Add a framework mechanism for prepared modules and validators to contribute checkpoint identity fingerprints

This commit is contained in:
2026-07-20 15:14:41 -05:00
parent 87c57681f6
commit 0f25e7339f
15 changed files with 539 additions and 26 deletions

View File

@@ -352,7 +352,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, err)
}
checkpointRecorder, checkpointLoader, err := checkpointHandlersForRun(effective.Config.Cache.Checkpoints, opts, effective.ResolvedPipeline, rawInput, only, llmProfiles, strings.TrimSpace(*llmProfile), strings.TrimSpace(sessionID.value), *resume)
checkpointRecorder, checkpointLoader, err := checkpointHandlersForRun(effective.Config.Cache.Checkpoints, opts, effective.ResolvedPipeline, prepared.CheckpointFingerprints(), rawInput, only, llmProfiles, strings.TrimSpace(*llmProfile), strings.TrimSpace(sessionID.value), *resume)
if err != nil {
return failPipelineCommand(stderr, commandState, terminalWriter, err)
}
@@ -434,6 +434,7 @@ func checkpointHandlersForRun(
settings config.CheckpointCacheConfig,
opts Options,
resolved pipeline.ResolvedPipeline,
componentFingerprints []pipeline.CheckpointFingerprint,
rawInput []byte,
only []string,
llmProfiles []artifacts.LLMProfileManifest,
@@ -454,7 +455,7 @@ func checkpointHandlersForRun(
SelectedLanes: only,
RuntimeOverrides: runtimeOverrideFingerprints(llmProfileOverride, sessionID),
References: pipeline.ReferenceProvenance(resolved),
ProvenanceFingerprints: llmProfileFingerprints(llmProfiles),
ProvenanceFingerprints: append(llmProfileFingerprints(llmProfiles), checkpointIdentityFingerprints(componentFingerprints)...),
})
if err != nil {
return nil, nil, fmt.Errorf("create checkpoint identity: %w", err)
@@ -480,6 +481,17 @@ func checkpointHandlersForRun(
return recorder, loader, nil
}
func checkpointIdentityFingerprints(values []pipeline.CheckpointFingerprint) []checkpoint.Fingerprint {
if len(values) == 0 {
return nil
}
out := make([]checkpoint.Fingerprint, len(values))
for index, value := range values {
out[index] = checkpoint.Fingerprint{Name: "component:" + value.Name, Value: value.Value}
}
return out
}
func rawInputDigest(data []byte) string {
sum := sha256.Sum256(data)
return "sha256:" + hex.EncodeToString(sum[:])

View File

@@ -11,6 +11,8 @@ import (
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/checkpoint"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
@@ -110,6 +112,97 @@ func TestConfiguredSpellCatalogBindingChangesResolvedPipelineIdentity(t *testing
}
}
func TestSemanticSpellCatalogFingerprintChangesCheckpointIdentityWithoutReferenceChange(t *testing.T) {
components := productionTestComponents(t)
configPath := repositoryPath("examples", "dnd-spells-production.config.yml")
effective, err := loadMaintainedExample(t, configPath).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
if err != nil {
t.Fatal(err)
}
materialized, _, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{ConfigPath: configPath, WorkingDir: filepath.Dir(configPath)})
if err != nil {
t.Fatal(err)
}
prepared, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}})
if err != nil {
t.Fatal(err)
}
fingerprints := prepared.CheckpointFingerprints()
if len(fingerprints) != 2 || fingerprints[0].Value != fingerprints[1].Value {
t.Fatalf("prepared fingerprints = %#v, want matching extractor and validator catalog identities", fingerprints)
}
identityFor := func(values []pipeline.CheckpointFingerprint) checkpoint.Identity {
identity, identityErr := checkpoint.NewIdentity(checkpoint.IdentityInput{
Pipeline: materialized,
InputKey: materialized.Input.Module,
RawInputDigest: "sha256:unchanged-input",
References: pipeline.ReferenceProvenance(materialized),
ProvenanceFingerprints: checkpointIdentityFingerprints(values),
})
if identityErr != nil {
t.Fatal(identityErr)
}
return identity
}
first := identityFor(fingerprints)
changed := append([]pipeline.CheckpointFingerprint(nil), fingerprints...)
changed[0].Value = "sha256:changed-effective-catalog"
second := identityFor(changed)
if first.Digest == second.Digest || reflect.DeepEqual(first.ReferenceDigests, nil) || !reflect.DeepEqual(first.ReferenceDigests, second.ReferenceDigests) {
t.Fatalf("identities = %#v / %#v, want semantic invalidation with unchanged reference provenance", first, second)
}
}
func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t *testing.T) {
components := productionTestComponents(t)
configPath := repositoryPath("examples", "dnd-spells-production.config.yml")
effective, err := loadMaintainedExample(t, configPath).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
if err != nil {
t.Fatal(err)
}
materialized, _, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{ConfigPath: configPath, WorkingDir: filepath.Dir(configPath)})
if err != nil {
t.Fatal(err)
}
prepared, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}})
if err != nil {
t.Fatal(err)
}
fingerprints := prepared.CheckpointFingerprints()
settings := config.CheckpointCacheConfig{Enabled: true, Directory: t.TempDir()}
recorder, _, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, []byte("same input"), nil, nil, "", "", false)
if err != nil {
t.Fatal(err)
}
doc := source.SourceDocument{ID: "source", Kind: "transcript", Format: "application/json"}
doc.Units = []source.SourceUnit{{ID: 1, Kind: "turn", Text: "Aria casts Cure Wounds.", Ref: source.SourceRef{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}}}
doc.Digest, err = source.DigestDocument(&doc)
if err != nil {
t.Fatal(err)
}
if err := recorder.SourceSucceeded(materialized.Input.Module, &doc); err != nil {
t.Fatal(err)
}
_, sameLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, fingerprints, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
if _, decision := sameLoader.Source(materialized.Input.Module); !decision.Reused {
t.Fatalf("same fingerprint decision = %#v, want reuse", decision)
}
changed := append([]pipeline.CheckpointFingerprint(nil), fingerprints...)
changed[0].Value = "sha256:changed-effective-catalog"
_, changedLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changed, []byte("same input"), nil, nil, "", "", true)
if err != nil {
t.Fatal(err)
}
if _, decision := changedLoader.Source(materialized.Input.Module); decision.Reused {
t.Fatalf("changed fingerprint decision = %#v, want cold miss", decision)
}
}
func TestMaintainedProductionOverlayRunAlignsGroundingValidationAndProvenance(t *testing.T) {
outputRoot := filepath.Join(t.TempDir(), "output")
fake := &productionFakeLLMClient{spellResponse: productionSpellResponse("Aegis of Emberfall")}

View File

@@ -16,6 +16,13 @@ type CheckpointFingerprint struct {
Value string `json:"value"`
}
// CheckpointFingerprintProvider supplies stable, non-secret semantic identity
// for a prepared module or validator. Values must not contain source content,
// credentials, local paths, timestamps, or other invocation-specific data.
type CheckpointFingerprintProvider interface {
CheckpointFingerprints() []CheckpointFingerprint
}
type CheckpointRecorder interface {
SourceRunning(moduleKey string) error
SourceSucceeded(moduleKey string, doc *source.SourceDocument) error

View File

@@ -72,6 +72,167 @@ func TestPrepareConstructsEverythingInStableOrder(t *testing.T) {
}
}
func TestPreparedCheckpointFingerprintsCollectEveryComponentInStableScopeOrder(t *testing.T) {
provider := func(value string) checkpointFingerprintTestProvider {
return checkpointFingerprintTestProvider{{Name: "identity", Value: value}}
}
prepared := &PreparedPipeline{
resolved: ResolvedPipeline{
ID: "fingerprints",
Input: Binding("input"),
Chunk: Binding("chunk"),
Output: Binding("output"),
},
input: provider("input"),
chunker: provider("chunk"),
chunkValidators: preparedValidatorChain{validators: []preparedValidator{{
resolved: ResolvedValidator{Binding: Binding("chunk-validator"), Target: ValidatorTargetChunk},
chunk: provider("chunk-validator"),
}}},
output: provider("output"),
}
lane := preparedLaneExecutor{
resolved: ResolvedArtifactLane{
ID: "spells",
Extract: Binding("extract"),
Merge: Binding("merge"),
Normalize: Binding("normalize"),
},
typed: &preparedTypedLane{
extractor: provider("extract"),
merger: provider("merge"),
normalizer: provider("normalize"),
},
extractValidators: fingerprintTestValidatorChain("extract-validator", provider("extract-validator")),
mergeValidators: fingerprintTestValidatorChain("merge-validator", provider("merge-validator")),
normalizeValidators: fingerprintTestValidatorChain("normalize-validator", provider("normalize-validator")),
}
prepared.lanes = []preparedLaneExecutor{lane}
first, err := collectPreparedCheckpointFingerprints(prepared)
if err != nil {
t.Fatalf("collectPreparedCheckpointFingerprints() error = %v, want nil", err)
}
second, err := collectPreparedCheckpointFingerprints(prepared)
if err != nil {
t.Fatalf("second collection error = %v, want nil", err)
}
if !reflect.DeepEqual(first, second) {
t.Fatalf("fingerprints are not deterministic: %#v / %#v", first, second)
}
if len(first) != 10 {
t.Fatalf("fingerprints = %#v, want all 10 prepared components", first)
}
for index := 1; index < len(first); index++ {
if first[index-1].Name >= first[index].Name {
t.Fatalf("fingerprints are not sorted: %#v", first)
}
}
prepared.checkpointFingerprints = first
copy := prepared.CheckpointFingerprints()
copy[0].Value = "mutated"
if reflect.DeepEqual(copy, prepared.CheckpointFingerprints()) {
t.Fatal("CheckpointFingerprints() exposed mutable backing storage")
}
}
func TestPreparedCheckpointFingerprintsValidateProviderValues(t *testing.T) {
tests := []struct {
name string
fingerprints []CheckpointFingerprint
want string
}{
{name: "empty name", fingerprints: []CheckpointFingerprint{{Value: "value"}}, want: "non-empty name and value"},
{name: "empty value", fingerprints: []CheckpointFingerprint{{Name: "name"}}, want: "non-empty name and value"},
{name: "duplicate after trimming", fingerprints: []CheckpointFingerprint{{Name: "same", Value: "one"}, {Name: " same ", Value: "two"}}, want: "duplicated"},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
prepared := &PreparedPipeline{
resolved: ResolvedPipeline{ID: "fingerprints", Input: Binding("input"), Chunk: Binding("chunk"), Output: Binding("output")},
input: checkpointFingerprintTestProvider(test.fingerprints),
}
_, err := collectPreparedCheckpointFingerprints(prepared)
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("error = %v, want substring %q", err, test.want)
}
})
}
}
func TestPreparedCheckpointFingerprintsRemainEmptyWithoutProviders(t *testing.T) {
registries, _ := constructionRegistries(t, nil, nil)
resolved, err := ResolvePipeline(constructionProfile(), ResolveOptions{}, registries.catalog())
if err != nil {
t.Fatal(err)
}
prepared, err := Prepare(resolved, registries, ModuleDependencies{})
if err != nil {
t.Fatal(err)
}
if got := prepared.CheckpointFingerprints(); len(got) != 0 {
t.Fatalf("CheckpointFingerprints() = %#v, want empty", got)
}
}
func TestPreparedCheckpointFingerprintsScopeRepeatedValidatorsByPosition(t *testing.T) {
provider := checkpointFingerprintTestProvider{{Name: "identity", Value: "same"}}
validator := func() preparedValidator {
return preparedValidator{resolved: ResolvedValidator{Binding: Binding("configured"), Target: ValidatorTargetChunk}, chunk: provider}
}
prepared := &PreparedPipeline{
resolved: ResolvedPipeline{ID: "fingerprints", Input: Binding("input"), Chunk: Binding("chunk"), Output: Binding("output")},
chunkValidators: preparedValidatorChain{validators: []preparedValidator{validator(), validator()}},
}
got, err := collectPreparedCheckpointFingerprints(prepared)
if err != nil {
t.Fatalf("collect repeated validators: %v", err)
}
if len(got) != 2 || got[0].Name == got[1].Name {
t.Fatalf("fingerprints = %#v, want independently scoped repeated validators", got)
}
}
type checkpointFingerprintTestProvider []CheckpointFingerprint
func (p checkpointFingerprintTestProvider) CheckpointFingerprints() []CheckpointFingerprint {
return append([]CheckpointFingerprint(nil), p...)
}
func (checkpointFingerprintTestProvider) Key() string { return "fingerprint-test" }
func (checkpointFingerprintTestProvider) ReferenceSlots() []contracts.ReferenceSlot { return nil }
func (checkpointFingerprintTestProvider) Parse(context.Context, contracts.ParseRequest) (*source.SourceDocument, error) {
return typedTestDocument(), nil
}
func (checkpointFingerprintTestProvider) Plan(context.Context, contracts.ChunkRequest) (contracts.ChunkPlanResult, error) {
return contracts.ChunkPlanResult{}, nil
}
func (checkpointFingerprintTestProvider) Encode(context.Context, contracts.OutputRequest) (contracts.OutputResult, error) {
return contracts.OutputResult{}, nil
}
func (checkpointFingerprintTestProvider) Name() string { return "fingerprint-test" }
func (checkpointFingerprintTestProvider) ExecutionClass() contracts.ExecutionClass {
return contracts.ExecutionClassDeterministic
}
func (checkpointFingerprintTestProvider) Validate(context.Context, contracts.ChunkValidationRequest) (contracts.ValidationResult, error) {
return contracts.ValidationResult{Approved: true}, nil
}
type checkpointFingerprintOutput struct {
contracts.OutputEncoder
fingerprints []CheckpointFingerprint
}
func (o checkpointFingerprintOutput) CheckpointFingerprints() []CheckpointFingerprint {
return append([]CheckpointFingerprint(nil), o.fingerprints...)
}
func fingerprintTestValidatorChain(key string, provider checkpointFingerprintTestProvider) preparedValidatorChain {
return preparedValidatorChain{validators: []preparedValidator{{
resolved: ResolvedValidator{Binding: Binding(key), Target: ValidatorTargetTyped},
typed: provider,
}}}
}
func TestPrepareDeliversTargetReferencesAsIndependentBuildInputs(t *testing.T) {
var built []string
var observations []constructionBuildObservation
@@ -183,9 +344,26 @@ func TestPrepareFailuresOccurBeforeInputParse(t *testing.T) {
}
}
func TestPrepareRejectsInvalidComponentCheckpointFingerprint(t *testing.T) {
failure := &constructionFailure{outputFingerprints: []CheckpointFingerprint{{Name: "identity"}}}
registries, input := constructionRegistries(t, nil, failure)
resolved, err := ResolvePipeline(constructionProfile(), ResolveOptions{}, registries.catalog())
if err != nil {
t.Fatal(err)
}
_, err = Prepare(resolved, registries, ModuleDependencies{})
if err == nil || !strings.Contains(err.Error(), "checkpoint fingerprint") || !strings.Contains(err.Error(), "output:output") {
t.Fatalf("Prepare() error = %v, want scoped checkpoint fingerprint error", err)
}
if len(input.requests) != 0 {
t.Fatalf("input Parse calls = %d, want zero", len(input.requests))
}
}
type constructionFailure struct {
requireExtractorLLM bool
output error
outputFingerprints []CheckpointFingerprint
}
func constructionProfile() PipelineProfile {
@@ -298,7 +476,11 @@ func constructionRegistriesWithHooks(t *testing.T, built *[]string, failure *con
if failure.output != nil {
return nil, failure.output
}
return &typedTestOutput{key: "output"}, nil
output := contracts.OutputEncoder(&typedTestOutput{key: "output"})
if failure.outputFingerprints != nil {
output = checkpointFingerprintOutput{OutputEncoder: output, fingerprints: failure.outputFingerprints}
}
return output, nil
}); err != nil {
t.Fatal(err)
}

View File

@@ -17,13 +17,14 @@ type PreparedPipeline struct {
ArtifactLanes []PreparedArtifactLane
Output ModuleBinding
resolved ResolvedPipeline
dependencies ModuleDependencies
input contracts.InputAdapter
chunker contracts.Chunker
chunkValidators preparedValidatorChain
lanes []preparedLaneExecutor
output contracts.OutputEncoder
resolved ResolvedPipeline
dependencies ModuleDependencies
input contracts.InputAdapter
chunker contracts.Chunker
chunkValidators preparedValidatorChain
lanes []preparedLaneExecutor
output contracts.OutputEncoder
checkpointFingerprints []CheckpointFingerprint
}
type PreparedArtifactLane struct {
@@ -114,6 +115,10 @@ func Prepare(resolved ResolvedPipeline, registries Registries, deps ModuleDepend
return nil, constructionError(stable.ID, "", StageOutput, stable.Output.Module, "", err)
}
prepared.output = output
prepared.checkpointFingerprints, err = collectPreparedCheckpointFingerprints(prepared)
if err != nil {
return nil, err
}
return prepared, nil
}

View File

@@ -0,0 +1,86 @@
package pipeline
import (
"fmt"
"sort"
"strings"
)
type checkpointFingerprintComponent struct {
scope string
module any
}
// CheckpointFingerprints returns a defensive copy of the stable semantic
// identities contributed by the pipeline's prepared modules and validators.
func (p *PreparedPipeline) CheckpointFingerprints() []CheckpointFingerprint {
if p == nil {
return nil
}
return append([]CheckpointFingerprint(nil), p.checkpointFingerprints...)
}
func collectPreparedCheckpointFingerprints(prepared *PreparedPipeline) ([]CheckpointFingerprint, error) {
components := []checkpointFingerprintComponent{
{scope: "input:" + prepared.resolved.Input.Module, module: prepared.input},
{scope: "chunk:" + prepared.resolved.Chunk.Module, module: prepared.chunker},
}
components = appendValidatorFingerprintComponents(components, "chunk:"+prepared.resolved.Chunk.Module, prepared.chunkValidators)
for _, lane := range prepared.lanes {
laneScope := func(stage ModuleStage, moduleKey string) string {
return string(stage) + ":" + lane.resolved.ID + ":" + moduleKey
}
components = append(components, checkpointFingerprintComponent{scope: laneScope(StageExtract, lane.resolved.Extract.Module), module: lane.typed.extractor})
components = appendValidatorFingerprintComponents(components, laneScope(StageExtract, lane.resolved.Extract.Module), lane.extractValidators)
components = append(components, checkpointFingerprintComponent{scope: laneScope(StageMerge, lane.resolved.Merge.Module), module: lane.typed.merger})
components = appendValidatorFingerprintComponents(components, laneScope(StageMerge, lane.resolved.Merge.Module), lane.mergeValidators)
components = append(components, checkpointFingerprintComponent{scope: laneScope(StageNormalize, lane.resolved.Normalize.Module), module: lane.typed.normalizer})
components = appendValidatorFingerprintComponents(components, laneScope(StageNormalize, lane.resolved.Normalize.Module), lane.normalizeValidators)
}
components = append(components, checkpointFingerprintComponent{scope: "output:" + prepared.resolved.Output.Module, module: prepared.output})
var values []CheckpointFingerprint
seen := make(map[string]struct{})
for _, item := range components {
provider, ok := item.module.(CheckpointFingerprintProvider)
if !ok {
continue
}
for _, fingerprint := range provider.CheckpointFingerprints() {
name := strings.TrimSpace(fingerprint.Name)
value := strings.TrimSpace(fingerprint.Value)
if name == "" || value == "" {
return nil, fmt.Errorf("pipeline %q checkpoint fingerprint for %s must have a non-empty name and value", prepared.resolved.ID, item.scope)
}
scopedName := item.scope + ":" + name
if _, exists := seen[scopedName]; exists {
return nil, fmt.Errorf("pipeline %q checkpoint fingerprint %q is duplicated", prepared.resolved.ID, scopedName)
}
seen[scopedName] = struct{}{}
values = append(values, CheckpointFingerprint{Name: scopedName, Value: value})
}
}
sort.Slice(values, func(i, j int) bool { return values[i].Name < values[j].Name })
return values, nil
}
func appendValidatorFingerprintComponents(components []checkpointFingerprintComponent, ownerScope string, chain preparedValidatorChain) []checkpointFingerprintComponent {
for index, validator := range chain.validators {
scope := fmt.Sprintf("%s:validator:%d:%s", ownerScope, index, validator.resolved.Binding.Module)
components = append(components, checkpointFingerprintComponent{scope: scope, module: preparedValidatorImplementation(validator)})
}
return components
}
func preparedValidatorImplementation(validator preparedValidator) any {
switch validator.resolved.Target {
case ValidatorTargetTyped:
return validator.typed
case ValidatorTargetChunk:
return validator.chunk
case ValidatorTargetSerialized:
return validator.serialized
default:
return nil
}
}

View File

@@ -43,6 +43,7 @@ func referenceSlots() []contracts.ReferenceSlot {
}
var _ contracts.Extractor[dnd.SpellList] = (*Extractor)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Extractor)(nil)
type Options struct{}
@@ -109,6 +110,13 @@ func (e *Extractor) ManifestMetadata() map[string]any {
return metadata
}
func (e *Extractor) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if e == nil {
return nil
}
return []pipeline.CheckpointFingerprint{{Name: "effective_catalog", Value: e.effectiveCatalog.Digest()}}
}
func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRequest) (contracts.TypedExtractionResult[dnd.SpellList], error) {
if e == nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("extractor must not be nil")

View File

@@ -117,6 +117,10 @@ func TestExtractPromptUsesCanonicalOverlayNamesWithoutAliasesOrMetadata(t *testi
if got, ok := metadata["catalog_overlay_ids"].([]string); !ok || !reflect.DeepEqual(got, []string{"campaign.example"}) {
t.Fatalf("catalog overlay metadata = %#v", metadata["catalog_overlay_ids"])
}
fingerprints := newExtractor(t, &fakeSpellsLLMClient{}, overlaySpellCatalogReference()).CheckpointFingerprints()
if len(fingerprints) != 1 || fingerprints[0].Name != "effective_catalog" || fingerprints[0].Value != metadata["catalog_digest"] {
t.Fatalf("checkpoint fingerprints = %#v, want manifest catalog digest %#v", fingerprints, metadata["catalog_digest"])
}
encoded, err := json.Marshal(metadata)
if err != nil {
t.Fatal(err)

View File

@@ -13,9 +13,11 @@ import (
)
const (
Key = "extract/dnd/spells/catalog"
ReasonCode = "unknown_spell"
maxIssues = 20
Key = "extract/dnd/spells/catalog"
ReasonCode = "unknown_spell"
maxIssues = 20
maxDisplayedNameRunes = 128
maxMessageBytes = 4096
)
type Options struct{}
@@ -25,6 +27,7 @@ type Validator struct {
}
var _ contracts.TypedValidator[dnd.SpellList] = (*Validator)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
func New(_ Options, references ...contracts.ReferenceSet) (*Validator, error) {
if len(references) > 1 {
@@ -47,6 +50,13 @@ func (v *Validator) ExecutionClass() contracts.ExecutionClass {
return contracts.ExecutionClassDeterministic
}
func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if v == nil {
return nil
}
return []pipeline.CheckpointFingerprint{{Name: "effective_catalog", Value: v.catalog.Digest()}}
}
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.SpellList]) (contracts.ValidationResult, error) {
if err := spellshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
@@ -74,19 +84,37 @@ type unknownSpell struct {
}
func rejection(unknown []unknownSpell) contracts.ValidationResult {
displayed := unknown
if len(displayed) > maxIssues {
displayed = displayed[:maxIssues]
limit := len(unknown)
if limit > maxIssues {
limit = maxIssues
}
issues := make([]string, len(displayed))
for index, item := range displayed {
issues[index] = fmt.Sprintf("spell_casts[%d].spell %q", item.index, item.name)
issues := make([]string, 0, limit)
for _, item := range unknown[:limit] {
issue := fmt.Sprintf("spell_casts[%d].spell %q", item.index, truncateDisplayedName(item.name))
candidate := rejectionMessage(append(issues, issue), len(unknown)-len(issues)-1)
if len(candidate) > maxMessageBytes {
break
}
issues = append(issues, issue)
}
message := fmt.Sprintf("unknown spell names: %s", strings.Join(issues, ", "))
if omitted := len(unknown) - len(displayed); omitted > 0 {
message := rejectionMessage(issues, len(unknown)-len(issues))
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: message}
}
func truncateDisplayedName(name string) string {
runes := []rune(name)
if len(runes) <= maxDisplayedNameRunes {
return name
}
return string(runes[:maxDisplayedNameRunes-1]) + "…"
}
func rejectionMessage(issues []string, omitted int) string {
message := "unknown spell names: " + strings.Join(issues, ", ")
if omitted > 0 {
message += fmt.Sprintf("; %d additional issue(s) omitted", omitted)
}
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: message}
return message
}
func Spec() pipeline.ValidatorSpec {

View File

@@ -6,6 +6,7 @@ import (
"reflect"
"strings"
"testing"
"unicode/utf8"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
@@ -29,6 +30,17 @@ func TestValidatorApprovesCanonicalNormalizedAndOverlayAliasNames(t *testing.T)
}
}
func TestValidatorCheckpointFingerprintUsesEffectiveCatalogDigest(t *testing.T) {
validator, err := New(Options{}, overlayReferences())
if err != nil {
t.Fatal(err)
}
fingerprints := validator.CheckpointFingerprints()
if len(fingerprints) != 1 || fingerprints[0].Name != "effective_catalog" || fingerprints[0].Value != validator.catalog.Digest() {
t.Fatalf("checkpoint fingerprints = %#v, want effective catalog digest %q", fingerprints, validator.catalog.Digest())
}
}
func TestValidatorRejectsMultipleUnknownCastsInStableOrder(t *testing.T) {
value := spellList("Unknown First", "Cure Wounds", "Unknown Second")
validator, err := New(Options{})
@@ -71,6 +83,50 @@ func TestValidatorBoundsUnknownCastMessage(t *testing.T) {
}
}
func TestValidatorBoundsUnknownSpellNamesAndTotalMessage(t *testing.T) {
longName := strings.Repeat("火", maxDisplayedNameRunes+100) + "\n\t"
value := dnd.SpellList{SpellCasts: make([]dnd.SpellCast, maxIssues)}
for index := range value.SpellCasts {
value.SpellCasts[index] = validCast(fmt.Sprintf("%s-%d", longName, index))
}
validator, err := New(Options{})
if err != nil {
t.Fatal(err)
}
result, err := validator.Validate(context.Background(), validationRequest(value))
if err != nil {
t.Fatal(err)
}
if result.Approved || len([]byte(result.Message)) > maxMessageBytes || !strings.Contains(result.Message, "…") {
t.Fatalf("message length/content = %d/%q, want bounded message with truncation", len([]byte(result.Message)), result.Message)
}
if !strings.Contains(result.Message, "additional issue(s) omitted") {
t.Fatalf("message = %q, want byte-budget omitted count", result.Message)
}
displayed := strings.Count(result.Message, "spell_casts[")
wantOmitted := fmt.Sprintf("%d additional issue(s) omitted", len(value.SpellCasts)-displayed)
if !strings.Contains(result.Message, wantOmitted) {
t.Fatalf("message = %q, want omitted count %q", result.Message, wantOmitted)
}
if !utf8.ValidString(result.Message) {
t.Fatal("bounded message is not valid UTF-8")
}
}
func TestValidatorQuotesControlCharactersInUnknownSpellName(t *testing.T) {
validator, err := New(Options{})
if err != nil {
t.Fatal(err)
}
result, err := validator.Validate(context.Background(), validationRequest(spellList("Unknown\nSpell\tName")))
if err != nil {
t.Fatal(err)
}
if strings.Contains(result.Message, "Unknown\nSpell") || !strings.Contains(result.Message, `Unknown\nSpell\tName`) {
t.Fatalf("message = %q, want safely quoted control characters", result.Message)
}
}
func TestValidatorDefersInvalidShape(t *testing.T) {
value := dnd.SpellList{SpellCasts: []dnd.SpellCast{{Spell: "Unknown Spell"}}}
validator, err := New(Options{})