185 lines
8.2 KiB
Go
185 lines
8.2 KiB
Go
package contracts
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"fmt"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestSemanticCorrectionOwnsValidatedContent(t *testing.T) {
|
|
assistant := []byte(`{"items":["original"]}`)
|
|
correction, err := NewSemanticCorrection(assistant, "Return one corrected replacement.")
|
|
if err != nil {
|
|
t.Fatalf("NewSemanticCorrection() error = %v", err)
|
|
}
|
|
assistant[0] = '['
|
|
if got := string(correction.AssistantResponse); got != `{"items":["original"]}` {
|
|
t.Fatalf("assistant response = %q, want owned original content", got)
|
|
}
|
|
|
|
clone, err := CloneSemanticCorrection(correction)
|
|
if err != nil {
|
|
t.Fatalf("CloneSemanticCorrection() error = %v", err)
|
|
}
|
|
clone.AssistantResponse[0] = '['
|
|
if got := string(correction.AssistantResponse); got != `{"items":["original"]}` {
|
|
t.Fatalf("source correction changed through clone = %q", got)
|
|
}
|
|
if nilClone, err := CloneSemanticCorrection(nil); err != nil || nilClone != nil {
|
|
t.Fatalf("CloneSemanticCorrection(nil) = %#v, %v; want nil, nil", nilClone, err)
|
|
}
|
|
|
|
encoded, err := json.Marshal(correction)
|
|
if err != nil {
|
|
t.Fatalf("marshal correction: %v", err)
|
|
}
|
|
if string(encoded) != "{}" {
|
|
t.Fatalf("correction JSON = %s, want no sensitive content", encoded)
|
|
}
|
|
}
|
|
|
|
func TestCorrectionContractsRejectInvalidContent(t *testing.T) {
|
|
tooLongAssistant := bytes.Repeat([]byte("a"), MaxAssistantResponseBytes+1)
|
|
tooLongGuidance := strings.Repeat("a", MaxCorrectionGuidanceBytes+1)
|
|
tooLongReason := strings.Repeat("a", MaxValidationReasonCodeBytes+1)
|
|
tooLongValidationGuidance := strings.Repeat("a", MaxValidationCorrectionGuidanceBytes+1)
|
|
|
|
for _, test := range []struct {
|
|
name string
|
|
call func() error
|
|
}{
|
|
{"blank assistant", func() error { _, err := NewSemanticCorrection([]byte(" \n"), "guidance"); return err }},
|
|
{"invalid assistant utf8", func() error { _, err := NewSemanticCorrection([]byte{0xff}, "guidance"); return err }},
|
|
{"oversized assistant", func() error { _, err := NewSemanticCorrection(tooLongAssistant, "guidance"); return err }},
|
|
{"blank guidance", func() error { _, err := NewSemanticCorrection([]byte("response"), " \t"); return err }},
|
|
{"invalid guidance utf8", func() error { _, err := NewSemanticCorrection([]byte("response"), string([]byte{0xff})); return err }},
|
|
{"oversized guidance", func() error { _, err := NewSemanticCorrection([]byte("response"), tooLongGuidance); return err }},
|
|
{"unsupported protocol", func() error { _, err := NewModelCandidate([]byte("response"), "multiple_responses"); return err }},
|
|
{"missing candidate protocol", func() error { _, err := NewModelCandidate([]byte("response"), ""); return err }},
|
|
{"blank candidate response", func() error { _, err := NewModelCandidate([]byte(" "), CorrectionProtocolSingleResponseV1); return err }},
|
|
{"missing rejection reason code", func() error {
|
|
return ValidateValidationResult(ValidationResult{CorrectionGuidance: "Correct the response."})
|
|
}},
|
|
{"missing rejection guidance", func() error { return ValidateValidationResult(ValidationResult{ReasonCode: "invalid"}) }},
|
|
{"oversized reason code", func() error {
|
|
return ValidateValidationResult(ValidationResult{ReasonCode: tooLongReason, CorrectionGuidance: "Correct the response."})
|
|
}},
|
|
{"blank reason code", func() error {
|
|
return ValidateValidationResult(ValidationResult{ReasonCode: " \t", CorrectionGuidance: "Correct the response."})
|
|
}},
|
|
{"invalid correction guidance utf8", func() error {
|
|
return ValidateValidationResult(ValidationResult{ReasonCode: "invalid", CorrectionGuidance: string([]byte{0xff})})
|
|
}},
|
|
{"oversized correction guidance", func() error {
|
|
return ValidateValidationResult(ValidationResult{ReasonCode: "invalid", CorrectionGuidance: tooLongValidationGuidance})
|
|
}},
|
|
} {
|
|
t.Run(test.name, func(t *testing.T) {
|
|
if err := test.call(); err == nil {
|
|
t.Fatal("validation error = nil, want error")
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestModelCandidateOwnsValidatedResponse(t *testing.T) {
|
|
response := []byte(`{"items":["original"]}`)
|
|
candidate, err := NewModelCandidate(response, CorrectionProtocolSingleResponseV1)
|
|
if err != nil {
|
|
t.Fatalf("NewModelCandidate() error = %v", err)
|
|
}
|
|
response[0] = '['
|
|
if got := string(candidate.Response); got != `{"items":["original"]}` {
|
|
t.Fatalf("candidate response = %q, want owned original content", got)
|
|
}
|
|
clone, err := CloneModelCandidate(candidate)
|
|
if err != nil {
|
|
t.Fatalf("CloneModelCandidate() error = %v", err)
|
|
}
|
|
clone.Response[0] = '['
|
|
if got := string(candidate.Response); got != `{"items":["original"]}` {
|
|
t.Fatalf("source candidate changed through clone = %q", got)
|
|
}
|
|
if nilClone, err := CloneModelCandidate(nil); err != nil || nilClone != nil {
|
|
t.Fatalf("CloneModelCandidate(nil) = %#v, %v; want nil, nil", nilClone, err)
|
|
}
|
|
}
|
|
|
|
func TestValidationResultAllowsAbsentOptionalCorrectionFields(t *testing.T) {
|
|
if err := ValidateValidationResult(ValidationResult{Approved: true}); err != nil {
|
|
t.Fatalf("ValidateValidationResult() error = %v, want nil", err)
|
|
}
|
|
if err := ValidateValidationResult(ValidationResult{ReasonCode: "invalid-evidence", CorrectionGuidance: "Provide source-backed evidence."}); err != nil {
|
|
t.Fatalf("ValidateValidationResult() error = %v, want nil", err)
|
|
}
|
|
if err := CorrectionProtocol("").Validate(); err == nil {
|
|
t.Fatal("empty correction protocol validation error = nil, want error")
|
|
}
|
|
}
|
|
|
|
func TestCloneStructuredCompletionRequestOwnsCorrection(t *testing.T) {
|
|
correction, err := NewSemanticCorrection([]byte(`{"value":"original"}`), "Correct the value.")
|
|
if err != nil {
|
|
t.Fatalf("NewSemanticCorrection() error = %v", err)
|
|
}
|
|
attempts := 2
|
|
request := StructuredCompletionRequest{
|
|
Inputs: LLMInputSet{"source": NewLLMInputMaterial("source", "application/json", []byte(`{"source":true}`), "", "")},
|
|
Vars: map[string]any{"labels": []string{"original"}},
|
|
StructuredOutputRepairAttempts: &attempts,
|
|
Correction: correction,
|
|
}
|
|
clone, err := CloneStructuredCompletionRequest(request)
|
|
if err != nil {
|
|
t.Fatalf("CloneStructuredCompletionRequest() error = %v", err)
|
|
}
|
|
correction.AssistantResponse[0] = '['
|
|
request.Inputs["source"] = NewLLMInputMaterial("source", "application/json", []byte(`{"source":false}`), "", "")
|
|
*request.StructuredOutputRepairAttempts = 7
|
|
if got := string(clone.Correction.AssistantResponse); got != `{"value":"original"}` {
|
|
t.Fatalf("cloned correction response = %q, want owned original content", got)
|
|
}
|
|
if got := string(clone.Inputs["source"].Content); got != `{"source":true}` {
|
|
t.Fatalf("cloned input = %q, want owned original content", got)
|
|
}
|
|
if clone.StructuredOutputRepairAttempts == nil || *clone.StructuredOutputRepairAttempts != 2 {
|
|
t.Fatalf("cloned repair attempts = %v, want 2", clone.StructuredOutputRepairAttempts)
|
|
}
|
|
}
|
|
|
|
func TestStructuredCompletionRequestDebugSummaryOmitsCorrectionContent(t *testing.T) {
|
|
const assistantResponse = `{"secret":"assistant response"}`
|
|
const userGuidance = "secret user guidance"
|
|
correction, err := NewSemanticCorrection([]byte(assistantResponse), userGuidance)
|
|
if err != nil {
|
|
t.Fatalf("NewSemanticCorrection() error = %v", err)
|
|
}
|
|
request := StructuredCompletionRequest{
|
|
Inputs: LLMInputSet{"source": NewLLMInputMaterial("source", "application/json", []byte(`{"source":true}`), "", "")},
|
|
Vars: map[string]any{"custom": "value"},
|
|
Correction: correction,
|
|
}
|
|
|
|
summary := request.DebugSummary()
|
|
if summary.InputCount != 1 || summary.VariableCount != 1 || summary.Correction == nil {
|
|
t.Fatalf("debug summary = %#v, want input, variable, and correction metadata", summary)
|
|
}
|
|
if summary.Correction.AssistantResponseBytes != len(assistantResponse) || summary.Correction.UserGuidanceBytes != len(userGuidance) ||
|
|
summary.Correction.AssistantResponseDigest == "" || summary.Correction.UserGuidanceDigest == "" {
|
|
t.Fatalf("correction summary = %#v, want byte counts and digests", summary.Correction)
|
|
}
|
|
encoded, err := json.Marshal(summary)
|
|
if err != nil {
|
|
t.Fatalf("marshal debug summary: %v", err)
|
|
}
|
|
for _, rendered := range []string{string(encoded), fmt.Sprintf("%+v", request), fmt.Sprintf("%#v", request)} {
|
|
for _, secret := range []string{assistantResponse, userGuidance} {
|
|
if strings.Contains(rendered, secret) {
|
|
t.Fatalf("content-safe request rendering leaked %q: %s", secret, rendered)
|
|
}
|
|
}
|
|
}
|
|
}
|