Merge branch 'main' into dev

Fix IMAP sync marking all emails as synced before fetching

.env.example

@@ -1,26 +1,44 @@
-# Application
+
+# --- Application Settings ---
+# Set to 'production' for production environments
 NODE_ENV=development
 PORT_BACKEND=4000
 PORT_FRONTEND=3000
+# The frequency of continuous email syncing. Default is every minutes, but you can change it to another value based on your needs.
+SYNC_FREQUENCY='* * * * *' 
 
+# --- Docker Compose Service Configuration ---
+# These variables are used by docker-compose.yml to configure the services. Leave them unchanged if you use Docker services for Postgresql, Valkey (Redis) and Meilisearch. If you decide to use your own instances of these services, you can substitute them with your own connection credentials.
 
 # PostgreSQL
-DATABASE_URL="postgresql://admin:password@postgres:5432/open_archive?schema=public"
-
-# Redis
-REDIS_HOST=redis
-REDIS_PORT=6379
+POSTGRES_DB=open_archive
+POSTGRES_USER=admin
+POSTGRES_PASSWORD=password
+DATABASE_URL="postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}"
 
 # Meilisearch
 MEILI_MASTER_KEY=aSampleMasterKey
 MEILI_HOST=http://meilisearch:7700
 
-# Storage
+
+
+# Redis (We use Valkey, which is Redis-compatible and open source)
+REDIS_HOST=valkey
+REDIS_PORT=6379
+REDIS_PASSWORD=defaultredispassword
+# If you run Valkey service from Docker Compose, set the REDIS_TLS_ENABLED variable to false.
+REDIS_TLS_ENABLED=false
+
+
+# --- Storage Settings ---
 # Choose your storage backend. Valid options are 'local' or 's3'.
 STORAGE_TYPE=local
+# The maximum request body size to accept in bytes including while streaming. The body size can also be specified with a unit suffix for kilobytes (K), megabytes (M), or gigabytes (G). For example, 512K or 1M. Defaults to 512kb. Or the value of  Infinity if you don't want any upload limit.
+BODY_SIZE_LIMIT=100M
 
 # --- Local Storage Settings ---
-# The absolute path on the server where files will be stored.
+# The path inside the container where files will be stored.
+# This is mapped to a Docker volume for persistence.
 # This is only used if STORAGE_TYPE is 'local'.
 STORAGE_LOCAL_ROOT_PATH=/var/data/open-archiver
 
@@ -34,18 +52,19 @@ STORAGE_S3_REGION=
 # Set to 'true' for MinIO and other non-AWS S3 services
 STORAGE_S3_FORCE_PATH_STYLE=false
 
+# --- Security & Authentication ---
+
 # JWT
-JWT_SECRET="a-very-secret-key"
+# IMPORTANT: Change this to a long, random, and secret string in your .env file
+JWT_SECRET=a-very-secret-key-that-you-should-change
 JWT_EXPIRES_IN="7d"
 
-
-
-# Admin users
-ADMIN_EMAIL=admin@local.com 
-ADMIN_PASSWORD=a_strong_pass
+# Set the credentials for the initial admin user.
 SUPER_API_KEY=
 
-# Master Encryption Key for sensitive data
+# Master Encryption Key for sensitive data (Such as Ingestion source credentials and passwords)
 # IMPORTANT: Generate a secure, random 32-byte hex string for this
-# Use `openssl rand -hex 32` to generate a key
+# You can use `openssl rand -hex 32` to generate a key.
 ENCRYPTION_KEY=
+
+

.github/CLA.md

@@ -0,0 +1,25 @@
+# Contributor License Agreement (CLA)
+
+This license is for your protection as a Contributor as well as the protection of the maintainers of the Open Archiver software; it does not change your rights to use your own Contributions for any other purpose. In the following, the maintainers of Open Archiver are referred to as "Open Archiver".
+
+You accept and agree to the following terms and conditions for Your present and future Contributions submitted to "Open Archiver". Except for the license granted herein to Open Archiver and recipients of software distributed by "Open Archiver", You reserve all right, title, and interest in and to Your Contributions.
+
+1. Definitions.
+
+    "You" (or "Your") shall mean the copyright owner or legal entity authorized by the copyright owner that is making this Agreement with "Open Archiver". For legal entities, the entity making a Contribution and all other entities that control, are controlled by, or are under common control with that entity are considered to be a single Contributor.
+
+    "Contribution" shall mean any original work of authorship, including any modifications or additions to an existing work, that is intentionally submitted by You to "Open Archiver" for inclusion in, or documentation of, any of the products owned or managed by "Open Archiver" (the "Work"). For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to "Open Archiver" or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, "Open Archiver" for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by You as "Not a Contribution."
+
+2. Grant of Copyright License. Subject to the terms and conditions of this Agreement, You grant to "Open Archiver" and to recipients of software distributed by "Open Archiver" a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute Your Contributions and such derivative works.
+
+3. Grant of Patent License. Subject to the terms and conditions of this Agreement, You grant to "Open Archiver" and to recipients of software distributed by "Open Archiver" a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by You that are necessarily infringed by Your Contribution(s) alone or by combination of Your Contribution(s) with the Work to which such Contribution(s) was submitted. If any entity institutes patent litigation against You or any other entity (including a cross-claim or counterclaim in a lawsuit) alleging that your Contribution, or the Work to which you have contributed, constitutes direct or contributory patent infringement, then any patent licenses granted to that entity under this Agreement for that Contribution or Work shall terminate as of the date such litigation is filed.
+
+4. You represent that you are legally entitled to grant the above license. If your employer(s) has rights to intellectual property that you create that includes your Contributions, you represent that you have received permission to make Contributions on behalf of that employer, that your employer has waived such rights for your Contributions to "Open Archiver", or that your employer has executed a separate Contributor License Agreement with "Open Archiver".
+
+5. You represent that each of Your Contributions is Your original creation (see section 7 for submissions on behalf of others). You represent that Your Contribution submissions include complete details of any third-party license or other restriction (including, but not limited to, related patents and trademarks) of which you are personally aware and which are associated with any part of Your Contributions.
+
+6. You are not expected to provide support for Your Contributions, except to the extent You desire to provide support. Unless required by applicable law or agreed to in writing, You provide Your Contributions on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE.
+
+7. Should You wish to submit work that is not Your original creation, You may submit it to "Open Archiver" separately from any Contribution, identifying the complete details of its source and of any license or other restriction (including, but not limited to, related patents, trademarks, and license agreements) of which you are personally aware, and conspicuously marking the work as "Submitted on behalf of a third-party: [named here]".
+
+8. You agree to notify "Open Archiver" of any facts or circumstances of which you become aware that would make these representations inaccurate in any respect.

.github/workflows/cla.yml

@@ -0,0 +1,32 @@
+name: 'CLA Assistant'
+on:
+    issue_comment:
+        types: [created]
+    pull_request_target:
+        types: [opened, closed, synchronize]
+
+# explicitly configure permissions, in case your GITHUB_TOKEN workflow permissions are set to read-only in repository settings
+permissions:
+    actions: write
+    contents: write # this can be 'read' if the signatures are in remote repository
+    pull-requests: write
+    statuses: write
+
+jobs:
+    CLAAssistant:
+        runs-on: ubuntu-latest
+        steps:
+            - name: 'CLA Assistant'
+              if: (github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I hereby sign the CLA') || github.event_name == 'pull_request_target'
+              uses: contributor-assistant/github-action@v2.6.1
+              env:
+                  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+                  PERSONAL_ACCESS_TOKEN: ${{ secrets.PERSONAL_ACCESS_TOKEN }}
+              with:
+                  path-to-signatures: 'signatures/version1/cla.json'
+                  path-to-document: 'https://github.com/LogicLabs-OU/OpenArchiver/tree/main/.github/CLA.md'
+                  branch: 'main'
+                  allowlist: 'wayneshn'
+
+                  remote-organization-name: 'LogicLabs-OU'
+                  remote-repository-name: 'cla-db'

.github/workflows/deploy-docs.yml

@@ -0,0 +1,43 @@
+name: Deploy Docs to GitHub Pages
+
+on:
+    push:
+        branches:
+            - main
+        paths:
+            - 'docs/**'
+
+jobs:
+    build-and-deploy:
+        runs-on: ubuntu-latest
+        permissions:
+            contents: write
+        steps:
+            - name: Checkout repository
+              uses: actions/checkout@v4
+
+            - name: Setup pnpm
+              uses: pnpm/action-setup@v2
+              with:
+                  version: 10.13.1
+
+            - name: Setup Node.js
+              uses: actions/setup-node@v4
+              with:
+                  node-version: '22'
+                  cache: 'pnpm'
+
+            - name: Install dependencies
+              run: pnpm install --frozen-lockfile
+
+            - name: Build documentation site
+              run: pnpm docs:build
+
+            - name: Create CNAME file
+              run: echo "docs.openarchiver.com" > docs/.vitepress/dist/CNAME
+
+            - name: Deploy to GitHub Pages
+              uses: peaceiris/actions-gh-pages@v3
+              with:
+                  github_token: ${{ secrets.GITHUB_TOKEN }}
+                  publish_dir: docs/.vitepress/dist

.github/workflows/docker-deployment.yml

@@ -0,0 +1,41 @@
+name: docker-deployment
+
+on:
+    push:
+        branches:
+            - main
+        paths-ignore:
+            - '**.md'
+            - 'docs/**'
+
+jobs:
+    docker:
+        runs-on: ubuntu-latest
+        steps:
+            - name: Checkout
+              uses: actions/checkout@v4
+
+            - name: Login to Docker Hub
+              uses: docker/login-action@v3
+              with:
+                  username: ${{ vars.DOCKERHUB_USERNAME }}
+                  password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+            - name: Set up QEMU
+              uses: docker/setup-qemu-action@v3
+
+            - name: Set up Docker Buildx
+              uses: docker/setup-buildx-action@v3
+
+            - name: Extract short SHA
+              id: sha
+              run: echo "sha=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+
+            - name: Build and push
+              uses: docker/build-push-action@v6
+              with:
+                  context: .
+                  file: ./docker/Dockerfile
+                  platforms: linux/amd64,linux/arm64
+                  push: true
+                  tags: logiclabshq/open-archiver:${{ steps.sha.outputs.sha }}

.gitignore

@@ -9,7 +9,6 @@ dist
 **/meili_data/
 
 # PNPM
-pnpm-lock.yaml
 pnpm-debug.log
 
 # IDE
@@ -21,3 +20,7 @@ pnpm-debug.log
 
 # Dev
 .dev
+
+# Vitepress
+docs/.vitepress/dist
+docs/.vitepress/cache

.prettierignore

@@ -0,0 +1,13 @@
+# Ignore artifacts
+dist
+.svelte-kit
+build
+node_modules
+pnpm-lock.yaml
+meili_data/
+
+## shadcn installs
+packages/frontend/src/lib/components/ui/
+
+# Ignore logs
+*.log

.prettierrc

@@ -1,12 +1,11 @@
 {
 	"useTabs": true,
 	"singleQuote": true,
-	"trailingComma": "none",
+	"trailingComma": "es5",
+	"semi": true,
+	"tabWidth": 4,
 	"printWidth": 100,
-	"plugins": [
-		"prettier-plugin-svelte",
-		"prettier-plugin-tailwindcss"
-	],
+	"plugins": ["prettier-plugin-svelte", "prettier-plugin-tailwindcss"],
 	"overrides": [
 		{
 			"files": "*.svelte",

CODE_OF_CONDUCT.md

@@ -16,24 +16,24 @@ We pledge to act and interact in ways that are welcoming, open, and respectful.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
--   Demonstrating empathy and kindness toward other people
--   Being respectful of differing opinions, viewpoints, and experiences
--   Giving and gracefully accepting constructive feedback
--   Accepting responsibility and apologizing to those affected by our mistakes,
-    and learning from the experience
--   Focusing on what is best not just for us as individuals, but for the
-    overall community
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the
+  overall community
 
 Examples of unacceptable behavior include:
 
--   The use of sexualized language or imagery, and sexual attention or
-    advances of any kind
--   Trolling, insulting or derogatory comments, and personal or political attacks
--   Public or private harassment
--   Publishing others' private information, such as a physical or email
-    address, without their explicit permission
--   Other conduct which could reasonably be considered inappropriate in a
-    professional setting
+- The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
 ## Enforcement Responsibilities
 

CONTRIBUTING.md

@@ -6,8 +6,8 @@ First off, thank you for considering contributing to Open Archiver! It's people
 
 Not sure where to start? You can:
 
--   Look through the [open issues](https://github.com/LogicLabs-OU/OpenArchiver/issues) for bugs or feature requests.
--   Check the issues labeled `good first issue` for tasks that are a good entry point into the codebase.
+- Look through the [open issues](https://github.com/LogicLabs-OU/OpenArchiver/issues) for bugs or feature requests.
+- Check the issues labeled `good first issue` for tasks that are a good entry point into the codebase.
 
 ## How to Contribute
 
@@ -29,6 +29,10 @@ If you have an idea for an enhancement, please open an issue to discuss it. This
 6.  **Update the documentation** if your changes require it.
 7.  **Submit a pull request** to the `main` branch of the main repository. Please provide a clear description of the problem and solution. Include the relevant issue number if applicable.
 
+## Contributor License Agreement
+
+By submitting a pull request to this repository, you agree to the terms and conditions of our [Contributor License Agreement](./.github/CLA.md)
+
 ## Code of Conduct
 
 This project and everyone participating in it is governed by the [Open Archiver Code of Conduct](CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please report unacceptable behavior.
@@ -37,13 +41,23 @@ This project and everyone participating in it is governed by the [Open Archiver
 
 ### Git Commit Messages
 
--   Use the present tense ("Add feature" not "Added feature").
--   Use the imperative mood ("Move cursor to..." not "Moves cursor to...").
--   Limit the first line to 72 characters or less.
--   Reference issues and pull requests liberally after the first line.
+- Use the present tense ("Add feature" not "Added feature").
+- Use the imperative mood ("Move cursor to..." not "Moves cursor to...").
+- Limit the first line to 72 characters or less.
+- Reference issues and pull requests liberally after the first line.
 
 ### TypeScript Styleguide
 
--   Follow the existing code style.
--   Use TypeScript's strict mode.
--   Avoid using `any` as a type. Define clear interfaces and types in the `packages/types` directory.
+- Follow the existing code style.
+- Use TypeScript's strict mode.
+- Avoid using `any` as a type. Define clear interfaces and types in the `packages/types` directory.
+
+### Formatting
+
+We use Prettier for code formatting. Before you commit new code, it is necessary to check code format by running this command from the root folder:
+
+`pnpm run lint`
+
+If there are any format issues, you can use the following command to fix them
+
+`pnpm run format`

README.md

@@ -1,45 +1,76 @@
 # Open Archiver
 
-> [!WARNING]
-> This project is currently in active development and has not yet reached a stable General Availability (GA) release. It is not recommended for use in production environments. We welcome contributions from the community to help us accelerate development and improve the platform. Please see our [Contributing](#contributing) section for more details.
+[![Docker Compose](https://img.shields.io/badge/Docker%20Compose-2496ED?style=for-the-badge&logo=docker&logoColor=white)](https://www.docker.com)
+[![PostgreSQL](https://img.shields.io/badge/PostgreSQL-4169E1?style=for-the-badge&logo=postgresql&logoColor=white)](https://www.postgresql.org/)
+[![Meilisearch](https://img.shields.io/badge/Meilisearch-FF5A5F?style=for-the-badge&logo=meilisearch&logoColor=white)](https://www.meilisearch.com/)
+[![TypeScript](https://img.shields.io/badge/TypeScript-3178C6?style=for-the-badge&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
+[![Redis](https://img.shields.io/badge/Redis-DC382D?style=for-the-badge&logo=redis&logoColor=white)](https://redis.io)
+[![SvelteKit](https://img.shields.io/badge/SvelteKit-FF3E00?style=for-the-badge&logo=svelte&logoColor=white)](https://svelte.dev/)
 
-**A secure, sovereign, and affordable open-source platform for email archiving and eDiscovery.**
+**A secure, sovereign, and open-source platform for email archiving and eDiscovery.**
 
-Open Archiver enables individuals and organizations to take control of their digital communication history. It provides a robust, self-hosted solution for ingesting, storing, indexing, and searching emails from major platforms, ensuring a permanent, tamper-proof record of your most critical data, free from vendor lock-in.
+Open Archiver provides a robust, self-hosted solution for archiving, storing, indexing, and searching emails from major platforms, including Google Workspace (Gmail), Microsoft 365, PST files, as well as generic IMAP-enabled email inboxes. Use Open Archiver to keep a permanent, tamper-proof record of your communication history, free from vendor lock-in.
 
-![Open Archiver Preview](assets/screenshots/email.png)
+## 📸 Screenshots
 
-## Vision
+![Open Archiver Preview](assets/screenshots/dashboard-1.png)
+_Dashboard_
 
-To provide individuals and organizations with a secure, sovereign, and affordable platform to preserve and access their digital communication history.
+![Open Archiver Preview](assets/screenshots/archived-emails.png)
+_Archived emails_
 
-## Key Features
+![Open Archiver Preview](assets/screenshots/search.png)
+_Full-text search across all your emails and attachments_
 
--   **Universal Ingestion**: Connect to Google Workspace, Microsoft 365, and standard IMAP servers to perform initial bulk imports and maintain continuous, real-time synchronization.
--   **Secure & Efficient Storage**: Emails are stored in the standard `.eml` format. The system uses deduplication and compression to minimize storage costs. All data is encrypted at rest.
--   **Pluggable Storage Backends**: Start with local filesystem storage and scale to S3-compatible object storage (like AWS S3 or MinIO) as your needs grow.
--   **Powerful Search & eDiscovery**: A high-performance search engine indexes the full text of emails and attachments (PDF, DOCX, etc.). The intuitive UI supports advanced search operators, filtering, and case management.
--   **Compliance & Retention**: Define granular retention policies to automatically manage the lifecycle of your data. Place legal holds on communications to prevent deletion during litigation.
--   **Comprehensive Auditing**: An immutable audit trail logs all system activities, ensuring you have a clear record of who accessed what and when.
--   **Role-Based Access Control (RBAC)**: Enforce the principle of least privilege with pre-defined roles for Administrators, Auditors, and End Users.
+## 👨‍👩‍👧‍👦 Join our community!
 
-## Tech Stack
+We are committed to build an engaging community around Open Archiver, and we are inviting all of you to join our community on Discord to get real-time support and connect with the team.
+
+[![Discord](https://img.shields.io/badge/Join%20our%20Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/MTtD7BhuTQ)
+
+[![Bluesky](https://img.shields.io/badge/Follow%20us%20on%20Bluesky-0265D4?style=for-the-badge&logo=bluesky&logoColor=white)](https://bsky.app/profile/openarchiver.bsky.social)
+
+## 🚀 Live demo
+
+Check out the live demo here: https://demo.openarchiver.com
+
+Username: admin@local.com
+
+Password: openarchiver_demo
+
+## ✨ Key Features
+
+- **Universal Ingestion**: Connect to any email provider to perform initial bulk imports and maintain continuous, real-time synchronization. Ingestion sources include:
+    - IMAP connection
+    - Google Workspace
+    - Microsoft 365
+    - PST files
+    - Zipped .eml files
+
+- **Secure & Efficient Storage**: Emails are stored in the standard `.eml` format. The system uses deduplication and compression to minimize storage costs. All data is encrypted at rest.
+- **Pluggable Storage Backends**: Support both local filesystem storage and S3-compatible object storage (like AWS S3 or MinIO).
+- **Powerful Search & eDiscovery**: A high-performance search engine indexes the full text of emails and attachments (PDF, DOCX, etc.).
+- **Thread discovery**: The ability to discover if an email belongs to a thread/conversation and present the context.
+- **Compliance & Retention**: Define granular retention policies to automatically manage the lifecycle of your data. Place legal holds on communications to prevent deletion during litigation (TBD).
+- **Comprehensive Auditing**: An immutable audit trail logs all system activities, ensuring you have a clear record of who accessed what and when (TBD).
+
+## 🛠️ Tech Stack
 
 Open Archiver is built on a modern, scalable, and maintainable technology stack:
 
--   **Frontend**: SvelteKit with Svelte 5
--   **Backend**: Node.js with Express.js & TypeScript
--   **Job Queue**: BullMQ on Redis for robust, asynchronous processing
--   **Search Engine**: Meilisearch for blazingly fast and resource-efficient search
--   **Database**: PostgreSQL for metadata, user management, and audit logs
--   **Deployment**: Docker Compose for easy, one-command deployment
+- **Frontend**: SvelteKit with Svelte 5
+- **Backend**: Node.js with Express.js & TypeScript
+- **Job Queue**: BullMQ on Redis for robust, asynchronous processing. (We use Valkey as the Redis service in the Docker Compose deployment mode, but you can use Redis as well.)
+- **Search Engine**: Meilisearch for blazingly fast and resource-efficient search
+- **Database**: PostgreSQL for metadata, user management, and audit logs
+- **Deployment**: Docker Compose deployment
 
-## Getting Started
+## 📦 Deployment
 
 ### Prerequisites
 
--   [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/)
--   A server or local machine with at least 2GB of RAM.
+- [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/)
+- A server or local machine with at least 4GB of RAM (2GB of RAM if you use external Postgres, Redis (Valkey) and Meilisearch instances).
 
 ### Installation
 
@@ -57,7 +88,7 @@ Open Archiver is built on a modern, scalable, and maintainable technology stack:
     cp .env.example .env
     ```
 
-    You will need to edit the `.env` file to set your database passwords, secret keys, and other essential configuration.
+    You will need to edit the `.env` file to set your admin passwords, secret keys, and other essential configuration. Read the .env.example for how to set up.
 
 3.  **Run the application:**
 
@@ -65,21 +96,29 @@ Open Archiver is built on a modern, scalable, and maintainable technology stack:
     docker compose up -d
     ```
 
-    This command will build the necessary Docker images and start all the services (frontend, backend, database, etc.) in the background.
+    This command will pull the pre-built Docker images and start all the services (frontend, backend, database, etc.) in the background.
 
 4.  **Access the application:**
     Once the services are running, you can access the Open Archiver web interface by navigating to `http://localhost:3000` in your web browser.
 
-## Contributing
+## ⚙️ Data Source Configuration
 
-We welcome contributions from the community! Whether you're a developer, a designer, or just an enthusiast, there are many ways to get involved.
+After deploying the application, you will need to configure one or more ingestion sources to begin archiving emails. Follow our detailed guides to connect to your email provider:
 
--   **Reporting Bugs**: If you find a bug, please open an issue on our GitHub repository.
--   **Suggesting Enhancements**: Have an idea for a new feature? We'd love to hear it. Open an issue to start the discussion.
--   **Code Contributions**: If you'd like to contribute code, please fork the repository and submit a pull request.
+- [Connecting to Google Workspace](https://docs.openarchiver.com/user-guides/email-providers/google-workspace.html)
+- [Connecting to Microsoft 365](https://docs.openarchiver.com/user-guides/email-providers/imap.html)
+- [Connecting to a Generic IMAP Server](https://docs.openarchiver.com/user-guides/email-providers/imap.html)
+
+## 🤝 Contributing
+
+We welcome contributions from the community!
+
+- **Reporting Bugs**: If you find a bug, please open an issue on our GitHub repository.
+- **Suggesting Enhancements**: Have an idea for a new feature? We'd love to hear it. Open an issue to start the discussion.
+- **Code Contributions**: If you'd like to contribute code, please fork the repository and submit a pull request.
 
 Please read our `CONTRIBUTING.md` file for more details on our code of conduct and the process for submitting pull requests.
 
-## License
+## 📈 Star History
 
-This project is licensed under the AGPL-3.0 License.
+[![Star History Chart](https://api.star-history.com/svg?repos=LogicLabs-OU/OpenArchiver&type=Date)](https://www.star-history.com/#LogicLabs-OU/OpenArchiver&Date)

docker-compose.yml

@@ -0,0 +1,74 @@
+version: '3.8'
+
+services:
+    open-archiver:
+        image: logiclabshq/open-archiver:latest
+        container_name: open-archiver
+        restart: unless-stopped
+        ports:
+            - '4000:4000' # Backend
+            - '3000:3000' # Frontend
+        env_file:
+            - .env
+        volumes:
+            - archiver-data:/var/data/open-archiver
+        depends_on:
+            - postgres
+            - valkey
+            - meilisearch
+        networks:
+            - open-archiver-net
+
+    postgres:
+        image: postgres:17-alpine
+        container_name: postgres
+        restart: unless-stopped
+        environment:
+            POSTGRES_DB: ${POSTGRES_DB:-open_archive}
+            POSTGRES_USER: ${POSTGRES_USER:-admin}
+            POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-password}
+        volumes:
+            - pgdata:/var/lib/postgresql/data
+        ports:
+            - '5432:5432'
+        networks:
+            - open-archiver-net
+
+    valkey:
+        image: valkey/valkey:8-alpine
+        container_name: valkey
+        restart: unless-stopped
+        command: valkey-server --requirepass ${REDIS_PASSWORD}
+        ports:
+            - '6379:6379'
+        volumes:
+            - valkeydata:/data
+        networks:
+            - open-archiver-net
+
+    meilisearch:
+        image: getmeili/meilisearch:v1.15
+        container_name: meilisearch
+        restart: unless-stopped
+        environment:
+            MEILI_MASTER_KEY: ${MEILI_MASTER_KEY:-aSampleMasterKey}
+        ports:
+            - '7700:7700'
+        volumes:
+            - meilidata:/meili_data
+        networks:
+            - open-archiver-net
+
+volumes:
+    pgdata:
+        driver: local
+    valkeydata:
+        driver: local
+    meilidata:
+        driver: local
+    archiver-data:
+        driver: local
+
+networks:
+    open-archiver-net:
+        driver: bridge

docker/Dockerfile

@@ -12,14 +12,15 @@ COPY package.json pnpm-workspace.yaml pnpm-lock.yaml* ./
 COPY packages/backend/package.json ./packages/backend/
 COPY packages/frontend/package.json ./packages/frontend/
 COPY packages/types/package.json ./packages/types/
+COPY packages/frontend/svelte.config.js ./packages/frontend/
 
-# Install all dependencies 
-RUN pnpm install --frozen-lockfile --prod=false
+# Install all dependencies. Use --shamefully-hoist to create a flat node_modules structure
+RUN pnpm install --shamefully-hoist --frozen-lockfile --prod=false
 
 # Copy the rest of the source code
 COPY . .
 
-# Build all packages
+# Build all packages.
 RUN pnpm build
 
 # 2. Production Stage: Install only production dependencies and copy built artifacts
@@ -35,8 +36,8 @@ COPY packages/backend/package.json ./packages/backend/
 COPY packages/frontend/package.json ./packages/frontend/
 COPY packages/types/package.json ./packages/types/
 
-# Install only production dependencies
-RUN pnpm install --frozen-lockfile --prod
+# Install production dependencies
+# RUN pnpm install --shamefully-hoist --frozen-lockfile --prod=true
 
 # Copy built application from build stage
 COPY --from=build /app/packages/backend/dist ./packages/backend/dist
@@ -45,9 +46,16 @@ COPY --from=build /app/packages/types/dist ./packages/types/dist
 COPY --from=build /app/packages/backend/drizzle.config.ts ./packages/backend/drizzle.config.ts
 COPY --from=build /app/packages/backend/src/database/migrations ./packages/backend/src/database/migrations
 
+# Copy the entrypoint script and make it executable
+COPY docker/docker-entrypoint.sh /usr/local/bin/
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
 # Expose the port the app runs on
 EXPOSE 4000
 EXPOSE 3000
 
+# Set the entrypoint
+ENTRYPOINT ["docker-entrypoint.sh"]
+
 # Start the application
 CMD ["pnpm", "docker-start"]

docker/docker-entrypoint.sh

@@ -0,0 +1,17 @@
+#!/bin/sh
+
+# Exit immediately if a command exits with a non-zero status
+set -e
+
+# Run pnpm install to ensure all dependencies, including native addons,
+# are built for the container's architecture. This is crucial for
+# multi-platform Docker images, as it prevents "exec format error"
+# when running on a different architecture than the one used for building.
+pnpm install --frozen-lockfile --prod
+
+# Run database migrations before starting the application to prevent
+# race conditions where the app starts before the database is ready.
+pnpm db:migrate
+
+# Execute the main container command
+exec "$@"

docs/.vitepress/config.mts

@@ -0,0 +1,80 @@
+import { defineConfig } from 'vitepress';
+
+export default defineConfig({
+	head: [
+		[
+			'script',
+			{
+				defer: '',
+				src: 'https://analytics.zenceipt.com/script.js',
+				'data-website-id': '2c8b452e-eab5-4f82-8ead-902d8f8b976f',
+			},
+		],
+	],
+	title: 'Open Archiver',
+	description: 'Official documentation for the Open Archiver project.',
+	themeConfig: {
+		search: {
+			provider: 'local',
+		},
+		logo: {
+			src: '/logo-sq.svg',
+		},
+		nav: [
+			{ text: 'Home', link: '/' },
+			{ text: 'Github', link: 'https://github.com/LogicLabs-OU/OpenArchiver' },
+			{ text: 'Website', link: 'https://openarchiver.com/' },
+			{ text: 'Discord', link: 'https://discord.gg/MTtD7BhuTQ' },
+		],
+		sidebar: [
+			{
+				text: 'User Guides',
+				items: [
+					{ text: 'Get Started', link: '/' },
+					{ text: 'Installation', link: '/user-guides/installation' },
+					{
+						text: 'Email Providers',
+						link: '/user-guides/email-providers/',
+						collapsed: true,
+						items: [
+							{
+								text: 'Generic IMAP Server',
+								link: '/user-guides/email-providers/imap',
+							},
+							{
+								text: 'Google Workspace',
+								link: '/user-guides/email-providers/google-workspace',
+							},
+							{
+								text: 'Microsoft 365',
+								link: '/user-guides/email-providers/microsoft-365',
+							},
+							{ text: 'EML Import', link: '/user-guides/email-providers/eml' },
+							{ text: 'PST Import', link: '/user-guides/email-providers/pst' },
+						],
+					},
+				],
+			},
+			{
+				text: 'API Reference',
+				items: [
+					{ text: 'Overview', link: '/api/' },
+					{ text: 'Authentication', link: '/api/authentication' },
+					{ text: 'Auth', link: '/api/auth' },
+					{ text: 'Archived Email', link: '/api/archived-email' },
+					{ text: 'Dashboard', link: '/api/dashboard' },
+					{ text: 'Ingestion', link: '/api/ingestion' },
+					{ text: 'Search', link: '/api/search' },
+					{ text: 'Storage', link: '/api/storage' },
+				],
+			},
+			{
+				text: 'Services',
+				items: [
+					{ text: 'Overview', link: '/services/' },
+					{ text: 'Storage Service', link: '/services/storage-service' },
+				],
+			},
+		],
+	},
+});

docs/SUMMARY.md

@@ -0,0 +1,17 @@
+# Table of contents
+
+## User guides
+
+- [Get started](index.md)
+- [Installation](user-guides/installation.md)
+- [email-providers](user-guides/email-providers/index.md)
+    - [Connecting to Google Workspace](user-guides/email-providers/google-workspace.md)
+    - [Connecting to a Generic IMAP Server](user-guides/email-providers/imap.md)
+    - [Connecting to Microsoft 365](user-guides/email-providers/microsoft-365.md)
+
+---
+
+- [api](api/index.md)
+    - [Ingestion Sources API Documentation](api/ingestion.md)
+- [services](services/index.md)
+    - [Pluggable Storage Service (StorageService)](services/storage-service.md)

docs/api/archived-email.md

@@ -0,0 +1,107 @@
+# Archived Email Service API
+
+The Archived Email Service is responsible for retrieving archived emails and their details from the database and storage.
+
+## Endpoints
+
+All endpoints in this service require authentication.
+
+### GET /api/v1/archived-emails/ingestion-source/:ingestionSourceId
+
+Retrieves a paginated list of archived emails for a specific ingestion source.
+
+**Access:** Authenticated
+
+#### URL Parameters
+
+| Parameter           | Type   | Description                                       |
+| :------------------ | :----- | :------------------------------------------------ |
+| `ingestionSourceId` | string | The ID of the ingestion source to get emails for. |
+
+#### Query Parameters
+
+| Parameter | Type   | Description                     | Default |
+| :-------- | :----- | :------------------------------ | :------ |
+| `page`    | number | The page number for pagination. | 1       |
+| `limit`   | number | The number of items per page.   | 10      |
+
+#### Responses
+
+- **200 OK:** A paginated list of archived emails.
+
+    ```json
+    {
+    	"items": [
+    		{
+    			"id": "email-id",
+    			"subject": "Test Email",
+    			"from": "sender@example.com",
+    			"sentAt": "2023-10-27T10:00:00.000Z",
+    			"hasAttachments": true,
+    			"recipients": [{ "name": "Recipient 1", "email": "recipient1@example.com" }]
+    		}
+    	],
+    	"total": 100,
+    	"page": 1,
+    	"limit": 10
+    }
+    ```
+
+- **500 Internal Server Error:** An unexpected error occurred.
+
+### GET /api/v1/archived-emails/:id
+
+Retrieves a single archived email by its ID, including its raw content and attachments.
+
+**Access:** Authenticated
+
+#### URL Parameters
+
+| Parameter | Type   | Description                   |
+| :-------- | :----- | :---------------------------- |
+| `id`      | string | The ID of the archived email. |
+
+#### Responses
+
+- **200 OK:** The archived email details.
+
+    ```json
+    {
+    	"id": "email-id",
+    	"subject": "Test Email",
+    	"from": "sender@example.com",
+    	"sentAt": "2023-10-27T10:00:00.000Z",
+    	"hasAttachments": true,
+    	"recipients": [{ "name": "Recipient 1", "email": "recipient1@example.com" }],
+    	"raw": "...",
+    	"attachments": [
+    		{
+    			"id": "attachment-id",
+    			"filename": "document.pdf",
+    			"mimeType": "application/pdf",
+    			"sizeBytes": 12345
+    		}
+    	]
+    }
+    ```
+
+- **404 Not Found:** The archived email with the specified ID was not found.
+- **500 Internal Server Error:** An unexpected error occurred.
+
+## Service Methods
+
+### `getArchivedEmails(ingestionSourceId: string, page: number, limit: number): Promise<PaginatedArchivedEmails>`
+
+Retrieves a paginated list of archived emails from the database for a given ingestion source.
+
+- **ingestionSourceId:** The ID of the ingestion source.
+- **page:** The page number for pagination.
+- **limit:** The number of items per page.
+- **Returns:** A promise that resolves to a `PaginatedArchivedEmails` object.
+
+### `getArchivedEmailById(emailId: string): Promise<ArchivedEmail | null>`
+
+Retrieves a single archived email by its ID, including its raw content and attachments.
+
+- **emailId:** The ID of the archived email.
+- **Returns:** A promise that resolves to an `ArchivedEmail` object or `null` if not found.

docs/api/auth.md

@@ -0,0 +1,84 @@
+# Auth Service API
+
+The Auth Service is responsible for handling user authentication, including login and token verification.
+
+## Endpoints
+
+### POST /api/v1/auth/login
+
+Authenticates a user and returns a JWT if the credentials are valid.
+
+**Access:** Public
+
+**Rate Limiting:** This endpoint is rate-limited to prevent brute-force attacks.
+
+#### Request Body
+
+| Field      | Type   | Description               |
+| :--------- | :----- | :------------------------ |
+| `email`    | string | The user's email address. |
+| `password` | string | The user's password.      |
+
+#### Responses
+
+- **200 OK:** Authentication successful.
+
+    ```json
+    {
+    	"accessToken": "your.jwt.token",
+    	"user": {
+    		"id": "user-id",
+    		"email": "user@example.com",
+    		"role": "user"
+    	}
+    }
+    ```
+
+- **400 Bad Request:** Email or password not provided.
+
+    ```json
+    {
+    	"message": "Email and password are required"
+    }
+    ```
+
+- **401 Unauthorized:** Invalid credentials.
+
+    ```json
+    {
+    	"message": "Invalid credentials"
+    }
+    ```
+
+- **500 Internal Server Error:** An unexpected error occurred.
+
+    ```json
+    {
+    	"message": "An internal server error occurred"
+    }
+    ```
+
+## Service Methods
+
+### `verifyPassword(password: string, hash: string): Promise<boolean>`
+
+Compares a plain-text password with a hashed password to verify its correctness.
+
+- **password:** The plain-text password.
+- **hash:** The hashed password to compare against.
+- **Returns:** A promise that resolves to `true` if the password is valid, otherwise `false`.
+
+### `login(email: string, password: string): Promise<LoginResponse | null>`
+
+Handles the user login process. It finds the user by email, verifies the password, and generates a JWT upon successful authentication.
+
+- **email:** The user's email.
+- **password:** The user's password.
+- **Returns:** A promise that resolves to a `LoginResponse` object containing the `accessToken` and `user` details, or `null` if authentication fails.
+
+### `verifyToken(token: string): Promise<AuthTokenPayload | null>`
+
+Verifies the authenticity and expiration of a JWT.
+
+- **token:** The JWT string to verify.
+- **Returns:** A promise that resolves to the token's `AuthTokenPayload` if valid, otherwise `null`.

docs/api/authentication.md

@@ -0,0 +1,60 @@
+# API Authentication
+
+To access protected API endpoints, you need to include a JSON Web Token (JWT) in the `Authorization` header of your requests.
+
+## Obtaining a JWT
+
+First, you need to authenticate with the `/api/v1/auth/login` endpoint by providing your email and password. If the credentials are correct, the API will return an `accessToken`.
+
+**Request:**
+
+```http
+POST /api/v1/auth/login
+Content-Type: application/json
+
+{
+  "email": "user@example.com",
+  "password": "your-password"
+}
+```
+
+**Successful Response:**
+
+```json
+{
+	"accessToken": "your.jwt.token",
+	"user": {
+		"id": "user-id",
+		"email": "user@example.com",
+		"role": "user"
+	}
+}
+```
+
+## Making Authenticated Requests
+
+Once you have the `accessToken`, you must include it in the `Authorization` header of all subsequent requests to protected endpoints, using the `Bearer` scheme.
+
+**Example:**
+
+```http
+GET /api/v1/dashboard/stats
+Authorization: Bearer your.jwt.token
+```
+
+If the token is missing, expired, or invalid, the API will respond with a `401 Unauthorized` status code.
+
+## Using a Super API Key
+
+Alternatively, for server-to-server communication or scripts, you can use a super API key. This key provides unrestricted access to the API and should be kept secret.
+
+You can set the `SUPER_API_KEY` in your `.env` file.
+
+To authenticate using the super API key, include it in the `Authorization` header as a Bearer token.
+
+**Example:**
+
+```http
+GET /api/v1/dashboard/stats
+Authorization: Bearer your-super-secret-api-key
+```

docs/api/dashboard.md

@@ -0,0 +1,114 @@
+# Dashboard Service API
+
+The Dashboard Service provides endpoints for retrieving statistics and data for the main dashboard.
+
+## Endpoints
+
+All endpoints in this service require authentication.
+
+### GET /api/v1/dashboard/stats
+
+Retrieves overall statistics, including the total number of archived emails, total storage used, and the number of failed ingestions in the last 7 days.
+
+**Access:** Authenticated
+
+#### Responses
+
+- **200 OK:** An object containing the dashboard statistics.
+
+    ```json
+    {
+    	"totalEmailsArchived": 12345,
+    	"totalStorageUsed": 54321098,
+    	"failedIngestionsLast7Days": 3
+    }
+    ```
+
+### GET /api/v1/dashboard/ingestion-history
+
+Retrieves the email ingestion history for the last 30 days, grouped by day.
+
+**Access:** Authenticated
+
+#### Responses
+
+- **200 OK:** An object containing the ingestion history.
+
+    ```json
+    {
+    	"history": [
+    		{
+    			"date": "2023-09-27T00:00:00.000Z",
+    			"count": 150
+    		},
+    		{
+    			"date": "2023-09-28T00:00:00.000Z",
+    			"count": 200
+    		}
+    	]
+    }
+    ```
+
+### GET /api/v1/dashboard/ingestion-sources
+
+Retrieves a list of all ingestion sources along with their status and storage usage.
+
+**Access:** Authenticated
+
+#### Responses
+
+- **200 OK:** An array of ingestion source objects.
+
+    ```json
+    [
+    	{
+    		"id": "source-id-1",
+    		"name": "Google Workspace",
+    		"provider": "google",
+    		"status": "active",
+    		"storageUsed": 12345678
+    	},
+    	{
+    		"id": "source-id-2",
+    		"name": "Microsoft 365",
+    		"provider": "microsoft",
+    		"status": "error",
+    		"storageUsed": 87654321
+    	}
+    ]
+    ```
+
+### GET /api/v1/dashboard/recent-syncs
+
+Retrieves a list of recent synchronization jobs. (Note: This is currently a placeholder and will return an empty array).
+
+**Access:** Authenticated
+
+#### Responses
+
+- **200 OK:** An empty array.
+
+    ```json
+    []
+    ```
+
+### GET /api/v1/dashboard/indexed-insights
+
+Retrieves insights from the indexed email data, such as the top senders.
+
+**Access:** Authenticated
+
+#### Responses
+
+- **200 OK:** An object containing indexed insights.
+
+    ```json
+    {
+    	"topSenders": [
+    		{
+    			"sender": "user@example.com",
+    			"count": 42
+    		}
+    	]
+    }
+    ```

docs/api/index.md

@@ -0,0 +1,18 @@
+# API Overview
+
+Welcome to the Open Archiver API documentation. This section provides detailed information about the available API endpoints.
+
+All API endpoints are prefixed with `/api/v1`.
+
+## Authentication
+
+Before making requests to protected endpoints, you must authenticate with the API. See the [Authentication Guide](./authentication.md) for details on how to obtain and use API tokens.
+
+## API Services
+
+- [**Auth Service**](./auth.md): Handles user authentication.
+- [**Archived Email Service**](./archived-email.md): Manages archived emails.
+- [**Dashboard Service**](./dashboard.md): Provides data for the main dashboard.
+- [**Ingestion Service**](./ingestion.md): Manages email ingestion sources.
+- [**Search Service**](./search.md): Handles email search functionality.
+- [**Storage Service**](./storage.md): Manages file storage and downloads.

docs/api/ingestion.md

@@ -1,206 +1,162 @@
-# Ingestion Sources API Documentation
+# Ingestion Service API
 
-A comprehensive guide to using the Ingestion Sources API.
+The Ingestion Service manages ingestion sources, which are configurations for connecting to email providers and importing emails.
 
-**Base Path:** `/v1/ingestion-sources`
+## Endpoints
 
----
+All endpoints in this service require authentication.
 
-## Authentication
+### POST /api/v1/ingestion-sources
 
-All endpoints in this API are protected and require authentication. Requests must include an `Authorization` header containing a valid Bearer token. This can be a JWT obtained from the login endpoint or a `SUPER_API_KEY` for administrative tasks.
+Creates a new ingestion source.
 
-**Header Example:**
-`Authorization: Bearer <YOUR_JWT_OR_SUPER_API_KEY>`
+**Access:** Authenticated
 
----
+#### Request Body
 
-## Core Concepts
+The request body should be a `CreateIngestionSourceDto` object.
 
-### Ingestion Providers
-
-The `provider` field determines the type of email source. Each provider requires a different configuration object, for example:
-
--   `google_workspace`: For connecting to Google Workspace accounts via OAuth 2.0.
--   `microsoft_365`: For connecting to Microsoft 365 accounts via OAuth 2.0.
--   `generic_imap`: For connecting to any email server that supports IMAP.
-
-### Ingestion Status
-
-The `status` field tracks the state of the ingestion source.
-
--   `pending_auth`: The source has been created but requires user authorization (OAuth flow).
--   `active`: The source is authenticated and ready to sync.
--   `syncing`: An import job is currently in progress.
--   `importing`: initial syncing in progress
--   `paused`: The source is temporarily disabled.
--   `error`: An error occurred during the last sync.
-
----
-
-## 1. Create Ingestion Source
-
--   **Method:** `POST`
--   **Path:** `/`
--   **Description:** Registers a new source for email ingestion. The `providerConfig` will vary based on the selected `provider`.
-
-#### Request Body (`CreateIngestionSourceDto`)
-
--   `name` (string, required): A user-friendly name for the source (e.g., "Marketing Department G-Suite").
--   `provider` (string, required): One of `google_workspace`, `microsoft_365`, or `generic_imap`.
--   `providerConfig` (object, required): Configuration specific to the provider.
-
-##### `providerConfig` for `google_workspace` / `microsoft_365`
-
-```json
-{
-    "name": "Corporate Google Workspace",
-    "provider": "google_workspace",
-    "providerConfig": {
-        "clientId": "your-oauth-client-id.apps.googleusercontent.com",
-        "clientSecret": "your-super-secret-client-secret",
-        "redirectUri": "https://yourapp.com/oauth/google/callback"
-    }
-}
-```
-
-##### `providerConfig` for `generic_imap`
-
-```json
-{
-    "name": "Legacy IMAP Server",
-    "provider": "generic_imap",
-    "providerConfig": {
-        "host": "imap.example.com",
-        "port": 993,
-        "secure": true,
-        "username": "archive-user",
-        "password": "imap-password"
-    }
+```typescript
+interface CreateIngestionSourceDto {
+	name: string;
+	provider: 'google' | 'microsoft' | 'generic_imap';
+	providerConfig: IngestionCredentials;
 }
 ```
 
 #### Responses
 
--   **Success (`201 Created`):** Returns the full `IngestionSource` object, which now includes a system-generated `id` and default status.
+- **201 Created:** The newly created ingestion source.
+- **500 Internal Server Error:** An unexpected error occurred.
 
-    ```json
-    {
-        "id": "a1b2c3d4-e5f6-7890-1234-567890abcdef",
-        "name": "Corporate Google Workspace",
-        "provider": "google_workspace",
-        "status": "pending_auth",
-        "createdAt": "2025-07-11T12:00:00.000Z",
-        "updatedAt": "2025-07-11T12:00:00.000Z",
-        "providerConfig": { ... }
-    }
-    ```
+### GET /api/v1/ingestion-sources
 
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem during creation.
+Retrieves all ingestion sources.
 
----
-
-## 2. Get All Ingestion Sources
-
--   **Method:** `GET`
--   **Path:** `/`
--   **Description:** Retrieves a list of all configured ingestion sources for the organization.
+**Access:** Authenticated
 
 #### Responses
 
--   **Success (`200 OK`):** Returns an array of `IngestionSource` objects.
+- **200 OK:** An array of ingestion source objects.
+- **500 Internal Server Error:** An unexpected error occurred.
 
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem.
+### GET /api/v1/ingestion-sources/:id
 
----
+Retrieves a single ingestion source by its ID.
 
-## 3. Get Ingestion Source by ID
-
--   **Method:** `GET`
--   **Path:** `/:id`
--   **Description:** Fetches the details of a specific ingestion source.
+**Access:** Authenticated
 
 #### URL Parameters
 
--   `id` (string, required): The UUID of the ingestion source.
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
 
 #### Responses
 
--   **Success (`200 OK`):** Returns the corresponding `IngestionSource` object.
+- **200 OK:** The ingestion source object.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.
 
--   **Error (`404 Not Found`):** Returned if no source with the given ID exists.
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem.
+### PUT /api/v1/ingestion-sources/:id
 
----
+Updates an existing ingestion source.
 
-## 4. Update Ingestion Source
-
--   **Method:** `PUT`
--   **Path:** `/:id`
--   **Description:** Modifies an existing ingestion source. This is useful for changing the name, pausing a source, or updating its configuration.
+**Access:** Authenticated
 
 #### URL Parameters
 
--   `id` (string, required): The UUID of the ingestion source to update.
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
 
-#### Request Body (`UpdateIngestionSourceDto`)
+#### Request Body
 
-All fields are optional. Only include the fields you want to change.
+The request body should be an `UpdateIngestionSourceDto` object.
 
-```json
-{
-    "name": "Marketing Dept G-Suite (Paused)",
-    "status": "paused"
+```typescript
+interface UpdateIngestionSourceDto {
+	name?: string;
+	provider?: 'google' | 'microsoft' | 'generic_imap';
+	providerConfig?: IngestionCredentials;
+	status?: 'pending_auth' | 'auth_success' | 'importing' | 'active' | 'paused' | 'error';
 }
 ```
 
 #### Responses
 
--   **Success (`200 OK`):** Returns the complete, updated `IngestionSource` object.
+- **200 OK:** The updated ingestion source object.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.
 
--   **Error (`404 Not Found`):** Returned if no source with the given ID exists.
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem.
+### DELETE /api/v1/ingestion-sources/:id
 
----
+Deletes an ingestion source and all associated data.
 
-## 5. Delete Ingestion Source
-
--   **Method:** `DELETE`
--   **Path:** `/:id`
--   **Description:** Permanently removes an ingestion source. This action cannot be undone.
+**Access:** Authenticated
 
 #### URL Parameters
 
--   `id` (string, required): The UUID of the ingestion source to delete.
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
 
 #### Responses
 
--   **Success (`204 No Content`):** Indicates successful deletion with no body content.
+- **204 No Content:** The ingestion source was deleted successfully.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.
 
--   **Error (`404 Not Found`):** Returned if no source with the given ID exists.
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem.
+### POST /api/v1/ingestion-sources/:id/import
 
----
+Triggers the initial import process for an ingestion source.
 
-## 6. Trigger Initial Import
-
--   **Method:** `POST`
--   **Path:** `/:id/sync`
--   **Description:** Initiates the email import process for a given source. This is an asynchronous operation that enqueues a background job and immediately returns a response. The status of the source will be updated to `importing`.
+**Access:** Authenticated
 
 #### URL Parameters
 
--   `id` (string, required): The UUID of the ingestion source to sync.
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
 
 #### Responses
 
--   **Success (`202 Accepted`):** Confirms that the sync request has been accepted for processing.
+- **202 Accepted:** The initial import was triggered successfully.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.
 
-    ```json
-    {
-        "message": "Initial import triggered successfully."
-    }
-    ```
+### POST /api/v1/ingestion-sources/:id/pause
 
--   **Error (`404 Not Found`):** Returned if no source with the given ID exists.
--   **Error (`500 Internal Server Error`):** Indicates a server-side problem.
+Pauses an active ingestion source.
+
+**Access:** Authenticated
+
+#### URL Parameters
+
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
+
+#### Responses
+
+- **200 OK:** The updated ingestion source object with a `paused` status.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.
+
+### POST /api/v1/ingestion-sources/:id/sync
+
+Triggers a forced synchronization for an ingestion source.
+
+**Access:** Authenticated
+
+#### URL Parameters
+
+| Parameter | Type   | Description                     |
+| :-------- | :----- | :------------------------------ |
+| `id`      | string | The ID of the ingestion source. |
+
+#### Responses
+
+- **202 Accepted:** The force sync was triggered successfully.
+- **404 Not Found:** Ingestion source not found.
+- **500 Internal Server Error:** An unexpected error occurred.

docs/api/search.md

@@ -0,0 +1,50 @@
+# Search Service API
+
+The Search Service provides an endpoint for searching indexed emails.
+
+## Endpoints
+
+All endpoints in this service require authentication.
+
+### GET /api/v1/search
+
+Performs a search query against the indexed emails.
+
+**Access:** Authenticated
+
+#### Query Parameters
+
+| Parameter          | Type   | Description                                                            | Default |
+| :----------------- | :----- | :--------------------------------------------------------------------- | :------ |
+| `keywords`         | string | The search query.                                                      |         |
+| `page`             | number | The page number for pagination.                                        | 1       |
+| `limit`            | number | The number of items per page.                                          | 10      |
+| `matchingStrategy` | string | The matching strategy to use (`all` or `last`).                        | `last`  |
+| `filters`          | object | Key-value pairs for filtering results (e.g., `from=user@example.com`). |         |
+
+#### Responses
+
+- **200 OK:** A search result object.
+
+    ```json
+    {
+    	"hits": [
+    		{
+    			"id": "email-id",
+    			"subject": "Test Email",
+    			"from": "sender@example.com",
+    			"_formatted": {
+    				"subject": "<em>Test</em> Email"
+    			}
+    		}
+    	],
+    	"total": 1,
+    	"page": 1,
+    	"limit": 10,
+    	"totalPages": 1,
+    	"processingTimeMs": 5
+    }
+    ```
+
+- **400 Bad Request:** Keywords are required.
+- **500 Internal Server Error:** An unexpected error occurred.

docs/api/storage.md

@@ -0,0 +1,26 @@
+# Storage Service API
+
+The Storage Service provides an endpoint for downloading files from the configured storage provider.
+
+## Endpoints
+
+All endpoints in this service require authentication.
+
+### GET /api/v1/storage/download
+
+Downloads a file from the storage.
+
+**Access:** Authenticated
+
+#### Query Parameters
+
+| Parameter | Type   | Description                                       |
+| :-------- | :----- | :------------------------------------------------ |
+| `path`    | string | The path to the file within the storage provider. |
+
+#### Responses
+
+- **200 OK:** The file stream.
+- **400 Bad Request:** File path is required or invalid.
+- **404 Not Found:** File not found.
+- **500 Internal Server Error:** An unexpected error occurred.

docs/index.md

@@ -0,0 +1,42 @@
+# Get Started 👋
+
+Welcome to Open Archiver! This guide will help you get started with setting up and using the platform.
+
+## What is Open Archiver? 🛡️
+
+**A secure, sovereign, and affordable open-source platform for email archiving and eDiscovery.**
+
+Open Archiver provides a robust, self-hosted solution for archiving, storing, indexing, and searching emails from major platforms, including Google Workspace (Gmail), Microsoft 365, as well as generic IMAP-enabled email inboxes. Use Open Archiver to keep a permanent, tamper-proof record of your communication history, free from vendor lock-in.
+
+## Key Features ✨
+
+- **Universal Ingestion**: Connect to Google Workspace, Microsoft 365, and standard IMAP servers to perform initial bulk imports and maintain continuous, real-time synchronization.
+- **Secure & Efficient Storage**: Emails are stored in the standard `.eml` format. The system uses deduplication and compression to minimize storage costs. All data is encrypted at rest.
+- **Pluggable Storage Backends**: Support both local filesystem storage and S3-compatible object storage (like AWS S3 or MinIO).
+- **Powerful Search & eDiscovery**: A high-performance search engine indexes the full text of emails and attachments (PDF, DOCX, etc.).
+- **Compliance & Retention**: Define granular retention policies to automatically manage the lifecycle of your data. Place legal holds on communications to prevent deletion during litigation (TBD).
+- **Comprehensive Auditing**: An immutable audit trail logs all system activities, ensuring you have a clear record of who accessed what and when (TBD).
+
+## Installation 🚀
+
+To get your own instance of Open Archiver running, follow our detailed installation guide:
+
+- [Installation Guide](./user-guides/installation.md)
+
+## Data Source Configuration 🔌
+
+After deploying the application, you will need to configure one or more ingestion sources to begin archiving emails. Follow our detailed guides to connect to your email provider:
+
+- [Connecting to Google Workspace](./user-guides/email-providers/google-workspace.md)
+- [Connecting to Microsoft 365](./user-guides/email-providers/microsoft-365.md)
+- [Connecting to a Generic IMAP Server](./user-guides/email-providers/imap.md)
+
+## Contributing ❤️
+
+We welcome contributions from the community!
+
+- **Reporting Bugs**: If you find a bug, please open an issue on our GitHub repository.
+- **Suggesting Enhancements**: Have an idea for a new feature? We'd love to hear it. Open an issue to start the discussion.
+- **Code Contributions**: If you'd like to contribute code, please fork the repository and submit a pull request.
+
+Please read our `CONTRIBUTING.md` file for more details on our code of conduct and the process for submitting pull requests.

docs/services/IAM-service/iam-policies.md

@@ -0,0 +1,141 @@
+# IAM Policies Guide
+
+This document provides a comprehensive guide to the Identity and Access Management (IAM) policies in Open Archiver. Our policy structure is inspired by AWS IAM, providing a powerful and flexible way to manage permissions.
+
+## 1. Policy Structure
+
+A policy is a JSON object that consists of one or more statements. Each statement includes an `Effect`, `Action`, and `Resource`.
+
+```json
+{
+	"Effect": "Allow",
+	"Action": ["archive:read", "archive:search"],
+	"Resource": ["archive/all"]
+}
+```
+
+- **`Effect`**: Specifies whether the statement results in an `Allow` or `Deny`. An explicit `Deny` always overrides an `Allow`.
+- **`Action`**: A list of operations that the policy grants or denies permission to perform. Actions are formatted as `service:operation`.
+- **`Resource`**: A list of resources to which the actions apply. Resources are specified in a hierarchical format. Wildcards (`*`) can be used.
+
+## 2. Wildcard Support
+
+Our IAM system supports wildcards (`*`) in both `Action` and `Resource` fields to provide flexible permission management, as defined in the `PolicyValidator`.
+
+### Action Wildcards
+
+You can use wildcards to grant broad permissions for actions:
+
+- **Global Wildcard (`*`)**: A standalone `*` in the `Action` field grants permission for all possible actions across all services.
+    ```json
+    "Action": ["*"]
+    ```
+- **Service-Level Wildcard (`service:*`)**: A wildcard at the end of an action string grants permission for all actions within that specific service.
+    ```json
+    "Action": ["archive:*"]
+    ```
+
+### Resource Wildcards
+
+Wildcards can also be used to specify resources:
+
+- **Global Wildcard (`*`)**: A standalone `*` in the `Resource` field applies the policy to all resources in the system.
+    ```json
+    "Resource": ["*"]
+    ```
+- **Partial Wildcards**: Some services allow wildcards at specific points in the resource path to refer to all resources of a certain type. For example, to target all ingestion sources:
+    ```json
+    "Resource": ["ingestion-source/*"]
+    ```
+
+## 3. Actions and Resources by Service
+
+The following sections define the available actions and resources, categorized by their respective services.
+
+### Service: `archive`
+
+The `archive` service pertains to all actions related to accessing and managing archived emails.
+
+**Actions:**
+
+| Action           | Description                                                            |
+| :--------------- | :--------------------------------------------------------------------- |
+| `archive:read`   | Grants permission to read the content and metadata of archived emails. |
+| `archive:search` | Grants permission to perform search queries against the email archive. |
+| `archive:export` | Grants permission to export search results or individual emails.       |
+
+**Resources:**
+
+| Resource                              | Description                                                                              |
+| :------------------------------------ | :--------------------------------------------------------------------------------------- |
+| `archive/all`                         | Represents the entire email archive.                                                     |
+| `archive/ingestion-source/{sourceId}` | Scopes the action to emails from a specific ingestion source.                            |
+| `archive/mailbox/{email}`             | Scopes the action to a single, specific mailbox, usually identified by an email address. |
+| `archive/custodian/{custodianId}`     | Scopes the action to emails belonging to a specific custodian.                           |
+
+---
+
+### Service: `ingestion`
+
+The `ingestion` service covers the management of email ingestion sources.
+
+**Actions:**
+
+| Action                   | Description                                                                  |
+| :----------------------- | :--------------------------------------------------------------------------- |
+| `ingestion:createSource` | Grants permission to create a new ingestion source.                          |
+| `ingestion:readSource`   | Grants permission to view the details of ingestion sources.                  |
+| `ingestion:updateSource` | Grants permission to modify the configuration of an ingestion source.        |
+| `ingestion:deleteSource` | Grants permission to delete an ingestion source.                             |
+| `ingestion:manageSync`   | Grants permission to trigger, pause, or force a sync on an ingestion source. |
+
+**Resources:**
+
+| Resource                      | Description                                               |
+| :---------------------------- | :-------------------------------------------------------- |
+| `ingestion-source/*`          | Represents all ingestion sources.                         |
+| `ingestion-source/{sourceId}` | Scopes the action to a single, specific ingestion source. |
+
+---
+
+### Service: `system`
+
+The `system` service is for managing system-level settings, users, and roles.
+
+**Actions:**
+
+| Action                  | Description                                         |
+| :---------------------- | :-------------------------------------------------- |
+| `system:readSettings`   | Grants permission to view system settings.          |
+| `system:updateSettings` | Grants permission to modify system settings.        |
+| `system:readUsers`      | Grants permission to list and view user accounts.   |
+| `system:createUser`     | Grants permission to create new user accounts.      |
+| `system:updateUser`     | Grants permission to modify existing user accounts. |
+| `system:deleteUser`     | Grants permission to delete user accounts.          |
+| `system:assignRole`     | Grants permission to assign roles to users.         |
+
+**Resources:**
+
+| Resource               | Description                                           |
+| :--------------------- | :---------------------------------------------------- |
+| `system/settings`      | Represents the system configuration.                  |
+| `system/users`         | Represents all user accounts within the system.       |
+| `system/user/{userId}` | Scopes the action to a single, specific user account. |
+
+---
+
+### Service: `dashboard`
+
+The `dashboard` service relates to viewing analytics and overview information.
+
+**Actions:**
+
+| Action           | Description                                                     |
+| :--------------- | :-------------------------------------------------------------- |
+| `dashboard:read` | Grants permission to view all dashboard widgets and statistics. |
+
+**Resources:**
+
+| Resource      | Description                                 |
+| :------------ | :------------------------------------------ |
+| `dashboard/*` | Represents all components of the dashboard. |

docs/services/index.md

@@ -0,0 +1 @@
+# services

docs/services/storage-service.md

@@ -14,8 +14,8 @@ The `StorageService` is configured via environment variables in the `.env` file.
 
 The `STORAGE_TYPE` variable determines which provider the service will use.
 
--   `STORAGE_TYPE=local`: Uses the local server's filesystem.
--   `STORAGE_TYPE=s3`: Uses an S3-compatible object storage service (e.g., AWS S3, MinIO, Google Cloud Storage).
+- `STORAGE_TYPE=local`: Uses the local server's filesystem.
+- `STORAGE_TYPE=s3`: Uses an S3-compatible object storage service (e.g., AWS S3, MinIO, Google Cloud Storage).
 
 ### 2. Local Filesystem Configuration
 
@@ -27,7 +27,7 @@ STORAGE_TYPE=local
 STORAGE_LOCAL_ROOT_PATH=/var/data/open-archiver
 ```
 
--   `STORAGE_LOCAL_ROOT_PATH`: The absolute path on the server where the archive will be created. The service will create subdirectories within this path as needed.
+- `STORAGE_LOCAL_ROOT_PATH`: The absolute path on the server where the archive will be created. The service will create subdirectories within this path as needed.
 
 ### 3. S3-Compatible Storage Configuration
 
@@ -44,12 +44,12 @@ STORAGE_S3_REGION=us-east-1
 STORAGE_S3_FORCE_PATH_STYLE=true
 ```
 
--   `STORAGE_S3_ENDPOINT`: The full URL of the S3 API endpoint.
--   `STORAGE_S3_BUCKET`: The name of the bucket to use for storage.
--   `STORAGE_S3_ACCESS_KEY_ID`: The access key for your S3 user.
--   `STORAGE_S3_SECRET_ACCESS_KEY`: The secret key for your S3 user.
--   `STORAGE_S3_REGION` (Optional): The AWS region of your bucket. Recommended for AWS S3.
--   `STORAGE_S3_FORCE_PATH_STYLE` (Optional): Set to `true` when using non-AWS S3 services like MinIO.
+- `STORAGE_S3_ENDPOINT`: The full URL of the S3 API endpoint.
+- `STORAGE_S3_BUCKET`: The name of the bucket to use for storage.
+- `STORAGE_S3_ACCESS_KEY_ID`: The access key for your S3 user.
+- `STORAGE_S3_SECRET_ACCESS_KEY`: The secret key for your S3 user.
+- `STORAGE_S3_REGION` (Optional): The AWS region of your bucket. Recommended for AWS S3.
+- `STORAGE_S3_FORCE_PATH_STYLE` (Optional): Set to `true` when using non-AWS S3 services like MinIO.
 
 ## How to Use the Service
 
@@ -61,31 +61,27 @@ The `StorageService` is designed to be used via dependency injection in other se
 import { StorageService } from './StorageService';
 
 class IngestionService {
-    private storageService: StorageService;
+	private storageService: StorageService;
 
-    constructor() {
-        // The StorageService is instantiated without any arguments.
-        // It automatically reads the configuration from the environment.
-        this.storageService = new StorageService();
-    }
+	constructor() {
+		// The StorageService is instantiated without any arguments.
+		// It automatically reads the configuration from the environment.
+		this.storageService = new StorageService();
+	}
 
-    public async archiveEmail(
-        rawEmail: Buffer,
-        userId: string,
-        messageId: string
-    ): Promise<void> {
-        // Define a structured, unique path for the email.
-        const archivePath = `${userId}/messages/${messageId}.eml`;
+	public async archiveEmail(rawEmail: Buffer, userId: string, messageId: string): Promise<void> {
+		// Define a structured, unique path for the email.
+		const archivePath = `${userId}/messages/${messageId}.eml`;
 
-        try {
-            // Use the service. It doesn't know or care if this is writing
-            // to a local disk or an S3 bucket.
-            await this.storageService.put(archivePath, rawEmail);
-            console.log(`Successfully archived email to ${archivePath}`);
-        } catch (error) {
-            console.error(`Failed to archive email ${messageId}`, error);
-        }
-    }
+		try {
+			// Use the service. It doesn't know or care if this is writing
+			// to a local disk or an S3 bucket.
+			await this.storageService.put(archivePath, rawEmail);
+			console.log(`Successfully archived email to ${archivePath}`);
+		} catch (error) {
+			console.error(`Failed to archive email ${messageId}`, error);
+		}
+	}
 }
 ```
 
@@ -99,9 +95,9 @@ The `StorageService` implements the `IStorageProvider` interface. All methods ar
 
 Stores a file at the specified path. If a file already exists at that path, it will be overwritten.
 
--   **`path: string`**: A unique identifier for the file, including its directory structure (e.g., `"user-123/emails/message-abc.eml"`).
--   **`content: Buffer | NodeJS.ReadableStream`**: The content of the file. It can be a `Buffer` for small files or a `ReadableStream` for large files to ensure memory efficiency.
--   **Returns**: `Promise<void>` - A promise that resolves when the file has been successfully stored.
+- **`path: string`**: A unique identifier for the file, including its directory structure (e.g., `"user-123/emails/message-abc.eml"`).
+- **`content: Buffer | NodeJS.ReadableStream`**: The content of the file. It can be a `Buffer` for small files or a `ReadableStream` for large files to ensure memory efficiency.
+- **Returns**: `Promise<void>` - A promise that resolves when the file has been successfully stored.
 
 ---
 
@@ -109,9 +105,9 @@ Stores a file at the specified path. If a file already exists at that path, it w
 
 Retrieves a file from the specified path as a readable stream.
 
--   **`path: string`**: The unique identifier of the file to retrieve.
--   **Returns**: `Promise<NodeJS.ReadableStream>` - A promise that resolves with a readable stream of the file's content.
--   **Throws**: An `Error` if the file is not found at the specified path.
+- **`path: string`**: The unique identifier of the file to retrieve.
+- **Returns**: `Promise<NodeJS.ReadableStream>` - A promise that resolves with a readable stream of the file's content.
+- **Throws**: An `Error` if the file is not found at the specified path.
 
 ---
 
@@ -119,8 +115,8 @@ Retrieves a file from the specified path as a readable stream.
 
 Deletes a file from the storage backend.
 
--   **`path: string`**: The unique identifier of the file to delete.
--   **Returns**: `Promise<void>` - A promise that resolves when the file is deleted. If the file does not exist, the promise will still resolve successfully without throwing an error.
+- **`path: string`**: The unique identifier of the file to delete.
+- **Returns**: `Promise<void>` - A promise that resolves when the file is deleted. If the file does not exist, the promise will still resolve successfully without throwing an error.
 
 ---
 
@@ -128,5 +124,5 @@ Deletes a file from the storage backend.
 
 Checks for the existence of a file.
 
--   **`path: string`**: The unique identifier of the file to check.
--   **Returns**: `Promise<boolean>` - A promise that resolves with `true` if the file exists, and `false` otherwise.
+- **`path: string`**: The unique identifier of the file to check.
+- **Returns**: `Promise<boolean>` - A promise that resolves with `true` if the file exists, and `false` otherwise.

docs/user-guides/email-providers/eml.md

@@ -0,0 +1,36 @@
+# EML Import
+
+OpenArchiver allows you to import EML files from a zip archive. This is useful for importing emails from a variety of sources, including other email clients and services.
+
+## Preparing the Zip File
+
+To ensure a successful import, you should compress your .eml files to one zip file according to the following guidelines:
+
+- **Structure:** The zip file can contain any number of `.eml` files, organized in any folder structure. The folder structure will be preserved in OpenArchiver, so you can use it to organize your emails.
+- **Compression:** The zip file should be compressed using standard zip compression.
+
+Here's an example of a valid folder structure:
+
+```
+archive.zip
+├── inbox
+│   ├── email-01.eml
+│   └── email-02.eml
+├── sent
+│   └── email-03.eml
+└── drafts
+    ├── nested-folder
+    │   └── email-04.eml
+    └── email-05.eml
+```
+
+## Creating an EML Ingestion Source
+
+1.  Go to the **Ingestion Sources** page in the OpenArchiver dashboard.
+2.  Click the **Create New** button.
+3.  Select **EML Import** as the provider.
+4.  Enter a name for the ingestion source.
+5.  Click the **Choose File** button and select the zip archive containing your EML files.
+6.  Click the **Submit** button.
+
+OpenArchiver will then start importing the EML files from the zip archive. The ingestion process may take some time, depending on the size of the archive.

docs/user-guides/email-providers/google-workspace.md

@@ -0,0 +1,124 @@
+# Connecting to Google Workspace
+
+This guide provides instructions for Google Workspace administrators to set up a connection that allows the archiving of all user mailboxes within their organization.
+
+The connection uses a **Google Cloud Service Account** with **Domain-Wide Delegation**. This is a secure method that grants the archiving service permission to access user data on behalf of the administrator, without requiring individual user passwords or consent.
+
+## Prerequisites
+
+- You must have **Super Administrator** privileges in your Google Workspace account.
+- You must have access to the **Google Cloud Console** associated with your organization.
+
+## Setup Overview
+
+The setup process involves three main parts:
+
+1.  Configuring the necessary permissions in the Google Cloud Console.
+2.  Authorizing the service account in the Google Workspace Admin Console.
+3.  Entering the generated credentials into the OpenArchiver application.
+
+---
+
+### Part 1: Google Cloud Console Setup
+
+In this part, you will create a service account and enable the APIs it needs to function.
+
+1.  **Create a Google Cloud Project:**
+    - Go to the [Google Cloud Console](https://console.cloud.google.com/).
+    - If you don't already have one, create a new project for the archiving service (e.g., "Email Archiver").
+
+2.  **Enable Required APIs:**
+    - In your selected project, navigate to the **"APIs & Services" > "Library"** section.
+    - Search for and enable the following two APIs:
+        - **Gmail API**
+        - **Admin SDK API**
+
+3.  **Create a Service Account:**
+    - Navigate to **"IAM & Admin" > "Service Accounts"**.
+    - Click **"Create Service Account"**.
+    - Give the service account a name (e.g., `email-archiver-service`) and a description.
+    - Click **"Create and Continue"**. You do not need to grant this service account any roles on the project. Click **"Done"**.
+
+4.  **Generate a JSON Key:**
+    - Find the service account you just created in the list.
+    - Click the three-dot menu under **"Actions"** and select **"Manage keys"**.
+    - Click **"Add Key"** > **"Create new key"**.
+    - Select **JSON** as the key type and click **"Create"**.
+    - A JSON file will be downloaded to your computer. **Keep this file secure, as it contains private credentials.** You will need the contents of this file in Part 3.
+
+### Troubleshooting
+
+#### Error: "iam.disableServiceAccountKeyCreation"
+
+If you receive an error message stating `The organization policy constraint 'iam.disableServiceAccountKeyCreation' is enforced` when trying to create a JSON key, it means your Google Cloud organization has a policy preventing the creation of new service account keys.
+
+To resolve this, you must have **Organization Administrator** permissions.
+
+1.  **Navigate to your Organization:** In the Google Cloud Console, use the project selector at the top of the page to select your organization node (it usually has a building icon).
+2.  **Go to IAM:** From the navigation menu, select **"IAM & Admin" > "IAM"**.
+3.  **Edit Your Permissions:** Find your user account in the list and click the pencil icon to edit roles. Add the following two roles:
+    - `Organization Policy Administrator`
+    - `Organization Administrator`
+      _Note: These roles are only available at the organization level, not the project level._
+4.  **Modify the Policy:**
+    - Navigate to **"IAM & Admin" > "Organization Policies"**.
+    - In the filter box, search for the policy **"iam.disableServiceAccountKeyCreation"**.
+    - Click on the policy to edit it.
+    - You can either disable the policy entirely (if your security rules permit) or add a rule to exclude the specific project you are using for the archiver from this policy.
+5.  **Retry Key Creation:** Once the policy is updated, return to your project and you should be able to generate the JSON key as described in Part 1.
+
+---
+
+### Part 2: Grant Domain-Wide Delegation
+
+Now, you will authorize the service account you created to access data from your Google Workspace.
+
+1.  **Get the Service Account's Client ID:**
+    - Go back to the list of service accounts in the Google Cloud Console.
+    - Click on the service account you created.
+    - Under the **"Details"** tab, find and copy the **Unique ID** (this is the Client ID).
+
+2.  **Authorize the Client in Google Workspace:**
+    - Go to your **Google Workspace Admin Console** at [admin.google.com](https://admin.google.com).
+    - Navigate to **Security > Access and data control > API controls**.
+    - Under the "Domain-wide Delegation" section, click **"Manage Domain-wide Delegation"**.
+    - Click **"Add new"**.
+
+3.  **Enter Client Details and Scopes:**
+    - In the **Client ID** field, paste the **Unique ID** you copied from the service account.
+    - In the **OAuth scopes** field, paste the following two scopes exactly as they appear, separated by a comma:
+        ```
+        https://www.googleapis.com/auth/admin.directory.user.readonly,https://www.googleapis.com/auth/gmail.readonly
+        ```
+    - Click **"Authorize"**.
+
+The service account is now permitted to list users and read their email data across your domain.
+
+---
+
+### Part 3: Connecting in OpenArchiver
+
+Finally, you will provide the generated credentials to the application.
+
+1.  **Navigate to Ingestion Sources:**
+    From the main dashboard, go to the **Ingestion Sources** page.
+
+2.  **Create a New Source:**
+    Click the **"Create New"** button.
+
+3.  **Fill in the Configuration Details:**
+    - **Name:** Give the source a name (e.g., "Google Workspace Archive").
+    - **Provider:** Select **"Google Workspace"** from the dropdown.
+    - **Service Account Key (JSON):** Open the JSON file you downloaded in Part 1. Copy the entire content of the file and paste it into this text area.
+    - **Impersonated Admin Email:** Enter the email address of a Super Administrator in your Google Workspace (e.g., `admin@your-domain.com`). The service will use this user's authority to discover all other users.
+
+4.  **Save Changes:**
+    Click **"Save changes"**.
+
+## What Happens Next?
+
+Once the connection is saved and verified, the system will begin the archiving process:
+
+1.  **User Discovery:** The service will first connect to the Admin SDK to get a list of all active users in your Google Workspace.
+2.  **Initial Import:** The system will then start a background job to import the mailboxes of all discovered users. The status will show as **"Importing"**. This can take a significant amount of time depending on the number of users and the size of their mailboxes.
+3.  **Continuous Sync:** After the initial import is complete, the status will change to **"Active"**. The system will then periodically check each user's mailbox for new emails and archive them automatically.

docs/user-guides/email-providers/imap.md

@@ -0,0 +1,66 @@
+# Connecting to a Generic IMAP Server
+
+This guide will walk you through connecting a standard IMAP email account as an ingestion source. This allows you to archive emails from any provider that supports the IMAP protocol, which is common for many self-hosted or traditional email services.
+
+## Step-by-Step Guide
+
+1.  **Navigate to Ingestion Sources:**
+    From the main dashboard, go to the **Ingestions** page.
+
+2.  **Create a New Source:**
+    Click the **"Create New"** button to open the ingestion source configuration dialog.
+
+3.  **Fill in the Configuration Details:**
+    You will see a form with several fields. Here is how to fill them out for an IMAP connection:
+    - **Name:** Give your ingestion source a descriptive name that you will easily recognize, such as "Work Email (IMAP)" or "Personal Gmail".
+
+    - **Provider:** From the dropdown menu, select **"Generic IMAP"**. This will reveal the specific fields required for an IMAP connection.
+
+    - **Host:** Enter the server address for your email provider's IMAP service. This often looks like `imap.your-provider.com` or `mail.your-domain.com`.
+
+    - **Port:** Enter the port number for the IMAP server. For a secure connection (which is strongly recommended), this is typically `993`.
+
+    - **Username:** Enter the full email address or username you use to log in to your email account.
+
+    - **Password:** Enter the password for your email account.
+
+4.  **Save Changes:**
+    Once you have filled in all the details, click the **"Save changes"** button.
+
+## Security Recommendation: Use an App Password
+
+For enhanced security, we strongly recommend using an **"app password"** (sometimes called an "app-specific password") instead of your main account password.
+
+Many email providers (like Gmail, Outlook, and Fastmail) allow you to generate a unique password that grants access only to a specific application (in this case, the archiving service). If you ever need to revoke access, you can simply delete the app password without affecting your main account login.
+
+Please consult your email provider's documentation to see if they support app passwords and how to create one.
+
+### How to Obtain an App Password for Gmail
+
+1.  **Enable 2-Step Verification:** You must have 2-Step Verification turned on for your Google Account.
+2.  **Go to App Passwords:** Visit [myaccount.google.com/apppasswords](https://myaccount.google.com/apppasswords). You may be asked to sign in again.
+3.  **Create the Password:**
+    - At the bottom, click **"Select app"** and choose **"Other (Custom name)"**.
+    - Give it a name you'll recognize, like "OpenArchiver".
+    - Click **"Generate"**.
+4.  **Use the Password:** A 16-digit password will be displayed. Copy this password and paste it into the **Password** field in the OpenArchiver ingestion source form.
+
+### How to Obtain an App Password for Outlook/Microsoft Accounts
+
+1.  **Enable Two-Step Verification:** You must have two-step verification enabled for your Microsoft account.
+2.  **Go to Security Options:** Sign in to your Microsoft account and navigate to the [Advanced security options](https://account.live.com/proofs/manage/additional).
+3.  **Create a New App Password:**
+    - Scroll down to the **"App passwords"** section.
+    - Click **"Create a new app password"**.
+4.  **Use the Password:** A new password will be generated. Use this password in the **Password** field in the OpenArchiver ingestion source form.
+
+## What Happens Next?
+
+After you save the connection, the system will attempt to connect to the IMAP server. The status of the ingestion source will update to reflect its current state:
+
+- **Importing:** The system is performing the initial, one-time import of all emails from your `INBOX`. This may take a while depending on the size of your mailbox.
+- **Active:** The initial import is complete, and the system will now periodically check for and archive new emails.
+- **Paused:** The connection is valid, but the system will not check for new emails until you resume it.
+- **Error:** The system was unable to connect using the provided credentials. Please double-check your Host, Port, Username, and Password and try again.
+
+You can view, edit, pause, or manually sync any of your ingestion sources from the main table on the **Ingestions** page.

docs/user-guides/email-providers/index.md

@@ -0,0 +1,11 @@
+# Connecting Email Providers
+
+Open Archiver can connect to a variety of email sources to ingest and archive your emails. This section provides guides for connecting to popular email providers.
+
+Choose your provider from the list below to get started:
+
+- [Google Workspace](./google-workspace.md)
+- [Microsoft 365](./microsoft-365.md)
+- [Generic IMAP Server](./imap.md)
+- [EML Import](./eml.md)
+- [PST Import](./pst.md)

docs/user-guides/email-providers/microsoft-365.md

@@ -0,0 +1,93 @@
+# Connecting to Microsoft 365
+
+This guide provides instructions for Microsoft 365 administrators to set up a connection that allows the archiving of all user mailboxes within their organization.
+
+The connection uses the **Microsoft Graph API** and an **App Registration** in Microsoft Entra ID. This is a secure, standard method that grants the archiving service permission to read email data on your behalf without ever needing to handle user passwords.
+
+## Prerequisites
+
+- You must have one of the following administrator roles in your Microsoft 365 tenant: **Global Administrator**, **Application Administrator**, or **Cloud Application Administrator**.
+
+## Setup Overview
+
+The setup process involves four main parts, all performed within the Microsoft Entra admin center and the OpenArchiver application:
+
+1.  Registering a new application identity for the archiver in Entra ID.
+2.  Granting the application the specific permissions it needs to read mail.
+3.  Creating a secure password (a client secret) for the application.
+4.  Entering the generated credentials into the OpenArchiver application.
+
+---
+
+### Part 1: Register a New Application in Microsoft Entra ID
+
+First, you will create an "App registration," which acts as an identity for the archiving service within your Microsoft 365 ecosystem.
+
+1.  Sign in to the [Microsoft Entra admin center](https://entra.microsoft.com).
+2.  In the left-hand navigation pane, go to **Identity > Applications > App registrations**.
+3.  Click the **+ New registration** button at the top of the page.
+4.  On the "Register an application" screen:
+    - **Name:** Give the application a descriptive name you will recognize, such as `OpenArchiver Service`.
+    - **Supported account types:** Select **"Accounts in this organizational directory only (Default Directory only - Single tenant)"**. This is the most secure option.
+    - **Redirect URI (optional):** You can leave this blank.
+5.  Click the **Register** button. You will be taken to the application's main "Overview" page.
+
+---
+
+### Part 2: Grant API Permissions
+
+Next, you must grant the application the specific permissions required to read user profiles and their mailboxes.
+
+1.  From your new application's page, select **API permissions** from the left-hand menu.
+2.  Click the **+ Add a permission** button.
+3.  In the "Request API permissions" pane, select **Microsoft Graph**.
+4.  Select **Application permissions**. This is critical as it allows the service to run in the background without a user being signed in.
+5.  In the "Select permissions" search box, find and check the boxes for the following two permissions:
+    - `Mail.Read`
+    - `User.Read.All`
+6.  Click the **Add permissions** button at the bottom.
+7.  **Crucial Final Step:** You will now see the permissions in your list with a warning status. You must grant consent on behalf of your organization. Click the **"Grant admin consent for [Your Organization's Name]"** button located above the permissions table. Click **Yes** in the confirmation dialog. The status for both permissions should now show a green checkmark.
+
+---
+
+### Part 3: Create a Client Secret
+
+The client secret is a password that the archiving service will use to authenticate. Treat this with the same level of security as an administrator's password.
+
+1.  In your application's menu, navigate to **Certificates & secrets**.
+2.  Select the **Client secrets** tab and click **+ New client secret**.
+3.  In the pane that appears:
+    - **Description:** Enter a clear description, such as `OpenArchiver Key`.
+    - **Expires:** Select an expiry duration. We recommend **12 or 24 months**. Set a calendar reminder to renew it before it expires to prevent service interruption.
+4.  Click **Add**.
+5.  **IMMEDIATELY COPY THE SECRET:** The secret is now visible in the **"Value"** column. This is the only time it will be fully displayed. Copy this value now and store it in a secure password manager before navigating away. If you lose it, you must create a new one.
+
+---
+
+### Part 4: Connecting in OpenArchiver
+
+You now have the three pieces of information required to configure the connection.
+
+1.  **Navigate to Ingestion Sources:**
+    In the OpenArchiver application, go to the **Ingestion Sources** page.
+
+2.  **Create a New Source:**
+    Click the **"Create New"** button.
+
+3.  **Fill in the Configuration Details:**
+    - **Name:** Give the source a name (e.g., "Microsoft 365 Archive").
+    - **Provider:** Select **"Microsoft 365"** from the dropdown.
+    - **Application (Client) ID:** Go to the **Overview** page of your app registration in the Entra admin center and copy this value.
+    - **Directory (Tenant) ID:** This value is also on the **Overview** page.
+    - **Client Secret Value:** Paste the secret **Value** (not the Secret ID) that you copied and saved in the previous step.
+
+4.  **Save Changes:**
+    Click **"Save changes"**.
+
+## What Happens Next?
+
+Once the connection is saved, the system will begin the archiving process:
+
+1.  **User Discovery:** The service will connect to the Microsoft Graph API to get a list of all users in your organization.
+2.  **Initial Import:** The system will begin a background job to import the mailboxes of all discovered users, folder by folder. The status will show as **"Importing"**. This can take a significant amount of time.
+3.  **Continuous Sync:** After the initial import, the status will change to **"Active"**. The system will use Microsoft Graph's delta query feature to efficiently fetch only new or changed emails, ensuring the archive stays up-to-date.

docs/user-guides/email-providers/pst.md

@@ -0,0 +1,21 @@
+# PST Import
+
+OpenArchiver allows you to import PST files. This is useful for importing emails from a variety of sources, including Microsoft Outlook.
+
+## Preparing the PST File
+
+To ensure a successful import, you should prepare your PST file according to the following guidelines:
+
+- **Structure:** The PST file can contain any number of emails, organized in any folder structure. The folder structure will be preserved in OpenArchiver, so you can use it to organize your emails.
+- **Password Protection:** OpenArchiver does not support password-protected PST files. Please remove the password from your PST file before importing it.
+
+## Creating a PST Ingestion Source
+
+1.  Go to the **Ingestion Sources** page in the OpenArchiver dashboard.
+2.  Click the **Create New** button.
+3.  Select **PST Import** as the provider.
+4.  Enter a name for the ingestion source.
+5.  Click the **Choose File** button and select the PST file.
+6.  Click the **Submit** button.
+
+OpenArchiver will then start importing the emails from the PST file. The ingestion process may take some time, depending on the size of the file.

docs/user-guides/installation.md

@@ -0,0 +1,299 @@
+# Installation Guide
+
+This guide will walk you through setting up Open Archiver using Docker Compose. This is the recommended method for deploying the application.
+
+## Prerequisites
+
+- [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) installed on your server or local machine.
+- A server or local machine with at least 4GB of RAM (2GB of RAM if you use external Postgres, Redis (Valkey) and Meilisearch instances).
+- [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) installed on your server or local machine.
+
+## 1. Clone the Repository
+
+First, clone the Open Archiver repository to your machine:
+
+```bash
+git clone https://github.com/LogicLabs-OU/OpenArchiver.git
+cd OpenArchiver
+```
+
+## 2. Configure Your Environment
+
+The application is configured using environment variables. You'll need to create a `.env` file to store your configuration.
+
+Copy the example environment file for Docker:
+
+```bash
+cp .env.example.docker .env
+```
+
+Now, open the `.env` file in a text editor and customize the settings.
+
+### Important Configuration
+
+You must change the following placeholder values to secure your instance:
+
+- `POSTGRES_PASSWORD`: A strong, unique password for the database.
+- `REDIS_PASSWORD`: A strong, unique password for the Valkey/Redis service.
+- `MEILI_MASTER_KEY`: A complex key for Meilisearch.
+- `JWT_SECRET`: A long, random string for signing authentication tokens.
+- `ENCRYPTION_KEY`: A 32-byte hex string for encrypting sensitive data in the database. You can generate one with the following command:
+    ```bash
+    openssl rand -hex 32
+    ```
+
+### Storage Configuration
+
+By default, the Docker Compose setup uses local filesystem storage, which is persisted using a Docker volume named `archiver-data`. This is suitable for most use cases.
+
+If you want to use S3-compatible object storage, change the `STORAGE_TYPE` to `s3` and fill in your S3 credentials (`STORAGE_S3_*` variables). When `STORAGE_TYPE` is set to `local`, the S3-related variables are not required.
+
+### Using External Services
+
+For convenience, the `docker-compose.yml` file includes services for PostgreSQL, Valkey (Redis), and Meilisearch. However, you can use your own external or managed instances for these services.
+
+To do so:
+
+1.  **Update your `.env` file**: Change the host, port, and credential variables to point to your external service instances. For example, you would update `DATABASE_URL`, `REDIS_HOST`, and `MEILI_HOST`.
+2.  **Modify `docker-compose.yml`**: Remove or comment out the service definitions for `postgres`, `valkey`, and `meilisearch` from your `docker-compose.yml` file.
+
+This will configure the Open Archiver application to connect to your services instead of starting the default ones.
+
+### Environment Variable Reference
+
+Here is a complete list of environment variables available for configuration:
+
+#### Application Settings
+
+| Variable         | Description                                                                                           | Default Value |
+| ---------------- | ----------------------------------------------------------------------------------------------------- | ------------- |
+| `NODE_ENV`       | The application environment.                                                                          | `development` |
+| `PORT_BACKEND`   | The port for the backend service.                                                                     | `4000`        |
+| `PORT_FRONTEND`  | The port for the frontend service.                                                                    | `3000`        |
+| `SYNC_FREQUENCY` | The frequency of continuous email syncing. See [cron syntax](https://crontab.guru/) for more details. | `* * * * *`   |
+
+#### Docker Compose Service Configuration
+
+These variables are used by `docker-compose.yml` to configure the services.
+
+| Variable            | Description                                     | Default Value                                            |
+| ------------------- | ----------------------------------------------- | -------------------------------------------------------- |
+| `POSTGRES_DB`       | The name of the PostgreSQL database.            | `open_archive`                                           |
+| `POSTGRES_USER`     | The username for the PostgreSQL database.       | `admin`                                                  |
+| `POSTGRES_PASSWORD` | The password for the PostgreSQL database.       | `password`                                               |
+| `DATABASE_URL`      | The connection URL for the PostgreSQL database. | `postgresql://admin:password@postgres:5432/open_archive` |
+| `MEILI_MASTER_KEY`  | The master key for Meilisearch.                 | `aSampleMasterKey`                                       |
+| `MEILI_HOST`        | The host for the Meilisearch service.           | `http://meilisearch:7700`                                |
+| `REDIS_HOST`        | The host for the Valkey (Redis) service.        | `valkey`                                                 |
+| `REDIS_PORT`        | The port for the Valkey (Redis) service.        | `6379`                                                   |
+| `REDIS_PASSWORD`    | The password for the Valkey (Redis) service.    | `defaultredispassword`                                   |
+| `REDIS_TLS_ENABLED` | Enable or disable TLS for Redis.                | `false`                                                  |
+
+#### Storage Settings
+
+| Variable                       | Description                                                                                                 | Default Value             |
+| ------------------------------ | ----------------------------------------------------------------------------------------------------------- | ------------------------- |
+| `STORAGE_TYPE`                 | The storage backend to use (`local` or `s3`).                                                               | `local`                   |
+| `BODY_SIZE_LIMIT`              | The maximum request body size for uploads. Can be a number in bytes or a string with a unit (e.g., `100M`). | `100M`                    |
+| `STORAGE_LOCAL_ROOT_PATH`      | The root path for local file storage.                                                                       | `/var/data/open-archiver` |
+| `STORAGE_S3_ENDPOINT`          | The endpoint for S3-compatible storage (required if `STORAGE_TYPE` is `s3`).                                |                           |
+| `STORAGE_S3_BUCKET`            | The bucket name for S3-compatible storage (required if `STORAGE_TYPE` is `s3`).                             |                           |
+| `STORAGE_S3_ACCESS_KEY_ID`     | The access key ID for S3-compatible storage (required if `STORAGE_TYPE` is `s3`).                           |                           |
+| `STORAGE_S3_SECRET_ACCESS_KEY` | The secret access key for S3-compatible storage (required if `STORAGE_TYPE` is `s3`).                       |                           |
+| `STORAGE_S3_REGION`            | The region for S3-compatible storage (required if `STORAGE_TYPE` is `s3`).                                  |                           |
+| `STORAGE_S3_FORCE_PATH_STYLE`  | Force path-style addressing for S3 (optional).                                                              | `false`                   |
+
+#### Security & Authentication
+
+| Variable         | Description                                                         | Default Value                              |
+| ---------------- | ------------------------------------------------------------------- | ------------------------------------------ |
+| `JWT_SECRET`     | A secret key for signing JWT tokens.                                | `a-very-secret-key-that-you-should-change` |
+| `JWT_EXPIRES_IN` | The expiration time for JWT tokens.                                 | `7d`                                       |
+| `SUPER_API_KEY`  | An API key with super admin privileges.                             |                                            |
+| `ENCRYPTION_KEY` | A 32-byte hex string for encrypting sensitive data in the database. |                                            |
+
+## 3. Run the Application
+
+Once you have configured your `.env` file, you can start all the services using Docker Compose:
+
+```bash
+docker compose up -d
+```
+
+This command will:
+
+- Pull the required Docker images for the frontend, backend, database, and other services.
+- Create and start the containers in the background (`-d` flag).
+- Create the persistent volumes for your data.
+
+You can check the status of the running containers with:
+
+```bash
+docker compose ps
+```
+
+## 4. Access the Application
+
+Once the services are running, you can access the Open Archiver web interface by navigating to `http://localhost:3000` in your web browser.
+
+You can log in with the `ADMIN_EMAIL` and `ADMIN_PASSWORD` you configured in your `.env` file.
+
+## 5. Next Steps
+
+After successfully deploying and logging into Open Archiver, the next step is to configure your ingestion sources to start archiving emails.
+
+- [Connecting to Google Workspace](./email-providers/google-workspace.md)
+- [Connecting to Microsoft 365](./email-providers/microsoft-365.md)
+- [Connecting to a Generic IMAP Server](./email-providers/imap.md)
+
+## Updating Your Installation
+
+To update your Open Archiver instance to the latest version, run the following commands:
+
+```bash
+# Pull the latest changes from the repository
+git pull
+
+# Pull the latest Docker images
+docker compose pull
+
+# Restart the services with the new images
+docker compose up -d
+```
+
+## Deploying on Coolify
+
+If you are deploying Open Archiver on [Coolify](https://coolify.io/), it is recommended to let Coolify manage the Docker networks for you. This can help avoid potential routing conflicts and simplify your setup.
+
+To do this, you will need to make a small modification to your `docker-compose.yml` file.
+
+### Modify `docker-compose.yml` for Coolify
+
+1.  **Open your `docker-compose.yml` file** in a text editor.
+
+2.  **Remove all `networks` sections** from the file. This includes the network configuration for each service and the top-level network definition.
+
+    Specifically, you need to remove:
+    - The `networks: - open-archiver-net` lines from the `open-archiver`, `postgres`, `valkey`, and `meilisearch` services.
+    - The entire `networks:` block at the end of the file.
+
+    Here is an example of what to remove from a service:
+
+    ```diff
+    services:
+      open-archiver:
+        image: logiclabshq/open-archiver:latest
+        # ... other settings
+    -   networks:
+    -     - open-archiver-net
+    ```
+
+    And remove this entire block from the end of the file:
+
+    ```diff
+    - networks:
+    -   open-archiver-net:
+    -     driver: bridge
+    ```
+
+3.  **Save the modified `docker-compose.yml` file.**
+
+By removing these sections, you allow Coolify to automatically create and manage the necessary networks, ensuring that all services can communicate with each other and are correctly exposed through Coolify's reverse proxy.
+
+After making these changes, you can proceed with deploying your application on Coolify as you normally would.
+
+## Where is my data stored (When using local storage and Docker)?
+
+If you are using local storage to store your emails, based on your `docker-compose.yml` file, your data is being stored in what's called a "named volume" (`archiver-data`). That's why you're not seeing the files in the `./data/open-archiver` directory you created.
+
+1.  **List all Docker volumes**:
+
+Run this command to see all the volumes on your system:
+
+    ```bash
+    docker volume ls
+    ```
+
+2.  **Identify the correct volume**:
+
+Look through the list for a volume name that ends with `_archiver-data`. The part before that will be your project's directory name. For example, if your project is in a folder named `OpenArchiver`, the volume will be `openarchiver_archiver-data` But it can be a randomly generated hash.
+
+3.  **Inspect the correct volume**:
+
+Once you've identified the correct volume name, use it in the `inspect` command. For example:
+
+    ```bash
+    docker volume inspect <your_volume_name_here>
+    ```
+
+This will give you the correct `Mountpoint` path where your data is being stored. It will look something like this (the exact path will vary depending on your system):
+
+    ```json
+    {
+        "CreatedAt": "2025-07-25T11:22:19Z",
+        "Driver": "local",
+        "Labels": {
+            "com.docker.compose.config-hash": "---",
+            "com.docker.compose.project": "---",
+            "com.docker.compose.version": "2.38.2",
+            "com.docker.compose.volume": "us8wwos0o4ok4go4gc8cog84_archiver-data"
+        },
+        "Mountpoint": "/var/lib/docker/volumes/us8wwos0o4ok4go4gc8cog84_archiver-data/_data",
+        "Name": "us8wwos0o4ok4go4gc8cog84_archiver-data",
+        "Options": null,
+        "Scope": "local"
+    }
+    ```
+
+In this example, the data is located at `/var/lib/docker/volumes/us8wwos0o4ok4go4gc8cog84_archiver-data/_data`. You can then `cd` into that directory to see your files.
+
+### To save data to a specific folder
+
+To save the data to a specific folder on your machine, you'll need to make a change to your `docker-compose.yml`. You need to switch from a named volume to a "bind mount".
+
+Here’s how you can do it:
+
+1.  **Edit `docker-compose.yml`**:
+
+Open the `docker-compose.yml` file and find the `open-archiver` service. You're going to change the `volumes` section.
+
+    **Change this:**
+
+    ```yaml
+    services:
+      open-archiver:
+        # ... other config
+        volumes:
+          - archiver-data:/var/data/open-archiver
+    ```
+
+    **To this:**
+
+    ```yaml
+    services:
+      open-archiver:
+        # ... other config
+        volumes:
+          - ./data/open-archiver:/var/data/open-archiver
+    ```
+
+You'll also want to remove the `archiver-data` volume definition at the bottom of the file, since it's no longer needed.
+
+    **Remove this whole block:**
+
+    ```yaml
+    volumes:
+      # ... other volumes
+      archiver-data:
+          driver: local
+    ```
+
+2.  **Restart your containers**:
+
+After you've saved the changes, run the following command in your terminal to apply them. The `--force-recreate` flag will ensure the container is recreated with the new volume settings.
+
+    ```bash
+    docker-compose up -d --force-recreate
+    ```
+
+After this, any new data will be saved directly into the `./data/open-archiver` folder in your project directory.

package.json

@@ -1,32 +1,41 @@
 {
-    "name": "open-archiver",
-    "private": true,
-    "scripts": {
-        "dev": "dotenv -- pnpm --filter \"./packages/*\" --parallel dev",
-        "build": "pnpm --filter \"./packages/*\" --parallel build",
-        "start": "dotenv -- pnpm --filter \"./packages/*\" --parallel start",
-        "start:workers": "dotenv -- concurrently \"pnpm --filter @open-archiver/backend start:ingestion-worker\" \"pnpm --filter @open-archiver/backend start:indexing-worker\" \"pnpm --filter @open-archiver/backend start:sync-scheduler\"",
-        "start:workers:dev": "dotenv -- concurrently \"pnpm --filter @open-archiver/backend start:ingestion-worker:dev\" \"pnpm --filter @open-archiver/backend start:indexing-worker:dev\" \"pnpm --filter @open-archiver/backend start:sync-scheduler:dev\"",
-        "db:generate": "dotenv -- pnpm --filter @open-archiver/backend db:generate",
-        "db:migrate": "dotenv -- pnpm --filter @open-archiver/backend db:migrate",
-        "db:migrate:dev": "dotenv -- pnpm --filter @open-archiver/backend db:migrate:dev",
-        "docker-start": "pnpm db:migrate && concurrently \"pnpm start:workers\" \"pnpm start\""
-    },
-    "dependencies": {
-        "concurrently": "^9.2.0",
-        "dotenv-cli": "8.0.0"
-    },
-    "devDependencies": {
-        "typescript": "5.8.3"
-    },
-    "packageManager": "pnpm@10.13.1",
-    "engines": {
-        "node": ">=22.0.0",
-        "pnpm": "10.13.1"
-    },
-    "pnpm": {
-        "onlyBuiltDependencies": [
-            "esbuild"
-        ]
-    }
+	"name": "open-archiver",
+	"private": true,
+	"scripts": {
+		"dev": "dotenv -- pnpm --filter \"./packages/*\" --parallel dev",
+		"build": "pnpm --filter \"./packages/*\" build",
+		"start": "dotenv -- pnpm --filter \"./packages/*\" --parallel start",
+		"start:workers": "dotenv -- concurrently \"pnpm --filter @open-archiver/backend start:ingestion-worker\" \"pnpm --filter @open-archiver/backend start:indexing-worker\" \"pnpm --filter @open-archiver/backend start:sync-scheduler\"",
+		"start:workers:dev": "dotenv -- concurrently \"pnpm --filter @open-archiver/backend start:ingestion-worker:dev\" \"pnpm --filter @open-archiver/backend start:indexing-worker:dev\" \"pnpm --filter @open-archiver/backend start:sync-scheduler:dev\"",
+		"db:generate": "dotenv -- pnpm --filter @open-archiver/backend db:generate",
+		"db:migrate": "dotenv -- pnpm --filter @open-archiver/backend db:migrate",
+		"db:migrate:dev": "dotenv -- pnpm --filter @open-archiver/backend db:migrate:dev",
+		"docker-start": "concurrently \"pnpm start:workers\" \"pnpm start\"",
+		"docs:dev": "vitepress dev docs --port 3009",
+		"docs:build": "vitepress build docs",
+		"docs:preview": "vitepress preview docs",
+		"format": "prettier --write .",
+		"lint": "prettier --check ."
+	},
+	"dependencies": {
+		"concurrently": "^9.2.0",
+		"dotenv-cli": "8.0.0"
+	},
+	"devDependencies": {
+		"prettier": "^3.6.2",
+		"prettier-plugin-svelte": "^3.4.0",
+		"prettier-plugin-tailwindcss": "^0.6.14",
+		"typescript": "5.8.3",
+		"vitepress": "^1.6.4"
+	},
+	"packageManager": "pnpm@10.13.1",
+	"engines": {
+		"node": ">=22.0.0",
+		"pnpm": "10.13.1"
+	},
+	"pnpm": {
+		"onlyBuiltDependencies": [
+			"esbuild"
+		]
+	}
 }

packages/backend/drizzle.config.ts

@@ -4,16 +4,16 @@ import { config } from 'dotenv';
 config();
 
 if (!process.env.DATABASE_URL) {
-    throw new Error('DATABASE_URL is not set in the .env file');
+	throw new Error('DATABASE_URL is not set in the .env file');
 }
 
 export default defineConfig({
-    schema: './src/database/schema.ts',
-    out: './src/database/migrations',
-    dialect: 'postgresql',
-    dbCredentials: {
-        url: process.env.DATABASE_URL,
-    },
-    verbose: true,
-    strict: true,
+	schema: './src/database/schema.ts',
+	out: './src/database/migrations',
+	dialect: 'postgresql',
+	dbCredentials: {
+		url: process.env.DATABASE_URL,
+	},
+	verbose: true,
+	strict: true,
 });

packages/backend/package.json

@@ -1,65 +1,75 @@
 {
-    "name": "@open-archiver/backend",
-    "version": "0.1.0",
-    "private": true,
-    "main": "dist/index.js",
-    "scripts": {
-        "dev": "ts-node-dev --respawn --transpile-only src/index.ts ",
-        "build": "tsc",
-        "start": "node dist/index.js",
-        "start:ingestion-worker": "node dist/workers/ingestion.worker.js",
-        "start:indexing-worker": "node dist/workers/indexing.worker.js",
-        "start:sync-scheduler": "node dist/jobs/schedulers/sync-scheduler.js",
-        "start:ingestion-worker:dev": "ts-node-dev --respawn --transpile-only src/workers/ingestion.worker.ts",
-        "start:indexing-worker:dev": "ts-node-dev --respawn --transpile-only src/workers/indexing.worker.ts",
-        "start:sync-scheduler:dev": "ts-node-dev --respawn --transpile-only src/jobs/schedulers/sync-scheduler.ts",
-        "db:generate": "drizzle-kit generate --config=drizzle.config.ts",
-        "db:push": "drizzle-kit push --config=drizzle.config.ts",
-        "db:migrate": "node dist/database/migrate.js",
-        "db:migrate:dev": "ts-node-dev src/database/migrate.ts"
-    },
-    "dependencies": {
-        "drizzle-kit": "^0.31.4",
-        "@aws-sdk/client-s3": "^3.844.0",
-        "@aws-sdk/lib-storage": "^3.844.0",
-        "@azure/msal-node": "^3.6.3",
-        "@microsoft/microsoft-graph-client": "^3.0.7",
-        "@open-archiver/types": "workspace:*",
-        "axios": "^1.10.0",
-        "bcryptjs": "^3.0.2",
-        "bullmq": "^5.56.3",
-        "cross-fetch": "^4.1.0",
-        "deepmerge-ts": "^7.1.5",
-        "dotenv": "^17.2.0",
-        "drizzle-orm": "^0.44.2",
-        "express": "^5.1.0",
-        "express-validator": "^7.2.1",
-        "google-auth-library": "^10.1.0",
-        "googleapis": "^152.0.0",
-        "imapflow": "^1.0.191",
-        "jose": "^6.0.11",
-        "mailparser": "^3.7.4",
-        "mammoth": "^1.9.1",
-        "meilisearch": "^0.51.0",
-        "pdf2json": "^3.1.6",
-        "pg": "^8.16.3",
-        "pino": "^9.7.0",
-        "pino-pretty": "^13.0.0",
-        "postgres": "^3.4.7",
-        "reflect-metadata": "^0.2.2",
-        "sqlite3": "^5.1.7",
-        "tsconfig-paths": "^4.2.0",
-        "xlsx": "^0.18.5"
-    },
-    "devDependencies": {
-        "@bull-board/api": "^6.11.0",
-        "@bull-board/express": "^6.11.0",
-        "@types/express": "^5.0.3",
-        "@types/mailparser": "^3.4.6",
-        "@types/microsoft-graph": "^2.40.1",
-        "@types/node": "^24.0.12",
-        "bull-board": "^2.1.3",
-        "ts-node-dev": "^2.0.0",
-        "typescript": "^5.8.3"
-    }
+	"name": "@open-archiver/backend",
+	"version": "0.1.0",
+	"private": true,
+	"main": "dist/index.js",
+	"scripts": {
+		"dev": "ts-node-dev --respawn --transpile-only src/index.ts ",
+		"build": "tsc",
+		"start": "node dist/index.js",
+		"start:ingestion-worker": "node dist/workers/ingestion.worker.js",
+		"start:indexing-worker": "node dist/workers/indexing.worker.js",
+		"start:sync-scheduler": "node dist/jobs/schedulers/sync-scheduler.js",
+		"start:ingestion-worker:dev": "ts-node-dev --respawn --transpile-only src/workers/ingestion.worker.ts",
+		"start:indexing-worker:dev": "ts-node-dev --respawn --transpile-only src/workers/indexing.worker.ts",
+		"start:sync-scheduler:dev": "ts-node-dev --respawn --transpile-only src/jobs/schedulers/sync-scheduler.ts",
+		"db:generate": "drizzle-kit generate --config=drizzle.config.ts",
+		"db:push": "drizzle-kit push --config=drizzle.config.ts",
+		"db:migrate": "node dist/database/migrate.js",
+		"db:migrate:dev": "ts-node-dev src/database/migrate.ts"
+	},
+	"dependencies": {
+		"@aws-sdk/client-s3": "^3.844.0",
+		"@aws-sdk/lib-storage": "^3.844.0",
+		"@azure/msal-node": "^3.6.3",
+		"@microsoft/microsoft-graph-client": "^3.0.7",
+		"@open-archiver/types": "workspace:*",
+		"archiver": "^7.0.1",
+		"axios": "^1.10.0",
+		"bcryptjs": "^3.0.2",
+		"bullmq": "^5.56.3",
+		"busboy": "^1.6.0",
+		"cross-fetch": "^4.1.0",
+		"deepmerge-ts": "^7.1.5",
+		"dotenv": "^17.2.0",
+		"drizzle-kit": "^0.31.4",
+		"drizzle-orm": "^0.44.2",
+		"express": "^5.1.0",
+		"express-rate-limit": "^8.0.1",
+		"express-validator": "^7.2.1",
+		"google-auth-library": "^10.1.0",
+		"googleapis": "^152.0.0",
+		"imapflow": "^1.0.191",
+		"jose": "^6.0.11",
+		"mailparser": "^3.7.4",
+		"mammoth": "^1.9.1",
+		"meilisearch": "^0.51.0",
+		"multer": "^2.0.2",
+		"pdf2json": "^3.1.6",
+		"pg": "^8.16.3",
+		"pino": "^9.7.0",
+		"pino-pretty": "^13.0.0",
+		"postgres": "^3.4.7",
+		"pst-extractor": "^1.11.0",
+		"reflect-metadata": "^0.2.2",
+		"sqlite3": "^5.1.7",
+		"tsconfig-paths": "^4.2.0",
+		"xlsx": "^0.18.5",
+		"yauzl": "^3.2.0"
+	},
+	"devDependencies": {
+		"@bull-board/api": "^6.11.0",
+		"@bull-board/express": "^6.11.0",
+		"@types/archiver": "^6.0.3",
+		"@types/busboy": "^1.5.4",
+		"@types/express": "^5.0.3",
+		"@types/mailparser": "^3.4.6",
+		"@types/microsoft-graph": "^2.40.1",
+		"@types/multer": "^2.0.0",
+		"@types/node": "^24.0.12",
+		"@types/yauzl": "^2.10.3",
+		"bull-board": "^2.1.3",
+		"ts-node-dev": "^2.0.0",
+		"typescript": "^5.8.3"
+	}
 }

packages/backend/src/api/controllers/archived-email.controller.ts

@@ -1,36 +1,57 @@
 import { Request, Response } from 'express';
 import { ArchivedEmailService } from '../../services/ArchivedEmailService';
+import { config } from '../../config';
 
 export class ArchivedEmailController {
-    public getArchivedEmails = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { ingestionSourceId } = req.params;
-            const page = parseInt(req.query.page as string, 10) || 1;
-            const limit = parseInt(req.query.limit as string, 10) || 10;
+	public getArchivedEmails = async (req: Request, res: Response): Promise<Response> => {
+		try {
+			const { ingestionSourceId } = req.params;
+			const page = parseInt(req.query.page as string, 10) || 1;
+			const limit = parseInt(req.query.limit as string, 10) || 10;
 
-            const result = await ArchivedEmailService.getArchivedEmails(
-                ingestionSourceId,
-                page,
-                limit
-            );
-            return res.status(200).json(result);
-        } catch (error) {
-            console.error('Get archived emails error:', error);
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+			const result = await ArchivedEmailService.getArchivedEmails(
+				ingestionSourceId,
+				page,
+				limit
+			);
+			return res.status(200).json(result);
+		} catch (error) {
+			console.error('Get archived emails error:', error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-    public getArchivedEmailById = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            const email = await ArchivedEmailService.getArchivedEmailById(id);
-            if (!email) {
-                return res.status(404).json({ message: 'Archived email not found' });
-            }
-            return res.status(200).json(email);
-        } catch (error) {
-            console.error(`Get archived email by id ${req.params.id} error:`, error);
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public getArchivedEmailById = async (req: Request, res: Response): Promise<Response> => {
+		try {
+			const { id } = req.params;
+			const email = await ArchivedEmailService.getArchivedEmailById(id);
+			if (!email) {
+				return res.status(404).json({ message: 'Archived email not found' });
+			}
+			return res.status(200).json(email);
+		} catch (error) {
+			console.error(`Get archived email by id ${req.params.id} error:`, error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
+
+	public deleteArchivedEmail = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			await ArchivedEmailService.deleteArchivedEmail(id);
+			return res.status(204).send();
+		} catch (error) {
+			console.error(`Delete archived email ${req.params.id} error:`, error);
+			if (error instanceof Error) {
+				if (error.message === 'Archived email not found') {
+					return res.status(404).json({ message: error.message });
+				}
+				return res.status(500).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 }

packages/backend/src/api/controllers/auth.controller.ts

@@ -1,32 +1,99 @@
 import type { Request, Response } from 'express';
-import type { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
+import { UserService } from '../../services/UserService';
+import { db } from '../../database';
+import * as schema from '../../database/schema';
+import { sql } from 'drizzle-orm';
+import 'dotenv/config';
 
 export class AuthController {
-    #authService: IAuthService;
+	#authService: AuthService;
+	#userService: UserService;
 
-    constructor(authService: IAuthService) {
-        this.#authService = authService;
-    }
+	constructor(authService: AuthService, userService: UserService) {
+		this.#authService = authService;
+		this.#userService = userService;
+	}
+	/**
+	 * Only used for setting up the instance, should only be displayed once upon instance set up.
+	 * @param req
+	 * @param res
+	 * @returns
+	 */
+	public setup = async (req: Request, res: Response): Promise<Response> => {
+		const { email, password, first_name, last_name } = req.body;
 
-    public login = async (req: Request, res: Response): Promise<Response> => {
-        const { email, password } = req.body;
+		if (!email || !password || !first_name || !last_name) {
+			return res.status(400).json({ message: 'Email, password, and name are required' });
+		}
 
-        if (!email || !password) {
-            return res.status(400).json({ message: 'Email and password are required' });
-        }
+		try {
+			const userCountResult = await db
+				.select({ count: sql<number>`count(*)` })
+				.from(schema.users);
+			const userCount = Number(userCountResult[0].count);
 
-        try {
-            const result = await this.#authService.login(email, password);
+			if (userCount > 0) {
+				return res.status(403).json({ message: 'Setup has already been completed.' });
+			}
 
-            if (!result) {
-                return res.status(401).json({ message: 'Invalid credentials' });
-            }
+			const newUser = await this.#userService.createAdminUser(
+				{ email, password, first_name, last_name },
+				true
+			);
+			const result = await this.#authService.login(email, password);
+			return res.status(201).json(result);
+		} catch (error) {
+			console.error('Setup error:', error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-            return res.status(200).json(result);
-        } catch (error) {
-            // In a real application, you'd want to log this error.
-            console.error('Login error:', error);
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public login = async (req: Request, res: Response): Promise<Response> => {
+		const { email, password } = req.body;
+
+		if (!email || !password) {
+			return res.status(400).json({ message: 'Email and password are required' });
+		}
+
+		try {
+			const result = await this.#authService.login(email, password);
+
+			if (!result) {
+				return res.status(401).json({ message: 'Invalid credentials' });
+			}
+
+			return res.status(200).json(result);
+		} catch (error) {
+			console.error('Login error:', error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
+
+	public status = async (req: Request, res: Response): Promise<Response> => {
+		try {
+			const userCountResult = await db
+				.select({ count: sql<number>`count(*)` })
+				.from(schema.users);
+			const userCount = Number(userCountResult[0].count);
+			const needsSetup = userCount === 0;
+			// in case user uses older version with admin user variables, we will create the admin user using those variables.
+			if (needsSetup && process.env.ADMIN_EMAIL && process.env.ADMIN_PASSWORD) {
+				await this.#userService.createAdminUser(
+					{
+						email: process.env.ADMIN_EMAIL,
+						password: process.env.ADMIN_PASSWORD,
+						first_name: 'Admin',
+						last_name: 'User',
+					},
+					true
+				);
+				return res.status(200).json({ needsSetup: false });
+			}
+			return res.status(200).json({ needsSetup });
+		} catch (error) {
+			console.error('Status check error:', error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 }

packages/backend/src/api/controllers/dashboard.controller.ts

@@ -2,30 +2,30 @@ import { Request, Response } from 'express';
 import { dashboardService } from '../../services/DashboardService';
 
 class DashboardController {
-    public async getStats(req: Request, res: Response) {
-        const stats = await dashboardService.getStats();
-        res.json(stats);
-    }
+	public async getStats(req: Request, res: Response) {
+		const stats = await dashboardService.getStats();
+		res.json(stats);
+	}
 
-    public async getIngestionHistory(req: Request, res: Response) {
-        const history = await dashboardService.getIngestionHistory();
-        res.json(history);
-    }
+	public async getIngestionHistory(req: Request, res: Response) {
+		const history = await dashboardService.getIngestionHistory();
+		res.json(history);
+	}
 
-    public async getIngestionSources(req: Request, res: Response) {
-        const sources = await dashboardService.getIngestionSources();
-        res.json(sources);
-    }
+	public async getIngestionSources(req: Request, res: Response) {
+		const sources = await dashboardService.getIngestionSources();
+		res.json(sources);
+	}
 
-    public async getRecentSyncs(req: Request, res: Response) {
-        const syncs = await dashboardService.getRecentSyncs();
-        res.json(syncs);
-    }
+	public async getRecentSyncs(req: Request, res: Response) {
+		const syncs = await dashboardService.getRecentSyncs();
+		res.json(syncs);
+	}
 
-    public async getIndexedInsights(req: Request, res: Response) {
-        const insights = await dashboardService.getIndexedInsights();
-        res.json(insights);
-    }
+	public async getIndexedInsights(req: Request, res: Response) {
+		const insights = await dashboardService.getIndexedInsights();
+		res.json(insights);
+	}
 }
 
 export const dashboardController = new DashboardController();

packages/backend/src/api/controllers/iam.controller.ts

@@ -0,0 +1,71 @@
+import { Request, Response } from 'express';
+import { IamService } from '../../services/IamService';
+import { PolicyValidator } from '../../iam-policy/policy-validator';
+import type { PolicyStatement } from '@open-archiver/types';
+
+export class IamController {
+	#iamService: IamService;
+
+	constructor(iamService: IamService) {
+		this.#iamService = iamService;
+	}
+
+	public getRoles = async (req: Request, res: Response): Promise<void> => {
+		try {
+			const roles = await this.#iamService.getRoles();
+			res.status(200).json(roles);
+		} catch (error) {
+			res.status(500).json({ error: 'Failed to get roles.' });
+		}
+	};
+
+	public getRoleById = async (req: Request, res: Response): Promise<void> => {
+		const { id } = req.params;
+
+		try {
+			const role = await this.#iamService.getRoleById(id);
+			if (role) {
+				res.status(200).json(role);
+			} else {
+				res.status(404).json({ error: 'Role not found.' });
+			}
+		} catch (error) {
+			res.status(500).json({ error: 'Failed to get role.' });
+		}
+	};
+
+	public createRole = async (req: Request, res: Response): Promise<void> => {
+		const { name, policy } = req.body;
+
+		if (!name || !policy) {
+			res.status(400).json({ error: 'Missing required fields: name and policy.' });
+			return;
+		}
+
+		for (const statement of policy) {
+			const { valid, reason } = PolicyValidator.isValid(statement as PolicyStatement);
+			if (!valid) {
+				res.status(400).json({ error: `Invalid policy statement: ${reason}` });
+				return;
+			}
+		}
+
+		try {
+			const role = await this.#iamService.createRole(name, policy);
+			res.status(201).json(role);
+		} catch (error) {
+			res.status(500).json({ error: 'Failed to create role.' });
+		}
+	};
+
+	public deleteRole = async (req: Request, res: Response): Promise<void> => {
+		const { id } = req.params;
+
+		try {
+			await this.#iamService.deleteRole(id);
+			res.status(204).send();
+		} catch (error) {
+			res.status(500).json({ error: 'Failed to delete role.' });
+		}
+	};
+}

packages/backend/src/api/controllers/ingestion.controller.ts

@@ -1,97 +1,156 @@
 import { Request, Response } from 'express';
 import { IngestionService } from '../../services/IngestionService';
-import { CreateIngestionSourceDto, UpdateIngestionSourceDto } from '@open-archiver/types';
+import {
+	CreateIngestionSourceDto,
+	UpdateIngestionSourceDto,
+	IngestionSource,
+	SafeIngestionSource,
+} from '@open-archiver/types';
+import { logger } from '../../config/logger';
+import { config } from '../../config';
 
 export class IngestionController {
-    public create = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const dto: CreateIngestionSourceDto = req.body;
-            const newSource = await IngestionService.create(dto);
-            return res.status(201).json(newSource);
-        } catch (error) {
-            console.error('Create ingestion source error:', error);
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	/**
+	 * Converts an IngestionSource object to a safe version for client-side consumption
+	 * by removing the credentials.
+	 * @param source The full IngestionSource object.
+	 * @returns An object conforming to the SafeIngestionSource type.
+	 */
+	private toSafeIngestionSource(source: IngestionSource): SafeIngestionSource {
+		const { credentials, ...safeSource } = source;
+		return safeSource;
+	}
 
-    public findAll = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const sources = await IngestionService.findAll();
-            return res.status(200).json(sources);
-        } catch (error) {
-            console.error('Find all ingestion sources error:', error);
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public create = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const dto: CreateIngestionSourceDto = req.body;
+			const newSource = await IngestionService.create(dto);
+			const safeSource = this.toSafeIngestionSource(newSource);
+			return res.status(201).json(safeSource);
+		} catch (error: any) {
+			logger.error({ err: error }, 'Create ingestion source error');
+			// Return a 400 Bad Request for connection errors
+			return res.status(400).json({
+				message:
+					error.message || 'Failed to create ingestion source due to a connection error.',
+			});
+		}
+	};
 
-    public findById = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            const source = await IngestionService.findById(id);
-            return res.status(200).json(source);
-        } catch (error) {
-            console.error(`Find ingestion source by id ${req.params.id} error:`, error);
-            if (error instanceof Error && error.message === 'Ingestion source not found') {
-                return res.status(404).json({ message: error.message });
-            }
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public findAll = async (req: Request, res: Response): Promise<Response> => {
+		try {
+			const sources = await IngestionService.findAll();
+			const safeSources = sources.map(this.toSafeIngestionSource);
+			return res.status(200).json(safeSources);
+		} catch (error) {
+			console.error('Find all ingestion sources error:', error);
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-    public update = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            const dto: UpdateIngestionSourceDto = req.body;
-            const updatedSource = await IngestionService.update(id, dto);
-            return res.status(200).json(updatedSource);
-        } catch (error) {
-            console.error(`Update ingestion source ${req.params.id} error:`, error);
-            if (error instanceof Error && error.message === 'Ingestion source not found') {
-                return res.status(404).json({ message: error.message });
-            }
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public findById = async (req: Request, res: Response): Promise<Response> => {
+		try {
+			const { id } = req.params;
+			const source = await IngestionService.findById(id);
+			const safeSource = this.toSafeIngestionSource(source);
+			return res.status(200).json(safeSource);
+		} catch (error) {
+			console.error(`Find ingestion source by id ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-    public delete = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            await IngestionService.delete(id);
-            return res.status(204).send();
-        } catch (error) {
-            console.error(`Delete ingestion source ${req.params.id} error:`, error);
-            if (error instanceof Error && error.message === 'Ingestion source not found') {
-                return res.status(404).json({ message: error.message });
-            }
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public update = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			const dto: UpdateIngestionSourceDto = req.body;
+			const updatedSource = await IngestionService.update(id, dto);
+			const safeSource = this.toSafeIngestionSource(updatedSource);
+			return res.status(200).json(safeSource);
+		} catch (error) {
+			console.error(`Update ingestion source ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-    public triggerInitialImport = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            await IngestionService.triggerInitialImport(id);
-            return res.status(202).json({ message: 'Initial import triggered successfully.' });
-        } catch (error) {
-            console.error(`Trigger initial import for ${req.params.id} error:`, error);
-            if (error instanceof Error && error.message === 'Ingestion source not found') {
-                return res.status(404).json({ message: error.message });
-            }
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public delete = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			await IngestionService.delete(id);
+			return res.status(204).send();
+		} catch (error) {
+			console.error(`Delete ingestion source ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 
-    public pause = async (req: Request, res: Response): Promise<Response> => {
-        try {
-            const { id } = req.params;
-            const updatedSource = await IngestionService.update(id, { status: 'paused' });
-            return res.status(200).json(updatedSource);
-        } catch (error) {
-            console.error(`Pause ingestion source ${req.params.id} error:`, error);
-            if (error instanceof Error && error.message === 'Ingestion source not found') {
-                return res.status(404).json({ message: error.message });
-            }
-            return res.status(500).json({ message: 'An internal server error occurred' });
-        }
-    };
+	public triggerInitialImport = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			await IngestionService.triggerInitialImport(id);
+			return res.status(202).json({ message: 'Initial import triggered successfully.' });
+		} catch (error) {
+			console.error(`Trigger initial import for ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
+
+	public pause = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			const updatedSource = await IngestionService.update(id, { status: 'paused' });
+			const safeSource = this.toSafeIngestionSource(updatedSource);
+			return res.status(200).json(safeSource);
+		} catch (error) {
+			console.error(`Pause ingestion source ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
+
+	public triggerForceSync = async (req: Request, res: Response): Promise<Response> => {
+		if (config.app.isDemo) {
+			return res.status(403).json({ message: 'This operation is not allowed in demo mode.' });
+		}
+		try {
+			const { id } = req.params;
+			await IngestionService.triggerForceSync(id);
+			return res.status(202).json({ message: 'Force sync triggered successfully.' });
+		} catch (error) {
+			console.error(`Trigger force sync for ${req.params.id} error:`, error);
+			if (error instanceof Error && error.message === 'Ingestion source not found') {
+				return res.status(404).json({ message: error.message });
+			}
+			return res.status(500).json({ message: 'An internal server error occurred' });
+		}
+	};
 }

packages/backend/src/api/controllers/search.controller.ts

@@ -3,32 +3,32 @@ import { SearchService } from '../../services/SearchService';
 import { MatchingStrategies } from 'meilisearch';
 
 export class SearchController {
-    private searchService: SearchService;
+	private searchService: SearchService;
 
-    constructor() {
-        this.searchService = new SearchService();
-    }
+	constructor() {
+		this.searchService = new SearchService();
+	}
 
-    public search = async (req: Request, res: Response): Promise<void> => {
-        try {
-            const { keywords, page, limit, matchingStrategy } = req.query;
+	public search = async (req: Request, res: Response): Promise<void> => {
+		try {
+			const { keywords, page, limit, matchingStrategy } = req.query;
 
-            if (!keywords) {
-                res.status(400).json({ message: 'Keywords are required' });
-                return;
-            }
+			if (!keywords) {
+				res.status(400).json({ message: 'Keywords are required' });
+				return;
+			}
 
-            const results = await this.searchService.searchEmails({
-                query: keywords as string,
-                page: page ? parseInt(page as string) : 1,
-                limit: limit ? parseInt(limit as string) : 10,
-                matchingStrategy: matchingStrategy as MatchingStrategies
-            });
+			const results = await this.searchService.searchEmails({
+				query: keywords as string,
+				page: page ? parseInt(page as string) : 1,
+				limit: limit ? parseInt(limit as string) : 10,
+				matchingStrategy: matchingStrategy as MatchingStrategies,
+			});
 
-            res.status(200).json(results);
-        } catch (error) {
-            const message = error instanceof Error ? error.message : 'An unknown error occurred';
-            res.status(500).json({ message });
-        }
-    };
+			res.status(200).json(results);
+		} catch (error) {
+			const message = error instanceof Error ? error.message : 'An unknown error occurred';
+			res.status(500).json({ message });
+		}
+	};
 }

packages/backend/src/api/controllers/storage.controller.ts

@@ -1,32 +1,50 @@
 import { Request, Response } from 'express';
 import { StorageService } from '../../services/StorageService';
+import * as path from 'path';
+import { storage as storageConfig } from '../../config/storage';
 
 export class StorageController {
-    constructor(private storageService: StorageService) { }
+	constructor(private storageService: StorageService) {}
 
-    public downloadFile = async (req: Request, res: Response): Promise<void> => {
-        const filePath = req.query.path as string;
+	public downloadFile = async (req: Request, res: Response): Promise<void> => {
+		const unsafePath = req.query.path as string;
 
-        if (!filePath) {
-            res.status(400).send('File path is required');
-            return;
-        }
+		if (!unsafePath) {
+			res.status(400).send('File path is required');
+			return;
+		}
 
-        try {
-            const fileExists = await this.storageService.exists(filePath);
-            if (!fileExists) {
-                console.log(filePath);
-                res.status(404).send('File not found');
-                return;
-            }
+		// Normalize the path to prevent directory traversal
+		const normalizedPath = path.normalize(unsafePath).replace(/^(\.\.(\/|\\|$))+/, '');
 
-            const fileStream = await this.storageService.get(filePath);
-            const fileName = filePath.split('/').pop();
-            res.setHeader('Content-Disposition', `attachment; filename=${fileName}`);
-            fileStream.pipe(res);
-        } catch (error) {
-            console.error('Error downloading file:', error);
-            res.status(500).send('Error downloading file');
-        }
-    };
+		// Determine the base path from storage configuration
+		const basePath = storageConfig.type === 'local' ? storageConfig.rootPath : '/';
+
+		// Resolve the full path and ensure it's within the storage directory
+		const fullPath = path.join(basePath, normalizedPath);
+
+		if (!fullPath.startsWith(basePath)) {
+			res.status(400).send('Invalid file path');
+			return;
+		}
+
+		// Use the sanitized, relative path for storage service operations
+		const safePath = path.relative(basePath, fullPath);
+
+		try {
+			const fileExists = await this.storageService.exists(safePath);
+			if (!fileExists) {
+				res.status(404).send('File not found');
+				return;
+			}
+
+			const fileStream = await this.storageService.get(safePath);
+			const fileName = path.basename(safePath);
+			res.setHeader('Content-Disposition', `attachment; filename="${fileName}"`);
+			fileStream.pipe(res);
+		} catch (error) {
+			console.error('Error downloading file:', error);
+			res.status(500).send('Error downloading file');
+		}
+	};
 }

packages/backend/src/api/controllers/upload.controller.ts

@@ -0,0 +1,25 @@
+import { Request, Response } from 'express';
+import { StorageService } from '../../services/StorageService';
+import { randomUUID } from 'crypto';
+import busboy from 'busboy';
+import { config } from '../../config/index';
+
+export const uploadFile = async (req: Request, res: Response) => {
+	const storage = new StorageService();
+	const bb = busboy({ headers: req.headers });
+	let filePath = '';
+	let originalFilename = '';
+
+	bb.on('file', (fieldname, file, filename) => {
+		originalFilename = filename.filename;
+		const uuid = randomUUID();
+		filePath = `${config.storage.openArchiverFolderName}/tmp/${uuid}-${originalFilename}`;
+		storage.put(filePath, file);
+	});
+
+	bb.on('finish', () => {
+		res.json({ filePath });
+	});
+
+	req.pipe(bb);
+};

packages/backend/src/api/middleware/rateLimiter.ts

@@ -0,0 +1,10 @@
+import rateLimit from 'express-rate-limit';
+
+// Rate limiter to prevent brute-force attacks on the login endpoint
+export const loginRateLimiter = rateLimit({
+	windowMs: 15 * 60 * 1000, // 15 minutes
+	max: 10, // Limit each IP to 10 login requests per windowMs
+	message: 'Too many login attempts from this IP, please try again after 15 minutes',
+	standardHeaders: true, // Return rate limit info in the `RateLimit-*` headers
+	legacyHeaders: false, // Disable the `X-RateLimit-*` headers
+});

packages/backend/src/api/middleware/requireAuth.ts

@@ -1,39 +1,41 @@
 import type { Request, Response, NextFunction } from 'express';
-import type { IAuthService } from '../../services/AuthService';
+import type { AuthService } from '../../services/AuthService';
 import type { AuthTokenPayload } from '@open-archiver/types';
 import 'dotenv/config';
 // By using module augmentation, we can add our custom 'user' property
 // to the Express Request interface in a type-safe way.
 declare global {
-    namespace Express {
-        export interface Request {
-            user?: AuthTokenPayload;
-        }
-    }
+	namespace Express {
+		export interface Request {
+			user?: AuthTokenPayload;
+		}
+	}
 }
 
-export const requireAuth = (authService: IAuthService) => {
-    return async (req: Request, res: Response, next: NextFunction) => {
-        const authHeader = req.headers.authorization;
-        if (!authHeader || !authHeader.startsWith('Bearer ')) {
-            return res.status(401).json({ message: 'Unauthorized: No token provided' });
-        }
-        const token = authHeader.split(' ')[1];
-        try {
-            // use a SUPER_API_KEY for all authentications.
-            if (token === process.env.SUPER_API_KEY) {
-                next();
-                return;
-            }
-            const payload = await authService.verifyToken(token);
-            if (!payload) {
-                return res.status(401).json({ message: 'Unauthorized: Invalid token' });
-            }
-            req.user = payload;
-            next();
-        } catch (error) {
-            console.error('Authentication error:', error);
-            return res.status(500).json({ message: 'An internal server error occurred during authentication' });
-        }
-    };
+export const requireAuth = (authService: AuthService) => {
+	return async (req: Request, res: Response, next: NextFunction) => {
+		const authHeader = req.headers.authorization;
+		if (!authHeader || !authHeader.startsWith('Bearer ')) {
+			return res.status(401).json({ message: 'Unauthorized: No token provided' });
+		}
+		const token = authHeader.split(' ')[1];
+		try {
+			// use a SUPER_API_KEY for all authentications. add process.env.SUPER_API_KEY conditional check in case user didn't set a SUPER_API_KEY.
+			if (process.env.SUPER_API_KEY && token === process.env.SUPER_API_KEY) {
+				next();
+				return;
+			}
+			const payload = await authService.verifyToken(token);
+			if (!payload) {
+				return res.status(401).json({ message: 'Unauthorized: Invalid token' });
+			}
+			req.user = payload;
+			next();
+		} catch (error) {
+			console.error('Authentication error:', error);
+			return res
+				.status(500)
+				.json({ message: 'An internal server error occurred during authentication' });
+		}
+	};
 };

packages/backend/src/api/routes/archived-email.routes.ts

@@ -1,20 +1,22 @@
 import { Router } from 'express';
 import { ArchivedEmailController } from '../controllers/archived-email.controller';
 import { requireAuth } from '../middleware/requireAuth';
-import { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
 
 export const createArchivedEmailRouter = (
-    archivedEmailController: ArchivedEmailController,
-    authService: IAuthService
+	archivedEmailController: ArchivedEmailController,
+	authService: AuthService
 ): Router => {
-    const router = Router();
+	const router = Router();
 
-    // Secure all routes in this module
-    router.use(requireAuth(authService));
+	// Secure all routes in this module
+	router.use(requireAuth(authService));
 
-    router.get('/ingestion-source/:ingestionSourceId', archivedEmailController.getArchivedEmails);
+	router.get('/ingestion-source/:ingestionSourceId', archivedEmailController.getArchivedEmails);
 
-    router.get('/:id', archivedEmailController.getArchivedEmailById);
+	router.get('/:id', archivedEmailController.getArchivedEmailById);
 
-    return router;
+	router.delete('/:id', archivedEmailController.deleteArchivedEmail);
+
+	return router;
 };

packages/backend/src/api/routes/auth.routes.ts

@@ -1,15 +1,30 @@
 import { Router } from 'express';
+import { loginRateLimiter } from '../middleware/rateLimiter';
 import type { AuthController } from '../controllers/auth.controller';
 
 export const createAuthRouter = (authController: AuthController): Router => {
-    const router = Router();
+	const router = Router();
 
-    /**
-     * @route POST /api/v1/auth/login
-     * @description Authenticates a user and returns a JWT.
-     * @access Public
-     */
-    router.post('/login', authController.login);
+	/**
+	 * @route POST /api/v1/auth/setup
+	 * @description Creates the initial administrator user.
+	 * @access Public
+	 */
+	router.post('/setup', loginRateLimiter, authController.setup);
 
-    return router;
+	/**
+	 * @route POST /api/v1/auth/login
+	 * @description Authenticates a user and returns a JWT.
+	 * @access Public
+	 */
+	router.post('/login', loginRateLimiter, authController.login);
+
+	/**
+	 * @route GET /api/v1/auth/status
+	 * @description Checks if the application has been set up.
+	 * @access Public
+	 */
+	router.get('/status', authController.status);
+
+	return router;
 };

packages/backend/src/api/routes/dashboard.routes.ts

@@ -1,18 +1,18 @@
 import { Router } from 'express';
 import { dashboardController } from '../controllers/dashboard.controller';
 import { requireAuth } from '../middleware/requireAuth';
-import { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
 
-export const createDashboardRouter = (authService: IAuthService): Router => {
-    const router = Router();
+export const createDashboardRouter = (authService: AuthService): Router => {
+	const router = Router();
 
-    router.use(requireAuth(authService));
+	router.use(requireAuth(authService));
 
-    router.get('/stats', dashboardController.getStats);
-    router.get('/ingestion-history', dashboardController.getIngestionHistory);
-    router.get('/ingestion-sources', dashboardController.getIngestionSources);
-    router.get('/recent-syncs', dashboardController.getRecentSyncs);
-    router.get('/indexed-insights', dashboardController.getIndexedInsights);
+	router.get('/stats', dashboardController.getStats);
+	router.get('/ingestion-history', dashboardController.getIngestionHistory);
+	router.get('/ingestion-sources', dashboardController.getIngestionSources);
+	router.get('/recent-syncs', dashboardController.getRecentSyncs);
+	router.get('/indexed-insights', dashboardController.getIndexedInsights);
 
-    return router;
+	return router;
 };

packages/backend/src/api/routes/iam.routes.ts

@@ -0,0 +1,36 @@
+import { Router } from 'express';
+import { requireAuth } from '../middleware/requireAuth';
+import type { IamController } from '../controllers/iam.controller';
+
+export const createIamRouter = (iamController: IamController): Router => {
+	const router = Router();
+
+	/**
+	 * @route GET /api/v1/iam/roles
+	 * @description Gets all roles.
+	 * @access Private
+	 */
+	router.get('/roles', requireAuth, iamController.getRoles);
+
+	/**
+	 * @route GET /api/v1/iam/roles/:id
+	 * @description Gets a role by ID.
+	 * @access Private
+	 */
+	router.get('/roles/:id', requireAuth, iamController.getRoleById);
+
+	/**
+	 * @route POST /api/v1/iam/roles
+	 * @description Creates a new role.
+	 * @access Private
+	 */
+	router.post('/roles', requireAuth, iamController.createRole);
+
+	/**
+	 * @route DELETE /api/v1/iam/roles/:id
+	 * @description Deletes a role.
+	 * @access Private
+	 */
+	router.delete('/roles/:id', requireAuth, iamController.deleteRole);
+	return router;
+};

packages/backend/src/api/routes/ingestion.routes.ts

@@ -1,30 +1,32 @@
 import { Router } from 'express';
 import { IngestionController } from '../controllers/ingestion.controller';
 import { requireAuth } from '../middleware/requireAuth';
-import { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
 
 export const createIngestionRouter = (
-    ingestionController: IngestionController,
-    authService: IAuthService
+	ingestionController: IngestionController,
+	authService: AuthService
 ): Router => {
-    const router = Router();
+	const router = Router();
 
-    // Secure all routes in this module
-    router.use(requireAuth(authService));
+	// Secure all routes in this module
+	router.use(requireAuth(authService));
 
-    router.post('/', ingestionController.create);
+	router.post('/', ingestionController.create);
 
-    router.get('/', ingestionController.findAll);
+	router.get('/', ingestionController.findAll);
 
-    router.get('/:id', ingestionController.findById);
+	router.get('/:id', ingestionController.findById);
 
-    router.put('/:id', ingestionController.update);
+	router.put('/:id', ingestionController.update);
 
-    router.delete('/:id', ingestionController.delete);
+	router.delete('/:id', ingestionController.delete);
 
-    router.post('/:id/sync', ingestionController.triggerInitialImport);
+	router.post('/:id/import', ingestionController.triggerInitialImport);
 
-    router.post('/:id/pause', ingestionController.pause);
+	router.post('/:id/pause', ingestionController.pause);
 
-    return router;
+	router.post('/:id/sync', ingestionController.triggerForceSync);
+
+	return router;
 };

packages/backend/src/api/routes/search.routes.ts

@@ -1,17 +1,17 @@
 import { Router } from 'express';
 import { SearchController } from '../controllers/search.controller';
 import { requireAuth } from '../middleware/requireAuth';
-import { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
 
 export const createSearchRouter = (
-    searchController: SearchController,
-    authService: IAuthService
+	searchController: SearchController,
+	authService: AuthService
 ): Router => {
-    const router = Router();
+	const router = Router();
 
-    router.use(requireAuth(authService));
+	router.use(requireAuth(authService));
 
-    router.get('/', searchController.search);
+	router.get('/', searchController.search);
 
-    return router;
+	return router;
 };

packages/backend/src/api/routes/storage.routes.ts

@@ -1,18 +1,18 @@
 import { Router } from 'express';
 import { StorageController } from '../controllers/storage.controller';
 import { requireAuth } from '../middleware/requireAuth';
-import { IAuthService } from '../../services/AuthService';
+import { AuthService } from '../../services/AuthService';
 
 export const createStorageRouter = (
-    storageController: StorageController,
-    authService: IAuthService
+	storageController: StorageController,
+	authService: AuthService
 ): Router => {
-    const router = Router();
+	const router = Router();
 
-    // Secure all routes in this module
-    router.use(requireAuth(authService));
+	// Secure all routes in this module
+	router.use(requireAuth(authService));
 
-    router.get('/download', storageController.downloadFile);
+	router.get('/download', storageController.downloadFile);
 
-    return router;
+	return router;
 };

packages/backend/src/api/routes/test.routes.ts

@@ -3,16 +3,4 @@ import { ingestionQueue } from '../../jobs/queues';
 
 const router: Router = Router();
 
-router.post('/trigger-job', async (req, res) => {
-    try {
-        const job = await ingestionQueue.add('initial-import', {
-            ingestionSourceId: 'test-source-id-test-2345'
-        });
-        res.status(202).json({ message: 'Test job triggered successfully', jobId: job.id });
-    } catch (error) {
-        console.error('Failed to trigger test job', error);
-        res.status(500).json({ message: 'Failed to trigger test job' });
-    }
-});
-
 export default router;

packages/backend/src/api/routes/upload.routes.ts

@@ -0,0 +1,14 @@
+import { Router } from 'express';
+import { uploadFile } from '../controllers/upload.controller';
+import { requireAuth } from '../middleware/requireAuth';
+import { AuthService } from '../../services/AuthService';
+
+export const createUploadRouter = (authService: AuthService): Router => {
+	const router = Router();
+
+	router.use(requireAuth(authService));
+
+	router.post('/', uploadFile);
+
+	return router;
+};

packages/backend/src/config/app.ts

@@ -1,7 +1,9 @@
 import 'dotenv/config';
 
 export const app = {
-    nodeEnv: process.env.NODE_ENV || 'development',
-    port: process.env.PORT_BACKEND ? parseInt(process.env.PORT_BACKEND, 10) : 4000,
-    encryptionKey: process.env.ENCRYPTION_KEY,
+	nodeEnv: process.env.NODE_ENV || 'development',
+	port: process.env.PORT_BACKEND ? parseInt(process.env.PORT_BACKEND, 10) : 4000,
+	encryptionKey: process.env.ENCRYPTION_KEY,
+	isDemo: process.env.IS_DEMO === 'true',
+	syncFrequency: process.env.SYNC_FREQUENCY || '* * * * *', //default to 1 minute
 };

packages/backend/src/config/index.ts

@@ -4,8 +4,8 @@ import { searchConfig } from './search';
 import { connection as redisConfig } from './redis';
 
 export const config = {
-    storage,
-    app,
-    search: searchConfig,
-    redis: redisConfig,
+	storage,
+	app,
+	search: searchConfig,
+	redis: redisConfig,
 };

packages/backend/src/config/logger.ts

@@ -1,11 +1,11 @@
 import pino from 'pino';
 
 export const logger = pino({
-    level: process.env.LOG_LEVEL || 'info',
-    transport: {
-        target: 'pino-pretty',
-        options: {
-            colorize: true
-        }
-    }
+	level: process.env.LOG_LEVEL || 'info',
+	transport: {
+		target: 'pino-pretty',
+		options: {
+			colorize: true,
+		},
+	},
 });

packages/backend/src/config/redis.ts

@@ -3,12 +3,17 @@ import 'dotenv/config';
 /**
  * @see https://github.com/taskforcesh/bullmq/blob/master/docs/gitbook/guide/connections.md
  */
-export const connection = {
-    host: process.env.REDIS_HOST || 'localhost',
-    port: (process.env.REDIS_PORT && parseInt(process.env.REDIS_PORT, 10)) || 6379,
-    password: process.env.REDIS_PASSWORD,
-    maxRetriesPerRequest: null,
-    tls: {
-        rejectUnauthorized: false
-    }
+const connectionOptions: any = {
+	host: process.env.REDIS_HOST || 'localhost',
+	port: (process.env.REDIS_PORT && parseInt(process.env.REDIS_PORT, 10)) || 6379,
+	password: process.env.REDIS_PASSWORD,
+	enableReadyCheck: true,
 };
+
+if (process.env.REDIS_TLS_ENABLED === 'true') {
+	connectionOptions.tls = {
+		rejectUnauthorized: false,
+	};
+}
+
+export const connection = connectionOptions;

packages/backend/src/config/search.ts

@@ -1,6 +1,6 @@
 import 'dotenv/config';
 
 export const searchConfig = {
-    host: process.env.MEILI_HOST || 'http://127.0.0.1:7700',
-    apiKey: process.env.MEILI_MASTER_KEY || '',
+	host: process.env.MEILI_HOST || 'http://127.0.0.1:7700',
+	apiKey: process.env.MEILI_MASTER_KEY || '',
 };

packages/backend/src/config/storage.ts

@@ -2,37 +2,39 @@ import { StorageConfig } from '@open-archiver/types';
 import 'dotenv/config';
 
 const storageType = process.env.STORAGE_TYPE;
-
+const openArchiverFolderName = 'open-archiver';
 let storageConfig: StorageConfig;
 
 if (storageType === 'local') {
-    if (!process.env.STORAGE_LOCAL_ROOT_PATH) {
-        throw new Error('STORAGE_LOCAL_ROOT_PATH is not defined in the environment variables');
-    }
-    storageConfig = {
-        type: 'local',
-        rootPath: process.env.STORAGE_LOCAL_ROOT_PATH,
-    };
+	if (!process.env.STORAGE_LOCAL_ROOT_PATH) {
+		throw new Error('STORAGE_LOCAL_ROOT_PATH is not defined in the environment variables');
+	}
+	storageConfig = {
+		type: 'local',
+		rootPath: process.env.STORAGE_LOCAL_ROOT_PATH,
+		openArchiverFolderName: openArchiverFolderName,
+	};
 } else if (storageType === 's3') {
-    if (
-        !process.env.STORAGE_S3_ENDPOINT ||
-        !process.env.STORAGE_S3_BUCKET ||
-        !process.env.STORAGE_S3_ACCESS_KEY_ID ||
-        !process.env.STORAGE_S3_SECRET_ACCESS_KEY
-    ) {
-        throw new Error('One or more S3 storage environment variables are not defined');
-    }
-    storageConfig = {
-        type: 's3',
-        endpoint: process.env.STORAGE_S3_ENDPOINT,
-        bucket: process.env.STORAGE_S3_BUCKET,
-        accessKeyId: process.env.STORAGE_S3_ACCESS_KEY_ID,
-        secretAccessKey: process.env.STORAGE_S3_SECRET_ACCESS_KEY,
-        region: process.env.STORAGE_S3_REGION,
-        forcePathStyle: process.env.STORAGE_S3_FORCE_PATH_STYLE === 'true',
-    };
+	if (
+		!process.env.STORAGE_S3_ENDPOINT ||
+		!process.env.STORAGE_S3_BUCKET ||
+		!process.env.STORAGE_S3_ACCESS_KEY_ID ||
+		!process.env.STORAGE_S3_SECRET_ACCESS_KEY
+	) {
+		throw new Error('One or more S3 storage environment variables are not defined');
+	}
+	storageConfig = {
+		type: 's3',
+		endpoint: process.env.STORAGE_S3_ENDPOINT,
+		bucket: process.env.STORAGE_S3_BUCKET,
+		accessKeyId: process.env.STORAGE_S3_ACCESS_KEY_ID,
+		secretAccessKey: process.env.STORAGE_S3_SECRET_ACCESS_KEY,
+		region: process.env.STORAGE_S3_REGION,
+		forcePathStyle: process.env.STORAGE_S3_FORCE_PATH_STYLE === 'true',
+		openArchiverFolderName: openArchiverFolderName,
+	};
 } else {
-    throw new Error(`Invalid STORAGE_TYPE: ${storageType}`);
+	throw new Error(`Invalid STORAGE_TYPE: ${storageType}`);
 }
 
 export const storage = storageConfig;

packages/backend/src/database/index.ts

@@ -3,10 +3,12 @@ import postgres from 'postgres';
 import 'dotenv/config';
 
 import * as schema from './schema';
+import { encodeDatabaseUrl } from '../helpers/db';
 
 if (!process.env.DATABASE_URL) {
-    throw new Error('DATABASE_URL is not set in the .env file');
+	throw new Error('DATABASE_URL is not set in the .env file');
 }
 
-const client = postgres(process.env.DATABASE_URL);
+const connectionString = encodeDatabaseUrl(process.env.DATABASE_URL);
+const client = postgres(connectionString);
 export const db = drizzle(client, { schema });

packages/backend/src/database/migrate.ts

@@ -2,26 +2,28 @@ import { migrate } from 'drizzle-orm/postgres-js/migrator';
 import { drizzle } from 'drizzle-orm/postgres-js';
 import postgres from 'postgres';
 import { config } from 'dotenv';
+import { encodeDatabaseUrl } from '../helpers/db';
 
 config();
 
 const runMigrate = async () => {
-    if (!process.env.DATABASE_URL) {
-        throw new Error('DATABASE_URL is not set in the .env file');
-    }
+	if (!process.env.DATABASE_URL) {
+		throw new Error('DATABASE_URL is not set in the .env file');
+	}
 
-    const connection = postgres(process.env.DATABASE_URL, { max: 1 });
-    const db = drizzle(connection);
+	const connectionString = encodeDatabaseUrl(process.env.DATABASE_URL);
+	const connection = postgres(connectionString, { max: 1 });
+	const db = drizzle(connection);
 
-    console.log('Running migrations...');
+	console.log('Running migrations...');
 
-    await migrate(db, { migrationsFolder: 'src/database/migrations' });
+	await migrate(db, { migrationsFolder: 'src/database/migrations' });
 
-    console.log('Migrations completed!');
-    process.exit(0);
+	console.log('Migrations completed!');
+	process.exit(0);
 };
 
 runMigrate().catch((err) => {
-    console.error('Migration failed!', err);
-    process.exit(1);
+	console.error('Migration failed!', err);
+	process.exit(1);
 });

packages/backend/src/database/migrations/0009_late_lenny_balinger.sql

@@ -0,0 +1,2 @@
+ALTER TABLE "archived_emails" ADD COLUMN "thread_id" text;--> statement-breakpoint
+CREATE INDEX "thread_id_idx" ON "archived_emails" USING btree ("thread_id");

packages/backend/src/database/migrations/0010_perpetual_lightspeed.sql

@@ -0,0 +1,36 @@
+CREATE TABLE "roles" (
+	"id" uuid PRIMARY KEY DEFAULT gen_random_uuid() NOT NULL,
+	"name" text NOT NULL,
+	"policies" jsonb DEFAULT '[]'::jsonb NOT NULL,
+	"created_at" timestamp DEFAULT now() NOT NULL,
+	"updated_at" timestamp DEFAULT now() NOT NULL,
+	CONSTRAINT "roles_name_unique" UNIQUE("name")
+);
+--> statement-breakpoint
+CREATE TABLE "sessions" (
+	"id" text PRIMARY KEY NOT NULL,
+	"user_id" uuid NOT NULL,
+	"expires_at" timestamp with time zone NOT NULL
+);
+--> statement-breakpoint
+CREATE TABLE "user_roles" (
+	"user_id" uuid NOT NULL,
+	"role_id" uuid NOT NULL,
+	CONSTRAINT "user_roles_user_id_role_id_pk" PRIMARY KEY("user_id","role_id")
+);
+--> statement-breakpoint
+CREATE TABLE "users" (
+	"id" uuid PRIMARY KEY DEFAULT gen_random_uuid() NOT NULL,
+	"email" text NOT NULL,
+	"name" text,
+	"password" text,
+	"provider" text DEFAULT 'local',
+	"provider_id" text,
+	"created_at" timestamp DEFAULT now() NOT NULL,
+	"updated_at" timestamp DEFAULT now() NOT NULL,
+	CONSTRAINT "users_email_unique" UNIQUE("email")
+);
+--> statement-breakpoint
+ALTER TABLE "sessions" ADD CONSTRAINT "sessions_user_id_users_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."users"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
+ALTER TABLE "user_roles" ADD CONSTRAINT "user_roles_user_id_users_id_fk" FOREIGN KEY ("user_id") REFERENCES "public"."users"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
+ALTER TABLE "user_roles" ADD CONSTRAINT "user_roles_role_id_roles_id_fk" FOREIGN KEY ("role_id") REFERENCES "public"."roles"("id") ON DELETE cascade ON UPDATE no action;

packages/backend/src/database/migrations/0011_tan_blackheart.sql

@@ -0,0 +1,2 @@
+ALTER TABLE "users" RENAME COLUMN "name" TO "first_name";--> statement-breakpoint
+ALTER TABLE "users" ADD COLUMN "last_name" text;

packages/backend/src/database/migrations/0012_warm_the_stranger.sql

@@ -0,0 +1,2 @@
+ALTER TYPE "public"."ingestion_provider" ADD VALUE 'pst_import';--> statement-breakpoint
+ALTER TYPE "public"."ingestion_status" ADD VALUE 'imported';

packages/backend/src/database/migrations/0013_classy_talkback.sql

@@ -0,0 +1,2 @@
+ALTER TABLE "archived_emails" ADD COLUMN "path" text;--> statement-breakpoint
+ALTER TABLE "archived_emails" ADD COLUMN "tags" jsonb;

packages/backend/src/database/migrations/0014_foamy_vapor.sql

@@ -0,0 +1 @@
+ALTER TYPE "public"."ingestion_provider" ADD VALUE 'eml_import';

packages/backend/src/database/migrations/meta/0009_snapshot.json

@@ -0,0 +1,812 @@
+{
+	"id": "701eda75-451a-4a6d-87e3-b6658fca65da",
+	"prevId": "86b6960e-1936-4543-846f-a2d24d6dc5d1",
+	"version": "7",
+	"dialect": "postgresql",
+	"tables": {
+		"public.archived_emails": {
+			"name": "archived_emails",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"thread_id": {
+					"name": "thread_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"ingestion_source_id": {
+					"name": "ingestion_source_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"user_email": {
+					"name": "user_email",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"message_id_header": {
+					"name": "message_id_header",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"sent_at": {
+					"name": "sent_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"subject": {
+					"name": "subject",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"sender_name": {
+					"name": "sender_name",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"sender_email": {
+					"name": "sender_email",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"recipients": {
+					"name": "recipients",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"storage_path": {
+					"name": "storage_path",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"storage_hash_sha256": {
+					"name": "storage_hash_sha256",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"size_bytes": {
+					"name": "size_bytes",
+					"type": "bigint",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"is_indexed": {
+					"name": "is_indexed",
+					"type": "boolean",
+					"primaryKey": false,
+					"notNull": true,
+					"default": false
+				},
+				"has_attachments": {
+					"name": "has_attachments",
+					"type": "boolean",
+					"primaryKey": false,
+					"notNull": true,
+					"default": false
+				},
+				"is_on_legal_hold": {
+					"name": "is_on_legal_hold",
+					"type": "boolean",
+					"primaryKey": false,
+					"notNull": true,
+					"default": false
+				},
+				"archived_at": {
+					"name": "archived_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				}
+			},
+			"indexes": {
+				"thread_id_idx": {
+					"name": "thread_id_idx",
+					"columns": [
+						{
+							"expression": "thread_id",
+							"isExpression": false,
+							"asc": true,
+							"nulls": "last"
+						}
+					],
+					"isUnique": false,
+					"concurrently": false,
+					"method": "btree",
+					"with": {}
+				}
+			},
+			"foreignKeys": {
+				"archived_emails_ingestion_source_id_ingestion_sources_id_fk": {
+					"name": "archived_emails_ingestion_source_id_ingestion_sources_id_fk",
+					"tableFrom": "archived_emails",
+					"tableTo": "ingestion_sources",
+					"columnsFrom": ["ingestion_source_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.attachments": {
+			"name": "attachments",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"filename": {
+					"name": "filename",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"mime_type": {
+					"name": "mime_type",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"size_bytes": {
+					"name": "size_bytes",
+					"type": "bigint",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"content_hash_sha256": {
+					"name": "content_hash_sha256",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"storage_path": {
+					"name": "storage_path",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {
+				"attachments_content_hash_sha256_unique": {
+					"name": "attachments_content_hash_sha256_unique",
+					"nullsNotDistinct": false,
+					"columns": ["content_hash_sha256"]
+				}
+			},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.email_attachments": {
+			"name": "email_attachments",
+			"schema": "",
+			"columns": {
+				"email_id": {
+					"name": "email_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"attachment_id": {
+					"name": "attachment_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": true
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"email_attachments_email_id_archived_emails_id_fk": {
+					"name": "email_attachments_email_id_archived_emails_id_fk",
+					"tableFrom": "email_attachments",
+					"tableTo": "archived_emails",
+					"columnsFrom": ["email_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"email_attachments_attachment_id_attachments_id_fk": {
+					"name": "email_attachments_attachment_id_attachments_id_fk",
+					"tableFrom": "email_attachments",
+					"tableTo": "attachments",
+					"columnsFrom": ["attachment_id"],
+					"columnsTo": ["id"],
+					"onDelete": "restrict",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {
+				"email_attachments_email_id_attachment_id_pk": {
+					"name": "email_attachments_email_id_attachment_id_pk",
+					"columns": ["email_id", "attachment_id"]
+				}
+			},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.audit_logs": {
+			"name": "audit_logs",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "bigserial",
+					"primaryKey": true,
+					"notNull": true
+				},
+				"timestamp": {
+					"name": "timestamp",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"actor_identifier": {
+					"name": "actor_identifier",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"action": {
+					"name": "action",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"target_type": {
+					"name": "target_type",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"target_id": {
+					"name": "target_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"details": {
+					"name": "details",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"is_tamper_evident": {
+					"name": "is_tamper_evident",
+					"type": "boolean",
+					"primaryKey": false,
+					"notNull": false,
+					"default": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.ediscovery_cases": {
+			"name": "ediscovery_cases",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"name": {
+					"name": "name",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"description": {
+					"name": "description",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"status": {
+					"name": "status",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "'open'"
+				},
+				"created_by_identifier": {
+					"name": "created_by_identifier",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {
+				"ediscovery_cases_name_unique": {
+					"name": "ediscovery_cases_name_unique",
+					"nullsNotDistinct": false,
+					"columns": ["name"]
+				}
+			},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.export_jobs": {
+			"name": "export_jobs",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"case_id": {
+					"name": "case_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"format": {
+					"name": "format",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"status": {
+					"name": "status",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "'pending'"
+				},
+				"query": {
+					"name": "query",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"file_path": {
+					"name": "file_path",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"created_by_identifier": {
+					"name": "created_by_identifier",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"completed_at": {
+					"name": "completed_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"export_jobs_case_id_ediscovery_cases_id_fk": {
+					"name": "export_jobs_case_id_ediscovery_cases_id_fk",
+					"tableFrom": "export_jobs",
+					"tableTo": "ediscovery_cases",
+					"columnsFrom": ["case_id"],
+					"columnsTo": ["id"],
+					"onDelete": "set null",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.legal_holds": {
+			"name": "legal_holds",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"case_id": {
+					"name": "case_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"custodian_id": {
+					"name": "custodian_id",
+					"type": "uuid",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"hold_criteria": {
+					"name": "hold_criteria",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"reason": {
+					"name": "reason",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"applied_by_identifier": {
+					"name": "applied_by_identifier",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"applied_at": {
+					"name": "applied_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"removed_at": {
+					"name": "removed_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"legal_holds_case_id_ediscovery_cases_id_fk": {
+					"name": "legal_holds_case_id_ediscovery_cases_id_fk",
+					"tableFrom": "legal_holds",
+					"tableTo": "ediscovery_cases",
+					"columnsFrom": ["case_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"legal_holds_custodian_id_custodians_id_fk": {
+					"name": "legal_holds_custodian_id_custodians_id_fk",
+					"tableFrom": "legal_holds",
+					"tableTo": "custodians",
+					"columnsFrom": ["custodian_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.retention_policies": {
+			"name": "retention_policies",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"name": {
+					"name": "name",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"description": {
+					"name": "description",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"priority": {
+					"name": "priority",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"retention_period_days": {
+					"name": "retention_period_days",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"action_on_expiry": {
+					"name": "action_on_expiry",
+					"type": "retention_action",
+					"typeSchema": "public",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"is_enabled": {
+					"name": "is_enabled",
+					"type": "boolean",
+					"primaryKey": false,
+					"notNull": true,
+					"default": true
+				},
+				"conditions": {
+					"name": "conditions",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {
+				"retention_policies_name_unique": {
+					"name": "retention_policies_name_unique",
+					"nullsNotDistinct": false,
+					"columns": ["name"]
+				}
+			},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.custodians": {
+			"name": "custodians",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"email": {
+					"name": "email",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"display_name": {
+					"name": "display_name",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"source_type": {
+					"name": "source_type",
+					"type": "ingestion_provider",
+					"typeSchema": "public",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {
+				"custodians_email_unique": {
+					"name": "custodians_email_unique",
+					"nullsNotDistinct": false,
+					"columns": ["email"]
+				}
+			},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		},
+		"public.ingestion_sources": {
+			"name": "ingestion_sources",
+			"schema": "",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "uuid",
+					"primaryKey": true,
+					"notNull": true,
+					"default": "gen_random_uuid()"
+				},
+				"name": {
+					"name": "name",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"provider": {
+					"name": "provider",
+					"type": "ingestion_provider",
+					"typeSchema": "public",
+					"primaryKey": false,
+					"notNull": true
+				},
+				"credentials": {
+					"name": "credentials",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"status": {
+					"name": "status",
+					"type": "ingestion_status",
+					"typeSchema": "public",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "'pending_auth'"
+				},
+				"last_sync_started_at": {
+					"name": "last_sync_started_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"last_sync_finished_at": {
+					"name": "last_sync_finished_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"last_sync_status_message": {
+					"name": "last_sync_status_message",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"sync_state": {
+					"name": "sync_state",
+					"type": "jsonb",
+					"primaryKey": false,
+					"notNull": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "timestamp with time zone",
+					"primaryKey": false,
+					"notNull": true,
+					"default": "now()"
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"policies": {},
+			"checkConstraints": {},
+			"isRLSEnabled": false
+		}
+	},
+	"enums": {
+		"public.retention_action": {
+			"name": "retention_action",
+			"schema": "public",
+			"values": ["delete_permanently", "notify_admin"]
+		},
+		"public.ingestion_provider": {
+			"name": "ingestion_provider",
+			"schema": "public",
+			"values": ["google_workspace", "microsoft_365", "generic_imap"]
+		},
+		"public.ingestion_status": {
+			"name": "ingestion_status",
+			"schema": "public",
+			"values": [
+				"active",
+				"paused",
+				"error",
+				"pending_auth",
+				"syncing",
+				"importing",
+				"auth_success"
+			]
+		}
+	},
+	"schemas": {},
+	"sequences": {},
+	"roles": {},
+	"policies": {},
+	"views": {},
+	"_meta": {
+		"columns": {},
+		"schemas": {},
+		"tables": {}
+	}
+}

packages/backend/src/database/migrations/meta/_journal.json

@@ -1,69 +1,111 @@
 {
-  "version": "7",
-  "dialect": "postgresql",
-  "entries": [
-    {
-      "idx": 0,
-      "version": "7",
-      "when": 1752225352591,
-      "tag": "0000_amusing_namora",
-      "breakpoints": true
-    },
-    {
-      "idx": 1,
-      "version": "7",
-      "when": 1752326803882,
-      "tag": "0001_odd_night_thrasher",
-      "breakpoints": true
-    },
-    {
-      "idx": 2,
-      "version": "7",
-      "when": 1752332648392,
-      "tag": "0002_lethal_quentin_quire",
-      "breakpoints": true
-    },
-    {
-      "idx": 3,
-      "version": "7",
-      "when": 1752332967084,
-      "tag": "0003_petite_wrecker",
-      "breakpoints": true
-    },
-    {
-      "idx": 4,
-      "version": "7",
-      "when": 1752606108876,
-      "tag": "0004_sleepy_paper_doll",
-      "breakpoints": true
-    },
-    {
-      "idx": 5,
-      "version": "7",
-      "when": 1752606327253,
-      "tag": "0005_chunky_sue_storm",
-      "breakpoints": true
-    },
-    {
-      "idx": 6,
-      "version": "7",
-      "when": 1753112018514,
-      "tag": "0006_majestic_caretaker",
-      "breakpoints": true
-    },
-    {
-      "idx": 7,
-      "version": "7",
-      "when": 1753190159356,
-      "tag": "0007_handy_archangel",
-      "breakpoints": true
-    },
-    {
-      "idx": 8,
-      "version": "7",
-      "when": 1753370737317,
-      "tag": "0008_eminent_the_spike",
-      "breakpoints": true
-    }
-  ]
-}
+	"version": "7",
+	"dialect": "postgresql",
+	"entries": [
+		{
+			"idx": 0,
+			"version": "7",
+			"when": 1752225352591,
+			"tag": "0000_amusing_namora",
+			"breakpoints": true
+		},
+		{
+			"idx": 1,
+			"version": "7",
+			"when": 1752326803882,
+			"tag": "0001_odd_night_thrasher",
+			"breakpoints": true
+		},
+		{
+			"idx": 2,
+			"version": "7",
+			"when": 1752332648392,
+			"tag": "0002_lethal_quentin_quire",
+			"breakpoints": true
+		},
+		{
+			"idx": 3,
+			"version": "7",
+			"when": 1752332967084,
+			"tag": "0003_petite_wrecker",
+			"breakpoints": true
+		},
+		{
+			"idx": 4,
+			"version": "7",
+			"when": 1752606108876,
+			"tag": "0004_sleepy_paper_doll",
+			"breakpoints": true
+		},
+		{
+			"idx": 5,
+			"version": "7",
+			"when": 1752606327253,
+			"tag": "0005_chunky_sue_storm",
+			"breakpoints": true
+		},
+		{
+			"idx": 6,
+			"version": "7",
+			"when": 1753112018514,
+			"tag": "0006_majestic_caretaker",
+			"breakpoints": true
+		},
+		{
+			"idx": 7,
+			"version": "7",
+			"when": 1753190159356,
+			"tag": "0007_handy_archangel",
+			"breakpoints": true
+		},
+		{
+			"idx": 8,
+			"version": "7",
+			"when": 1753370737317,
+			"tag": "0008_eminent_the_spike",
+			"breakpoints": true
+		},
+		{
+			"idx": 9,
+			"version": "7",
+			"when": 1754337938241,
+			"tag": "0009_late_lenny_balinger",
+			"breakpoints": true
+		},
+		{
+			"idx": 10,
+			"version": "7",
+			"when": 1754420780849,
+			"tag": "0010_perpetual_lightspeed",
+			"breakpoints": true
+		},
+		{
+			"idx": 11,
+			"version": "7",
+			"when": 1754422064158,
+			"tag": "0011_tan_blackheart",
+			"breakpoints": true
+		},
+		{
+			"idx": 12,
+			"version": "7",
+			"when": 1754476962901,
+			"tag": "0012_warm_the_stranger",
+			"breakpoints": true
+		},
+		{
+			"idx": 13,
+			"version": "7",
+			"when": 1754659373517,
+			"tag": "0013_classy_talkback",
+			"breakpoints": true
+		},
+		{
+			"idx": 14,
+			"version": "7",
+			"when": 1754831765718,
+			"tag": "0014_foamy_vapor",
+			"breakpoints": true
+		}
+	]
+}

packages/backend/src/database/schema.ts

@@ -4,3 +4,4 @@ export * from './schema/audit-logs';
 export * from './schema/compliance';
 export * from './schema/custodians';
 export * from './schema/ingestion-sources';
+export * from './schema/users';

packages/backend/src/database/schema/archived-emails.ts

@@ -1,31 +1,38 @@
 import { relations } from 'drizzle-orm';
-import { boolean, jsonb, pgTable, text, timestamp, uuid, bigint } from 'drizzle-orm/pg-core';
+import { boolean, jsonb, pgTable, text, timestamp, uuid, bigint, index } from 'drizzle-orm/pg-core';
 import { ingestionSources } from './ingestion-sources';
 
-export const archivedEmails = pgTable('archived_emails', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    ingestionSourceId: uuid('ingestion_source_id')
-        .notNull()
-        .references(() => ingestionSources.id, { onDelete: 'cascade' }),
-    userEmail: text('user_email').notNull(),
-    messageIdHeader: text('message_id_header'),
-    sentAt: timestamp('sent_at', { withTimezone: true }).notNull(),
-    subject: text('subject'),
-    senderName: text('sender_name'),
-    senderEmail: text('sender_email').notNull(),
-    recipients: jsonb('recipients'),
-    storagePath: text('storage_path').notNull(),
-    storageHashSha256: text('storage_hash_sha256').notNull(),
-    sizeBytes: bigint('size_bytes', { mode: 'number' }).notNull(),
-    isIndexed: boolean('is_indexed').notNull().default(false),
-    hasAttachments: boolean('has_attachments').notNull().default(false),
-    isOnLegalHold: boolean('is_on_legal_hold').notNull().default(false),
-    archivedAt: timestamp('archived_at', { withTimezone: true }).notNull().defaultNow(),
-});
+export const archivedEmails = pgTable(
+	'archived_emails',
+	{
+		id: uuid('id').primaryKey().defaultRandom(),
+		threadId: text('thread_id'),
+		ingestionSourceId: uuid('ingestion_source_id')
+			.notNull()
+			.references(() => ingestionSources.id, { onDelete: 'cascade' }),
+		userEmail: text('user_email').notNull(),
+		messageIdHeader: text('message_id_header'),
+		sentAt: timestamp('sent_at', { withTimezone: true }).notNull(),
+		subject: text('subject'),
+		senderName: text('sender_name'),
+		senderEmail: text('sender_email').notNull(),
+		recipients: jsonb('recipients'),
+		storagePath: text('storage_path').notNull(),
+		storageHashSha256: text('storage_hash_sha256').notNull(),
+		sizeBytes: bigint('size_bytes', { mode: 'number' }).notNull(),
+		isIndexed: boolean('is_indexed').notNull().default(false),
+		hasAttachments: boolean('has_attachments').notNull().default(false),
+		isOnLegalHold: boolean('is_on_legal_hold').notNull().default(false),
+		archivedAt: timestamp('archived_at', { withTimezone: true }).notNull().defaultNow(),
+		path: text('path'),
+		tags: jsonb('tags'),
+	},
+	(table) => [index('thread_id_idx').on(table.threadId)]
+);
 
 export const archivedEmailsRelations = relations(archivedEmails, ({ one }) => ({
-    ingestionSource: one(ingestionSources, {
-        fields: [archivedEmails.ingestionSourceId],
-        references: [ingestionSources.id]
-    })
+	ingestionSource: one(ingestionSources, {
+		fields: [archivedEmails.ingestionSourceId],
+		references: [ingestionSources.id],
+	}),
 }));

packages/backend/src/database/schema/attachments.ts

@@ -3,32 +3,40 @@ import { pgTable, text, uuid, bigint, primaryKey } from 'drizzle-orm/pg-core';
 import { archivedEmails } from './archived-emails';
 
 export const attachments = pgTable('attachments', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    filename: text('filename').notNull(),
-    mimeType: text('mime_type'),
-    sizeBytes: bigint('size_bytes', { mode: 'number' }).notNull(),
-    contentHashSha256: text('content_hash_sha256').notNull().unique(),
-    storagePath: text('storage_path').notNull(),
+	id: uuid('id').primaryKey().defaultRandom(),
+	filename: text('filename').notNull(),
+	mimeType: text('mime_type'),
+	sizeBytes: bigint('size_bytes', { mode: 'number' }).notNull(),
+	contentHashSha256: text('content_hash_sha256').notNull().unique(),
+	storagePath: text('storage_path').notNull(),
 });
 
-export const emailAttachments = pgTable('email_attachments', {
-    emailId: uuid('email_id').notNull().references(() => archivedEmails.id, { onDelete: 'cascade' }),
-    attachmentId: uuid('attachment_id').notNull().references(() => attachments.id, { onDelete: 'restrict' }),
-}, (t) => ({
-    pk: primaryKey({ columns: [t.emailId, t.attachmentId] }),
-}));
+export const emailAttachments = pgTable(
+	'email_attachments',
+	{
+		emailId: uuid('email_id')
+			.notNull()
+			.references(() => archivedEmails.id, { onDelete: 'cascade' }),
+		attachmentId: uuid('attachment_id')
+			.notNull()
+			.references(() => attachments.id, { onDelete: 'restrict' }),
+	},
+	(t) => ({
+		pk: primaryKey({ columns: [t.emailId, t.attachmentId] }),
+	})
+);
 
 export const attachmentsRelations = relations(attachments, ({ many }) => ({
-    emailAttachments: many(emailAttachments),
+	emailAttachments: many(emailAttachments),
 }));
 
 export const emailAttachmentsRelations = relations(emailAttachments, ({ one }) => ({
-    archivedEmail: one(archivedEmails, {
-        fields: [emailAttachments.emailId],
-        references: [archivedEmails.id],
-    }),
-    attachment: one(attachments, {
-        fields: [emailAttachments.attachmentId],
-        references: [attachments.id],
-    }),
+	archivedEmail: one(archivedEmails, {
+		fields: [emailAttachments.emailId],
+		references: [archivedEmails.id],
+	}),
+	attachment: one(attachments, {
+		fields: [emailAttachments.attachmentId],
+		references: [attachments.id],
+	}),
 }));

packages/backend/src/database/schema/audit-logs.ts

@@ -1,12 +1,12 @@
 import { bigserial, boolean, jsonb, pgTable, text, timestamp } from 'drizzle-orm/pg-core';
 
 export const auditLogs = pgTable('audit_logs', {
-    id: bigserial('id', { mode: 'number' }).primaryKey(),
-    timestamp: timestamp('timestamp', { withTimezone: true }).notNull().defaultNow(),
-    actorIdentifier: text('actor_identifier').notNull(),
-    action: text('action').notNull(),
-    targetType: text('target_type'),
-    targetId: text('target_id'),
-    details: jsonb('details'),
-    isTamperEvident: boolean('is_tamper_evident').default(false),
+	id: bigserial('id', { mode: 'number' }).primaryKey(),
+	timestamp: timestamp('timestamp', { withTimezone: true }).notNull().defaultNow(),
+	actorIdentifier: text('actor_identifier').notNull(),
+	action: text('action').notNull(),
+	targetType: text('target_type'),
+	targetId: text('target_id'),
+	details: jsonb('details'),
+	isTamperEvident: boolean('is_tamper_evident').default(false),
 });

packages/backend/src/database/schema/compliance.ts

@@ -1,80 +1,94 @@
 import { relations } from 'drizzle-orm';
-import { boolean, integer, jsonb, pgEnum, pgTable, text, timestamp, uuid } from 'drizzle-orm/pg-core';
+import {
+	boolean,
+	integer,
+	jsonb,
+	pgEnum,
+	pgTable,
+	text,
+	timestamp,
+	uuid,
+} from 'drizzle-orm/pg-core';
 import { custodians } from './custodians';
 
 // --- Enums ---
 
-export const retentionActionEnum = pgEnum('retention_action', ['delete_permanently', 'notify_admin']);
+export const retentionActionEnum = pgEnum('retention_action', [
+	'delete_permanently',
+	'notify_admin',
+]);
 
 // --- Tables ---
 
 export const retentionPolicies = pgTable('retention_policies', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    name: text('name').notNull().unique(),
-    description: text('description'),
-    priority: integer('priority').notNull(),
-    retentionPeriodDays: integer('retention_period_days').notNull(),
-    actionOnExpiry: retentionActionEnum('action_on_expiry').notNull(),
-    isEnabled: boolean('is_enabled').notNull().default(true),
-    conditions: jsonb('conditions'),
-    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
-    updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
+	id: uuid('id').primaryKey().defaultRandom(),
+	name: text('name').notNull().unique(),
+	description: text('description'),
+	priority: integer('priority').notNull(),
+	retentionPeriodDays: integer('retention_period_days').notNull(),
+	actionOnExpiry: retentionActionEnum('action_on_expiry').notNull(),
+	isEnabled: boolean('is_enabled').notNull().default(true),
+	conditions: jsonb('conditions'),
+	createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+	updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
 });
 
 export const ediscoveryCases = pgTable('ediscovery_cases', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    name: text('name').notNull().unique(),
-    description: text('description'),
-    status: text('status').notNull().default('open'),
-    createdByIdentifier: text('created_by_identifier').notNull(),
-    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
-    updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
+	id: uuid('id').primaryKey().defaultRandom(),
+	name: text('name').notNull().unique(),
+	description: text('description'),
+	status: text('status').notNull().default('open'),
+	createdByIdentifier: text('created_by_identifier').notNull(),
+	createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+	updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
 });
 
 export const legalHolds = pgTable('legal_holds', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    caseId: uuid('case_id').notNull().references(() => ediscoveryCases.id, { onDelete: 'cascade' }),
-    custodianId: uuid('custodian_id').references(() => custodians.id, { onDelete: 'cascade' }),
-    holdCriteria: jsonb('hold_criteria'),
-    reason: text('reason'),
-    appliedByIdentifier: text('applied_by_identifier').notNull(),
-    appliedAt: timestamp('applied_at', { withTimezone: true }).notNull().defaultNow(),
-    removedAt: timestamp('removed_at', { withTimezone: true }),
+	id: uuid('id').primaryKey().defaultRandom(),
+	caseId: uuid('case_id')
+		.notNull()
+		.references(() => ediscoveryCases.id, { onDelete: 'cascade' }),
+	custodianId: uuid('custodian_id').references(() => custodians.id, { onDelete: 'cascade' }),
+	holdCriteria: jsonb('hold_criteria'),
+	reason: text('reason'),
+	appliedByIdentifier: text('applied_by_identifier').notNull(),
+	appliedAt: timestamp('applied_at', { withTimezone: true }).notNull().defaultNow(),
+	removedAt: timestamp('removed_at', { withTimezone: true }),
 });
 
 export const exportJobs = pgTable('export_jobs', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    caseId: uuid('case_id').references(() => ediscoveryCases.id, { onDelete: 'set null' }),
-    format: text('format').notNull(),
-    status: text('status').notNull().default('pending'),
-    query: jsonb('query').notNull(),
-    filePath: text('file_path'),
-    createdByIdentifier: text('created_by_identifier').notNull(),
-    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
-    completedAt: timestamp('completed_at', { withTimezone: true }),
+	id: uuid('id').primaryKey().defaultRandom(),
+	caseId: uuid('case_id').references(() => ediscoveryCases.id, { onDelete: 'set null' }),
+	format: text('format').notNull(),
+	status: text('status').notNull().default('pending'),
+	query: jsonb('query').notNull(),
+	filePath: text('file_path'),
+	createdByIdentifier: text('created_by_identifier').notNull(),
+	createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+	completedAt: timestamp('completed_at', { withTimezone: true }),
 });
 
 // --- Relations ---
 
 export const ediscoveryCasesRelations = relations(ediscoveryCases, ({ many }) => ({
-    legalHolds: many(legalHolds),
-    exportJobs: many(exportJobs),
+	legalHolds: many(legalHolds),
+	exportJobs: many(exportJobs),
 }));
 
 export const legalHoldsRelations = relations(legalHolds, ({ one }) => ({
-    ediscoveryCase: one(ediscoveryCases, {
-        fields: [legalHolds.caseId],
-        references: [ediscoveryCases.id],
-    }),
-    custodian: one(custodians, {
-        fields: [legalHolds.custodianId],
-        references: [custodians.id],
-    }),
+	ediscoveryCase: one(ediscoveryCases, {
+		fields: [legalHolds.caseId],
+		references: [ediscoveryCases.id],
+	}),
+	custodian: one(custodians, {
+		fields: [legalHolds.custodianId],
+		references: [custodians.id],
+	}),
 }));
 
 export const exportJobsRelations = relations(exportJobs, ({ one }) => ({
-    ediscoveryCase: one(ediscoveryCases, {
-        fields: [exportJobs.caseId],
-        references: [ediscoveryCases.id],
-    }),
+	ediscoveryCase: one(ediscoveryCases, {
+		fields: [exportJobs.caseId],
+		references: [ediscoveryCases.id],
+	}),
 }));

packages/backend/src/database/schema/custodians.ts

@@ -2,10 +2,10 @@ import { pgTable, text, timestamp, uuid } from 'drizzle-orm/pg-core';
 import { ingestionProviderEnum } from './ingestion-sources';
 
 export const custodians = pgTable('custodians', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    email: text('email').notNull().unique(),
-    displayName: text('display_name'),
-    sourceType: ingestionProviderEnum('source_type').notNull(),
-    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
-    updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow()
+	id: uuid('id').primaryKey().defaultRandom(),
+	email: text('email').notNull().unique(),
+	displayName: text('display_name'),
+	sourceType: ingestionProviderEnum('source_type').notNull(),
+	createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+	updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
 });

packages/backend/src/database/schema/ingestion-sources.ts

@@ -1,31 +1,34 @@
 import { jsonb, pgEnum, pgTable, text, timestamp, uuid } from 'drizzle-orm/pg-core';
 
 export const ingestionProviderEnum = pgEnum('ingestion_provider', [
-    'google_workspace',
-    'microsoft_365',
-    'generic_imap'
+	'google_workspace',
+	'microsoft_365',
+	'generic_imap',
+	'pst_import',
+	'eml_import',
 ]);
 
 export const ingestionStatusEnum = pgEnum('ingestion_status', [
-    'active',
-    'paused',
-    'error',
-    'pending_auth',
-    'syncing',
-    'importing',
-    'auth_success'
+	'active',
+	'paused',
+	'error',
+	'pending_auth',
+	'syncing',
+	'importing',
+	'auth_success',
+	'imported',
 ]);
 
 export const ingestionSources = pgTable('ingestion_sources', {
-    id: uuid('id').primaryKey().defaultRandom(),
-    name: text('name').notNull(),
-    provider: ingestionProviderEnum('provider').notNull(),
-    credentials: text('credentials'),
-    status: ingestionStatusEnum('status').notNull().default('pending_auth'),
-    lastSyncStartedAt: timestamp('last_sync_started_at', { withTimezone: true }),
-    lastSyncFinishedAt: timestamp('last_sync_finished_at', { withTimezone: true }),
-    lastSyncStatusMessage: text('last_sync_status_message'),
-    syncState: jsonb('sync_state'),
-    createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
-    updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow()
+	id: uuid('id').primaryKey().defaultRandom(),
+	name: text('name').notNull(),
+	provider: ingestionProviderEnum('provider').notNull(),
+	credentials: text('credentials'),
+	status: ingestionStatusEnum('status').notNull().default('pending_auth'),
+	lastSyncStartedAt: timestamp('last_sync_started_at', { withTimezone: true }),
+	lastSyncFinishedAt: timestamp('last_sync_finished_at', { withTimezone: true }),
+	lastSyncStatusMessage: text('last_sync_status_message'),
+	syncState: jsonb('sync_state'),
+	createdAt: timestamp('created_at', { withTimezone: true }).notNull().defaultNow(),
+	updatedAt: timestamp('updated_at', { withTimezone: true }).notNull().defaultNow(),
 });

packages/backend/src/database/schema/users.ts

@@ -0,0 +1,85 @@
+import { relations, sql } from 'drizzle-orm';
+import { pgTable, text, timestamp, uuid, primaryKey, jsonb } from 'drizzle-orm/pg-core';
+import type { PolicyStatement } from '@open-archiver/types';
+
+/**
+ * The `users` table stores the core user information for authentication and identification.
+ */
+export const users = pgTable('users', {
+	id: uuid('id').primaryKey().defaultRandom(),
+	email: text('email').notNull().unique(),
+	first_name: text('first_name'),
+	last_name: text('last_name'),
+	password: text('password'),
+	provider: text('provider').default('local'),
+	providerId: text('provider_id'),
+	createdAt: timestamp('created_at').defaultNow().notNull(),
+	updatedAt: timestamp('updated_at').defaultNow().notNull(),
+});
+
+/**
+ * The `sessions` table stores user session information for managing login state.
+ * It links a session to a user and records its expiration time.
+ */
+export const sessions = pgTable('sessions', {
+	id: text('id').primaryKey(),
+	userId: uuid('user_id')
+		.notNull()
+		.references(() => users.id, { onDelete: 'cascade' }),
+	expiresAt: timestamp('expires_at', {
+		withTimezone: true,
+		mode: 'date',
+	}).notNull(),
+});
+
+/**
+ * The `roles` table defines the roles that can be assigned to users.
+ * Each role has a name and a set of policies that define its permissions.
+ */
+export const roles = pgTable('roles', {
+	id: uuid('id').primaryKey().defaultRandom(),
+	name: text('name').notNull().unique(),
+	policies: jsonb('policies')
+		.$type<PolicyStatement[]>()
+		.notNull()
+		.default(sql`'[]'::jsonb`),
+	createdAt: timestamp('created_at').defaultNow().notNull(),
+	updatedAt: timestamp('updated_at').defaultNow().notNull(),
+});
+
+/**
+ * The `user_roles` table is a join table that maps users to their assigned roles.
+ * This many-to-many relationship allows a user to have multiple roles.
+ */
+export const userRoles = pgTable(
+	'user_roles',
+	{
+		userId: uuid('user_id')
+			.notNull()
+			.references(() => users.id, { onDelete: 'cascade' }),
+		roleId: uuid('role_id')
+			.notNull()
+			.references(() => roles.id, { onDelete: 'cascade' }),
+	},
+	(t) => [primaryKey({ columns: [t.userId, t.roleId] })]
+);
+
+// Define relationships for Drizzle ORM
+export const usersRelations = relations(users, ({ many }) => ({
+	userRoles: many(userRoles),
+}));
+
+export const rolesRelations = relations(roles, ({ many }) => ({
+	userRoles: many(userRoles),
+}));
+
+export const userRolesRelations = relations(userRoles, ({ one }) => ({
+	role: one(roles, {
+		fields: [userRoles.roleId],
+		references: [roles.id],
+	}),
+	user: one(users, {
+		fields: [userRoles.userId],
+		references: [users.id],
+	}),
+}));

packages/backend/src/helpers/db.ts

@@ -0,0 +1,12 @@
+export const encodeDatabaseUrl = (databaseUrl: string): string => {
+	try {
+		const url = new URL(databaseUrl);
+		if (url.password) {
+			url.password = encodeURIComponent(url.password);
+		}
+		return url.toString();
+	} catch (error) {
+		console.error('Invalid DATABASE_URL, please check your .env file.', error);
+		throw new Error('Invalid DATABASE_URL');
+	}
+};