Model/scripts/query_failed_modelling_e2e.py

"""Query failed modelling_e2e subtasks and write a markdown report.

Joins sub_task → tasks, pulls property_ids from the inputs JSON, then looks up
UPRNs from the property table.

Hit Run — output written to scripts/failed_modelling_e2e.md
"""

from __future__ import annotations

import json
import sys
from pathlib import Path
from typing import Any, cast

_REPO_ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(_REPO_ROOT))

from sqlalchemy import text  # noqa: E402

from scripts.e2e_common import ENV_PATH, build_engine, load_env  # noqa: E402

_OUTPUT = _REPO_ROOT / "scripts" / "failed_modelling_e2e.md"

load_env(ENV_PATH)
engine = build_engine()

with engine.connect() as conn:
    subtask_rows = conn.execute(text("""
        SELECT
            st.id          AS subtask_id,
            st.task_id,
            st.inputs,
            st.outputs,
            st.updated_at
        FROM sub_task st
        JOIN tasks t ON t.id = st.task_id
        WHERE t.task_source = 'modelling_e2e'
          AND st.status = 'failed'
        ORDER BY st.updated_at DESC
    """)).fetchall()

    if not subtask_rows:
        print("No failed modelling_e2e subtasks found.")
        _OUTPUT.write_text(
            "# Failed modelling_e2e Subtasks\n\nNone found.\n", encoding="utf-8"
        )
        exit(0)

    def _error_text(outputs_raw: object) -> str:
        """Pull the persisted failure reason out of the subtask outputs JSON."""
        try:
            outputs: Any = (
                json.loads(outputs_raw)
                if isinstance(outputs_raw, str)
                else (outputs_raw or {})
            )
        except Exception:
            return str(outputs_raw or "")
        if isinstance(outputs, dict):
            return str(cast("dict[str, Any]", outputs).get("error", ""))
        return ""

    # Collect all property_ids across all rows
    all_property_ids: list[int] = []
    parsed: list[tuple[str, str, list[int], str, str, str]] = []
    for subtask_id, task_id, inputs_raw, outputs_raw, updated_at in subtask_rows:
        try:
            inputs: Any = (
                json.loads(inputs_raw)
                if isinstance(inputs_raw, str)
                else (inputs_raw or {})
            )
            raw_ids = cast("list[Any]", cast("dict[str, Any]", inputs).get("property_ids") or [])
            property_ids: list[int] = [int(p) for p in raw_ids]
        except Exception:
            property_ids = []
        parsed.append(
            (
                str(subtask_id),
                str(task_id),
                property_ids,
                str(updated_at),
                inputs_raw or "",
                _error_text(outputs_raw),
            )
        )
        all_property_ids.extend(property_ids)

    # Look up UPRNs
    uprn_map: dict[int, int] = {}
    if all_property_ids:
        uprn_rows = conn.execute(
            text("SELECT id, uprn FROM property WHERE id = ANY(:ids)"),
            {"ids": all_property_ids},
        ).fetchall()
        uprn_map = {int(r[0]): int(r[1]) for r in uprn_rows}

def _cell(value: str) -> str:
    """Escape table-breaking characters so multi-line errors stay on one row."""
    return value.replace("|", "\\|").replace("\n", "<br>")


lines: list[str] = [
    "# Failed modelling_e2e Subtasks\n",
    f"| Subtask ID | Task ID | Updated At | Property ID | UPRN | Error | Inputs |",
    f"|-----------|---------|------------|-------------|------|-------|--------|",
]

for subtask_id, task_id, property_ids, updated_at, inputs_raw, error in parsed:
    inputs_cell = _cell(inputs_raw or "")
    error_cell = _cell(error or "")
    if property_ids:
        for pid in property_ids:
            uprn = uprn_map.get(pid, "unknown")
            lines.append(
                f"| {subtask_id} | {task_id} | {updated_at} | {pid} | {uprn} | {error_cell} | {inputs_cell} |"
            )
    else:
        lines.append(
            f"| {subtask_id} | {task_id} | {updated_at} | — | — | {error_cell} | {inputs_cell} |"
        )

_OUTPUT.write_text("\n".join(lines) + "\n", encoding="utf-8")
print(f"Written {len(parsed)} failed subtasks → {_OUTPUT}")