scripts/generate_sample_traces.py

"""Generate stable public sample traces for the mock MVP."""

from __future__ import annotations

import json
import sys
from datetime import datetime, timezone
from pathlib import Path

PROJECT_ROOT = Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

from src.examples import EXAMPLE_OBJECTS
from src.pipeline import generate_object_diary


DEFAULT_OUTPUT_DIR = Path("data/traces/samples")


def generate_sample_traces(output_dir: Path = DEFAULT_OUTPUT_DIR) -> list[Path]:
    output_dir.mkdir(parents=True, exist_ok=True)
    written_paths: list[Path] = []

    for index, example in enumerate(EXAMPLE_OBJECTS, start=1):
        description = example["description"]
        mode = example["mode"]
        result = generate_object_diary(
            image_path=None,
            description=description,
            mode=mode,
            save=False,
            trace_id=f"sample-{index:02d}",
            created_at=datetime(2026, 6, 5, 0, index, tzinfo=timezone.utc),
        )

        filename = f"sample-{index:02d}-{_slug(example['label'])}.json"
        path = output_dir / filename
        path.write_text(
            json.dumps(result.trace.model_dump(mode="json"), ensure_ascii=False, indent=2),
            encoding="utf-8",
        )
        written_paths.append(path)

    return written_paths


def _slug(value: str) -> str:
    slug = value.split("/", maxsplit=1)[0].strip().lower()
    return "".join(char if char.isalnum() else "-" for char in slug).strip("-")


if __name__ == "__main__":
    for generated_path in generate_sample_traces():
        print(generated_path)