Expose backend identity and capacity errors

internal/adapter/cli/run.go

@@ -148,7 +148,7 @@ func runCommand(args []string, stdout, stderr io.Writer) int {
 
 	res, runErr := engine.Run(context.Background(), req)
 	if runErr != nil {
-		fmt.Fprintf(stderr, "run error: %v\n", runErr)
+		fmt.Fprintln(stderr, runErrorMessage(runErr))
 		return ExitRuntimeError
 	}
 
@@ -732,9 +732,19 @@ func printSummary(stderr io.Writer, res *promptkit.RunResult) {
 	if res.Usage.CachedTokens != 0 || res.Usage.CacheWriteTokens != 0 {
 		fmt.Fprintf(stderr, " cached_tokens=%d cache_write_tokens=%d", res.Usage.CachedTokens, res.Usage.CacheWriteTokens)
 	}
+	if res.SelectedBackendID != "" {
+		fmt.Fprintf(stderr, " backend=%s", res.SelectedBackendID)
+	}
 	fmt.Fprintln(stderr)
 }
 
+func runErrorMessage(err error) string {
+	if errors.Is(err, promptkit.ErrCapacityExceeded) {
+		return "run error: model backend capacity is exhausted"
+	}
+	return fmt.Sprintf("run error: %v", err)
+}
+
 func printUsage(w io.Writer) {
 	fmt.Fprintln(w, "usage: scriptorium <run|render|serve> ...")
 	fmt.Fprintln(w, "  run:   scriptorium run [--config PATH] [--prompt-dir DIR] [--profile-dir DIR] --prompt ID [--prompt-version VERSION] [--input name=path] [--profile ID] [--session-id ID] [--llm-base-url URL] [--model NAME] [--api-key-env ENV] [--temperature N] [--max-tokens N] [--top-p N] [--reasoning-effort VALUE] [--var k=v] [--out path] [--timeout 10m]")

internal/adapter/cli/run_test.go

@@ -1033,13 +1033,16 @@ backends:
     queue_capacity: 0
 `, lib.promptDir, lib.profileDir))
 
-	code, _, stderr := runCLICommand(t, renderCommand, []string{
+	code, stdout, stderr := runCLICommand(t, renderCommand, []string{
 		"--config", configPath,
 		"--prompt", "custom",
 	})
 	if code != ExitOK {
 		t.Fatalf("expected ExitOK, got %d stderr=%q", code, stderr)
 	}
+	if !strings.Contains(stdout, "selected_backend_id: local-gpu") {
+		t.Fatalf("expected configured backend in prepared output, got:\n%s", stdout)
+	}
 }
 
 func TestRenderCommandMapsReasoningEffortAndSessionID(t *testing.T) {
@@ -1624,6 +1627,9 @@ func TestWriteOutputAndSummaryUseSeparateWriters(t *testing.T) {
 	if strings.Contains(stderr.String(), "cached_tokens=") || strings.Contains(stderr.String(), "cache_write_tokens=") {
 		t.Fatalf("expected zero cache usage to be omitted from summary, got %q", stderr.String())
 	}
+	if strings.Contains(stderr.String(), "backend=") {
+		t.Fatalf("expected endpoint-only backend to be omitted from summary, got %q", stderr.String())
+	}
 }
 
 func TestPrintSummaryIncludesCacheUsageWhenPresent(t *testing.T) {
@@ -1653,6 +1659,32 @@ func TestPrintSummaryIncludesCacheUsageWhenPresent(t *testing.T) {
 	if !strings.Contains(summary, "cached_tokens=0 cache_write_tokens=3") {
 		t.Fatalf("expected cache usage in summary, got %q", summary)
 	}
+	if strings.Contains(summary, "backend=") {
+		t.Fatalf("expected endpoint-only backend to be omitted from summary, got %q", summary)
+	}
+}
+
+func TestPrintSummaryIncludesBackendWhenPresent(t *testing.T) {
+	var stderr bytes.Buffer
+	printSummary(&stderr, &promptkit.RunResult{
+		PromptID:           "p",
+		PromptVersion:      "1",
+		SelectedProfileID:  "exec",
+		SelectedBackendID:  "local",
+		ModelName:          "m",
+		Validation:         promptkit.ValidationResult{Status: promptkit.ValidationPassed, Mode: promptkit.ValidationBasic},
+		RenderedPromptHash: "h",
+	})
+	if !strings.Contains(stderr.String(), "backend=local") {
+		t.Fatalf("expected backend in summary, got %q", stderr.String())
+	}
+}
+
+func TestRunErrorMessageDoesNotExposeCapacityDetails(t *testing.T) {
+	got := runErrorMessage(&promptkit.CapacityError{BackendID: "private-backend"})
+	if got != "run error: model backend capacity is exhausted" {
+		t.Fatalf("unexpected capacity diagnostic: %q", got)
+	}
 }
 
 type cliTestLibrary struct {