eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Make module-stage LLM handling resilient and report warnings

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-23 10:07:06 -05:00
parent a84941d681
commit a3655f5540
43 changed files with 856 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
internal/framework/runner/runner_test.go
View File

@@ -47,11 +47,12 @@ type fakeModule struct {
func (m fakeModule) Key() string { return m.key }
func (m fakeModule) ReplacementPolicy() proposals.ReplacementPolicy { return m.policy }
func (m fakeModule) Validators() []contracts.Validator { return m.validators }
func (m fakeModule) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
func (m fakeModule) Propose(ctx context.Context, req contracts.ProposalRequest) (contracts.ProposalResult, error) {
if m.proposeF == nil {
return nil, nil
return contracts.ProposalResult{}, nil
}
return m.proposeF(req)
proposalsOut, err := m.proposeF(req)
return contracts.ProposalResult{Proposals: proposalsOut}, err
}
type fakeValidator struct {
@@ -1191,7 +1192,7 @@ func TestRunnerLLMValidatorRejectionPreventsApplication(t *testing.T) {
}
}
func TestRunnerLLMValidatorMalformedResponseFailsWithPartialProgress(t *testing.T) {
func TestRunnerLLMValidatorMalformedResponseRejectsBatchAndKeepsPartialProgress(t *testing.T) {
client := &fakeStructuredClient{responses: []validators.LLMValidationResponse{{Validations: []validators.LLMValidationDecision{{CorrectionIndex: 99, Approved: true, Confidence: 0.9, Reason: "bad index"}}}}}
llmValidator, _ := validators.NewLLMBackedValidator("spoken_form_plausibility_review", validators.LLMValidatorTypeSpokenFormPlausibility, "")
r := New(fakeFactory{modules: map[string]contracts.TranscriptModule{
@@ -1209,15 +1210,21 @@ func TestRunnerLLMValidatorMalformedResponseFailsWithPartialProgress(t *testing.
ModuleSpecs: []contracts.ModuleRunSpec{{ModuleKey: "m1", InstanceName: "m1"}, {ModuleKey: "m2", InstanceName: "m2"}},
ValidationLLMClient: client,
})
if err == nil {
t.Fatal("expected llm validator failure")
if err != nil {
t.Fatalf("expected malformed validator response to downgrade, got %v", err)
}
if out.FinalTranscript.Segments[0].Text != "the cat" {
t.Fatalf("expected partial progress retained")
}
if len(out.ModuleResults) != 2 || len(out.ModuleResults[1].ValidatorRejected) != 1 {
t.Fatalf("expected second module rejection, got %+v", out.ModuleResults)
}
if len(out.ModuleResults[1].Warnings) != 1 || out.ModuleResults[1].Warnings[0].ReasonCode != validators.ReasonValidatorMalformed {
t.Fatalf("expected malformed warning, got %+v", out.ModuleResults[1].Warnings)
}
}
func TestRunnerLLMValidatorMissingDecisionFails(t *testing.T) {
func TestRunnerLLMValidatorMissingDecisionRejectsBatch(t *testing.T) {
client := &fakeStructuredClient{responses: []validators.LLMValidationResponse{{Validations: []validators.LLMValidationDecision{}}}}
llmValidator, _ := validators.NewLLMBackedValidator("spoken_form_plausibility_review", validators.LLMValidatorTypeSpokenFormPlausibility, "")
r := New(fakeFactory{modules: map[string]contracts.TranscriptModule{
@@ -1232,12 +1239,12 @@ func TestRunnerLLMValidatorMissingDecisionFails(t *testing.T) {
ModuleSpecs: []contracts.ModuleRunSpec{{ModuleKey: "m", InstanceName: "m"}},
ValidationLLMClient: client,
})
if err == nil {
t.Fatal("expected missing decision failure")
if err != nil {
t.Fatalf("expected missing decision downgrade, got %v", err)
}
}
func TestRunnerLLMValidatorDuplicateDecisionFails(t *testing.T) {
func TestRunnerLLMValidatorDuplicateDecisionRejectsBatch(t *testing.T) {
client := &fakeStructuredClient{responses: []validators.LLMValidationResponse{{Validations: []validators.LLMValidationDecision{
{CorrectionIndex: 0, Approved: true, Confidence: 0.9, Reason: "ok"},
{CorrectionIndex: 0, Approved: false, Confidence: 0.9, Reason: "dup"},
@@ -1255,8 +1262,8 @@ func TestRunnerLLMValidatorDuplicateDecisionFails(t *testing.T) {
ModuleSpecs: []contracts.ModuleRunSpec{{ModuleKey: "m", InstanceName: "m"}},
ValidationLLMClient: client,
})
if err == nil {
t.Fatal("expected duplicate decision failure")
if err != nil {
t.Fatalf("expected duplicate decision downgrade, got %v", err)
}
}
@@ -1355,7 +1362,7 @@ type proposalGenerationModule struct {
func (m proposalGenerationModule) Key() string { return m.key }
func (m proposalGenerationModule) ReplacementPolicy() proposals.ReplacementPolicy { return m.policy }
func (m proposalGenerationModule) Validators() []contracts.Validator { return nil }
func (m proposalGenerationModule) Propose(ctx context.Context, req contracts.ProposalRequest) ([]proposals.CorrectionProposal, error) {
func (m proposalGenerationModule) Propose(ctx context.Context, req contracts.ProposalRequest) (contracts.ProposalResult, error) {
result, err := proposal_generation.GenerateCandidates(ctx, proposal_generation.Request{
ModuleKey: req.RunSpec.ModuleKey,
ModuleInstance: req.RunSpec.InstanceName,
@@ -1372,9 +1379,9 @@ func (m proposalGenerationModule) Propose(ctx context.Context, req contracts.Pro
DiagnosticsDir: req.DiagnosticsDir,
})
if err != nil {
return nil, err
return contracts.ProposalResult{}, err
}
return result.Corrections, nil
return contracts.ProposalResult{Proposals: result.Corrections, Warnings: result.Warnings}, nil
}
type fakeProposalStructuredClient struct {