Complete Phase 12 grammar module
This commit is contained in:
@@ -15,6 +15,7 @@ import (
|
||||
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
|
||||
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
|
||||
"gitea.maximumdirect.net/eric/audita/internal/framework/modules"
|
||||
"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
|
||||
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
|
||||
"gitea.maximumdirect.net/eric/audita/internal/framework/validators"
|
||||
)
|
||||
@@ -615,8 +616,8 @@ func TestRunProcessReportJSONIncludesChunkingSummary(t *testing.T) {
|
||||
if report.Chunking.MaxSectionTokens == 0 {
|
||||
t.Errorf("expected max_section_tokens in report")
|
||||
}
|
||||
if report.Phase != "phase11-proposal-generation-framework" {
|
||||
t.Errorf("expected phase 'phase11-proposal-generation-framework', got %q", report.Phase)
|
||||
if report.Phase != "phase12-grammar-module" {
|
||||
t.Errorf("expected phase 'phase12-grammar-module', got %q", report.Phase)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -661,8 +662,9 @@ func (v fakeValidator) Validate(ctx context.Context, req contracts.ValidationReq
|
||||
}
|
||||
|
||||
type fakeStructuredLLMClient struct {
|
||||
responses []validators.LLMValidationResponse
|
||||
err error
|
||||
validationResponses []validators.LLMValidationResponse
|
||||
proposalResponses []proposal_generation.StructuredCorrectionSet
|
||||
err error
|
||||
}
|
||||
|
||||
func (f *fakeStructuredLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
|
||||
@@ -671,13 +673,24 @@ func (f *fakeStructuredLLMClient) CompleteStructured(ctx context.Context, req co
|
||||
if f.err != nil {
|
||||
return contracts.StructuredCompletionResponse{}, f.err
|
||||
}
|
||||
if len(f.responses) == 0 {
|
||||
return contracts.StructuredCompletionResponse{}, errors.New("unexpected llm call")
|
||||
switch target := out.(type) {
|
||||
case *validators.LLMValidationResponse:
|
||||
if len(f.validationResponses) == 0 {
|
||||
return contracts.StructuredCompletionResponse{}, errors.New("unexpected validation llm call")
|
||||
}
|
||||
*target = f.validationResponses[0]
|
||||
f.validationResponses = f.validationResponses[1:]
|
||||
return contracts.StructuredCompletionResponse{}, nil
|
||||
case *proposal_generation.StructuredCorrectionSet:
|
||||
if len(f.proposalResponses) == 0 {
|
||||
return contracts.StructuredCompletionResponse{}, errors.New("unexpected proposal llm call")
|
||||
}
|
||||
*target = f.proposalResponses[0]
|
||||
f.proposalResponses = f.proposalResponses[1:]
|
||||
return contracts.StructuredCompletionResponse{}, nil
|
||||
default:
|
||||
return contracts.StructuredCompletionResponse{}, errors.New("unexpected llm output type")
|
||||
}
|
||||
target := out.(*validators.LLMValidationResponse)
|
||||
*target = f.responses[0]
|
||||
f.responses = f.responses[1:]
|
||||
return contracts.StructuredCompletionResponse{}, nil
|
||||
}
|
||||
|
||||
func TestRunProcessInjectedFactoryExecutesRunnerAndReportsModules(t *testing.T) {
|
||||
@@ -771,7 +784,7 @@ func TestRunProcessInjectedFactoryLLMValidatorResultsInReports(t *testing.T) {
|
||||
t.Fatalf("NewLLMBackedValidator: %v", err)
|
||||
}
|
||||
processValidationLLMClient = &fakeStructuredLLMClient{
|
||||
responses: []validators.LLMValidationResponse{{
|
||||
validationResponses: []validators.LLMValidationResponse{{
|
||||
Validations: []validators.LLMValidationDecision{{CorrectionIndex: 0, Approved: false, Confidence: 0.99, Reason: "reject"}},
|
||||
}},
|
||||
}
|
||||
@@ -940,6 +953,249 @@ func TestRunProcessProductionRegistryUnimplementedModuleFailsCleanly(t *testing.
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessExplicitUnimplementedModulesFailClearly(t *testing.T) {
|
||||
for _, moduleKey := range []string{"glossary", "homophones", "spoken_word"} {
|
||||
t.Run(moduleKey, func(t *testing.T) {
|
||||
var stdout, stderr bytes.Buffer
|
||||
transcriptPath := writeFile(t, "transcript.json", `[
|
||||
{"id":1,"speaker":"Alice","start":0.0,"end":1.0,"text":"Hello"}
|
||||
]`)
|
||||
exitCode := Run([]string{
|
||||
"process", transcriptPath,
|
||||
"--glossary", fixturePath("tiny_glossary.yaml"),
|
||||
"--modules", moduleKey,
|
||||
}, &stdout, &stderr)
|
||||
if exitCode == 0 {
|
||||
t.Fatalf("expected failure for %s", moduleKey)
|
||||
}
|
||||
if stdout.Len() != 0 {
|
||||
t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
|
||||
}
|
||||
if !strings.Contains(stderr.String(), "recognized but not implemented") {
|
||||
t.Fatalf("expected unimplemented message, got %q", stderr.String())
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessExplicitGrammarAppliesCorrectionAndReportsDiagnostics(t *testing.T) {
|
||||
secret := "phase12-secret"
|
||||
processProposalLLMClient = &fakeStructuredLLMClient{
|
||||
proposalResponses: []proposal_generation.StructuredCorrectionSet{
|
||||
{
|
||||
Corrections: []proposal_generation.StructuredCorrectionProposal{
|
||||
{TargetSegmentID: 1, OriginalText: "hello ,world", CorrectedText: "Hello, world", Confidence: 0.95},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
processValidationLLMClient = &fakeStructuredLLMClient{
|
||||
validationResponses: []validators.LLMValidationResponse{
|
||||
{Validations: []validators.LLMValidationDecision{{CorrectionIndex: 0, Approved: true, Confidence: 0.99, Reason: "ok"}}},
|
||||
{Validations: []validators.LLMValidationDecision{{CorrectionIndex: 0, Approved: true, Confidence: 0.99, Reason: secret}}},
|
||||
},
|
||||
}
|
||||
t.Setenv("AUDITA_LLM_API_KEY", secret)
|
||||
t.Setenv("AUDITA_VALIDATION_LLM_API_KEY", secret)
|
||||
t.Cleanup(func() {
|
||||
processProposalLLMClient = nil
|
||||
processValidationLLMClient = nil
|
||||
processProposalLLMScheduler = nil
|
||||
processValidationLLMScheduler = nil
|
||||
})
|
||||
|
||||
var stdout, stderr bytes.Buffer
|
||||
workDir := t.TempDir()
|
||||
reportPath := filepath.Join(t.TempDir(), "report.json")
|
||||
outputPath := filepath.Join(t.TempDir(), "out.json")
|
||||
transcriptPath := writeFile(t, "transcript.json", `[
|
||||
{"id":1,"speaker":"Alice","start":0.0,"end":1.0,"text":"hello ,world"}
|
||||
]`)
|
||||
|
||||
exitCode := Run([]string{
|
||||
"process", transcriptPath,
|
||||
"--glossary", fixturePath("tiny_glossary.yaml"),
|
||||
"--modules", "grammar",
|
||||
"--output", outputPath,
|
||||
"--report-json", reportPath,
|
||||
"--work-dir", workDir,
|
||||
"--work-dir-retention", "always",
|
||||
}, &stdout, &stderr)
|
||||
if exitCode != 0 {
|
||||
t.Fatalf("expected success, got %d stderr=%q", exitCode, stderr.String())
|
||||
}
|
||||
if stdout.Len() != 0 {
|
||||
t.Fatalf("expected empty stdout with --output, got %q", stdout.String())
|
||||
}
|
||||
|
||||
parsed, err := schema.ParseTranscriptJSON(readFile(t, outputPath))
|
||||
if err != nil {
|
||||
t.Fatalf("parse output: %v", err)
|
||||
}
|
||||
if parsed.Segments[0].Text != "Hello, world" {
|
||||
t.Fatalf("expected grammar correction applied, got %q", parsed.Segments[0].Text)
|
||||
}
|
||||
|
||||
report := readProcessReport(t, reportPath)
|
||||
if len(report.ModuleResults) != 1 || report.ModuleResults[0].ModuleKey != "grammar" {
|
||||
t.Fatalf("expected one grammar module result, got %+v", report.ModuleResults)
|
||||
}
|
||||
if len(report.ModuleResults[0].AppliedChanges) != 1 {
|
||||
t.Fatalf("expected one applied grammar change, got %+v", report.ModuleResults[0].AppliedChanges)
|
||||
}
|
||||
if len(report.ModuleResults[0].ValidatorDecisions) == 0 {
|
||||
t.Fatalf("expected validator decisions in report")
|
||||
}
|
||||
|
||||
runDir := onlyRunDir(t, workDir)
|
||||
runReport := readProcessReport(t, filepath.Join(runDir, "report.json"))
|
||||
if len(runReport.ModuleResults) != 1 {
|
||||
t.Fatalf("expected module results in run-dir report")
|
||||
}
|
||||
|
||||
diagFiles, globErr := filepath.Glob(filepath.Join(runDir, "grammar", "*response-payload.json"))
|
||||
if globErr != nil {
|
||||
t.Fatalf("glob diagnostics: %v", globErr)
|
||||
}
|
||||
if len(diagFiles) == 0 {
|
||||
t.Fatalf("expected grammar diagnostics payload files in %s", filepath.Join(runDir, "grammar"))
|
||||
}
|
||||
for _, f := range diagFiles {
|
||||
raw := string(readFile(t, f))
|
||||
if strings.Contains(raw, secret) {
|
||||
t.Fatalf("secret leaked in diagnostics %q: %s", f, raw)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessExplicitGrammarRejectedAndApplicationSkipAreDistinct(t *testing.T) {
|
||||
processProposalLLMClient = &fakeStructuredLLMClient{
|
||||
proposalResponses: []proposal_generation.StructuredCorrectionSet{
|
||||
{
|
||||
Corrections: []proposal_generation.StructuredCorrectionProposal{
|
||||
{TargetSegmentID: 1, OriginalText: "Hello", CorrectedText: "Hi", Confidence: 0.99},
|
||||
{TargetSegmentID: 1, OriginalText: "Hello world", CorrectedText: "Hi world", Confidence: 0.99},
|
||||
{TargetSegmentID: 1, OriginalText: "world", CorrectedText: "earth", Confidence: 0.99},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
processValidationLLMClient = &fakeStructuredLLMClient{
|
||||
validationResponses: []validators.LLMValidationResponse{
|
||||
{
|
||||
Validations: []validators.LLMValidationDecision{
|
||||
{CorrectionIndex: 0, Approved: true, Confidence: 0.9, Reason: "ok"},
|
||||
{CorrectionIndex: 1, Approved: true, Confidence: 0.9, Reason: "ok"},
|
||||
{CorrectionIndex: 2, Approved: false, Confidence: 0.9, Reason: "reject"},
|
||||
},
|
||||
},
|
||||
{
|
||||
Validations: []validators.LLMValidationDecision{
|
||||
{CorrectionIndex: 0, Approved: true, Confidence: 0.9, Reason: "ok"},
|
||||
{CorrectionIndex: 1, Approved: true, Confidence: 0.9, Reason: "ok"},
|
||||
},
|
||||
},
|
||||
},
|
||||
}
|
||||
t.Cleanup(func() {
|
||||
processProposalLLMClient = nil
|
||||
processValidationLLMClient = nil
|
||||
})
|
||||
|
||||
var stdout, stderr bytes.Buffer
|
||||
reportPath := filepath.Join(t.TempDir(), "report.json")
|
||||
outputPath := filepath.Join(t.TempDir(), "out.json")
|
||||
transcriptPath := writeFile(t, "transcript.json", `[
|
||||
{"id":1,"speaker":"Alice","start":0.0,"end":1.0,"text":"Hello world"}
|
||||
]`)
|
||||
exitCode := Run([]string{
|
||||
"process", transcriptPath,
|
||||
"--glossary", fixturePath("tiny_glossary.yaml"),
|
||||
"--modules", "grammar",
|
||||
"--output", outputPath,
|
||||
"--report-json", reportPath,
|
||||
}, &stdout, &stderr)
|
||||
if exitCode != 0 {
|
||||
t.Fatalf("expected success, got %d stderr=%q", exitCode, stderr.String())
|
||||
}
|
||||
|
||||
report := readProcessReport(t, reportPath)
|
||||
if len(report.ModuleResults) != 1 {
|
||||
t.Fatalf("expected one module result")
|
||||
}
|
||||
module := report.ModuleResults[0]
|
||||
if len(module.ValidatorRejected) != 1 {
|
||||
t.Fatalf("expected one validator rejection, got %+v", module.ValidatorRejected)
|
||||
}
|
||||
if len(module.SkippedChanges) != 1 {
|
||||
t.Fatalf("expected one application skip, got %+v", module.SkippedChanges)
|
||||
}
|
||||
if module.ValidatorRejected[0].ReasonCode == string(module.SkippedChanges[0].SkipReason) {
|
||||
t.Fatalf("validator rejection and application skip should remain distinct")
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessExplicitGrammarMalformedLLMOutputFailsWithErrorLog(t *testing.T) {
|
||||
processProposalLLMClient = &fakeStructuredLLMClient{err: errors.New("malformed structured output")}
|
||||
t.Cleanup(func() { processProposalLLMClient = nil })
|
||||
|
||||
var stdout, stderr bytes.Buffer
|
||||
workDir := t.TempDir()
|
||||
reportPath := filepath.Join(t.TempDir(), "report.json")
|
||||
transcriptPath := writeFile(t, "transcript.json", `[
|
||||
{"id":1,"speaker":"Alice","start":0.0,"end":1.0,"text":"hello"}
|
||||
]`)
|
||||
|
||||
exitCode := Run([]string{
|
||||
"process", transcriptPath,
|
||||
"--glossary", fixturePath("tiny_glossary.yaml"),
|
||||
"--modules", "grammar",
|
||||
"--work-dir", workDir,
|
||||
"--work-dir-retention", "always",
|
||||
"--report-json", reportPath,
|
||||
}, &stdout, &stderr)
|
||||
if exitCode == 0 {
|
||||
t.Fatal("expected failure")
|
||||
}
|
||||
if stdout.Len() != 0 {
|
||||
t.Fatalf("expected empty stdout on failure, got %q", stdout.String())
|
||||
}
|
||||
if !strings.Contains(stderr.String(), "runner_execution") {
|
||||
t.Fatalf("expected runner_execution error, got %q", stderr.String())
|
||||
}
|
||||
runDir := onlyRunDir(t, workDir)
|
||||
if _, err := os.Stat(filepath.Join(runDir, "error.log")); err != nil {
|
||||
t.Fatalf("expected error.log on failed grammar run: %v", err)
|
||||
}
|
||||
report := readProcessReport(t, reportPath)
|
||||
if report.Status != "failed" || report.ErrorPhase != "runner_execution" {
|
||||
t.Fatalf("expected failed runner_execution report, got %+v", report)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessDefaultBehaviorRemainsDeterministicWithoutExplicitModules(t *testing.T) {
|
||||
var stdout, stderr bytes.Buffer
|
||||
reportPath := filepath.Join(t.TempDir(), "report.json")
|
||||
outputPath := filepath.Join(t.TempDir(), "out.json")
|
||||
transcriptPath := writeFile(t, "transcript.json", `[
|
||||
{"id":1,"speaker":"Alice","start":0.0,"end":1.0,"text":"hello ,world"}
|
||||
]`)
|
||||
|
||||
exitCode := Run([]string{
|
||||
"process", transcriptPath,
|
||||
"--glossary", fixturePath("tiny_glossary.yaml"),
|
||||
"--output", outputPath,
|
||||
"--report-json", reportPath,
|
||||
}, &stdout, &stderr)
|
||||
if exitCode != 0 {
|
||||
t.Fatalf("expected success, got %d stderr=%q", exitCode, stderr.String())
|
||||
}
|
||||
report := readProcessReport(t, reportPath)
|
||||
if report.ModulesSummary != nil || len(report.ModuleResults) != 0 {
|
||||
t.Fatalf("expected no module execution without explicit --modules, got summary=%+v results=%+v", report.ModulesSummary, report.ModuleResults)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunProcessChunkingSummaryArtifactWritten(t *testing.T) {
|
||||
var stdout bytes.Buffer
|
||||
var stderr bytes.Buffer
|
||||
|
||||
Reference in New Issue
Block a user