Jyotisha/scripts/research/varga_resolution_probe.py

#!/usr/bin/env python3
"""Run the deterministic BUG-1105 varga-resolution M0 replay.

The production scorer remains untouched.  Scoring candidates are sampled at a
fixed two-minute step, while an independent one-minute context scan supplies
varga rising-sign segments.  ``refresh_probes=False`` is intentional and is
recorded in the machine result; an empty probe pool is reported rather than
silently replaced with refreshed dasha-boundary probes.
"""
from __future__ import annotations

import argparse
import json
import sys
from collections import Counter
from pathlib import Path
from typing import Any, Iterable, Sequence

ROOT = Path(__file__).resolve().parents[2]
if str(ROOT) not in sys.path:
    sys.path.insert(0, str(ROOT))

from scripts.research.cluster_width_lib import delivery_from_public  # noqa: E402
from scripts.research.varga_resolution_lib import (  # noqa: E402
    RADII,
    VARGA_PREFIXES,
    native_case,
    segment_rows,
    sign_value,
)

HOLDOUT = ROOT / "references" / "real_case_calibration" / "minute_rectification_holdout_v5.json"
SCHEMA = "bug-1105-varga-resolution-v1"
SCORING_STEP = 2
SCAN_STEP = 1
REFRESH_PROBES = False


def load_cases() -> list[dict[str, Any]]:
    payload = json.loads(HOLDOUT.read_text(encoding="utf-8"))
    return list(payload.get("cases") or [])


def hhmm(value: object) -> str:
    return str(value or "")[:5]


def clock(stamp: str) -> int:
    hour, minute = stamp[:5].split(":")
    return int(hour) * 60 + int(minute)


def in_envelope(stamp: str, start: str | None, end: str | None) -> bool:
    if not start or not end:
        return False
    value, lower, upper = clock(stamp), clock(start), clock(end)
    return lower <= value <= upper if lower <= upper else value >= lower or value <= upper


def stable_unique(values: Iterable[str]) -> list[str]:
    return list(dict.fromkeys(str(value)[:5] for value in values if value))


def interval_times(chart_rows: Sequence[dict[str, Any]], delivery: dict[str, Any]) -> list[str]:
    return [
        hhmm(row.get("time"))
        for row in chart_rows
        if in_envelope(hhmm(row.get("time")), delivery.get("start"), delivery.get("end"))
    ]


def valid_candidate_times(state: dict[str, Any]) -> list[str]:
    values: list[str] = []
    for row in state.get("valid") or []:
        values.extend(hhmm(value) for value in row.get("cluster_times") or [row.get("time")])
    return stable_unique(values)


def represented_segments(
    chart_rows: Sequence[dict[str, Any]],
    prefix: str,
    times: Iterable[str],
) -> list[dict[str, Any]]:
    wanted = set(stable_unique(times))
    return [
        segment for segment in segment_rows(chart_rows, prefix)
        if wanted.intersection(segment.get("times") or [])
    ]


def represented_values(rows: Sequence[dict[str, Any]], prefix: str, times: Iterable[str]) -> list[Any]:
    wanted = set(stable_unique(times))
    return stable_values(sign_value(row, prefix) for row in rows if hhmm(row.get("time")) in wanted)


def stable_values(values: Iterable[Any]) -> list[Any]:
    result: list[Any] = []
    for value in values:
        if value is None or value in result:
            continue
        result.append(value)
    return result


def majority(values: Sequence[Any], truth: Any) -> tuple[bool | None, bool]:
    if not values:
        return None, False
    counts = Counter(values)
    peak = max(counts.values())
    leaders = {value for value, count in counts.items() if count == peak}
    return (truth in leaders if len(leaders) == 1 else None), len(leaders) > 1


def window_summary(chart_rows: Sequence[dict[str, Any]]) -> dict[str, Any]:
    counts: dict[str, int] = {}
    segments: dict[str, int] = {}
    for prefix in VARGA_PREFIXES:
        counts[prefix] = len(stable_values(sign_value(row, prefix) for row in chart_rows))
        segments[prefix] = len(segment_rows(chart_rows, prefix))
    combinations = len({tuple(sign_value(row, prefix) for prefix in VARGA_PREFIXES) for row in chart_rows})
    return {
        "scan_point_count": len(chart_rows),
        "sign_counts": counts,
        "segment_counts": segments,
        "combination_count": combinations,
        "d1_single_sign": counts["D1"] == 1,
    }


def interval_summary(
    chart_rows: Sequence[dict[str, Any]],
    state: dict[str, Any],
    true_time: str,
) -> dict[str, Any]:
    delivery = state.get("delivery") or {}
    envelope = interval_times(chart_rows, delivery)
    real = valid_candidate_times(state)
    values: dict[str, dict[str, Any]] = {}
    for prefix in VARGA_PREFIXES:
        truth_row = next((row for row in chart_rows if hhmm(row.get("time")) == true_time), None)
        truth = sign_value(truth_row or {}, prefix)
        envelope_segments = represented_segments(chart_rows, prefix, envelope)
        real_segments = represented_segments(chart_rows, prefix, real)
        envelope_values = [sign_value(row, prefix) for row in chart_rows if hhmm(row.get("time")) in set(envelope)]
        exact_values = represented_values(chart_rows, prefix, real)
        envelope_majority, envelope_tie = majority(envelope_values, truth)
        exact_majority, exact_tie = majority(exact_values, truth)
        truth_segment = next(
            (segment for segment in segment_rows(chart_rows, prefix) if true_time in (segment.get("times") or [])),
            None,
        )
        truth_segment_id = truth_segment.get("segment_id") if truth_segment else None
        values[prefix] = {
            "truth_sign": truth,
            "truth_segment_id": truth_segment_id,
            "envelope_start": delivery.get("start"),
            "envelope_end": delivery.get("end"),
            "envelope_scan_point_count": len(envelope),
            "envelope_sign_count": len(stable_values(envelope_values)),
            "envelope_segment_count": len(envelope_segments),
            "envelope_majority_truth": envelope_majority,
            "envelope_majority_tie": envelope_tie,
            "real_valid_candidate_count": len(real),
            "real_valid_sign_count": len(exact_values),
            "real_valid_segment_count": len(real_segments),
            "real_valid_majority_truth": exact_majority,
            "real_valid_majority_tie": exact_tie,
            "truth_segment_retained_in_real_set": truth_segment_id is not None and any(
                segment.get("segment_id") == truth_segment_id for segment in real_segments
            ),
        }
    combo_envelope = {
        tuple(sign_value(row, prefix) for prefix in VARGA_PREFIXES)
        for row in chart_rows
        if hhmm(row.get("time")) in set(envelope)
    }
    combo_real = {
        tuple(sign_value(row, prefix) for prefix in VARGA_PREFIXES)
        for row in chart_rows
        if hhmm(row.get("time")) in set(real)
    }
    truth_row = next((row for row in chart_rows if hhmm(row.get("time")) == true_time), None)
    truth_combo = tuple(sign_value(truth_row or {}, prefix) for prefix in VARGA_PREFIXES)
    envelope_combo_majority, envelope_combo_tie = majority(
        [tuple(sign_value(row, prefix) for prefix in VARGA_PREFIXES) for row in chart_rows if hhmm(row.get("time")) in set(envelope)],
        truth_combo,
    )
    return {
        "scoring_candidate_times": real,
        "interval_envelope": {
            "start": delivery.get("start"),
            "end": delivery.get("end"),
            "scan_point_count": len(envelope),
            "times": envelope,
        },
        "by_varga": values,
        "combination": {
            "envelope_count": len(combo_envelope),
            "real_valid_count": len(combo_real),
            "envelope_majority_truth": envelope_combo_majority,
            "envelope_majority_tie": envelope_combo_tie,
        },
    }


def case_result(case: dict[str, Any], radius: int) -> dict[str, Any]:
    result = native_case(case, radius, do_reconcile=True)
    state = result["state"]
    chart_rows = result["chart_rows"]
    return {
        "case_id": str(case.get("case_id") or ""),
        "radius": radius,
        "true_time": result["true_time"],
        "scoring_candidate_count": len(result["rows"]),
        "scan_point_count": len(chart_rows),
        "probe_count": len(result["probes"]),
        "answered_count": int((state.get("result") or {}).get("questions") or 0),
        "reconciliation": result["reconciliation"],
        "window": window_summary(chart_rows),
        "six_question_delivery": interval_summary(chart_rows, state, result["true_time"]),
    }


def ratio(numerator: int, denominator: int) -> float | None:
    return round(numerator / denominator, 8) if denominator else None


def aggregate(results: Sequence[dict[str, Any]], radius: int) -> dict[str, Any]:
    rows = [row for row in results if row["radius"] == radius]
    n = len(rows)
    window = {
        "case_count": n,
        "d1_single_sign": sum(row["window"]["d1_single_sign"] for row in rows),
        "mean_sign_counts": {
            prefix: round(sum(row["window"]["sign_counts"][prefix] for row in rows) / n, 8) if n else None
            for prefix in VARGA_PREFIXES
        },
        "mean_segment_counts": {
            prefix: round(sum(row["window"]["segment_counts"][prefix] for row in rows) / n, 8) if n else None
            for prefix in VARGA_PREFIXES
        },
        "mean_combination_count": round(sum(row["window"]["combination_count"] for row in rows) / n, 8) if n else None,
    }
    by_varga: dict[str, Any] = {}
    for prefix in VARGA_PREFIXES:
        items = [row["six_question_delivery"]["by_varga"][prefix] for row in rows]
        by_varga[prefix] = {
            "envelope_only_one_sign": sum(item["envelope_sign_count"] == 1 for item in items),
            "envelope_at_most_two_signs": sum(item["envelope_sign_count"] <= 2 for item in items),
            "envelope_majority_truth": sum(item["envelope_majority_truth"] is True for item in items),
            "envelope_majority_ties": sum(item["envelope_majority_tie"] for item in items),
            "real_truth_segment_retained": sum(item["truth_segment_retained_in_real_set"] for item in items),
            "real_at_most_two_segments": sum(item["real_valid_segment_count"] <= 2 for item in items),
            "denominator": n,
        }
        for key in (
            "envelope_only_one_sign",
            "envelope_at_most_two_signs",
            "envelope_majority_truth",
            "real_truth_segment_retained",
            "real_at_most_two_segments",
        ):
            by_varga[prefix][f"{key}_rate"] = ratio(by_varga[prefix][key], n)
    combo = [row["six_question_delivery"]["combination"] for row in rows]
    return {
        "radius": radius,
        "case_count": n,
        "reconciliation": {
            "all_zero_diff": all(not row["reconciliation"].get("changed") for row in rows),
            "case_count": n,
            "changed_case_count": sum(bool(row["reconciliation"].get("changed")) for row in rows),
            "denominator": n,
        },
        "window": window,
        "delivery_envelope": {
            "by_varga": by_varga,
            "combination_only_one": sum(item["envelope_count"] == 1 for item in combo),
            "combination_at_most_two": sum(item["envelope_count"] <= 2 for item in combo),
            "combination_majority_truth": sum(item["envelope_majority_truth"] is True for item in combo),
            "combination_majority_ties": sum(item["envelope_majority_tie"] for item in combo),
            "denominator": n,
        },
    }


def main() -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument("--radii", default=",".join(str(value) for value in RADII))
    parser.add_argument("--vargas", default=",".join(VARGA_PREFIXES))
    parser.add_argument("--limit", type=int, default=0)
    parser.add_argument("--json-out", required=True)
    args = parser.parse_args()
    radii = tuple(int(value) for value in str(args.radii).split(",") if value.strip())
    vargas = tuple(value.strip() for value in str(args.vargas).split(",") if value.strip())
    cases = load_cases()
    if args.limit:
        cases = cases[: args.limit]
    results: list[dict[str, Any]] = []
    errors: list[dict[str, str | int]] = []
    for case in cases:
        for radius in radii:
            label = f"{case.get('case_id')} ±{radius}"
            try:
                row = case_result(case, radius)
                results.append(row)
                print(
                    f"{label} score={row['scoring_candidate_count']} scan={row['scan_point_count']} "
                    f"probes={row['probe_count']} reconcile_changed={bool(row['reconciliation'].get('changed'))}",
                    flush=True,
                )
            except Exception as exc:  # noqa: BLE001
                errors.append({"case_id": str(case.get("case_id") or ""), "radius": radius, "error": f"{type(exc).__name__}: {exc}"})
                print(f"{label} ERROR {type(exc).__name__}: {exc}", flush=True)
    payload = {
        "schema": SCHEMA,
        "metadata": {
            "holdout": str(HOLDOUT.relative_to(ROOT)).replace("\\", "/"),
            "case_count_requested": len(cases),
            "case_count_completed": len({row["case_id"] for row in results}),
            "radii": list(radii),
            "vargas": list(vargas),
            "ayanamsa": "raman",
            "node_mode": "mean",
            "scoring_candidate_step_minutes": SCORING_STEP,
            "segment_scan_step_minutes": SCAN_STEP,
            "refresh_probes": REFRESH_PROBES,
            "replay_probe_source": "existing event_probes.discriminating_event_probes; no refresh",
            "questions_requested": 6,
            "questions_answered_is_recorded_per_case": True,
            "real_valid_candidate_set": "union of cluster_times from still_valid_public after replay; scoring-grid candidates only",
            "interval_envelope": "unionStillValidRange equivalent: min/max clock edges over the real valid candidate clusters; envelope is not the real set",
            "segment_definition": "maximal contiguous one-minute scan run of equal D1/D9/D10 sign; repeated non-contiguous signs retain separate IDs; 23:59->00:00 is contiguous",
            "aggregation_denominator": "77 cases per radius when full run completes; empty coverage and ties are separate counts",
            "reconciliation_scope": "every case and radius, scoring grid only; single-case zero-diff is smoke evidence, not full-set evidence",
            "deterministic_json": True,
        },
        "aggregates": [aggregate(results, radius) for radius in radii],
        "results": results,
        "errors": errors,
    }
    out = Path(args.json_out)
    out.parent.mkdir(parents=True, exist_ok=True)
    out.write_text(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8")
    print(json.dumps(payload["aggregates"], ensure_ascii=False, indent=2, sort_keys=True), flush=True)
    return 0 if not errors and all(item["reconciliation"]["all_zero_diff"] for item in payload["aggregates"]) else 1


if __name__ == "__main__":
    raise SystemExit(main())