PostgreSQL Enabled TaskFlow #261

mikedane-bitovi · 2025-11-28T16:56:23Z

No description provided.

Copilot

Pull request overview

This PR migrates the TaskFlow application from SQLite to PostgreSQL, adds comprehensive debugging infrastructure for E2E tests, and includes diagnostic logging to troubleshoot a Kanban board bug where tasks were not displaying correctly.

Migrated database from SQLite to PostgreSQL with Docker support
Added E2E test orchestration with server management and browser console logging
Implemented task status normalization logic to handle inconsistent status values
Added extensive debugging logs throughout the application

Reviewed changes

Copilot reviewed 24 out of 25 changed files in this pull request and generated 12 comments.

Show a summary per file

File	Description
`prisma/schema.prisma`	Migrated datasource from SQLite to PostgreSQL with environment-based DATABASE_URL
`prisma/migrations/20251126214802_init/migration.sql`	New PostgreSQL migration creating User, Session, and Task tables
`prisma/migrations/20250807190813_add_task_entity/migration.sql`	Removed SQLite-specific Task table migration
`prisma/migrations/20250807174134_add_session/migration.sql`	Removed SQLite-specific Session table migration
`prisma/migrations/20250807161730_init/migration.sql`	Removed SQLite-specific User table migration
`prisma/migrations/migration_lock.toml`	Updated migration lock from sqlite to postgresql
`prisma/seed.js`	Added warning comment and introduced various case/format task status values for testing
`docker-compose.yml`	Added PostgreSQL service with healthcheck and configured app to depend on database
`docker-compose.dev.yml`	New development environment configuration with devcontainer and PostgreSQL services
`.devcontainer/docker-compose.yml`	New devcontainer Docker Compose configuration with PostgreSQL integration
`.devcontainer/devcontainer.json`	Updated to use Docker Compose with PostgreSQL support and added Prisma extension
`.devcontainer/Dockerfile`	Replaced SQLite dependencies with postgresql-client
`Dockerfile`	Removed SQLite installation, added Prisma client generation and migration deployment
`package.json`	Added test:e2e:debug script and db:migrate command, updated db:setup to use migrations
`app/(dashboard)/board/page.tsx`	Added extensive debug logging and status normalization logic for Kanban columns
`app/(dashboard)/tasks/actions.ts`	Added debug logging to getAllTasks and modified updateTaskStatus structure
`tests/e2e/tasks.spec.ts`	Added test assertion to verify priority field persistence after edit
`tests/e2e/console-log-proxy.js`	New Playwright bootstrap script to pipe browser console logs to terminal
`scripts/test-e2e-with-server.js`	New orchestration script for running E2E tests with automatic dev server management
`.env`	Added environment file with PostgreSQL DATABASE_URL (tracked in git for demo)
`.gitignore`	Commented out .env exclusion and added SQLite database file patterns
`.vscode/mcp.json`	Added PostgreSQL MCP server configuration for GitHub Copilot integration
`POSTGRESQL_SETUP.md`	Comprehensive documentation for PostgreSQL setup, commands, and troubleshooting
`BUG_REPORT.md`	Documented Kanban board task visibility bug with reproduction steps
`.github/prompts/debug-with-logs.prompt.md`	Added debugging workflow guide for investigating reported bugs

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review for a chance to win a $100 gift card. Take the survey.

Copilot · 2025-11-28T17:00:52Z

app/(dashboard)/tasks/actions.ts

+        const updateData: { status: string; priority?: string } = { status };
+
+        await prisma.task.update({ where: { id: taskId }, data: updateData });


The variable updateData is declared but the priority property is never assigned. This suggests incomplete code or dead code. Either remove the unused priority?: string type annotation and simplify to await prisma.task.update({ where: { id: taskId }, data: { status } });, or implement the intended priority update logic.

Suggested change

const updateData: { status: string; priority?: string } = { status };

await prisma.task.update({ where: { id: taskId }, data: updateData });

await prisma.task.update({ where: { id: taskId }, data: { status } });

Copilot · 2025-11-28T17:00:53Z

prisma/migrations/20251126214802_init/migration.sql

+CREATE TABLE "public"."User" (
+    "id" SERIAL NOT NULL,
+    "email" TEXT NOT NULL,
+    "password" TEXT NOT NULL,
+    "name" TEXT NOT NULL,
+
+    CONSTRAINT "User_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "public"."Session" (
+    "id" SERIAL NOT NULL,
+    "token" TEXT NOT NULL,
+    "userId" INTEGER NOT NULL,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+
+    CONSTRAINT "Session_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateTable
+CREATE TABLE "public"."Task" (
+    "id" SERIAL NOT NULL,
+    "name" TEXT NOT NULL,
+    "description" TEXT NOT NULL,
+    "priority" TEXT NOT NULL,
+    "status" TEXT NOT NULL,
+    "dueDate" TIMESTAMP(3),
+    "assigneeId" INTEGER,
+    "creatorId" INTEGER NOT NULL,
+    "createdAt" TIMESTAMP(3) NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    "updatedAt" TIMESTAMP(3) NOT NULL,
+
+    CONSTRAINT "Task_pkey" PRIMARY KEY ("id")
+);
+
+-- CreateIndex
+CREATE UNIQUE INDEX "User_email_key" ON "public"."User"("email");
+
+-- CreateIndex
+CREATE UNIQUE INDEX "Session_token_key" ON "public"."Session"("token");
+
+-- AddForeignKey
+ALTER TABLE "public"."Session" ADD CONSTRAINT "Session_userId_fkey" FOREIGN KEY ("userId") REFERENCES "public"."User"("id") ON DELETE RESTRICT ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "public"."Task" ADD CONSTRAINT "Task_assigneeId_fkey" FOREIGN KEY ("assigneeId") REFERENCES "public"."User"("id") ON DELETE SET NULL ON UPDATE CASCADE;
+
+-- AddForeignKey
+ALTER TABLE "public"."Task" ADD CONSTRAINT "Task_creatorId_fkey" FOREIGN KEY ("creatorId") REFERENCES "public"."User"("id") ON DELETE RESTRICT ON UPDATE CASCADE;


The explicit "public" schema prefix in table names is unnecessary and non-standard for PostgreSQL migrations. By default, PostgreSQL uses the public schema, and Prisma migrations typically don't include the schema prefix unless working with multiple schemas. This should be simplified to CREATE TABLE "User" instead of CREATE TABLE "public"."User" (and similarly for other tables and indexes) for consistency with standard Prisma migration patterns.

Copilot · 2025-11-28T17:00:53Z

docker-compose.yml

+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    healthcheck:
+      test: [ "CMD-SHELL", "pg_isready -U taskflow" ]


[nitpick] The healthcheck test command uses YAML flow sequence syntax with spaces after brackets ([ "CMD-SHELL", ... ]). While this is valid YAML, it's inconsistent with the same healthcheck definition in .devcontainer/docker-compose.yml which uses the same syntax. For better consistency and to avoid potential parsing issues with some YAML parsers, consider using the standard array format without spaces: ["CMD-SHELL", "pg_isready -U taskflow"].

Suggested change

test: [ "CMD-SHELL", "pg_isready -U taskflow" ]

test: ["CMD-SHELL", "pg_isready -U taskflow"]

Copilot · 2025-11-28T17:00:53Z

app/(dashboard)/board/page.tsx


+    let matchedCount = 0;
+    let unmatchedCount = 0;
+    const unmatchedTasks: any[] = [];


Using any[] type defeats the purpose of TypeScript's type safety. Define a proper type for unmatched tasks, such as { id: number; name: string; status: string; normalized: string | undefined }[] to maintain type safety and provide better IDE support.

Copilot · 2025-11-28T17:00:54Z

BUG_REPORT.md

+
+## IMPORTANT Considerations
+
+- Any modifications to data in the database must use the PostgreSQL MCP server. 


The sentence is incomplete and ends abruptly. Complete the sentence to provide clear guidance on using the PostgreSQL MCP server.

Suggested change

- Any modifications to data in the database must use the PostgreSQL MCP server.

- Any modifications to data in the database must use the PostgreSQL MCP server. Please use the official MCP management interface or the provided SQL scripts as documented in [MCP Server Guide](https://company-internal-docs/mcp-server-guide) to ensure data consistency and audit compliance.

Copilot · 2025-11-28T17:00:54Z

prisma/seed.js

+    'todo', 'Todo', 'TODO',
+    'in_progress', 'In Progress', 'IN PROGRESS',
+    'done', 'Done', 'DONE',
+    'review', 'Review', 'REVIEW'


The seed script is creating tasks with inconsistent status values (e.g., 'todo', 'Todo', 'TODO', 'in_progress', 'In Progress', 'IN PROGRESS'). This will cause issues because the Kanban board expects normalized lowercase with underscores status values ('todo', 'in_progress', 'review', 'done'). While the board page now includes normalization logic to handle this, seeding with inconsistent data is a bad practice that could lead to bugs and makes testing unreliable. The statuses array should only contain valid normalized values: ['todo', 'in_progress', 'done', 'review'].

Suggested change

'todo', 'Todo', 'TODO',

'in_progress', 'In Progress', 'IN PROGRESS',

'done', 'Done', 'DONE',

'review', 'Review', 'REVIEW'

'todo',

'in_progress',

'done',

'review'

Copilot · 2025-11-28T17:00:55Z

.env

+# THIS FILE WILL NOT BE IGNORED BY GIT, USE FOR DEMO PURPOSES ONLY
+# You can store environment variables here for local development
+# IMPORTANT: DO NOT STORE SENSITIVE INFORMATION IN THIS FILE!!
+
+# Database Configuration
+DATABASE_URL="postgresql://taskflow:taskflow@localhost:5432/taskflow"


The .env file should not be committed to version control as it can contain sensitive information. While the comment at the top indicates this is for demo purposes only, the .gitignore changes show .env* files are now being tracked (lines 33-35 are commented out). This is a security risk. Even for demo purposes, use .env.example for sample configurations and keep .env in .gitignore.

Suggested change

# THIS FILE WILL NOT BE IGNORED BY GIT, USE FOR DEMO PURPOSES ONLY

# You can store environment variables here for local development

# IMPORTANT: DO NOT STORE SENSITIVE INFORMATION IN THIS FILE!!

# Database Configuration

DATABASE_URL="postgresql://taskflow:taskflow@localhost:5432/taskflow"

# .env.example

# Copy this file to .env and fill in your actual secrets for local development.

# IMPORTANT: DO NOT COMMIT YOUR REAL .env FILE TO VERSION CONTROL!

# Database Configuration

DATABASE_URL="postgresql://USER:PASSWORD@localhost:5432/DATABASE"

Copilot · 2025-11-28T17:00:55Z

scripts/test-e2e-with-server.js

+        setTimeout(() => {
+            if (devServer && !devServer.killed) {
+                devServer.kill('SIGKILL');
+            }
+        }, 5000);


The cleanup function's setTimeout creates a timer that may not be cleared when the process exits, potentially causing the script to hang. The timer keeps the event loop alive, which prevents the process from exiting cleanly. Use setTimeout(...).unref() to allow the process to exit even if the timer hasn't fired, or clear the timer when cleanup completes.

Suggested change

setTimeout(() => {

if (devServer && !devServer.killed) {

devServer.kill('SIGKILL');

}

}, 5000);

const forceKillTimer = setTimeout(() => {

if (devServer && !devServer.killed) {

devServer.kill('SIGKILL');

}

}, 5000);

forceKillTimer.unref();

Copilot · 2025-11-28T17:00:55Z

tests/e2e/console-log-proxy.js

+ * This file patches the @playwright/test module to automatically attach
+ * console and error listeners to all pages during test execution.
+ * 
+ * Load this via NODE_OPTIONS: NODE_OPTIONS='--require ./tests/playwright-bootstrap.js'


The file path referenced in this comment is incorrect. The actual file path is ./tests/e2e/console-log-proxy.js, not ./tests/playwright-bootstrap.js.

Suggested change

* Load this via NODE_OPTIONS: NODE_OPTIONS='--require ./tests/playwright-bootstrap.js'

* Load this via NODE_OPTIONS: NODE_OPTIONS='--require ./tests/e2e/console-log-proxy.js'

Copilot · 2025-11-28T17:00:56Z

app/(dashboard)/board/page.tsx

+    console.log("[board/page.tsx - BoardPage] Fetching tasks for board view");
    const { tasks, error } = await getAllTasks()

    if (error) {
-        console.error("Error fetching tasks:", error)
+        console.error("[board/page.tsx - BoardPage] Error fetching tasks:", error)
        return <p className="p-8">Could not load data. Please try again later.</p>
    }

+    console.log(`[board/page.tsx - BoardPage] Received ${tasks?.length || 0} tasks from getAllTasks`);
+
    const initialColumns: KanbanData = {
        todo: { id: "todo", title: "To Do", tasks: [] },
        in_progress: { id: "in_progress", title: "In Progress", tasks: [] },
        review: { id: "review", title: "Review", tasks: [] },
        done: { id: "done", title: "Done", tasks: [] },
    }

+    let matchedCount = 0;
+    let unmatchedCount = 0;
+    const unmatchedTasks: any[] = [];
+
    tasks?.forEach((task) => {
-        // Ensure task status is a valid key for initialColumns
-        if (task.status && task.status in initialColumns) {
-            initialColumns[task.status as keyof KanbanData].tasks.push(task)
+        // Normalize the status to lowercase and replace spaces with underscores
+        const normalizedStatus = task.status?.toLowerCase().replace(/\s+/g, '_');
+        console.log(`[board/page.tsx - BoardPage] Processing task ${task.id}: name="${task.name}", status="${task.status}", normalized="${normalizedStatus}", status in columns: ${normalizedStatus in initialColumns}`);
+        // Ensure task status is a valid key for initialColumns after normalization
+        if (normalizedStatus && normalizedStatus in initialColumns) {
+            initialColumns[normalizedStatus as keyof KanbanData].tasks.push(task)
+            matchedCount++;
+        } else {
+            unmatchedCount++;
+            unmatchedTasks.push({ id: task.id, name: task.name, status: task.status, normalized: normalizedStatus });
        }
    })

+    console.log(`[board/page.tsx - BoardPage] Task distribution summary:`);
+    console.log(`  - Matched tasks: ${matchedCount}`);
+    console.log(`  - Unmatched tasks: ${unmatchedCount}`);
+    if (unmatchedTasks.length > 0) {
+        console.log(`  - Unmatched task details:`, unmatchedTasks);
+    }
+    console.log(`  - Column counts:`, {
+        todo: initialColumns.todo.tasks.length,
+        in_progress: initialColumns.in_progress.tasks.length,
+        review: initialColumns.review.tasks.length,
+        done: initialColumns.done.tasks.length,
+    });


These extensive debug logging statements should be removed from production code. Server-side rendering code runs on every request, and these console.log statements will clutter server logs significantly. Consider using a proper logging library with configurable log levels, or remove these logs after debugging is complete.

mikedane-bitovi added 10 commits November 26, 2025 15:45

added debug script

8f43dc9

added combined logging and orchestration

bb0a185

added bug and report

a1ddfa2

added better test running for debugging

2ee8c31

using postgresql

362fd83

added postgres mcp

94e6a73

added buggy data

315a79a

added database step to debug prompt

d3a380c

updated seed file

c8d5250

added env to commit for demo purposes only

3c0329c

Copilot AI review requested due to automatic review settings November 28, 2025 16:56

Copilot started reviewing on behalf of mikedane-bitovi November 28, 2025 16:56 View session

Copilot finished reviewing on behalf of mikedane-bitovi November 28, 2025 16:59

Copilot AI reviewed Nov 28, 2025

View reviewed changes

mikedane-bitovi added 3 commits December 1, 2025 10:08

added copilot instructions

7394b02

removed debug logs

96fd16c

pinned prisma version

c623078

mikedane-bitovi closed this Dec 11, 2025

mikedane-bitovi deleted the debug-3 branch December 11, 2025 19:22

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

PostgreSQL Enabled TaskFlow #261

PostgreSQL Enabled TaskFlow #261

Uh oh!

mikedane-bitovi commented Nov 28, 2025

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Copilot AI Nov 28, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		const updateData: { status: string; priority?: string } = { status };

		await prisma.task.update({ where: { id: taskId }, data: updateData });

	test: [ "CMD-SHELL", "pg_isready -U taskflow" ]
	test: ["CMD-SHELL", "pg_isready -U taskflow"]


		## IMPORTANT Considerations

		- Any modifications to data in the database must use the PostgreSQL MCP server. No newline at end of file

	* Load this via NODE_OPTIONS: NODE_OPTIONS='--require ./tests/playwright-bootstrap.js'
	* Load this via NODE_OPTIONS: NODE_OPTIONS='--require ./tests/e2e/console-log-proxy.js'

PostgreSQL Enabled TaskFlow #261

PostgreSQL Enabled TaskFlow #261

Uh oh!

Conversation

mikedane-bitovi commented Nov 28, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 28, 2025

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants