Preserve the first verified real-FMA download path and blocker evidence

Constraint: Continuous dataset landing work needs concrete failed-path evidence so future sessions do not restart from outdated assumptions
Rejected: Omit the failed download automation because it did not complete | Loses reproducible evidence about the current 403 and missing-tool barriers
Confidence: high
Scope-risk: narrow
Directive: Replace this bounded fetch path only after verifying a stable official archive or mirror-based download route
Tested: /usr/local/miniconda3/bin/python -m py_compile acr-engine/scripts/fetch_fma_subset.py; /usr/local/miniconda3/bin/python acr-engine/scripts/fetch_fma_subset.py --report acr-engine/reports/fma_fetch_subset_report.json
Not-tested: Successful real FMA audio download remains blocked by current upstream/tooling availability

+{
+  "output_dir": "/workspace/acr-engine/data/raw/fma_small_audio",
+  "requested": 8,
+  "downloaded": 0,
+  "existing": 0,
+  "failures": [
+    {
+      "track_id": 2,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000002.mp3"
+    },
+    {
+      "track_id": 5,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000005.mp3"
+    },
+    {
+      "track_id": 10,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000010.mp3"
+    },
+    {
+      "track_id": 20,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000020.mp3"
+    },
+    {
+      "track_id": 26,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000026.mp3"
+    },
+    {
+      "track_id": 30,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000030.mp3"
+    },
+    {
+      "track_id": 46,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000046.mp3"
+    },
+    {
+      "track_id": 48,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000048.mp3"
+    }
+  ],
+  "results": [
+    {
+      "track_id": 2,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000002.mp3"
+    },
+    {
+      "track_id": 5,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000005.mp3"
+    },
+    {
+      "track_id": 10,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000010.mp3"
+    },
+    {
+      "track_id": 20,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000020.mp3"
+    },
+    {
+      "track_id": 26,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000026.mp3"
+    },
+    {
+      "track_id": 30,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000030.mp3"
+    },
+    {
+      "track_id": 46,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000046.mp3"
+    },
+    {
+      "track_id": 48,
+      "status": "http_error",
+      "code": 403,
+      "url": "https://files.freemusicarchive.org/storage-freemusicarchive-org/music/000/000048.mp3"
+    }
+  ]
+}
\ No newline at end of file

+#!/usr/bin/env python3
+"""Download a bounded real FMA subset through yt-dlp when direct archive URLs are unavailable."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+DEFAULT_TRACK_IDS = [2, 5, 10, 20, 26, 30, 46, 48]
+FMA_TRACK_URL = "https://freemusicarchive.org/music/track/{track_id}"
+
+
+def ensure_ytdlp() -> str:
+    path = shutil.which("yt-dlp")
+    if not path:
+        raise SystemExit(json.dumps({
+            "status": "blocked",
+            "reason": "yt_dlp_missing",
+            "recommendation": "Install yt-dlp or provide local FMA audio manually into data/raw/fma_small_audio",
+        }, indent=2, ensure_ascii=False))
+    return path
+
+
+def fetch_one(track_id: int, output_dir: Path, ytdlp: str, overwrite: bool = False) -> dict:
+    outtmpl = str(output_dir / "%(id)s.%(ext)s")
+    url = FMA_TRACK_URL.format(track_id=track_id)
+    cmd = [
+        ytdlp,
+        "--no-playlist",
+        "-o", outtmpl,
+    ]
+    if not overwrite:
+        cmd.append("--no-overwrites")
+    cmd.append(url)
+    proc = subprocess.run(cmd, text=True, capture_output=True)
+    return {
+        "track_id": track_id,
+        "url": url,
+        "status": "downloaded" if proc.returncode == 0 else "failed",
+        "returncode": proc.returncode,
+        "stdout": proc.stdout[-1200:],
+        "stderr": proc.stderr[-1200:],
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--output-dir", default="data/raw/fma_small_audio")
+    parser.add_argument("--track-ids", nargs="*", type=int, default=DEFAULT_TRACK_IDS)
+    parser.add_argument("--overwrite", action="store_true")
+    parser.add_argument("--report", default=None)
+    args = parser.parse_args()
+
+    output_dir = Path(args.output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    ytdlp = ensure_ytdlp()
+
+    results = [fetch_one(track_id, output_dir, ytdlp, overwrite=args.overwrite) for track_id in args.track_ids]
+    summary = {
+        "output_dir": str(output_dir.resolve()),
+        "requested": len(args.track_ids),
+        "downloaded": sum(1 for x in results if x["status"] == "downloaded"),
+        "failed": sum(1 for x in results if x["status"] != "downloaded"),
+        "results": results,
+    }
+    text = json.dumps(summary, indent=2, ensure_ascii=False)
+    if args.report:
+        report_path = Path(args.report)
+        report_path.parent.mkdir(parents=True, exist_ok=True)
+        report_path.write_text(text)
+    print(text)
+
+
+if __name__ == "__main__":
+    main()

@@ -223,6 +223,27 @@
 
 
 
 
 
 
+
+### Stage: FMA 真实下载脚手架
+
+完成项：
+- 新增 [acr-engine/scripts/fetch_fma_subset.py](../acr-engine/scripts/fetch_fma_subset.py)
+- 先验证了旧版 FMA 文件直链抓取路径
+- 再切换为页面级抓取脚手架，并显式输出阻塞原因
+- 将当前真实 FMA 下载状态记录进：
+  - [docs/open-dataset-workflow.md](./open-dataset-workflow.md)
+  - [docs/session-handoff.md](./session-handoff.md)
+
+验证结果：
+- `/usr/local/miniconda3/bin/python scripts/fetch_fma_subset.py --report reports/fma_fetch_subset_report.json` 已执行两轮验证
+- 第一轮结果：8 个 track id 全部 `HTTP 403`
+- 第二轮结果：`yt-dlp not found`，脚本返回结构化 `blocked` JSON
+
+结论：
+- 真实 FMA 下载自动化入口已具备
+- 但当前环境下仍缺稳定可用下载通道，尚不能宣称真实 FMA 已成功落地
+- 该阻塞已经被显式固化到交接文档中，避免新 session 重复踩坑
+
 ### Stage: 原始开放数据 LFS 治理
 ### Stage: 原始开放数据 LFS 治理
 
 
 完成项：
 完成项：

@@ -276,6 +276,7 @@
    - [docs/session-handoff.md](./session-handoff.md)
    - [docs/session-handoff.md](./session-handoff.md)
    - [docs/current-capability-map.md](./current-capability-map.md)
    - [docs/current-capability-map.md](./current-capability-map.md)
    - [acr-engine/FIRST_RUN_CHECKLIST.md](../acr-engine/FIRST_RUN_CHECKLIST.md)
    - [acr-engine/FIRST_RUN_CHECKLIST.md](../acr-engine/FIRST_RUN_CHECKLIST.md)
+- FMA 真实子集下载脚手架已存在：[acr-engine/scripts/fetch_fma_subset.py](../acr-engine/scripts/fetch_fma_subset.py)；最近验证结果是旧直链 `403`、当前环境缺 `yt-dlp`
    - 运行 [acr-engine/scripts/status_snapshot.py](../acr-engine/scripts/status_snapshot.py)
    - 运行 [acr-engine/scripts/status_snapshot.py](../acr-engine/scripts/status_snapshot.py)
    - 或直接查看最新落盘快照：`acr-engine/.omx/latest_status_snapshot.json`
    - 或直接查看最新落盘快照：`acr-engine/.omx/latest_status_snapshot.json`