merge cognitive task evaluation locale fix
CI / test (push) Failing after 30s

This commit is contained in:
m
2026-08-29 21:17:13 +03:00
2 changed files with 26 additions and 1 deletions
+1 -1
View File
@@ -100,7 +100,7 @@ func (g cognitiveGateway) executeTaskEvaluationCases(ctx context.Context, reques
go func(index int, item capability.TaskEvaluationCase) {
defer wg.Done()
started := time.Now()
invocation := cognitive.AdvisoryRequest{Version: cognitive.CreatorAdvisoryV1, RequestID: cognitive.RequestID(fmt.Sprintf("task-evaluation:%s:%s", request.Profile.ID, item.CaseID)), ActorID: request.ActorID, PrincipalID: request.PrincipalID, ScopeID: request.ScopeID, Message: item.Prompt, MaxOutputBytes: int(request.MaxOutputBytes), ProviderBindingID: selected.Binding.ID, ProviderBindingRevision: selected.Binding.Revision, ProviderInstanceID: selected.Provider.ID, ModelDescriptorID: selected.Model.ID, ProviderModelID: selected.Model.ProviderModelID}
invocation := cognitive.AdvisoryRequest{Version: cognitive.CreatorAdvisoryV1, RequestID: cognitive.RequestID(fmt.Sprintf("task-evaluation:%s:%s", request.Profile.ID, item.CaseID)), ActorID: request.ActorID, PrincipalID: request.PrincipalID, ScopeID: request.ScopeID, Message: item.Prompt, Locale: "en-US", MaxOutputBytes: int(request.MaxOutputBytes), ProviderBindingID: selected.Binding.ID, ProviderBindingRevision: selected.Binding.Revision, ProviderInstanceID: selected.Provider.ID, ModelDescriptorID: selected.Model.ID, ProviderModelID: selected.Model.ProviderModelID}
response, invokeErr := g.invokeAdmitted(ctx, string(invocation.RequestID), provider, invocation, int(request.MaxOutputBytes))
latency := time.Since(started).Microseconds()
observations[index] = capability.TaskCaseObservation{CaseID: item.CaseID, Result: capability.EvaluationUnknown, CriticalFailure: invokeErr != nil || response.FinishReason != cognitive.FinishCompleted || strings.TrimSpace(response.AdvisoryText) == "", EvidenceArtifactRef: item.EvidenceArtifactRef, LatencyMicros: latency}
@@ -4,6 +4,7 @@ import (
"bytes"
"context"
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"testing"
@@ -57,6 +58,30 @@ func TestTaskEvaluationHandlerInvokesEveryBoundedCase(t *testing.T) {
}
}
type localeCheckingProvider struct{ stubAdvisoryProvider }
func (p *localeCheckingProvider) Advise(ctx context.Context, request cognitive.AdvisoryRequest) (cognitive.AdvisoryResponse, error) {
if request.Locale == "" {
return cognitive.AdvisoryResponse{}, fmt.Errorf("task evaluation omitted required locale")
}
return p.stubAdvisoryProvider.Advise(ctx, request)
}
func TestTaskEvaluationSuppliesLocaleToProviderAdapter(t *testing.T) {
selected := gatewaySelection()
provider := &localeCheckingProvider{stubAdvisoryProvider{response: cognitive.AdvisoryResponse{Version: cognitive.CreatorAdvisoryV1, FinishReason: cognitive.FinishCompleted, AdvisoryText: "observed response"}}}
registry := &candidateRegistryStub{selected: selected}
gateway := cognitiveGateway{resolver: registry, providers: map[capability.ProviderKind][]providerRegistration{selected.Provider.Kind: {{ProviderInstanceID: selected.Provider.ID, Kind: selected.Provider.Kind, EndpointRef: selected.Provider.EndpointRef, CredentialRef: selected.Provider.CredentialRef, Provider: provider}}}, now: time.Now}
profile := capability.TaskEvaluationProfile{ID: "profile-locale", Revision: 1, CapabilityID: selected.Binding.CapabilityID, Stage: capability.TaskEvaluationGeneral, BenchmarkVersion: "locale-v1", RequiredCaseIDs: []string{"case-locale"}, QualityWeightMillis: 600, ReliabilityWeightMillis: 300, LatencyWeightMillis: 100}
request := capability.TaskEvaluationExecutionRequest{Profile: profile, CapabilityID: selected.Binding.CapabilityID, BindingID: selected.Binding.ID, BindingRevision: selected.Binding.Revision, ActorID: identity.ActorID("actor-1"), PrincipalID: selected.Binding.OwnerPrincipalID, ScopeID: authority.ScopeID("scope-1"), MaxOutputBytes: 512, EgressAcknowledged: true, Cases: []capability.TaskEvaluationCase{{CaseID: "case-locale", Prompt: "one", EvidenceArtifactRef: "artifact:locale"}}}
payload, _ := json.Marshal(request)
recorder := httptest.NewRecorder()
gateway.taskEvaluationHandler(recorder, httptest.NewRequest(http.MethodPost, "/v1/task-evaluations/execute", bytes.NewReader(payload)))
if recorder.Code != http.StatusOK {
t.Fatalf("status=%d body=%s", recorder.Code, recorder.Body.String())
}
}
type taskEvaluationFailoverRegistry struct {
primary, fallback capability.ResolvedCognitiveBinding
resolveCalls int