"""只读探查：Milvus 知识集合的真实 schema（用于评审 NL_develop 的字段映射改动）。

只做 describe / query，不写入。结果写 `docs/evidence/knowledge-collections.json`：

    python tools/probe_knowledge_collections.py

要回答的问题（对应交付说明 §4.2）：
1. 现库集合的**实际字段名**是什么 —— 是 `doc_id`/`content`/`visibility` 那套，
   还是 `knowledge_id`/`snippet` 那套？他选的字段映射（A 方案）建立在这个前提上；
2. 每个集合有多少行；
3. 有没有 `visibility` 字段 —— 没有的话，检索层的内部资料硬隔离就是关着的。
"""

from __future__ import annotations

import json
from pathlib import Path
from typing import Any

from app.core.config import get_settings

OUTPUT = Path("docs/evidence/knowledge-collections.json")


def _client() -> Any:
    from pymilvus import MilvusClient  # type: ignore[import-untyped]

    settings = get_settings()
    return MilvusClient(uri=settings.milvus_uri, token=settings.milvus_token or None)


def collect() -> dict[str, Any]:
    client = _client()
    report: dict[str, Any] = {"collections": []}
    for name in sorted(client.list_collections()):
        try:
            described = client.describe_collection(name)
            fields = [
                {
                    "name": str(field.get("name")),
                    "type": str(field.get("type")),
                    "is_primary": bool(field.get("is_primary", False)),
                }
                for field in described.get("fields", [])
            ]
            stats = client.get_collection_stats(name)
            row_count = stats.get("row_count") if isinstance(stats, dict) else None
        except Exception as exc:  # 单个集合探测失败不影响其余
            report["collections"].append(
                {"collection": name, "error": f"{type(exc).__name__}: {exc}"}
            )
            continue
        report["collections"].append(
            {
                "collection": name,
                "row_count": row_count,
                "field_names": [field["name"] for field in fields],
                "fields": fields,
                "has_visibility": any(field["name"] == "visibility" for field in fields),
                "looks_like_legacy_schema": any(
                    field["name"] in {"doc_id", "chapter", "doc_no"} for field in fields
                ),
            }
        )
    return report


def main() -> None:
    report = collect()
    OUTPUT.parent.mkdir(parents=True, exist_ok=True)
    OUTPUT.write_text(
        json.dumps(report, ensure_ascii=False, indent=2, default=str),
        encoding="utf-8",
    )
    print(f"wrote {OUTPUT}")


if __name__ == "__main__":
    main()