P2 (WIP): raw X/Y assembly, canonical Parquet model, simurg ingest

- signal/raw_xy.py: vectorised Infinium I/II raw X/Y and control assembly
  (plan §7.1) with a per-chip address-map cache; IN-027 coverage gate
- core/schemas.py: Arrow schemas (loci, sample_intensity, controls),
  deterministic atomic Parquet writing
- pipeline/ingest.py + CLI: discovery, sheet, IN-010 naming, overwrite
  check before any work, spawn-based workers, per-sample isolation,
  --resume by input hashes, run manifest, exit codes 0/3/4
- matches gtc2vcf raw X/Y and controls exactly on 18 GSA samples;
  outputs byte-identical across thread counts and layouts

src/simurg/cli/main.py

@@ -1,6 +1,6 @@
 """``simurg`` command-line interface (spec §2, plan §14).
 
-Phase P1 provides ``simurg version`` and ``simurg inspect``. Later phases add the other commands of CLI-001.
+Available: ``version``, ``inspect`` (P1), ``ingest`` (P2). Later phases add the other commands of CLI-001.
 """
 
 from __future__ import annotations
@@ -203,5 +203,54 @@ def inspect_cmd(
     run_guarded(rep, body)
 
 
+# --------------------------------------------------------------------------------------------------------
+@app.command("ingest")
+def ingest_cmd(
+    bpm: Annotated[Path, typer.Option("--bpm", help="BPM manifest (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,
+    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,
+    resume: Annotated[bool, typer.Option("--resume", help="Keep outputs whose inputs are unchanged.")] = 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,
+    log_level: Annotated[str, typer.Option("--log-level", help="debug|info|warning|error")] = "info",
+    quiet: Annotated[bool, typer.Option("--quiet", "--no-progress", help="Suppress info messages.")] = False,
+) -> None:
+    """IDAT pairs + BPM → canonical per-sample raw intensities (Parquet). Phase P2."""
+    from simurg.pipeline.ingest import IngestOptions, run_ingest
+
+    if layout not in ("nested", "flat"):
+        raise typer.BadParameter("--layout must be nested or flat")
+    if on_duplicate_idat not in ("error", "first", "newest"):
+        raise typer.BadParameter("--on-duplicate-idat must be error, first or newest")
+    rep = Reporter(
+        command="ingest",
+        level="debug" if debug else log_level,
+        json_stderr=log_json,
+        debug=debug,
+        quiet=quiet,
+        log_file=out / "logs" / "ingest.log",
+    )
+    opts = IngestOptions(
+        out=out,
+        bpm=bpm,
+        idats=idats,
+        sheet=sheet,
+        csv=csv,
+        threads=threads,
+        force=force,
+        resume=resume,
+        layout=layout,
+        on_duplicate_idat=on_duplicate_idat,
+        argv=sys.argv[1:],
+    )
+    run_guarded(rep, lambda: run_ingest(opts, rep))
+
+
 if __name__ == "__main__":  # pragma: no cover
     app()