Keep session IDs on repair requests and retire completed plans

internal/usecase/repairer.go

@@ -17,6 +17,7 @@ type OutputRepairer interface {
 type RepairRequest struct {
 	PreviousOutput   string
 	ValidationErrors []string
+	SessionID        string
 	Target           domain.ExecutionTarget
 	StructuredOutput *domain.StructuredOutputSpec
 	Attempt          int
@@ -42,23 +43,26 @@ func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (
 		errs = strings.Join(req.ValidationErrors, "\n")
 	}
 
-	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.",
+	prompt := domain.RenderedPrompt{
+		SessionID: req.SessionID,
+		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,
+				),
+			},
 		},
-		{
-			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,
-			),
-		},
-	}}
+	}
 
 	resp, err := r.llm.Generate(ctx, domain.GenerateRequest{
 		Prompt:           prompt,

internal/usecase/runner.go

@@ -127,6 +127,7 @@ func (r *Runner) Run(ctx context.Context, req domain.RunRequest) (*domain.RunRes
 			repairResp, repairErr := r.repairer.Repair(ctx, RepairRequest{
 				PreviousOutput:   genResp.Content,
 				ValidationErrors: validationResult.Errors,
+				SessionID:        prepared.SessionID,
 				Target:           prepared.EffectiveModelParams,
 				StructuredOutput: prepared.StructuredOutput,
 				Attempt:          attemptsUsed,

internal/usecase/runner_test.go

@@ -1690,6 +1690,41 @@ func TestRunnerRunStructuredRepairRemainsBoundedAndUsesEffectiveModelSettings(t
 	}
 }
 
+func TestRunnerRunRepairCarriesEffectiveSessionID(t *testing.T) {
+	llmClient := &fakeLLM{resp: &domain.GenerateResponse{Content: `{"broken":`}}
+	runner := NewRunnerWithRepairer(
+		&fakePromptRepo{def: promptDef(domain.FormatJSON, domain.ValidationJSON, 1)},
+		&fakeExecutionProfileRepo{profiles: map[string]*domain.ExecutionProfile{
+			"exec": {ID: "exec", Endpoint: "http://example.test/v1", Model: "model"},
+		}},
+		nil,
+		defaultArtifactReader(),
+		defaultRenderer(),
+		llmClient,
+		validate.NewStandardValidator("."),
+		NewDefaultOutputRepairer(llmClient),
+	)
+
+	result, err := runner.Run(context.Background(), domain.RunRequest{
+		PromptID:  "p",
+		ProfileID: "exec",
+		SessionID: " repair-session ",
+		Inputs:    singleInputRef(),
+	})
+	if err != nil {
+		t.Fatalf("expected no error, got %v", err)
+	}
+	if llmClient.calls != 2 {
+		t.Fatalf("expected initial generation and one repair, got %d calls", llmClient.calls)
+	}
+	if llmClient.lastReq.Prompt.SessionID != "repair-session" {
+		t.Fatalf("expected repair generation to retain effective session, got %q", llmClient.lastReq.Prompt.SessionID)
+	}
+	if result.SessionID != "repair-session" {
+		t.Fatalf("expected result to retain effective session, got %q", result.SessionID)
+	}
+}
+
 func TestRunnerRunJSONSchemaRepairCarriesStructuredOutputSpec(t *testing.T) {
 	def := promptDef(domain.FormatJSON, domain.ValidationJSONSchema, 1)
 	def.Validation.SchemaPath = "events.schema.json"