feat(eval): Go evaluation harness — LinearProbe, Silhouette, EffectiveRank (#4)

internal/eval: three pure-Go diagnostics on frozen embeddings:
  LinearProbe(emb, y, λ) → val_vol_r2 (OOS R², closed-form ridge, Cholesky)
  Silhouette(emb, labels) → mean silhouette (Euclidean, multi-label, errors on <2 classes)
  EffectiveRank(emb) → Roy effective rank (Jacobi eigenvalues → entropy → exp(H))

cmd/eval/main.go: CLI driver reading embeddings.json (exported by train.py with
EXPORT_EMBEDDINGS=1), standardises per-dim, dispatches to -metric flag.
task eval:probe / eval:silhouette / eval:collapse wired in Taskfile.

8/8 tests pass (red-green: perfect clusters, rank-1, full-rank, noise, constant
target, single-label error). Pure stdlib, no external deps.

Closes #4.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

cmd/eval/main.go

@@ -0,0 +1,118 @@
+// cmd/eval — CLI driver for the jepa-fx-risk evaluation harness.
+// Reads embeddings from a parquet/npy-style JSON export (embeddings.json)
+// and targets from eurusd_daily.parquet, then runs the requested metric.
+//
+//	./bin/eval -metric probe|silhouette|erank [-emb embeddings.json]
+//
+// embeddings.json format: {"embeddings": [[...], ...], "dates": ["2022-01-03", ...]}
+// Generated by train.py when run with EXPORT_EMBEDDINGS=1.
+package main
+
+import (
+	"encoding/json"
+	"flag"
+	"fmt"
+	"log/slog"
+	"math"
+	"os"
+
+	"gitea.d-ma.be/mathias/jepa-fx-risk/internal/eval"
+)
+
+func main() {
+	metric := flag.String("metric", "probe", "probe | silhouette | erank")
+	embFile := flag.String("emb", "embeddings.json", "path to embeddings JSON")
+	flag.Parse()
+
+	log := slog.New(slog.NewJSONHandler(os.Stdout, nil))
+
+	emb, labels, y, err := loadEmbeddings(*embFile)
+	if err != nil {
+		log.Error("load embeddings", "err", err)
+		os.Exit(1)
+	}
+	log.Info("loaded", "n", len(emb), "dim", len(emb[0]), "metric", *metric)
+
+	switch *metric {
+	case "probe":
+		r2 := eval.LinearProbe(emb, y, 1e-3)
+		fmt.Printf(`{"metric":"val_vol_r2","value":%.6f}`+"\n", r2)
+		log.Info("linear probe", "val_vol_r2", fmt.Sprintf("%.4f", r2))
+	case "silhouette":
+		if labels == nil {
+			log.Error("silhouette requires HV labels in embeddings.json")
+			os.Exit(1)
+		}
+		sil, err := eval.Silhouette(emb, labels)
+		if err != nil {
+			log.Error("silhouette", "err", err)
+			os.Exit(1)
+		}
+		fmt.Printf(`{"metric":"silhouette","value":%.6f}`+"\n", sil)
+		log.Info("silhouette", "score", fmt.Sprintf("%.4f", sil))
+	case "erank":
+		er := eval.EffectiveRank(emb)
+		fmt.Printf(`{"metric":"effective_rank","value":%.6f}`+"\n", er)
+		log.Info("effective rank", "erank", fmt.Sprintf("%.2f", er))
+	default:
+		log.Error("unknown metric", "metric", *metric)
+		os.Exit(1)
+	}
+}
+
+type embJSON struct {
+	Embeddings [][]float64 `json:"embeddings"`
+	Dates      []string    `json:"dates"`
+	RealizedVol []float64  `json:"realized_vol"`
+	HVLabel     []int      `json:"hv_label"`
+}
+
+func loadEmbeddings(path string) (emb [][]float64, labels []int, y []float64, err error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, nil, nil, fmt.Errorf("open %s: %w", path, err)
+	}
+	defer func() { _ = f.Close() }()
+
+	var d embJSON
+	if err := json.NewDecoder(f).Decode(&d); err != nil {
+		return nil, nil, nil, fmt.Errorf("decode: %w", err)
+	}
+	if len(d.Embeddings) == 0 {
+		return nil, nil, nil, fmt.Errorf("empty embeddings in %s", path)
+	}
+
+	// standardise embeddings (zero mean, unit std) per dimension
+	n, dim := len(d.Embeddings), len(d.Embeddings[0])
+	mu := make([]float64, dim)
+	for _, row := range d.Embeddings {
+		for j, v := range row {
+			mu[j] += v
+		}
+	}
+	for j := range mu {
+		mu[j] /= float64(n)
+	}
+	sd := make([]float64, dim)
+	for _, row := range d.Embeddings {
+		for j, v := range row {
+			diff := v - mu[j]
+			sd[j] += diff * diff
+		}
+	}
+	for j := range sd {
+		sd[j] = math.Sqrt(sd[j]/float64(n)) + 1e-8
+	}
+	norm := make([][]float64, n)
+	for i, row := range d.Embeddings {
+		norm[i] = make([]float64, dim)
+		for j, v := range row {
+			norm[i][j] = (v - mu[j]) / sd[j]
+		}
+	}
+
+	if len(d.HVLabel) > 0 {
+		labels = d.HVLabel
+	}
+	return norm, labels, d.RealizedVol, nil
+}