Prevent empty local dataset folders from masquerading as smoke-ready

Constraint: Real-data validation now depends on user-requested local corpus drop zones that may exist before they contain any audio
Rejected: Let smoke-local fail deep inside training | Produces slower and less actionable feedback for continuous sessions
Confidence: high
Scope-risk: narrow
Directive: Keep readiness thresholds aligned with the minimum viable query split assumptions before expanding real-data automation
Tested: /usr/local/miniconda3/bin/python -m py_compile src/data/external_adapters.py scripts/status_snapshot.py; /usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0; /usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0; /usr/local/miniconda3/bin/python scripts/status_snapshot.py --output .omx/latest_status_snapshot.json
Not-tested: Full smoke-local on real FMA or MTG-Jamendo remains blocked until audio is actually downloaded

@@ -6,39 +6,67 @@ from pathlib import Path
 
 root = Path.cwd()
 workspace_root = root.parent
+PYTHON = "/usr/local/miniconda3/bin/python"
+
 
 def sh(cmd):
     return subprocess.check_output(cmd, shell=True, text=True).strip()
 
+
+def check_dataset(dataset: str, input_dir: str):
+    cmd = [
+        PYTHON,
+        "src/data/external_adapters.py",
+        "check-local-ready",
+        dataset,
+        input_dir,
+        "--eval-ratio", "0.2",
+        "--query-duration", "8.0",
+    ]
+    result = subprocess.check_output(cmd, text=True)
+    return json.loads(result)
+
+
 def build_snapshot():
+    fma_dir = "data/raw/fma_small_audio"
+    jamendo_dir = "data/raw/mtg_jamendo_audio"
+    fma_ready = check_dataset("fma", fma_dir)
+    jamendo_ready = check_dataset("mtg_jamendo", jamendo_dir)
     return {
-        'latest_commit': sh('git log --oneline -n 1'),
-        'docs': {
-            'readme': str((workspace_root / 'docs/README.md').resolve()),
-            'handoff': str((workspace_root / 'docs/session-handoff.md').resolve()),
-            'workflow': str((workspace_root / 'docs/open-dataset-workflow.md').resolve()),
+        "latest_commit": sh("git log --oneline -n 1"),
+        "docs": {
+            "readme": str((workspace_root / "docs/README.md").resolve()),
+            "handoff": str((workspace_root / "docs/session-handoff.md").resolve()),
+            "workflow": str((workspace_root / "docs/open-dataset-workflow.md").resolve()),
+            "capability_map": str((workspace_root / "docs/current-capability-map.md").resolve()),
         },
-        'drop_zones': {
-            'fma': str((root / 'data/raw/fma_small_audio').resolve()),
-            'mtg_jamendo': str((root / 'data/raw/mtg_jamendo_audio').resolve()),
+        "drop_zones": {
+            "fma": str((root / fma_dir).resolve()),
+            "mtg_jamendo": str((root / jamendo_dir).resolve()),
         },
-        'verified_open_smoke_dirs': {
-            'manifests': str((root / 'data/external_ingested/synthetic_as_open_fixed/fma/manifests').resolve()),
-            'reports': str((root / 'reports/open-smoke-fixed/fma').resolve()),
-            'one_shot_reports': str((root / 'data/external_smoke/fma_reports_smoke').resolve()),
+        "dataset_readiness": {
+            "fma": fma_ready,
+            "mtg_jamendo": jamendo_ready,
+        },
+        "verified_open_smoke_dirs": {
+            "manifests": str((root / "data/external_ingested/synthetic_as_open_fixed/fma/manifests").resolve()),
+            "reports": str((root / "reports/open-smoke-fixed/fma").resolve()),
+            "one_shot_reports": str((root / "data/external_smoke/fma_reports_smoke").resolve()),
+        },
+        "next_commands": {
+            "check_fma": f"{PYTHON} src/data/external_adapters.py check-local-ready fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0",
+            "inspect_fma": f"{PYTHON} src/data/external_adapters.py inspect-local fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0",
+            "smoke_fma": f"{PYTHON} src/data/external_adapters.py smoke-local fma data/raw/fma_small_audio --output-root data/external_smoke --eval-ratio 0.2 --query-duration 8.0 --train-epochs 1 --batch-size 2",
+            "check_jamendo": f"{PYTHON} src/data/external_adapters.py check-local-ready mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0",
+            "inspect_jamendo": f"{PYTHON} src/data/external_adapters.py inspect-local mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0",
+            "smoke_jamendo": f"{PYTHON} src/data/external_adapters.py smoke-local mtg_jamendo data/raw/mtg_jamendo_audio --output-root data/external_smoke --eval-ratio 0.2 --query-duration 8.0 --train-epochs 1 --batch-size 2",
         },
-        'next_commands': {
-            'inspect_fma': '/usr/local/miniconda3/bin/python src/data/external_adapters.py inspect-local fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0',
-            'smoke_fma': '/usr/local/miniconda3/bin/python src/data/external_adapters.py smoke-local fma data/raw/fma_small_audio --output-root data/external_smoke --eval-ratio 0.2 --query-duration 8.0 --train-epochs 1 --batch-size 2',
-            'inspect_jamendo': '/usr/local/miniconda3/bin/python src/data/external_adapters.py inspect-local mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0',
-            'smoke_jamendo': '/usr/local/miniconda3/bin/python src/data/external_adapters.py smoke-local mtg_jamendo data/raw/mtg_jamendo_audio --output-root data/external_smoke --eval-ratio 0.2 --query-duration 8.0 --train-epochs 1 --batch-size 2'
-        }
     }
 
 
 def main():
     parser = argparse.ArgumentParser()
-    parser.add_argument('--output', default=None)
+    parser.add_argument("--output", default=None)
     args = parser.parse_args()
 
     snapshot = build_snapshot()
@@ -50,5 +78,5 @@ def main():
     print(text)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

@@ -10,6 +10,11 @@ import json
 import subprocess
 
 
+AUDIO_EXTS = (".wav", ".mp3", ".flac", ".ogg")
+MIN_SMOKE_AUDIO_FILES = 2
+MIN_SMOKE_ELIGIBLE_QUERY_FILES = 2
+
+
 @dataclass
 class DatasetRecord:
     name: str
@@ -198,6 +203,77 @@ REGISTRY: List[DatasetRecord] = [
 ]
 
 
+def count_audio_files(input_dir: Path) -> int:
+    return len([p for p in input_dir.rglob("*") if p.suffix.lower() in AUDIO_EXTS])
+
+
+def assess_local_dataset_ready(
+    dataset: str,
+    input_dir: Path,
+    query_duration: float = 8.0,
+    eval_ratio: float = 0.2,
+) -> Dict:
+    adapter = ADAPTERS[dataset]
+    input_dir = input_dir.resolve()
+    exists = input_dir.exists()
+    is_dir = input_dir.is_dir()
+    inspect_summary = None
+    num_audio_files = 0
+    eligible_query_files = 0
+    issues = []
+
+    if not exists:
+        issues.append("input_dir_missing")
+    elif not is_dir:
+        issues.append("input_path_not_directory")
+    else:
+        inspect_summary = adapter.inspect_local_audio(
+            input_dir,
+            query_duration=query_duration,
+            eval_ratio=eval_ratio,
+        )
+        num_audio_files = int(inspect_summary.get("num_audio_files", 0))
+        eligible_query_files = int(inspect_summary.get("eligible_query_files", 0))
+        if num_audio_files < MIN_SMOKE_AUDIO_FILES:
+            issues.append("not_enough_audio_files_for_smoke")
+        if eligible_query_files < MIN_SMOKE_ELIGIBLE_QUERY_FILES:
+            issues.append("not_enough_query_eligible_files_for_smoke")
+
+    ready = len(issues) == 0
+    recommendations = []
+    if "input_dir_missing" in issues:
+        recommendations.append(f"Create and populate {input_dir} with local audio files ({', '.join(AUDIO_EXTS)})")
+    if "input_path_not_directory" in issues:
+        recommendations.append("Replace the input path with a directory containing local audio files")
+    if "not_enough_audio_files_for_smoke" in issues:
+        recommendations.append(f"Add at least {MIN_SMOKE_AUDIO_FILES} audio files before running smoke-local")
+    if "not_enough_query_eligible_files_for_smoke" in issues:
+        recommendations.append(
+            f"Add at least {MIN_SMOKE_ELIGIBLE_QUERY_FILES} files with duration >= {query_duration:.1f}s"
+        )
+    if ready:
+        recommendations.append("Run smoke-local to verify the full train/index/eval/artifact pipeline on this local dataset")
+
+    return {
+        "dataset": dataset,
+        "input_dir": str(input_dir),
+        "exists": exists,
+        "is_dir": is_dir,
+        "ready_for_smoke": ready,
+        "num_audio_files": num_audio_files,
+        "eligible_query_files": eligible_query_files,
+        "minimum_requirements": {
+            "audio_files": MIN_SMOKE_AUDIO_FILES,
+            "eligible_query_files": MIN_SMOKE_ELIGIBLE_QUERY_FILES,
+            "query_duration": query_duration,
+            "eval_ratio": eval_ratio,
+        },
+        "issues": issues,
+        "recommendations": recommendations,
+        "inspect": inspect_summary,
+    }
+
+
 def write_registry(output_path: str):
     out = Path(output_path)
     out.parent.mkdir(parents=True, exist_ok=True)
@@ -231,8 +307,21 @@ def smoke_local_dataset(
     train_epochs: int,
     batch_size: int,
 ) -> Dict:
+    readiness = assess_local_dataset_ready(
+        dataset,
+        input_dir,
+        query_duration=query_duration,
+        eval_ratio=eval_ratio,
+    )
+    if not readiness["ready_for_smoke"]:
+        raise SystemExit(json.dumps({
+            "status": "blocked",
+            "reason": "dataset_not_ready_for_smoke",
+            "readiness": readiness,
+        }, indent=2, ensure_ascii=False))
+
     adapter = ADAPTERS[dataset]
-    inspect_summary = adapter.inspect_local_audio(input_dir, query_duration=query_duration, eval_ratio=eval_ratio)
+    inspect_summary = readiness["inspect"]
     prepare_summary = adapter.prepare_local_audio(
         input_dir,
         output_root / dataset,
@@ -305,6 +394,7 @@ def smoke_local_dataset(
 
     return {
         "dataset": dataset,
+        "readiness": readiness,
         "inspect": inspect_summary,
         "prepare": prepare_summary,
         "validate": validate_summary,
@@ -352,6 +442,12 @@ def main():
     p.add_argument("dataset", choices=sorted(ADAPTERS))
     p.add_argument("manifests_dir")
 
+    p = sub.add_parser("check-local-ready")
+    p.add_argument("dataset", choices=sorted(ADAPTERS))
+    p.add_argument("input_dir")
+    p.add_argument("--eval-ratio", type=float, default=0.2)
+    p.add_argument("--query-duration", type=float, default=8.0)
+
     p = sub.add_parser("smoke-local")
     p.add_argument("dataset", choices=sorted(ADAPTERS))
     p.add_argument("input_dir")
@@ -394,6 +490,14 @@ def main():
     elif args.cmd == "validate-local":
         summary = ADAPTERS[args.dataset].validate_local_manifests(Path(args.manifests_dir))
         print(json.dumps(summary, indent=2, ensure_ascii=False))
+    elif args.cmd == "check-local-ready":
+        summary = assess_local_dataset_ready(
+            dataset=args.dataset,
+            input_dir=Path(args.input_dir),
+            eval_ratio=args.eval_ratio,
+            query_duration=args.query_duration,
+        )
+        print(json.dumps(summary, indent=2, ensure_ascii=False))
     elif args.cmd == "smoke-local":
         summary = smoke_local_dataset(
             dataset=args.dataset,

@@ -221,6 +221,32 @@
 - 新 session 现在可以直接读取最近一次状态快照文件
 - 交接信息更适合自动化和长期持续开发
 
+
+### Stage: 真实数据就绪度守门
+
+完成项：
+- 为 [acr-engine/src/data/external_adapters.py](../acr-engine/src/data/external_adapters.py) 新增 `check-local-ready`
+- 为 `smoke-local` 增加前置就绪度守门，避免对空目录直接进入训练链路
+- 增强 [acr-engine/scripts/status_snapshot.py](../acr-engine/scripts/status_snapshot.py)，输出：
+  - `dataset_readiness`
+  - `capability_map` 文档入口
+  - `check-local-ready` 下一步命令
+- 补充 [docs/open-dataset-workflow.md](./open-dataset-workflow.md) 与 [docs/session-handoff.md](./session-handoff.md) 的真实数据检查说明
+
+验证结果：
+- `/usr/local/miniconda3/bin/python -m py_compile src/data/external_adapters.py scripts/status_snapshot.py` 成功
+- `/usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0` 成功
+- `/usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0` 成功
+- `/usr/local/miniconda3/bin/python scripts/status_snapshot.py --output .omx/latest_status_snapshot.json` 成功
+- 当前结果：
+  - `fma.ready_for_smoke=false`
+  - `mtg_jamendo.ready_for_smoke=false`
+  - 原因均为音频文件数与可切 query 文件数不足
+
+结论：
+- 真实开放数据现在有了明确的“进入 smoke 前门槛”
+- 新 session 和自动化脚本可以立刻识别空目录，而不是误以为真实数据已经准备完成
+
 ### Stage: 当前能力地图
 
 完成项：

 # Open Dataset Workflow / 开放数据工作流
 
+## 0. 本地真实数据就绪检查
+
+在跑 `smoke-local` 前，先确认目录里真的有足够的音频：
+
+```bash
+/usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready fma data/raw/fma_small_audio --eval-ratio 0.2 --query-duration 8.0
+/usr/local/miniconda3/bin/python src/data/external_adapters.py check-local-ready mtg_jamendo data/raw/mtg_jamendo_audio --eval-ratio 0.2 --query-duration 8.0
+```
+
+判定标准：
+
+- 至少 `2` 个音频文件
+- 至少 `2` 个时长 `>= 8s` 的可切 query 文件
+- `ready_for_smoke=true` 才进入完整 smoke
+
+如果目录为空，状态快照脚本也会明确提示未就绪。
+
+
 > 更新：2026-06-02
 
 ## 一页结论