Clarify normalize fallback ownership

docs/internal/llm.md

@@ -157,18 +157,18 @@ messages remain canonical shared assets rather than copied package text.
 ### D&D NPC Normalization Prompt Ordering And Cache Boundaries
 
 NPC normalization has a distinct prompt and response-schema identity from NPC
-extraction. Its stable message tiers are the common D&D system and identity
-assets, followed by package-owned task and normalization instructions. Cache
-boundaries follow the shared identity tier and the package instructions. The
-variable tail contains the private candidate-name-and-range input and a
-windowed transcript input whose cited units provide local context; neither has
-a cache boundary because it changes with the document.
+extraction. Its stable message tiers are the common D&D system asset, followed
+by package-owned task and normalization instructions. Cache boundaries follow
+the shared system tier and the package instructions. The variable tail contains
+the private candidate-name-and-range input and a windowed transcript input
+whose cited units provide local context; neither has a cache boundary because
+it changes with the document.
 
-This prompt intentionally omits extraction-evidence and campaign-reference
-assets: it reconciles existing records rather than extracting events or adding
-evidence. Its package-owned manifest and schema identity are fingerprinted
-separately, so a normalization prompt or schema change cannot reuse a prior
-normalization checkpoint.
+This prompt intentionally omits shared identity guidance,
+extraction-evidence, and campaign-reference assets: it reconciles existing
+records rather than extracting events or adding evidence. Its package-owned
+manifest and schema identity are fingerprinted separately, so a normalization
+prompt or schema change cannot reuse a prior normalization checkpoint.
 
 Shared wording belongs in the canonical assets under
 `internal/modules/dnd/shared`; extraction packages reference those assets in

docs/internal/pipeline.md

@@ -325,12 +325,24 @@ processing immediately.
 Structured-completion adapters classify malformed or undecodable provider
 output with the provider-neutral `contracts.ErrInvalidStructuredOutput` error.
 A typed normalizer may turn that condition, or another unsafe proposal, into a
-normalize retry directive with a deterministic safe candidate, stable
+normalize retry directive with a module-supplied safe candidate, stable
 diagnostic, and fallback warnings. The directive consumes the same configured
 normalize retry budget: `retries` permits that many additional attempts after
 the initial attempt. It neither creates a normalizer-local retry loop nor
 records an accepted checkpoint for the discarded attempt.
 
+Before adding a normalize retry directive to attempt debug data, the runner
+requires a nonblank, valid UTF-8 reason code of at most 128 bytes and a
+nonblank, valid UTF-8 message of at most 4,096 bytes. These are encoded-byte
+limits. The framework rejects an invalid directive without truncating or
+rewriting either field. It validates only this mechanical contract; normalizers
+remain responsible for ensuring their otherwise valid diagnostics do not expose
+source material, credentials, paths, names, or other sensitive content.
+
+The framework treats a module-supplied candidate as opaque. The normalizer owns
+its safety determination, and the configured normalizer validator chain remains
+the acceptance boundary for the final fallback.
+
 When a later normalize attempt succeeds, its candidate alone proceeds through
 the usual validation and checkpoint path. When the final attempt still returns
 a directive, the runner validates its supplied safe fallback through that same

docs/operations.md

@@ -93,9 +93,9 @@ generated-reference barrier, `dnd/npcs` performs one document-level semantic
 normalization call for each configured normalize attempt when eligible distinct
 names remain. The normalize binding's `retries` setting controls additional
 attempts. If an invalid or unsafe identity proposal exhausts that budget, the
-run safely accepts the deterministic and any independently safe partial
-consolidation, with a bounded warning; ordinary validation still applies before
-the artifact can cross the barrier.
+run safely accepts the deterministic base result and any independently
+validated, model-proposed partial consolidation, with a bounded warning;
+ordinary validation still applies before the artifact can cross the barrier.
 
 An accepted normalized NPC checkpoint can be reused on `--resume` just like
 other accepted normalize work. A changed normalization prompt, response schema,

internal/framework/contracts/typed_pipeline.go

@@ -95,6 +95,11 @@ type TypedNormalizeResult[T any] struct {
 
 // NormalizeRetry asks the framework to retry normalization while retaining a
 // safe candidate for acceptance if the retry budget is exhausted.
+const (
+	MaxNormalizeRetryReasonCodeBytes = 128
+	MaxNormalizeRetryMessageBytes    = 4096
+)
+
 type NormalizeRetry struct {
 	ReasonCode       string
 	Message          string

internal/framework/pipeline/normalize_retry.go

@@ -0,0 +1,34 @@
+package pipeline
+
+import (
+	"errors"
+	"strings"
+	"unicode/utf8"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func validateNormalizeRetry(retry *contracts.NormalizeRetry) error {
+	if retry == nil {
+		return errors.New("normalize retry directive is missing")
+	}
+	if !utf8.ValidString(retry.ReasonCode) {
+		return errors.New("normalize retry directive reason code has invalid UTF-8")
+	}
+	if strings.TrimSpace(retry.ReasonCode) == "" {
+		return errors.New("normalize retry directive reason code is blank")
+	}
+	if len(retry.ReasonCode) > contracts.MaxNormalizeRetryReasonCodeBytes {
+		return errors.New("normalize retry directive reason code exceeds maximum length")
+	}
+	if !utf8.ValidString(retry.Message) {
+		return errors.New("normalize retry directive message has invalid UTF-8")
+	}
+	if strings.TrimSpace(retry.Message) == "" {
+		return errors.New("normalize retry directive message is blank")
+	}
+	if len(retry.Message) > contracts.MaxNormalizeRetryMessageBytes {
+		return errors.New("normalize retry directive message exceeds maximum length")
+	}
+	return nil
+}

internal/framework/pipeline/runner_normalize_retry_test.go

@@ -150,14 +150,112 @@ func TestRunnerHandlesRetryableNormalizeFallbacks(t *testing.T) {
 	}
 }
 
-func TestRunnerRejectsBlankNormalizeRetryDiagnostic(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: &contracts.NormalizeRetry{ReasonCode: " ", Message: "missing reason"}}, nil
+func TestRunnerValidatesNormalizeRetryDiagnostics(t *testing.T) {
+	const (
+		reasonSentinel  = "reason-diagnostic-sentinel"
+		messageSentinel = "message-diagnostic-sentinel"
+	)
+	reasonOverLimit := strings.Repeat("r", contracts.MaxNormalizeRetryReasonCodeBytes-len(reasonSentinel)) + reasonSentinel + "x"
+	messageOverLimit := strings.Repeat("m", contracts.MaxNormalizeRetryMessageBytes-len(messageSentinel)) + messageSentinel + "x"
+	tests := []struct {
+		name         string
+		retry        contracts.NormalizeRetry
+		wantError    string
+		hiddenValues []string
+	}{
+		{
+			name: "accepts byte limits",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: strings.Repeat("r", contracts.MaxNormalizeRetryReasonCodeBytes),
+				Message:    strings.Repeat("m", contracts.MaxNormalizeRetryMessageBytes),
+			},
+		},
+		{
+			name: "rejects oversized reason code",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: reasonOverLimit,
+				Message:    messageSentinel,
+			},
+			wantError:    "reason code exceeds maximum length",
+			hiddenValues: []string{reasonSentinel, messageSentinel},
+		},
+		{
+			name: "rejects oversized message",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: reasonSentinel,
+				Message:    messageOverLimit,
+			},
+			wantError:    "message exceeds maximum length",
+			hiddenValues: []string{reasonSentinel, messageSentinel},
+		},
+		{
+			name: "rejects invalid reason code UTF-8",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: reasonSentinel + string([]byte{0xff}),
+				Message:    messageSentinel,
+			},
+			wantError:    "reason code has invalid UTF-8",
+			hiddenValues: []string{reasonSentinel, messageSentinel},
+		},
+		{
+			name: "rejects invalid message UTF-8",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: reasonSentinel,
+				Message:    messageSentinel + string([]byte{0xff}),
+			},
+			wantError:    "message has invalid UTF-8",
+			hiddenValues: []string{reasonSentinel, messageSentinel},
+		},
+		{
+			name: "rejects blank reason code",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: " \t\n ",
+				Message:    messageSentinel,
+			},
+			wantError:    "reason code is blank",
+			hiddenValues: []string{messageSentinel},
+		},
+		{
+			name: "rejects blank message",
+			retry: contracts.NormalizeRetry{
+				ReasonCode: reasonSentinel,
+				Message:    " \t\n ",
+			},
+			wantError:    "message is blank",
+			hiddenValues: []string{reasonSentinel},
+		},
 	}
-	_, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Debug: newCapturedDebugRecorder()})
-	if err == nil || !strings.Contains(err.Error(), "blank reason code or message") {
-		t.Fatalf("Run() error = %v, want retry diagnostic contract error", err)
+
+	for _, tc := range tests {
+		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
+			}
+			debug := newCapturedDebugRecorder()
+			output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Debug: debug})
+			if tc.wantError == "" {
+				if err != nil {
+					t.Fatalf("Run() error = %v, want accepted retry fallback", err)
+				}
+				if len(output.NormalizeOutputs) != 1 {
+					t.Fatalf("normalize outputs = %#v, want one accepted fallback", output.NormalizeOutputs)
+				}
+				return
+			}
+			if err == nil || !strings.Contains(err.Error(), tc.wantError) {
+				t.Fatalf("Run() error = %v, want fixed %q error", err, tc.wantError)
+			}
+			var debugOutput strings.Builder
+			for _, name := range debug.names() {
+				debugOutput.Write(debug.json[name])
+			}
+			for _, value := range tc.hiddenValues {
+				if strings.Contains(err.Error(), value) || strings.Contains(debugOutput.String(), value) {
+					t.Fatalf("retry diagnostic leaked %q", value)
+				}
+			}
+		})
 	}
 }
 

internal/framework/pipeline/runner_typed.go

@@ -8,7 +8,6 @@ import (
 	"errors"
 	"fmt"
 	"path"
-	"strings"
 	"time"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
@@ -365,8 +364,8 @@ func (r *Runner) runNormalizeStage(ctx context.Context, input RunInput, checkpoi
 			}
 			var retryPayload map[string]any
 			if result.Retry != nil {
-				if strings.TrimSpace(result.Retry.ReasonCode) == "" || strings.TrimSpace(result.Retry.Message) == "" {
-					return false, nil, terminal.record(map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings)}, fmt.Errorf("normalize lane %q returned retry directive with blank reason code or message", lane.ID))
+				if err := validateNormalizeRetry(result.Retry); err != nil {
+					return false, nil, terminal.record(map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings)}, fmt.Errorf("normalize lane %q returned invalid retry directive: %w", lane.ID, err))
 				}
 				retryRemaining := attempt <= lane.Normalize.Retries
 				retryPayload = map[string]any{

internal/modules/dnd/normalize/npcs/assets/prompts/dnd.npcs.normalize.yaml

@@ -11,8 +11,6 @@ inputs:
 messages:
   - role: system
     content_file: ./sharedassets/common-dnd-system.md
-  - role: user
-    content_file: ./sharedassets/common-dnd-identity.md
     cache_control:
       type: ephemeral
   - role: user

internal/modules/dnd/normalize/npcs/context_material.go

@@ -119,15 +119,15 @@ func buildNormalizeContextMaterials(doc *source.SourceDocument, records []dnd.NP
 
 	windows, err := normalizeContextWindows(doc.Units, coalesceIntervals(intervals), cited)
 	if err != nil {
-		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: copy source metadata: %w", err)
+		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: invalid source metadata")
 	}
 	candidateContent, err := json.Marshal(normalizeCandidateInput{NPCs: candidates})
 	if err != nil {
-		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: encode candidates: %w", err)
+		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: invalid candidate material")
 	}
 	transcriptContent, err := json.Marshal(normalizeTranscriptInput{Windows: windows})
 	if err != nil {
-		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: encode transcript: %w", err)
+		return normalizeContextMaterials{}, false, fmt.Errorf("build NPC normalization context: invalid transcript material")
 	}
 	return normalizeContextMaterials{
 		Candidates:         newNormalizeInputMaterial("candidates", candidateContent),

internal/modules/dnd/normalize/npcs/scriptorium_assets.go

@@ -21,7 +21,6 @@ var promptAssetManifest = shared.PromptAssetManifest{
 	},
 	SharedFiles: []string{
 		"common-dnd-system.md",
-		"common-dnd-identity.md",
 		"common-dnd-transcript.md",
 	},
 }

internal/modules/dnd/normalize/npcs/scriptorium_assets_test.go

@@ -2,6 +2,7 @@ package npcs
 
 import (
 	"context"
+	"reflect"
 	"strings"
 	"testing"
 	"time"
@@ -11,6 +12,12 @@ import (
 )
 
 func TestRegisterPromptAssetsPreparesNormalizationPrompt(t *testing.T) {
+	if want := []string{"common-dnd-system.md", "common-dnd-transcript.md"}; !reflect.DeepEqual(promptAssetManifest.SharedFiles, want) {
+		t.Fatalf("shared prompt assets = %#v, want %#v", promptAssetManifest.SharedFiles, want)
+	}
+	if promptHash, err := scriptoriumPromptMetadata(); err != nil || promptHash == "" {
+		t.Fatalf("scriptoriumPromptMetadata() = %q, %v; want prompt fingerprint", promptHash, err)
+	}
 	registry := llm.NewAssetRegistry()
 	if err := RegisterPromptAssets(registry); err != nil {
 		t.Fatalf("RegisterPromptAssets() error = %v", err)
@@ -39,23 +46,36 @@ func TestRegisterPromptAssetsPreparesNormalizationPrompt(t *testing.T) {
 	if prepared.PromptID != PromptID || prepared.OutputContract.SchemaPath != "dnd_npcs_normalize_llm.v1.json" {
 		t.Fatalf("prepared prompt = %#v, want normalization prompt identity and schema", prepared)
 	}
-	if len(prepared.Messages) != 6 {
-		t.Fatalf("prepared messages = %d, want 6", len(prepared.Messages))
+	if len(prepared.Messages) != 5 {
+		t.Fatalf("prepared messages = %d, want 5", len(prepared.Messages))
 	}
-	for _, index := range []int{1, 3} {
+	for index, role := range []string{"system", "user", "user", "user", "user"} {
+		if prepared.Messages[index].Role != role {
+			t.Errorf("message %d role = %q, want %q", index, prepared.Messages[index].Role, role)
+		}
+	}
+	for _, index := range []int{0, 2} {
 		if cache := prepared.Messages[index].CacheControl; cache == nil || cache.Type != scriptorium.CacheControlEphemeral {
 			t.Errorf("message %d cache control = %#v, want ephemeral", index, cache)
 		}
 	}
-	for _, index := range []int{0, 2, 4, 5} {
+	for _, index := range []int{1, 3, 4} {
 		if cache := prepared.Messages[index].CacheControl; cache != nil {
 			t.Errorf("message %d cache control = %#v, want nil", index, cache)
 		}
 	}
-	if !strings.Contains(prepared.Messages[4].Content, `"Mira"`) || strings.Contains(prepared.Messages[4].Content, `"windows"`) {
-		t.Fatalf("candidate message = %q, want only rendered candidates", prepared.Messages[4].Content)
+	if !strings.Contains(prepared.Messages[3].Content, `"Mira"`) || strings.Contains(prepared.Messages[3].Content, `"windows"`) {
+		t.Fatalf("candidate message = %q, want only rendered candidates", prepared.Messages[3].Content)
 	}
-	if !strings.Contains(prepared.Messages[5].Content, `"windows"`) || strings.Contains(prepared.Messages[5].Content, `"Mira"`) {
-		t.Fatalf("transcript message = %q, want only rendered transcript", prepared.Messages[5].Content)
+	if !strings.Contains(prepared.Messages[4].Content, `"windows"`) || strings.Contains(prepared.Messages[4].Content, `"Mira"`) {
+		t.Fatalf("transcript message = %q, want only rendered transcript", prepared.Messages[4].Content)
+	}
+	for index, message := range prepared.Messages {
+		if index != 3 && strings.Contains(message.Content, `"Mira"`) {
+			t.Errorf("message %d unexpectedly rendered candidate input", index)
+		}
+		if index != 4 && strings.Contains(message.Content, `"windows"`) {
+			t.Errorf("message %d unexpectedly rendered transcript input", index)
+		}
 	}
 }

internal/modules/dnd/normalize/npcs/semantic_normalizer_test.go

@@ -136,17 +136,39 @@ func TestNormalizeInvalidStructuredOutputAndOperationalErrorsRemainDistinct(t *t
 	}
 }
 
-func TestNormalizeRejectsContextEncodingFailuresWithoutLeakingContent(t *testing.T) {
+func TestNormalizeRedactsContextMaterialFailures(t *testing.T) {
 	client := &recordingNPCNormalizerClient{}
 	normalizer := newNormalizer(t, client)
-	doc := semanticDocument()
-	doc.Units[0].Metadata = map[string]any{"invalid": math.NaN()}
-	input := dnd.NPCList{NPCs: []dnd.NPC{
-		{Name: "Mira", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
-		{Name: "Mira Thorn", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
+	const (
+		metadataKey   = "normalizer-sensitive-metadata-key"
+		metadataValue = "normalizer-sensitive-metadata-value"
+		sourceID      = "normalizer-sensitive-source-id"
+		originPath    = "file:///normalizer-sensitive-origin.json"
+		transcript    = "normalizer-sensitive-transcript"
+		firstName     = "Normalizer Sensitive"
+		secondName    = "Normalizer Sensitive Alias"
+	)
+	doc := &source.SourceDocument{ID: sourceID, Units: []source.SourceUnit{
+		{ID: 10, Kind: "speech", Text: transcript, Metadata: map[string]any{metadataKey: math.NaN(), "value": metadataValue}},
+		{ID: 20, Kind: "speech", Text: "other context"},
 	}}
-	if _, err := normalizer.Normalize(context.Background(), normalizeRequestWithSource(input, doc)); err == nil || !strings.Contains(err.Error(), "build semantic context") || strings.Contains(err.Error(), doc.Units[0].Text) || len(client.requests) != 0 {
-		t.Fatalf("Normalize() error = %v, calls = %d; want safe preparation error before completion", err, len(client.requests))
+	input := dnd.NPCList{NPCs: []dnd.NPC{
+		{Name: firstName, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
+		{Name: secondName, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
+	}}
+	request := normalizeRequestWithSource(input, doc)
+	request.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(transcript), "sha256:test", originPath)
+	_, err := normalizer.Normalize(context.Background(), request)
+	if err == nil || !strings.Contains(err.Error(), "build NPC normalization context: invalid source metadata") {
+		t.Fatalf("Normalize() error = %v; want content-safe context-material failure", err)
+	}
+	for _, forbidden := range []string{metadataKey, metadataValue, transcript, firstName, secondName, sourceID, originPath, "float64", "non-finite"} {
+		if strings.Contains(err.Error(), forbidden) {
+			t.Fatalf("Normalize() error leaked %q: %v", forbidden, err)
+		}
+	}
+	if len(client.requests) != 0 {
+		t.Fatalf("completion calls = %d, want context failure before completion", len(client.requests))
 	}
 }