P6 complete: optional VCF fields, SNV+indel merging, auxiliary MNV loci, PLINK 2 .pgen

- gtc-to-vcf --info-fields ASSAY_TYPE,NORM_BIN,GENTRAIN,CLUSTER_SEP,ILMN_STRAND,PROBE_IDS (--egt) and
  --extra-format X,Y,NORMX,NORMY,THETA,R, in per-sample VCFs and the --merge BCF (OUT-012, plan §8.3);
  equal to gtc2vcf's values (THETA/R missing where both normalized intensities are 0, K-023)
- --merge-snv-indel (OUT-021, EDGE-013): alleles extended to the longest REF; SNV probes read the base at POS
- --auxiliary-loci (OUT-035, EDGE-015): rules (a)-(e), E_AUX_INVALID; rule (d) uses the last plus-strand base
  for minus-strand designs (spec amended, as GTCtoVCF)
- export plink --format bed|pgen|both: PLINK 2 fixed-width .pgen/.pvar/.psam; plink2 reads it back to a .bed
  byte-identical to ours
- cohort store keeps raw/normalized intensities for the BCF path; tests (unit + gtc2vcf oracle); docs

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

src/simurg/cli/main.py

@@ -397,6 +397,22 @@ def gtc_to_vcf_cmd(
     merge: Annotated[
         bool, typer.Option("--merge", help="One multi-sample BCF (+ .csi) instead of per-sample VCFs.")
     ] = False,
+    auxiliary_loci: Annotated[
+        Path | None, typer.Option("--auxiliary-loci", help="VCF of true MNV definitions for manifest probes (OUT-035).")
+    ] = None,
+    merge_snv_indel: Annotated[
+        bool, typer.Option("--merge-snv-indel", help="One record for an SNV and an indel at the same position.")
+    ] = False,
+    info_fields: Annotated[
+        str,
+        typer.Option(
+            "--info-fields", help="Comma list: ASSAY_TYPE,NORM_BIN,GENTRAIN,CLUSTER_SEP,ILMN_STRAND,PROBE_IDS"
+        ),
+    ] = "",
+    extra_format: Annotated[
+        str, typer.Option("--extra-format", help="Comma list: X,Y,NORMX,NORMY,THETA,R (single-probe records)")
+    ] = "",
+    egt: Annotated[Path | None, typer.Option("--egt", help="Cluster file (INFO GENTRAIN, CLUSTER_SEP).")] = None,
     force: Annotated[bool, typer.Option("--force", help="Replace existing outputs.")] = False,
     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,
@@ -417,7 +433,12 @@ def gtc_to_vcf_cmd(
         out=out, bpm=bpm, fasta=fasta, gtcs=gtcs, sheet=sheet, csv=csv, bgzip=not no_bgzip, genome_cache=genome_cache,
         exclude_loci=exclude_loci, include_loci=include_loci, unsquash_duplicates=unsquash_duplicates,
         inf1_nocall_informative=inf1_nocall_informative, drop_ambiguous=drop_ambiguous, filter_gs=filter_gs,
-        contig_alias=contig_alias, ploidy_policy=ploidy_policy, threads=threads, merge=merge, force=force,
+        contig_alias=contig_alias, ploidy_policy=ploidy_policy, threads=threads, merge=merge,
+        merge_snv_indel=merge_snv_indel,
+        auxiliary_loci=auxiliary_loci,
+        force=force,
+        info_fields=[x.strip().upper() for x in info_fields.split(",") if x.strip()],
+        extra_format=[x.strip().upper() for x in extra_format.split(",") if x.strip()], egt=egt,
         argv=sys.argv[1:],
     )  # fmt: skip
     run_guarded(rep, lambda: run_gtc_to_vcf(opts, rep))
@@ -485,6 +506,7 @@ def export_plink_cmd(
     sheet: Annotated[Path | None, typer.Option("--sheet", help="Sample sheet (reported sex).")] = None,
     gtcs: Annotated[Path | None, typer.Option("--gtcs", help="GTC folder (estimated sex).")] = None,
     multiallelic: Annotated[str, typer.Option("--multiallelic", help="split|drop")] = "split",
+    fmt: Annotated[str, typer.Option("--format", help="bed (PLINK 1), pgen (PLINK 2) or both")] = "bed",
     prefix: Annotated[str, typer.Option("--prefix", help="Output file prefix.")] = "cohort",
     force: Annotated[bool, typer.Option("--force", help="Replace existing outputs.")] = False,
     log_json: Annotated[bool, typer.Option("--log-json", "--json-log")] = False,
@@ -495,8 +517,17 @@ def export_plink_cmd(
     from simurg.pipeline.export import PlinkOptions, run_export_plink
 
     rep = _plain_reporter("export plink", log_json, debug, quiet)
-    opts = PlinkOptions(out=out, vcfs=vcfs, sheet=sheet, gtcs=gtcs, multiallelic=multiallelic, prefix=prefix,
-                        force=force, argv=sys.argv[1:])  # fmt: skip
+    opts = PlinkOptions(
+        out=out,
+        vcfs=vcfs,
+        sheet=sheet,
+        gtcs=gtcs,
+        multiallelic=multiallelic,
+        format=fmt,
+        prefix=prefix,
+        force=force,
+        argv=sys.argv[1:],
+    )
     run_guarded(rep, lambda: run_export_plink(opts, rep))