PGx CN: scan-date batch warning (PCN-006), CN-consistent BAF evidence (PCN-010, --bafs-in-cn),

noise-outlier exclusion + robustness test (PCN-017/EDGE-026), platform from the CSV manifest (CLI-032)

Also: star-allele calls are checked for one manifest/build per run (PGX-011), duplications at the CN cap are
named xN (PGX-022), and tandem names attach supporting variants to their full copy.

tests/unit/test_pgx_cn.py

@@ -57,7 +57,7 @@ def test_packaged_regions() -> None:  # PCN-001
     assert next(r for r in regs if r.gene == "GSTT1").chrom == "chr22_KI270879v1_alt"
 
 
-def _dataset(tmp: Path, n_samples: int = 40) -> tuple[Path, Path, Path, Path]:
+def _dataset(tmp: Path, n_samples: int = 40, n_outliers: int = 0) -> tuple[Path, Path, Path, Path]:
     rng = np.random.default_rng(5)
     loci = []
     for c in ("1", "2"):
@@ -94,6 +94,16 @@ def _dataset(tmp: Path, n_samples: int = 40) -> tuple[Path, Path, Path, Path]:
                 cluster_file="c.egt")  # fmt: skip
         (gtcs / sid).mkdir(parents=True)
         write_gtc(g, gtcs / sid / f"{sid}.gtc")
+    for j in range(n_outliers):  # EDGE-026: noisy, shifted arrays that still pass the LRR SD gate
+        sid = f"2000000099{j:02d}_R01C01"
+        lrr = rng.normal(0.3, 0.19, n)
+        g = Gtc(num_snps=n, genotypes=np.ones(n, np.uint8), genotype_scores=np.full(n, 0.9, np.float32),
+                b_allele_freqs=np.zeros(n, np.float32), logr_ratios=lrr.astype(np.float32),
+                raw_x=np.full(n, 1000, np.uint16), raw_y=np.full(n, 1000, np.uint16),
+                base_calls=np.zeros((n, 2), np.uint8), gender=b"F", call_rate=0.995, logr_dev=0.19,
+                cluster_file="c.egt")  # fmt: skip
+        (gtcs / sid).mkdir(parents=True)
+        write_gtc(g, gtcs / sid / f"{sid}.gtc")
     (tmp / "truth.txt").write_text("\n".join(f"{k}\t{a}\t{b}" for k, (a, b) in truth.items()))
     return bpm, fa, gtcs, regions
 
@@ -102,10 +112,11 @@ def test_pgx_cn_train_and_call(tmp_path: Path) -> None:  # CLI-031/032, PCN-002/
     bpm, fa, gtcs, regions = _dataset(tmp_path)
     run = CliRunner()
     r = run.invoke(app, ["pgx", "copy-number", "train", "--gtcs", str(gtcs), "--bpm", str(bpm), "--fasta", str(fa),
-                         "--out", str(tmp_path / "model"), "--regions", str(regions), "--quiet"])  # fmt: skip
+                         "--out", str(tmp_path / "model"), "--regions", str(regions), "--platform", "EX",
+                         "--quiet"])  # fmt: skip
     assert r.exit_code == 2 and "E_PGX_TRAIN_TOO_SMALL" in r.output  # 40 < 96 (PCN-005)
     r = run.invoke(app, ["pgx", "copy-number", "train", "--gtcs", str(gtcs), "--bpm", str(bpm), "--fasta", str(fa),
-                         "--out", str(tmp_path / "model"), "--regions", str(regions), "--min-samples", "30",
+                         "--out", str(tmp_path / "model"), "--regions", str(regions), "--min-samples", "30", "--platform", "EX",
                          "--min-passing", "30", "--quiet"])  # fmt: skip
     assert r.exit_code == 0, r.output
     model = tmp_path / "model" / "m.simurg-pgxcn"
@@ -143,3 +154,36 @@ def test_pgx_cn_train_and_call(tmp_path: Path) -> None:  # CLI-031/032, PCN-002/
     head = (out / "pgx_cn_sample_summary.tsv").read_text().splitlines()[0].split("\t")
     assert head[:6] == ["sample_id", "sample_name", "sample_folder", "logr_dev", "passed_batch_qc",
                         "used_in_reference"] and head[-1] == "flags"  # fmt: skip
+
+
+def _calls(out: Path) -> dict[str, str]:
+    rows = [ln.split("\t") for ln in (out / "pgx_cn_sample_summary.tsv").read_text().splitlines()]
+    head = rows[0]
+    return {r[0]: ":".join(r[head.index("cn_GENEA")] + r[head.index("cn_GENEB")]) for r in rows[1:]}
+
+
+def test_outlier_robustness(tmp_path: Path) -> None:  # PCN-017 / EDGE-026: 10 % outliers leave other calls alone
+    run = CliRunner()
+    res = {}
+    for tag, n_out in (("clean", 0), ("outliers", 4)):
+        d = tmp_path / tag
+        d.mkdir()
+        bpm, fa, gtcs, regions = _dataset(d, 40, n_out)
+        r = run.invoke(app, ["pgx", "copy-number", "train", "--gtcs", str(gtcs), "--bpm", str(bpm), "--fasta", str(fa),
+                             "--out", str(d / "model"), "--regions", str(regions), "--min-samples", "30",
+                             "--min-passing", "30", "--platform", "EX", "--quiet"])  # fmt: skip
+        assert r.exit_code == 0, r.output
+        r = run.invoke(app, ["pgx", "copy-number", "call", "--gtcs", str(gtcs), "--model", str(d / "model" / "m.simurg-pgxcn"),
+                             "--fasta", str(fa), "--out", str(d / "call"), "--quiet"])  # fmt: skip
+        assert r.exit_code == 0, r.output
+        res[tag] = _calls(d / "call")
+        assert (d / "call" / "pgx_cn_baf_evidence.tsv").exists()  # PCN-010 output
+    same = sum(res["clean"][k] == res["outliers"][k] for k in res["clean"])
+    assert same >= 0.99 * len(res["clean"])
+
+
+def test_platform_required(tmp_path: Path) -> None:  # CLI-032: --platform auto needs a CSV manifest
+    bpm, fa, gtcs, regions = _dataset(tmp_path, 30)
+    r = CliRunner().invoke(app, ["pgx", "copy-number", "train", "--gtcs", str(gtcs), "--bpm", str(bpm), "--fasta",
+                                 str(fa), "--out", str(tmp_path / "m"), "--regions", str(regions), "--quiet"])  # fmt: skip
+    assert r.exit_code == 2 and "E_PGX_PLATFORM_UNKNOWN" in r.output