Add configurable transient retries for CLI execution

internal/adapter/cli/run_test.go

@@ -1258,6 +1258,81 @@ func TestPromptkitDefinitionsRenderThroughCLI(t *testing.T) {
 	}
 }
 
+func TestTransientRetrySettingsAndCLIOverride(t *testing.T) {
+	lib := newCLITestLibrary(t)
+	inputPath := lib.writeInputFile(t, "transcript.md", "hello")
+	writePromptFile(t, lib.promptDir, "retry.prompt", "local-default")
+	var hits int32
+	provider := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if atomic.AddInt32(&hits, 1) == 1 {
+			http.Error(w, "temporary", http.StatusServiceUnavailable)
+			return
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"role":"assistant","content":"recovered"}}]}`))
+	}))
+	defer provider.Close()
+	writeProfileFile(t, lib.profileDir, "local-default", provider.URL+"/v1", "local-model")
+	configPath := writeAppConfigFile(t, fmt.Sprintf("prompt_dir: %q\nprofile_dir: %q\ntransient_retries: 1\n", lib.promptDir, lib.profileDir))
+	args := []string{"--config", configPath, "--prompt", "retry.prompt", "--input", "transcript=" + inputPath}
+
+	serve, err := parseServeArgs([]string{"--config", configPath})
+	if err != nil || serve.transientRetries == nil || *serve.transientRetries != 1 {
+		t.Fatalf("server did not inherit retry setting: cfg=%+v err=%v", serve, err)
+	}
+	if _, err := newEngine(serve.engineSettings()); err != nil {
+		t.Fatalf("server engine configuration: %v", err)
+	}
+
+	code, stdout, stderr := runCLICommand(t, runCommand, args)
+	if code != ExitOK || stdout != "recovered" || atomic.LoadInt32(&hits) != 2 {
+		t.Fatalf("configured retry was not applied: code=%d stdout=%q stderr=%q hits=%d", code, stdout, stderr, atomic.LoadInt32(&hits))
+	}
+	atomic.StoreInt32(&hits, 0)
+	code, stdout, stderr = runCLICommand(t, runCommand, append(append([]string{}, args...), "--transient-retries", "0"))
+	if code != ExitRuntimeError || stdout != "" || atomic.LoadInt32(&hits) != 1 {
+		t.Fatalf("explicit zero did not override configuration: code=%d stdout=%q stderr=%q hits=%d", code, stdout, stderr, atomic.LoadInt32(&hits))
+	}
+
+	for _, tc := range []struct {
+		name string
+		args []string
+		want *int
+	}{
+		{name: "omitted", args: args},
+		{name: "zero", args: append(append([]string{}, args...), "--transient-retries", "0"), want: intPointer(0)},
+		{name: "positive", args: append(append([]string{}, args...), "--transient-retries", "3"), want: intPointer(3)},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			cfg, err := parseRunArgs(tc.args)
+			if err != nil {
+				t.Fatal(err)
+			}
+			req, err := buildRunRequestFromConfig(cfg)
+			if err != nil {
+				t.Fatal(err)
+			}
+			if !reflect.DeepEqual(req.TransientRetries, tc.want) {
+				t.Fatalf("request retry override: got %v, want %v", req.TransientRetries, tc.want)
+			}
+		})
+	}
+	for _, invalid := range []string{"-1", "wrong"} {
+		if _, err := parseRunArgs(append(append([]string{}, args...), "--transient-retries", invalid)); err == nil {
+			t.Fatalf("run accepted invalid retry count %q", invalid)
+		}
+		if _, err := parseRenderArgs(append(append([]string{}, args...), "--transient-retries", invalid)); err == nil {
+			t.Fatalf("render accepted invalid retry count %q", invalid)
+		}
+	}
+	code, stdout, stderr = runCLICommand(t, renderCommand, append(append([]string{}, args...), "--transient-retries", "0", "--format", "json"))
+	if code != ExitOK || strings.Contains(stdout, "transient_retries") {
+		t.Fatalf("render retry override changed prepared output: code=%d stdout=%q stderr=%q", code, stdout, stderr)
+	}
+}
+
+func intPointer(value int) *int { return &value }
+
 func TestPromptkitPromptInspectionSelectsVersionsAndContracts(t *testing.T) {
 	fixtureRoot := definitionFixtureRoot(t)
 	configPath := writeDefinitionFixtureConfig(t, fixtureRoot, true)