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.

src/simurg/pipeline/pgx_star.py

@@ -11,6 +11,7 @@ import contextlib
 import gzip
 import json
 import math
+import re
 import sqlite3
 from collections import defaultdict
 from dataclasses import dataclass, field
@@ -205,7 +206,9 @@ def solution_detail(m: GeneModel, obs: Observations, recs: list[dict[str, Any] |
     hap_of = {m.haplotypes[i]: i for i in s.copies}
     reason = {NO_CALL: "no_call", MASKED: "masked", NOT_COVERED: "not_on_array"}
     for name in names:
-        core = name.split("x")[0] if "x" in name and name.split("x")[-1].isdigit() else name
+        unit = name.split("+")[-1]  # "*68+*4" → the full copy "*4"; "*2x2"/"*1xN" → "*2"/"*1"
+        mx = re.fullmatch(r"(.+?)x(\d+|N)", unit)
+        core = mx.group(1) if mx else unit
         h = hap_of.get(core)
         sup, unres = [], []
         if h is not None:
@@ -300,6 +303,7 @@ def run_star_call(o: StarOptions, rep: Reporter) -> int:
     unres_rows: list[dict[str, Any]] = []
     not_cov_rows: dict[tuple[str, str], dict[str, Any]] = {}
     calls_json = []
+    first_ident: tuple[str, str] | None = None
     for sid, path in sorted(snv.items()):
         recs, meta = read_vcf_sites(path, wanted)
         opts = meta.get("simurg_options", "")
@@ -313,6 +317,12 @@ def run_star_call(o: StarOptions, rep: Reporter) -> int:
             or kv.get("include_loci", "none").lower() != "none"
         ):  # PGX-011
             raise SimurgError("E_PGX_VCF_UNSUITABLE", f"{path}: made with unsquashed duplicates or a locus filter")
+        ident = (meta.get("simurg_manifest", "").split(";")[0], meta.get("simurg_genome_build", ""))
+        if first_ident is None:
+            first_ident = ident
+        elif ident != first_ident and not o.allow_foreign_vcf:  # PGX-011 (4)
+            raise SimurgError("E_PGX_VCF_UNSUITABLE", f"{path}: manifest/build {ident} differs from {first_ident}",
+                              hint="call one manifest and build per run")  # fmt: skip
         cn = {} if o.no_cn or sid not in cnv else read_cn_vcf(cnv[sid])
         masked = masks.get(meta.get("simurg_manifest", "").split(";")[0], set())
         sample_name = sid
@@ -375,6 +385,12 @@ def call_one_gene(
                                feasible_ratio=o.feasible_ratio, structure=structure)  # fmt: skip
     if not sols:
         return None, [], [], [], []
+    if gcn is not None and gcn >= 5:  # PGX-022: CN 5 means "5 or more" → the duplication count is unknown (xN)
+        import re as _re
+
+        for s_ in sols:
+            s_.haplotypes = tuple(_re.sub(r"x\d+$", "xN", h) for h in s_.haplotypes)
+            s_.members = [tuple(_re.sub(r"x\d+$", "xN", h) for h in mm) for mm in s_.members]
     top = sols[0]
     details = [solution_detail(m, obs, vrec, s_, top, o.low_gs, MAX_EDIT_DISTANCE) for s_ in sols]
     flags = []