fix(detect): 钳掉 Label Studio 导出坐标的浮点溢出

真实导出里出现 height=1.0000000000000002：Label Studio 按百分比存框，导出时 /100
留下浮点误差。ultralytics 读标签时对 >1 的坐标直接报错，所以这点溢出必须钳掉，
否则装配出的数据集根本训不起来。

只钳 1e-6 量级的溢出，真正越界的坐标仍然报错。顺带把坐标统一写成 6 位小数。

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tests/test_build_yolo_dataset.py

@@ -76,7 +76,10 @@ def test_builds_a_split_dataset(export, tmp_path):
     images, labels = outputs(out, "images"), outputs(out, "labels")
     assert set(images) == set(LABELS) == set(labels)
     for stem, path in labels.items():
-        assert path.read_text(encoding="utf-8") == LABELS[stem]
+        # 内容等价，但坐标统一成 6 位小数
+        written = [line.split() for line in path.read_text(encoding="utf-8").splitlines()]
+        expected = [line.split() for line in LABELS[stem].splitlines()]
+        assert [[v[0], *(f"{float(x):.6f}" for x in v[1:])] for v in expected] == written
         # 图与标签必须落在同一个 split，否则验证集会混进训练图
         assert path.parent.name == images[stem].parent.name
 
@@ -227,3 +230,41 @@ def test_refuses_to_clobber_and_dry_run_writes_nothing(export, tmp_path):
     assert run(export, out) == 0
     assert run(export, out) != 0                  # 已存在且非空
     assert run(export, out, "--overwrite") == 0
+
+
+def _repack(archive, tmp_path, replacements):
+    """复制一份导出，替换其中几个标签文件。"""
+    broken = tmp_path / "repacked.zip"
+    with zipfile.ZipFile(archive) as source, zipfile.ZipFile(broken, "w") as target:
+        for item in source.namelist():
+            data = replacements.get(item, source.read(item))
+            target.writestr(item, data.encode("utf-8") if isinstance(data, str) else data)
+    return broken
+
+
+def test_float_overshoot_is_clamped(export, tmp_path, capsys):
+    """Label Studio 按百分比存框，/100 后会出现 1.0000000000000002。
+
+    回归：不钳位的话 ultralytics 读标签时会直接报"坐标未归一化"而拒绝训练。
+    """
+    archive, images = export
+    overshoot = "1 0.49999999999999994 0.5000000000000001 0.9999999999999999 1.0000000000000002\n"
+    repacked = _repack(archive, tmp_path, {"labels/grease_0001.txt": overshoot})
+
+    out = tmp_path / "out"
+    assert run((repacked, images), out) == 0
+    assert "已钳到 [0,1]" in capsys.readouterr().out
+
+    written = outputs(out, "labels")["grease_0001"].read_text(encoding="utf-8").split()
+    assert written == ["1", "0.500000", "0.500000", "1.000000", "1.000000"]
+    assert all(0.0 <= float(v) <= 1.0 for v in written[1:])
+    # 四个值里只有 1.0000000000000002 真的越界，其余虽有浮点误差但仍在 [0,1] 内
+    assert json.loads((out / "summary.json").read_text(encoding="utf-8"))["clamped_coordinates"] == 1
+
+
+def test_real_out_of_range_is_still_rejected(export, tmp_path, capsys):
+    """只钳浮点误差量级；真正越界的坐标仍要报错。"""
+    archive, images = export
+    repacked = _repack(archive, tmp_path, {"labels/grease_0001.txt": "1 0.5 1.02 0.1 0.1\n"})
+    assert run((repacked, images), tmp_path / "out") != 0
+    assert "不在 [0,1]" in capsys.readouterr().out