Files
audita/internal/framework/validators/models.go

134 lines
4.9 KiB
Go

package validators
import (
"context"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/audita/internal/core/config"
"gitea.maximumdirect.net/eric/audita/internal/core/modulecatalog"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
stagewarnings "gitea.maximumdirect.net/eric/audita/internal/framework/warnings"
)
const (
ReasonApproved = "approved"
ReasonLowConfidence = "low_confidence"
ReasonMissingOriginalText = "missing_original_text"
ReasonMissingTargetSegment = "missing_target_segment"
ReasonEmptyResultingText = "empty_resulting_segment"
ReasonNoEffect = "no_effect"
ReasonProtectedGlossaryTerm = "protected_glossary_term"
ReasonInvalidTargetSegment = "invalid_target_segment_id"
ReasonEmptyOriginalText = "empty_original_text"
ReasonInvalidConfidence = "invalid_confidence"
ReasonValidatorMalformed = "validator_response_malformed"
ReasonValidatorInputTooLarge = "validator_input_too_large"
)
// 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:"-"`
LLMClient StructuredLLMClient `json:"-"`
Scheduler ValidationScheduler `json:"-"`
DiagnosticsWriter InteractionDiagnosticsWriter `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"`
DiagnosticArtifactPath string `json:"diagnostic_artifact_path,omitempty"`
}
// Result is one validator output containing exactly one decision per proposal index.
type Result struct {
ValidatorName string `json:"validator_name"`
Decisions []Decision `json:"decisions"`
Warnings []stagewarnings.StageWarning `json:"warnings,omitempty"`
}
// ValidationScheduler provides bounded execution for validator LLM calls.
type ValidationScheduler interface {
Run(ctx context.Context, fn func(context.Context) error) error
}
type InteractionDiagnosticsWriter interface {
WriteInteraction(stage string, requestMetadata any, requestPayload any, responsePayload any, errorPayload any) (InteractionArtifacts, error)
}
type InteractionArtifacts struct {
RequestMetadataPath string `json:"request_metadata_path,omitempty"`
RequestPayloadPath string `json:"request_payload_path,omitempty"`
ResponsePayloadPath string `json:"response_payload_path,omitempty"`
ErrorPayloadPath string `json:"error_payload_path,omitempty"`
}
// 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 modulecatalog.KeyGlossary:
return cfg.Thresholds.Glossary
case modulecatalog.KeyGrammar:
return cfg.Thresholds.Grammar
case modulecatalog.KeyHomophones:
return cfg.Thresholds.Homophones
case modulecatalog.KeySpokenWord:
return cfg.Thresholds.SpokenWord
default:
return 0.0
}
}