buster/packages/ai/tests/workflows/integration/analyst-workflow.int.test.ts

544 lines
21 KiB
TypeScript
Raw Normal View History

Mastra braintrust (#391) * type fixes * biome clean on ai * add user to flag chat * attempt to get vercel deployed * Update tsup.config.ts * Update pnpm-lock.yaml * Add @buster/server2 Hono API app with Vercel deployment configuration * slack oauth integration * mainly some clean up and biome formatting * slack oauth * slack migration + snapshot * remove unused files * finalized docker image for porter * Create porter_app_buster-server_3155.yml file * Add integration tests for Slack handler and refactor Slack OAuth service - Introduced integration tests for the Slack handler, covering OAuth initiation, callback handling, and integration status retrieval. - Refactored Slack OAuth service to improve error handling and ensure proper integration state management. - Updated token storage implementation to use a database vault instead of Supabase. - Enhanced existing tests for better coverage and reliability, including cleanup of test data. - Added new utility functions for managing vault secrets in the database. * docker image update * new prompts * individual tests and a schema fix * server build * final working dockerfile * Update Dockerfile * new messages to slack messages (#369) * Update dockerfile * Update validate-env.js * update build pipeline * Update the dockerfile flow * finalize logging for pino * stable base * Update cors middleware logger * Update cors.ts * update docker to be more imformative * Update index.ts * Update auth.ts * Update cors.ts * Update cors.ts * Update logger.ts * remove logs * more cors updates * build server shared * Refactor PostgreSQL credentials handling and remove unused memory storage. Update package dependencies. (#370) * tons of file parsing errors (#371) * Refactor PostgreSQL credentials handling and remove unused memory storage. Update package dependencies. * tons of file parsing errors * Dev mode updates * more stable electric handler * Dal/agent-self-healing-fixes (#372) * change to 6 min * optmizations around saving and non-blocking actions. * stream optimizations * Dal/agent-self-healing-fixes (#373) * change to 6 min * optmizations around saving and non-blocking actions. * stream optimizations * change porter staging deploy to mastra-braintrust. * new path for porter deploy * deploy to staging fix * Create porter_app_mastra-braintrust-api_3155.yml file (#375) Co-authored-by: porter-deployment-app[bot] <87230664+porter-deployment-app[bot]@users.noreply.github.com> * Update sizing and opacity * supe up the instance for mastra * environment staging * ssl script * copy path * Update list padding * no throttle and the anthropic cached * move select to the top * Update margin inline start * shrink reasoning vertical space to 2px * semi bold font for headers * update animation timing * haiku * Add createTodoList tool and integrate into create-todos-step * chat helper on post chat * only trigger cicd when change made * Start created streaming text components * Refactor analyst agent task to initialize Braintrust logging asynchronously and parallelize database queries for improved performance. Adjusted cleanup timeout for Braintrust traces to reduce delays. * fixed reasoned for X, so that it rounds down to the minute * Update users page * update build pipeline for new web * document title update * Named chats for page * Datasets titles * Refactor visualization tools and enhance error handling in retryable agent stream. Removed unused metricValueLabel from metrics file tool, updated metric configuration schemas, and improved healing mechanism for tool errors during streaming. * analyst * document title updates * Update useDocumentTitle.tsx * Refactor tool choice configuration in create-todos-step to use structured object. Remove exponential backoff logic from retryable agent stream for healable errors. Introduce new test for real-world healing scenarios in retryable agent stream. * Refactor SQL validation logic in modify-metrics-file-tool to skip unnecessary checks when SQL has not changed. Enhance error handling and update validation messages. Clean up code formatting for improved readability. * update collapse for filecard * chevron collapse * Jacob prompt changes (#376) * prompt changes to improve filtering logic and handle priv/sec errors * prompt changes to make aggregation better and improved filter best practices * Update packages/ai/src/steps/create-todos-step.ts Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Update packages/ai/src/agents/think-and-prep-agent/think-and-prep-instructions.ts Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Update packages/ai/src/steps/create-todos-step.ts Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> Co-authored-by: dal <dallin@buster.so> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * think and prep * change header and strong fonts weights * Update get collection * combo chart x axis update * Create a chart schemas as types * schema types * simple unit tests for line chart props * fix the response file ordering iwth active selection. * copy around reasoning messages taken care of * fix nullable user message and file processing and such. * update ticks for chart config * fix todo parsing. * app markdown update * Update splitter to use border instead of width * change ml * If no file is found we should auto redirect * Refactor database connection handling to support SSL modes. Introduced functions to extract SSL parameters and manage connections based on SSL requirements, including a custom verifier for unverified connections. * black box message update * chat title updates * optimizations for trigger. * some keepalive logic on the anthropic cached * keep title empty until new one * no duplicate messages * null user message on asset pull * posthog error handling * 20 sec idle timeout on anthropic * null req message * fixed modificiation names missing * Refactor tool call handling to support new content array format in asset messages and context loaders * cache most recent file from workflow * Enhance date and number detection in createDataMetadata function to improve data type handling for metrics files * group hover effect for message * logging for chat * Add messageId handling and file association tracking in dashboard and metrics tools - Updated runtime context to include messageId in create and modify dashboard and metrics file tools. - Implemented file association tracking based on messageId in create and modify functions for both dashboards and metrics. - Ensured type consistency by using AnalystRuntimeContext in runtime context parameters. * logging for chat * message type update * Route to first file instead * trigger moved to catalog * Enhance file selection logic to support YAML parsing and improve logging - Updated `extractMetricIdsFromDashboard` to first attempt JSON parsing, falling back to a regex-based YAML parsing for metric IDs. - Added detailed debug logging in `selectFilesForResponse` to track file selection process, including metrics and dashboards involved. - Introduced tests for various scenarios in `file-selection.test.ts` to ensure correct behavior with dashboard context and edge cases. * trigger dev v4-beta * Retry + Self Healing (#381) * Refactor retry logic in analyst and think-and-prep steps Co-authored-by: dallin <dallin@buster.so> * some fixes * console log error * self healing * todos retry --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> * remove lots of logs * Remove chat streaming * Remove chat streaming * timeout * Change to updated at field * link to home * Update timeout settings for HTTP and HTTPS agents from 20 seconds to 10 seconds for improved responsiveness. * Add utils module and integrate message conversion in post_chat_handler * Implement error handling for extract values (#382) * Remove chat streaming * Improve error handling and logging in extract values and chat title steps Co-authored-by: dallin <dallin@buster.so> --------- Co-authored-by: Nate Kelley <nate@buster.so> Co-authored-by: Cursor Agent <cursoragent@cursor.com> * loading icon for buster avatar * finalize tooltip cache * upgrade mastra * increase retries * Add redo functionality for chat messages - Introduced `redoFromMessageId` parameter in `handleExistingChat` to allow users to specify a message to redo from. - Implemented validation to ensure the specified message belongs to the current chat. - Added `softDeleteMessagesFromPoint` function to soft delete a message and all subsequent messages in the same chat, facilitating the redo feature. * fix electric potential memory leak * tooltip cache and chart cleanup * Update bullet to be more indented * latest version number * add support endpoint to new server * Fix jank in combo bar charts * index check for dashboard * Collapse only if there are metrics * Is finished reasoing back * Update dependencies and enhance chat message handling - Upgraded `@mastra/core` to version 0.10.8 and added `node-sql-parser` at version 5.3.10 in the lock file. - Improved integration tests for chat message redo functionality, ensuring correct behavior when deriving `chat_id` from `message_id`. - Enhanced error handling and validation in the `initializeChat` function to manage cases where `chat_id` is not provided. * Update pnpm-lock and enhance chat message integration tests - Added `node-sql-parser` version 5.3.10 to dependencies and updated the lock file. - Improved integration tests for chat message redo functionality, ensuring accurate deletion and retrieval of messages. - Enhanced the `initializeChat` function to derive `chat_id` from `message_id` when not provided, improving error handling and validation. * remove .env import breaking build * add updated at to the get chat handler * zmall runtime error fix * permission tests passing * return updated at on the get chat handler now * slq parser fixes * Implement chat access control logic and add comprehensive tests - Developed the `canUserAccessChat` function to determine user access to chats based on direct permissions, collection permissions, creator status, and organizational roles. - Introduced helper functions for checking permissions and retrieving chat information. - Added integration tests to validate access control logic, covering various scenarios including direct permissions, collection permissions, and user roles. - Created unit tests to ensure the correctness of the access control function with mocked database interactions. - Included simple integration tests to verify functionality with existing database data. * sql parser and int tests working. * fix test and lint issues * comment to kick off deployment lo * access controls on datasets * electric context bug fix with sql helpers. * permission and read only * Add lru-cache dependency and export cache management functions - Added `lru-cache` as a dependency in the access-controls package. - Exported new cache management functions from `chats-cached` module, including `canUserAccessChatCached`, `getCacheStats`, `resetCacheStats`, `clearCache`, `invalidateAccess`, `invalidateUserAccess`, and `invalidateChatAccess`. * packages deploy as well * wrong workflow lol * Update AppVerticalCodeSplitter.tsx * Add error handling for query run and SQL save operations Co-authored-by: natemkelley <natemkelley@gmail.com> * Trim whitespace from input values before sending chat prompts Co-authored-by: natemkelley <natemkelley@gmail.com> * type in think-and-prep * use the cached access chat * update package version * new asset import message * Error fallback for login * Update BusterChart.BarChart.stories.tsx * Staging changes to fix number card titles, combo chart axis, and using dynamic filters (#386) Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> * db init command pass through * combo chart fixes (#387) Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> * clarifying question and connection logic * pino pretty error fix * clarifying is a finishing tool * change update latest version logic * Update support endpoint * fixes for horizontal bar charts and added the combo chart logic to update metrics (#388) Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> * permission fix on dashboard metric handlers for workspace and data admin * Add more try catches * Hide avatar is no more * Horizontal bar fixes (#389) * fixes for horizontal bar charts and added the combo chart logic to update metrics * hopefully fixed horizontal bar charts --------- Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> * reasoning shimmer update * Make the embed flow work with versions * new account warning update * Move support modal * compact number for pie label * Add final reasoning message tracking and workflow start time to chunk processor and related steps - Introduced `finalReasoningMessage` to schemas in `analyst-step`, `mark-message-complete-step`, and `create-todos-step`. - Updated `ChunkProcessor` to calculate and store the final reasoning message based on workflow duration. - Enhanced various steps to utilize the new `workflowStartTime` for better tracking of execution duration. - Improved database update logic to include `finalReasoningMessage` when applicable. * 9 digit cutoff for pie * trigger update * test on mastra braintrust * test deployment * testing * pnpm install * pnpm * node 22 * pnpm version * trigger main * get initial chat file * hono main deploymenbt * clear timeouts * Remove console logs * migration test to staging * db url * try again * k get rid of tls var * hmmm lets try this * mark migrations * fix migration file? * drizzle-kit upgrade * tweaks to the github actions --------- Co-authored-by: Nate Kelley <nate@buster.so> Co-authored-by: porter-deployment-app[bot] <87230664+porter-deployment-app[bot]@users.noreply.github.com> Co-authored-by: Nate Kelley <133379588+nate-kelley-buster@users.noreply.github.com> Co-authored-by: Jacob Anderson <jacobanderson@Jacobs-MacBook-Air.local> Co-authored-by: jacob-buster <jacob@buster.so> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: natemkelley <natemkelley@gmail.com>
2025-07-03 05:33:40 +08:00
import { chats, db, eq, messages } from '@buster/database';
import { createTestChat, createTestMessage } from '@buster/test-utils';
import { RuntimeContext } from '@mastra/core/runtime-context';
import type { CoreMessage } from 'ai';
import { initLogger, wrapTraced } from 'braintrust';
import { afterAll, beforeAll, describe, expect, test } from 'vitest';
import { getRawLlmMessagesByMessageId } from '../../../src';
import analystWorkflow, {
type AnalystRuntimeContext,
} from '../../../src/workflows/analyst-workflow';
describe('Analyst Workflow Integration Tests', () => {
beforeAll(() => {
initLogger({
apiKey: process.env.BRAINTRUST_KEY,
projectName: 'ANALYST-WORKFLOW',
});
});
afterAll(async () => {
await new Promise((resolve) => setTimeout(resolve, 10000));
});
test('should successfully execute analyst workflow with conversation history', async () => {
// Use the provided conversation history from think-and-prep to analyst
const conversationHistory: CoreMessage[] = [
{
content: [
{
text: 'what are our top 10 products from the last 6 months from accessories',
type: 'text',
},
],
role: 'user',
},
];
const testInput = {
prompt: 'What is the follow-up analysis for the previous customer data?',
conversationHistory: conversationHistory.length > 0 ? conversationHistory : undefined,
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
// Note: No messageId set to test non-database scenario
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow with History' }
);
const result = await tracedWorkflow();
expect(result).toBeDefined();
}, 300000);
test('should successfully execute analyst workflow with messageId for database save', async () => {
// Use existing test organization and user IDs to avoid database creation issues
const organizationId = 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce';
const userId = 'c2dd64cd-f7f3-4884-bc91-d46ae431901e';
const chatId = crypto.randomUUID();
const messageId = crypto.randomUUID();
const workflowStartTime = Date.now();
// Create chat first
try {
await db.insert(chats).values({
id: chatId,
title: 'Test Chat for Message Save',
organizationId,
createdBy: userId,
updatedBy: userId,
publiclyAccessible: false,
});
// Then create message
await db.insert(messages).values({
id: messageId,
chatId,
createdBy: userId,
title: 'Test Message',
requestMessage: 'which product was bought the most last month from our accessory product',
responseMessages: [],
reasoning: [],
rawLlmMessages: [],
finalReasoningMessage: '',
isCompleted: false,
});
} catch (error) {
console.error('Failed to create test data:', error);
// Clean up if chat was created but message failed
try {
await db.delete(chats).where(eq(chats.id, chatId));
} catch {} // Ignore cleanup errors
return;
}
const testInput = {
prompt: 'which product was bought the most last month from our accessory product',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', userId);
runtimeContext.set('chatId', chatId);
runtimeContext.set('organizationId', organizationId);
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
runtimeContext.set('messageId', messageId); // This should trigger database saves
runtimeContext.set('workflowStartTime', workflowStartTime);
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow with Database Save' }
);
const result = await tracedWorkflow();
expect(result).toBeDefined();
// Add a small delay to ensure all database saves have completed
await new Promise((resolve) => setTimeout(resolve, 2000));
// Verify that conversation history was saved to database
const updatedMessage = await db.select().from(messages).where(eq(messages.id, messageId));
expect(updatedMessage).toHaveLength(1);
console.log('\n=== DATABASE SAVE VERIFICATION ===');
console.log('Message ID:', messageId);
console.log('Raw LLM Messages count:', updatedMessage[0]!.rawLlmMessages?.length || 0);
console.log('Reasoning entries count:', updatedMessage[0]!.reasoning?.length || 0);
console.log('Response messages count:', updatedMessage[0]!.responseMessages?.length || 0);
// Check reasoning entries for partial content
if (updatedMessage[0]!.reasoning && Array.isArray(updatedMessage[0]!.reasoning)) {
console.log('\n=== REASONING ENTRIES ===');
updatedMessage[0]!.reasoning.forEach(
(
entry: { type: string; title: string; status: string; message?: string },
index: number
) => {
console.log(`\nReasoning Entry ${index + 1}:`);
console.log(' Type:', entry.type);
console.log(' Title:', entry.title);
console.log(' Status:', entry.status);
if (entry.message) {
console.log(' Message length:', entry.message.length);
console.log(' Message preview:', `${entry.message.substring(0, 100)}...`);
}
}
);
}
// Check response messages
if (updatedMessage[0]!.responseMessages && Array.isArray(updatedMessage[0]!.responseMessages)) {
console.log('\n=== RESPONSE MESSAGES ===');
updatedMessage[0]!.responseMessages.forEach(
(entry: { type: string; is_final_message: boolean; message?: string }, index: number) => {
console.log(`\nResponse Message ${index + 1}:`);
console.log(' Type:', entry.type);
console.log(' Is Final:', entry.is_final_message);
if (entry.message) {
console.log(' Message length:', entry.message.length);
console.log(' Message preview:', `${entry.message.substring(0, 100)}...`);
}
}
);
}
// Assert that we have raw LLM messages
expect(updatedMessage[0]!.rawLlmMessages).toBeDefined();
expect(Array.isArray(updatedMessage[0]!.rawLlmMessages)).toBe(true);
if (Array.isArray(updatedMessage[0]!.rawLlmMessages)) {
expect(updatedMessage[0]!.rawLlmMessages.length).toBeGreaterThan(0);
}
// Assert that we have response messages with actual content
expect(updatedMessage[0]!.responseMessages).toBeDefined();
expect(Array.isArray(updatedMessage[0]!.responseMessages)).toBe(true);
expect(updatedMessage[0]!.responseMessages.length).toBeGreaterThan(0);
// Check that at least one response message has content
const responseWithContent = updatedMessage[0]!.responseMessages.find(
(msg: { message?: string }) => msg.message && msg.message.length > 0
);
expect(responseWithContent).toBeDefined();
expect(responseWithContent?.message).toBeTruthy();
expect(responseWithContent?.message?.length).toBeGreaterThan(10); // Should have meaningful content
}, 300000);
test('should successfully execute analyst workflow with valid input', async () => {
const testInput = {
prompt:
'What are the top 5 customers by total revenue for this quarter? Please include their names and total order amounts.',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow Basic Test' }
);
const result = await tracedWorkflow();
expect(result).toBeDefined();
}, 300000);
test('should successfully execute analyst workflow with valid input', async () => {
const testInput = {
prompt:
'Can you show me our highest value customers and their total order amounts? Include customer details.',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow Basic Test' }
);
const result = await tracedWorkflow();
expect(result).toBeDefined();
}, 300000);
test('should execute initial message then follow-up with retrieved conversation history', async () => {
// Step 1: Create test chat and message in database
// Use the same organizationId and userId as other tests to ensure they exist
const organizationId = 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce';
const userId = 'c2dd64cd-f7f3-4884-bc91-d46ae431901e';
const { chatId } = await createTestChat(organizationId, userId);
const messageId = await createTestMessage(chatId, userId);
// Step 2: Run initial workflow with messageId to save conversation history
const initialInput = {
prompt: 'What are our top 5 products by revenue in the last quarter?',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', userId);
runtimeContext.set('chatId', chatId);
runtimeContext.set('organizationId', organizationId);
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
runtimeContext.set('messageId', messageId); // This triggers saving to rawLlmMessages
const initialTracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: initialInput,
runtimeContext,
});
},
{ name: 'Initial Message Workflow' }
);
const initialResult = await initialTracedWorkflow();
expect(initialResult).toBeDefined();
console.log('Initial workflow completed');
// Step 3: Retrieve conversation history from database
console.log('Retrieving conversation history from database...');
const conversationHistory = await getRawLlmMessagesByMessageId(messageId);
// Verify conversation history was saved
expect(conversationHistory).toBeDefined();
expect(conversationHistory).not.toBeNull();
if (conversationHistory) {
expect(Array.isArray(conversationHistory)).toBe(true);
expect(conversationHistory.length).toBeGreaterThan(0);
console.log(`Retrieved ${conversationHistory.length} messages from conversation history`);
}
// Step 4: Run follow-up workflow with retrieved conversation history
const followUpInput = {
prompt: 'Can you show me the year-over-year growth for these top products?',
conversationHistory: conversationHistory as CoreMessage[],
};
// Create new message for follow-up
const followUpMessageId = await createTestMessage(chatId, userId);
runtimeContext.set('messageId', followUpMessageId);
console.log('Running follow-up workflow with conversation history...');
const followUpTracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: followUpInput,
runtimeContext,
});
},
{ name: 'Follow-up Message Workflow' }
);
const followUpResult = await followUpTracedWorkflow();
expect(followUpResult).toBeDefined();
console.log('Follow-up workflow completed');
// Verify both messages were saved to database
const allMessages = await db
.select()
.from(messages)
.where(eq(messages.chatId, chatId))
.orderBy(messages.createdAt);
expect(allMessages).toHaveLength(2);
expect(allMessages[0]!.id).toBe(messageId);
expect(allMessages[1]!.id).toBe(followUpMessageId);
// Verify both have rawLlmMessages
expect(allMessages[0]!.rawLlmMessages).toBeDefined();
expect(allMessages[1]!.rawLlmMessages).toBeDefined();
console.log('Test completed successfully - both messages saved with conversation history');
}, 600000); // Increased timeout for two workflow runs
test('should execute workflow with conversation history passed directly from first to second run', async () => {
// Step 1: Run initial workflow WITHOUT database save (no messageId)
const initialInput = {
prompt: 'What are the top 3 suppliers by total order value in our database?',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
// Note: No messageId set - this should prevent database save and allow direct output usage
console.log('Running initial workflow without database save...');
const initialTracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: initialInput,
runtimeContext,
});
},
{ name: 'Initial Workflow (No Database)' }
);
const initialResult = await initialTracedWorkflow();
expect(initialResult).toBeDefined();
console.log('Initial workflow completed');
// Debug: Log what the initial workflow actually returned
console.log('=== INITIAL WORKFLOW RESULT DEBUG ===');
console.log('Result keys:', Object.keys(initialResult));
console.log('Result status:', initialResult.status);
// Get conversation history based on workflow result structure
let conversationHistory: CoreMessage[] | undefined;
if (initialResult.status === 'success') {
conversationHistory = initialResult.result?.conversationHistory;
console.log('Has result.conversationHistory:', !!conversationHistory);
console.log('result.conversationHistory length:', conversationHistory?.length || 0);
} else {
console.log('Workflow failed or suspended');
conversationHistory = undefined;
}
// Step 3: Run follow-up workflow with the conversation history from the first run
const followUpInput = {
prompt:
'For these top suppliers, can you show me their contact information and which countries they are located in?',
conversationHistory: conversationHistory,
};
// Debug: Log what we're passing to the follow-up workflow
console.log('=== FOLLOW-UP INPUT DEBUG ===');
console.log('followUpInput keys:', Object.keys(followUpInput));
console.log(
'followUpInput.conversationHistory length:',
followUpInput.conversationHistory?.length || 0
);
console.log('Running follow-up workflow with conversation history from first run...');
const followUpTracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: followUpInput,
runtimeContext, // Reuse same context (but still no messageId for database save)
});
},
{ name: 'Follow-up Workflow (Direct History)' }
);
const followUpResult = await followUpTracedWorkflow();
expect(followUpResult).toBeDefined();
console.log('Follow-up workflow completed');
// Debug: Log the actual follow-up result structure
console.log('=== FOLLOW-UP WORKFLOW RESULT DEBUG ===');
console.log('Follow-up result keys:', Object.keys(followUpResult));
console.log('Follow-up result status:', followUpResult.status);
// Step 4: Verify that the follow-up workflow also has conversation history
if (followUpResult.status === 'success' && initialResult.status === 'success') {
expect(followUpResult.result?.conversationHistory).toBeDefined();
expect(Array.isArray(followUpResult.result?.conversationHistory)).toBe(true);
expect(followUpResult.result?.conversationHistory?.length).toBeGreaterThan(
initialResult.result?.conversationHistory?.length || 0
);
console.log(
`Follow-up workflow returned ${followUpResult.result?.conversationHistory?.length} messages (increased from ${initialResult.result?.conversationHistory?.length})`
);
// Step 5: Verify that the conversation history includes both interactions
const finalHistory = followUpResult.result?.conversationHistory;
if (finalHistory) {
// Should contain messages from both the initial prompt and follow-up
const userMessages = (finalHistory as CoreMessage[]).filter((msg) => msg.role === 'user');
expect(userMessages.length).toBeGreaterThanOrEqual(2); // At least initial + follow-up
}
console.log(
'Test completed successfully - conversation history passed directly between workflows'
);
} else {
console.log('One or both workflows failed, skipping conversation history verification');
}
}, 600000); // Increased timeout for two workflow runs
test('should handle inappropriate/impossible requests gracefully', async () => {
const testInput = {
prompt: 'who is your daddy and what does he do?',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow - Impossible Request Test' }
);
const result = await tracedWorkflow();
// The workflow should not crash and should return a result
expect(result).toBeDefined();
// Check if the workflow completed successfully or failed gracefully
if (result.status === 'success') {
// If successful, it should have some kind of response
expect(result.result).toBeDefined();
console.log('Workflow handled impossible request gracefully:', result.result);
} else if (result.status === 'failed') {
// If failed, it should have error information
expect(result.error).toBeDefined();
console.log('Workflow failed gracefully with error:', result.error.message);
}
console.log('Impossible request test completed - workflow did not crash');
}, 300000);
test('should handle another type of non-data request gracefully', async () => {
const testInput = {
prompt: 'tell me a joke about databases',
};
const runtimeContext = new RuntimeContext<AnalystRuntimeContext>();
runtimeContext.set('userId', 'c2dd64cd-f7f3-4884-bc91-d46ae431901e');
runtimeContext.set('chatId', crypto.randomUUID());
runtimeContext.set('organizationId', 'bf58d19a-8bb9-4f1d-a257-2d2105e7f1ce');
runtimeContext.set('dataSourceId', 'cc3ef3bc-44ec-4a43-8dc4-681cae5c996a');
runtimeContext.set('dataSourceSyntax', 'postgres');
const tracedWorkflow = wrapTraced(
async () => {
const run = analystWorkflow.createRun();
return await run.start({
inputData: testInput,
runtimeContext,
});
},
{ name: 'Analyst Workflow - Non-Data Request Test' }
);
const result = await tracedWorkflow();
// The workflow should not crash and should return a result
expect(result).toBeDefined();
// Log the result for debugging
console.log('Non-data request test result:', result);
// The workflow should either succeed with a helpful response or fail gracefully
expect(['success', 'failed'].includes(result.status)).toBe(true);
}, 300000);
});