P5a: QC — control metrics, thresholds, status, contamination, relatedness, locus summary

- qc/controls: canonical control names (QC-002), bkg/offset (QC-003), 13 genotyping metrics (QC-004/005),
  missing/zero-divisor handling (QC-007/008); controls_raw.tsv / controls_qc.tsv (QC-009/011) incl. compat CSVs
- qc/thresholds + profiles: YAML schema, validation codes, precedence, shipped profiles, auto (QC-020..025)
- qc/status: functional PASS/FAIL/NA, control CLEAR/FLAGGED, flags (QC-030..033)
- qc/contamination: BAF regression; bit-compatible with gtc2vcf BAFregress (36/36, K-017), exact mode too
- qc/relatedness: KING-robust, duplicates, Mendelian errors, pedigree from sheet (IN-018)
- qc/locus_summary: OUT-072, bit-identical to BeadArrayFiles except ChiTest (K-018)
- qc/suggest: suggest-thresholds (QC-026)
- pipeline/qc: disk-backed cohort store; CLI qc controls|samples|contamination|relatedness|loci|suggest-thresholds
- genotype: control tables (OUT-070), het_rate, QC columns, cohort QC
- tests: unit + oracle (BAFregress plugin, BeadArrayFiles locus summary)

src/simurg/core/errors.py

@@ -89,6 +89,30 @@ CATALOGUE: dict[str, MessageDef] = dict(
         _m("E_EGT_LOAD", "error", "Cluster (EGT) file cannot be loaded", "IN-044"),
         _m("W_EGT_NAME", "warning", "Cluster file name is not portable", "IN-045"),
         _m("W_MANIFEST_NO_REFSTRAND", "warning", "Manifest lacks RefStrand annotation", "IN-040"),
+        # --- QC (QC-001 .. QC-064) -----------------------------------------------------------------
+        _m("W_CTRL_MISSING", "warning", "Controls needed by a metric are absent; metric not evaluable", "QC-007"),
+        _m("W_CTRL_ZERO_DIVISOR", "warning", "Control metric has a zero denominator (NaN)", "QC-008"),
+        _m("W_CTRL_DEFS_DIFFER", "warning", "BPM and CSV control definitions differ; the BPM wins", "QC-001"),
+        _m("E_QC_METHYLATION", "error", "Methylation control metrics are not available yet (v2)", "QC-006"),
+        _m("E_QC_NO_DATASETS", "error", "No QC dataset folder found", "QC-041"),
+        _m("E_QC_DATASET_INCOMPLETE", "error", "Dataset folder lacks a required file", "QC-041"),
+        _m("E_QC_LABEL_COUNT", "error", "Number of labels does not match number of datasets", "QC-042"),
+        _m("E_QC_LABEL_DUPLICATE", "error", "Dataset labels are not unique", "QC-042"),
+        _m("W_QC_LABEL_SANITIZED", "warning", "Dataset label was sanitized", "QC-042"),
+        _m("E_QC_MIXED_TYPES", "error", "Genotyping and methylation datasets cannot be mixed", "QC-043"),
+        _m("W_QC_UNMATCHED_SAMPLES", "warning", "Sample IDs present in one QC file but not the other", "QC-040"),
+        _m("E_QC_FORMAT", "error", "Invalid --output-format value", "QC-063"),
+        _m("E_QC_CONFIG_MISSING", "error", "QC config file does not exist", "QC-021"),
+        _m("E_QC_CONFIG_EXT", "error", "QC config file must be .yaml or .yml", "QC-021"),
+        _m("E_QC_CONFIG_PARSE", "error", "QC config file is not valid YAML", "QC-021"),
+        _m("E_QC_CONFIG_STRUCTURE", "error", "QC config lacks the qc/report (QC/Report) wrapper", "QC-021"),
+        _m("E_QC_THRESHOLD_KEY", "error", "Unknown QC threshold key", "QC-021"),
+        _m("E_QC_THRESHOLD_VALUE", "error", "QC threshold value is not numeric or null", "QC-021"),
+        _m("E_QC_THRESHOLD_RANGE", "error", "QC threshold value out of range", "QC-021"),
+        _m("E_QC_PROFILE", "error", "Unknown QC profile", "QC-024"),
+        _m("W_QC_PEDIGREE", "warning", "Parent1/Parent2/Replicate value does not name a sample in the set", "IN-018"),
+        _m("W_QC_NO_BAF", "warning", "GTC has no B-allele frequencies; contamination not estimated", "QC-064"),
+        _m("W_QC_TOO_FEW", "warning", "Too few samples or sites for a cohort QC statistic", "QC-026"),
     ]
 )