P4 (WIP): GenCall-equivalent calling, BAF/LRR, sex, GTC v5, simurg genotype

- genotype/clusters.py: EGT aligned to manifest order (float32 mean R)
- genotype/gencall.py: flair, six-case likelihood, priors/posteriors,
  fuzzy sub-scores and score map, vectorised with the reference's
  float/double evaluation order and libm transcendentals
- genotype/baf_lrr.py, sex.py (rules v1/v2), sample.py (IDAT -> Gtc)
- pipeline/inputs.py shared by ingest and genotype
- pipeline/genotype.py + CLI: GTC per sample, sample_summary.tsv/json
  (OUT-060..063), run manifest
- GTCs from IDATs are byte-identical to the oracle for 36 GSA samples x
  2 normalization versions (NaN sign canonicalised to the x86 pattern)

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv

src/simurg/cli/main.py

@@ -1,6 +1,6 @@
 """``simurg`` command-line interface (spec §2, plan §14).
 
-Available: ``version``, ``inspect`` (P1), ``ingest`` (P2), ``normalize`` (P3).
+Available: ``version``, ``inspect`` (P1), ``ingest`` (P2), ``normalize`` (P3), ``genotype`` (P4).
 Later phases add the other commands of CLI-001.
 """
 
@@ -274,5 +274,67 @@ def normalize_cmd(
     run_guarded(rep, lambda: run_normalize(opts, rep))
 
 
+# --------------------------------------------------------------------------------------------------------
+@app.command("genotype")
+def genotype_cmd(
+    bpm: Annotated[Path, typer.Option("--bpm", help="BPM manifest (required).")],
+    egt: Annotated[Path, typer.Option("--egt", help="EGT cluster file (required).")],
+    out: Annotated[Path, typer.Option("--out", help="Output folder (required).")],
+    idats: Annotated[Path | None, typer.Option("--idats", help="Folder searched recursively for IDAT pairs.")] = None,
+    sheet: Annotated[Path | None, typer.Option("--sheet", help="Sample sheet (CSV).")] = None,
+    csv: Annotated[Path | None, typer.Option("--csv", help="CSV manifest, checked against the BPM.")] = None,
+    cutoff: Annotated[float, typer.Option("--cutoff", help="GenCall score below which a call is a no-call.")] = 0.15,
+    norm_version: Annotated[str, typer.Option("--norm-version", help="1.2.0 (current) or 1.1.2")] = "1.2.0",
+    sex_version: Annotated[int, typer.Option("--sex-version", min=1, max=2, help="Sex estimate rule (1 or 2).")] = 2,
+    gtc_version: Annotated[int, typer.Option("--gtc-version", help="GTC format version (3 or 5).")] = 5,
+    autocall_date: Annotated[
+        str | None, typer.Option("--autocall-date", help="Fixed value for GTC field 201 (reproducible output).")
+    ] = None,
+    threads: Annotated[int, typer.Option("--threads", min=0, max=1024, help="Worker processes (0 = auto).")] = 0,
+    force: Annotated[bool, typer.Option("--force", help="Replace existing outputs.")] = False,
+    layout: Annotated[str, typer.Option("--layout", help="nested|flat")] = "nested",
+    on_duplicate_idat: Annotated[str, typer.Option("--on-duplicate-idat", help="error|first|newest")] = "error",
+    log_json: Annotated[bool, typer.Option("--log-json", "--json-log", help="JSON Lines log on stderr.")] = False,
+    debug: Annotated[bool, typer.Option("--debug", help="Debug logging with tracebacks.")] = False,
+    quiet: Annotated[bool, typer.Option("--quiet", "--no-progress", help="Suppress info messages.")] = False,
+) -> None:
+    """IDAT pairs → GTC files and a sample summary (GenCall-equivalent calling; phase P4)."""
+    from simurg.pipeline.genotype import GenotypeOptions, run_genotype
+
+    if layout not in ("nested", "flat"):
+        raise typer.BadParameter("--layout must be nested or flat")
+    if gtc_version not in (3, 5):
+        raise typer.BadParameter("--gtc-version must be 3 or 5")
+    if norm_version not in ("1.2.0", "1.1.2"):
+        raise typer.BadParameter("--norm-version must be 1.2.0 or 1.1.2")
+    rep = Reporter(
+        command="genotype",
+        level="debug" if debug else "info",
+        json_stderr=log_json,
+        debug=debug,
+        quiet=quiet,
+        log_file=out / "logs" / "genotype.log",
+    )
+    opts = GenotypeOptions(
+        out=out,
+        bpm=bpm,
+        egt=egt,
+        idats=idats,
+        sheet=sheet,
+        csv=csv,
+        threads=threads,
+        force=force,
+        layout=layout,
+        on_duplicate_idat=on_duplicate_idat,
+        cutoff=cutoff,
+        norm_version=norm_version,
+        sex_version=sex_version,
+        gtc_version=gtc_version,
+        autocall_date=autocall_date,
+        argv=sys.argv[1:],
+    )
+    run_guarded(rep, lambda: run_genotype(opts, rep))
+
+
 if __name__ == "__main__":  # pragma: no cover
     app()