test(09-03): add failing test for cross-source Dedup

pkg/recon/dedup_test.go

@@ -0,0 +1,55 @@
+package recon
+
+import (
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/salvacybersec/keyhunter/pkg/engine"
+)
+
+func TestDedupEmpty(t *testing.T) {
+	require.Nil(t, Dedup(nil))
+	require.Nil(t, Dedup([]engine.Finding{}))
+}
+
+func TestDedupNoDuplicates(t *testing.T) {
+	in := []engine.Finding{
+		{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/a"},
+		{ProviderName: "anthropic", KeyMasked: "sk-ant-1...2def", Source: "https://example.com/b"},
+		{ProviderName: "cohere", KeyMasked: "co-abcde...wxyz", Source: "https://example.com/c"},
+	}
+	out := Dedup(in)
+	require.Len(t, out, 3)
+	require.Equal(t, in, out, "order must be preserved")
+}
+
+func TestDedupAllDuplicates(t *testing.T) {
+	f := engine.Finding{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/a"}
+	out := Dedup([]engine.Finding{f, f, f})
+	require.Len(t, out, 1)
+	require.Equal(t, f, out[0])
+}
+
+func TestDedupPreservesFirstSeen(t *testing.T) {
+	first := time.Date(2026, 1, 1, 0, 0, 0, 0, time.UTC)
+	second := time.Date(2026, 2, 2, 0, 0, 0, 0, time.UTC)
+	in := []engine.Finding{
+		{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/a", DetectedAt: first, Confidence: "high"},
+		{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/a", DetectedAt: second, Confidence: "low"},
+	}
+	out := Dedup(in)
+	require.Len(t, out, 1)
+	require.Equal(t, first, out[0].DetectedAt, "first-seen timestamp must win")
+	require.Equal(t, "high", out[0].Confidence, "first-seen metadata must win")
+}
+
+func TestDedupDifferentSource(t *testing.T) {
+	in := []engine.Finding{
+		{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/a"},
+		{ProviderName: "openai", KeyMasked: "sk-abc12...9xyz", Source: "https://example.com/b"},
+	}
+	out := Dedup(in)
+	require.Len(t, out, 2, "same provider+masked but different Source URLs must both be kept")
+}