Filter first-party domains from tracker mapping

Tracker scripts loaded through a first-party reverse proxy (e.g.
t.probo.com proxying PostHog) share the scanned site's eTLD+1 and
were incorrectly matched against the site owner's own
CommonThirdParty entry in matchByDomain. This caused trackers like
ph_phc_* to be attributed to the site owner instead of PostHog.

Load the CookieBanner origin in Process and pass it to both
matchByDomain and identifyWithAgent. Both now filter out initiator
domains whose eTLD+1 matches the site before querying the catalog
or feeding domains to the LLM agent. The prompt is also updated to
warn about proxy domains.

Signed-off-by: Émile Ré <emile@probo.com>

pkg/uri/uri.go

@@ -102,3 +102,26 @@ func ExtractDomain(rawURL string) string {
 
 	return domain
 }
+
+// FilterFirstPartyDomains removes domains that match the eTLD+1 of
+// siteOrigin. Tracker scripts loaded through a first-party proxy (e.g.
+// t.probo.com proxying PostHog on a probo.com site) share the site's
+// eTLD+1 and carry no signal about the actual third party. siteOrigin
+// is a full URL such as "https://app.probo.com". The input domains are
+// expected to be eTLD+1 strings (as produced by ExtractDomain).
+func FilterFirstPartyDomains(domains []string, siteOrigin string) []string {
+	siteDomain := ExtractDomain(siteOrigin)
+	if siteDomain == "" {
+		return domains
+	}
+
+	filtered := make([]string, 0, len(domains))
+
+	for _, d := range domains {
+		if d != siteDomain {
+			filtered = append(filtered, d)
+		}
+	}
+
+	return filtered
+}

pkg/uri/uri_test.go

@@ -291,3 +291,76 @@ func TestExtractDomain(t *testing.T) {
 		)
 	}
 }
+
+func TestFilterFirstPartyDomains(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name       string
+		domains    []string
+		siteOrigin string
+		want       []string
+	}{
+		{
+			name:       "removes site domain from proxy",
+			domains:    []string{"probo.com", "posthog.com"},
+			siteOrigin: "https://app.probo.com",
+			want:       []string{"posthog.com"},
+		},
+		{
+			name:       "keeps all third-party domains",
+			domains:    []string{"stripe.com", "google.com"},
+			siteOrigin: "https://app.probo.com",
+			want:       []string{"stripe.com", "google.com"},
+		},
+		{
+			name:       "removes only matching domain",
+			domains:    []string{"example.com", "googletagmanager.com", "example.com"},
+			siteOrigin: "https://www.example.com",
+			want:       []string{"googletagmanager.com"},
+		},
+		{
+			name:       "all domains are first party",
+			domains:    []string{"probo.com"},
+			siteOrigin: "https://t.probo.com",
+			want:       []string{},
+		},
+		{
+			name:       "empty domains list",
+			domains:    []string{},
+			siteOrigin: "https://probo.com",
+			want:       []string{},
+		},
+		{
+			name:       "nil domains list",
+			domains:    nil,
+			siteOrigin: "https://probo.com",
+			want:       []string{},
+		},
+		{
+			name:       "invalid site origin preserves all",
+			domains:    []string{"probo.com", "stripe.com"},
+			siteOrigin: "not-a-url",
+			want:       []string{"probo.com", "stripe.com"},
+		},
+		{
+			name:       "empty site origin preserves all",
+			domains:    []string{"probo.com", "stripe.com"},
+			siteOrigin: "",
+			want:       []string{"probo.com", "stripe.com"},
+		},
+		{
+			name:       "co.uk site origin",
+			domains:    []string{"example.co.uk", "analytics.google.com"},
+			siteOrigin: "https://shop.example.co.uk",
+			want:       []string{"analytics.google.com"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+			assert.Equal(t, tt.want, FilterFirstPartyDomains(tt.domains, tt.siteOrigin))
+		})
+	}
+}