")] for p in _dicts(v.get("pairs"))],
     ),
+    # 2026-11-03 (test-demo #17): the profiling / ML tools return `stats`, so a cluster,
+    # anomaly or forecast answer had no evidence at all (its raw model input is skipped)
+    # and a descriptive / data-quality answer was evidenced by ten raw rows.
+    "analyze_cluster": lambda v: _cluster_table(v),
+    "analyze_anomaly": lambda v: _anomaly_table(v),
+    "analyze_descriptive": lambda v: _descriptive_table(v),
+    "analyze_data_quality": lambda v: _data_quality_table(v),
+    "analyze_forecast": lambda v: (
+        ["period", "value", "kind"],
+        [[p.get("period"), p.get("value"), "actual"] for p in _dicts(v.get("history"))[-3:]]
+        + [[p.get("period"), p.get("value"), "forecast"] for p in _dicts(v.get("forecast"))],
+    ),
 }
 
+# Members per cluster shown in the evidence table; the tool carries up to 15.
+_EVIDENCE_MEMBERS = 5
+# Scored columns shown per anomaly row, after its label columns and before the score.
+_EVIDENCE_ANOMALY_COLS = 4
+_DESCRIPTIVE_STATS = ("count", "mean", "median", "std", "min", "max")
+
+
+def _cluster_table(v: dict) -> tuple[list[str], list[list[Any]]]:
+    """cluster · size · share · per-column means · a few example members."""
+    measures = [c for c in v.get("column_ids") or [] if isinstance(c, str)]
+    clusters = _dicts(v.get("clusters"))
+    named = any("example_members" in c for c in clusters)
+    cols = ["cluster", "size", "share %"] + measures + (["example members"] if named else [])
+    rows = []
+    for c in clusters:
+        row = [c.get("cluster"), c.get("size"), _pct(c.get("share"))]
+        row += [c.get(m) for m in measures]
+        if named:
+            members = [str(m) for m in c.get("example_members") or []]
+            shown = members[:_EVIDENCE_MEMBERS]
+            more = " …" if (c.get("size") or 0) > len(shown) else ""
+            row.append(", ".join(shown) + more)
+        rows.append(row)
+    return cols, rows
+
+
+def _anomaly_table(v: dict) -> tuple[list[str], list[list[Any]]]:
+    """The flagged rows, most anomalous first: labels, a few scored columns, score."""
+    flagged = _dicts(v.get("anomalies"))
+    if not flagged:
+        return [], []
+    scored = [c for c in v.get("column_ids") or [] if isinstance(c, str)]
+    labels = [k for k in flagged[0] if k not in scored and k != "anomaly_score"]
+    cols = labels + scored[:_EVIDENCE_ANOMALY_COLS] + ["anomaly_score"]
+    return cols, [[a.get(c) for c in cols] for a in flagged]
+
+
+def _descriptive_table(v: dict) -> tuple[list[str], list[list[Any]]]:
+    """One row per column with its headline statistics."""
+    profiles = {k: p for k, p in v.items() if isinstance(p, dict)}
+    present = [s for s in _DESCRIPTIVE_STATS if any(s in p for p in profiles.values())]
+    return ["column"] + present, [[k] + [p.get(s) for s in present] for k, p in profiles.items()]
+
+
+def _data_quality_table(v: dict) -> tuple[list[str], list[list[Any]]]:
+    """One row per column, the most missing / most outliers first.
+
+    A 0/1 flag (≤ 2 distinct values) sorts after the rest: its IQR "outliers" are just
+    the rarer value — the local run of 3 Nov put `is_mtbs_achieved` on top.
+    """
+    columns = v.get("columns")
+    profiles = (
+        {k: p for k, p in columns.items() if isinstance(p, dict)}
+        if isinstance(columns, dict) else {}
+    )
+    ordered = sorted(
+        profiles.items(),
+        key=lambda kv: (
+            -(kv[1].get("null_rate") or 0),
+            (kv[1].get("distinct_count") or 0) <= 2,
+            -(kv[1].get("outlier_count") or 0),
+        ),
+    )
+    return (
+        ["column", "missing %", "distinct", "outliers", "min", "max"],
+        [
+            [k, _pct(p.get("null_rate")), p.get("distinct_count"), p.get("outlier_count"),
+             p.get("min"), p.get("max")]
+            for k, p in ordered
+        ],
+    )
+
 
 def _tool_table(rec: AnalysisRecord) -> tuple[list[str], list[list[Any]]] | None:
     """(columns, rows) of the LAST analysis-tool output with a table form, else None."""