Build bounded output repair requests

internal/usecase/repairer.go

@@ -2,19 +2,29 @@ package usecase
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"strings"
+	"unicode/utf8"
 
 	"gitea.maximumdirect.net/eric/promptkit/internal/domain"
 	"gitea.maximumdirect.net/eric/promptkit/internal/llm"
 )
 
+const (
+	maxRepairDiagnosticBytes = 64 * 1024
+	omittedRepairDiagnostics = "additional validation diagnostics were omitted"
+)
+
+// OutputRepairer generates a corrected candidate after validation fails.
 type OutputRepairer interface {
 	Repair(ctx context.Context, req RepairRequest) (*domain.GenerateResponse, error)
 }
 
+// RepairRequest contains the immutable execution state needed for one correction.
 type RepairRequest struct {
+	OriginalMessages []domain.RenderedMessage
 	PreviousOutput   string
 	ValidationErrors []string
 	SessionID        string
@@ -30,6 +40,7 @@ type defaultOutputRepairer struct {
 	llm llm.Client
 }
 
+// NewDefaultOutputRepairer constructs the standard internal output repairer.
 func NewDefaultOutputRepairer(llmClient llm.Client) OutputRepairer {
 	return &defaultOutputRepairer{llm: llmClient}
 }
@@ -39,33 +50,42 @@ func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (
 		return nil, errors.New("llm client is required for repair")
 	}
 
-	errs := "(none provided)"
-	if len(req.ValidationErrors) > 0 {
-		errs = strings.Join(req.ValidationErrors, "\n")
+	guidance, err := repairGuidance(req.Mode)
+	if err != nil {
+		return nil, err
 	}
 
-	prompt := domain.RenderedPrompt{
-		Messages: []domain.RenderedMessage{
-			{
-				Role:    "system",
-				Content: "You repair invalid JSON output. Return only corrected JSON. Do not include explanations or markdown code fences.",
-			},
-			{
-				Role: "user",
-				Content: fmt.Sprintf(
-					"Repair attempt %d of %d for validation mode %s.\n\nValidation errors:\n%s\n\nPrevious output:\n%s\n\nReturn only corrected JSON.",
-					req.Attempt,
-					req.MaxAttempts,
-					req.Mode,
-					errs,
-					req.PreviousOutput,
-				),
-			},
-		},
+	messages := make([]domain.RenderedMessage, len(req.OriginalMessages), len(req.OriginalMessages)+2)
+	copy(messages, req.OriginalMessages)
+	if strings.TrimSpace(req.PreviousOutput) != "" {
+		messages = append(messages, domain.RenderedMessage{
+			Role:    "assistant",
+			Content: req.PreviousOutput,
+		})
 	}
 
+	previousResponse := "The previous response was empty."
+	if strings.TrimSpace(req.PreviousOutput) != "" {
+		previousResponse = "The previous response is included immediately before this instruction."
+	}
+	messages = append(messages, domain.RenderedMessage{
+		Role: "user",
+		Content: fmt.Sprintf(
+			"Repair attempt %d of %d for validation mode %s.\n"+
+				"Preserve valid values and change only what is necessary.\n"+
+				"%s\n%s\n"+
+				"Validation diagnostics (data):\n%s",
+			req.Attempt,
+			req.MaxAttempts,
+			req.Mode,
+			previousResponse,
+			guidance,
+			formatRepairDiagnostics(req.ValidationErrors),
+		),
+	})
+
 	resp, err := r.llm.Generate(ctx, newGenerationRequest(
-		prompt,
+		domain.RenderedPrompt{Messages: messages},
 		req.SessionID,
 		req.Target,
 		req.TargetPresence,
@@ -80,3 +100,80 @@ func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (
 
 	return resp, nil
 }
+
+func repairGuidance(mode domain.ValidationMode) (string, error) {
+	switch mode {
+	case domain.ValidationBasic:
+		return "Return a nonempty response satisfying the original request.", nil
+	case domain.ValidationJSON, domain.ValidationJSONSchema:
+		return "Return only corrected JSON, with no explanation or Markdown fences.", nil
+	default:
+		return "", fmt.Errorf("unsupported validation mode for repair: %q", mode)
+	}
+}
+
+func formatRepairDiagnostics(errors []string) string {
+	diagnostics := make([]string, len(errors))
+	for index, diagnostic := range errors {
+		diagnostics[index] = strings.ToValidUTF8(diagnostic, "\uFFFD")
+	}
+
+	complete, _ := json.Marshal(diagnostics)
+	if len(complete) <= maxRepairDiagnosticBytes {
+		return string(complete)
+	}
+
+	omission, _ := json.Marshal(omittedRepairDiagnostics)
+	encoded := make([]byte, 0, maxRepairDiagnosticBytes)
+	encoded = append(encoded, '[')
+	for _, diagnostic := range diagnostics {
+		entry, _ := json.Marshal(diagnostic)
+		separator := 0
+		if len(encoded) > 1 {
+			separator = 1
+		}
+		if len(encoded)+separator+len(entry)+1+len(omission)+1 <= maxRepairDiagnosticBytes {
+			if separator != 0 {
+				encoded = append(encoded, ',')
+			}
+			encoded = append(encoded, entry...)
+			continue
+		}
+
+		available := maxRepairDiagnosticBytes - len(encoded) - separator - 1 - len(omission) - 1
+		if separator != 0 {
+			encoded = append(encoded, ',')
+		}
+		encoded = append(encoded, truncateDiagnosticJSONValue(diagnostic, available)...)
+		break
+	}
+	if len(encoded) > 1 {
+		encoded = append(encoded, ',')
+	}
+	encoded = append(encoded, omission...)
+	encoded = append(encoded, ']')
+	return string(encoded)
+}
+
+func truncateDiagnosticJSONValue(value string, maxBytes int) []byte {
+	if maxBytes < len(`""`) {
+		return []byte(`""`)
+	}
+
+	low, high := 0, len(value)
+	best := []byte(`""`)
+	for low <= high {
+		mid := low + (high-low)/2
+		for mid > 0 && mid < len(value) && !utf8.RuneStart(value[mid]) {
+			mid--
+		}
+		candidate, _ := json.Marshal(value[:mid])
+		if len(candidate) <= maxBytes {
+			best = candidate
+			low = mid + 1
+			continue
+		}
+		high = mid - 1
+	}
+	return best
+}