eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Complete Phase 8 deterministic validators

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-12 00:26:27 +00:00
parent 28fe899aa1
commit aeb31f1c0d
13 changed files with 940 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

161
internal/framework/validators/deterministic.go Normal file
View File

@@ -0,0 +1,161 @@
package validators
import (
"context"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
)
type ConfidenceThresholdValidator struct{}
func (v ConfidenceThresholdValidator) Name() string { return "confidence_threshold" }
func (v ConfidenceThresholdValidator) Validate(_ context.Context, req Request) (Result, error) {
threshold := confidenceThresholdForModule(req.ModuleKey, req.Config)
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
if c.Confidence < threshold {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonLowConfidence, fmt.Sprintf("confidence %.4f below threshold %.4f", c.Confidence, threshold)))
continue
}
decisions = append(decisions, approval(c.ProposalIndex))
}
if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
return Result{}, err
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
type OriginalTextPresenceValidator struct{}
func (v OriginalTextPresenceValidator) Name() string { return "original_text_presence" }
func (v OriginalTextPresenceValidator) Validate(_ context.Context, req Request) (Result, error) {
byID := make(map[int]string)
if req.WorkingTranscript != nil {
for _, seg := range req.WorkingTranscript.Segments {
byID[seg.ID] = seg.Text
}
}
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
text, ok := byID[c.TargetSegmentID]
if !ok {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonMissingTargetSegment, "target segment was not found"))
continue
}
if !strings.Contains(text, c.OriginalText) {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonMissingOriginalText, "original_text was not found in current segment text"))
continue
}
decisions = append(decisions, approval(c.ProposalIndex))
}
if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
return Result{}, err
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
type NonEmptyCorrectionValidator struct{}
func (v NonEmptyCorrectionValidator) Name() string { return "non_empty_correction" }
func (v NonEmptyCorrectionValidator) Validate(_ context.Context, req Request) (Result, error) {
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
if strings.TrimSpace(c.CorrectedText) == "" {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonEmptyCorrectedText, "corrected_text must not be empty"))
continue
}
decisions = append(decisions, approval(c.ProposalIndex))
}
if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
return Result{}, err
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
type NoEffectValidator struct{}
func (v NoEffectValidator) Name() string { return "no_effect" }
func (v NoEffectValidator) Validate(_ context.Context, req Request) (Result, error) {
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
if c.OriginalText == c.CorrectedText {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonNoEffect, "original_text and corrected_text are identical"))
continue
}
decisions = append(decisions, approval(c.ProposalIndex))
}
if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
return Result{}, err
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
type ProtectedGlossaryTermValidator struct{}
func (v ProtectedGlossaryTermValidator) Name() string { return "protected_glossary_terms" }
func (v ProtectedGlossaryTermValidator) Validate(_ context.Context, req Request) (Result, error) {
if req.ModuleKey == "glossary" {
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
decisions = append(decisions, approval(c.ProposalIndex))
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
terms := glossaryTerms(req)
decisions := make([]Decision, 0, len(req.CandidateProposal))
for _, c := range req.CandidateProposal {
if altersProtectedTerm(c.CorrectionProposal, terms) {
decisions = append(decisions, rejection(c.ProposalIndex, ReasonProtectedGlossaryTerm, "proposal may alter protected glossary terminology"))
continue
}
decisions = append(decisions, approval(c.ProposalIndex))
}
if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
return Result{}, err
}
return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
}
func glossaryTerms(req Request) []string {
if req.Glossary == nil {
return nil
}
out := make([]string, 0)
for _, e := range req.Glossary.Entries {
if t := strings.TrimSpace(strings.ToLower(e.Name)); t != "" {
out = append(out, t)
}
for _, a := range e.Aliases {
if t := strings.TrimSpace(strings.ToLower(a)); t != "" {
out = append(out, t)
}
}
if t := strings.TrimSpace(strings.ToLower(e.Plural)); t != "" {
out = append(out, t)
}
}
return out
}
func altersProtectedTerm(p proposals.CorrectionProposal, terms []string) bool {
if len(terms) == 0 {
return false
}
orig := strings.ToLower(p.OriginalText)
corr := strings.ToLower(p.CorrectedText)
for _, t := range terms {
if strings.Contains(orig, t) && !strings.Contains(corr, t) {
return true
}
}
return false
}

105
internal/framework/validators/models.go Normal file
View File

@@ -0,0 +1,105 @@
package validators
import (
"context"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/audita/internal/core/config"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
)
const (
ReasonApproved = "approved"
ReasonLowConfidence = "low_confidence"
ReasonMissingOriginalText = "missing_original_text"
ReasonMissingTargetSegment = "missing_target_segment"
ReasonEmptyCorrectedText = "empty_corrected_text"
ReasonNoEffect = "no_effect"
ReasonProtectedGlossaryTerm = "protected_glossary_term"
)
// Request is the runtime input shared by deterministic validators.
type Request struct {
WorkingTranscript *schema.Transcript `json:"-"`
CandidateProposal []proposals.EnrichedCorrectionProposal `json:"candidate_proposals"`
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`
ReplacementPolicy proposals.ReplacementPolicy `json:"replacement_policy"`
Glossary *schema.Glossary `json:"-"`
Config *config.Config `json:"-"`
}
// Decision is one validator decision for one proposal index.
type Decision struct {
ProposalIndex int `json:"proposal_index"`
Approved bool `json:"approved"`
ReasonCode string `json:"reason_code"`
Message string `json:"message"`
}
// Result is one validator output containing exactly one decision per proposal index.
type Result struct {
ValidatorName string `json:"validator_name"`
Decisions []Decision `json:"decisions"`
}
// Validator is the deterministic runtime validator interface.
type Validator interface {
Name() string
Validate(ctx context.Context, req Request) (Result, error)
}
// EnforceDecisionCardinality verifies every candidate proposal index receives exactly one decision.
func EnforceDecisionCardinality(candidate []proposals.EnrichedCorrectionProposal, decisions []Decision) error {
expected := make(map[int]struct{}, len(candidate))
for _, c := range candidate {
expected[c.ProposalIndex] = struct{}{}
}
seen := make(map[int]int, len(decisions))
for _, d := range decisions {
if _, ok := expected[d.ProposalIndex]; !ok {
return fmt.Errorf("unknown decision proposal index %d", d.ProposalIndex)
}
seen[d.ProposalIndex]++
if seen[d.ProposalIndex] > 1 {
return fmt.Errorf("duplicate decision proposal index %d", d.ProposalIndex)
}
}
for idx := range expected {
if seen[idx] == 0 {
return fmt.Errorf("missing decision proposal index %d", idx)
}
}
return nil
}
func approval(index int) Decision {
return Decision{ProposalIndex: index, Approved: true, ReasonCode: ReasonApproved, Message: "approved"}
}
func rejection(index int, reasonCode string, msg string) Decision {
return Decision{ProposalIndex: index, Approved: false, ReasonCode: reasonCode, Message: strings.TrimSpace(msg)}
}
func confidenceThresholdForModule(moduleKey string, cfg *config.Config) float64 {
if cfg == nil {
return 0.0
}
switch moduleKey {
case "glossary":
return cfg.Thresholds.Glossary
case "grammar":
return cfg.Thresholds.Grammar
case "homophones":
return cfg.Thresholds.Homophones
case "spoken_word":
return cfg.Thresholds.SpokenWord
default:
return 0.0
}
}

181
internal/framework/validators/validators_test.go Normal file
View File

@@ -0,0 +1,181 @@
package validators
import (
"context"
"strings"
"testing"
"gitea.maximumdirect.net/eric/audita/internal/core/config"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
)
func mkCandidate(index int, segID int, orig, corr string, conf float64) proposals.EnrichedCorrectionProposal {
return proposals.EnrichedCorrectionProposal{
CorrectionProposal: proposals.CorrectionProposal{TargetSegmentID: segID, OriginalText: orig, CorrectedText: corr, Confidence: conf},
ProposalMetadata: proposals.ProposalMetadata{ProposalIndex: index, ModuleKey: "grammar", ModuleInstance: "grammar_1"},
}
}
func TestEnforceDecisionCardinalitySuccess(t *testing.T) {
candidates := []proposals.EnrichedCorrectionProposal{mkCandidate(0, 1, "teh", "the", 0.9), mkCandidate(1, 1, "recieve", "receive", 0.9)}
decisions := []Decision{{ProposalIndex: 0, Approved: true}, {ProposalIndex: 1, Approved: false}}
if err := EnforceDecisionCardinality(candidates, decisions); err != nil {
t.Fatalf("unexpected error: %v", err)
}
}
func TestEnforceDecisionCardinalityMissingDecision(t *testing.T) {
candidates := []proposals.EnrichedCorrectionProposal{mkCandidate(0, 1, "teh", "the", 0.9), mkCandidate(1, 1, "recieve", "receive", 0.9)}
err := EnforceDecisionCardinality(candidates, []Decision{{ProposalIndex: 0, Approved: true}})
if err == nil || !strings.Contains(err.Error(), "missing decision") {
t.Fatalf("expected missing decision error, got %v", err)
}
}
func TestEnforceDecisionCardinalityDuplicateDecision(t *testing.T) {
candidates := []proposals.EnrichedCorrectionProposal{mkCandidate(0, 1, "teh", "the", 0.9)}
err := EnforceDecisionCardinality(candidates, []Decision{{ProposalIndex: 0, Approved: true}, {ProposalIndex: 0, Approved: false}})
if err == nil || !strings.Contains(err.Error(), "duplicate decision") {
t.Fatalf("expected duplicate decision error, got %v", err)
}
}
func TestEnforceDecisionCardinalityUnknownDecision(t *testing.T) {
candidates := []proposals.EnrichedCorrectionProposal{mkCandidate(0, 1, "teh", "the", 0.9)}
err := EnforceDecisionCardinality(candidates, []Decision{{ProposalIndex: 99, Approved: true}})
if err == nil || !strings.Contains(err.Error(), "unknown decision") {
t.Fatalf("expected unknown decision error, got %v", err)
}
}
func TestConfidenceThresholdValidator(t *testing.T) {
cfg := config.Default()
cfg.Thresholds.Grammar = 0.8
req := Request{ModuleKey: "grammar", Config: &cfg, CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "teh", "the", 0.9),
mkCandidate(1, 1, "recieve", "receive", 0.7),
}}
res, err := (ConfidenceThresholdValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if !res.Decisions[0].Approved || res.Decisions[0].ReasonCode != ReasonApproved {
t.Fatalf("expected first decision approved, got %+v", res.Decisions[0])
}
if res.Decisions[1].Approved || res.Decisions[1].ReasonCode != ReasonLowConfidence {
t.Fatalf("expected second decision low confidence reject, got %+v", res.Decisions[1])
}
}
func TestOriginalTextPresenceValidator(t *testing.T) {
req := Request{WorkingTranscript: &schema.Transcript{Segments: []schema.Segment{{ID: 1, Text: "hello world"}}}, CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "hello", "hi", 0.9),
mkCandidate(1, 1, "missing", "x", 0.9),
mkCandidate(2, 5, "hello", "hi", 0.9),
}}
res, err := (OriginalTextPresenceValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if !res.Decisions[0].Approved {
t.Fatalf("expected proposal 0 approved")
}
if res.Decisions[1].ReasonCode != ReasonMissingOriginalText {
t.Fatalf("expected missing_original_text, got %+v", res.Decisions[1])
}
if res.Decisions[2].ReasonCode != ReasonMissingTargetSegment {
t.Fatalf("expected missing_target_segment, got %+v", res.Decisions[2])
}
}
func TestNonEmptyCorrectionValidator(t *testing.T) {
req := Request{CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "hello", "hi", 0.9),
mkCandidate(1, 1, "hello", " ", 0.9),
}}
res, err := (NonEmptyCorrectionValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if !res.Decisions[0].Approved {
t.Fatalf("expected proposal 0 approved")
}
if res.Decisions[1].ReasonCode != ReasonEmptyCorrectedText {
t.Fatalf("expected empty_corrected_text, got %+v", res.Decisions[1])
}
}
func TestNoEffectValidator(t *testing.T) {
req := Request{CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "hello", "hello", 0.9),
mkCandidate(1, 1, "hello", "hi", 0.9),
}}
res, err := (NoEffectValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if res.Decisions[0].ReasonCode != ReasonNoEffect || res.Decisions[0].Approved {
t.Fatalf("expected no_effect rejection, got %+v", res.Decisions[0])
}
if !res.Decisions[1].Approved {
t.Fatalf("expected proposal 1 approved")
}
}
func TestProtectedGlossaryTermValidator(t *testing.T) {
glossary := &schema.Glossary{Entries: []schema.GlossaryEntry{{Name: "OpenAI", Aliases: []string{"Open AI"}, Plural: "OpenAIs", Category: "brand", Summary: "brand"}}}
req := Request{
Glossary: glossary,
ModuleKey: "grammar",
CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "OpenAI", "Open A I", 0.9),
mkCandidate(1, 1, "teh", "the", 0.9),
},
}
res, err := (ProtectedGlossaryTermValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if res.Decisions[0].ReasonCode != ReasonProtectedGlossaryTerm || res.Decisions[0].Approved {
t.Fatalf("expected protected glossary rejection, got %+v", res.Decisions[0])
}
if !res.Decisions[1].Approved {
t.Fatalf("expected non-glossary proposal approved")
}
}
func TestProtectedGlossaryTermValidatorAllowsGlossaryModule(t *testing.T) {
glossary := &schema.Glossary{Entries: []schema.GlossaryEntry{{Name: "OpenAI", Category: "brand", Summary: "brand"}}}
req := Request{
Glossary: glossary,
ModuleKey: "glossary",
CandidateProposal: []proposals.EnrichedCorrectionProposal{
mkCandidate(0, 1, "OpenAI", "Open A I", 0.9),
},
}
res, err := (ProtectedGlossaryTermValidator{}).Validate(context.Background(), req)
if err != nil {
t.Fatalf("Validate error: %v", err)
}
if !res.Decisions[0].Approved {
t.Fatalf("expected glossary module approval, got %+v", res.Decisions[0])
}
}
func TestStableReasonCodes(t *testing.T) {
codes := []string{
ReasonApproved,
ReasonLowConfidence,
ReasonMissingOriginalText,
ReasonMissingTargetSegment,
ReasonEmptyCorrectedText,
ReasonNoEffect,
ReasonProtectedGlossaryTerm,
}
for _, code := range codes {
if strings.TrimSpace(code) == "" {
t.Fatalf("reason code must not be empty")
}
}
}