validator: port FillValidator + EmailValidator from Rust validator crate

Per architecture_comparison.md universal-win for Go side: ports the Rust crates/validator/src/staffing/ to internal/validator/. Production safety net Go was missing — FillValidator catches phantom worker IDs + status/blacklist/geo/role mismatches; EmailValidator catches SSN-shape PII + salary disclosure + wrong-target name in email/SMS drafts. Files: - types.go: Artifact (FillProposal | EmailDraft), Validator interface, WorkerLookup interface, ValidationError + Finding + Severity - lookup.go: InMemoryWorkerLookup with case-insensitive ID lookup - fill.go: FillValidator — schema → completeness → cross-roster (phantom ID / status / blacklist / geo / role) - email.go: EmailValidator — schema → length → PII (SSN + salary) → worker-name consistency - fill_test.go + email_test.go: 24 tests covering happy path + every error variant + the load-bearing edge cases (phone-pattern not flagged as SSN, flanking-digit guard rejects extended numeric runs) Validator names match Rust (staffing.fill / staffing.email) so cross-runtime audit logs share the same identifier. PII scanners (containsSSNPattern, containsSalaryDisclosure) ported byte-for-byte so a draft flagged by one runtime is flagged by the other. Caveat: the Rust validator crate also has parquet_lookup.rs (loads workers_500k.parquet at startup) and playbook.rs (additional checks). Those weren't ported in this wave — only the two load-bearing validators that were named in the comparison doc. Closes one of the two universal-win items for Go side. The other (materializer port) remains deferred — it's a bigger surface change and depends on transforms.ts source-class adapters. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-01 04:49:55 -05:00
parent b3ad14832d
commit b03521a506
6 changed files with 1190 additions and 0 deletions
@@ -0,0 +1,226 @@
+package validator
+
+import (
+	"errors"
+	"testing"
+)
+
+// Helpers — mirror the Rust test helpers.
+
+func mkLookup(records ...WorkerRecord) WorkerLookup {
+	return NewInMemoryWorkerLookup(records)
+}
+
+func mkWorker(id, name, status, city, state, role string) WorkerRecord {
+	return WorkerRecord{
+		CandidateID: id,
+		Name:        name,
+		Status:      status,
+		City:        strPtr(city),
+		State:       strPtr(state),
+		Role:        strPtr(role),
+	}
+}
+
+func asValidationError(err error) (*ValidationError, bool) {
+	var ve *ValidationError
+	if errors.As(err, &ve) {
+		return ve, true
+	}
+	return nil, false
+}
+
+// ── Schema-level errors ──
+
+func TestFill_WrongArtifactType_FailsSchema(t *testing.T) {
+	v := NewFillValidator(mkLookup())
+	_, err := v.Validate(Artifact{EmailDraft: map[string]any{}})
+	ve, ok := asValidationError(err)
+	if !ok {
+		t.Fatalf("expected ValidationError, got %v", err)
+	}
+	if ve.Kind != ErrSchema || ve.Field != "artifact" {
+		t.Errorf("expected schema/artifact error, got %+v", ve)
+	}
+}
+
+func TestFill_MissingFillsArray_FailsSchema(t *testing.T) {
+	v := NewFillValidator(mkLookup())
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrSchema || ve.Field != "fills" {
+		t.Errorf("expected schema/fills error, got %+v", ve)
+	}
+}
+
+func TestFill_MissingCandidateID_FailsSchema(t *testing.T) {
+	v := NewFillValidator(mkLookup())
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"fills": []any{
+			map[string]any{"name": "Alice"},
+		},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrSchema || ve.Field != "fills[0].candidate_id" {
+		t.Errorf("expected schema/fills[0].candidate_id error, got %+v", ve)
+	}
+}
+
+// ── Completeness ──
+
+func TestFill_TargetCountMismatch_FailsCompleteness(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "active", "Toledo", "OH", "Welder")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{"target_count": float64(2)},
+		"fills":    []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrCompleteness {
+		t.Errorf("expected completeness error, got %+v", ve)
+	}
+}
+
+// ── Cross-roster checks ──
+
+func TestFill_PhantomID_FailsConsistency(t *testing.T) {
+	// Lookup is empty → any candidate_id is "phantom" — the
+	// load-bearing check for the 0→85% pattern.
+	v := NewFillValidator(mkLookup())
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"fills": []any{map[string]any{"candidate_id": "phantom-id", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrConsistency {
+		t.Errorf("expected consistency error on phantom ID, got %+v", ve)
+	}
+}
+
+func TestFill_DuplicateID_FailsConsistency(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "active", "Toledo", "OH", "Welder")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"fills": []any{
+			map[string]any{"candidate_id": "w1", "name": "Alice"},
+			map[string]any{"candidate_id": "w1", "name": "Alice"},
+		},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrConsistency {
+		t.Errorf("expected consistency error on duplicate ID, got %+v", ve)
+	}
+}
+
+func TestFill_InactiveStatus_FailsConsistency(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "inactive", "Toledo", "OH", "Welder")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"fills": []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrConsistency {
+		t.Errorf("expected consistency error on inactive status, got %+v", ve)
+	}
+}
+
+func TestFill_Blacklist_FailsPolicy(t *testing.T) {
+	w := mkWorker("w1", "Alice", "active", "Toledo", "OH", "Welder")
+	w.BlacklistedClients = []string{"CLI-99"}
+	v := NewFillValidator(mkLookup(w))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{"client_id": "cli-99"}, // case-insensitive
+		"fills":    []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrPolicy {
+		t.Errorf("expected policy error on blacklist, got %+v", ve)
+	}
+}
+
+func TestFill_GeoMismatch_FailsConsistency(t *testing.T) {
+	// Worker in Detroit, contract says Toledo.
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "active", "Detroit", "MI", "Welder")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{"city": "Toledo", "state": "OH"},
+		"fills":    []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrConsistency {
+		t.Errorf("expected consistency error on geo mismatch, got %+v", ve)
+	}
+}
+
+func TestFill_RoleMismatch_FailsConsistency(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "active", "Toledo", "OH", "Forklift Operator")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{"role": "Welder"},
+		"fills":    []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	ve, _ := asValidationError(err)
+	if ve == nil || ve.Kind != ErrConsistency {
+		t.Errorf("expected consistency error on role mismatch, got %+v", ve)
+	}
+}
+
+// ── Happy path ──
+
+func TestFill_WellFormed_Passes(t *testing.T) {
+	v := NewFillValidator(mkLookup(
+		mkWorker("w1", "Alice", "active", "Toledo", "OH", "Welder"),
+		mkWorker("w2", "Bob", "active", "Toledo", "OH", "Welder"),
+	))
+	report, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{
+			"target_count": float64(2),
+			"city":         "Toledo",
+			"state":        "OH",
+			"role":         "Welder",
+		},
+		"fills": []any{
+			map[string]any{"candidate_id": "w1", "name": "Alice"},
+			map[string]any{"candidate_id": "w2", "name": "Bob"},
+		},
+	}})
+	if err != nil {
+		t.Fatalf("expected pass, got %v", err)
+	}
+	if len(report.Findings) != 0 {
+		t.Errorf("expected zero findings, got %v", report.Findings)
+	}
+}
+
+// ── Name mismatch is a Finding (warning), not an error ──
+
+func TestFill_NameMismatch_EmitsWarning(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice Smith", "active", "Toledo", "OH", "Welder")))
+	report, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"fills": []any{
+			map[string]any{"candidate_id": "w1", "name": "Alyssa Smith"}, // typo / outdated
+		},
+	}})
+	if err != nil {
+		t.Fatalf("name mismatch should NOT error, got %v", err)
+	}
+	if len(report.Findings) != 1 || report.Findings[0].Severity != SeverityWarning {
+		t.Errorf("expected 1 warning finding, got %v", report.Findings)
+	}
+}
+
+// ── Case-insensitive matches ──
+
+func TestFill_CaseInsensitiveMatch_Passes(t *testing.T) {
+	v := NewFillValidator(mkLookup(mkWorker("w1", "Alice", "ACTIVE", "TOLEDO", "oh", "Welder")))
+	_, err := v.Validate(Artifact{FillProposal: map[string]any{
+		"_context": map[string]any{"city": "Toledo", "state": "OH"},
+		"fills":    []any{map[string]any{"candidate_id": "w1", "name": "Alice"}},
+	}})
+	if err != nil {
+		t.Errorf("case-insensitive comparisons should pass, got %v", err)
+	}
+}
+
+// ── Validator name is stable ──
+
+func TestFill_NameMatchesRust(t *testing.T) {
+	v := NewFillValidator(mkLookup())
+	if v.Name() != "staffing.fill" {
+		t.Errorf("name should match Rust 'staffing.fill', got %q", v.Name())
+	}
+}