Merge branch 'master' of https://github.com/n8n-io/n8n into node-2015-google-calendar-confusing-errors

packages/cli/src/credentials/credentials.service.ee.ts

@@ -87,7 +87,7 @@ export class EnterpriseCredentialsService {
 		if (credential) {
 			// Decrypt the data if we found the credential with the `credential:update`
 			// scope.
-			decryptedData = this.credentialsService.decrypt(credential);
+			decryptedData = this.credentialsService.decrypt(credential, true);
 		} else {
 			// Otherwise try to find them with only the `credential:read` scope. In
 			// that case we return them without the decrypted data.

packages/cli/src/credentials/credentials.service.ts

@@ -542,7 +542,7 @@ export class CredentialsService {
 		if (sharing) {
 			// Decrypt the data if we found the credential with the `credential:update`
 			// scope.
-			decryptedData = this.decrypt(sharing.credentials);
+			decryptedData = this.decrypt(sharing.credentials, true);
 		} else {
 			// Otherwise try to find them with only the `credential:read` scope. In
 			// that case we return them without the decrypted data.

packages/cli/src/databases/entities/test-definition.ee.ts

@@ -9,7 +9,8 @@ import { jsonColumnType, WithTimestampsAndStringId } from './abstract-entity';
 
 // Entity representing a node in a workflow under test, for which data should be mocked during test execution
 export type MockedNodeItem = {
-	name: string;
+	name?: string;
+	id: string;
 };
 
 /**

packages/cli/src/evaluation.ee/test-definition.schema.ts

@@ -16,6 +16,6 @@ export const testDefinitionPatchRequestBodySchema = z
 		description: z.string().optional(),
 		evaluationWorkflowId: z.string().min(1).optional(),
 		annotationTagId: z.string().min(1).optional(),
-		mockedNodes: z.array(z.object({ name: z.string() })).optional(),
+		mockedNodes: z.array(z.object({ id: z.string(), name: z.string() })).optional(),
 	})
 	.strict();

packages/cli/src/evaluation.ee/test-definition.service.ee.ts

@@ -121,13 +121,26 @@ export class TestDefinitionService {
 				relations: ['workflow'],
 			});
 
-			const existingNodeNames = new Set(existingTestDefinition.workflow.nodes.map((n) => n.name));
+			const existingNodeNames = new Map(
+				existingTestDefinition.workflow.nodes.map((n) => [n.name, n]),
+			);
+			const existingNodeIds = new Map(existingTestDefinition.workflow.nodes.map((n) => [n.id, n]));
 
 			attrs.mockedNodes.forEach((node) => {
-				if (!existingNodeNames.has(node.name)) {
-					throw new BadRequestError(`Pinned node not found in the workflow: ${node.name}`);
+				if (!existingNodeIds.has(node.id) || (node.name && !existingNodeNames.has(node.name))) {
+					throw new BadRequestError(
+						`Pinned node not found in the workflow: ${node.id} (${node.name})`,
+					);
 				}
 			});
+
+			// Update the node names OR node ids if they are not provided
+			attrs.mockedNodes = attrs.mockedNodes.map((node) => {
+				return {
+					id: node.id ?? (node.name && existingNodeNames.get(node.name)?.id),
+					name: node.name ?? (node.id && existingNodeIds.get(node.id)?.name),
+				};
+			});
 		}
 
 		// Update the test definition

packages/cli/src/evaluation.ee/test-runner/__tests__/create-pin-data.ee.test.ts

@@ -7,13 +7,24 @@ const wfUnderTestJson = JSON.parse(
 	readFileSync(path.join(__dirname, './mock-data/workflow.under-test.json'), { encoding: 'utf-8' }),
 );
 
+const wfUnderTestRenamedNodesJson = JSON.parse(
+	readFileSync(path.join(__dirname, './mock-data/workflow.under-test-renamed-nodes.json'), {
+		encoding: 'utf-8',
+	}),
+);
+
 const executionDataJson = JSON.parse(
 	readFileSync(path.join(__dirname, './mock-data/execution-data.json'), { encoding: 'utf-8' }),
 );
 
 describe('createPinData', () => {
 	test('should create pin data from past execution data', () => {
-		const mockedNodes = ['When clicking ‘Test workflow’'].map((name) => ({ name }));
+		const mockedNodes = [
+			{
+				id: '72256d90-3a67-4e29-b032-47df4e5768af',
+				name: 'When clicking ‘Test workflow’',
+			},
+		];
 
 		const pinData = createPinData(wfUnderTestJson, mockedNodes, executionDataJson);
 
@@ -25,7 +36,7 @@ describe('createPinData', () => {
 	});
 
 	test('should not create pin data for non-existing mocked nodes', () => {
-		const mockedNodes = ['Non-existing node'].map((name) => ({ name }));
+		const mockedNodes = ['non-existing-ID'].map((id) => ({ id }));
 
 		const pinData = createPinData(wfUnderTestJson, mockedNodes, executionDataJson);
 
@@ -33,9 +44,17 @@ describe('createPinData', () => {
 	});
 
 	test('should create pin data for all mocked nodes', () => {
-		const mockedNodes = ['When clicking ‘Test workflow’', 'Edit Fields', 'Code'].map((name) => ({
-			name,
-		}));
+		const mockedNodes = [
+			{
+				id: '72256d90-3a67-4e29-b032-47df4e5768af', // 'When clicking ‘Test workflow’'
+			},
+			{
+				id: '319f29bc-1dd4-4122-b223-c584752151a4', // 'Edit Fields'
+			},
+			{
+				id: 'd2474215-63af-40a4-a51e-0ea30d762621', // 'Code'
+			},
+		];
 
 		const pinData = createPinData(wfUnderTestJson, mockedNodes, executionDataJson);
 
@@ -53,4 +72,33 @@ describe('createPinData', () => {
 
 		expect(pinData).toEqual({});
 	});
+
+	test('should create pin data for all mocked nodes with renamed nodes', () => {
+		const mockedNodes = [
+			{
+				id: '72256d90-3a67-4e29-b032-47df4e5768af', // 'Manual Run'
+			},
+			{
+				id: '319f29bc-1dd4-4122-b223-c584752151a4', // 'Set Attribute'
+			},
+			{
+				id: 'd2474215-63af-40a4-a51e-0ea30d762621', // 'Code'
+			},
+		];
+
+		const pinData = createPinData(
+			wfUnderTestRenamedNodesJson,
+			mockedNodes,
+			executionDataJson,
+			wfUnderTestJson, // Pass original workflow JSON as pastWorkflowData
+		);
+
+		expect(pinData).toEqual(
+			expect.objectContaining({
+				'Manual Run': expect.anything(),
+				'Set Attribute': expect.anything(),
+				Code: expect.anything(),
+			}),
+		);
+	});
 });

packages/cli/src/evaluation.ee/test-runner/__tests__/mock-data/workflow.under-test-renamed-nodes.json

@@ -0,0 +1,78 @@
+{
+	"name": "Workflow Under Test",
+	"nodes": [
+		{
+			"parameters": {},
+			"type": "n8n-nodes-base.manualTrigger",
+			"typeVersion": 1,
+			"position": [-80, 0],
+			"id": "72256d90-3a67-4e29-b032-47df4e5768af",
+			"name": "Manual Run"
+		},
+		{
+			"parameters": {
+				"assignments": {
+					"assignments": [
+						{
+							"id": "acfeecbe-443c-4220-b63b-d44d69216902",
+							"name": "foo",
+							"value": "bar",
+							"type": "string"
+						}
+					]
+				},
+				"options": {}
+			},
+			"type": "n8n-nodes-base.set",
+			"typeVersion": 3.4,
+			"position": [140, 0],
+			"id": "319f29bc-1dd4-4122-b223-c584752151a4",
+			"name": "Set Attribute"
+		},
+		{
+			"parameters": {
+				"jsCode": "for (const item of $input.all()) {\n  item.json.random = Math.random();\n}\n\nreturn $input.all();"
+			},
+			"type": "n8n-nodes-base.code",
+			"typeVersion": 2,
+			"position": [380, 0],
+			"id": "d2474215-63af-40a4-a51e-0ea30d762621",
+			"name": "Code"
+		}
+	],
+	"connections": {
+		"Manual Run": {
+			"main": [
+				[
+					{
+						"node": "Set attribute",
+						"type": "main",
+						"index": 0
+					}
+				]
+			]
+		},
+		"Set attribute": {
+			"main": [
+				[
+					{
+						"node": "Wait",
+						"type": "main",
+						"index": 0
+					}
+				]
+			]
+		},
+		"Wait": {
+			"main": [
+				[
+					{
+						"node": "Code",
+						"type": "main",
+						"index": 0
+					}
+				]
+			]
+		}
+	}
+}

packages/cli/src/evaluation.ee/test-runner/__tests__/test-runner.service.ee.test.ts

@@ -27,6 +27,12 @@ const wfUnderTestJson = JSON.parse(
 	readFileSync(path.join(__dirname, './mock-data/workflow.under-test.json'), { encoding: 'utf-8' }),
 );
 
+const wfUnderTestRenamedNodesJson = JSON.parse(
+	readFileSync(path.join(__dirname, './mock-data/workflow.under-test-renamed-nodes.json'), {
+		encoding: 'utf-8',
+	}),
+);
+
 const wfEvaluationJson = JSON.parse(
 	readFileSync(path.join(__dirname, './mock-data/workflow.evaluation.json'), { encoding: 'utf-8' }),
 );
@@ -60,6 +66,7 @@ const executionMocks = [
 		status: 'success',
 		executionData: {
 			data: stringify(executionDataJson),
+			workflowData: wfUnderTestJson,
 		},
 	}),
 	mock<ExecutionEntity>({
@@ -68,6 +75,7 @@ const executionMocks = [
 		status: 'success',
 		executionData: {
 			data: stringify(executionDataJson),
+			workflowData: wfUnderTestRenamedNodesJson,
 		},
 	}),
 ];
@@ -250,7 +258,7 @@ describe('TestRunnerService', () => {
 			mock<TestDefinition>({
 				workflowId: 'workflow-under-test-id',
 				evaluationWorkflowId: 'evaluation-workflow-id',
-				mockedNodes: [{ name: 'When clicking ‘Test workflow’' }],
+				mockedNodes: [{ id: '72256d90-3a67-4e29-b032-47df4e5768af' }],
 			}),
 		);
 
@@ -347,7 +355,7 @@ describe('TestRunnerService', () => {
 			mock<TestDefinition>({
 				workflowId: 'workflow-under-test-id',
 				evaluationWorkflowId: 'evaluation-workflow-id',
-				mockedNodes: [{ name: 'When clicking ‘Test workflow’' }],
+				mockedNodes: [{ id: '72256d90-3a67-4e29-b032-47df4e5768af' }],
 			}),
 		);
 

packages/cli/src/evaluation.ee/test-runner/test-runner.service.ee.ts

@@ -1,13 +1,14 @@
 import { Service } from '@n8n/di';
 import { parse } from 'flatted';
+import { NodeConnectionType, Workflow } from 'n8n-workflow';
 import type {
 	IDataObject,
 	IRun,
 	IRunData,
 	IRunExecutionData,
+	IWorkflowBase,
 	IWorkflowExecutionDataProcess,
 } from 'n8n-workflow';
-import { NodeConnectionType, Workflow } from 'n8n-workflow';
 import assert from 'node:assert';
 
 import { ActiveExecutions } from '@/active-executions';
@@ -94,11 +95,17 @@ export class TestRunnerService {
 	private async runTestCase(
 		workflow: WorkflowEntity,
 		pastExecutionData: IRunExecutionData,
+		pastExecutionWorkflowData: IWorkflowBase,
 		mockedNodes: MockedNodeItem[],
 		userId: string,
 	): Promise<IRun | undefined> {
 		// Create pin data from the past execution data
-		const pinData = createPinData(workflow, mockedNodes, pastExecutionData);
+		const pinData = createPinData(
+			workflow,
+			mockedNodes,
+			pastExecutionData,
+			pastExecutionWorkflowData,
+		);
 
 		// Prepare the data to run the workflow
 		const data: IWorkflowExecutionDataProcess = {
@@ -127,6 +134,7 @@ export class TestRunnerService {
 		evaluationWorkflow: WorkflowEntity,
 		expectedData: IRunData,
 		actualData: IRunData,
+		testRunId?: string,
 	) {
 		// Prepare the evaluation wf input data.
 		// Provide both the expected data and the actual data
@@ -139,7 +147,13 @@ export class TestRunnerService {
 
 		// Prepare the data to run the evaluation workflow
 		const data = await getRunData(evaluationWorkflow, [evaluationInputData]);
-
+		// FIXME: This is a hack to add the testRunId to the evaluation workflow execution data
+		// So that we can fetch all execution runs for a test run
+		if (testRunId && data.executionData) {
+			data.executionData.resultData.metadata = {
+				testRunId,
+			};
+		}
 		data.executionMode = 'evaluation';
 
 		// Trigger the evaluation workflow
@@ -235,6 +249,7 @@ export class TestRunnerService {
 			const testCaseExecution = await this.runTestCase(
 				workflow,
 				executionData,
+				pastExecution.executionData.workflowData,
 				test.mockedNodes,
 				user.id,
 			);
@@ -256,10 +271,9 @@ export class TestRunnerService {
 				evaluationWorkflow,
 				originalRunData,
 				testCaseRunData,
+				testRun.id,
 			);
 			assert(evalExecution);
-
-			// Extract the output of the last node executed in the evaluation workflow
 			metrics.addResults(this.extractEvaluationResult(evalExecution));
 		}
 

packages/cli/src/evaluation.ee/test-runner/utils.ee.ts

@@ -1,4 +1,5 @@
-import type { IRunExecutionData, IPinData } from 'n8n-workflow';
+import assert from 'assert';
+import type { IRunExecutionData, IPinData, IWorkflowBase } from 'n8n-workflow';
 
 import type { MockedNodeItem } from '@/databases/entities/test-definition.ee';
 import type { WorkflowEntity } from '@/databases/entities/workflow-entity';
@@ -13,16 +14,33 @@ export function createPinData(
 	workflow: WorkflowEntity,
 	mockedNodes: MockedNodeItem[],
 	executionData: IRunExecutionData,
+	pastWorkflowData?: IWorkflowBase,
 ) {
 	const pinData = {} as IPinData;
 
-	const workflowNodeNames = new Set(workflow.nodes.map((node) => node.name));
+	const workflowNodeIds = new Map(workflow.nodes.map((node) => [node.id, node.name]));
+
+	// If the past workflow data is provided, use it to create a map between node IDs and node names
+	const pastWorkflowNodeIds = new Map<string, string>();
+	if (pastWorkflowData) {
+		for (const node of pastWorkflowData.nodes) {
+			pastWorkflowNodeIds.set(node.id, node.name);
+		}
+	}
 
 	for (const mockedNode of mockedNodes) {
-		if (workflowNodeNames.has(mockedNode.name)) {
-			const nodeData = executionData.resultData.runData[mockedNode.name];
+		assert(mockedNode.id, 'Mocked node ID is missing');
+
+		const nodeName = workflowNodeIds.get(mockedNode.id);
+
+		// If mocked node is still present in the workflow
+		if (nodeName) {
+			// Try to restore node name from past execution data (it might have been renamed between past execution and up-to-date workflow)
+			const pastNodeName = pastWorkflowNodeIds.get(mockedNode.id) ?? nodeName;
+			const nodeData = executionData.resultData.runData[pastNodeName];
+
 			if (nodeData?.[0]?.data?.main?.[0]) {
-				pinData[mockedNode.name] = nodeData[0]?.data?.main?.[0];
+				pinData[nodeName] = nodeData[0]?.data?.main?.[0];
 			}
 		}
 	}

packages/cli/test/integration/credentials/credentials.api.ee.test.ts

@@ -2,6 +2,7 @@ import { Container } from '@n8n/di';
 import { In } from '@n8n/typeorm';
 
 import config from '@/config';
+import { CredentialsService } from '@/credentials/credentials.service';
 import type { Project } from '@/databases/entities/project';
 import type { ProjectRole } from '@/databases/entities/project-relation';
 import type { User } from '@/databases/entities/user';
@@ -555,6 +556,22 @@ describe('GET /credentials/:id', () => {
 		expect(secondCredential.data).toBeDefined();
 	});
 
+	test('should not redact the data when `includeData:true` is passed', async () => {
+		const credentialService = Container.get(CredentialsService);
+		const redactSpy = jest.spyOn(credentialService, 'redact');
+		const savedCredential = await saveCredential(randomCredentialPayload(), {
+			user: owner,
+		});
+
+		const response = await authOwnerAgent
+			.get(`/credentials/${savedCredential.id}`)
+			.query({ includeData: true });
+
+		validateMainCredentialData(response.body.data);
+		expect(response.body.data.data).toBeDefined();
+		expect(redactSpy).not.toHaveBeenCalled();
+	});
+
 	test('should retrieve non-owned cred for owner', async () => {
 		const [member1, member2] = await createManyUsers(2, {
 			role: 'global:member',

packages/cli/test/integration/credentials/credentials.api.test.ts

@@ -4,6 +4,7 @@ import type { Scope } from '@sentry/node';
 import { Credentials } from 'n8n-core';
 import { randomString } from 'n8n-workflow';
 
+import { CredentialsService } from '@/credentials/credentials.service';
 import type { Project } from '@/databases/entities/project';
 import type { User } from '@/databases/entities/user';
 import { CredentialsRepository } from '@/databases/repositories/credentials.repository';
@@ -1272,6 +1273,23 @@ describe('GET /credentials/:id', () => {
 		expect(secondResponse.body.data.data).toBeDefined();
 	});
 
+	test('should not redact the data when `includeData:true` is passed', async () => {
+		const credentialService = Container.get(CredentialsService);
+		const redactSpy = jest.spyOn(credentialService, 'redact');
+		const savedCredential = await saveCredential(randomCredentialPayload(), {
+			user: owner,
+			role: 'credential:owner',
+		});
+
+		const response = await authOwnerAgent
+			.get(`/credentials/${savedCredential.id}`)
+			.query({ includeData: true });
+
+		validateMainCredentialData(response.body.data);
+		expect(response.body.data.data).toBeDefined();
+		expect(redactSpy).not.toHaveBeenCalled();
+	});
+
 	test('should retrieve owned cred for member', async () => {
 		const savedCredential = await saveCredential(randomCredentialPayload(), {
 			user: member,

packages/cli/test/integration/evaluation/test-definitions.api.test.ts

@@ -405,13 +405,14 @@ describe('PATCH /evaluation/test-definitions/:id', () => {
 		const resp = await authOwnerAgent.patch(`/evaluation/test-definitions/${newTest.id}`).send({
 			mockedNodes: [
 				{
+					id: 'uuid-1234',
 					name: 'Schedule Trigger',
 				},
 			],
 		});
 
 		expect(resp.statusCode).toBe(200);
-		expect(resp.body.data.mockedNodes).toEqual([{ name: 'Schedule Trigger' }]);
+		expect(resp.body.data.mockedNodes).toEqual([{ id: 'uuid-1234', name: 'Schedule Trigger' }]);
 	});
 
 	test('should return error if pinned nodes are invalid', async () => {

packages/design-system/src/components/N8nSelect/Select.vue

@@ -31,6 +31,10 @@ const props = defineProps({
 	multiple: {
 		type: Boolean,
 	},
+	multipleLimit: {
+		type: Number,
+		default: 0,
+	},
 	filterMethod: {
 		type: Function,
 	},
@@ -120,6 +124,7 @@ defineExpose({
 		<ElSelect
 			v-bind="{ ...$props, ...listeners }"
 			ref="innerSelect"
+			:multiple-limit="props.multipleLimit"
 			:model-value="props.modelValue ?? undefined"
 			:size="computedSize"
 			:popper-class="props.popperClass"

packages/editor-ui/src/api/testDefinition.ee.ts

@@ -1,5 +1,6 @@
 import type { IRestApiContext } from '@/Interface';
-import { makeRestApiRequest } from '@/utils/apiUtils';
+import { makeRestApiRequest, request } from '@/utils/apiUtils';
+
 export interface TestDefinitionRecord {
 	id: string;
 	name: string;
@@ -9,7 +10,10 @@ export interface TestDefinitionRecord {
 	description?: string | null;
 	updatedAt?: string;
 	createdAt?: string;
+	annotationTag?: string | null;
+	mockedNodes?: Array<{ name: string }>;
 }
+
 interface CreateTestDefinitionParams {
 	name: string;
 	workflowId: string;
@@ -21,31 +25,63 @@ export interface UpdateTestDefinitionParams {
 	evaluationWorkflowId?: string | null;
 	annotationTagId?: string | null;
 	description?: string | null;
+	mockedNodes?: Array<{ name: string }>;
 }
+
 export interface UpdateTestResponse {
 	createdAt: string;
 	updatedAt: string;
 	id: string;
 	name: string;
 	workflowId: string;
-	description: string | null;
-	annotationTag: string | null;
-	evaluationWorkflowId: string | null;
-	annotationTagId: string | null;
+	description?: string | null;
+	annotationTag?: string | null;
+	evaluationWorkflowId?: string | null;
+	annotationTagId?: string | null;
+}
+
+export interface TestRunRecord {
+	id: string;
+	testDefinitionId: string;
+	status: 'new' | 'running' | 'completed' | 'error';
+	metrics?: Record<string, number>;
+	createdAt: string;
+	updatedAt: string;
+	runAt: string;
+	completedAt: string;
+}
+
+interface GetTestRunParams {
+	testDefinitionId: string;
+	runId: string;
+}
+
+interface DeleteTestRunParams {
+	testDefinitionId: string;
+	runId: string;
 }
 
 const endpoint = '/evaluation/test-definitions';
+const getMetricsEndpoint = (testDefinitionId: string, metricId?: string) =>
+	`${endpoint}/${testDefinitionId}/metrics${metricId ? `/${metricId}` : ''}`;
 
-export async function getTestDefinitions(context: IRestApiContext) {
+export async function getTestDefinitions(
+	context: IRestApiContext,
+	params?: { workflowId?: string },
+) {
+	let url = endpoint;
+	if (params?.workflowId) {
+		url += `?filter=${JSON.stringify({ workflowId: params.workflowId })}`;
+	}
 	return await makeRestApiRequest<{ count: number; testDefinitions: TestDefinitionRecord[] }>(
 		context,
 		'GET',
-		endpoint,
+		url,
 	);
 }
 
 export async function getTestDefinition(context: IRestApiContext, id: string) {
-	return await makeRestApiRequest<{ id: string }>(context, 'GET', `${endpoint}/${id}`);
+	return await makeRestApiRequest<TestDefinitionRecord>(context, 'GET', `${endpoint}/${id}`);
 }
 
 export async function createTestDefinition(
@@ -71,3 +107,125 @@ export async function updateTestDefinition(
 export async function deleteTestDefinition(context: IRestApiContext, id: string) {
 	return await makeRestApiRequest<{ success: boolean }>(context, 'DELETE', `${endpoint}/${id}`);
 }
+
+// Metrics
+export interface TestMetricRecord {
+	id: string;
+	name: string;
+	testDefinitionId: string;
+	createdAt?: string;
+	updatedAt?: string;
+}
+
+export interface CreateTestMetricParams {
+	testDefinitionId: string;
+	name: string;
+}
+
+export interface UpdateTestMetricParams {
+	name: string;
+	id: string;
+	testDefinitionId: string;
+}
+
+export interface DeleteTestMetricParams {
+	testDefinitionId: string;
+	id: string;
+}
+
+export const getTestMetrics = async (context: IRestApiContext, testDefinitionId: string) => {
+	return await makeRestApiRequest<TestMetricRecord[]>(
+		context,
+		'GET',
+		getMetricsEndpoint(testDefinitionId),
+	);
+};
+
+export const getTestMetric = async (
+	context: IRestApiContext,
+	testDefinitionId: string,
+	id: string,
+) => {
+	return await makeRestApiRequest<TestMetricRecord>(
+		context,
+		'GET',
+		getMetricsEndpoint(testDefinitionId, id),
+	);
+};
+
+export const createTestMetric = async (
+	context: IRestApiContext,
+	params: CreateTestMetricParams,
+) => {
+	return await makeRestApiRequest<TestMetricRecord>(
+		context,
+		'POST',
+		getMetricsEndpoint(params.testDefinitionId),
+		{ name: params.name },
+	);
+};
+
+export const updateTestMetric = async (
+	context: IRestApiContext,
+	params: UpdateTestMetricParams,
+) => {
+	return await makeRestApiRequest<TestMetricRecord>(
+		context,
+		'PATCH',
+		getMetricsEndpoint(params.testDefinitionId, params.id),
+		{ name: params.name },
+	);
+};
+
+export const deleteTestMetric = async (
+	context: IRestApiContext,
+	params: DeleteTestMetricParams,
+) => {
+	return await makeRestApiRequest(
+		context,
+		'DELETE',
+		getMetricsEndpoint(params.testDefinitionId, params.id),
+	);
+};
+
+const getRunsEndpoint = (testDefinitionId: string, runId?: string) =>
+	`${endpoint}/${testDefinitionId}/runs${runId ? `/${runId}` : ''}`;
+
+// Get all test runs for a test definition
+export const getTestRuns = async (context: IRestApiContext, testDefinitionId: string) => {
+	return await makeRestApiRequest<TestRunRecord[]>(
+		context,
+		'GET',
+		getRunsEndpoint(testDefinitionId),
+	);
+};
+
+// Get specific test run
+export const getTestRun = async (context: IRestApiContext, params: GetTestRunParams) => {
+	return await makeRestApiRequest<TestRunRecord>(
+		context,
+		'GET',
+		getRunsEndpoint(params.testDefinitionId, params.runId),
+	);
+};
+
+// Start a new test run
+export const startTestRun = async (context: IRestApiContext, testDefinitionId: string) => {
+	const response = await request({
+		method: 'POST',
+		baseURL: context.baseUrl,
+		endpoint: `${endpoint}/${testDefinitionId}/run`,
+		headers: { 'push-ref': context.pushRef },
+	});
+	// CLI is returning the response without wrapping it in `data` key
+	return response as { success: boolean };
+};
+
+// Delete a test run
+export const deleteTestRun = async (context: IRestApiContext, params: DeleteTestRunParams) => {
+	return await makeRestApiRequest<{ success: boolean }>(
+		context,
+		'DELETE',
+		getRunsEndpoint(params.testDefinitionId, params.runId),
+	);
+};

packages/editor-ui/src/components/MainHeader/MainHeader.vue

@@ -43,6 +43,25 @@ const executionToReturnTo = ref('');
 const dirtyState = ref(false);
 const githubButtonHidden = useLocalStorage(LOCAL_STORAGE_HIDE_GITHUB_STAR_BUTTON, false);
 
+// Track the routes that are used for the tabs
+// This is used to determine which tab to show when the route changes
+// TODO: It might be easier to manage this in the router config, by passing meta information to the routes
+// This would allow us to specify it just once on the root route, and then have the tabs be determined for children
+const testDefinitionRoutes: VIEWS[] = [
+	VIEWS.TEST_DEFINITION,
+	VIEWS.TEST_DEFINITION_EDIT,
+	VIEWS.TEST_DEFINITION_RUNS,
+	VIEWS.TEST_DEFINITION_RUNS_DETAIL,
+	VIEWS.TEST_DEFINITION_RUNS_COMPARE,
+];
+
+const workflowRoutes: VIEWS[] = [VIEWS.WORKFLOW, VIEWS.NEW_WORKFLOW, VIEWS.EXECUTION_DEBUG];
+
+const executionRoutes: VIEWS[] = [
+	VIEWS.EXECUTION_HOME,
+	VIEWS.WORKFLOW_EXECUTIONS,
+	VIEWS.EXECUTION_PREVIEW,
+];
 const tabBarItems = computed(() => {
 	const items = [
 		{ value: MAIN_HEADER_TABS.WORKFLOW, label: locale.baseText('generic.editor') },
@@ -92,24 +111,30 @@ onMounted(async () => {
 	syncTabsWithRoute(route);
 });
 
+function isViewRoute(name: unknown): name is VIEWS {
+	return (
+		typeof name === 'string' &&
+		[testDefinitionRoutes, workflowRoutes, executionRoutes].flat().includes(name as VIEWS)
+	);
+}
+
 function syncTabsWithRoute(to: RouteLocation, from?: RouteLocation): void {
-	if (to.matched.some((record) => record.name === VIEWS.TEST_DEFINITION)) {
-		activeHeaderTab.value = MAIN_HEADER_TABS.TEST_DEFINITION;
-	}
-	if (
-		to.name === VIEWS.EXECUTION_HOME ||
-		to.name === VIEWS.WORKFLOW_EXECUTIONS ||
-		to.name === VIEWS.EXECUTION_PREVIEW
-	) {
-		activeHeaderTab.value = MAIN_HEADER_TABS.EXECUTIONS;
-	} else if (
-		to.name === VIEWS.WORKFLOW ||
-		to.name === VIEWS.NEW_WORKFLOW ||
-		to.name === VIEWS.EXECUTION_DEBUG
-	) {
-		activeHeaderTab.value = MAIN_HEADER_TABS.WORKFLOW;
+	// Map route types to their corresponding tab in the header
+	const routeTabMapping = [
+		{ routes: testDefinitionRoutes, tab: MAIN_HEADER_TABS.TEST_DEFINITION },
+		{ routes: executionRoutes, tab: MAIN_HEADER_TABS.EXECUTIONS },
+		{ routes: workflowRoutes, tab: MAIN_HEADER_TABS.WORKFLOW },
+	];
+
+	// Update the active tab based on the current route
+	if (to.name && isViewRoute(to.name)) {
+		const matchingTab = routeTabMapping.find(({ routes }) => routes.includes(to.name as VIEWS));
+		if (matchingTab) {
+			activeHeaderTab.value = matchingTab.tab;
+		}
 	}
 
+	// Store the current workflow ID, but only if it's not a new workflow
 	if (to.params.name !== 'new' && typeof to.params.name === 'string') {
 		workflowToReturnTo.value = to.params.name;
 	}

packages/editor-ui/src/components/Projects/ProjectNavigation.vue

@@ -122,7 +122,7 @@ const showAddFirstProject = computed(
 				},
 			]"
 			:disabled="isCreatingProject"
-			type="tertiary"
+			type="secondary"
 			icon="plus"
 			data-test-id="add-first-project-button"
 			@click="globalEntityCreation.createProject"
@@ -187,7 +187,6 @@ const showAddFirstProject = computed(
 }
 
 .addFirstProjectBtn {
-	border: 1px solid var(--color-background-dark);
 	font-size: var(--font-size-xs);
 	padding: var(--spacing-3xs);
 	margin: 0 var(--spacing-m) var(--spacing-m);

packages/editor-ui/src/components/TagsDropdown.vue

@@ -16,7 +16,10 @@ interface TagsDropdownProps {
 	allTags: ITag[];
 	isLoading: boolean;
 	tagsById: Record<string, ITag>;
+	createEnabled?: boolean;
+	manageEnabled?: boolean;
 	createTag?: (name: string) => Promise<ITag>;
+	multipleLimit?: number;
 }
 
 const i18n = useI18n();
@@ -27,6 +30,10 @@ const props = withDefaults(defineProps<TagsDropdownProps>(), {
 	placeholder: '',
 	modelValue: () => [],
 	eventBus: null,
+	createEnabled: true,
+	manageEnabled: true,
+	createTag: undefined,
+	multipleLimit: 0,
 });
 
 const emit = defineEmits<{
@@ -59,6 +66,17 @@ const appliedTags = computed<string[]>(() => {
 	return props.modelValue.filter((id: string) => props.tagsById[id]);
 });
 
+const containerClasses = computed(() => {
+	return { 'tags-container': true, focused: focused.value };
+});
+
+const dropdownClasses = computed(() => ({
+	'tags-dropdown': true,
+	[`tags-dropdown-${dropdownId}`]: true,
+	'tags-dropdown-create-enabled': props.createEnabled,
+	'tags-dropdown-manage-enabled': props.manageEnabled,
+}));
+
 watch(
 	() => props.allTags,
 	() => {
@@ -189,7 +207,7 @@ onClickOutside(
 </script>
 
 <template>
-	<div ref="container" :class="{ 'tags-container': true, focused }" @keydown.stop>
+	<div ref="container" :class="containerClasses" @keydown.stop>
 		<N8nSelect
 			ref="selectRef"
 			:teleported="true"
@@ -199,16 +217,17 @@ onClickOutside(
 			:filter-method="filterOptions"
 			filterable
 			multiple
+			:multiple-limit="props.multipleLimit"
 			:reserve-keyword="false"
 			loading-text="..."
-			:popper-class="['tags-dropdown', 'tags-dropdown-' + dropdownId].join(' ')"
+			:popper-class="dropdownClasses"
 			data-test-id="tags-dropdown"
 			@update:model-value="onTagsUpdated"
 			@visible-change="onVisibleChange"
 			@remove-tag="onRemoveTag"
 		>
 			<N8nOption
-				v-if="options.length === 0 && filter"
+				v-if="createEnabled && options.length === 0 && filter"
 				:key="CREATE_KEY"
 				ref="createRef"
 				:value="CREATE_KEY"
@@ -220,7 +239,7 @@ onClickOutside(
 				</span>
 			</N8nOption>
 			<N8nOption v-else-if="options.length === 0" value="message" disabled>
-				<span>{{ i18n.baseText('tagsDropdown.typeToCreateATag') }}</span>
+				<span v-if="createEnabled">{{ i18n.baseText('tagsDropdown.typeToCreateATag') }}</span>
 				<span v-if="allTags.length > 0">{{
 					i18n.baseText('tagsDropdown.noMatchingTagsExist')
 				}}</span>
@@ -237,7 +256,7 @@ onClickOutside(
 				data-test-id="tag"
 			/>
 
-			<N8nOption :key="MANAGE_KEY" :value="MANAGE_KEY" class="ops manage-tags">
+			<N8nOption v-if="manageEnabled" :key="MANAGE_KEY" :value="MANAGE_KEY" class="ops manage-tags">
 				<font-awesome-icon icon="cog" />
 				<span>{{ i18n.baseText('tagsDropdown.manageTags') }}</span>
 			</N8nOption>
@@ -313,7 +332,7 @@ onClickOutside(
 			}
 		}
 
-		&:after {
+		.tags-dropdown-manage-enabled &:after {
 			content: ' ';
 			display: block;
 			min-height: $--item-height;

packages/editor-ui/src/components/TestDefinition/EditDefinition/EvaluationHeader.vue

@@ -1,18 +1,15 @@
 <script setup lang="ts">
 import { useI18n } from '@/composables/useI18n';
+import type { EditableField } from '../types';
 
 export interface EvaluationHeaderProps {
-	modelValue: {
-		value: string;
-		isEditing: boolean;
-		tempValue: string;
-	};
-	startEditing: (field: string) => void;
-	saveChanges: (field: string) => void;
-	handleKeydown: (e: KeyboardEvent, field: string) => void;
+	modelValue: EditableField<string>;
+	startEditing: (field: 'name') => void;
+	saveChanges: (field: 'name') => void;
+	handleKeydown: (e: KeyboardEvent, field: 'name') => void;
 }
 
-defineEmits<{ 'update:modelValue': [value: EvaluationHeaderProps['modelValue']] }>();
+defineEmits<{ 'update:modelValue': [value: EditableField<string>] }>();
 defineProps<EvaluationHeaderProps>();
 
 const locale = useI18n();

packages/editor-ui/src/components/TestDefinition/EditDefinition/EvaluationStep.vue

@@ -2,12 +2,14 @@
 import { useI18n } from '@/composables/useI18n';
 import { ElCollapseTransition } from 'element-plus';
 import { ref, nextTick } from 'vue';
+import N8nTooltip from 'n8n-design-system/components/N8nTooltip';
 
 interface EvaluationStep {
 	title: string;
 	warning?: boolean;
 	small?: boolean;
 	expanded?: boolean;
+	tooltip?: string;
 }
 
 const props = withDefaults(defineProps<EvaluationStep>(), {
@@ -15,12 +17,14 @@ const props = withDefaults(defineProps<EvaluationStep>(), {
 	warning: false,
 	small: false,
 	expanded: true,
+	tooltip: '',
 });
 
 const locale = useI18n();
 const isExpanded = ref(props.expanded);
 const contentRef = ref<HTMLElement | null>(null);
 const containerRef = ref<HTMLElement | null>(null);
+const isTooltipVisible = ref(false);
 
 const toggleExpand = async () => {
 	isExpanded.value = !isExpanded.value;
@@ -31,11 +35,32 @@ const toggleExpand = async () => {
 		}
 	}
 };
+
+const showTooltip = () => {
+	isTooltipVisible.value = true;
+};
+
+const hideTooltip = () => {
+	isTooltipVisible.value = false;
+};
 </script>
 
 <template>
-	<div ref="containerRef" :class="[$style.evaluationStep, small && $style.small]">
-		<div :class="$style.content">
+	<div
+		ref="containerRef"
+		:class="[$style.evaluationStep, small && $style.small]"
+		data-test-id="evaluation-step"
+	>
+		<N8nTooltip :disabled="!tooltip" placement="right" :offset="25" :visible="isTooltipVisible">
+			<template #content>
+				{{ tooltip }}
+			</template>
+			<!-- This empty div is needed to ensure the tooltip trigger area spans the full width of the step.
+			     Without it, the tooltip would only show when hovering over the content div, which is narrower.
+			     The contentPlaceholder creates an invisible full-width area that can trigger the tooltip. -->
+			<div :class="$style.contentPlaceholder"></div>
+		</N8nTooltip>
+		<div :class="$style.content" @mouseenter="showTooltip" @mouseleave="hideTooltip">
 			<div :class="$style.header">
 				<div :class="[$style.icon, warning && $style.warning]">
 					<slot name="icon" />
@@ -47,6 +72,7 @@ const toggleExpand = async () => {
 					:class="$style.collapseButton"
 					:aria-expanded="isExpanded"
 					:aria-controls="'content-' + title.replace(/\s+/g, '-')"
+					data-test-id="evaluation-step-collapse-button"
 					@click="toggleExpand"
 				>
 					{{
@@ -59,7 +85,7 @@ const toggleExpand = async () => {
 			</div>
 			<ElCollapseTransition v-if="$slots.cardContent">
 				<div v-show="isExpanded" :class="$style.cardContentWrapper">
-					<div ref="contentRef" :class="$style.cardContent">
+					<div ref="contentRef" :class="$style.cardContent" data-test-id="evaluation-step-content">
 						<slot name="cardContent" />
 					</div>
 				</div>
@@ -85,6 +111,14 @@ const toggleExpand = async () => {
 		width: 80%;
 	}
 }
+.contentPlaceholder {
+	position: absolute;
+	top: 0;
+	left: 0;
+	width: 100%;
+	height: 100%;
+	z-index: -1;
+}
 .icon {
 	display: flex;
 	align-items: center;

packages/editor-ui/src/components/TestDefinition/EditDefinition/MetricsInput.vue

@@ -1,22 +1,30 @@
 <script setup lang="ts">
+import type { TestMetricRecord } from '@/api/testDefinition.ee';
 import { useI18n } from '@/composables/useI18n';
 
 export interface MetricsInputProps {
-	modelValue: string[];
+	modelValue: Array<Partial<TestMetricRecord>>;
 }
 const props = defineProps<MetricsInputProps>();
-const emit = defineEmits<{ 'update:modelValue': [value: MetricsInputProps['modelValue']] }>();
+const emit = defineEmits<{
+	'update:modelValue': [value: MetricsInputProps['modelValue']];
+	deleteMetric: [metric: Partial<TestMetricRecord>];
+}>();
 const locale = useI18n();
 
 function addNewMetric() {
-	emit('update:modelValue', [...props.modelValue, '']);
+	emit('update:modelValue', [...props.modelValue, { name: '' }]);
 }
 
-function updateMetric(index: number, value: string) {
+function updateMetric(index: number, name: string) {
 	const newMetrics = [...props.modelValue];
-	newMetrics[index] = value;
+	newMetrics[index].name = name;
 	emit('update:modelValue', newMetrics);
 }
+
+function onDeleteMetric(metric: Partial<TestMetricRecord>) {
+	emit('deleteMetric', metric);
+}
 </script>
 
 <template>
@@ -27,14 +35,15 @@ function updateMetric(index: number, value: string) {
 			:class="$style.metricField"
 		>
 			<div :class="$style.metricsContainer">
-				<div v-for="(metric, index) in modelValue" :key="index">
+				<div v-for="(metric, index) in modelValue" :key="index" :class="$style.metricItem">
 					<N8nInput
 						:ref="`metric_${index}`"
 						data-test-id="evaluation-metric-item"
-						:model-value="metric"
+						:model-value="metric.name"
 						:placeholder="locale.baseText('testDefinition.edit.metricsPlaceholder')"
 						@update:model-value="(value: string) => updateMetric(index, value)"
 					/>
+					<n8n-icon-button icon="trash" type="text" @click="onDeleteMetric(metric)" />
 				</div>
 				<n8n-button
 					type="tertiary"
@@ -54,6 +63,11 @@ function updateMetric(index: number, value: string) {
 	gap: var(--spacing-xs);
 }
 
+.metricItem {
+	display: flex;
+	align-items: center;
+}
+
 .metricField {
 	width: 100%;
 	margin-top: var(--spacing-xs);

packages/editor-ui/src/components/TestDefinition/EditDefinition/NodesPinning.vue

@@ -0,0 +1,194 @@
+<script setup lang="ts">
+import { useWorkflowsStore } from '@/stores/workflows.store';
+import { useNodeTypesStore } from '@/stores/nodeTypes.store';
+import { computed, onMounted, ref, useCssModule } from 'vue';
+import { useRoute, useRouter } from 'vue-router';
+import { useCanvasOperations } from '@/composables/useCanvasOperations';
+import { useCanvasMapping } from '@/composables/useCanvasMapping';
+import { createEventBus, N8nTooltip } from 'n8n-design-system';
+import type { CanvasConnectionPort, CanvasEventBusEvents, CanvasNodeData } from '@/types';
+import { useVueFlow } from '@vue-flow/core';
+import { useI18n } from '@/composables/useI18n';
+
+const workflowsStore = useWorkflowsStore();
+const nodeTypesStore = useNodeTypesStore();
+const route = useRoute();
+const router = useRouter();
+const locale = useI18n();
+
+const { resetWorkspace, initializeWorkspace } = useCanvasOperations({ router });
+
+const eventBus = createEventBus<CanvasEventBusEvents>();
+const style = useCssModule();
+const uuid = crypto.randomUUID();
+const props = defineProps<{
+	modelValue: Array<{ name: string }>;
+}>();
+
+const emit = defineEmits<{
+	'update:modelValue': [value: Array<{ name: string }>];
+}>();
+
+const isLoading = ref(true);
+
+const workflowId = computed(() => route.params.name as string);
+const testId = computed(() => route.params.testId as string);
+const workflow = computed(() => workflowsStore.getWorkflowById(workflowId.value));
+const workflowObject = computed(() => workflowsStore.getCurrentWorkflow(true));
+const canvasId = computed(() => `${uuid}-${testId.value}`);
+
+const { onNodesInitialized, fitView, zoomTo } = useVueFlow({ id: canvasId.value });
+const nodes = computed(() => {
+	return workflow.value.nodes ?? [];
+});
+const connections = computed(() => workflow.value.connections);
+
+const { nodes: mappedNodes, connections: mappedConnections } = useCanvasMapping({
+	nodes,
+	connections,
+	workflowObject,
+});
+async function loadData() {
+	workflowsStore.resetState();
+	resetWorkspace();
+	const loadingPromise = Promise.all([
+		nodeTypesStore.getNodeTypes(),
+		workflowsStore.fetchWorkflow(workflowId.value),
+	]);
+	await loadingPromise;
+	initializeWorkspace(workflow.value);
+	disableAllNodes();
+}
+function getNodeNameById(id: string) {
+	return mappedNodes.value.find((node) => node.id === id)?.data?.name;
+}
+function updateNodeClasses(nodeIds: string[], isPinned: boolean) {
+	eventBus.emit('nodes:action', {
+		ids: nodeIds,
+		action: 'update:node:class',
+		payload: {
+			className: style.pinnedNode,
+			add: isPinned,
+		},
+	});
+	eventBus.emit('nodes:action', {
+		ids: nodeIds,
+		action: 'update:node:class',
+		payload: {
+			className: style.notPinnedNode,
+			add: !isPinned,
+		},
+	});
+}
+function disableAllNodes() {
+	const ids = mappedNodes.value.map((node) => node.id);
+	updateNodeClasses(ids, false);
+
+	const pinnedNodes = props.modelValue
+		.map((node) => {
+			const matchedNode = mappedNodes.value.find(
+				(mappedNode) => mappedNode?.data?.name === node.name,
+			);
+			return matchedNode?.id ?? null;
+		})
+		.filter((n) => n !== null);
+
+	if (pinnedNodes.length > 0) {
+		updateNodeClasses(pinnedNodes, true);
+	}
+}
+function onPinButtonClick(data: CanvasNodeData) {
+	const nodeName = getNodeNameById(data.id);
+	if (!nodeName) return;
+
+	const isPinned = props.modelValue.some((node) => node.name === nodeName);
+	const updatedNodes = isPinned
+		? props.modelValue.filter((node) => node.name !== nodeName)
+		: [...props.modelValue, { name: nodeName }];
+
+	emit('update:modelValue', updatedNodes);
+	updateNodeClasses([data.id], !isPinned);
+}
+function isPinButtonVisible(outputs: CanvasConnectionPort[]) {
+	return outputs.length === 1;
+}
+
+onNodesInitialized(async () => {
+	await fitView();
+	isLoading.value = false;
+	await zoomTo(0.7, { duration: 400 });
+});
+onMounted(loadData);
+</script>
+
+<template>
+	<div :class="$style.container">
+		<N8nSpinner v-if="isLoading" size="xlarge" type="dots" :class="$style.spinner" />
+		<Canvas
+			:id="canvasId"
+			:loading="isLoading"
+			:class="{ [$style.canvas]: true }"
+			:nodes="mappedNodes"
+			:connections="mappedConnections"
+			:show-bug-reporting-button="false"
+			:read-only="true"
+			:event-bus="eventBus"
+		>
+			<template #nodeToolbar="{ data, outputs }">
+				<div :class="$style.pinButtonContainer">
+					<N8nTooltip v-if="isPinButtonVisible(outputs)" placement="left">
+						<template #content>
+							{{ locale.baseText('testDefinition.edit.nodesPinning.pinButtonTooltip') }}
+						</template>
+						<n8n-icon-button
+							type="tertiary"
+							size="large"
+							icon="thumbtack"
+							:class="$style.pinButton"
+							@click="onPinButtonClick(data)"
+						/>
+					</N8nTooltip>
+				</div>
+			</template>
+		</Canvas>
+	</div>
+</template>
+
+<style lang="scss" module>
+.container {
+	width: 100vw;
+	height: 100%;
+}
+.pinButtonContainer {
+	position: absolute;
+	right: 0;
+	display: flex;
+	justify-content: flex-end;
+	bottom: 100%;
+}
+
+.pinButton {
+	cursor: pointer;
+	color: var(--canvas-node--border-color);
+	border: none;
+}
+.notPinnedNode,
+.pinnedNode {
+	:global(.n8n-node-icon) > div {
+		filter: contrast(40%) brightness(1.5) grayscale(100%);
+	}
+}
+.pinnedNode {
+	--canvas-node--border-color: hsla(247, 49%, 55%, 1);
+
+	:global(.n8n-node-icon) > div {
+		filter: contrast(40%) brightness(1.5) grayscale(100%);
+	}
+}
+.spinner {
+	position: absolute;
+	top: 50%;
+	left: 50%;
+	transform: translate(-50%, -50%);
+}
+</style>

packages/editor-ui/src/components/TestDefinition/EditDefinition/TagsInput.vue

@@ -3,40 +3,48 @@ import { useI18n } from '@/composables/useI18n';
 import type { ITag } from '@/Interface';
 import { createEventBus } from 'n8n-design-system';
 import { computed } from 'vue';
+import type { EditableField } from '../types';
 
 export interface TagsInputProps {
-	modelValue?: {
-		isEditing: boolean;
-		appliedTagIds: string[];
-	};
+	modelValue: EditableField<string[]>;
 	allTags: ITag[];
 	tagsById: Record<string, ITag>;
 	isLoading: boolean;
-	startEditing: (field: string) => void;
-	saveChanges: (field: string) => void;
-	cancelEditing: (field: string) => void;
+	startEditing: (field: 'tags') => void;
+	saveChanges: (field: 'tags') => void;
+	cancelEditing: (field: 'tags') => void;
+	createTag?: (name: string) => Promise<ITag>;
 }
 
 const props = withDefaults(defineProps<TagsInputProps>(), {
 	modelValue: () => ({
 		isEditing: false,
-		appliedTagIds: [],
+		value: [],
+		tempValue: [],
 	}),
+	createTag: undefined,
 });
 
 const emit = defineEmits<{ 'update:modelValue': [value: TagsInputProps['modelValue']] }>();
 
 const locale = useI18n();
 const tagsEventBus = createEventBus();
+
+/**
+ * Compute the tag name by ID
+ */
 const getTagName = computed(() => (tagId: string) => {
 	return props.tagsById[tagId]?.name ?? '';
 });
 
+/**
+ * Update the tempValue of the tags when the dropdown changes.
+ * This does not finalize the changes; that happens on blur or hitting enter.
+ */
 function updateTags(tags: string[]) {
-	const newTags = tags[0] ? [tags[0]] : [];
 	emit('update:modelValue', {
 		...props.modelValue,
-		appliedTagIds: newTags,
+		tempValue: tags,
 	});
 }
 </script>
@@ -48,12 +56,13 @@ function updateTags(tags: string[]) {
 			:bold="false"
 			size="small"
 		>
+			<!-- Read-only view -->
 			<div v-if="!modelValue.isEditing" :class="$style.tagsRead" @click="startEditing('tags')">
-				<n8n-text v-if="modelValue.appliedTagIds.length === 0" size="small">
+				<n8n-text v-if="modelValue.value.length === 0" size="small">
 					{{ locale.baseText('testDefinition.edit.selectTag') }}
 				</n8n-text>
 				<n8n-tag
-					v-for="tagId in modelValue.appliedTagIds"
+					v-for="tagId in modelValue.value"
 					:key="tagId"
 					:text="getTagName(tagId)"
 					data-test-id="evaluation-tag-field"
@@ -66,24 +75,26 @@ function updateTags(tags: string[]) {
 					transparent
 				/>
 			</div>
+
+			<!-- Editing view -->
 			<TagsDropdown
 				v-else
-				:model-value="modelValue.appliedTagIds"
+				:model-value="modelValue.tempValue"
 				:placeholder="locale.baseText('executionAnnotationView.chooseOrCreateATag')"
-				:create-enabled="false"
+				:create-enabled="modelValue.tempValue.length === 0"
 				:all-tags="allTags"
 				:is-loading="isLoading"
 				:tags-by-id="tagsById"
 				data-test-id="workflow-tags-dropdown"
 				:event-bus="tagsEventBus"
+				:create-tag="createTag"
+				:manage-enabled="false"
+				:multiple-limit="1"
 				@update:model-value="updateTags"
 				@esc="cancelEditing('tags')"
 				@blur="saveChanges('tags')"
 			/>
 		</n8n-input-label>
-		<n8n-text size="small" color="text-light">{{
-			locale.baseText('testDefinition.edit.tagsHelpText')
-		}}</n8n-text>
 	</div>
 </template>
 

packages/editor-ui/src/components/TestDefinition/ListDefinition/TestItem.vue

@@ -1,5 +1,6 @@
 <script setup lang="ts">
 import type { TestListItem } from '@/components/TestDefinition/types';
+import TimeAgo from '@/components/TimeAgo.vue';
 import { useI18n } from '@/composables/useI18n';
 import n8nIconButton from 'n8n-design-system/components/N8nIconButton';
 
@@ -20,21 +21,25 @@ const emit = defineEmits<{
 const actions = [
 	{
 		icon: 'play',
+		id: 'run',
 		event: () => emit('run-test', props.test.id),
 		tooltip: locale.baseText('testDefinition.runTest'),
 	},
 	{
 		icon: 'list',
+		id: 'view',
 		event: () => emit('view-details', props.test.id),
 		tooltip: locale.baseText('testDefinition.viewDetails'),
 	},
 	{
 		icon: 'pen',
+		id: 'edit',
 		event: () => emit('edit-test', props.test.id),
 		tooltip: locale.baseText('testDefinition.editTest'),
 	},
 	{
 		icon: 'trash',
+		id: 'delete',
 		event: () => emit('delete-test', props.test.id),
 		tooltip: locale.baseText('testDefinition.deleteTest'),
 	},
@@ -42,20 +47,27 @@ const actions = [
 </script>
 
 <template>
-	<div :class="$style.testItem" @click="$emit('view-details', test.id)">
+	<div
+		:class="$style.testItem"
+		:data-test-id="`test-item-${test.id}`"
+		@click="$emit('view-details', test.id)"
+	>
 		<div :class="$style.testInfo">
 			<div :class="$style.testName">
 				{{ test.name }}
-				<n8n-tag v-if="test.tagName" :text="test.tagName" />
 			</div>
 			<div :class="$style.testCases">
-				{{ locale.baseText('testDefinition.list.testCases', { adjustToNumber: test.testCases }) }}
-				<n8n-loading v-if="!test.execution.lastRun" :loading="true" :rows="1" />
-				<span v-else>{{
-					locale.baseText('testDefinition.list.lastRun', {
-						interpolate: { lastRun: test.execution.lastRun },
-					})
-				}}</span>
+				<n8n-text size="small">
+					{{ locale.baseText('testDefinition.list.testRuns', { adjustToNumber: test.testCases }) }}
+				</n8n-text>
+				<template v-if="test.execution.status === 'running'">
+					{{ locale.baseText('testDefinition.list.running') }}
+					<n8n-spinner />
+				</template>
+				<span v-else-if="test.execution.lastRun">
+					{{ locale.baseText('testDefinition.list.lastRun') }}
+					<TimeAgo :date="test.execution.lastRun" />
+				</span>
 			</div>
 		</div>
 
@@ -68,7 +80,7 @@ const actions = [
 				}}
 			</div>
 			<div v-for="(value, key) in test.execution.metrics" :key="key" :class="$style.metric">
-				{{ key }}: {{ value ?? '-' }}
+				{{ key }}: {{ value.toFixed(2) ?? '-' }}
 			</div>
 		</div>
 
@@ -80,6 +92,7 @@ const actions = [
 				<component
 					:is="n8nIconButton"
 					:icon="action.icon"
+					:data-test-id="`${action.id}-test-button-${test.id}`"
 					type="tertiary"
 					size="mini"
 					@click.stop="action.event"
@@ -115,7 +128,6 @@ const actions = [
 	align-items: center;
 	gap: var(--spacing-2xs);
 	font-weight: var(--font-weight-bold);
-	margin-bottom: var(--spacing-4xs);
 	font-size: var(--font-size-s);
 }
 

packages/editor-ui/src/components/TestDefinition/ListDefinition/TestsList.vue

@@ -12,7 +12,7 @@ const locale = useI18n();
 </script>
 
 <template>
-	<div :class="$style.testsList">
+	<div :class="$style.testsList" data-test-id="test-definition-list">
 		<div :class="$style.testsHeader">
 			<n8n-button
 				:label="locale.baseText('testDefinition.list.createNew')"

packages/editor-ui/src/components/TestDefinition/ListRuns/MetricsChart.vue

@@ -0,0 +1,108 @@
+<script setup lang="ts">
+import { computed, watchEffect } from 'vue';
+import { Line } from 'vue-chartjs';
+import { useMetricsChart } from '../composables/useMetricsChart';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+import { useI18n } from '@/composables/useI18n';
+import type { AppliedThemeOption } from '@/Interface';
+
+const emit = defineEmits<{
+	'update:selectedMetric': [value: string];
+}>();
+
+const props = defineProps<{
+	selectedMetric: string;
+	runs: TestRunRecord[];
+	theme?: AppliedThemeOption;
+}>();
+
+const locale = useI18n();
+const metricsChart = useMetricsChart(props.theme);
+
+const availableMetrics = computed(() => {
+	return props.runs.reduce((acc, run) => {
+		const metricKeys = Object.keys(run.metrics ?? {});
+		return [...new Set([...acc, ...metricKeys])];
+	}, [] as string[]);
+});
+
+const chartData = computed(() => metricsChart.generateChartData(props.runs, props.selectedMetric));
+
+const chartOptions = computed(() =>
+	metricsChart.generateChartOptions({
+		metric: props.selectedMetric,
+		xTitle: locale.baseText('testDefinition.listRuns.runDate'),
+	}),
+);
+
+watchEffect(() => {
+	if (props.runs.length > 0 && !props.selectedMetric) {
+		emit('update:selectedMetric', availableMetrics.value[0]);
+	}
+});
+</script>
+
+<template>
+	<div v-if="availableMetrics.length > 0" :class="$style.metricsChartContainer">
+		<div :class="$style.chartHeader">
+			<N8nText>{{ locale.baseText('testDefinition.listRuns.metricsOverTime') }}</N8nText>
+			<N8nSelect
+				:model-value="selectedMetric"
+				:class="$style.metricSelect"
+				placeholder="Select metric"
+				@update:model-value="emit('update:selectedMetric', $event)"
+			>
+				<N8nOption
+					v-for="metric in availableMetrics"
+					:key="metric"
+					:label="metric"
+					:value="metric"
+				/>
+			</N8nSelect>
+		</div>
+		<div :class="$style.chartWrapper">
+			<Line
+				v-if="availableMetrics.length > 0"
+				:key="selectedMetric"
+				:data="chartData"
+				:options="chartOptions"
+				:class="$style.metricsChart"
+			/>
+		</div>
+	</div>
+</template>
+
+<style lang="scss" module>
+.metricsChartContainer {
+	margin: var(--spacing-m) 0;
+	background: var(--color-background-xlight);
+	border-radius: var(--border-radius-large);
+	box-shadow: var(--box-shadow-base);
+
+	.chartHeader {
+		display: flex;
+		justify-content: space-between;
+		align-items: center;
+		margin-bottom: var(--spacing-m);
+		padding: var(--spacing-s);
+		border-bottom: 1px solid var(--color-foreground-base);
+	}
+
+	.chartTitle {
+		font-size: var(--font-size-l);
+		font-weight: var(--font-weight-bold);
+		color: var(--color-text-base);
+	}
+
+	.metricSelect {
+		max-width: 15rem;
+	}
+
+	.chartWrapper {
+		position: relative;
+		height: 400px;
+		width: 100%;
+		padding: var(--spacing-s);
+	}
+}
+</style>

packages/editor-ui/src/components/TestDefinition/ListRuns/TestRunsTable.vue

@@ -0,0 +1,119 @@
+<script setup lang="ts">
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+import { computed, ref } from 'vue';
+import type { TestDefinitionTableColumn } from '../shared/TestDefinitionTable.vue';
+import TestDefinitionTable from '../shared/TestDefinitionTable.vue';
+import { convertToDisplayDate } from '@/utils/typesUtils';
+import { VIEWS } from '@/constants';
+import { useI18n } from '@/composables/useI18n';
+
+const emit = defineEmits<{
+	getRunDetail: [run: TestRunRecord];
+	selectionChange: [runs: TestRunRecord[]];
+	deleteRuns: [runs: TestRunRecord[]];
+}>();
+
+const props = defineProps<{
+	runs: TestRunRecord[];
+	selectable?: boolean;
+}>();
+
+const locale = useI18n();
+const navigateToRunDetail = (run: TestRunRecord) => emit('getRunDetail', run);
+const selectedRows = ref<TestRunRecord[]>([]);
+
+const metrics = computed(() => {
+	return props.runs.reduce((acc, run) => {
+		const metricKeys = Object.keys(run.metrics ?? {});
+		return [...new Set([...acc, ...metricKeys])];
+	}, [] as string[]);
+});
+
+const columns = computed((): Array<TestDefinitionTableColumn<TestRunRecord>> => {
+	return [
+		{
+			prop: 'runNumber',
+			label: locale.baseText('testDefinition.listRuns.runNumber'),
+			width: 200,
+			route: (row: TestRunRecord) => ({
+				name: VIEWS.TEST_DEFINITION_RUNS_DETAIL,
+				params: { testId: row.testDefinitionId, runId: row.id },
+			}),
+			formatter: (row: TestRunRecord) => `${row.id}`,
+		},
+		{
+			prop: 'status',
+			label: locale.baseText('testDefinition.listRuns.status'),
+			filters: [
+				{ text: locale.baseText('testDefinition.listRuns.status.new'), value: 'new' },
+				{ text: locale.baseText('testDefinition.listRuns.status.running'), value: 'running' },
+				{ text: locale.baseText('testDefinition.listRuns.status.completed'), value: 'completed' },
+				{ text: locale.baseText('testDefinition.listRuns.status.error'), value: 'error' },
+			],
+			filterMethod: (value: string, row: TestRunRecord) => row.status === value,
+		},
+		{
+			prop: 'date',
+			label: locale.baseText('testDefinition.listRuns.runDate'),
+			sortable: true,
+			formatter: (row: TestRunRecord) => convertToDisplayDate(new Date(row.runAt).getTime()),
+		},
+
+		...metrics.value.map((metric) => ({
+			prop: `metrics.${metric}`,
+			label: metric,
+			sortable: true,
+			formatter: (row: TestRunRecord) => `${row.metrics?.[metric]?.toFixed(2) ?? '-'}`,
+		})),
+	];
+});
+
+function onSelectionChange(runs: TestRunRecord[]) {
+	selectedRows.value = runs;
+	emit('selectionChange', runs);
+}
+
+function deleteRuns() {
+	emit('deleteRuns', selectedRows.value);
+}
+</script>
+
+<template>
+	<div :class="$style.container">
+		<div :class="$style.footer">
+			<n8n-button
+				v-show="selectedRows.length > 0"
+				type="danger"
+				:class="$style.activator"
+				:size="'medium'"
+				:icon="'trash'"
+				data-test-id="delete-runs-button"
+				@click="deleteRuns"
+			>
+				{{
+					locale.baseText('testDefinition.listRuns.deleteRuns', {
+						adjustToNumber: selectedRows.length,
+					})
+				}}
+			</n8n-button>
+		</div>
+		<TestDefinitionTable
+			:data="runs"
+			:columns="columns"
+			selectable
+			@row-click="navigateToRunDetail"
+			@selection-change="onSelectionChange"
+		/>
+		<N8nText :class="$style.runsTableTotal">{{
+			locale.baseText('testDefinition.edit.pastRuns.total', { adjustToNumber: runs.length })
+		}}</N8nText>
+	</div>
+</template>
+
+<style module lang="scss">
+.container {
+	display: flex;
+	flex-direction: column;
+	gap: 10px;
+}
+</style>

packages/editor-ui/src/components/TestDefinition/composables/useMetricsChart.ts

@@ -0,0 +1,145 @@
+import type { ChartData, ChartOptions } from 'chart.js';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+import dateFormat from 'dateformat';
+import type { AppliedThemeOption } from '@/Interface';
+
+const THEME_COLORS = {
+	light: {
+		primary: 'rgb(255, 110, 92)',
+		text: {
+			primary: 'rgb(68, 68, 68)',
+			secondary: 'rgb(102, 102, 102)',
+		},
+		background: 'rgb(255, 255, 255)',
+		grid: 'rgba(68, 68, 68, 0.1)',
+	},
+	dark: {
+		primary: 'rgb(255, 110, 92)',
+		text: {
+			primary: 'rgb(255, 255, 255)',
+			secondary: 'rgba(255, 255, 255, 0.7)',
+		},
+		background: 'rgb(32, 32, 32)',
+		grid: 'rgba(255, 255, 255, 0.1)',
+	},
+};
+
+export function useMetricsChart(mode: AppliedThemeOption = 'light') {
+	const colors = THEME_COLORS[mode];
+	const toRGBA = (color: string, alpha: number) => {
+		if (color.includes('rgba')) return color;
+		return color.replace('rgb', 'rgba').replace(')', `, ${alpha})`);
+	};
+	function generateChartData(runs: TestRunRecord[], metric: string): ChartData<'line'> {
+		const sortedRuns = [...runs]
+			.sort((a, b) => new Date(a.runAt).getTime() - new Date(b.runAt).getTime())
+			.filter((run) => run.metrics?.[metric]);
+
+		return {
+			labels: sortedRuns.map((run) => {
+				return dateFormat(run.runAt, 'yyyy-mm-dd HH:MM');
+			}),
+			datasets: [
+				{
+					label: metric,
+					data: sortedRuns.map((run) => run.metrics?.[metric] ?? 0),
+					borderColor: colors.primary,
+					backgroundColor: toRGBA(colors.primary, 0.1),
+					borderWidth: 2,
+					pointRadius: 4,
+					pointHoverRadius: 6,
+					pointBackgroundColor: colors.primary,
+					pointBorderColor: colors.primary,
+					pointHoverBackgroundColor: colors.background,
+					pointHoverBorderColor: colors.primary,
+					tension: 0.4,
+					fill: true,
+				},
+			],
+		};
+	}
+
+	function generateChartOptions(params: { metric: string; xTitle: string }): ChartOptions<'line'> {
+		return {
+			responsive: true,
+			maintainAspectRatio: false,
+			devicePixelRatio: 2,
+			interaction: {
+				mode: 'index' as const,
+				intersect: false,
+			},
+			scales: {
+				y: {
+					beginAtZero: true,
+					grid: {
+						color: colors.grid,
+					},
+					ticks: {
+						padding: 8,
+						color: colors.text.primary,
+					},
+					title: {
+						display: true,
+						text: params.metric,
+						padding: 16,
+						color: colors.text.primary,
+					},
+				},
+				x: {
+					grid: {
+						display: false,
+					},
+					ticks: {
+						maxRotation: 45,
+						minRotation: 45,
+						color: colors.text.primary,
+					},
+					title: {
+						display: true,
+						text: params.xTitle,
+						padding: 16,
+						color: colors.text.primary,
+					},
+				},
+			},
+			plugins: {
+				tooltip: {
+					backgroundColor: colors.background,
+					titleColor: colors.text.primary,
+					titleFont: {
+						weight: '600',
+					},
+					bodyColor: colors.text.secondary,
+					bodySpacing: 4,
+					padding: 12,
+					borderColor: toRGBA(colors.primary, 0.2),
+					borderWidth: 1,
+					displayColors: true,
+					callbacks: {
+						title: (tooltipItems) => tooltipItems[0].label,
+						label: (context) => `${params.metric}: ${context.parsed.y.toFixed(2)}`,
+					},
+				},
+				legend: {
+					display: false,
+				},
+			},
+			animation: {
+				duration: 750,
+				easing: 'easeInOutQuart',
+			},
+			transitions: {
+				active: {
+					animation: {
+						duration: 300,
+					},
+				},
+			},
+		};
+	}
+
+	return {
+		generateChartData,
+		generateChartOptions,
+	};
+}

packages/editor-ui/src/components/TestDefinition/composables/useTestDefinitionForm.ts

@@ -1,27 +1,10 @@
 import { ref, computed } from 'vue';
-import type { ComponentPublicInstance } from 'vue';
-import type { INodeParameterResourceLocator } from 'n8n-workflow';
+import type { ComponentPublicInstance, ComputedRef } from 'vue';
 import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
 import type AnnotationTagsDropdownEe from '@/components/AnnotationTagsDropdown.ee.vue';
 import type { N8nInput } from 'n8n-design-system';
 import type { UpdateTestDefinitionParams } from '@/api/testDefinition.ee';
-
-interface EditableField {
-	value: string;
-	isEditing: boolean;
-	tempValue: string;
-}
-
-export interface IEvaluationFormState {
-	name: EditableField;
-	description: string;
-	tags: {
-		isEditing: boolean;
-		appliedTagIds: string[];
-	};
-	evaluationWorkflow: INodeParameterResourceLocator;
-	metrics: string[];
-}
+import type { EditableField, EditableFormState, EvaluationFormState } from '../types';
 
 type FormRefs = {
 	nameInput: ComponentPublicInstance<typeof N8nInput>;
@@ -29,64 +12,75 @@ type FormRefs = {
 };
 
 export function useTestDefinitionForm() {
-	// Stores
 	const evaluationsStore = useTestDefinitionStore();
 
-	// Form state
-	const state = ref<IEvaluationFormState>({
-		description: '',
+	// State initialization
+	const state = ref<EvaluationFormState>({
 		name: {
-			value: `My Test [${new Date().toLocaleString(undefined, { month: 'numeric', day: 'numeric', hour: 'numeric', minute: 'numeric', second: 'numeric' })}]`,
-			isEditing: false,
+			value: `My Test ${evaluationsStore.allTestDefinitions.length + 1}`,
 			tempValue: '',
+			isEditing: false,
 		},
 		tags: {
+			value: [],
+			tempValue: [],
 			isEditing: false,
-			appliedTagIds: [],
 		},
+		description: '',
 		evaluationWorkflow: {
 			mode: 'list',
 			value: '',
 			__rl: true,
 		},
-		metrics: [''],
+		metrics: [],
+		mockedNodes: [],
 	});
 
-	// Loading states
 	const isSaving = ref(false);
 	const fieldsIssues = ref<Array<{ field: string; message: string }>>([]);
-
-	// Field refs
 	const fields = ref<FormRefs>({} as FormRefs);
 
-	// Methods
+	// A computed mapping of editable fields to their states
+	// This ensures TS knows the exact type of each field.
+	const editableFields: ComputedRef<{
+		name: EditableField<string>;
+		tags: EditableField<string[]>;
+	}> = computed(() => ({
+		name: state.value.name,
+		tags: state.value.tags,
+	}));
+
+	/**
+	 * Load test data including metrics.
+	 */
 	const loadTestData = async (testId: string) => {
 		try {
 			await evaluationsStore.fetchAll({ force: true });
 			const testDefinition = evaluationsStore.testDefinitionsById[testId];
 
 			if (testDefinition) {
-				state.value = {
-					description: testDefinition.description ?? '',
-					name: {
-						value: testDefinition.name ?? '',
-						isEditing: false,
-						tempValue: '',
-					},
-					tags: {
-						isEditing: false,
-						appliedTagIds: testDefinition.annotationTagId ? [testDefinition.annotationTagId] : [],
-					},
-					evaluationWorkflow: {
-						mode: 'list',
-						value: testDefinition.evaluationWorkflowId ?? '',
-						__rl: true,
-					},
-					metrics: [''],
+				const metrics = await evaluationsStore.fetchMetrics(testId);
+
+				state.value.description = testDefinition.description ?? '';
+				state.value.name = {
+					value: testDefinition.name ?? '',
+					isEditing: false,
+					tempValue: '',
 				};
+				state.value.tags = {
+					isEditing: false,
+					value: testDefinition.annotationTagId ? [testDefinition.annotationTagId] : [],
+					tempValue: [],
+				};
+				state.value.evaluationWorkflow = {
+					mode: 'list',
+					value: testDefinition.evaluationWorkflowId ?? '',
+					__rl: true,
+				};
+				state.value.metrics = metrics;
+				state.value.mockedNodes = testDefinition.mockedNodes ?? [];
 			}
 		} catch (error) {
-			// TODO: Throw better errors
 			console.error('Failed to load test data', error);
 		}
 	};
@@ -98,22 +92,43 @@ export function useTestDefinitionForm() {
 		fieldsIssues.value = [];
 
 		try {
-			// Prepare parameters for creating a new test
 			const params = {
 				name: state.value.name.value,
 				workflowId,
 				description: state.value.description,
 			};
-
-			const newTest = await evaluationsStore.create(params);
-			return newTest;
-		} catch (error) {
-			throw error;
+			return await evaluationsStore.create(params);
 		} finally {
 			isSaving.value = false;
 		}
 	};
 
+	const deleteMetric = async (metricId: string, testId: string) => {
+		await evaluationsStore.deleteMetric({ id: metricId, testDefinitionId: testId });
+		state.value.metrics = state.value.metrics.filter((metric) => metric.id !== metricId);
+	};
+
+	const updateMetrics = async (testId: string) => {
+		const promises = state.value.metrics.map(async (metric) => {
+			if (!metric.name) return;
+			if (!metric.id) {
+				const createdMetric = await evaluationsStore.createMetric({
+					name: metric.name,
+					testDefinitionId: testId,
+				});
+				metric.id = createdMetric.id;
+			} else {
+				await evaluationsStore.updateMetric({
+					name: metric.name,
+					id: metric.id,
+					testDefinitionId: testId,
+				});
+			}
+		});
+
+		await Promise.all(promises);
+	};
+
 	const updateTest = async (testId: string) => {
 		if (isSaving.value) return;
 
@@ -121,74 +136,93 @@ export function useTestDefinitionForm() {
 		fieldsIssues.value = [];
 
 		try {
-			// Check if the test ID is provided
 			if (!testId) {
 				throw new Error('Test ID is required for updating a test');
 			}
 
-			// Prepare parameters for updating the existing test
 			const params: UpdateTestDefinitionParams = {
 				name: state.value.name.value,
 				description: state.value.description,
 			};
+
 			if (state.value.evaluationWorkflow.value) {
 				params.evaluationWorkflowId = state.value.evaluationWorkflow.value.toString();
 			}
 
-			const annotationTagId = state.value.tags.appliedTagIds[0];
+			const annotationTagId = state.value.tags.value[0];
 			if (annotationTagId) {
 				params.annotationTagId = annotationTagId;
 			}
-			// Update the existing test
+			if (state.value.mockedNodes.length > 0) {
+				params.mockedNodes = state.value.mockedNodes;
+			}
+
 			return await evaluationsStore.update({ ...params, id: testId });
-		} catch (error) {
-			throw error;
 		} finally {
 			isSaving.value = false;
 		}
 	};
 
-	const startEditing = async (field: string) => {
-		if (field === 'name') {
-			state.value.name.tempValue = state.value.name.value;
-			state.value.name.isEditing = true;
-		} else {
-			state.value.tags.isEditing = true;
+	/**
+	 * Start editing an editable field by copying `value` to `tempValue`.
+	 */
+	function startEditing<T extends keyof EditableFormState>(field: T) {
+		const fieldObj = editableFields.value[field];
+		if (fieldObj.isEditing) {
+			// Already editing, do nothing
+			return;
 		}
-	};
 
-	const saveChanges = (field: string) => {
-		if (field === 'name') {
-			state.value.name.value = state.value.name.tempValue;
-			state.value.name.isEditing = false;
+		if (Array.isArray(fieldObj.value)) {
+			fieldObj.tempValue = [...fieldObj.value];
 		} else {
-			state.value.tags.isEditing = false;
+			fieldObj.tempValue = fieldObj.value;
 		}
-	};
+		fieldObj.isEditing = true;
+	}
+	/**
+	 * Save changes by copying `tempValue` back into `value`.
+	 */
+	function saveChanges<T extends keyof EditableFormState>(field: T) {
+		const fieldObj = editableFields.value[field];
+		fieldObj.value = Array.isArray(fieldObj.tempValue)
+			? [...fieldObj.tempValue]
+			: fieldObj.tempValue;
+		fieldObj.isEditing = false;
+	}
 
-	const cancelEditing = (field: string) => {
-		if (field === 'name') {
-			state.value.name.isEditing = false;
-			state.value.name.tempValue = '';
+	/**
+	 * Cancel editing and revert `tempValue` from `value`.
+	 */
+	function cancelEditing<T extends keyof EditableFormState>(field: T) {
+		const fieldObj = editableFields.value[field];
+		if (Array.isArray(fieldObj.value)) {
+			fieldObj.tempValue = [...fieldObj.value];
 		} else {
-			state.value.tags.isEditing = false;
+			fieldObj.tempValue = fieldObj.value;
 		}
-	};
+		fieldObj.isEditing = false;
+	}
 
-	const handleKeydown = (event: KeyboardEvent, field: string) => {
+	/**
+	 * Handle keyboard events during editing.
+	 */
+	function handleKeydown<T extends keyof EditableFormState>(event: KeyboardEvent, field: T) {
 		if (event.key === 'Escape') {
 			cancelEditing(field);
 		} else if (event.key === 'Enter' && !event.shiftKey) {
 			event.preventDefault();
 			saveChanges(field);
 		}
-	};
+	}
 
 	return {
 		state,
 		fields,
 		isSaving: computed(() => isSaving.value),
 		fieldsIssues: computed(() => fieldsIssues.value),
+		deleteMetric,
+		updateMetrics,
 		loadTestData,
 		createTest,
 		updateTest,

packages/editor-ui/src/components/TestDefinition/shared/TableCell.vue

@@ -0,0 +1,74 @@
+<script setup lang="ts" generic="T">
+import { useI18n } from '@/composables/useI18n';
+import type { TestDefinitionTableColumn } from './TestDefinitionTable.vue';
+import { useRouter } from 'vue-router';
+
+defineProps<{
+	column: TestDefinitionTableColumn<T>;
+	row: T;
+}>();
+
+defineEmits<{
+	click: [];
+}>();
+
+const locale = useI18n();
+const router = useRouter();
+interface WithStatus {
+	status: string;
+}
+
+function hasStatus(row: unknown): row is WithStatus {
+	return typeof row === 'object' && row !== null && 'status' in row;
+}
+
+const statusThemeMap: Record<string, string> = {
+	new: 'info',
+	running: 'warning',
+	completed: 'success',
+	error: 'danger',
+	success: 'success',
+};
+
+const statusLabelMap: Record<string, string> = {
+	new: locale.baseText('testDefinition.listRuns.status.new'),
+	running: locale.baseText('testDefinition.listRuns.status.running'),
+	completed: locale.baseText('testDefinition.listRuns.status.completed'),
+	error: locale.baseText('testDefinition.listRuns.status.error'),
+	success: locale.baseText('testDefinition.listRuns.status.success'),
+};
+
+function hasProperty(row: unknown, prop: string): row is Record<string, unknown> {
+	return typeof row === 'object' && row !== null && prop in row;
+}
+
+const getCellContent = (column: TestDefinitionTableColumn<T>, row: T) => {
+	if (column.formatter) {
+		return column.formatter(row);
+	}
+	return hasProperty(row, column.prop) ? row[column.prop] : undefined;
+};
+</script>
+
+<template>
+	<div v-if="column.route">
+		<a v-if="column.openInNewTab" :href="router.resolve(column.route(row)).href" target="_blank">
+			{{ getCellContent(column, row) }}
+		</a>
+		<router-link v-else :to="column.route(row)">
+			{{ getCellContent(column, row) }}
+		</router-link>
+	</div>
+
+	<N8nBadge
+		v-else-if="column.prop === 'status' && hasStatus(row)"
+		:theme="statusThemeMap[row.status]"
+		class="mr-4xs"
+	>
+		{{ statusLabelMap[row.status] }}
+	</N8nBadge>
+
+	<div v-else>
+		{{ getCellContent(column, row) }}
+	</div>
+</template>

packages/editor-ui/src/components/TestDefinition/shared/TestDefinitionTable.vue

@@ -0,0 +1,95 @@
+<script setup lang="ts" generic="T">
+import type { RouteLocationRaw } from 'vue-router';
+import TableCell from './TableCell.vue';
+import { ElTable, ElTableColumn } from 'element-plus';
+import { ref } from 'vue';
+import type { TableInstance } from 'element-plus';
+
+/**
+ * A reusable table component for displaying test definition data
+ * @template T - The type of data being displayed in the table rows
+ */
+
+/**
+ * Configuration for a table column
+ * @template TRow - The type of data in each table row
+ */
+export type TestDefinitionTableColumn<TRow> = {
+	prop: string;
+	label: string;
+	width?: number;
+	sortable?: boolean;
+	filters?: Array<{ text: string; value: string }>;
+	filterMethod?: (value: string, row: TRow) => boolean;
+	route?: (row: TRow) => RouteLocationRaw;
+	openInNewTab?: boolean;
+	formatter?: (row: TRow) => string;
+};
+
+withDefaults(
+	defineProps<{
+		data: T[];
+		columns: Array<TestDefinitionTableColumn<T>>;
+		showControls?: boolean;
+		defaultSort?: { prop: string; order: 'ascending' | 'descending' };
+		selectable?: boolean;
+		selectableFilter?: (row: T) => boolean;
+	}>(),
+	{
+		defaultSort: () => ({ prop: 'date', order: 'ascending' }),
+		selectable: false,
+		selectableFilter: () => true,
+	},
+);
+
+const tableRef = ref<TableInstance>();
+const selectedRows = ref<T[]>([]);
+
+const emit = defineEmits<{
+	rowClick: [row: T];
+	selectionChange: [rows: T[]];
+}>();
+
+const handleSelectionChange = (rows: T[]) => {
+	selectedRows.value = rows;
+	emit('selectionChange', rows);
+};
+</script>
+
+<template>
+	<ElTable
+		ref="tableRef"
+		:default-sort="defaultSort"
+		:data="data"
+		style="width: 100%"
+		:border="true"
+		max-height="800"
+		resizable
+		@selection-change="handleSelectionChange"
+	>
+		<ElTableColumn
+			v-if="selectable"
+			type="selection"
+			:selectable="selectableFilter"
+			width="55"
+			data-test-id="table-column-select"
+		/>
+		<ElTableColumn
+			v-for="column in columns"
+			:key="column.prop"
+			v-bind="column"
+			style="width: 100%"
+			:resizable="true"
+			data-test-id="table-column"
+		>
+			<template #default="{ row }">
+				<TableCell
+					:column="column"
+					:row="row"
+					@click="$emit('rowClick', row)"
+					data-test-id="table-cell"
+				/>
+			</template>
+		</ElTableColumn>
+	</ElTable>
+</template>

packages/editor-ui/src/components/TestDefinition/tests/MetricsInput.test.ts

@@ -6,11 +6,11 @@ import userEvent from '@testing-library/user-event';
 const renderComponent = createComponentRenderer(MetricsInput);
 
 describe('MetricsInput', () => {
-	let props: { modelValue: string[] };
+	let props: { modelValue: Array<{ name: string }> };
 
 	beforeEach(() => {
 		props = {
-			modelValue: ['Metric 1', 'Metric 2'],
+			modelValue: [{ name: 'Metric 1' }, { name: 'Metric 2' }],
 		};
 	});
 
@@ -25,14 +25,18 @@ describe('MetricsInput', () => {
 	it('should update a metric when typing in the input', async () => {
 		const { getAllByPlaceholderText, emitted } = renderComponent({
 			props: {
-				modelValue: [''],
+				modelValue: [{ name: '' }],
 			},
 		});
 		const inputs = getAllByPlaceholderText('Enter metric name');
 		await userEvent.type(inputs[0], 'Updated Metric 1');
 
-		expect(emitted('update:modelValue')).toBeTruthy();
-		expect(emitted('update:modelValue')).toEqual('Updated Metric 1'.split('').map((c) => [[c]]));
+		// Every character typed triggers an update event. Let's check the last emission.
+		const allEmits = emitted('update:modelValue');
+		expect(allEmits).toBeTruthy();
+		// The last emission should contain the fully updated name
+		const lastEmission = allEmits[allEmits.length - 1];
+		expect(lastEmission).toEqual([[{ name: 'Updated Metric 1' }]]);
 	});
 
 	it('should render correctly with no initial metrics', () => {
@@ -47,10 +51,89 @@ describe('MetricsInput', () => {
 		const { getByText, emitted } = renderComponent({ props });
 		const addButton = getByText('New metric');
 
-		addButton.click();
-		addButton.click();
-		addButton.click();
+		await userEvent.click(addButton);
+		await userEvent.click(addButton);
+		await userEvent.click(addButton);
 
-		expect(emitted('update:modelValue')).toHaveProperty('length', 3);
+		// Each click adds a new metric
+		const updateEvents = emitted('update:modelValue');
+		expect(updateEvents).toHaveLength(3);
+
+		// Check the structure of one of the emissions
+		// Initial: [{ name: 'Metric 1' }, { name: 'Metric 2' }]
+		// After first click: [{ name: 'Metric 1' }, { name: 'Metric 2' }, { name: '' }]
+		expect(updateEvents[0]).toEqual([[{ name: 'Metric 1' }, { name: 'Metric 2' }, { name: '' }]]);
+	});
+
+	it('should emit "deleteMetric" event when a delete button is clicked', async () => {
+		const { getAllByRole, emitted } = renderComponent({ props });
+
+		// Each metric row has a delete button, identified by "button"
+		const deleteButtons = getAllByRole('button', { name: '' });
+		expect(deleteButtons).toHaveLength(props.modelValue.length);
+
+		// Click on the delete button for the second metric
+		await userEvent.click(deleteButtons[1]);
+
+		expect(emitted('deleteMetric')).toBeTruthy();
+		expect(emitted('deleteMetric')[0]).toEqual([{ name: 'Metric 2' }]);
+	});
+
+	it('should emit multiple update events as the user types and reflect the final name correctly', async () => {
+		const { getAllByPlaceholderText, emitted } = renderComponent({
+			props: {
+				modelValue: [{ name: '' }],
+			},
+		});
+		const inputs = getAllByPlaceholderText('Enter metric name');
+		await userEvent.type(inputs[0], 'ABC');
+
+		const allEmits = emitted('update:modelValue');
+		expect(allEmits).toBeTruthy();
+		// Each character typed should emit a new value
+		expect(allEmits.length).toBe(3);
+		expect(allEmits[2]).toEqual([[{ name: 'ABC' }]]);
+	});
+
+	it('should not break if metrics are empty and still allow adding a new metric', async () => {
+		props.modelValue = [];
+		const { queryAllByRole, getByText, emitted } = renderComponent({ props });
+
+		// No metrics initially
+		const inputs = queryAllByRole('textbox');
+		expect(inputs).toHaveLength(0);
+
+		const addButton = getByText('New metric');
+		await userEvent.click(addButton);
+
+		const updates = emitted('update:modelValue');
+		expect(updates).toBeTruthy();
+		expect(updates[0]).toEqual([[{ name: '' }]]);
+
+		// After adding one metric, we should now have an input
+		const { getAllByPlaceholderText } = renderComponent({
+			props: { modelValue: [{ name: '' }] },
+		});
+		const updatedInputs = getAllByPlaceholderText('Enter metric name');
+		expect(updatedInputs).toHaveLength(1);
+	});
+
+	it('should handle deleting the first metric and still display remaining metrics correctly', async () => {
+		const { getAllByPlaceholderText, getAllByRole, rerender, emitted } = renderComponent({
+			props,
+		});
+		const inputs = getAllByPlaceholderText('Enter metric name');
+		expect(inputs).toHaveLength(2);
+
+		const deleteButtons = getAllByRole('button', { name: '' });
+		await userEvent.click(deleteButtons[0]);
+
+		expect(emitted('deleteMetric')).toBeTruthy();
+		expect(emitted('deleteMetric')[0]).toEqual([{ name: 'Metric 1' }]);
+
+		await rerender({ modelValue: [{ name: 'Metric 2' }] });
+		const updatedInputs = getAllByPlaceholderText('Enter metric name');
+		expect(updatedInputs).toHaveLength(1);
+		expect(updatedInputs[0]).toHaveValue('Metric 2');
 	});
 });

packages/editor-ui/src/components/TestDefinition/tests/useMetricsChart.test.ts

@@ -0,0 +1,127 @@
+import { describe, it, expect } from 'vitest';
+import { useMetricsChart } from '../composables/useMetricsChart';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+
+describe('useMetricsChart', () => {
+	const mockRuns: TestRunRecord[] = [
+		{
+			id: '1',
+			testDefinitionId: 'test1',
+			status: 'completed',
+			createdAt: '2025-01-06T10:00:00Z',
+			updatedAt: '2025-01-06T10:00:00Z',
+			completedAt: '2025-01-06T10:00:00Z',
+			runAt: '2025-01-06T10:00:00Z',
+			metrics: { responseTime: 100, successRate: 95 },
+		},
+		{
+			id: '2',
+			testDefinitionId: 'test1',
+			status: 'completed',
+			createdAt: '2025-01-06T10:00:00Z',
+			updatedAt: '2025-01-06T10:00:00Z',
+			completedAt: '2025-01-06T10:00:00Z',
+			runAt: '2025-01-06T10:00:00Z',
+			metrics: { responseTime: 150, successRate: 98 },
+		},
+	] as TestRunRecord[];
+
+	describe('generateChartData', () => {
+		it('should generate correct chart data structure', () => {
+			const { generateChartData } = useMetricsChart('light');
+			const result = generateChartData(mockRuns, 'responseTime');
+
+			expect(result.labels).toHaveLength(2);
+			expect(result.datasets).toHaveLength(1);
+			expect(result.datasets[0].data).toEqual([100, 150]);
+		});
+
+		it('should sort runs by date', () => {
+			const unsortedRuns = [
+				{
+					id: '1',
+					testDefinitionId: 'test1',
+					status: 'completed',
+					createdAt: '2025-01-06T10:05:00Z',
+					updatedAt: '2025-01-06T10:05:00Z',
+					completedAt: '2025-01-06T10:05:00Z',
+					runAt: '2025-01-06T10:05:00Z',
+					metrics: { responseTime: 150 },
+				},
+				{
+					id: '2',
+					testDefinitionId: 'test1',
+					status: 'completed',
+					createdAt: '2025-01-06T10:00:00Z',
+					updatedAt: '2025-01-06T10:00:00Z',
+					completedAt: '2025-01-06T10:00:00Z',
+					runAt: '2025-01-06T10:00:00Z',
+					metrics: { responseTime: 100 },
+				},
+			] as TestRunRecord[];
+
+			const { generateChartData } = useMetricsChart('light');
+			const result = generateChartData(unsortedRuns, 'responseTime');
+
+			expect(result.datasets[0].data).toEqual([100, 150]);
+		});
+
+		it('should filter out runs without specified metric', () => {
+			const runsWithMissingMetrics = [
+				{
+					id: '1',
+					testDefinitionId: 'test1',
+					status: 'completed',
+					createdAt: '2025-01-06T10:00:00Z',
+					updatedAt: '2025-01-06T10:00:00Z',
+					completedAt: '2025-01-06T10:00:00Z',
+					runAt: '2025-01-06T10:00:00Z',
+					metrics: { responseTime: 100 },
+				},
+				{
+					id: '2',
+					testDefinitionId: 'test1',
+					status: 'completed',
+					createdAt: '2025-01-06T10:00:00Z',
+					updatedAt: '2025-01-06T10:00:00Z',
+					completedAt: '2025-01-06T10:00:00Z',
+					runAt: '2025-01-06T10:00:00Z',
+					metrics: {},
+				},
+			] as TestRunRecord[];
+
+			const { generateChartData } = useMetricsChart('light');
+			const result = generateChartData(runsWithMissingMetrics, 'responseTime');
+
+			expect(result.labels).toHaveLength(1);
+			expect(result.datasets[0].data).toEqual([100]);
+		});
+
+		it('should handle dark theme colors', () => {
+			const { generateChartData } = useMetricsChart('dark');
+			const result = generateChartData(mockRuns, 'responseTime');
+
+			expect(result.datasets[0].pointHoverBackgroundColor).toBe('rgb(32, 32, 32)');
+		});
+	});
+
+	describe('generateChartOptions', () => {
+		it('should generate correct chart options structure', () => {
+			const { generateChartOptions } = useMetricsChart('light');
+			const result = generateChartOptions({ metric: 'responseTime', xTitle: 'Time' });
+
+			expect(result.scales?.y?.title?.text).toBe('responseTime');
+			expect(result.scales?.x?.title?.text).toBe('Time');
+			expect(result.responsive).toBe(true);
+			expect(result.maintainAspectRatio).toBe(false);
+		});
+
+		it('should apply correct theme colors', () => {
+			const { generateChartOptions } = useMetricsChart('dark');
+			const result = generateChartOptions({ metric: 'responseTime', xTitle: 'Time' });
+
+			expect(result.scales?.y?.ticks?.color).toBe('rgb(255, 255, 255)');
+			expect(result.plugins?.tooltip?.backgroundColor).toBe('rgb(32, 32, 32)');
+		});
+	});
+});

packages/editor-ui/src/components/TestDefinition/tests/useTestDefinitionForm.test.ts

@@ -12,18 +12,21 @@ const TEST_DEF_A: TestDefinitionRecord = {
 	evaluationWorkflowId: '456',
 	workflowId: '123',
 	annotationTagId: '789',
+	annotationTag: null,
 };
 const TEST_DEF_B: TestDefinitionRecord = {
 	id: '2',
 	name: 'Test Definition B',
 	workflowId: '123',
 	description: 'Description B',
+	annotationTag: null,
 };
 const TEST_DEF_NEW: TestDefinitionRecord = {
 	id: '3',
 	workflowId: '123',
 	name: 'New Test Definition',
 	description: 'New Description',
+	annotationTag: null,
 };
 
 beforeEach(() => {
@@ -35,44 +38,78 @@ afterEach(() => {
 	vi.clearAllMocks();
 });
 
-describe('useTestDefinitionForm', async () => {
-	it('should initialize with default props', async () => {
+describe('useTestDefinitionForm', () => {
+	it('should initialize with default props', () => {
 		const { state } = useTestDefinitionForm();
 
-		expect(state.value.description).toEqual('');
+		expect(state.value.description).toBe('');
 		expect(state.value.name.value).toContain('My Test');
-		expect(state.value.tags.appliedTagIds).toEqual([]);
-		expect(state.value.metrics).toEqual(['']);
-		expect(state.value.evaluationWorkflow.value).toEqual('');
+		expect(state.value.tags.value).toEqual([]);
+		expect(state.value.metrics).toEqual([]);
+		expect(state.value.evaluationWorkflow.value).toBe('');
 	});
 
 	it('should load test data', async () => {
 		const { loadTestData, state } = useTestDefinitionForm();
-		const fetchSpy = vi.fn();
+		const fetchSpy = vi.spyOn(useTestDefinitionStore(), 'fetchAll');
+		const fetchMetricsSpy = vi.spyOn(useTestDefinitionStore(), 'fetchMetrics').mockResolvedValue([
+			{
+				id: 'metric1',
+				name: 'Metric 1',
+				testDefinitionId: TEST_DEF_A.id,
+			},
+		]);
 		const evaluationsStore = mockedStore(useTestDefinitionStore);
 
-		expect(state.value.description).toEqual('');
-		expect(state.value.name.value).toContain('My Test');
 		evaluationsStore.testDefinitionsById = {
 			[TEST_DEF_A.id]: TEST_DEF_A,
 			[TEST_DEF_B.id]: TEST_DEF_B,
 		};
-		evaluationsStore.fetchAll = fetchSpy;
 
 		await loadTestData(TEST_DEF_A.id);
 		expect(fetchSpy).toBeCalled();
+		expect(fetchMetricsSpy).toBeCalledWith(TEST_DEF_A.id);
 		expect(state.value.name.value).toEqual(TEST_DEF_A.name);
 		expect(state.value.description).toEqual(TEST_DEF_A.description);
-		expect(state.value.tags.appliedTagIds).toEqual([TEST_DEF_A.annotationTagId]);
+		expect(state.value.tags.value).toEqual([TEST_DEF_A.annotationTagId]);
 		expect(state.value.evaluationWorkflow.value).toEqual(TEST_DEF_A.evaluationWorkflowId);
+		expect(state.value.metrics).toEqual([
+			{ id: 'metric1', name: 'Metric 1', testDefinitionId: TEST_DEF_A.id },
+		]);
+	});
+
+	it('should gracefully handle loadTestData when no test definition found', async () => {
+		const { loadTestData, state } = useTestDefinitionForm();
+		const fetchSpy = vi.spyOn(useTestDefinitionStore(), 'fetchAll');
+		const evaluationsStore = mockedStore(useTestDefinitionStore);
+
+		evaluationsStore.testDefinitionsById = {};
+
+		await loadTestData('unknown-id');
+		expect(fetchSpy).toBeCalled();
+		// Should remain unchanged since no definition found
+		expect(state.value.description).toBe('');
+		expect(state.value.name.value).toContain('My Test');
+		expect(state.value.tags.value).toEqual([]);
+		expect(state.value.metrics).toEqual([]);
+	});
+
+	it('should handle errors while loading test data', async () => {
+		const { loadTestData } = useTestDefinitionForm();
+		const fetchSpy = vi
+			.spyOn(useTestDefinitionStore(), 'fetchAll')
+			.mockRejectedValue(new Error('Fetch Failed'));
+		const consoleErrorSpy = vi.spyOn(console, 'error').mockImplementation(() => {});
+
+		await loadTestData(TEST_DEF_A.id);
+		expect(fetchSpy).toBeCalled();
+		expect(consoleErrorSpy).toBeCalledWith('Failed to load test data', expect.any(Error));
+		consoleErrorSpy.mockRestore();
 	});
 
 	it('should save a new test', async () => {
 		const { createTest, state } = useTestDefinitionForm();
-		const createSpy = vi.fn().mockResolvedValue(TEST_DEF_NEW);
-		const evaluationsStore = mockedStore(useTestDefinitionStore);
-
-		evaluationsStore.create = createSpy;
+		const createSpy = vi.spyOn(useTestDefinitionStore(), 'create').mockResolvedValue(TEST_DEF_NEW);
 
 		state.value.name.value = TEST_DEF_NEW.name;
 		state.value.description = TEST_DEF_NEW.description ?? '';
@@ -86,12 +123,24 @@ describe('useTestDefinitionForm', async () => {
 		expect(newTest).toEqual(TEST_DEF_NEW);
 	});
 
+	it('should handle errors when creating a new test', async () => {
+		const { createTest } = useTestDefinitionForm();
+		const createSpy = vi
+			.spyOn(useTestDefinitionStore(), 'create')
+			.mockRejectedValue(new Error('Create Failed'));
+
+		await expect(createTest('123')).rejects.toThrow('Create Failed');
+		expect(createSpy).toBeCalled();
+	});
+
 	it('should update an existing test', async () => {
 		const { updateTest, state } = useTestDefinitionForm();
-		const updateSpy = vi.fn().mockResolvedValue(TEST_DEF_B);
-		const evaluationsStore = mockedStore(useTestDefinitionStore);
-
-		evaluationsStore.update = updateSpy;
+		const updatedBTest = {
+			...TEST_DEF_B,
+			updatedAt: '2022-01-01T00:00:00.000Z',
+			createdAt: '2022-01-01T00:00:00.000Z',
+		};
+		const updateSpy = vi.spyOn(useTestDefinitionStore(), 'update').mockResolvedValue(updatedBTest);
 
 		state.value.name.value = TEST_DEF_B.name;
 		state.value.description = TEST_DEF_B.description ?? '';
@@ -102,75 +151,183 @@ describe('useTestDefinitionForm', async () => {
 			name: TEST_DEF_B.name,
 			description: TEST_DEF_B.description,
 		});
-		expect(updatedTest).toEqual(TEST_DEF_B);
+		expect(updatedTest).toEqual(updatedBTest);
 	});
 
-	it('should start editing a field', async () => {
+	it('should throw an error if no testId is provided when updating a test', async () => {
+		const { updateTest } = useTestDefinitionForm();
+		await expect(updateTest('')).rejects.toThrow('Test ID is required for updating a test');
+	});
+
+	it('should handle errors when updating a test', async () => {
+		const { updateTest, state } = useTestDefinitionForm();
+		const updateSpy = vi
+			.spyOn(useTestDefinitionStore(), 'update')
+			.mockRejectedValue(new Error('Update Failed'));
+
+		state.value.name.value = 'Test';
+		state.value.description = 'Some description';
+
+		await expect(updateTest(TEST_DEF_A.id)).rejects.toThrow('Update Failed');
+		expect(updateSpy).toBeCalled();
+	});
+
+	it('should delete a metric', async () => {
+		const { state, deleteMetric } = useTestDefinitionForm();
+		const evaluationsStore = mockedStore(useTestDefinitionStore);
+		const deleteMetricSpy = vi.spyOn(evaluationsStore, 'deleteMetric');
+
+		state.value.metrics = [
+			{
+				id: 'metric1',
+				name: 'Metric 1',
+				testDefinitionId: '1',
+			},
+			{
+				id: 'metric2',
+				name: 'Metric 2',
+				testDefinitionId: '1',
+			},
+		];
+
+		await deleteMetric('metric1', TEST_DEF_A.id);
+		expect(deleteMetricSpy).toBeCalledWith({ id: 'metric1', testDefinitionId: TEST_DEF_A.id });
+		expect(state.value.metrics).toEqual([
+			{ id: 'metric2', name: 'Metric 2', testDefinitionId: '1' },
+		]);
+	});
+
+	it('should update metrics', async () => {
+		const { state, updateMetrics } = useTestDefinitionForm();
+		const evaluationsStore = mockedStore(useTestDefinitionStore);
+		const updateMetricSpy = vi.spyOn(evaluationsStore, 'updateMetric');
+		const createMetricSpy = vi
+			.spyOn(evaluationsStore, 'createMetric')
+			.mockResolvedValue({ id: 'metric_new', name: 'Metric 2', testDefinitionId: TEST_DEF_A.id });
+
+		state.value.metrics = [
+			{
+				id: 'metric1',
+				name: 'Metric 1',
+				testDefinitionId: TEST_DEF_A.id,
+			},
+			{
+				id: '',
+				name: 'Metric 2',
+				testDefinitionId: TEST_DEF_A.id,
+			}, // New metric that needs creation
+		];
+
+		await updateMetrics(TEST_DEF_A.id);
+		expect(createMetricSpy).toHaveBeenCalledWith({
+			name: 'Metric 2',
+			testDefinitionId: TEST_DEF_A.id,
+		});
+		expect(updateMetricSpy).toHaveBeenCalledWith({
+			name: 'Metric 1',
+			id: 'metric1',
+			testDefinitionId: TEST_DEF_A.id,
+		});
+		expect(state.value.metrics).toEqual([
+			{ id: 'metric1', name: 'Metric 1', testDefinitionId: TEST_DEF_A.id },
+			{ id: 'metric_new', name: 'Metric 2', testDefinitionId: TEST_DEF_A.id },
+		]);
+	});
+
+	it('should start editing a field', () => {
 		const { state, startEditing } = useTestDefinitionForm();
 
-		await startEditing('name');
+		startEditing('name');
 		expect(state.value.name.isEditing).toBe(true);
 		expect(state.value.name.tempValue).toBe(state.value.name.value);
 
-		await startEditing('tags');
+		startEditing('tags');
 		expect(state.value.tags.isEditing).toBe(true);
+		expect(state.value.tags.tempValue).toEqual(state.value.tags.value);
 	});
 
-	it('should save changes to a field', async () => {
+	it('should do nothing if startEditing is called while already editing', () => {
+		const { state, startEditing } = useTestDefinitionForm();
+		state.value.name.isEditing = true;
+		state.value.name.tempValue = 'Original Name';
+
+		startEditing('name');
+		// Should remain unchanged because it was already editing
+		expect(state.value.name.isEditing).toBe(true);
+		expect(state.value.name.tempValue).toBe('Original Name');
+	});
+
+	it('should save changes to a field', () => {
 		const { state, startEditing, saveChanges } = useTestDefinitionForm();
 
-		await startEditing('name');
+		// Name
+		startEditing('name');
 		state.value.name.tempValue = 'New Name';
 		saveChanges('name');
 		expect(state.value.name.isEditing).toBe(false);
 		expect(state.value.name.value).toBe('New Name');
 
-		await startEditing('tags');
-		state.value.tags.appliedTagIds = ['123'];
+		// Tags
+		startEditing('tags');
+		state.value.tags.tempValue = ['123'];
 		saveChanges('tags');
 		expect(state.value.tags.isEditing).toBe(false);
-		expect(state.value.tags.appliedTagIds).toEqual(['123']);
+		expect(state.value.tags.value).toEqual(['123']);
 	});
 
-	it('should cancel editing a field', async () => {
+	it('should cancel editing a field', () => {
 		const { state, startEditing, cancelEditing } = useTestDefinitionForm();
 
-		await startEditing('name');
+		const originalName = state.value.name.value;
+		startEditing('name');
 		state.value.name.tempValue = 'New Name';
 		cancelEditing('name');
 		expect(state.value.name.isEditing).toBe(false);
-		expect(state.value.name.tempValue).toBe('');
+		expect(state.value.name.tempValue).toBe(originalName);
 
-		await startEditing('tags');
-		state.value.tags.appliedTagIds = ['123'];
+		const originalTags = [...state.value.tags.value];
+		startEditing('tags');
+		state.value.tags.tempValue = ['123'];
 		cancelEditing('tags');
 		expect(state.value.tags.isEditing).toBe(false);
+		expect(state.value.tags.tempValue).toEqual(originalTags);
 	});
 
-	it('should handle keydown - Escape', async () => {
+	it('should handle keydown - Escape', () => {
 		const { state, startEditing, handleKeydown } = useTestDefinitionForm();
 
-		await startEditing('name');
+		startEditing('name');
 		handleKeydown(new KeyboardEvent('keydown', { key: 'Escape' }), 'name');
 		expect(state.value.name.isEditing).toBe(false);
 
-		await startEditing('tags');
+		startEditing('tags');
 		handleKeydown(new KeyboardEvent('keydown', { key: 'Escape' }), 'tags');
 		expect(state.value.tags.isEditing).toBe(false);
 	});
 
-	it('should handle keydown - Enter', async () => {
+	it('should handle keydown - Enter', () => {
 		const { state, startEditing, handleKeydown } = useTestDefinitionForm();
 
-		await startEditing('name');
+		startEditing('name');
 		state.value.name.tempValue = 'New Name';
 		handleKeydown(new KeyboardEvent('keydown', { key: 'Enter' }), 'name');
 		expect(state.value.name.isEditing).toBe(false);
 		expect(state.value.name.value).toBe('New Name');
 
-		await startEditing('tags');
-		state.value.tags.appliedTagIds = ['123'];
+		startEditing('tags');
+		state.value.tags.tempValue = ['123'];
 		handleKeydown(new KeyboardEvent('keydown', { key: 'Enter' }), 'tags');
 		expect(state.value.tags.isEditing).toBe(false);
+		expect(state.value.tags.value).toEqual(['123']);
+	});
+
+	it('should not save changes when shift+Enter is pressed', () => {
+		const { state, startEditing, handleKeydown } = useTestDefinitionForm();
+
+		startEditing('name');
+		state.value.name.tempValue = 'New Name With Shift';
+		handleKeydown(new KeyboardEvent('keydown', { key: 'Enter', shiftKey: true }), 'name');
+		expect(state.value.name.isEditing).toBe(true);
+		expect(state.value.name.value).not.toBe('New Name With Shift');
 	});
 });

packages/editor-ui/src/components/TestDefinition/types.ts

@@ -1,7 +1,29 @@
+import type { TestMetricRecord, TestRunRecord } from '@/api/testDefinition.ee';
+import type { INodeParameterResourceLocator } from 'n8n-workflow';
+
+export interface EditableField<T = string> {
+	value: T;
+	tempValue: T;
+	isEditing: boolean;
+}
+
+export interface EditableFormState {
+	name: EditableField<string>;
+	tags: EditableField<string[]>;
+}
+
+export interface EvaluationFormState extends EditableFormState {
+	description: string;
+	evaluationWorkflow: INodeParameterResourceLocator;
+	metrics: TestMetricRecord[];
+	mockedNodes: Array<{ name: string }>;
+}
+
 export interface TestExecution {
 	lastRun: string | null;
 	errorRate: number | null;
 	metrics: Record<string, number>;
+	status: TestRunRecord['status'];
 }
 
 export interface TestListItem {

packages/editor-ui/src/components/WorkflowTagsDropdown.vue

@@ -15,7 +15,7 @@ interface TagsDropdownWrapperProps {
 const props = withDefaults(defineProps<TagsDropdownWrapperProps>(), {
 	placeholder: '',
 	modelValue: () => [],
-	createEnabled: false,
+	createEnabled: true,
 	eventBus: null,
 });
 

packages/editor-ui/src/components/canvas/Canvas.vue

@@ -80,6 +80,7 @@ const props = withDefaults(
 		executing?: boolean;
 		keyBindings?: boolean;
 		showBugReportingButton?: boolean;
+		loading?: boolean;
 	}>(),
 	{
 		id: 'canvas',
@@ -90,6 +91,7 @@ const props = withDefaults(
 		readOnly: false,
 		executing: false,
 		keyBindings: true,
+		loading: false,
 	},
 );
 
@@ -131,7 +133,7 @@ const isPaneReady = ref(false);
 
 const classes = computed(() => ({
 	[$style.canvas]: true,
-	[$style.ready]: isPaneReady.value,
+	[$style.ready]: !props.loading && isPaneReady.value,
 }));
 
 /**
@@ -695,7 +697,11 @@ provide(CanvasKey, {
 				@update:outputs="onUpdateNodeOutputs"
 				@move="onUpdateNodePosition"
 				@add="onClickNodeAdd"
-			/>
+			>
+				<template v-if="$slots.nodeToolbar" #toolbar="toolbarProps">
+					<slot name="nodeToolbar" v-bind="toolbarProps" />
+				</template>
+			</Node>
 		</template>
 
 		<template #edge-canvas-edge="edgeProps">

packages/editor-ui/src/components/canvas/elements/nodes/CanvasNode.vue

@@ -39,6 +39,14 @@ type Props = NodeProps<CanvasNodeData> & {
 	hovered?: boolean;
 };
 
+const slots = defineSlots<{
+	toolbar?: (props: {
+		inputs: (typeof mainInputs)['value'];
+		outputs: (typeof mainOutputs)['value'];
+		data: CanvasNodeData;
+	}) => void;
+}>();
+
 const emit = defineEmits<{
 	add: [id: string, handle: string];
 	delete: [id: string];
@@ -62,6 +70,10 @@ const contextMenu = useContextMenu();
 
 const { connectingHandle } = useCanvas();
 
+/*
+  Toolbar slot classes
+*/
+const nodeClasses = ref<string[]>([]);
 const inputs = computed(() => props.data.inputs);
 const outputs = computed(() => props.data.outputs);
 const connections = computed(() => props.data.connections);
@@ -83,6 +95,7 @@ const classes = computed(() => ({
 	[style.showToolbar]: showToolbar.value,
 	hovered: props.hovered,
 	selected: props.selected,
+	...Object.fromEntries([...nodeClasses.value].map((c) => [c, true])),
 }));
 
 /**
@@ -92,7 +105,7 @@ const classes = computed(() => ({
 const canvasNodeEventBus = ref(createEventBus<CanvasNodeEventBusEvents>());
 
 function emitCanvasNodeEvent(event: CanvasEventBusEvents['nodes:action']) {
-	if (event.ids.includes(props.id)) {
+	if (event.ids.includes(props.id) && canvasNodeEventBus.value) {
 		canvasNodeEventBus.value.emit(event.action, event.payload);
 	}
 }
@@ -233,6 +246,12 @@ function onMove(position: XYPosition) {
 	emit('move', props.id, position);
 }
 
+function onUpdateClass({ className, add = true }: CanvasNodeEventBusEvents['update:node:class']) {
+	nodeClasses.value = add
+		? [...new Set([...nodeClasses.value, className])]
+		: nodeClasses.value.filter((c) => c !== className);
+}
+
 /**
  * Provide
  */
@@ -282,10 +301,12 @@ watch(outputs, (newValue, oldValue) => {
 
 onMounted(() => {
 	props.eventBus?.on('nodes:action', emitCanvasNodeEvent);
+	canvasNodeEventBus.value?.on('update:node:class', onUpdateClass);
 });
 
 onBeforeUnmount(() => {
 	props.eventBus?.off('nodes:action', emitCanvasNodeEvent);
+	canvasNodeEventBus.value?.off('update:node:class', onUpdateClass);
 });
 </script>
 
@@ -323,8 +344,13 @@ onBeforeUnmount(() => {
 			/>
 		</template>
 
+		<template v-if="slots.toolbar">
+			<slot name="toolbar" :inputs="mainInputs" :outputs="mainOutputs" :data="data" />
+		</template>
+
 		<CanvasNodeToolbar
-			v-if="nodeTypeDescription"
+			v-else-if="nodeTypeDescription"
+			data-test-id="canvas-node-toolbar"
 			:read-only="readOnly"
 			:class="$style.canvasNodeToolbar"
 			@delete="onDelete"

packages/editor-ui/src/constants.ts

@@ -53,6 +53,7 @@ export const WORKFLOW_SETTINGS_MODAL_KEY = 'settings';
 export const WORKFLOW_SHARE_MODAL_KEY = 'workflowShare';
 export const PERSONALIZATION_MODAL_KEY = 'personalization';
 export const CONTACT_PROMPT_MODAL_KEY = 'contactPrompt';
+export const NODE_PINNING_MODAL_KEY = 'nodePinning';
 export const NPS_SURVEY_MODAL_KEY = 'npsSurvey';
 export const WORKFLOW_ACTIVE_MODAL_KEY = 'activation';
 export const COMMUNITY_PACKAGE_INSTALL_MODAL_KEY = 'communityPackageInstall';
@@ -497,6 +498,9 @@ export const enum VIEWS {
 	WORKFLOW_EXECUTIONS = 'WorkflowExecutions',
 	TEST_DEFINITION = 'TestDefinition',
 	TEST_DEFINITION_EDIT = 'TestDefinitionEdit',
+	TEST_DEFINITION_RUNS = 'TestDefinitionRuns',
+	TEST_DEFINITION_RUNS_COMPARE = 'TestDefinitionRunsCompare',
+	TEST_DEFINITION_RUNS_DETAIL = 'TestDefinitionRunsDetail',
 	NEW_TEST_DEFINITION = 'NewTestDefinition',
 	USAGE = 'Usage',
 	LOG_STREAMING_SETTINGS = 'LogStreamingSettingsView',

packages/editor-ui/src/plugins/i18n/locales/en.json

@@ -2557,7 +2557,7 @@
 	"projects.menu.overview": "Overview",
 	"projects.menu.title": "Projects",
 	"projects.menu.personal": "Personal",
-	"projects.menu.addFirstProject": "Add first project",
+	"projects.menu.addFirstProject": "Add project",
 	"projects.settings": "Project settings",
 	"projects.settings.newProjectName": "My project",
 	"projects.settings.iconPicker.button.tooltip": "Choose project icon",
@@ -2787,24 +2787,58 @@
 	"testDefinition.edit.testSaved": "Test saved",
 	"testDefinition.edit.testSaveFailed": "Failed to save test",
 	"testDefinition.edit.description": "Description",
+	"testDefinition.edit.description.tooltip": "Add details about what this test evaluates and what success looks like",
 	"testDefinition.edit.tagName": "Tag name",
 	"testDefinition.edit.step.intro": "When running a test",
-	"testDefinition.edit.step.executions": "Fetch 5 past executions",
+	"testDefinition.edit.step.executions": "Fetch past executions | Fetch {count} past execution | Fetch {count} past executions",
+	"testDefinition.edit.step.executions.tooltip": "Select which tagged executions to use as test cases. Each execution will be replayed to compare performance",
 	"testDefinition.edit.step.nodes": "Mock nodes",
 	"testDefinition.edit.step.mockedNodes": "No nodes mocked | {count} node mocked | {count} nodes mocked",
+	"testDefinition.edit.step.nodes.tooltip": "Replace specific nodes with test data to isolate what you're testing",
 	"testDefinition.edit.step.reRunExecutions": "Re-run executions",
+	"testDefinition.edit.step.reRunExecutions.tooltip": "Each test case will be re-run using the current workflow version",
 	"testDefinition.edit.step.compareExecutions": "Compare each past and new execution",
+	"testDefinition.edit.step.compareExecutions.tooltip": "Select which workflow to use for running the comparison tests",
 	"testDefinition.edit.step.metrics": "Summarise metrics",
+	"testDefinition.edit.step.metrics.tooltip": "Define which output fields to track and compare between test runs",
 	"testDefinition.edit.step.collapse": "Collapse",
 	"testDefinition.edit.step.expand": "Expand",
+	"testDefinition.edit.selectNodes": "Select nodes",
+	"testDefinition.edit.runExecution": "Run execution",
+	"testDefinition.edit.pastRuns": "Past runs",
+	"testDefinition.edit.pastRuns.total": "No runs | {count} run | {count} runs",
+	"testDefinition.edit.nodesPinning.pinButtonTooltip": "Pin execution data of this node during test run",
 	"testDefinition.list.testDeleted": "Test deleted",
 	"testDefinition.list.tests": "Tests",
 	"testDefinition.list.createNew": "Create new test",
 	"testDefinition.list.actionDescription": "Replay past executions to check whether performance has changed",
 	"testDefinition.list.actionButton": "Create Test",
-	"testDefinition.list.testCases": "No test cases | {count} test case | {count} test cases",
-	"testDefinition.list.lastRun": "Ran {lastRun}",
+	"testDefinition.list.testRuns": "No test runs | {count} test run | {count} test runs",
+	"testDefinition.list.lastRun": "Ran",
+	"testDefinition.list.running": "Running",
 	"testDefinition.list.errorRate": "Error rate: {errorRate}",
+	"testDefinition.list.testStartError": "Failed to start test run",
+	"testDefinition.list.testStarted": "Test run started",
+	"testDefinition.list.loadError": "Failed to load tests",
+	"testDefinition.listRuns.status.new": "New",
+	"testDefinition.listRuns.status.running": "Running",
+	"testDefinition.listRuns.status.completed": "Completed",
+	"testDefinition.listRuns.status.error": "Error",
+	"testDefinition.listRuns.status.success": "Success",
+	"testDefinition.listRuns.metricsOverTime": "Metrics over time",
+	"testDefinition.listRuns.status": "Status",
+	"testDefinition.listRuns.runNumber": "Run #",
+	"testDefinition.listRuns.runDate": "Run date",
+	"testDefinition.listRuns.runStatus": "Run status",
+	"testDefinition.listRuns.noRuns": "No test runs",
+	"testDefinition.listRuns.noRuns.description": "Run a test to see the results here",
+	"testDefinition.listRuns.deleteRuns": "No runs to delete | Delete {count} run | Delete {count} runs",
+	"testDefinition.listRuns.noRuns.button": "Run Test",
+	"testDefinition.runDetail.ranAt": "Ran at",
+	"testDefinition.runDetail.testCase": "Test case",
+	"testDefinition.runDetail.testCase.id": "Test case ID",
+	"testDefinition.runDetail.testCase.status": "Test case status",
+	"testDefinition.runDetail.totalCases": "Total cases",
 	"testDefinition.runTest": "Run Test",
 	"testDefinition.notImplemented": "This feature is not implemented yet!",
 	"testDefinition.viewDetails": "View Details",

packages/editor-ui/src/router.ts

@@ -18,6 +18,8 @@ import type { RouterMiddleware } from '@/types/router';
 import { initializeAuthenticatedFeatures, initializeCore } from '@/init';
 import { tryToParseNumber } from '@/utils/typesUtils';
 import { projectsRoutes } from '@/routes/projects.routes';
+import TestDefinitionRunsListView from './views/TestDefinition/TestDefinitionRunsListView.vue';
+import TestDefinitionRunDetailView from './views/TestDefinition/TestDefinitionRunDetailView.vue';
 
 const ChangePasswordView = async () => await import('./views/ChangePasswordView.vue');
 const ErrorView = async () => await import('./views/ErrorView.vue');
@@ -299,6 +301,32 @@ export const routes: RouteRecordRaw[] = [
 					middleware: ['authenticated'],
 				},
 			},
+			{
+				path: ':testId/runs',
+				name: VIEWS.TEST_DEFINITION_RUNS,
+				components: {
+					default: TestDefinitionRunsListView,
+					header: MainHeader,
+					sidebar: MainSidebar,
+				},
+				meta: {
+					keepWorkflowAlive: true,
+					middleware: ['authenticated'],
+				},
+			},
+			{
+				path: ':testId/runs/:runId',
+				name: VIEWS.TEST_DEFINITION_RUNS_DETAIL,
+				components: {
+					default: TestDefinitionRunDetailView,
+					header: MainHeader,
+					sidebar: MainSidebar,
+				},
+				meta: {
+					keepWorkflowAlive: true,
+					middleware: ['authenticated'],
+				},
+			},
 		],
 	},
 	{

packages/editor-ui/src/stores/executions.store.ts

@@ -172,6 +172,7 @@ export const useExecutionsStore = defineStore('executions', () => {
 
 			executionsCount.value = data.count;
 			executionsCountEstimated.value = data.estimated;
+			return data;
 		} catch (e) {
 			throw e;
 		} finally {

packages/editor-ui/src/stores/testDefinition.store.ee.test.ts

@@ -2,21 +2,49 @@ import { createPinia, setActivePinia } from 'pinia';
 import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee'; // Adjust the import path as necessary
 import { useRootStore } from '@/stores/root.store';
 import { usePostHog } from '@/stores/posthog.store';
-import type { TestDefinitionRecord } from '@/api/testDefinition.ee';
+import type { TestDefinitionRecord, TestRunRecord } from '@/api/testDefinition.ee';
 
-const { createTestDefinition, deleteTestDefinition, getTestDefinitions, updateTestDefinition } =
-	vi.hoisted(() => ({
-		getTestDefinitions: vi.fn(),
-		createTestDefinition: vi.fn(),
-		updateTestDefinition: vi.fn(),
-		deleteTestDefinition: vi.fn(),
-	}));
+const {
+	createTestDefinition,
+	deleteTestDefinition,
+	getTestDefinitions,
+	updateTestDefinition,
+	getTestMetrics,
+	createTestMetric,
+	updateTestMetric,
+	deleteTestMetric,
+	getTestRuns,
+	getTestRun,
+	startTestRun,
+	deleteTestRun,
+} = vi.hoisted(() => ({
+	getTestDefinitions: vi.fn(),
+	createTestDefinition: vi.fn(),
+	updateTestDefinition: vi.fn(),
+	deleteTestDefinition: vi.fn(),
+	getTestMetrics: vi.fn(),
+	createTestMetric: vi.fn(),
+	updateTestMetric: vi.fn(),
+	deleteTestMetric: vi.fn(),
+	getTestRuns: vi.fn(),
+	getTestRun: vi.fn(),
+	startTestRun: vi.fn(),
+	deleteTestRun: vi.fn(),
+}));
 
 vi.mock('@/api/testDefinition.ee', () => ({
 	createTestDefinition,
 	deleteTestDefinition,
 	getTestDefinitions,
 	updateTestDefinition,
+	getTestMetrics,
+	createTestMetric,
+	updateTestMetric,
+	deleteTestMetric,
+	getTestRuns,
+	getTestRun,
+	startTestRun,
+	deleteTestRun,
 }));
 
 vi.mock('@/stores/root.store', () => ({
@@ -44,6 +72,23 @@ const TEST_DEF_NEW: TestDefinitionRecord = {
 	description: 'New Description',
 };
 
+const TEST_METRIC = {
+	id: 'metric1',
+	name: 'Test Metric',
+	testDefinitionId: '1',
+};
+
+const TEST_RUN: TestRunRecord = {
+	id: 'run1',
+	testDefinitionId: '1',
+	status: 'completed',
+	metrics: { metric1: 0.75 },
+	createdAt: '2024-01-01',
+	updatedAt: '2024-01-01',
+	runAt: '2024-01-01',
+	completedAt: '2024-01-01',
+};
+
 describe('testDefinition.store.ee', () => {
 	let store: ReturnType<typeof useTestDefinitionStore>;
 	let rootStoreMock: ReturnType<typeof useRootStore>;
@@ -64,6 +109,11 @@ describe('testDefinition.store.ee', () => {
 		createTestDefinition.mockResolvedValue(TEST_DEF_NEW);
 
 		deleteTestDefinition.mockResolvedValue({ success: true });
+
+		getTestRuns.mockResolvedValue([TEST_RUN]);
+		getTestRun.mockResolvedValue(TEST_RUN);
+		startTestRun.mockResolvedValue({ success: true });
+		deleteTestRun.mockResolvedValue({ success: true });
 	});
 
 	test('Initialization', () => {
@@ -72,193 +122,460 @@ describe('testDefinition.store.ee', () => {
 		expect(store.hasTestDefinitions).toBe(false);
 	});
 
-	test('Fetching Test Definitions', async () => {
-		expect(store.isLoading).toBe(false);
+	describe('Test Definitions', () => {
+		test('Fetching Test Definitions', async () => {
+			expect(store.isLoading).toBe(false);
 
-		const result = await store.fetchAll();
+			const result = await store.fetchAll({ workflowId: '123' });
 
-		expect(getTestDefinitions).toHaveBeenCalledWith(rootStoreMock.restApiContext);
-		expect(store.testDefinitionsById).toEqual({
-			'1': TEST_DEF_A,
-			'2': TEST_DEF_B,
+			expect(getTestDefinitions).toHaveBeenCalledWith(rootStoreMock.restApiContext, {
+				workflowId: '123',
+			});
+			expect(store.testDefinitionsById).toEqual({
+				'1': TEST_DEF_A,
+				'2': TEST_DEF_B,
+			});
+			expect(store.isLoading).toBe(false);
+			expect(result).toEqual({
+				count: 2,
+				testDefinitions: [TEST_DEF_A, TEST_DEF_B],
+			});
 		});
-		expect(store.isLoading).toBe(false);
-		expect(result).toEqual({
-			count: 2,
-			testDefinitions: [TEST_DEF_A, TEST_DEF_B],
+
+		test('Fetching Test Definitions with force flag', async () => {
+			expect(store.isLoading).toBe(false);
+
+			const result = await store.fetchAll({ force: true, workflowId: '123' });
+
+			expect(getTestDefinitions).toHaveBeenCalledWith(rootStoreMock.restApiContext, {
+				workflowId: '123',
+			});
+			expect(store.testDefinitionsById).toEqual({
+				'1': TEST_DEF_A,
+				'2': TEST_DEF_B,
+			});
+			expect(store.isLoading).toBe(false);
+			expect(result).toEqual({
+				count: 2,
+				testDefinitions: [TEST_DEF_A, TEST_DEF_B],
+			});
+		});
+
+		test('Fetching Test Definitions when already fetched', async () => {
+			store.fetchedAll = true;
+
+			const result = await store.fetchAll();
+
+			expect(getTestDefinitions).not.toHaveBeenCalled();
+			expect(store.testDefinitionsById).toEqual({});
+			expect(result).toEqual({
+				count: 0,
+				testDefinitions: [],
+			});
+		});
+
+		test('Upserting Test Definitions - New Definition', () => {
+			const newDefinition = TEST_DEF_NEW;
+
+			store.upsertTestDefinitions([newDefinition]);
+
+			expect(store.testDefinitionsById).toEqual({
+				'3': TEST_DEF_NEW,
+			});
+		});
+
+		test('Upserting Test Definitions - Existing Definition', () => {
+			store.testDefinitionsById = {
+				'1': TEST_DEF_A,
+			};
+
+			const updatedDefinition = {
+				id: '1',
+				name: 'Updated Test Definition A',
+				description: 'Updated Description A',
+				workflowId: '123',
+			};
+
+			store.upsertTestDefinitions([updatedDefinition]);
+
+			expect(store.testDefinitionsById).toEqual({
+				1: updatedDefinition,
+			});
+		});
+
+		test('Creating a Test Definition', async () => {
+			const params = {
+				name: 'New Test Definition',
+				workflowId: 'test-workflow-id',
+				evaluationWorkflowId: 'test-evaluation-workflow-id',
+				description: 'New Description',
+			};
+
+			const result = await store.create(params);
+
+			expect(createTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
+			expect(store.testDefinitionsById).toEqual({
+				'3': TEST_DEF_NEW,
+			});
+			expect(result).toEqual(TEST_DEF_NEW);
+		});
+
+		test('Updating a Test Definition', async () => {
+			store.testDefinitionsById = {
+				'1': TEST_DEF_A,
+				'2': TEST_DEF_B,
+			};
+
+			const params = {
+				id: '1',
+				name: 'Updated Test Definition A',
+				description: 'Updated Description A',
+				workflowId: '123',
+			};
+			updateTestDefinition.mockResolvedValue(params);
+
+			const result = await store.update(params);
+
+			expect(updateTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1', {
+				name: 'Updated Test Definition A',
+				description: 'Updated Description A',
+				workflowId: '123',
+			});
+			expect(store.testDefinitionsById).toEqual({
+				'1': params,
+				'2': TEST_DEF_B,
+			});
+			expect(result).toEqual(params);
+		});
+
+		test('Deleting a Test Definition', () => {
+			store.testDefinitionsById = {
+				'1': TEST_DEF_A,
+				'2': TEST_DEF_B,
+			};
+
+			store.deleteTestDefinition('1');
+
+			expect(store.testDefinitionsById).toEqual({
+				'2': TEST_DEF_B,
+			});
+		});
+
+		test('Deleting a Test Definition by ID', async () => {
+			store.testDefinitionsById = {
+				'1': TEST_DEF_A,
+			};
+
+			const result = await store.deleteById('1');
+
+			expect(deleteTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1');
+			expect(store.testDefinitionsById).toEqual({});
+			expect(result).toBe(true);
 		});
 	});
 
-	test('Fetching Test Definitions with force flag', async () => {
-		expect(store.isLoading).toBe(false);
+	describe('Metrics', () => {
+		test('Fetching Metrics for a Test Definition', async () => {
+			getTestMetrics.mockResolvedValue([TEST_METRIC]);
 
-		const result = await store.fetchAll({ force: true });
+			const metrics = await store.fetchMetrics('1');
 
-		expect(getTestDefinitions).toHaveBeenCalledWith(rootStoreMock.restApiContext);
-		expect(store.testDefinitionsById).toEqual({
-			'1': TEST_DEF_A,
-			'2': TEST_DEF_B,
+			expect(getTestMetrics).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1');
+			expect(store.metricsById).toEqual({
+				metric1: TEST_METRIC,
+			});
+			expect(metrics).toEqual([TEST_METRIC]);
 		});
-		expect(store.isLoading).toBe(false);
-		expect(result).toEqual({
-			count: 2,
-			testDefinitions: [TEST_DEF_A, TEST_DEF_B],
+
+		test('Creating a Metric', async () => {
+			createTestMetric.mockResolvedValue(TEST_METRIC);
+
+			const params = {
+				name: 'Test Metric',
+				testDefinitionId: '1',
+			};
+
+			const result = await store.createMetric(params);
+
+			expect(createTestMetric).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
+			expect(store.metricsById).toEqual({
+				metric1: TEST_METRIC,
+			});
+			expect(result).toEqual(TEST_METRIC);
+		});
+
+		test('Updating a Metric', async () => {
+			const updatedMetric = { ...TEST_METRIC, name: 'Updated Metric' };
+			updateTestMetric.mockResolvedValue(updatedMetric);
+
+			const result = await store.updateMetric(updatedMetric);
+
+			expect(updateTestMetric).toHaveBeenCalledWith(rootStoreMock.restApiContext, updatedMetric);
+			expect(store.metricsById).toEqual({
+				metric1: updatedMetric,
+			});
+			expect(result).toEqual(updatedMetric);
+		});
+
+		test('Deleting a Metric', async () => {
+			store.metricsById = {
+				metric1: TEST_METRIC,
+			};
+
+			const params = { id: 'metric1', testDefinitionId: '1' };
+			deleteTestMetric.mockResolvedValue(undefined);
+
+			await store.deleteMetric(params);
+
+			expect(deleteTestMetric).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
+			expect(store.metricsById).toEqual({});
+		});
+
+		test('Getting Metrics by Test ID', () => {
+			const metric1 = { ...TEST_METRIC, id: 'metric1', testDefinitionId: '1' };
+			const metric2 = { ...TEST_METRIC, id: 'metric2', testDefinitionId: '1' };
+			const metric3 = { ...TEST_METRIC, id: 'metric3', testDefinitionId: '2' };
+
+			store.metricsById = {
+				metric1,
+				metric2,
+				metric3,
+			};
+
+			const metricsForTest1 = store.metricsByTestId['1'];
+			expect(metricsForTest1).toEqual([metric1, metric2]);
+
+			const metricsForTest2 = store.metricsByTestId['2'];
+			expect(metricsForTest2).toEqual([metric3]);
 		});
 	});
 
-	test('Fetching Test Definitions when already fetched', async () => {
-		store.fetchedAll = true;
+	describe('Computed Properties', () => {
+		test('hasTestDefinitions', () => {
+			store.testDefinitionsById = {};
 
-		const result = await store.fetchAll();
+			expect(store.hasTestDefinitions).toBe(false);
+			store.testDefinitionsById = {
+				'1': TEST_DEF_A,
+			};
 
-		expect(getTestDefinitions).not.toHaveBeenCalled();
-		expect(store.testDefinitionsById).toEqual({});
-		expect(result).toEqual({
-			count: 0,
-			testDefinitions: [],
+			expect(store.hasTestDefinitions).toBe(true);
+		});
+
+		test('isFeatureEnabled', () => {
+			posthogStoreMock.isFeatureEnabled = vi.fn().mockReturnValue(false);
+
+			expect(store.isFeatureEnabled).toBe(false);
+			posthogStoreMock.isFeatureEnabled = vi.fn().mockReturnValue(true);
+
+			expect(store.isFeatureEnabled).toBe(true);
+		});
+
+		test('allTestDefinitionsByWorkflowId', () => {
+			store.testDefinitionsById = {
+				'1': { ...TEST_DEF_A, workflowId: 'workflow1' },
+				'2': { ...TEST_DEF_B, workflowId: 'workflow1' },
+				'3': { ...TEST_DEF_NEW, workflowId: 'workflow2' },
+			};
+
+			expect(store.allTestDefinitionsByWorkflowId).toEqual({
+				workflow1: [
+					{ ...TEST_DEF_A, workflowId: 'workflow1' },
+					{ ...TEST_DEF_B, workflowId: 'workflow1' },
+				],
+				workflow2: [{ ...TEST_DEF_NEW, workflowId: 'workflow2' }],
+			});
+		});
+
+		test('lastRunByTestId', () => {
+			const olderRun = {
+				...TEST_RUN,
+				id: 'run2',
+				testDefinitionId: '1',
+				updatedAt: '2023-12-31',
+			};
+
+			const newerRun = {
+				...TEST_RUN,
+				id: 'run3',
+				testDefinitionId: '2',
+				updatedAt: '2024-01-02',
+			};
+
+			store.testRunsById = {
+				run1: { ...TEST_RUN, testDefinitionId: '1' },
+				run2: olderRun,
+				run3: newerRun,
+			};
+
+			expect(store.lastRunByTestId).toEqual({
+				'1': TEST_RUN,
+				'2': newerRun,
+			});
+		});
+
+		test('lastRunByTestId with no runs', () => {
+			store.testRunsById = {};
+			expect(store.lastRunByTestId).toEqual({});
 		});
 	});
 
-	test('Upserting Test Definitions - New Definition', () => {
-		const newDefinition = TEST_DEF_NEW;
+	describe('Error Handling', () => {
+		test('create', async () => {
+			createTestDefinition.mockRejectedValue(new Error('Create failed'));
 
-		store.upsertTestDefinitions([newDefinition]);
+			await expect(
+				store.create({ name: 'New Test Definition', workflowId: 'test-workflow-id' }),
+			).rejects.toThrow('Create failed');
+		});
 
-		expect(store.testDefinitionsById).toEqual({
-			'3': TEST_DEF_NEW,
+		test('update', async () => {
+			updateTestDefinition.mockRejectedValue(new Error('Update failed'));
+
+			await expect(store.update({ id: '1', name: 'Updated Test Definition A' })).rejects.toThrow(
+				'Update failed',
+			);
+		});
+
+		test('deleteById', async () => {
+			deleteTestDefinition.mockResolvedValue({ success: false });
+
+			const result = await store.deleteById('1');
+
+			expect(result).toBe(false);
 		});
 	});
 
-	test('Upserting Test Definitions - Existing Definition', () => {
-		store.testDefinitionsById = {
-			'1': TEST_DEF_A,
-		};
+	describe('Test Runs', () => {
+		test('Fetching Test Runs', async () => {
+			const result = await store.fetchTestRuns('1');
 
-		const updatedDefinition = {
-			id: '1',
-			name: 'Updated Test Definition A',
-			description: 'Updated Description A',
-			workflowId: '123',
-		};
+			expect(getTestRuns).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1');
+			expect(store.testRunsById).toEqual({
+				run1: TEST_RUN,
+			});
+			expect(result).toEqual([TEST_RUN]);
+		});
 
-		store.upsertTestDefinitions([updatedDefinition]);
+		test('Getting specific Test Run', async () => {
+			const params = { testDefinitionId: '1', runId: 'run1' };
+			const result = await store.getTestRun(params);
 
-		expect(store.testDefinitionsById).toEqual({
-			1: updatedDefinition,
+			expect(getTestRun).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
+			expect(store.testRunsById).toEqual({
+				run1: TEST_RUN,
+			});
+			expect(result).toEqual(TEST_RUN);
+		});
+
+		test('Starting Test Run', async () => {
+			const result = await store.startTestRun('1');
+
+			expect(startTestRun).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1');
+			expect(result).toEqual({ success: true });
+		});
+
+		test('Deleting Test Run', async () => {
+			store.testRunsById = { run1: TEST_RUN };
+			const params = { testDefinitionId: '1', runId: 'run1' };
+
+			const result = await store.deleteTestRun(params);
+
+			expect(deleteTestRun).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
+			expect(store.testRunsById).toEqual({});
+			expect(result).toEqual({ success: true });
+		});
+
+		test('Getting Test Runs by Test ID', () => {
+			store.testRunsById = {
+				run1: TEST_RUN,
+				run2: { ...TEST_RUN, id: 'run2', testDefinitionId: '2' },
+			};
+
+			const runs = store.testRunsByTestId['1'];
+
+			expect(runs).toEqual([TEST_RUN]);
 		});
 	});
 
-	test('Deleting Test Definitions', () => {
-		store.testDefinitionsById = {
-			'1': TEST_DEF_A,
-			'2': TEST_DEF_B,
-		};
-
-		store.deleteTestDefinition('1');
-
-		expect(store.testDefinitionsById).toEqual({
-			'2': TEST_DEF_B,
+	describe('Polling Mechanism', () => {
+		beforeEach(() => {
+			vi.useFakeTimers();
 		});
-	});
 
-	test('Creating a Test Definition', async () => {
-		const params = {
-			name: 'New Test Definition',
-			workflowId: 'test-workflow-id',
-			evaluationWorkflowId: 'test-evaluation-workflow-id',
-			description: 'New Description',
-		};
-
-		const result = await store.create(params);
-
-		expect(createTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, params);
-		expect(store.testDefinitionsById).toEqual({
-			'3': TEST_DEF_NEW,
+		afterEach(() => {
+			vi.useRealTimers();
 		});
-		expect(result).toEqual(TEST_DEF_NEW);
-	});
 
-	test('Updating a Test Definition', async () => {
-		store.testDefinitionsById = {
-			'1': TEST_DEF_A,
-			'2': TEST_DEF_B,
-		};
+		test('should start polling for running test runs', async () => {
+			const runningTestRun = {
+				...TEST_RUN,
+				status: 'running',
+			};
 
-		const params = {
-			id: '1',
-			name: 'Updated Test Definition A',
-			description: 'Updated Description A',
-			workflowId: '123',
-		};
-		updateTestDefinition.mockResolvedValue(params);
+			getTestRuns.mockResolvedValueOnce([runningTestRun]);
 
-		const result = await store.update(params);
+			// First call returns running status
+			getTestRun.mockResolvedValueOnce({
+				...runningTestRun,
+				status: 'running',
+			});
 
-		expect(updateTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1', {
-			name: 'Updated Test Definition A',
-			description: 'Updated Description A',
-			workflowId: '123',
+			// Second call returns completed status
+			getTestRun.mockResolvedValueOnce({
+				...runningTestRun,
+				status: 'completed',
+			});
+
+			await store.fetchTestRuns('1');
+
+			expect(store.testRunsById).toEqual({
+				run1: runningTestRun,
+			});
+
+			// Advance timer to trigger the first poll
+			await vi.advanceTimersByTimeAsync(1000);
+
+			// Verify first poll happened
+			expect(getTestRun).toHaveBeenCalledWith(rootStoreMock.restApiContext, {
+				testDefinitionId: '1',
+				runId: 'run1',
+			});
+
+			// Advance timer again
+			await vi.advanceTimersByTimeAsync(1000);
+
+			// Verify polling stopped after status changed to completed
+			expect(getTestRun).toHaveBeenCalledTimes(2);
 		});
-		expect(store.testDefinitionsById).toEqual({
-			'1': params,
-			'2': TEST_DEF_B,
+
+		test('should cleanup polling timeouts', async () => {
+			const runningTestRun = {
+				...TEST_RUN,
+				status: 'running',
+			};
+
+			getTestRuns.mockResolvedValueOnce([runningTestRun]);
+			getTestRun.mockResolvedValue({
+				...runningTestRun,
+				status: 'running',
+			});
+
+			await store.fetchTestRuns('1');
+
+			// Wait for the first poll to complete
+			await vi.runOnlyPendingTimersAsync();
+
+			// Clear mock calls from initial setup
+			getTestRun.mockClear();
+
+			store.cleanupPolling();
+
+			// Advance timer
+			await vi.advanceTimersByTimeAsync(1000);
+
+			// Verify no more polling happened after cleanup
+			expect(getTestRun).not.toHaveBeenCalled();
 		});
-		expect(result).toEqual(params);
-	});
-
-	test('Deleting a Test Definition by ID', async () => {
-		store.testDefinitionsById = {
-			'1': TEST_DEF_A,
-		};
-
-		const result = await store.deleteById('1');
-
-		expect(deleteTestDefinition).toHaveBeenCalledWith(rootStoreMock.restApiContext, '1');
-		expect(store.testDefinitionsById).toEqual({});
-		expect(result).toBe(true);
-	});
-
-	test('Computed Properties - hasTestDefinitions', () => {
-		store.testDefinitionsById = {};
-
-		expect(store.hasTestDefinitions).toBe(false);
-		store.testDefinitionsById = {
-			'1': TEST_DEF_A,
-		};
-
-		expect(store.hasTestDefinitions).toBe(true);
-	});
-
-	test('Computed Properties - isFeatureEnabled', () => {
-		posthogStoreMock.isFeatureEnabled = vi.fn().mockReturnValue(false);
-
-		expect(store.isFeatureEnabled).toBe(false);
-		posthogStoreMock.isFeatureEnabled = vi.fn().mockReturnValue(true);
-
-		expect(store.isFeatureEnabled).toBe(true);
-	});
-
-	test('Error Handling - create', async () => {
-		createTestDefinition.mockRejectedValue(new Error('Create failed'));
-
-		await expect(
-			store.create({ name: 'New Test Definition', workflowId: 'test-workflow-id' }),
-		).rejects.toThrow('Create failed');
-	});
-
-	test('Error Handling - update', async () => {
-		updateTestDefinition.mockRejectedValue(new Error('Update failed'));
-
-		await expect(store.update({ id: '1', name: 'Updated Test Definition A' })).rejects.toThrow(
-			'Update failed',
-		);
-	});
-
-	test('Error Handling - deleteById', async () => {
-		deleteTestDefinition.mockResolvedValue({ success: false });
-
-		const result = await store.deleteById('1');
-
-		expect(result).toBe(false);
 	});
 });

packages/editor-ui/src/stores/testDefinition.store.ee.ts

@@ -2,7 +2,7 @@ import { defineStore } from 'pinia';
 import { computed, ref } from 'vue';
 import { useRootStore } from './root.store';
 import * as testDefinitionsApi from '@/api/testDefinition.ee';
-import type { TestDefinitionRecord } from '@/api/testDefinition.ee';
+import type { TestDefinitionRecord, TestRunRecord } from '@/api/testDefinition.ee';
 import { usePostHog } from './posthog.store';
 import { STORES, WORKFLOW_EVALUATION_EXPERIMENT } from '@/constants';
 
@@ -13,6 +13,9 @@ export const useTestDefinitionStore = defineStore(
 		const testDefinitionsById = ref<Record<string, TestDefinitionRecord>>({});
 		const loading = ref(false);
 		const fetchedAll = ref(false);
+		const metricsById = ref<Record<string, testDefinitionsApi.TestMetricRecord>>({});
+		const testRunsById = ref<Record<string, TestRunRecord>>({});
+		const pollingTimeouts = ref<Record<string, NodeJS.Timeout>>({});
 
 		// Store instances
 		const posthogStore = usePostHog();
@@ -25,6 +28,19 @@ export const useTestDefinitionStore = defineStore(
 			);
 		});
 
+		const allTestDefinitionsByWorkflowId = computed(() => {
+			return Object.values(testDefinitionsById.value).reduce(
+				(acc: Record<string, TestDefinitionRecord[]>, test) => {
+					if (!acc[test.workflowId]) {
+						acc[test.workflowId] = [];
+					}
+					acc[test.workflowId].push(test);
+					return acc;
+				},
+				{},
+			);
+		});
+
 		// Enable with `window.featureFlags.override('025_workflow_evaluation', true)`
 		const isFeatureEnabled = computed(() =>
 			posthogStore.isFeatureEnabled(WORKFLOW_EVALUATION_EXPERIMENT),
@@ -34,6 +50,56 @@ export const useTestDefinitionStore = defineStore(
 
 		const hasTestDefinitions = computed(() => Object.keys(testDefinitionsById.value).length > 0);
 
+		const metricsByTestId = computed(() => {
+			return Object.values(metricsById.value).reduce(
+				(acc: Record<string, testDefinitionsApi.TestMetricRecord[]>, metric) => {
+					if (!acc[metric.testDefinitionId]) {
+						acc[metric.testDefinitionId] = [];
+					}
+					acc[metric.testDefinitionId].push(metric);
+					return acc;
+				},
+				{},
+			);
+		});
+
+		const testRunsByTestId = computed(() => {
+			return Object.values(testRunsById.value).reduce(
+				(acc: Record<string, TestRunRecord[]>, run) => {
+					if (!acc[run.testDefinitionId]) {
+						acc[run.testDefinitionId] = [];
+					}
+					acc[run.testDefinitionId].push(run);
+					return acc;
+				},
+				{},
+			);
+		});
+
+		const lastRunByTestId = computed(() => {
+			const grouped = Object.values(testRunsById.value).reduce(
+				(acc: Record<string, TestRunRecord[]>, run) => {
+					if (!acc[run.testDefinitionId]) {
+						acc[run.testDefinitionId] = [];
+					}
+					acc[run.testDefinitionId].push(run);
+					return acc;
+				},
+				{},
+			);
+
+			return Object.entries(grouped).reduce(
+				(acc: Record<string, TestRunRecord | null>, [testId, runs]) => {
+					acc[testId] =
+						runs.sort(
+							(a, b) => new Date(b.updatedAt).getTime() - new Date(a.updatedAt).getTime(),
+						)[0] || null;
+					return acc;
+				},
+				{},
+			);
+		});
+
 		// Methods
 		const setAllTestDefinitions = (definitions: TestDefinitionRecord[]) => {
 			testDefinitionsById.value = definitions.reduce(
@@ -69,13 +135,32 @@ export const useTestDefinitionStore = defineStore(
 			testDefinitionsById.value = rest;
 		};
 
+		const fetchRunsForAllTests = async () => {
+			const testDefinitions = Object.values(testDefinitionsById.value);
+			try {
+				await Promise.all(testDefinitions.map(async (testDef) => await fetchTestRuns(testDef.id)));
+			} catch (error) {
+				console.error('Error fetching test runs:', error);
+			}
+		};
+
+		const fetchTestDefinition = async (id: string) => {
+			const testDefinition = await testDefinitionsApi.getTestDefinition(
+				rootStore.restApiContext,
+				id,
+			);
+			testDefinitionsById.value[testDefinition.id] = testDefinition;
+
+			return testDefinition;
+		};
+
 		/**
 		 * Fetches all test definitions from the API.
 		 * @param {boolean} force - If true, fetches the definitions from the API even if they were already fetched before.
 		 */
-		const fetchAll = async (params?: { force?: boolean }) => {
-			const { force = false } = params ?? {};
-			if (!force && fetchedAll.value) {
+		const fetchAll = async (params?: { force?: boolean; workflowId?: string }) => {
+			const { force = false, workflowId } = params ?? {};
+			if (!force && fetchedAll.value && !workflowId) {
 				const testDefinitions = Object.values(testDefinitionsById.value);
 				return {
 					count: testDefinitions.length,
@@ -87,10 +172,13 @@ export const useTestDefinitionStore = defineStore(
 			try {
 				const retrievedDefinitions = await testDefinitionsApi.getTestDefinitions(
 					rootStore.restApiContext,
+					{ workflowId },
 				);
 
 				setAllTestDefinitions(retrievedDefinitions.testDefinitions);
 				fetchedAll.value = true;
+
+				await fetchRunsForAllTests();
 				return retrievedDefinitions;
 			} finally {
 				loading.value = false;
@@ -147,24 +235,142 @@ export const useTestDefinitionStore = defineStore(
 			return result.success;
 		};
 
+		const fetchMetrics = async (testId: string) => {
+			loading.value = true;
+			try {
+				const metrics = await testDefinitionsApi.getTestMetrics(rootStore.restApiContext, testId);
+				metrics.forEach((metric) => {
+					metricsById.value[metric.id] = metric;
+				});
+				return metrics;
+			} finally {
+				loading.value = false;
+			}
+		};
+
+		const createMetric = async (params: {
+			name: string;
+			testDefinitionId: string;
+		}): Promise<testDefinitionsApi.TestMetricRecord> => {
+			const metric = await testDefinitionsApi.createTestMetric(rootStore.restApiContext, params);
+			metricsById.value[metric.id] = metric;
+			return metric;
+		};
+
+		const updateMetric = async (
+			params: testDefinitionsApi.TestMetricRecord,
+		): Promise<testDefinitionsApi.TestMetricRecord> => {
+			const metric = await testDefinitionsApi.updateTestMetric(rootStore.restApiContext, params);
+			metricsById.value[metric.id] = metric;
+			return metric;
+		};
+
+		const deleteMetric = async (
+			params: testDefinitionsApi.DeleteTestMetricParams,
+		): Promise<void> => {
+			await testDefinitionsApi.deleteTestMetric(rootStore.restApiContext, params);
+			const { [params.id]: deleted, ...rest } = metricsById.value;
+			metricsById.value = rest;
+		};
+
+		// Test Runs Methods
+		const fetchTestRuns = async (testDefinitionId: string) => {
+			loading.value = true;
+			try {
+				const runs = await testDefinitionsApi.getTestRuns(
+					rootStore.restApiContext,
+					testDefinitionId,
+				);
+				runs.forEach((run) => {
+					testRunsById.value[run.id] = run;
+					if (['running', 'new'].includes(run.status)) {
+						startPollingTestRun(testDefinitionId, run.id);
+					}
+				});
+				return runs;
+			} finally {
+				loading.value = false;
+			}
+		};
+
+		const getTestRun = async (params: { testDefinitionId: string; runId: string }) => {
+			const run = await testDefinitionsApi.getTestRun(rootStore.restApiContext, params);
+			testRunsById.value[run.id] = run;
+			return run;
+		};
+
+		const startTestRun = async (testDefinitionId: string) => {
+			const result = await testDefinitionsApi.startTestRun(
+				rootStore.restApiContext,
+				testDefinitionId,
+			);
+			return result;
+		};
+
+		const deleteTestRun = async (params: { testDefinitionId: string; runId: string }) => {
+			const result = await testDefinitionsApi.deleteTestRun(rootStore.restApiContext, params);
+			if (result.success) {
+				const { [params.runId]: deleted, ...rest } = testRunsById.value;
+				testRunsById.value = rest;
+			}
+			return result;
+		};
+
+		// TODO: This is a temporary solution to poll for test run status.
+		// We should use a more efficient polling mechanism in the future.
+		const startPollingTestRun = (testDefinitionId: string, runId: string) => {
+			const poll = async () => {
+				const run = await getTestRun({ testDefinitionId, runId });
+				if (['running', 'new'].includes(run.status)) {
+					pollingTimeouts.value[runId] = setTimeout(poll, 1000);
+				} else {
+					delete pollingTimeouts.value[runId];
+				}
+			};
+			void poll();
+		};
+
+		const cleanupPolling = () => {
+			Object.values(pollingTimeouts.value).forEach((timeout) => {
+				clearTimeout(timeout);
+			});
+			pollingTimeouts.value = {};
+		};
+
 		return {
 			// State
 			fetchedAll,
 			testDefinitionsById,
+			testRunsById,
 
 			// Computed
 			allTestDefinitions,
+			allTestDefinitionsByWorkflowId,
 			isLoading,
 			hasTestDefinitions,
 			isFeatureEnabled,
+			metricsById,
+			metricsByTestId,
+			testRunsByTestId,
+			lastRunByTestId,
 
 			// Methods
+			fetchTestDefinition,
 			fetchAll,
 			create,
 			update,
 			deleteById,
 			upsertTestDefinitions,
 			deleteTestDefinition,
+			fetchMetrics,
+			createMetric,
+			updateMetric,
+			deleteMetric,
+			fetchTestRuns,
+			getTestRun,
+			startTestRun,
+			deleteTestRun,
+			cleanupPolling,
 		};
 	},
 	{},

packages/editor-ui/src/stores/ui.store.ts

@@ -16,6 +16,7 @@ import {
 	LOG_STREAM_MODAL_KEY,
 	MFA_SETUP_MODAL_KEY,
 	PERSONALIZATION_MODAL_KEY,
+	NODE_PINNING_MODAL_KEY,
 	STORES,
 	TAGS_MANAGER_MODAL_KEY,
 	ANNOTATION_TAGS_MANAGER_MODAL_KEY,
@@ -45,6 +46,7 @@ import type {
 	NotificationOptions,
 	ModalState,
 	ModalKey,
+	AppliedThemeOption,
 } from '@/Interface';
 import { defineStore } from 'pinia';
 import { useRootStore } from '@/stores/root.store';
@@ -98,6 +100,7 @@ export const useUIStore = defineStore(STORES.UI, () => {
 				CREDENTIAL_SELECT_MODAL_KEY,
 				DUPLICATE_MODAL_KEY,
 				PERSONALIZATION_MODAL_KEY,
+				NODE_PINNING_MODAL_KEY,
 				INVITE_USER_MODAL_KEY,
 				TAGS_MANAGER_MODAL_KEY,
 				ANNOTATION_TAGS_MANAGER_MODAL_KEY,
@@ -184,8 +187,15 @@ export const useUIStore = defineStore(STORES.UI, () => {
 	const rootStore = useRootStore();
 	const userStore = useUsersStore();
 
+	// Keep track of the preferred theme and update it when the system preference changes
+	const preferredTheme = getPreferredTheme();
+	const preferredSystemTheme = ref<AppliedThemeOption>(preferredTheme.theme);
+	preferredTheme.mediaQuery?.addEventListener('change', () => {
+		preferredSystemTheme.value = getPreferredTheme().theme;
+	});
+
 	const appliedTheme = computed(() => {
-		return theme.value === 'system' ? getPreferredTheme() : theme.value;
+		return theme.value === 'system' ? preferredSystemTheme.value : theme.value;
 	});
 
 	const contextBasedTranslationKeys = computed(() => {

packages/editor-ui/src/stores/ui.utils.ts

@@ -31,9 +31,11 @@ export function updateTheme(theme: ThemeOption) {
 	}
 }
 
-export function getPreferredTheme(): AppliedThemeOption {
-	const isDarkMode =
-		!!window.matchMedia && window.matchMedia('(prefers-color-scheme: dark)')?.matches;
+export function getPreferredTheme(): { theme: AppliedThemeOption; mediaQuery: MediaQueryList } {
+	const isDarkModeQuery = !!window.matchMedia && window.matchMedia('(prefers-color-scheme: dark)');
 
-	return isDarkMode ? 'dark' : 'light';
+	return {
+		theme: isDarkModeQuery?.matches ? 'dark' : 'light',
+		mediaQuery: isDarkModeQuery,
+	};
 }

packages/editor-ui/src/types/canvas.ts

@@ -144,6 +144,7 @@ export interface CanvasInjectionData {
 export type CanvasNodeEventBusEvents = {
 	'update:sticky:color': never;
 	'update:node:active': never;
+	'update:node:class': { className: string; add?: boolean };
 };
 
 export type CanvasEventBusEvents = {

packages/editor-ui/src/views/TestDefinition/TestDefinitionEditView.vue

@@ -1,7 +1,7 @@
 <script setup lang="ts">
-import { computed, onMounted, watch } from 'vue';
+import { computed, onMounted, watch, ref } from 'vue';
 import { useRoute, useRouter } from 'vue-router';
-import { VIEWS } from '@/constants';
+import { NODE_PINNING_MODAL_KEY, VIEWS } from '@/constants';
 import { useToast } from '@/composables/useToast';
 import { useI18n } from '@/composables/useI18n';
 import { useAnnotationTagsStore } from '@/stores/tags.store';
@@ -14,6 +14,12 @@ import EvaluationStep from '@/components/TestDefinition/EditDefinition/Evaluatio
 import TagsInput from '@/components/TestDefinition/EditDefinition/TagsInput.vue';
 import WorkflowSelector from '@/components/TestDefinition/EditDefinition/WorkflowSelector.vue';
 import MetricsInput from '@/components/TestDefinition/EditDefinition/MetricsInput.vue';
+import type { TestMetricRecord, TestRunRecord } from '@/api/testDefinition.ee';
+import Modal from '@/components/Modal.vue';
+import type { ModalState } from '@/Interface';
+import { useUIStore } from '@/stores/ui.store';
+import TestRunsTable from '@/components/TestDefinition/ListRuns/TestRunsTable.vue';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
 
 const props = defineProps<{
 	testId?: string;
@@ -24,31 +30,50 @@ const route = useRoute();
 const locale = useI18n();
 const { debounce } = useDebounce();
 const toast = useToast();
-const { isLoading, allTags, tagsById, fetchAll } = useAnnotationTagsStore();
-
-const testId = computed(() => props.testId ?? (route.params.testId as string));
-const currentWorkflowId = computed(() => route.params.name as string);
-const buttonLabel = computed(() =>
-	testId.value
-		? locale.baseText('testDefinition.edit.updateTest')
-		: locale.baseText('testDefinition.edit.saveTest'),
-);
-
+const testDefinitionStore = useTestDefinitionStore();
+const tagsStore = useAnnotationTagsStore();
+const uiStore = useUIStore();
 const {
 	state,
 	fieldsIssues,
-	isSaving,
+	cancelEditing,
 	loadTestData,
 	createTest,
 	updateTest,
 	startEditing,
 	saveChanges,
-	cancelEditing,
 	handleKeydown,
+	deleteMetric,
+	updateMetrics,
 } = useTestDefinitionForm();
 
+const isLoading = computed(() => tagsStore.isLoading);
+const allTags = computed(() => tagsStore.allTags);
+const tagsById = computed(() => tagsStore.tagsById);
+const testId = computed(() => props.testId ?? (route.params.testId as string));
+const currentWorkflowId = computed(() => route.params.name as string);
+
+const tagUsageCount = computed(
+	() => tagsStore.tagsById[state.value.tags.value[0]]?.usageCount ?? 0,
+);
+
+const nodePinningModal = ref<ModalState | null>(null);
+const modalContentWidth = ref(0);
+
 onMounted(async () => {
-	await fetchAll();
+	if (!testDefinitionStore.isFeatureEnabled) {
+		toast.showMessage({
+			title: locale.baseText('testDefinition.notImplemented'),
+			type: 'warning',
+		});
+
+		void router.push({
+			name: VIEWS.WORKFLOW,
+			params: { name: router.currentRoute.value.params.name },
+		});
+		return; // Add early return to prevent loading if feature is disabled
+	}
+	void tagsStore.fetchAll({ withUsageCount: true });
 	if (testId.value) {
 		await loadTestData(testId.value);
 	} else {
@@ -64,16 +89,12 @@ async function onSaveTest() {
 		} else {
 			savedTest = await createTest(currentWorkflowId.value);
 		}
-		if (savedTest && route.name === VIEWS.TEST_DEFINITION_EDIT) {
+		if (savedTest && route.name === VIEWS.NEW_TEST_DEFINITION) {
 			await router.replace({
 				name: VIEWS.TEST_DEFINITION_EDIT,
 				params: { testId: savedTest.id },
 			});
 		}
-		toast.showMessage({
-			title: locale.baseText('testDefinition.edit.testSaved'),
-			type: 'success',
-		});
 	} catch (e: unknown) {
 		toast.showError(e, locale.baseText('testDefinition.edit.testSaveFailed'));
 	}
@@ -83,12 +104,69 @@ function hasIssues(key: string) {
 	return fieldsIssues.value.some((issue) => issue.field === key);
 }
 
-watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: true });
+async function onDeleteMetric(deletedMetric: Partial<TestMetricRecord>) {
+	if (deletedMetric.id) {
+		await deleteMetric(deletedMetric.id, testId.value);
+	}
+}
+
+async function handleCreateTag(tagName: string) {
+	try {
+		const newTag = await tagsStore.create(tagName);
+		return newTag;
+	} catch (error) {
+		toast.showError(error, 'Error', error.message);
+		throw error;
+	}
+}
+
+async function openPinningModal() {
+	uiStore.openModal(NODE_PINNING_MODAL_KEY);
+}
+
+async function runTest() {
+	await testDefinitionStore.startTestRun(testId.value);
+	await testDefinitionStore.fetchTestRuns(testId.value);
+}
+
+const runs = computed(() =>
+	Object.values(testDefinitionStore.testRunsById ?? {}).filter(
+		(run) => run.testDefinitionId === testId.value,
+	),
+);
+
+async function onDeleteRuns(runs: TestRunRecord[]) {
+	await Promise.all(
+		runs.map(async (run) => {
+			await testDefinitionStore.deleteTestRun({ testDefinitionId: testId.value, runId: run.id });
+		}),
+	);
+}
+
+// Debounced watchers for auto-saving
+watch(
+	() => state.value.metrics,
+	debounce(async () => await updateMetrics(testId.value), { debounceTime: 400 }),
+	{ deep: true },
+);
+
+watch(
+	() => [
+		state.value.description,
+		state.value.name,
+		state.value.tags,
+		state.value.evaluationWorkflow,
+		state.value.mockedNodes,
+	],
+	debounce(onSaveTest, { debounceTime: 400 }),
+	{ deep: true },
+);
 </script>
 
 <template>
 	<div :class="$style.container">
-		<div :class="$style.content">
+		<div :class="$style.formContent">
+			<!-- Name -->
 			<EvaluationHeader
 				v-model="state.name"
 				:class="{ 'has-issues': hasIssues('name') }"
@@ -96,24 +174,33 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 				:save-changes="saveChanges"
 				:handle-keydown="handleKeydown"
 			/>
-
-			<EvaluationStep
-				:class="$style.step"
-				:title="locale.baseText('testDefinition.edit.description')"
-				:expanded="false"
-			>
-				<template #icon><font-awesome-icon icon="thumbtack" size="lg" /></template>
-				<template #cardContent>
-					<DescriptionInput v-model="state.description" />
-				</template>
-			</EvaluationStep>
-
-			<div :class="$style.panelIntro">{{ locale.baseText('testDefinition.edit.step.intro') }}</div>
-			<BlockArrow :class="$style.introArrow" />
 			<div :class="$style.panelBlock">
+				<!-- Description -->
 				<EvaluationStep
 					:class="$style.step"
-					:title="locale.baseText('testDefinition.edit.step.executions')"
+					:title="locale.baseText('testDefinition.edit.description')"
+					:expanded="false"
+					:tooltip="locale.baseText('testDefinition.edit.description.tooltip')"
+				>
+					<template #icon><font-awesome-icon icon="thumbtack" size="lg" /></template>
+					<template #cardContent>
+						<DescriptionInput v-model="state.description" />
+					</template>
+				</EvaluationStep>
+
+				<div :class="$style.panelIntro">
+					{{ locale.baseText('testDefinition.edit.step.intro') }}
+				</div>
+				<BlockArrow :class="$style.introArrow" />
+				<!-- Select Executions -->
+				<EvaluationStep
+					:class="$style.step"
+					:title="
+						locale.baseText('testDefinition.edit.step.executions', {
+							adjustToNumber: tagUsageCount,
+						})
+					"
+					:tooltip="locale.baseText('testDefinition.edit.step.executions.tooltip')"
 				>
 					<template #icon><font-awesome-icon icon="history" size="lg" /></template>
 					<template #cardContent>
@@ -126,6 +213,7 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 							:start-editing="startEditing"
 							:save-changes="saveChanges"
 							:cancel-editing="cancelEditing"
+							:create-tag="handleCreateTag"
 						/>
 					</template>
 				</EvaluationStep>
@@ -133,29 +221,46 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 					<BlockArrow />
 					<BlockArrow />
 				</div>
+
+				<!-- Mocked Nodes -->
 				<EvaluationStep
 					:class="$style.step"
-					:title="locale.baseText('testDefinition.edit.step.nodes')"
+					:title="
+						locale.baseText('testDefinition.edit.step.mockedNodes', {
+							adjustToNumber: state.mockedNodes?.length ?? 0,
+						})
+					"
 					:small="true"
-					:expanded="false"
+					:expanded="true"
+					:tooltip="locale.baseText('testDefinition.edit.step.nodes.tooltip')"
 				>
 					<template #icon><font-awesome-icon icon="thumbtack" size="lg" /></template>
-					<template #cardContent>{{
-						locale.baseText('testDefinition.edit.step.mockedNodes', { adjustToNumber: 0 })
-					}}</template>
+					<template #cardContent>
+						<n8n-button
+							size="small"
+							data-test-id="select-nodes-button"
+							:label="locale.baseText('testDefinition.edit.selectNodes')"
+							type="tertiary"
+							@click="openPinningModal"
+						/>
+					</template>
 				</EvaluationStep>
 
+				<!-- Re-run Executions -->
 				<EvaluationStep
 					:class="$style.step"
 					:title="locale.baseText('testDefinition.edit.step.reRunExecutions')"
 					:small="true"
+					:tooltip="locale.baseText('testDefinition.edit.step.reRunExecutions.tooltip')"
 				>
 					<template #icon><font-awesome-icon icon="redo" size="lg" /></template>
 				</EvaluationStep>
 
+				<!-- Compare Executions -->
 				<EvaluationStep
 					:class="$style.step"
 					:title="locale.baseText('testDefinition.edit.step.compareExecutions')"
+					:tooltip="locale.baseText('testDefinition.edit.step.compareExecutions.tooltip')"
 				>
 					<template #icon><font-awesome-icon icon="equals" size="lg" /></template>
 					<template #cardContent>
@@ -166,27 +271,69 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 					</template>
 				</EvaluationStep>
 
+				<!-- Metrics -->
 				<EvaluationStep
 					:class="$style.step"
 					:title="locale.baseText('testDefinition.edit.step.metrics')"
+					:tooltip="locale.baseText('testDefinition.edit.step.metrics.tooltip')"
 				>
 					<template #icon><font-awesome-icon icon="chart-bar" size="lg" /></template>
 					<template #cardContent>
-						<MetricsInput v-model="state.metrics" :class="{ 'has-issues': hasIssues('metrics') }" />
+						<MetricsInput
+							v-model="state.metrics"
+							:class="{ 'has-issues': hasIssues('metrics') }"
+							@delete-metric="onDeleteMetric"
+						/>
 					</template>
 				</EvaluationStep>
 			</div>
 
-			<div :class="$style.footer">
-				<n8n-button
-					type="primary"
-					data-test-id="run-test-button"
-					:label="buttonLabel"
-					:loading="isSaving"
-					@click="onSaveTest"
-				/>
-			</div>
+			<n8n-button
+				v-if="state.evaluationWorkflow.value && state.tags.value.length > 0"
+				:class="$style.runTestButton"
+				size="small"
+				data-test-id="run-test-button"
+				:label="locale.baseText('testDefinition.runTest')"
+				type="primary"
+				@click="runTest"
+			/>
+			<n8n-button
+				v-else
+				:class="$style.runTestButton"
+				size="small"
+				data-test-id="run-test-button"
+				:label="'Save Test'"
+				type="primary"
+				@click="onSaveTest"
+			/>
 		</div>
+		<!-- Past Runs Table -->
+		<div v-if="runs.length > 0" :class="$style.runsTable">
+			<N8nHeading size="large" :bold="true" :class="$style.runsTableHeading">{{
+				locale.baseText('testDefinition.edit.pastRuns')
+			}}</N8nHeading>
+			<TestRunsTable
+				:runs="runs"
+				:selectable="true"
+				data-test-id="past-runs-table"
+				@delete-runs="onDeleteRuns"
+			/>
+		</div>
+
+		<Modal ref="nodePinningModal" width="80vw" height="85vh" :name="NODE_PINNING_MODAL_KEY">
+			<template #header>
+				<N8nHeading size="large" :bold="true" :class="$style.runsTableHeading">{{
+					locale.baseText('testDefinition.edit.selectNodes')
+				}}</N8nHeading>
+			</template>
+			<template #content>
+				<NodesPinning
+					v-model="state.mockedNodes"
+					:width="modalContentWidth"
+					data-test-id="nodes-pinning-modal"
+				/>
+			</template>
+		</Modal>
 	</div>
 </template>
 
@@ -194,22 +341,40 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 .container {
 	width: 100%;
 	height: 100%;
+	overflow: hidden;
 	padding: var(--spacing-s);
 	display: grid;
 	grid-template-columns: minmax(auto, 24rem) 1fr;
 	gap: var(--spacing-2xl);
 }
 
-.content {
-	min-width: 0;
+.formContent {
 	width: 100%;
+	min-width: fit-content;
+	padding-bottom: 10px;
+	overflow: hidden;
+	display: flex;
+	flex-direction: column;
+}
+.runsTableTotal {
+	display: block;
+	margin-bottom: var(--spacing-xs);
+}
+.runsTable {
+	flex-shrink: 1;
+	max-width: 100%;
+	max-height: 80vh;
+	overflow: auto;
+}
+.runsTableHeading {
+	display: block;
+	margin-bottom: var(--spacing-xl);
 }
-
 .panelBlock {
 	max-width: var(--evaluation-edit-panel-width, 24rem);
 	display: grid;
-
-	justify-items: end;
+	overflow-y: auto;
+	min-height: 0;
 }
 .panelIntro {
 	font-size: var(--font-size-m);
@@ -231,7 +396,7 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 	justify-self: center;
 }
 .evaluationArrows {
-	--arrow-height: 11rem;
+	--arrow-height: 13.8rem;
 	display: flex;
 	justify-content: space-between;
 	width: 100%;
@@ -267,4 +432,11 @@ watch(() => state.value, debounce(onSaveTest, { debounceTime: 400 }), { deep: tr
 	justify-items: end;
 	align-items: start;
 }
+.mockedNodesLabel {
+	min-height: 1.5rem;
+	display: block;
+}
+.runTestButton {
+	margin-top: var(--spacing-m);
+}
 </style>

packages/editor-ui/src/views/TestDefinition/TestDefinitionListView.vue

@@ -19,17 +19,22 @@ const toast = useToast();
 const locale = useI18n();
 
 const tests = computed<TestListItem[]>(() => {
-	return testDefinitionStore.allTestDefinitions
+	return (
+		testDefinitionStore.allTestDefinitionsByWorkflowId[
+			router.currentRoute.value.params.name as string
+		] ?? []
+	)
 		.filter((test): test is TestDefinitionRecord => test.id !== undefined)
 		.sort((a, b) => new Date(b?.updatedAt ?? '').getTime() - new Date(a?.updatedAt ?? '').getTime())
 		.map((test) => ({
 			id: test.id,
 			name: test.name ?? '',
 			tagName: test.annotationTagId ? getTagName(test.annotationTagId) : '',
-			testCases: 0, // TODO: This should come from the API
+			testCases: testDefinitionStore.testRunsByTestId[test.id]?.length ?? 0,
 			execution: getTestExecution(test.id),
 		}));
 });
+
 const hasTests = computed(() => tests.value.length > 0);
 const allTags = computed(() => tagsStore.allTags);
 
@@ -39,21 +44,25 @@ function getTagName(tagId: string) {
 	return matchingTag?.name ?? '';
 }
 
-// TODO: Replace with actual API call once implemented
-function getTestExecution(_testId: string): TestExecution {
+function getTestExecution(testId: string): TestExecution {
+	const lastRun = testDefinitionStore.lastRunByTestId[testId];
+	if (!lastRun) {
+		return {
+			lastRun: null,
+			errorRate: 0,
+			metrics: {},
+			status: 'new',
+		};
+	}
+
 	const mockExecutions = {
-		lastRun: 'an hour ago',
+		lastRun: lastRun.updatedAt ?? '',
 		errorRate: 0,
-		metrics: { metric1: 0.12, metric2: 0.99, metric3: 0.87 },
+		metrics: lastRun.metrics ?? {},
+		status: lastRun.status ?? 'running',
 	};
 
-	return (
-		mockExecutions || {
-			lastRun: null,
-			errorRate: null,
-			metrics: { metric1: null, metric2: null, metric3: null },
-		}
-	);
+	return mockExecutions;
 }
 
 // Action handlers
@@ -61,20 +70,27 @@ function onCreateTest() {
 	void router.push({ name: VIEWS.NEW_TEST_DEFINITION });
 }
 
-function onRunTest(_testId: string) {
-	// TODO: Implement test run logic
-	toast.showMessage({
-		title: locale.baseText('testDefinition.notImplemented'),
-		type: 'warning',
-	});
+async function onRunTest(testId: string) {
+	try {
+		const result = await testDefinitionStore.startTestRun(testId);
+		if (result.success) {
+			toast.showMessage({
+				title: locale.baseText('testDefinition.list.testStarted'),
+				type: 'success',
+			});
+
+			// Optionally fetch the updated test runs
+			await testDefinitionStore.fetchTestRuns(testId);
+		} else {
+			throw new Error('Test run failed to start');
+		}
+	} catch (error) {
+		toast.showError(error, locale.baseText('testDefinition.list.testStartError'));
+	}
 }
 
-function onViewDetails(_testId: string) {
-	// TODO: Implement test details view
-	toast.showMessage({
-		title: locale.baseText('testDefinition.notImplemented'),
-		type: 'warning',
-	});
+async function onViewDetails(testId: string) {
+	void router.push({ name: VIEWS.TEST_DEFINITION_RUNS, params: { testId } });
 }
 
 function onEditTest(testId: number) {
@@ -92,12 +108,22 @@ async function onDeleteTest(testId: string) {
 
 // Load initial data
 async function loadInitialData() {
-	isLoading.value = true;
-	try {
-		await tagsStore.fetchAll();
-		await testDefinitionStore.fetchAll();
-	} finally {
-		isLoading.value = false;
+	if (!isLoading.value) {
+		// Add guard to prevent multiple loading states
+		isLoading.value = true;
+		try {
+			await Promise.all([
+				tagsStore.fetchAll(),
+				testDefinitionStore.fetchAll({
+					workflowId: router.currentRoute.value.params.name as string,
+				}),
+			]);
+			isLoading.value = false;
+		} catch (error) {
+			toast.showError(error, locale.baseText('testDefinition.list.loadError'));
+		} finally {
+			isLoading.value = false;
+		}
 	}
 }
 
@@ -112,7 +138,9 @@ onMounted(() => {
 			name: VIEWS.WORKFLOW,
 			params: { name: router.currentRoute.value.params.name },
 		});
+		return; // Add early return to prevent loading if feature is disabled
 	}
+
 	void loadInitialData();
 });
 </script>
@@ -124,7 +152,11 @@ onMounted(() => {
 		</div>
 
 		<template v-else>
-			<EmptyState v-if="!hasTests" @create-test="onCreateTest" />
+			<EmptyState
+				v-if="!hasTests"
+				data-test-id="test-definition-empty-state"
+				@create-test="onCreateTest"
+			/>
 			<TestsList
 				v-else
 				:tests="tests"

packages/editor-ui/src/views/TestDefinition/TestDefinitionRunDetailView.vue

@@ -0,0 +1,292 @@
+<script setup lang="ts">
+import { computed, onMounted, ref } from 'vue';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
+import { useRouter } from 'vue-router';
+import { convertToDisplayDate } from '@/utils/typesUtils';
+import { useI18n } from '@/composables/useI18n';
+import { N8nCard, N8nText } from 'n8n-design-system';
+import TestDefinitionTable from '@/components/TestDefinition/shared/TestDefinitionTable.vue';
+import type { TestDefinitionTableColumn } from '@/components/TestDefinition/shared/TestDefinitionTable.vue';
+import { useExecutionsStore } from '@/stores/executions.store';
+import { get } from 'lodash-es';
+import type { ExecutionSummaryWithScopes } from '@/Interface';
+import { VIEWS } from '@/constants';
+import { useWorkflowsStore } from '@/stores/workflows.store';
+import { useToast } from '@/composables/useToast';
+
+interface TestCase extends ExecutionSummaryWithScopes {
+	metrics: Record<string, number>;
+}
+
+const router = useRouter();
+const toast = useToast();
+const testDefinitionStore = useTestDefinitionStore();
+const executionsStore = useExecutionsStore();
+const workflowStore = useWorkflowsStore();
+const locale = useI18n();
+
+const isLoading = ref(true);
+const testCases = ref<TestCase[]>([]);
+
+const runId = computed(() => router.currentRoute.value.params.runId as string);
+const testId = computed(() => router.currentRoute.value.params.testId as string);
+
+const run = computed(() => testDefinitionStore.testRunsById[runId.value]);
+const test = computed(() => testDefinitionStore.testDefinitionsById[testId.value]);
+const workflow = computed(
+	() => workflowStore.workflowsById[test.value?.evaluationWorkflowId ?? ''],
+);
+const filteredTestCases = computed(() => {
+	return testCases.value;
+});
+
+const columns = computed(
+	(): Array<TestDefinitionTableColumn<TestCase>> => [
+		{
+			prop: 'id',
+			width: 200,
+			label: locale.baseText('testDefinition.runDetail.testCase'),
+			sortable: true,
+			route: (row: TestCase) => ({
+				name: VIEWS.EXECUTION_PREVIEW,
+				params: { name: row.workflowId, executionId: row.id },
+			}),
+			formatter: (row: TestCase) => `[${row.id}] ${workflow.value?.name}`,
+			openInNewTab: true,
+		},
+		{
+			prop: 'status',
+			label: locale.baseText('testDefinition.listRuns.status'),
+			filters: [
+				{ text: locale.baseText('testDefinition.listRuns.status.new'), value: 'new' },
+				{ text: locale.baseText('testDefinition.listRuns.status.running'), value: 'running' },
+				{ text: locale.baseText('testDefinition.listRuns.status.success'), value: 'success' },
+				{ text: locale.baseText('testDefinition.listRuns.status.error'), value: 'error' },
+			],
+			filterMethod: (value: string, row: TestCase) => row.status === value,
+		},
+		...Object.keys(run.value?.metrics ?? {}).map((metric) => ({
+			prop: `metrics.${metric}`,
+			label: metric,
+			sortable: true,
+			filter: true,
+			formatter: (row: TestCase) => row.metrics[metric]?.toFixed(2) ?? '-',
+		})),
+	],
+);
+
+const metrics = computed(() => run.value?.metrics ?? {});
+
+// Temporary workaround to fetch test cases by manually getting workflow executions
+// TODO: Replace with dedicated API endpoint once available
+const fetchExecutionTestCases = async () => {
+	if (!runId.value || !testId.value) return;
+
+	isLoading.value = true;
+	try {
+		const testRun = await testDefinitionStore.getTestRun({
+			testDefinitionId: testId.value,
+			runId: runId.value,
+		});
+		const testDefinition = await testDefinitionStore.fetchTestDefinition(testId.value);
+
+		// Fetch workflow executions that match this test run
+		const evaluationWorkflowExecutions = await executionsStore.fetchExecutions({
+			workflowId: testDefinition.evaluationWorkflowId ?? '',
+			metadata: [{ key: 'testRunId', value: testRun.id }],
+		});
+
+		// For each execution, fetch full details and extract metrics
+		const executionsData = await Promise.all(
+			evaluationWorkflowExecutions?.results.map(async (execution) => {
+				const executionData = await executionsStore.fetchExecution(execution.id);
+				const lastExecutedNode = executionData?.data?.resultData?.lastNodeExecuted;
+				if (!lastExecutedNode) {
+					throw new Error('Last executed node is required');
+				}
+				const metricsData = get(
+					executionData,
+					[
+						'data',
+						'resultData',
+						'runData',
+						lastExecutedNode,
+						'0',
+						'data',
+						'main',
+						'0',
+						'0',
+						'json',
+					],
+					{},
+				);
+
+				return {
+					...execution,
+					metrics: metricsData,
+				};
+			}),
+		);
+
+		testCases.value = executionsData ?? [];
+	} catch (error) {
+		toast.showError(error, 'Failed to load run details');
+	} finally {
+		isLoading.value = false;
+	}
+};
+
+onMounted(async () => {
+	await fetchExecutionTestCases();
+});
+</script>
+
+<template>
+	<div :class="$style.container" data-test-id="test-definition-run-detail">
+		<div :class="$style.header">
+			<button :class="$style.backButton" @click="router.back()">
+				<i class="mr-xs"><font-awesome-icon icon="arrow-left" /></i>
+				<n8n-heading size="large" :bold="true">{{ test?.name }}</n8n-heading>
+				<i class="ml-xs mr-xs"><font-awesome-icon icon="chevron-right" /></i>
+				<n8n-heading size="large" :bold="true"
+					>{{ locale.baseText('testDefinition.listRuns.runNumber') }}{{ run?.id }}</n8n-heading
+				>
+			</button>
+		</div>
+
+		<div :class="$style.cardGrid">
+			<N8nCard :class="$style.summaryCard">
+				<div :class="$style.stat">
+					<N8nText size="small">
+						{{ locale.baseText('testDefinition.runDetail.totalCases') }}
+					</N8nText>
+					<N8nText size="large">{{ testCases.length }}</N8nText>
+				</div>
+			</N8nCard>
+
+			<N8nCard :class="$style.summaryCard">
+				<div :class="$style.stat">
+					<N8nText size="small">
+						{{ locale.baseText('testDefinition.runDetail.ranAt') }}
+					</N8nText>
+					<N8nText size="medium">{{
+						convertToDisplayDate(new Date(run?.runAt).getTime())
+					}}</N8nText>
+				</div>
+			</N8nCard>
+
+			<N8nCard :class="$style.summaryCard">
+				<div :class="$style.stat">
+					<N8nText size="small">
+						{{ locale.baseText('testDefinition.listRuns.status') }}
+					</N8nText>
+					<N8nText size="large" :class="run?.status.toLowerCase()">
+						{{ run?.status }}
+					</N8nText>
+				</div>
+			</N8nCard>
+
+			<N8nCard v-for="(value, key) in metrics" :key="key" :class="$style.summaryCard">
+				<div :class="$style.stat">
+					<N8nText size="small">{{ key }}</N8nText>
+					<N8nText size="large">{{ value.toFixed(2) }}</N8nText>
+				</div>
+			</N8nCard>
+		</div>
+
+		<N8nCard>
+			<div v-if="isLoading" :class="$style.loading">
+				<n8n-loading :loading="true" :rows="5" />
+			</div>
+			<TestDefinitionTable
+				v-else
+				:data="filteredTestCases"
+				:columns="columns"
+				:default-sort="{ prop: 'id', order: 'descending' }"
+			/>
+		</N8nCard>
+	</div>
+</template>
+
+<style module lang="scss">
+.container {
+	padding: var(--spacing-xl) var(--spacing-l);
+	height: 100%;
+	width: 100%;
+	max-width: var(--content-container-width);
+}
+
+.backButton {
+	display: flex;
+	align-items: center;
+	gap: var(--spacing-s);
+	border: none;
+	background: none;
+	cursor: pointer;
+	color: var(--color-text-base);
+}
+
+.header {
+	display: flex;
+	align-items: center;
+	gap: var(--spacing-s);
+	margin-bottom: var(--spacing-l);
+
+	.timestamp {
+		color: var(--color-text-base);
+		font-size: var(--font-size-s);
+	}
+}
+
+.summary {
+	margin-bottom: var(--spacing-m);
+
+	.summaryStats {
+		display: flex;
+		gap: var(--spacing-l);
+	}
+}
+.stat {
+	display: flex;
+	flex-direction: column;
+}
+
+.controls {
+	display: flex;
+	gap: var(--spacing-s);
+	margin-bottom: var(--spacing-s);
+}
+
+.downloadButton {
+	margin-bottom: var(--spacing-s);
+}
+
+.loading {
+	display: flex;
+	justify-content: center;
+	align-items: center;
+	height: 200px;
+}
+
+.cardGrid {
+	display: grid;
+	grid-template-columns: repeat(auto-fit, minmax(6rem, 1fr));
+	gap: var(--spacing-xs);
+	margin-bottom: var(--spacing-m);
+}
+
+:global {
+	.new {
+		color: var(--color-info);
+	}
+	.running {
+		color: var(--color-warning);
+	}
+	.completed {
+		color: var(--color-success);
+	}
+	.error {
+		color: var(--color-danger);
+	}
+}
+</style>

packages/editor-ui/src/views/TestDefinition/TestDefinitionRunsListView.vue

@@ -0,0 +1,129 @@
+<script setup lang="ts">
+import { computed, onMounted, ref } from 'vue';
+import { useRouter } from 'vue-router';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+import TestRunsTable from '@/components/TestDefinition/ListRuns/TestRunsTable.vue';
+import { VIEWS } from '@/constants';
+import { useI18n } from '@/composables/useI18n';
+import { useToast } from '@/composables/useToast';
+import { useUIStore } from '@/stores/ui.store';
+
+const router = useRouter();
+const testDefinitionStore = useTestDefinitionStore();
+const uiStore = useUIStore();
+const locale = useI18n();
+const toast = useToast();
+
+const selectedMetric = ref();
+const isLoading = ref(false);
+
+const appliedTheme = computed(() => uiStore.appliedTheme);
+const testId = computed(() => {
+	return router.currentRoute.value.params.testId as string;
+});
+
+async function loadInitialData() {
+	if (!isLoading.value) {
+		// Add guard to prevent multiple loading states
+		isLoading.value = true;
+		try {
+			await testDefinitionStore.fetchTestDefinition(testId.value);
+			await testDefinitionStore.fetchTestRuns(testId.value);
+			isLoading.value = false;
+		} catch (error) {
+		} finally {
+			isLoading.value = false;
+		}
+	}
+}
+// TODO: We're currently doing the filtering on the FE but there should be an endpoint to get the runs for a test
+const runs = computed(() => {
+	return Object.values(testDefinitionStore.testRunsById ?? {}).filter(
+		(run) => run.testDefinitionId === testId.value,
+	);
+});
+
+const testDefinition = computed(() => {
+	return testDefinitionStore.testDefinitionsById[testId.value];
+});
+
+const getRunDetail = (run: TestRunRecord) => {
+	void router.push({
+		name: VIEWS.TEST_DEFINITION_RUNS_DETAIL,
+		params: { testId: testId.value, runId: run.id },
+	});
+};
+
+async function runTest() {
+	try {
+		const result = await testDefinitionStore.startTestRun(testId.value);
+		if (result.success) {
+			toast.showMessage({
+				title: locale.baseText('testDefinition.list.testStarted'),
+				type: 'success',
+			});
+
+			// Optionally fetch the updated test runs
+			await testDefinitionStore.fetchTestRuns(testId.value);
+		} else {
+			throw new Error('Test run failed to start');
+		}
+	} catch (error) {
+		toast.showError(error, locale.baseText('testDefinition.list.testStartError'));
+	}
+}
+
+async function onDeleteRuns(runsToDelete: TestRunRecord[]) {
+	await Promise.all(
+		runsToDelete.map(async (run) => {
+			await testDefinitionStore.deleteTestRun({ testDefinitionId: testId.value, runId: run.id });
+		}),
+	);
+}
+
+onMounted(async () => {
+	await loadInitialData();
+});
+</script>
+
+<template>
+	<div :class="$style.container">
+		<router-link :to="{ name: VIEWS.TEST_DEFINITION }" :class="$style.backButton">
+			<i class="mr-xs"><font-awesome-icon icon="arrow-left" /></i>
+			<n8n-heading size="large" :bold="true">{{ testDefinition?.name }}</n8n-heading>
+		</router-link>
+		<N8nText :class="$style.description" size="medium">{{ testDefinition?.description }}</N8nText>
+		<template v-if="isLoading">
+			<N8nLoading :rows="5" />
+			<N8nLoading :rows="10" />
+		</template>
+		<template v-else-if="runs.length > 0">
+			<MetricsChart v-model:selectedMetric="selectedMetric" :runs="runs" :theme="appliedTheme" />
+			<TestRunsTable :runs="runs" @get-run-detail="getRunDetail" @delete-runs="onDeleteRuns" />
+		</template>
+		<template v-else>
+			<N8nActionBox
+				:heading="locale.baseText('testDefinition.listRuns.noRuns')"
+				:description="locale.baseText('testDefinition.listRuns.noRuns.description')"
+				:button-text="locale.baseText('testDefinition.listRuns.noRuns.button')"
+				@click:button="runTest"
+			/>
+		</template>
+	</div>
+</template>
+<style module lang="scss">
+.container {
+	padding: var(--spacing-xl) var(--spacing-l);
+	height: 100%;
+	width: 100%;
+	max-width: var(--content-container-width);
+}
+.backButton {
+	color: var(--color-text-base);
+}
+.description {
+	margin-top: var(--spacing-xs);
+	display: block;
+}
+</style>

packages/editor-ui/src/views/TestDefinition/tests/TestDefinitionEditView.test.ts

@@ -1,3 +1,4 @@
+import type { Mock } from 'vitest';
 import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
 import { createPinia, setActivePinia } from 'pinia';
 import { createTestingPinia } from '@pinia/testing';
@@ -8,57 +9,89 @@ import { useToast } from '@/composables/useToast';
 import { useTestDefinitionForm } from '@/components/TestDefinition/composables/useTestDefinitionForm';
 import { useAnnotationTagsStore } from '@/stores/tags.store';
 import { ref, nextTick } from 'vue';
+import { cleanupAppModals, createAppModals, mockedStore } from '@/__tests__/utils';
+import { VIEWS } from '@/constants';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
 
 vi.mock('vue-router');
 vi.mock('@/composables/useToast');
 vi.mock('@/components/TestDefinition/composables/useTestDefinitionForm');
-vi.mock('@/stores/tags.store');
 vi.mock('@/stores/projects.store');
 
 describe('TestDefinitionEditView', () => {
 	const renderComponent = createComponentRenderer(TestDefinitionEditView);
 
+	let createTestMock: Mock;
+	let updateTestMock: Mock;
+	let loadTestDataMock: Mock;
+	let deleteMetricMock: Mock;
+	let updateMetricsMock: Mock;
+	let showMessageMock: Mock;
+	let showErrorMock: Mock;
+
+	const renderComponentWithFeatureEnabled = ({
+		testRunsById = {},
+	}: { testRunsById?: Record<string, TestRunRecord> } = {}) => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const mockedTestDefinitionStore = mockedStore(useTestDefinitionStore);
+		mockedTestDefinitionStore.isFeatureEnabled = true;
+		mockedTestDefinitionStore.testRunsById = testRunsById;
+		return { ...renderComponent({ pinia }), mockedTestDefinitionStore };
+	};
+
 	beforeEach(() => {
 		setActivePinia(createPinia());
+		createAppModals();
 
+		// Default route mock: no testId
 		vi.mocked(useRoute).mockReturnValue({
 			params: {},
-			path: '/test-path',
-			name: 'test-route',
+			name: VIEWS.NEW_TEST_DEFINITION,
 		} as ReturnType<typeof useRoute>);
 
 		vi.mocked(useRouter).mockReturnValue({
 			push: vi.fn(),
+			replace: vi.fn(),
 			resolve: vi.fn().mockReturnValue({ href: '/test-href' }),
+			currentRoute: { value: { params: {} } },
 		} as unknown as ReturnType<typeof useRouter>);
 
+		createTestMock = vi.fn().mockResolvedValue({ id: 'newTestId' });
+		updateTestMock = vi.fn().mockResolvedValue({});
+		loadTestDataMock = vi.fn();
+		deleteMetricMock = vi.fn();
+		updateMetricsMock = vi.fn();
+		showMessageMock = vi.fn();
+		showErrorMock = vi.fn();
+		// const mockedTestDefinitionStore = mockedStore(useTestDefinitionStore);
+
 		vi.mocked(useToast).mockReturnValue({
-			showMessage: vi.fn(),
-			showError: vi.fn(),
+			showMessage: showMessageMock,
+			showError: showErrorMock,
 		} as unknown as ReturnType<typeof useToast>);
 		vi.mocked(useTestDefinitionForm).mockReturnValue({
 			state: ref({
 				name: { value: '', isEditing: false, tempValue: '' },
 				description: '',
-				tags: { appliedTagIds: [], isEditing: false },
-				evaluationWorkflow: { id: '1', name: 'Test Workflow' },
+				tags: { value: [], tempValue: [], isEditing: false },
+				evaluationWorkflow: { mode: 'list', value: '', __rl: true },
 				metrics: [],
 			}),
 			fieldsIssues: ref([]),
 			isSaving: ref(false),
-			loadTestData: vi.fn(),
-			saveTest: vi.fn(),
+			loadTestData: loadTestDataMock,
+			createTest: createTestMock,
+			updateTest: updateTestMock,
 			startEditing: vi.fn(),
 			saveChanges: vi.fn(),
 			cancelEditing: vi.fn(),
 			handleKeydown: vi.fn(),
+			deleteMetric: deleteMetricMock,
+			updateMetrics: updateMetricsMock,
 		} as unknown as ReturnType<typeof useTestDefinitionForm>);
-		vi.mocked(useAnnotationTagsStore).mockReturnValue({
-			isLoading: ref(false),
-			allTags: ref([]),
-			tagsById: ref({}),
-			fetchAll: vi.fn(),
-		} as unknown as ReturnType<typeof useAnnotationTagsStore>);
 
 		vi.mock('@/stores/projects.store', () => ({
 			useProjectsStore: vi.fn().mockReturnValue({
@@ -71,138 +104,197 @@ describe('TestDefinitionEditView', () => {
 
 	afterEach(() => {
 		vi.clearAllMocks();
+		cleanupAppModals();
 	});
 
 	it('should load test data when testId is provided', async () => {
 		vi.mocked(useRoute).mockReturnValue({
 			params: { testId: '1' },
-			path: '/test-path',
-			name: 'test-route',
+			name: VIEWS.TEST_DEFINITION_EDIT,
 		} as unknown as ReturnType<typeof useRoute>);
-		const loadTestDataMock = vi.fn();
-		vi.mocked(useTestDefinitionForm).mockReturnValue({
-			...vi.mocked(useTestDefinitionForm)(),
-			loadTestData: loadTestDataMock,
-		} as unknown as ReturnType<typeof useTestDefinitionForm>);
+		renderComponentWithFeatureEnabled();
 
-		renderComponent({
-			pinia: createTestingPinia(),
-		});
+		mockedStore(useAnnotationTagsStore).fetchAll.mockResolvedValue([]);
 
-		await nextTick();
 		expect(loadTestDataMock).toHaveBeenCalledWith('1');
 	});
 
 	it('should not load test data when testId is not provided', async () => {
-		const loadTestDataMock = vi.fn();
-		vi.mocked(useTestDefinitionForm).mockReturnValue({
-			...vi.mocked(useTestDefinitionForm)(),
-			loadTestData: loadTestDataMock,
-		} as unknown as ReturnType<typeof useTestDefinitionForm>);
+		// Here route returns no testId
+		vi.mocked(useRoute).mockReturnValue({
+			params: {},
+			name: VIEWS.NEW_TEST_DEFINITION,
+		} as unknown as ReturnType<typeof useRoute>);
+		renderComponentWithFeatureEnabled();
 
-		renderComponent({
-			pinia: createTestingPinia(),
-		});
-
-		await nextTick();
 		expect(loadTestDataMock).not.toHaveBeenCalled();
 	});
 
-	it('should save test and show success message on successful save', async () => {
-		const saveTestMock = vi.fn().mockResolvedValue({});
-		const routerPushMock = vi.fn();
-		const routerResolveMock = vi.fn().mockReturnValue({ href: '/test-href' });
-		vi.mocked(useTestDefinitionForm).mockReturnValue({
-			...vi.mocked(useTestDefinitionForm)(),
-			createTest: saveTestMock,
-		} as unknown as ReturnType<typeof useTestDefinitionForm>);
+	it('should create a new test and show success message on save if no testId is present', async () => {
+		vi.mocked(useRoute).mockReturnValue({
+			params: {},
+			name: VIEWS.NEW_TEST_DEFINITION,
+		} as ReturnType<typeof useRoute>);
+		const { getByTestId } = renderComponentWithFeatureEnabled();
 
-		vi.mocked(useRouter).mockReturnValue({
-			push: routerPushMock,
-			resolve: routerResolveMock,
-		} as unknown as ReturnType<typeof useRouter>);
+		mockedStore(useAnnotationTagsStore).fetchAll.mockResolvedValue([]);
 
-		const { getByTestId } = renderComponent({
-			pinia: createTestingPinia(),
-		});
 		await nextTick();
 		const saveButton = getByTestId('run-test-button');
 		saveButton.click();
 		await nextTick();
 
-		expect(saveTestMock).toHaveBeenCalled();
+		expect(createTestMock).toHaveBeenCalled();
 	});
 
-	it('should show error message on failed save', async () => {
-		const saveTestMock = vi.fn().mockRejectedValue(new Error('Save failed'));
-		const showErrorMock = vi.fn();
-		vi.mocked(useTestDefinitionForm).mockReturnValue({
-			...vi.mocked(useTestDefinitionForm)(),
-			createTest: saveTestMock,
-		} as unknown as ReturnType<typeof useTestDefinitionForm>);
-		vi.mocked(useToast).mockReturnValue({ showError: showErrorMock } as unknown as ReturnType<
-			typeof useToast
-		>);
-
-		const { getByTestId } = renderComponent({
-			pinia: createTestingPinia(),
-		});
-		await nextTick();
-		const saveButton = getByTestId('run-test-button');
-		saveButton.click();
-		await nextTick();
-		expect(saveTestMock).toHaveBeenCalled();
-		expect(showErrorMock).toHaveBeenCalled();
-	});
-
-	it('should display "Update Test" button when editing existing test', async () => {
+	it('should update test and show success message on save if testId is present', async () => {
 		vi.mocked(useRoute).mockReturnValue({
 			params: { testId: '1' },
-			path: '/test-path',
-			name: 'test-route',
+			name: VIEWS.TEST_DEFINITION_EDIT,
 		} as unknown as ReturnType<typeof useRoute>);
-		const { getByTestId } = renderComponent({
-			pinia: createTestingPinia(),
-		});
+
+		const { getByTestId } = renderComponentWithFeatureEnabled();
+
+		const saveButton = getByTestId('run-test-button');
+		saveButton.click();
 		await nextTick();
-		const updateButton = getByTestId('run-test-button');
-		expect(updateButton.textContent).toContain('Update test');
+
+		expect(updateTestMock).toHaveBeenCalledWith('1');
 	});
 
-	it('should display "Run Test" button when creating new test', async () => {
-		const { getByTestId } = renderComponent({
-			pinia: createTestingPinia(),
-		});
-		await nextTick();
+	it('should show error message on failed test creation', async () => {
+		createTestMock.mockRejectedValue(new Error('Save failed'));
+
+		vi.mocked(useRoute).mockReturnValue({
+			params: {},
+			name: VIEWS.NEW_TEST_DEFINITION,
+		} as unknown as ReturnType<typeof useRoute>);
+
+		const { getByTestId } = renderComponentWithFeatureEnabled();
+
 		const saveButton = getByTestId('run-test-button');
-		expect(saveButton).toBeTruthy();
+		saveButton.click();
+		await nextTick();
+
+		expect(createTestMock).toHaveBeenCalled();
+		expect(showErrorMock).toHaveBeenCalledWith(expect.any(Error), expect.any(String));
+	});
+
+	it('should display "Save Test" button when editing test without eval workflow and tags', async () => {
+		vi.mocked(useRoute).mockReturnValue({
+			params: { testId: '1' },
+			name: VIEWS.TEST_DEFINITION_EDIT,
+		} as unknown as ReturnType<typeof useRoute>);
+
+		const { getByTestId } = renderComponentWithFeatureEnabled();
+
+		await nextTick();
+		const updateButton = getByTestId('run-test-button');
+		expect(updateButton.textContent?.toLowerCase()).toContain('save');
+	});
+
+	it('should display "Save Test" button when creating new test', async () => {
+		vi.mocked(useRoute).mockReturnValue({
+			params: {},
+			name: VIEWS.NEW_TEST_DEFINITION,
+		} as unknown as ReturnType<typeof useRoute>);
+
+		const { getByTestId } = renderComponentWithFeatureEnabled();
+
+		const saveButton = getByTestId('run-test-button');
+		expect(saveButton.textContent?.toLowerCase()).toContain('save test');
 	});
 
 	it('should apply "has-issues" class to inputs with issues', async () => {
 		vi.mocked(useTestDefinitionForm).mockReturnValue({
 			...vi.mocked(useTestDefinitionForm)(),
-			fieldsIssues: ref([{ field: 'name' }, { field: 'tags' }]),
+			fieldsIssues: ref([
+				{ field: 'name', message: 'Name is required' },
+				{ field: 'tags', message: 'Tag is required' },
+			]),
 		} as unknown as ReturnType<typeof useTestDefinitionForm>);
 
-		const { container } = renderComponent({
-			pinia: createTestingPinia(),
-		});
+		const { container } = renderComponentWithFeatureEnabled();
+
 		await nextTick();
-		expect(container.querySelector('.has-issues')).toBeTruthy();
+		const issueElements = container.querySelectorAll('.has-issues');
+		expect(issueElements.length).toBeGreaterThan(0);
 	});
 
 	it('should fetch all tags on mount', async () => {
-		const fetchAllMock = vi.fn();
-		vi.mocked(useAnnotationTagsStore).mockReturnValue({
-			...vi.mocked(useAnnotationTagsStore)(),
-			fetchAll: fetchAllMock,
-		} as unknown as ReturnType<typeof useAnnotationTagsStore>);
+		renderComponentWithFeatureEnabled();
+		await nextTick();
+		expect(mockedStore(useAnnotationTagsStore).fetchAll).toHaveBeenCalled();
+	});
 
-		renderComponent({
-			pinia: createTestingPinia(),
+	describe('Test Runs functionality', () => {
+		it('should display test runs table when runs exist', async () => {
+			vi.mocked(useRoute).mockReturnValue({
+				params: { testId: '1' },
+				name: VIEWS.TEST_DEFINITION_EDIT,
+			} as unknown as ReturnType<typeof useRoute>);
+
+			const { getByTestId } = renderComponentWithFeatureEnabled({
+				testRunsById: {
+					run1: {
+						id: 'run1',
+						testDefinitionId: '1',
+						status: 'completed',
+						runAt: '2023-01-01',
+						createdAt: '2023-01-01',
+						updatedAt: '2023-01-01',
+						completedAt: '2023-01-01',
+					},
+					run2: {
+						id: 'run2',
+						testDefinitionId: '1',
+						status: 'running',
+						runAt: '2023-01-02',
+						createdAt: '2023-01-02',
+						updatedAt: '2023-01-02',
+						completedAt: '',
+					},
+				},
+			});
+
+			const runsTable = getByTestId('past-runs-table');
+			expect(runsTable).toBeTruthy();
 		});
 
-		await nextTick();
-		expect(fetchAllMock).toHaveBeenCalled();
+		it('should not display test runs table when no runs exist', async () => {
+			const { container } = renderComponentWithFeatureEnabled();
+
+			const runsTable = container.querySelector('[data-test-id="past-runs-table"]');
+			expect(runsTable).toBeFalsy();
+		});
+
+		it('should start a test run when run test button is clicked', async () => {
+			vi.mocked(useTestDefinitionForm).mockReturnValue({
+				...vi.mocked(useTestDefinitionForm)(),
+				state: ref({
+					name: { value: 'Test', isEditing: false, tempValue: '' },
+					description: '',
+					tags: { value: ['tag1'], tempValue: [], isEditing: false },
+					evaluationWorkflow: { mode: 'list', value: 'workflow1', __rl: true },
+					metrics: [],
+					mockedNodes: [],
+				}),
+			} as unknown as ReturnType<typeof useTestDefinitionForm>);
+
+			vi.mocked(useRoute).mockReturnValue({
+				params: { testId: '1' },
+				name: VIEWS.TEST_DEFINITION_EDIT,
+			} as unknown as ReturnType<typeof useRoute>);
+
+			const { getByTestId, mockedTestDefinitionStore } = renderComponentWithFeatureEnabled();
+			await nextTick();
+
+			const runButton = getByTestId('run-test-button');
+			runButton.click();
+			await nextTick();
+
+			expect(mockedTestDefinitionStore.startTestRun).toHaveBeenCalledWith('1');
+			expect(mockedTestDefinitionStore.fetchTestRuns).toHaveBeenCalledWith('1');
+		});
 	});
 });

packages/editor-ui/src/views/TestDefinition/tests/TestDefinitionListView.test.ts

@@ -0,0 +1,174 @@
+import type { Mock } from 'vitest';
+import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+import { createPinia, setActivePinia } from 'pinia';
+import { createTestingPinia } from '@pinia/testing';
+import { createComponentRenderer } from '@/__tests__/render';
+import TestDefinitionListView from '@/views/TestDefinition/TestDefinitionListView.vue';
+import { useRoute, useRouter } from 'vue-router';
+import { useToast } from '@/composables/useToast';
+import { useAnnotationTagsStore } from '@/stores/tags.store';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
+import { nextTick, ref } from 'vue';
+import { mockedStore, waitAllPromises } from '@/__tests__/utils';
+import { VIEWS } from '@/constants';
+import type { TestDefinitionRecord } from '@/api/testDefinition.ee';
+
+vi.mock('vue-router');
+vi.mock('@/composables/useToast');
+
+describe('TestDefinitionListView', () => {
+	const renderComponent = createComponentRenderer(TestDefinitionListView);
+
+	let showMessageMock: Mock;
+	let showErrorMock: Mock;
+	let startTestRunMock: Mock;
+	let fetchTestRunsMock: Mock;
+	let deleteByIdMock: Mock;
+	let fetchAllMock: Mock;
+
+	const mockTestDefinitions: TestDefinitionRecord[] = [
+		{
+			id: '1',
+			name: 'Test 1',
+			workflowId: 'workflow1',
+			updatedAt: '2023-01-01T00:00:00.000Z',
+			annotationTagId: 'tag1',
+		},
+		{
+			id: '2',
+			name: 'Test 2',
+			workflowId: 'workflow1',
+			updatedAt: '2023-01-02T00:00:00.000Z',
+		},
+		{
+			id: '3',
+			name: 'Test 3',
+			workflowId: 'workflow1',
+			updatedAt: '2023-01-03T00:00:00.000Z',
+		},
+	];
+
+	beforeEach(() => {
+		setActivePinia(createPinia());
+
+		vi.mocked(useRoute).mockReturnValue(
+			ref({
+				params: { name: 'workflow1' },
+				name: VIEWS.TEST_DEFINITION,
+			}) as unknown as ReturnType<typeof useRoute>,
+		);
+
+		vi.mocked(useRouter).mockReturnValue({
+			push: vi.fn(),
+			currentRoute: { value: { params: { name: 'workflow1' } } },
+		} as unknown as ReturnType<typeof useRouter>);
+
+		showMessageMock = vi.fn();
+		showErrorMock = vi.fn();
+		startTestRunMock = vi.fn().mockResolvedValue({ success: true });
+		fetchTestRunsMock = vi.fn();
+		deleteByIdMock = vi.fn();
+		fetchAllMock = vi.fn().mockResolvedValue({ testDefinitions: mockTestDefinitions });
+
+		vi.mocked(useToast).mockReturnValue({
+			showMessage: showMessageMock,
+			showError: showErrorMock,
+		} as unknown as ReturnType<typeof useToast>);
+	});
+
+	afterEach(() => {
+		vi.clearAllMocks();
+	});
+
+	const renderComponentWithFeatureEnabled = async (
+		{ testDefinitions }: { testDefinitions: TestDefinitionRecord[] } = {
+			testDefinitions: mockTestDefinitions,
+		},
+	) => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		// const tagsStore = mockedStore(useAnnotationTagsStore);
+		testDefinitionStore.isFeatureEnabled = true;
+		testDefinitionStore.fetchAll = fetchAllMock;
+		testDefinitionStore.startTestRun = startTestRunMock;
+		testDefinitionStore.fetchTestRuns = fetchTestRunsMock;
+		testDefinitionStore.deleteById = deleteByIdMock;
+		testDefinitionStore.allTestDefinitionsByWorkflowId = { workflow1: testDefinitions };
+
+		const component = renderComponent({ pinia });
+		await waitAllPromises();
+		return { ...component, testDefinitionStore };
+	};
+
+	it('should render empty state when no tests exist', async () => {
+		const { getByTestId } = await renderComponentWithFeatureEnabled({ testDefinitions: [] });
+
+		expect(getByTestId('test-definition-empty-state')).toBeTruthy();
+	});
+
+	it('should render tests list when tests exist', async () => {
+		const { getByTestId } = await renderComponentWithFeatureEnabled();
+
+		expect(getByTestId('test-definition-list')).toBeTruthy();
+	});
+
+	it('should load initial data on mount', async () => {
+		const { testDefinitionStore } = await renderComponentWithFeatureEnabled();
+
+		expect(testDefinitionStore.fetchAll).toHaveBeenCalledWith({
+			workflowId: 'workflow1',
+		});
+		expect(mockedStore(useAnnotationTagsStore).fetchAll).toHaveBeenCalled();
+	});
+
+	it('should start test run and show success message', async () => {
+		const { getByTestId } = await renderComponentWithFeatureEnabled();
+
+		const runButton = getByTestId('run-test-button-1');
+		runButton.click();
+		await nextTick();
+
+		expect(startTestRunMock).toHaveBeenCalledWith('1');
+		expect(fetchTestRunsMock).toHaveBeenCalledWith('1');
+		expect(showMessageMock).toHaveBeenCalledWith({
+			title: expect.any(String),
+			type: 'success',
+		});
+	});
+
+	it('should show error message on failed test run', async () => {
+		const { getByTestId, testDefinitionStore } = await renderComponentWithFeatureEnabled();
+		testDefinitionStore.startTestRun = vi.fn().mockRejectedValue(new Error('Run failed'));
+
+		const runButton = getByTestId('run-test-button-1');
+		runButton.click();
+		await nextTick();
+
+		expect(showErrorMock).toHaveBeenCalledWith(expect.any(Error), expect.any(String));
+	});
+
+	it('should delete test and show success message', async () => {
+		const { getByTestId, testDefinitionStore } = await renderComponentWithFeatureEnabled();
+
+		const deleteButton = getByTestId('delete-test-button-1');
+		deleteButton.click();
+		await nextTick();
+
+		expect(testDefinitionStore.deleteById).toHaveBeenCalledWith('1');
+		expect(showMessageMock).toHaveBeenCalledWith({
+			title: expect.any(String),
+			type: 'success',
+		});
+	});
+
+	it('should sort tests by updated date in descending order', async () => {
+		const { container } = await renderComponentWithFeatureEnabled();
+
+		const testItems = container.querySelectorAll('[data-test-id^="test-item-"]');
+		expect(testItems[0].getAttribute('data-test-id')).toBe('test-item-3');
+		expect(testItems[1].getAttribute('data-test-id')).toBe('test-item-2');
+		expect(testItems[2].getAttribute('data-test-id')).toBe('test-item-1');
+	});
+});

packages/editor-ui/src/views/TestDefinition/tests/TestDefinitionRunDetailView.test.ts

@@ -0,0 +1,267 @@
+import type { Mock } from 'vitest';
+import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+import { createPinia, setActivePinia } from 'pinia';
+import { createTestingPinia } from '@pinia/testing';
+import { createComponentRenderer } from '@/__tests__/render';
+import TestDefinitionRunDetailView from '@/views/TestDefinition/TestDefinitionRunDetailView.vue';
+import { useRoute, useRouter } from 'vue-router';
+import { useToast } from '@/composables/useToast';
+import { useTestDefinitionStore } from '@/stores/testDefinition.store.ee';
+import { useExecutionsStore } from '@/stores/executions.store';
+import { useWorkflowsStore } from '@/stores/workflows.store';
+import { nextTick, ref } from 'vue';
+import { mockedStore, waitAllPromises } from '@/__tests__/utils';
+import { VIEWS } from '@/constants';
+import type { TestRunRecord } from '@/api/testDefinition.ee';
+import type { IWorkflowDb } from '@/Interface';
+
+vi.mock('vue-router');
+vi.mock('@/composables/useToast');
+
+describe('TestDefinitionRunDetailView', () => {
+	const renderComponent = createComponentRenderer(TestDefinitionRunDetailView);
+
+	let showErrorMock: Mock;
+	let getTestRunMock: Mock;
+	let fetchExecutionsMock: Mock;
+	let fetchExecutionMock: Mock;
+
+	const mockTestRun: TestRunRecord = {
+		id: 'run1',
+		status: 'completed',
+		runAt: '2023-01-01T00:00:00.000Z',
+		metrics: {
+			accuracy: 0.95,
+			precision: 0.88,
+		},
+		testDefinitionId: 'test1',
+		createdAt: '2023-01-01T00:00:00.000Z',
+		updatedAt: '2023-01-01T00:00:00.000Z',
+		completedAt: '2023-01-01T00:00:00.000Z',
+	};
+
+	const mockTestDefinition = {
+		id: 'test1',
+		name: 'Test Definition 1',
+		evaluationWorkflowId: 'workflow1',
+		workflowId: 'workflow1',
+	};
+
+	const mockWorkflow = {
+		id: 'workflow1',
+		name: 'Evaluation Workflow',
+	};
+
+	const mockExecutions = {
+		results: [
+			{ id: 'exec1', status: 'success' },
+			{ id: 'exec2', status: 'error' },
+		],
+	};
+
+	beforeEach(() => {
+		setActivePinia(createPinia());
+
+		// Mock route with testId and runId
+		vi.mocked(useRoute).mockReturnValue(
+			ref({
+				params: { testId: 'test1', runId: 'run1' },
+				name: VIEWS.TEST_DEFINITION_RUNS,
+			}) as unknown as ReturnType<typeof useRoute>,
+		);
+
+		vi.mocked(useRouter).mockReturnValue({
+			back: vi.fn(),
+			currentRoute: { value: { params: { testId: 'test1', runId: 'run1' } } },
+			resolve: vi.fn().mockResolvedValue({ href: 'test-definition-run-detail' }),
+		} as unknown as ReturnType<typeof useRouter>);
+
+		showErrorMock = vi.fn();
+		getTestRunMock = vi.fn().mockResolvedValue(mockTestRun);
+		fetchExecutionsMock = vi.fn().mockResolvedValue(mockExecutions);
+		fetchExecutionMock = vi.fn().mockResolvedValue({
+			data: {
+				resultData: {
+					lastNodeExecuted: 'Node1',
+					runData: {
+						Node1: [{ data: { main: [[{ json: { accuracy: 0.95 } }]] } }],
+					},
+				},
+			},
+		});
+
+		vi.mocked(useToast).mockReturnValue({
+			showError: showErrorMock,
+		} as unknown as ReturnType<typeof useToast>);
+	});
+
+	afterEach(() => {
+		vi.clearAllMocks();
+	});
+
+	it('should load run details on mount', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.testRunsById = { run1: mockTestRun };
+		testDefinitionStore.testDefinitionsById = { test1: mockTestDefinition };
+		testDefinitionStore.getTestRun = getTestRunMock;
+
+		const executionsStore = mockedStore(useExecutionsStore);
+		executionsStore.fetchExecutions = fetchExecutionsMock;
+		executionsStore.fetchExecution = fetchExecutionMock;
+
+		const workflowsStore = mockedStore(useWorkflowsStore);
+		workflowsStore.workflowsById = { workflow1: mockWorkflow as IWorkflowDb };
+
+		const { getByTestId } = renderComponent({ pinia });
+		await nextTick();
+
+		expect(getTestRunMock).toHaveBeenCalledWith({
+			testDefinitionId: 'test1',
+			runId: 'run1',
+		});
+		// expect(fetchExecutionsMock).toHaveBeenCalled();
+		expect(getByTestId('test-definition-run-detail')).toBeTruthy();
+	});
+
+	it('should display test run metrics', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.testRunsById = { run1: mockTestRun };
+		testDefinitionStore.testDefinitionsById = { test1: mockTestDefinition };
+		testDefinitionStore.getTestRun = getTestRunMock;
+
+		const { container } = renderComponent({ pinia });
+		await nextTick();
+
+		const metricsCards = container.querySelectorAll('.summaryCard');
+		expect(metricsCards.length).toBeGreaterThan(0);
+		expect(container.textContent).toContain('0.95'); // Check for accuracy metric
+	});
+
+	it('should handle errors when loading run details', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.getTestRun = vi.fn().mockRejectedValue(new Error('Failed to load'));
+
+		renderComponent({ pinia });
+		await nextTick();
+
+		expect(showErrorMock).toHaveBeenCalledWith(expect.any(Error), 'Failed to load run details');
+	});
+
+	it('should navigate back when back button is clicked', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const router = useRouter();
+		const { getByTestId } = renderComponent({ pinia });
+		await nextTick();
+
+		const backButton = getByTestId('test-definition-run-detail').querySelector('.backButton');
+		backButton?.dispatchEvent(new Event('click'));
+
+		expect(router.back).toHaveBeenCalled();
+	});
+
+	// Test loading states
+	it('should show loading state while fetching data', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.getTestRun = vi
+			.fn()
+			.mockImplementation(async () => await new Promise(() => {})); // Never resolves
+
+		const { container } = renderComponent({ pinia });
+		await nextTick();
+
+		expect(container.querySelector('.loading')).toBeTruthy();
+	});
+
+	// Test metrics display
+	it('should correctly format and display all metrics', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testRunWithMultipleMetrics = {
+			...mockTestRun,
+			metrics: {
+				accuracy: 0.956789,
+				precision: 0.887654,
+				recall: 0.923456,
+				f1_score: 0.901234,
+			},
+		};
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.testRunsById = { run1: testRunWithMultipleMetrics };
+		testDefinitionStore.testDefinitionsById = { test1: mockTestDefinition };
+
+		const { container } = renderComponent({ pinia });
+		await nextTick();
+
+		// Check if the metrics are displayed correctly with 2 decimal places
+		expect(container.textContent).toContain('0.96');
+		expect(container.textContent).toContain('0.89');
+		expect(container.textContent).toContain('0.92');
+		expect(container.textContent).toContain('0.90');
+	});
+
+	// Test status display
+	it('should display correct status with appropriate styling', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testRunWithStatus: TestRunRecord = {
+			...mockTestRun,
+			status: 'error',
+		};
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		testDefinitionStore.testRunsById = { run1: testRunWithStatus };
+		testDefinitionStore.testDefinitionsById = { test1: mockTestDefinition };
+
+		const { container } = renderComponent({ pinia });
+		await nextTick();
+
+		const statusElement = container.querySelector('.error');
+		expect(statusElement).toBeTruthy();
+		expect(statusElement?.textContent?.trim()).toBe('error');
+	});
+
+	// Test table data
+	it('should correctly populate the test cases table', async () => {
+		const pinia = createTestingPinia();
+		setActivePinia(pinia);
+
+		const testDefinitionStore = mockedStore(useTestDefinitionStore);
+		const executionsStore = mockedStore(useExecutionsStore);
+
+		// Mock all required store methods
+		testDefinitionStore.testRunsById = { run1: mockTestRun };
+		testDefinitionStore.testDefinitionsById = { test1: mockTestDefinition };
+		testDefinitionStore.getTestRun = getTestRunMock;
+		// Add this mock for fetchTestDefinition
+		testDefinitionStore.fetchTestDefinition = vi.fn().mockResolvedValue(mockTestDefinition);
+
+		executionsStore.fetchExecutions = fetchExecutionsMock;
+		executionsStore.fetchExecution = fetchExecutionMock;
+
+		const { container } = renderComponent({ pinia });
+		await nextTick();
+
+		// Wait for all promises to resolve
+		await waitAllPromises();
+
+		const tableRows = container.querySelectorAll('.el-table__row');
+		expect(tableRows.length).toBe(mockExecutions.results.length);
+	});
+});

packages/nodes-base/nodes/Form/Form.node.ts

@@ -19,7 +19,6 @@ import {
 	WAIT_INDEFINITELY,
 } from 'n8n-workflow';
 
-import { type CompletionPageConfig } from './interfaces';
 import { formDescription, formFields, formTitle } from '../Form/common.descriptions';
 import { prepareFormReturnItem, renderForm, resolveRawData } from '../Form/utils';
 
@@ -273,19 +272,19 @@ export class Form extends Node {
 		const method = context.getRequestObject().method;
 
 		if (operation === 'completion' && method === 'GET') {
-			const staticData = context.getWorkflowStaticData('node');
-			const id = `${context.getExecutionId()}-${context.getNode().name}`;
-			const config = staticData?.[id] as CompletionPageConfig;
-			delete staticData[id];
+			const completionTitle = context.getNodeParameter('completionTitle', '') as string;
+			const completionMessage = context.getNodeParameter('completionMessage', '') as string;
+			const redirectUrl = context.getNodeParameter('redirectUrl', '') as string;
+			const options = context.getNodeParameter('options', {}) as { formTitle: string };
 
-			if (config.redirectUrl) {
+			if (redirectUrl) {
 				res.send(
-					`<html><head><meta http-equiv="refresh" content="0; url=${config.redirectUrl}"></head></html>`,
+					`<html><head><meta http-equiv="refresh" content="0; url=${redirectUrl}"></head></html>`,
 				);
 				return { noWebhookResponse: true };
 			}
 
-			let title = config.pageTitle;
+			let title = options.formTitle;
 			if (!title) {
 				title = context.evaluateExpression(
 					`{{ $('${trigger?.name}').params.formTitle }}`,
@@ -296,8 +295,8 @@ export class Form extends Node {
 			) as boolean;
 
 			res.render('form-trigger-completion', {
-				title: config.completionTitle,
-				message: config.completionMessage,
+				title: completionTitle,
+				message: completionMessage,
 				formTitle: title,
 				appendAttribution,
 			});
@@ -419,28 +418,7 @@ export class Form extends Node {
 			);
 		}
 
-		if (operation !== 'completion') {
-			await context.putExecutionToWait(WAIT_INDEFINITELY);
-		} else {
-			const staticData = context.getWorkflowStaticData('node');
-			const completionTitle = context.getNodeParameter('completionTitle', 0, '') as string;
-			const completionMessage = context.getNodeParameter('completionMessage', 0, '') as string;
-			const redirectUrl = context.getNodeParameter('redirectUrl', 0, '') as string;
-			const options = context.getNodeParameter('options', 0, {}) as { formTitle: string };
-			const id = `${context.getExecutionId()}-${context.getNode().name}`;
-
-			const config: CompletionPageConfig = {
-				completionTitle,
-				completionMessage,
-				redirectUrl,
-				pageTitle: options.formTitle,
-			};
-
-			staticData[id] = config;
-
-			const waitTill = new Date(WAIT_INDEFINITELY);
-			await context.putExecutionToWait(waitTill);
-		}
+		await context.putExecutionToWait(WAIT_INDEFINITELY);
 
 		return [context.getInputData()];
 	}

packages/nodes-base/nodes/Form/interfaces.ts

@@ -32,11 +32,4 @@ export type FormTriggerData = {
 	buttonLabel?: string;
 };
 
-export type CompletionPageConfig = {
-	pageTitle?: string;
-	completionMessage?: string;
-	completionTitle?: string;
-	redirectUrl?: string;
-};
-
 export const FORM_TRIGGER_AUTHENTICATION_PROPERTY = 'authentication';

packages/nodes-base/nodes/Form/test/Form.node.test.ts

@@ -172,7 +172,7 @@ describe('Form Node', () => {
 			]);
 		});
 
-		it('should handle completion operation', async () => {
+		it('should handle completion operation and render completion page', async () => {
 			mockWebhookFunctions.getRequestObject.mockReturnValue({ method: 'GET' } as Request);
 			mockWebhookFunctions.getNodeParameter.mockImplementation((paramName) => {
 				if (paramName === 'operation') return 'completion';
@@ -181,6 +181,7 @@ describe('Form Node', () => {
 				if (paramName === 'respondWith') return 'text';
 				if (paramName === 'completionTitle') return 'Test Title';
 				if (paramName === 'completionMessage') return 'Test Message';
+				if (paramName === 'redirectUrl') return '';
 				return {};
 			});
 			mockWebhookFunctions.getParentNodes.mockReturnValue([
@@ -202,16 +203,55 @@ describe('Form Node', () => {
 			);
 			mockWebhookFunctions.getNode.mockReturnValue(mock<INode>({ name: formCompletionNodeName }));
 			mockWebhookFunctions.getExecutionId.mockReturnValue(testExecutionId);
-			mockWebhookFunctions.getWorkflowStaticData.mockReturnValue({
-				[`${testExecutionId}-${formCompletionNodeName}`]: { redirectUrl: '' },
-			});
 
 			const result = await form.webhook(mockWebhookFunctions);
 
 			expect(result).toEqual({ noWebhookResponse: true });
-			expect(mockResponseObject.render).toHaveBeenCalledWith(
-				'form-trigger-completion',
-				expect.any(Object),
+			expect(mockResponseObject.render).toHaveBeenCalledWith('form-trigger-completion', {
+				appendAttribution: 'test',
+				formTitle: 'test',
+				message: 'Test Message',
+				title: 'Test Title',
+			});
+		});
+
+		it('should handle completion operation and redirect', async () => {
+			mockWebhookFunctions.getRequestObject.mockReturnValue({ method: 'GET' } as Request);
+			mockWebhookFunctions.getNodeParameter.mockImplementation((paramName) => {
+				if (paramName === 'operation') return 'completion';
+				if (paramName === 'useJson') return false;
+				if (paramName === 'jsonOutput') return '[]';
+				if (paramName === 'respondWith') return 'text';
+				if (paramName === 'completionTitle') return 'Test Title';
+				if (paramName === 'completionMessage') return 'Test Message';
+				if (paramName === 'redirectUrl') return 'https://n8n.io';
+				return {};
+			});
+			mockWebhookFunctions.getParentNodes.mockReturnValue([
+				{
+					type: 'n8n-nodes-base.formTrigger',
+					name: 'Form Trigger',
+					typeVersion: 2.1,
+					disabled: false,
+				},
+			]);
+			mockWebhookFunctions.evaluateExpression.mockReturnValue('test');
+
+			const mockResponseObject = {
+				render: jest.fn(),
+				redirect: jest.fn(),
+				send: jest.fn(),
+			};
+			mockWebhookFunctions.getResponseObject.mockReturnValue(
+				mockResponseObject as unknown as Response,
+			);
+			mockWebhookFunctions.getNode.mockReturnValue(mock<INode>({ name: formCompletionNodeName }));
+
+			const result = await form.webhook(mockWebhookFunctions);
+
+			expect(result).toEqual({ noWebhookResponse: true });
+			expect(mockResponseObject.send).toHaveBeenCalledWith(
+				'<html><head><meta http-equiv="refresh" content="0; url=https://n8n.io"></head></html>',
 			);
 		});
 	});