Migrate location reconciliation to shared engine
This commit is contained in:
@@ -2,7 +2,9 @@ package locationregistry
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"strconv"
|
||||
"strings"
|
||||
@@ -11,9 +13,10 @@ import (
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/framework/semanticreconcile"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/entityreconcile"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
|
||||
)
|
||||
|
||||
func TestModuleContractAndMetadata(t *testing.T) {
|
||||
@@ -30,11 +33,14 @@ func TestModuleContractAndMetadata(t *testing.T) {
|
||||
}
|
||||
normalizer := newNormalizer(t, &recordingLocationNormalizerClient{})
|
||||
metadata := normalizer.ManifestMetadata()
|
||||
if metadata["identity_policy"] != identity.Policy || metadata["response_schema_id"] != entityreconcile.ResponseSchemaID || metadata["normalization_policy"] != normalizationPolicy || metadata["semantic_context_radius"] != semanticContextRadius {
|
||||
limits, ok := metadata["semantic_reconciliation_limits"].(map[string]any)
|
||||
if !ok || metadata["identity_policy"] != identity.Policy || metadata["normalization_policy"] != normalizationPolicy || metadata["prompt_id"] != PromptID || metadata["prompt_version"] != PromptVersion || metadata["response_schema_key"] != string(semanticreconcile.ResponseSchemaKey) || metadata["response_schema_id"] != semanticreconcile.ResponseSchemaID || metadata["response_schema_name"] != semanticreconcile.ResponseSchemaName || metadata["semantic_reconciliation_policy"] != semanticreconcile.Policy || len(limits) != 3 {
|
||||
t.Fatalf("metadata = %#v", metadata)
|
||||
}
|
||||
if got := normalizer.CheckpointFingerprints(); len(got) != 5 || got[2].Value != identity.Policy || got[3].Value != normalizationPolicy || got[4].Value != semanticContextPolicy+":2" {
|
||||
t.Fatalf("fingerprints = %#v", got)
|
||||
for _, name := range []string{"prompt", "response_schema", "semantic_reconciliation_policy", "semantic_reconciliation_limits", "identity_policy", "normalization_policy"} {
|
||||
if !hasFingerprint(normalizer.CheckpointFingerprints(), name) {
|
||||
t.Fatalf("fingerprints missing %q", name)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -46,7 +52,8 @@ func TestNormalizePreparesOnlyExactDuplicatesAndRetainsSameNameAndNestedPlaces(t
|
||||
{Name: "The Tavern Cellar", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}},
|
||||
}}
|
||||
before := dnd.LocationRegistry{Locations: append([]dnd.Location(nil), input.Locations...)}
|
||||
result, err := newNormalizer(t, &recordingLocationNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input))
|
||||
client := &recordingLocationNormalizerClient{}
|
||||
result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequest(input))
|
||||
if err != nil || len(result.Value.Locations) != 3 {
|
||||
t.Fatalf("Normalize() = %#v, %v; want one exact duplicate removed", result, err)
|
||||
}
|
||||
@@ -56,7 +63,7 @@ func TestNormalizePreparesOnlyExactDuplicatesAndRetainsSameNameAndNestedPlaces(t
|
||||
if got := []string{result.Value.Locations[0].Name, result.Value.Locations[1].Name, result.Value.Locations[2].Name}; !reflect.DeepEqual(got, []string{"The Tavern", "The Tavern", "The Tavern Cellar"}) {
|
||||
t.Fatalf("locations = %#v, want same names and nested place retained", got)
|
||||
}
|
||||
if result.Value.Locations[0].ID == result.Value.Locations[1].ID || !hasWarning(result.Warnings, ReasonCodeDuplicateLocationCollapsed) {
|
||||
if result.Value.Locations[0].ID == result.Value.Locations[1].ID || !hasWarning(result.Warnings, ReasonCodeDuplicateLocationCollapsed) || len(client.requests) != 0 {
|
||||
t.Fatalf("result = %#v, want evidence-anchored IDs and exact duplicate warning", result)
|
||||
}
|
||||
}
|
||||
@@ -79,7 +86,7 @@ func BenchmarkExactDuplicateGroupsManyDistinct(b *testing.B) {
|
||||
}
|
||||
|
||||
func TestNormalizeAppliesSafeAliasGroupAndUsesContextualInputs(t *testing.T) {
|
||||
client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000002"}]}`}
|
||||
client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"candidate_ids":[1,2],"canonical_candidate_id":2}]}`}
|
||||
doc := semanticDocument()
|
||||
input := dnd.LocationRegistry{Locations: []dnd.Location{
|
||||
{Name: "Old Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
|
||||
@@ -107,7 +114,7 @@ func TestNormalizeRejectsUnsafeAndOverlappingGroupsWithoutLosingCandidates(t *te
|
||||
{Name: "Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
|
||||
{Name: "Tavern", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}},
|
||||
}}
|
||||
client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000001"},{"members":["candidate-000002","candidate-000003"],"canonical":"candidate-000003"}]}`}
|
||||
client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"candidate_ids":[1,2],"canonical_candidate_id":1},{"candidate_ids":[2,3],"canonical_candidate_id":3}]}`}
|
||||
result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
|
||||
if err != nil || result.Retry == nil || len(result.Value.Locations) != 3 || !strings.Contains(result.Retry.Message, "overlapping_member") {
|
||||
t.Fatalf("Normalize() = %#v, %v; want safe retry fallback", result, err)
|
||||
@@ -117,6 +124,54 @@ func TestNormalizeRejectsUnsafeAndOverlappingGroupsWithoutLosingCandidates(t *te
|
||||
}
|
||||
}
|
||||
|
||||
func TestReconciliationCandidatesKeepSameNameEvidenceDistinct(t *testing.T) {
|
||||
doc := semanticDocument()
|
||||
records := []normalizedRecord{
|
||||
{location: dnd.Location{Name: "The Tavern", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, inputIndexes: []int{0}, earliest: 0},
|
||||
{location: dnd.Location{Name: "The Tavern", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}}, inputIndexes: []int{1}, earliest: 1},
|
||||
}
|
||||
candidates, _, err := reconciliationInputs(records)
|
||||
if err != nil {
|
||||
t.Fatalf("reconciliationInputs() error = %v", err)
|
||||
}
|
||||
preparation, err := semanticreconcile.Prepare(doc, candidates, semanticreconcile.DefaultLimits())
|
||||
if err != nil || preparation.Disposition() != semanticreconcile.Ready {
|
||||
t.Fatalf("Prepare() = %#v, %v; want ready candidates", preparation, err)
|
||||
}
|
||||
var candidateInput struct {
|
||||
Candidates []struct {
|
||||
CandidateID int `json:"candidate_id"`
|
||||
Label string `json:"label"`
|
||||
} `json:"candidates"`
|
||||
}
|
||||
if err := json.Unmarshal(preparation.Materials()["candidates"].Content, &candidateInput); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if len(candidateInput.Candidates) != 2 || candidateInput.Candidates[0].CandidateID != 1 || candidateInput.Candidates[1].CandidateID != 2 || candidateInput.Candidates[0].Label != "The Tavern" || candidateInput.Candidates[1].Label != "The Tavern" {
|
||||
t.Fatalf("candidate input = %#v, want distinct integer handles for equal names", candidateInput)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNormalizeLimitSkipDoesNotCallLLMAndAddsBoundedFallbackWarning(t *testing.T) {
|
||||
client := &recordingLocationNormalizerClient{}
|
||||
doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Kind: "narration", Text: "A sprawling city"}}}
|
||||
limit := semanticreconcile.DefaultLimits().MaximumCandidates
|
||||
input := dnd.LocationRegistry{Locations: make([]dnd.Location, limit+1)}
|
||||
for index := range input.Locations {
|
||||
input.Locations[index] = dnd.Location{Name: fmt.Sprintf("Place %d", index), SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}}}
|
||||
}
|
||||
result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
|
||||
if err != nil || result.Retry != nil {
|
||||
t.Fatalf("Normalize() = %#v, %v; want deterministic limit fallback", result, err)
|
||||
}
|
||||
if len(client.requests) != 0 || len(result.Value.Locations) != limit+1 {
|
||||
t.Fatalf("completion calls = %d, locations = %d; want no call and all records", len(client.requests), len(result.Value.Locations))
|
||||
}
|
||||
if !hasWarning(result.Warnings, ReasonCodeLocationSemanticReconciliationExhausted) || len(result.Warnings) > diagnostics.MaxWarnings {
|
||||
t.Fatalf("warnings = %#v, want bounded reconciliation fallback", result.Warnings)
|
||||
}
|
||||
}
|
||||
|
||||
func TestNormalizeHandlesRetryFallbackAndErrors(t *testing.T) {
|
||||
doc := semanticDocument()
|
||||
input := dnd.LocationRegistry{Locations: []dnd.Location{{Name: "Old Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}}}
|
||||
@@ -152,3 +207,12 @@ func TestNormalizeOrdersEvidenceAndIsIdempotent(t *testing.T) {
|
||||
t.Fatalf("second Normalize() = %#v, %v; want idempotent value %#v", second, err, first.Value)
|
||||
}
|
||||
}
|
||||
|
||||
func hasFingerprint(fingerprints []pipeline.CheckpointFingerprint, name string) bool {
|
||||
for _, fingerprint := range fingerprints {
|
||||
if fingerprint.Name == name && fingerprint.Value != "" {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user