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>
This commit is contained in:
root
@@ -0,0 +1,274 @@
|
||||
package validator
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// FillValidator is the Go port of Rust's FillValidator. Per
|
||||
// `crates/validator/src/staffing/fill.rs`:
|
||||
//
|
||||
// - Schema compliance (propose_done shape: {fills: [{candidate_id, name}]})
|
||||
// - Completeness (endorsed count == target_count)
|
||||
// - Worker existence (every candidate_id present in workers roster)
|
||||
// - Status check (worker.status == "active")
|
||||
// - Client blacklist (worker NOT in client.blacklisted_clients)
|
||||
// - Geo/role match (worker city/state/role matches contract)
|
||||
//
|
||||
// Contract metadata travels alongside the JSON payload under a
|
||||
// `_context` key:
|
||||
//
|
||||
// {"_context": {"target_count": 2, "city": "Toledo", "state": "OH",
|
||||
// "role": "Welder", "client_id": "CLI-00099"}, "fills": [...]}
|
||||
//
|
||||
// The duplicate-ID guard inside one fill catches the LLM mistake
|
||||
// of repeating the same candidate twice to satisfy a higher
|
||||
// target_count.
|
||||
type FillValidator struct {
|
||||
workers WorkerLookup
|
||||
}
|
||||
|
||||
// NewFillValidator constructs a FillValidator with the given lookup.
|
||||
// Lookup must be non-nil; pass NewInMemoryWorkerLookup(nil) for
|
||||
// tests that don't exercise existence checks.
|
||||
func NewFillValidator(workers WorkerLookup) *FillValidator {
|
||||
return &FillValidator{workers: workers}
|
||||
}
|
||||
|
||||
// Name satisfies Validator. Stable string used for audit
|
||||
// trail / receipts. Matches Rust output "staffing.fill" so
|
||||
// cross-runtime audit logs share the same name.
|
||||
func (v *FillValidator) Name() string { return "staffing.fill" }
|
||||
|
||||
// fillContext is the optional contract metadata extracted from
|
||||
// _context. Each field is independently nil-able (Rust's Option<T>
|
||||
// pattern) — validators only enforce a check when both contract
|
||||
// and roster sides have a value.
|
||||
type fillContext struct {
|
||||
TargetCount *int
|
||||
City *string
|
||||
State *string
|
||||
Role *string
|
||||
ClientID *string
|
||||
}
|
||||
|
||||
func extractContext(value map[string]any) fillContext {
|
||||
ctx, ok := value["_context"].(map[string]any)
|
||||
if !ok {
|
||||
return fillContext{}
|
||||
}
|
||||
out := fillContext{}
|
||||
if v, ok := ctx["target_count"]; ok {
|
||||
if n, ok := toInt(v); ok {
|
||||
out.TargetCount = &n
|
||||
}
|
||||
}
|
||||
if s, ok := ctx["city"].(string); ok {
|
||||
out.City = &s
|
||||
}
|
||||
if s, ok := ctx["state"].(string); ok {
|
||||
out.State = &s
|
||||
}
|
||||
if s, ok := ctx["role"].(string); ok {
|
||||
out.Role = &s
|
||||
}
|
||||
if s, ok := ctx["client_id"].(string); ok {
|
||||
out.ClientID = &s
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// toInt accepts JSON numbers (float64) and integers, returning
|
||||
// the int form when the value is a whole number ≥ 0.
|
||||
func toInt(v any) (int, bool) {
|
||||
switch n := v.(type) {
|
||||
case int:
|
||||
return n, true
|
||||
case int64:
|
||||
return int(n), true
|
||||
case float64:
|
||||
// JSON unmarshals all numbers as float64; whole-number check
|
||||
// is mandatory because target_count=2.5 makes no sense.
|
||||
i := int(n)
|
||||
if float64(i) == n {
|
||||
return i, true
|
||||
}
|
||||
return 0, false
|
||||
}
|
||||
return 0, false
|
||||
}
|
||||
|
||||
// eqCI is the case-insensitive equality used everywhere validators
|
||||
// compare strings (status, role, city, etc.). Trim+lowercase mirrors
|
||||
// Rust's `.trim().eq_ignore_ascii_case(other.trim())`.
|
||||
func eqCI(a, b string) bool {
|
||||
return strings.EqualFold(strings.TrimSpace(a), strings.TrimSpace(b))
|
||||
}
|
||||
|
||||
// Validate implements the Validator interface. Mirrors the Rust
|
||||
// validation order exactly: schema → completeness → cross-roster
|
||||
// per-fill checks.
|
||||
func (v *FillValidator) Validate(artifact Artifact) (Report, error) {
|
||||
started := time.Now()
|
||||
value := artifact.FillProposal
|
||||
if value == nil {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrSchema,
|
||||
Field: "artifact",
|
||||
Reason: fmt.Sprintf("FillValidator expects FillProposal, got %s", artifact.Kind()),
|
||||
}
|
||||
}
|
||||
|
||||
// ── Schema check ──
|
||||
fillsRaw, ok := value["fills"].([]any)
|
||||
if !ok {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrSchema,
|
||||
Field: "fills",
|
||||
Reason: "expected top-level `fills` array",
|
||||
}
|
||||
}
|
||||
for i, fillRaw := range fillsRaw {
|
||||
fill, ok := fillRaw.(map[string]any)
|
||||
if !ok {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrSchema,
|
||||
Field: fmt.Sprintf("fills[%d]", i),
|
||||
Reason: "expected object",
|
||||
}
|
||||
}
|
||||
if _, ok := fill["candidate_id"]; !ok {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrSchema,
|
||||
Field: fmt.Sprintf("fills[%d].candidate_id", i),
|
||||
Reason: "missing",
|
||||
}
|
||||
}
|
||||
if _, ok := fill["name"]; !ok {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrSchema,
|
||||
Field: fmt.Sprintf("fills[%d].name", i),
|
||||
Reason: "missing",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ctx := extractContext(value)
|
||||
|
||||
// ── Completeness ──
|
||||
if ctx.TargetCount != nil && len(fillsRaw) != *ctx.TargetCount {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrCompleteness,
|
||||
Reason: fmt.Sprintf("endorsed count %d != target_count %d",
|
||||
len(fillsRaw), *ctx.TargetCount),
|
||||
}
|
||||
}
|
||||
|
||||
// ── Cross-roster checks ──
|
||||
var findings []Finding
|
||||
seenIDs := make(map[string]bool, len(fillsRaw))
|
||||
for i, fillRaw := range fillsRaw {
|
||||
fill := fillRaw.(map[string]any) // already type-checked in schema pass
|
||||
candidateID, _ := fill["candidate_id"].(string)
|
||||
proposedName, _ := fill["name"].(string)
|
||||
|
||||
// Duplicate-ID guard inside one fill.
|
||||
if seenIDs[candidateID] {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"duplicate candidate_id %q appears multiple times in fills",
|
||||
candidateID,
|
||||
),
|
||||
}
|
||||
}
|
||||
seenIDs[candidateID] = true
|
||||
|
||||
// Worker existence — load-bearing check for the 0→85% pattern.
|
||||
worker, ok := v.workers.Find(candidateID)
|
||||
if !ok {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d].candidate_id %q does not exist in worker roster",
|
||||
i, candidateID,
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
// Status — only "active" workers can be endorsed.
|
||||
if !eqCI(worker.Status, "active") {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d] worker %q has status %q, expected \"active\"",
|
||||
i, candidateID, worker.Status,
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
// Client blacklist.
|
||||
if ctx.ClientID != nil {
|
||||
for _, b := range worker.BlacklistedClients {
|
||||
if eqCI(b, *ctx.ClientID) {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrPolicy,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d] worker %q blacklisted for client %q",
|
||||
i, candidateID, *ctx.ClientID,
|
||||
),
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Geo / role match — only when BOTH sides have a value.
|
||||
if ctx.City != nil && worker.City != nil && !eqCI(*ctx.City, *worker.City) {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d] worker %q city %q doesn't match contract city %q",
|
||||
i, candidateID, *worker.City, *ctx.City,
|
||||
),
|
||||
}
|
||||
}
|
||||
if ctx.State != nil && worker.State != nil && !eqCI(*ctx.State, *worker.State) {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d] worker %q state %q doesn't match contract state %q",
|
||||
i, candidateID, *worker.State, *ctx.State,
|
||||
),
|
||||
}
|
||||
}
|
||||
if ctx.Role != nil && worker.Role != nil && !eqCI(*ctx.Role, *worker.Role) {
|
||||
return Report{}, &ValidationError{
|
||||
Kind: ErrConsistency,
|
||||
Reason: fmt.Sprintf(
|
||||
"fills[%d] worker %q role %q doesn't match contract role %q",
|
||||
i, candidateID, *worker.Role, *ctx.Role,
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
// Name-mismatch is a warning, not an error — recruiters
|
||||
// sometimes send updated names through the proposal layer
|
||||
// before the roster catches up.
|
||||
if proposedName != "" && !eqCI(proposedName, worker.Name) {
|
||||
findings = append(findings, Finding{
|
||||
Field: fmt.Sprintf("fills[%d].name", i),
|
||||
Severity: SeverityWarning,
|
||||
Message: fmt.Sprintf(
|
||||
"proposed name %q differs from roster name %q for %q",
|
||||
proposedName, worker.Name, candidateID,
|
||||
),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
return Report{
|
||||
Findings: findings,
|
||||
ElapsedMs: elapsed(started),
|
||||
}, nil
|
||||
}
|
||||
Reference in New Issue
Block a user