feat(research): consult biography backtest harness and pre-change baseline

TASK-consult-no-presupposition-and-backtest-20261001 T4 infrastructure only
(T1-T3 untouched). New files only, so it merges cleanly with the parallel
evidence-card brief.

- capture_consult_biography_backtest_golden.py: same handler/body/trim as the
  evidence-card golden; nine public AA charts x parents/marriage/health/career.
- consult-biography-backtest-golden.json: real engine output, byte-reproducible.
- consult_biography_backtest_rubric.json: facts with sources, must_not,
  expected_signals per figure x domain.
- consult-biography-backtest.mts: runs the product's real agent, tools, card,
  methodology, user-turn shape and streamAgentResponse; deterministic checks only.
- Baseline on 9b937c4a: 39/72 severe biography conflicts; all five audit cases
  reproduce in both runs.

BUG-1170 is registered when brief 3 lands.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4f2nya58RoRu4yEmJgRGE

scripts/research/capture_consult_biography_backtest_golden.py

@@ -0,0 +1,179 @@
+"""Capture real engine consultation responses for the biography backtest.
+
+Same path as `capture_consult_evidence_card_golden.py` (same handler, same
+request body, same research reference date, raman ayanamsa, mean nodes, the
+external VedAstro stand-in), extended to nine public Rodden AA charts and to the
+four engine routes the backtest asks about: `family` (the engine route the
+product's `parents` domain runs as), `marriage`, `health` and `career`. Each
+response is trimmed by key only with the same `trim()` as the evidence-card
+golden: every kept value is the engine's own value, unchanged.
+
+The chart block (`workflow.chart`) is almost route-independent: the keys all
+four routes agree on are stored once per figure as `shared_chart`, and the
+keys that differ (today `modules.yogas` and `modules.chara_dasha`) stay with
+each route under `chart` / `chart_modules`. The TypeScript reader overlays
+them back (`frontend/scripts/research/consult-biography-backtest.mts`), so
+every route's chart is exactly what the engine returned.
+
+    JYOTISH_API_CHART_CACHE_TTL_SECONDS=0 PYTHONHASHSEED=0 \
+        python3 scripts/research/capture_consult_biography_backtest_golden.py
+
+Birth data only from the repository's public case libraries (Astro-Databank
+AA); no user chart is ever read.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import sys
+from pathlib import Path
+from typing import Any
+
+ROOT = Path(__file__).resolve().parents[2]
+sys.path[:0] = [str(ROOT), str(ROOT / "scripts"), str(ROOT / "scripts" / "research")]
+
+from consult_evidence_card_lib import AYANAMSA, NODE_MODE, REFERENCE_DATE  # noqa: E402
+import consult_evidence_card_run as runner  # noqa: E402
+from capture_consult_evidence_card_golden import trim  # noqa: E402
+
+OUT = ROOT / "frontend" / "tests" / "fixtures" / "consult-biography-backtest-golden.json"
+CASES = "references/real_case_calibration"
+
+# id, label, case library, case id. The rubric
+# (docs/research/consult_biography_backtest_rubric.json) carries why each is here.
+FIGURES = (
+    ("steve_jobs", "Steve Jobs", f"{CASES}/minute_rectification_development_v1.json", "steve_jobs_1955_development"),
+    ("barack_obama", "Barack Obama", f"{CASES}/minute_rectification_holdout_v4.json", "barack_obama_1961_aa_v4_holdout"),
+    ("elizabeth_taylor", "Elizabeth Taylor", f"{CASES}/minute_rectification_holdout_v4.json", "elizabeth_taylor_1932_aa_v4_holdout"),
+    ("marilyn_monroe", "Marilyn Monroe", f"{CASES}/minute_rectification_holdout_v5.json", "marilyn_monroe_1926_aa_v5_holdout"),
+    ("judy_garland", "Judy Garland", f"{CASES}/minute_rectification_holdout_v5.json", "judy_garland_1922_aa_v5_holdout"),
+    ("edith_piaf", "Édith Piaf", f"{CASES}/minute_rectification_holdout_v5.json", "edith_piaf_1915_aa_v5_holdout"),
+    ("frida_kahlo", "Frida Kahlo", f"{CASES}/minute_rectification_holdout_v5.json", "frida_kahlo_1907_aa_v5_holdout"),
+    ("george_w_bush", "George W. Bush", f"{CASES}/minute_rectification_holdout_v5.json", "george_w_bush_1946_aa_v5_holdout"),
+    ("zinedine_zidane", "Zinedine Zidane", f"{CASES}/minute_rectification_holdout_v5.json", "zinedine_zidane_1972_aa_v5_holdout"),
+)
+
+# Product domain -> engine route and the question the backtest asks. The
+# product sends a card-only domain (parents) as its engine route's contract
+# (frontend/src/lib/consultation-workflow-request.ts).
+ROUTES = (
+    {"domain": "parents", "engine_route": "family", "question": "我和父母关系如何，他们怎么对待我？"},
+    {"domain": "marriage", "engine_route": "marriage", "question": "我的婚姻和感情会是什么样？"},
+    {"domain": "health", "engine_route": "health", "question": "我的身体底子怎么样，健康上要注意什么？"},
+    {"domain": "career", "engine_route": "career", "question": "我的事业会往什么方向走，能做到什么程度？"},
+)
+
+
+def load_chart(spec: tuple[str, str, str, str]) -> dict[str, Any]:
+    figure_id, label, path, case_id = spec
+    payload = json.loads((ROOT / path).read_text(encoding="utf-8"))
+    case = next(item for item in payload["cases"] if item["case_id"] == case_id)
+    birth = case["birth"]
+    year, month, day = (int(part) for part in birth["date"].split("-"))
+    hour, minute = (int(part) for part in birth["time"].split(":")[:2])
+    source = birth.get("source") or {}
+    return {
+        "id": figure_id,
+        "label": label,
+        "source": path,
+        "case_id": case_id,
+        "rodden_rating": source.get("rodden_rating"),
+        "birth_source_url": source.get("url"),
+        # Same body as consult_evidence_card_lib.load_public_charts.
+        "body": {
+            "year": year,
+            "month": month,
+            "day": day,
+            "hour": hour,
+            "minute": minute,
+            "second": 0,
+            "lat": birth["latitude"],
+            "lon": birth["longitude"],
+            "tz": birth["timezone_offset"],
+            "city": birth.get("place") or label,
+            "ayanamsa": AYANAMSA,
+            "node_mode": NODE_MODE,
+            "today": REFERENCE_DATE,
+            "entry_mode": "direct_chart",
+            "defer_optional_external_evidence": True,
+            "declared_accuracy": "minute",
+            "birth_time_accuracy": "confirmed",
+        },
+    }
+
+
+def split_shared_chart(routes: dict[str, dict[str, Any]]) -> dict[str, Any]:
+    """Lift the chart keys every route agrees on into one copy.
+
+    A key (or a `modules` key) whose value differs between routes stays with
+    each route under `chart` (or `chart_modules`); the reader overlays it on
+    the shared copy, so every route's chart comes back exactly as captured.
+    """
+    charts = [value.pop("chart") for value in routes.values()]
+    shared: dict[str, Any] = {}
+    keys = {key for chart in charts for key in chart if key != "modules"}
+    for key in sorted(keys):
+        values = [chart.get(key) for chart in charts]
+        if all(key in chart for chart in charts) and all(item == values[0] for item in values):
+            shared[key] = values[0]
+        else:
+            for value, chart in zip(routes.values(), charts):
+                if key in chart:
+                    value.setdefault("chart", {})[key] = chart[key]
+    modules = [chart.get("modules") or {} for chart in charts]
+    shared["modules"] = {}
+    for key in sorted({key for item in modules for key in item}):
+        values = [item.get(key) for item in modules]
+        if all(key in item for item in modules) and all(entry == values[0] for entry in values):
+            shared["modules"][key] = values[0]
+        else:
+            for value, item in zip(routes.values(), modules):
+                if key in item:
+                    value.setdefault("chart_modules", {})[key] = item[key]
+    return shared
+
+
+def main() -> int:
+    if os.environ.get("PYTHONHASHSEED") != "0":
+        raise SystemExit("Set PYTHONHASHSEED=0 before starting this process (ERR-111).")
+    only = {item for item in os.environ.get("BACKTEST_FIGURES", "").split(",") if item}
+    runner._block_external_vedastro()
+    figures = []
+    for spec in FIGURES:
+        if only and spec[0] not in only:
+            continue
+        chart = load_chart(spec)
+        routes: dict[str, dict[str, Any]] = {}
+        for route in ROUTES:
+            question = {"id": route["domain"], "domain": route["engine_route"], "question": route["question"]}
+            routes[route["domain"]] = trim(runner._run_workflow(runner._workflow_body(chart, question)))
+            print(f"{chart['id']} {route['domain']} ok", flush=True)
+        shared = split_shared_chart(routes)
+        figures.append({
+            "id": chart["id"],
+            "label": chart["label"],
+            "source": chart["source"],
+            "case_id": chart["case_id"],
+            "rodden_rating": chart["rodden_rating"],
+            "birth_source_url": chart["birth_source_url"],
+            "shared_chart": shared,
+            "routes": routes,
+        })
+    payload = {
+        "source": "scripts/research/capture_consult_biography_backtest_golden.py",
+        "note": "Real engine consultation_workflow responses for nine public AA charts x four routes, trimmed by key only (same trim as consult-evidence-card-golden.json).",
+        "reference_date": REFERENCE_DATE,
+        "ayanamsa": AYANAMSA,
+        "node_mode": NODE_MODE,
+        "routes": list(ROUTES),
+        "external_vedastro": "not_called",
+        "figures": figures,
+    }
+    OUT.write_text(json.dumps(payload, ensure_ascii=False, separators=(",", ":")) + "\n", encoding="utf-8")
+    print(f"wrote {OUT} ({OUT.stat().st_size} bytes)")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())