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

Improve semantic reconciliation retries

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-28 18:25:00 +00:00
parent 5cab4e512e
commit 4da9360d74
25 changed files with 771 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
internal/framework/pipeline/runner_normalize_retry_test.go
View File

@@ -153,6 +153,60 @@ func TestRunnerHandlesRetryableNormalizeFallbacks(t *testing.T) {
}
}
func TestRunnerForwardsModuleRequestedNormalizeCorrection(t *testing.T) {
const (
defective = `{"duplicate_groups":[{"candidate_ids":[1,99],"canonical_candidate_id":1}]}`
guidance = "Duplicate group 1 must use only supplied candidate IDs. Return one complete corrected response."
)
prepared := preparedAttemptDebugPipeline(t)
lane := &prepared.Steps[0].lanes[0]
lane.resolved.Normalize.Retries = 1
var observed *contracts.SemanticCorrection
calls := 0
lane.typed.normalize = func(_ context.Context, _ any, request contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) {
calls++
if request.Correction != nil {
clone, err := contracts.CloneSemanticCorrection(request.Correction)
if err != nil {
return erasedTypedResult{}, err
}
observed = clone
}
if calls == 1 {
return erasedTypedResult{
Value: codecNotes{Items: []string{"safe fallback"}},
ModelCandidate: attemptCandidate(t, defective),
Retry: &contracts.NormalizeRetry{
ReasonCode: "semantic_proposal_invalid",
Message: "operator-facing proposal diagnostic",
CorrectionGuidance: guidance,
},
}, nil
}
return erasedTypedResult{Value: codecNotes{Items: []string{"corrected"}}}, nil
}
debug := newCapturedDebugRecorder()
output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Debug: debug})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if calls != 2 || observed == nil || string(observed.AssistantResponse) != defective || observed.UserGuidance != guidance {
t.Fatalf("normalize calls = %d correction = %#v", calls, observed)
}
if len(output.NormalizeOutputs) != 1 || len(output.Rejected) != 0 {
t.Fatalf("run output = %#v, want corrected accepted output", output)
}
var retryDebug strings.Builder
for _, name := range debug.names() {
if strings.HasPrefix(name, "normalize/notes/attempt-") && strings.HasSuffix(name, ".json") {
retryDebug.Write(debug.json[name])
}
}
if !strings.Contains(retryDebug.String(), `"correction_available":true`) || strings.Contains(retryDebug.String(), guidance) || strings.Contains(retryDebug.String(), defective) {
t.Fatalf("retry debug = %s, want safe correction metadata without content", retryDebug.String())
}
}
func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
const (
reasonSentinel = "reason-diagnostic-sentinel"
@@ -160,9 +214,11 @@ func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
)
reasonOverLimit := strings.Repeat("r", contracts.MaxNormalizeRetryReasonCodeBytes-len(reasonSentinel)) + reasonSentinel + "x"
messageOverLimit := strings.Repeat("m", contracts.MaxNormalizeRetryMessageBytes-len(messageSentinel)) + messageSentinel + "x"
guidanceOverLimit := strings.Repeat("g", contracts.MaxNormalizeRetryCorrectionGuidanceBytes-len(messageSentinel)) + messageSentinel + "x"
tests := []struct {
name string
retry contracts.NormalizeRetry
candidate *contracts.ModelCandidate
wantError string
hiddenValues []string
}{
@@ -173,6 +229,15 @@ func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
Message: strings.Repeat("m", contracts.MaxNormalizeRetryMessageBytes),
},
},
{
name: "accepts correction guidance byte limit with candidate",
retry: contracts.NormalizeRetry{
ReasonCode: reasonSentinel,
Message: messageSentinel,
CorrectionGuidance: strings.Repeat("g", contracts.MaxNormalizeRetryCorrectionGuidanceBytes),
},
candidate: attemptCandidate(t, `{"duplicate_groups":[]}`),
},
{
name: "rejects oversized reason code",
retry: contracts.NormalizeRetry{
@@ -209,6 +274,46 @@ func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
wantError: "message has invalid UTF-8",
hiddenValues: []string{reasonSentinel, messageSentinel},
},
{
name: "rejects oversized correction guidance",
retry: contracts.NormalizeRetry{
ReasonCode: reasonSentinel,
Message: messageSentinel,
CorrectionGuidance: guidanceOverLimit,
},
wantError: "correction guidance exceeds maximum length",
hiddenValues: []string{reasonSentinel, messageSentinel},
},
{
name: "rejects invalid correction guidance UTF-8",
retry: contracts.NormalizeRetry{
ReasonCode: reasonSentinel,
Message: messageSentinel,
CorrectionGuidance: messageSentinel + string([]byte{0xff}),
},
wantError: "correction guidance has invalid UTF-8",
hiddenValues: []string{reasonSentinel, messageSentinel},
},
{
name: "rejects blank correction guidance",
retry: contracts.NormalizeRetry{
ReasonCode: reasonSentinel,
Message: messageSentinel,
CorrectionGuidance: " \t\n ",
},
wantError: "correction guidance is blank",
hiddenValues: []string{reasonSentinel, messageSentinel},
},
{
name: "rejects correction guidance without candidate",
retry: contracts.NormalizeRetry{
ReasonCode: reasonSentinel,
Message: messageSentinel,
CorrectionGuidance: "Return one complete corrected response.",
},
wantError: "requires a model candidate",
hiddenValues: []string{reasonSentinel, messageSentinel},
},
{
name: "rejects blank reason code",
retry: contracts.NormalizeRetry{
@@ -233,7 +338,7 @@ func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
t.Run(tc.name, func(t *testing.T) {
prepared := preparedAttemptDebugPipeline(t)
prepared.Steps[0].lanes[0].typed.normalize = func(context.Context, any, contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) {
return erasedTypedResult{Value: codecNotes{Items: []string{"safe"}}, Retry: &tc.retry}, nil
return erasedTypedResult{Value: codecNotes{Items: []string{"safe"}}, Retry: &tc.retry, ModelCandidate: tc.candidate}, nil
}
debug := newCapturedDebugRecorder()
output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Debug: debug})