ci: Bump version to 0.11.0 for production release [skip ci]

Allows test environment PM2 processes to load environment variables
from /var/www/flyer-crawler-test.projectium.com/.env file, enabling
manual restarts without requiring CI/CD to inject variables.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.claude/settings.local.json

@@ -91,7 +91,14 @@
       "Bash(ping:*)",
       "Bash(tee:*)",
       "Bash(timeout 1800 podman exec flyer-crawler-dev npm run test:unit:*)",
-      "mcp__filesystem__edit_file"
+      "mcp__filesystem__edit_file",
+      "Bash(timeout 300 tail:*)",
+      "mcp__filesystem__list_allowed_directories",
+      "mcp__memory__add_observations",
+      "Bash(ssh:*)",
+      "mcp__redis__list",
+      "Read(//d/gitea/bugsink-mcp/**)",
+      "Bash(d:/nodejs/npm.cmd install)"
     ]
   }
 }

.gitea/workflows/deploy-to-prod.yml

@@ -63,8 +63,8 @@ jobs:
       - name: Check for Production Database Schema Changes
         env:
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+          DB_USER: ${{ secrets.DB_USER_PROD }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
           DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
         run: |
           if [ -z "$DB_HOST" ] || [ -z "$DB_USER" ] || [ -z "$DB_PASSWORD" ] || [ -z "$DB_NAME" ]; then
@@ -117,8 +117,8 @@ jobs:
         env:
           # --- Production Secrets Injection ---
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+          DB_USER: ${{ secrets.DB_USER_PROD }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
           DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
           # Explicitly use database 0 for production (test uses database 1)
           REDIS_URL: 'redis://localhost:6379/0'
@@ -171,7 +171,7 @@ jobs:
             else
               echo "Version mismatch (Running: $RUNNING_VERSION -> Deployed: $NEW_VERSION) or app not running. Reloading PM2..."
             fi
-            pm2 startOrReload ecosystem.config.cjs --env production --update-env && pm2 save
+            pm2 startOrReload ecosystem.config.cjs --update-env && pm2 save
             echo "Production backend server reloaded successfully."
           else
             echo "Version $NEW_VERSION is already running. Skipping PM2 reload."

.gitea/workflows/deploy-to-test.yml

@@ -121,10 +121,11 @@ jobs:
         env:
           # --- Database credentials for the test suite ---
           # These are injected from Gitea secrets into the runner's environment.
+          # CRITICAL: Use TEST-specific credentials that have CREATE privileges on the public schema.
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
-          DB_NAME: 'flyer-crawler-test' # Explicitly set for tests
+          DB_USER: ${{ secrets.DB_USER_TEST }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_TEST }}
+          DB_NAME: ${{ secrets.DB_DATABASE_TEST }}
 
           # --- Redis credentials for the test suite ---
           # CRITICAL: Use Redis database 1 to isolate tests from production (which uses db 0).
@@ -328,10 +329,11 @@ jobs:
       - name: Check for Test Database Schema Changes
         env:
           # Use test database credentials for this check.
+          # CRITICAL: Use TEST-specific credentials that have CREATE privileges on the public schema.
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }} # This is used by psql
-          DB_NAME: ${{ secrets.DB_DATABASE_TEST }} # This is used by the application
+          DB_USER: ${{ secrets.DB_USER_TEST }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_TEST }}
+          DB_NAME: ${{ secrets.DB_DATABASE_TEST }}
         run: |
           # Fail-fast check to ensure secrets are configured in Gitea.
           if [ -z "$DB_HOST" ] || [ -z "$DB_USER" ] || [ -z "$DB_PASSWORD" ] || [ -z "$DB_NAME" ]; then
@@ -427,9 +429,10 @@ jobs:
           # Your Node.js application will read these directly from `process.env`.
 
           # Database Credentials
+          # CRITICAL: Use TEST-specific credentials that have CREATE privileges on the public schema.
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+          DB_USER: ${{ secrets.DB_USER_TEST }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_TEST }}
           DB_NAME: ${{ secrets.DB_DATABASE_TEST }}
 
           # Redis Credentials (use database 1 to isolate from production)
@@ -476,10 +479,11 @@ jobs:
           echo "Cleaning up errored or stopped PM2 processes..."
           node -e "const exec = require('child_process').execSync; try { const list = JSON.parse(exec('pm2 jlist').toString()); list.forEach(p => { if (p.pm2_env.status === 'errored' || p.pm2_env.status === 'stopped') { console.log('Deleting ' + p.pm2_env.status + ' process: ' + p.name + ' (' + p.pm2_env.pm_id + ')'); try { exec('pm2 delete ' + p.pm2_env.pm_id); } catch(e) { console.error('Failed to delete ' + p.pm2_env.pm_id); } } }); } catch (e) { console.error('Error cleaning up processes:', e); }"
 
-          # Use `startOrReload` with the ecosystem file. This is the standard, idempotent way to deploy.
-          # It will START the process if it's not running, or RELOAD it if it is.
+          # Use `startOrReload` with the TEST ecosystem file. This starts test-specific processes
+          # (flyer-crawler-api-test, flyer-crawler-worker-test, flyer-crawler-analytics-worker-test)
+          # that run separately from production processes.
           # We also add `&& pm2 save` to persist the process list across server reboots.
-          pm2 startOrReload ecosystem.config.cjs --env test --update-env && pm2 save
+          pm2 startOrReload ecosystem-test.config.cjs --update-env && pm2 save
           echo "Test backend server reloaded successfully."
 
           # After a successful deployment, update the schema hash in the database.

.gitea/workflows/manual-db-backup.yml

@@ -20,9 +20,9 @@ jobs:
       # Use production database credentials for this entire job.
       DB_HOST: ${{ secrets.DB_HOST }}
       DB_PORT: ${{ secrets.DB_PORT }}
-      DB_USER: ${{ secrets.DB_USER }}
-      DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
-      DB_NAME: ${{ secrets.DB_NAME_PROD }}
+      DB_USER: ${{ secrets.DB_USER_PROD }}
+      DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
+      DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
 
     steps:
       - name: Validate Secrets

.gitea/workflows/manual-db-reset-prod.yml

@@ -23,9 +23,9 @@ jobs:
     env:
       # Use production database credentials for this entire job.
       DB_HOST: ${{ secrets.DB_HOST }}
-      DB_USER: ${{ secrets.DB_USER }}
-      DB_PASSWORD: ${{ secrets.DB_PASSWORD }} # Used by psql
-      DB_NAME: ${{ secrets.DB_DATABASE_PROD }} # Used by the application
+      DB_USER: ${{ secrets.DB_USER_PROD }}
+      DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
+      DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
 
     steps:
       - name: Checkout Code

.gitea/workflows/manual-db-reset-test.yml

@@ -23,9 +23,9 @@ jobs:
     env:
       # Use test database credentials for this entire job.
       DB_HOST: ${{ secrets.DB_HOST }}
-      DB_USER: ${{ secrets.DB_USER }}
-      DB_PASSWORD: ${{ secrets.DB_PASSWORD }} # Used by psql
-      DB_NAME: ${{ secrets.DB_DATABASE_TEST }} # Used by the application
+      DB_USER: ${{ secrets.DB_USER_TEST }}
+      DB_PASSWORD: ${{ secrets.DB_PASSWORD_TEST }}
+      DB_NAME: ${{ secrets.DB_DATABASE_TEST }}
 
     steps:
       - name: Checkout Code

.gitea/workflows/manual-db-restore.yml

@@ -22,8 +22,8 @@ jobs:
     env:
       # Use production database credentials for this entire job.
       DB_HOST: ${{ secrets.DB_HOST }}
-      DB_USER: ${{ secrets.DB_USER }}
-      DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+      DB_USER: ${{ secrets.DB_USER_PROD }}
+      DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
       DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
       BACKUP_DIR: '/var/www/backups' # Define a dedicated directory for backups
 

.gitea/workflows/manual-deploy-major.yml

@@ -62,8 +62,8 @@ jobs:
       - name: Check for Production Database Schema Changes
         env:
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+          DB_USER: ${{ secrets.DB_USER_PROD }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
           DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
         run: |
           if [ -z "$DB_HOST" ] || [ -z "$DB_USER" ] || [ -z "$DB_PASSWORD" ] || [ -z "$DB_NAME" ]; then
@@ -113,8 +113,8 @@ jobs:
         env:
           # --- Production Secrets Injection ---
           DB_HOST: ${{ secrets.DB_HOST }}
-          DB_USER: ${{ secrets.DB_USER }}
-          DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
+          DB_USER: ${{ secrets.DB_USER_PROD }}
+          DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
           DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
           # Explicitly use database 0 for production (test uses database 1)
           REDIS_URL: 'redis://localhost:6379/0'

.gitignore

@@ -37,3 +37,4 @@ test-output.txt
 Thumbs.db
 .claude
 nul
+tmpclaude*

CLAUDE-MCP.md

@@ -0,0 +1,378 @@
+# Claude Code MCP Configuration Guide
+
+This document explains how to configure MCP (Model Context Protocol) servers for Claude Code, covering both the CLI and VS Code extension.
+
+## The Two Config Files
+
+Claude Code uses **two separate configuration files** for MCP servers. They must be kept in sync manually.
+
+| File                      | Used By                       | Notes                                       |
+| ------------------------- | ----------------------------- | ------------------------------------------- |
+| `~/.claude.json`          | Claude CLI (`claude` command) | Requires `"type": "stdio"` in each server   |
+| `~/.claude/settings.json` | VS Code Extension             | Simpler format, supports `"disabled": true` |
+
+**Important:** Changes to one file do NOT automatically sync to the other!
+
+## File Locations (Windows)
+
+```text
+C:\Users\<username>\.claude.json           # CLI config
+C:\Users\<username>\.claude\settings.json  # VS Code extension config
+```
+
+## Config Format Differences
+
+### VS Code Extension Format (`~/.claude/settings.json`)
+
+```json
+{
+  "mcpServers": {
+    "server-name": {
+      "command": "path/to/executable",
+      "args": ["arg1", "arg2"],
+      "env": {
+        "ENV_VAR": "value"
+      },
+      "disabled": true // Optional - disable without removing
+    }
+  }
+}
+```
+
+### CLI Format (`~/.claude.json`)
+
+The CLI config is a larger file with many settings. The `mcpServers` section is nested within it:
+
+```json
+{
+  "numStartups": 14,
+  "installMethod": "global",
+  // ... other settings ...
+  "mcpServers": {
+    "server-name": {
+      "type": "stdio", // REQUIRED for CLI
+      "command": "path/to/executable",
+      "args": ["arg1", "arg2"],
+      "env": {
+        "ENV_VAR": "value"
+      }
+    }
+  }
+  // ... more settings ...
+}
+```
+
+**Key difference:** CLI format requires `"type": "stdio"` in each server definition.
+
+## Common MCP Server Examples
+
+### Memory (Knowledge Graph)
+
+```json
+// VS Code format
+"memory": {
+  "command": "D:\\nodejs\\npx.cmd",
+  "args": ["-y", "@modelcontextprotocol/server-memory"]
+}
+
+// CLI format
+"memory": {
+  "type": "stdio",
+  "command": "D:\\nodejs\\npx.cmd",
+  "args": ["-y", "@modelcontextprotocol/server-memory"],
+  "env": {}
+}
+```
+
+### Filesystem
+
+```json
+// VS Code format
+"filesystem": {
+  "command": "d:\\nodejs\\node.exe",
+  "args": [
+    "c:\\Users\\<user>\\AppData\\Roaming\\npm\\node_modules\\@modelcontextprotocol\\server-filesystem\\dist\\index.js",
+    "d:\\path\\to\\project"
+  ]
+}
+
+// CLI format
+"filesystem": {
+  "type": "stdio",
+  "command": "d:\\nodejs\\node.exe",
+  "args": [
+    "c:\\Users\\<user>\\AppData\\Roaming\\npm\\node_modules\\@modelcontextprotocol\\server-filesystem\\dist\\index.js",
+    "d:\\path\\to\\project"
+  ],
+  "env": {}
+}
+```
+
+### Podman/Docker
+
+```json
+// VS Code format
+"podman": {
+  "command": "D:\\nodejs\\npx.cmd",
+  "args": ["-y", "podman-mcp-server@latest"],
+  "env": {
+    "DOCKER_HOST": "npipe:////./pipe/podman-machine-default"
+  }
+}
+```
+
+### Gitea
+
+```json
+// VS Code format
+"gitea-myserver": {
+  "command": "d:\\gitea-mcp\\gitea-mcp.exe",
+  "args": ["run", "-t", "stdio"],
+  "env": {
+    "GITEA_HOST": "https://gitea.example.com",
+    "GITEA_ACCESS_TOKEN": "your-token-here"
+  }
+}
+```
+
+### Redis
+
+```json
+// VS Code format
+"redis": {
+  "command": "D:\\nodejs\\npx.cmd",
+  "args": ["-y", "@modelcontextprotocol/server-redis", "redis://localhost:6379"]
+}
+```
+
+### Bugsink (Error Tracking)
+
+**Important:** Bugsink has a different API than Sentry. Use `bugsink-mcp`, NOT `sentry-selfhosted-mcp`.
+
+**Note:** The `bugsink-mcp` npm package is NOT published. You must clone and build from source:
+
+```bash
+# Clone and build bugsink-mcp
+git clone https://github.com/j-shelfwood/bugsink-mcp.git d:\gitea\bugsink-mcp
+cd d:\gitea\bugsink-mcp
+npm install
+npm run build
+```
+
+```json
+// VS Code format (using locally built version)
+"bugsink": {
+  "command": "d:\\nodejs\\node.exe",
+  "args": ["d:\\gitea\\bugsink-mcp\\dist\\index.js"],
+  "env": {
+    "BUGSINK_URL": "https://bugsink.example.com",
+    "BUGSINK_TOKEN": "your-api-token"
+  }
+}
+
+// CLI format
+"bugsink": {
+  "type": "stdio",
+  "command": "d:\\nodejs\\node.exe",
+  "args": ["d:\\gitea\\bugsink-mcp\\dist\\index.js"],
+  "env": {
+    "BUGSINK_URL": "https://bugsink.example.com",
+    "BUGSINK_TOKEN": "your-api-token"
+  }
+}
+```
+
+- GitHub: <https://github.com/j-shelfwood/bugsink-mcp>
+- Get token from Bugsink UI: Settings > API Tokens
+- **Do NOT use npx** - the package is not on npm
+
+### Sentry (Cloud or Self-hosted)
+
+For actual Sentry instances (not Bugsink), use:
+
+```json
+"sentry": {
+  "command": "D:\\nodejs\\npx.cmd",
+  "args": ["-y", "@sentry/mcp-server"],
+  "env": {
+    "SENTRY_AUTH_TOKEN": "your-sentry-token"
+  }
+}
+```
+
+## Troubleshooting
+
+### Server Not Loading
+
+1. **Check both config files** - Make sure the server is defined in both `~/.claude.json` AND `~/.claude/settings.json`
+
+2. **Verify server order** - Servers load sequentially. Broken/slow servers can block others. Put important servers first.
+
+3. **Check for timeout** - Each server has 30 seconds to connect. Slow npx downloads can cause timeouts.
+
+4. **Fully restart VS Code** - Window reload is not enough. Close all VS Code windows and reopen.
+
+### Verifying Configuration
+
+**For CLI:**
+
+```bash
+claude mcp list
+```
+
+**For VS Code:**
+
+1. Open VS Code
+2. View → Output
+3. Select "Claude" from the dropdown
+4. Look for MCP server connection logs
+
+### Common Errors
+
+| Error                                | Cause                         | Solution                                                                    |
+| ------------------------------------ | ----------------------------- | --------------------------------------------------------------------------- |
+| `Connection timed out after 30000ms` | Server took too long to start | Move server earlier in config, or use pre-installed packages instead of npx |
+| `npm error 404 Not Found`            | Package doesn't exist         | Check package name spelling                                                 |
+| `The system cannot find the path`    | Wrong executable path         | Verify the command path exists                                              |
+| `Connection closed`                  | Server crashed on startup     | Check server logs, verify environment variables                             |
+
+### Disabling Problem Servers
+
+In `~/.claude/settings.json`, add `"disabled": true`:
+
+```json
+"problem-server": {
+  "command": "...",
+  "args": ["..."],
+  "disabled": true
+}
+```
+
+**Note:** The CLI config (`~/.claude.json`) does not support the `disabled` flag. You must remove the server entirely from that file.
+
+## Adding a New MCP Server
+
+1. **Install/clone the MCP server** (if not using npx)
+
+2. **Add to VS Code config** (`~/.claude/settings.json`):
+
+   ```json
+   "new-server": {
+     "command": "path/to/command",
+     "args": ["arg1", "arg2"],
+     "env": { "VAR": "value" }
+   }
+   ```
+
+3. **Add to CLI config** (`~/.claude.json`) - find the `mcpServers` section:
+
+   ```json
+   "new-server": {
+     "type": "stdio",
+     "command": "path/to/command",
+     "args": ["arg1", "arg2"],
+     "env": { "VAR": "value" }
+   }
+   ```
+
+4. **Fully restart VS Code**
+
+5. **Verify with `claude mcp list`**
+
+## Quick Reference: Available MCP Servers
+
+| Server              | Package/Repo                                       | Purpose                     |
+| ------------------- | -------------------------------------------------- | --------------------------- |
+| memory              | `@modelcontextprotocol/server-memory`              | Knowledge graph persistence |
+| filesystem          | `@modelcontextprotocol/server-filesystem`          | File system access          |
+| redis               | `@modelcontextprotocol/server-redis`               | Redis cache inspection      |
+| postgres            | `@modelcontextprotocol/server-postgres`            | PostgreSQL queries          |
+| sequential-thinking | `@modelcontextprotocol/server-sequential-thinking` | Step-by-step reasoning      |
+| podman              | `podman-mcp-server`                                | Container management        |
+| gitea               | `gitea-mcp` (binary)                               | Gitea API access            |
+| bugsink             | `j-shelfwood/bugsink-mcp` (build from source)      | Error tracking for Bugsink  |
+| sentry              | `@sentry/mcp-server`                               | Error tracking for Sentry   |
+| playwright          | `@anthropics/mcp-server-playwright`                | Browser automation          |
+
+## Best Practices
+
+1. **Keep configs in sync** - When you change one file, update the other
+
+2. **Order servers by importance** - Put essential servers (memory, filesystem) first
+
+3. **Disable instead of delete** - Use `"disabled": true` in settings.json to troubleshoot
+
+4. **Use node.exe directly** - For faster startup, install packages globally and use `node.exe` instead of `npx`
+
+5. **Store sensitive data in memory** - Use the memory MCP to store API tokens and config for future sessions
+
+---
+
+## Future: MCP Launchpad
+
+**Project:** <https://github.com/kenneth-liao/mcp-launchpad>
+
+MCP Launchpad is a CLI tool that wraps multiple MCP servers into a single interface. Worth revisiting when:
+
+- [ ] Windows support is stable (currently experimental)
+- [ ] Available as an MCP server itself (currently Bash-based)
+
+**Why it's interesting:**
+
+| Benefit                | Description                                                    |
+| ---------------------- | -------------------------------------------------------------- |
+| Single config file     | No more syncing `~/.claude.json` and `~/.claude/settings.json` |
+| Project-level configs  | Drop `mcp.json` in any project for instant MCP setup           |
+| Context window savings | One MCP server in context instead of 10+, reducing token usage |
+| Persistent daemon      | Keeps server connections alive for faster repeated calls       |
+| Tool search            | Find tools across all servers with `mcpl search`               |
+
+**Current limitations:**
+
+- Experimental Windows support
+- Requires Python 3.13+ and uv
+- Claude calls tools via Bash instead of native MCP integration
+- Different mental model (runtime discovery vs startup loading)
+
+---
+
+## Future: Graphiti (Advanced Knowledge Graph)
+
+**Project:** <https://github.com/getzep/graphiti>
+
+Graphiti provides temporal-aware knowledge graphs - it tracks not just facts, but _when_ they became true/outdated. Much more powerful than simple memory MCP, but requires significant infrastructure.
+
+**Ideal setup:** Run on a Linux server, connect via HTTP from Windows:
+
+```json
+// Windows client config (settings.json)
+"graphiti": {
+  "type": "sse",
+  "url": "http://linux-server:8000/mcp/"
+}
+```
+
+**Linux server setup:**
+
+```bash
+git clone https://github.com/getzep/graphiti.git
+cd graphiti/mcp_server
+docker compose up -d  # Starts FalkorDB + MCP server on port 8000
+```
+
+**Requirements:**
+
+- Docker on Linux server
+- OpenAI API key (for embeddings)
+- Port 8000 open on LAN
+
+**Benefits of remote deployment:**
+
+- Heavy lifting (Neo4j/FalkorDB + embeddings) offloaded to Linux
+- Always-on server, Windows connects/disconnects freely
+- Multiple machines can share the same knowledge graph
+- Avoids Windows Docker/WSL2 complexity
+
+---
+
+\_Last updated: January 2026

CLAUDE.md

@@ -1,5 +1,35 @@
 # Claude Code Project Instructions
 
+## Session Startup Checklist
+
+**IMPORTANT**: At the start of every session, perform these steps:
+
+1. **Check Memory First** - Use `mcp__memory__read_graph` or `mcp__memory__search_nodes` to recall:
+   - Project-specific configurations and credentials
+   - Previous work context and decisions
+   - Infrastructure details (URLs, ports, access patterns)
+   - Known issues and their solutions
+
+2. **Review Recent Git History** - Check `git log --oneline -10` to understand recent changes
+
+3. **Check Container Status** - Use `mcp__podman__container_list` to see what's running
+
+---
+
+## Project Instructions
+
+### Things to Remember
+
+Before writing any code:
+
+1. State how you will verify this change works (test, bash command, browser check, etc.)
+
+2. Write the test or verification step first
+
+3. Then implement the code
+
+4. Run verification and iterate until it passes
+
 ## Communication Style: Ask Before Assuming
 
 **IMPORTANT**: When helping with tasks, **ask clarifying questions before making assumptions**. Do not assume:
@@ -40,10 +70,16 @@ npm run test:integration  # Run integration tests (requires DB/Redis)
 
 ### Running Tests via Podman (from Windows host)
 
+**Note:** This project has 2900+ unit tests. For AI-assisted development, pipe output to a file for easier processing.
+
 The command to run unit tests in the dev container via podman:
 
 ```bash
+# Basic (output to terminal)
 podman exec -it flyer-crawler-dev npm run test:unit
+
+# Recommended for AI processing: pipe to file
+podman exec -it flyer-crawler-dev npm run test:unit 2>&1 | tee test-results.txt
 ```
 
 The command to run integration tests in the dev container via podman:
@@ -257,7 +293,7 @@ To add a new secret (e.g., `SENTRY_DSN`):
 
 **Shared (used by both environments):**
 
-- `DB_HOST`, `DB_USER`, `DB_PASSWORD` - Database credentials
+- `DB_HOST` - Database host (shared PostgreSQL server)
 - `JWT_SECRET` - Authentication
 - `GOOGLE_MAPS_API_KEY` - Google Maps
 - `GOOGLE_CLIENT_ID`, `GOOGLE_CLIENT_SECRET` - Google OAuth
@@ -265,14 +301,16 @@ To add a new secret (e.g., `SENTRY_DSN`):
 
 **Production-specific:**
 
-- `DB_DATABASE_PROD` - Production database name
+- `DB_USER_PROD`, `DB_PASSWORD_PROD` - Production database credentials (`flyer_crawler_prod`)
+- `DB_DATABASE_PROD` - Production database name (`flyer-crawler`)
 - `REDIS_PASSWORD_PROD` - Redis password (uses database 0)
 - `VITE_GOOGLE_GENAI_API_KEY` - Gemini API key for production
 - `SENTRY_DSN`, `VITE_SENTRY_DSN` - Bugsink error tracking DSNs (production projects)
 
 **Test-specific:**
 
-- `DB_DATABASE_TEST` - Test database name
+- `DB_USER_TEST`, `DB_PASSWORD_TEST` - Test database credentials (`flyer_crawler_test`)
+- `DB_DATABASE_TEST` - Test database name (`flyer-crawler-test`)
 - `REDIS_PASSWORD_TEST` - Redis password (uses database 1 for isolation)
 - `VITE_GOOGLE_GENAI_API_KEY_TEST` - Gemini API key for test
 - `SENTRY_DSN_TEST`, `VITE_SENTRY_DSN_TEST` - Bugsink error tracking DSNs (test projects)
@@ -286,6 +324,55 @@ The test environment (`flyer-crawler-test.projectium.com`) uses **both** Gitea C
 - **Redis database 1**: Isolates test job queues from production (which uses database 0)
 - **PM2 process names**: Suffixed with `-test` (e.g., `flyer-crawler-api-test`)
 
+### Database User Setup (Test Environment)
+
+**CRITICAL**: The test database requires specific PostgreSQL permissions to be configured manually. Schema ownership alone is NOT sufficient - explicit privileges must be granted.
+
+**Database Users:**
+
+| User                 | Database             | Purpose    |
+| -------------------- | -------------------- | ---------- |
+| `flyer_crawler_prod` | `flyer-crawler`      | Production |
+| `flyer_crawler_test` | `flyer-crawler-test` | Testing    |
+
+**Required Setup Commands** (run as `postgres` superuser):
+
+```bash
+# Connect as postgres superuser
+sudo -u postgres psql
+
+# Create the test database and user (if not exists)
+CREATE DATABASE "flyer-crawler-test";
+CREATE USER flyer_crawler_test WITH PASSWORD 'your-password-here';
+
+# Grant ownership and privileges
+ALTER DATABASE "flyer-crawler-test" OWNER TO flyer_crawler_test;
+\c "flyer-crawler-test"
+ALTER SCHEMA public OWNER TO flyer_crawler_test;
+GRANT CREATE, USAGE ON SCHEMA public TO flyer_crawler_test;
+
+# Create required extension (must be done by superuser)
+CREATE EXTENSION IF NOT EXISTS "uuid-ossp";
+```
+
+**Why These Steps Are Necessary:**
+
+1. **Schema ownership alone is insufficient** - PostgreSQL requires explicit `GRANT CREATE, USAGE` privileges even when the user owns the schema
+2. **uuid-ossp extension** - Required by the application for UUID generation; must be created by a superuser before the app can use it
+3. **Separate users for prod/test** - Prevents accidental cross-environment data access; each environment has its own credentials in Gitea secrets
+
+**Verification:**
+
+```bash
+# Check schema privileges (should show 'UC' for flyer_crawler_test)
+psql -d "flyer-crawler-test" -c "\dn+ public"
+
+# Expected output:
+#  Name  |       Owner        |            Access privileges
+# -------+--------------------+------------------------------------------
+# public | flyer_crawler_test | flyer_crawler_test=UC/flyer_crawler_test
+```
+
 ### Dev Container Environment
 
 The dev container runs its own **local Bugsink instance** - it does NOT connect to the production Bugsink server:
@@ -317,7 +404,7 @@ The following MCP servers are configured for this project:
 | redis                 | Redis cache inspection (localhost:6379)     |
 | sentry-selfhosted-mcp | Error tracking via Bugsink (localhost:8000) |
 
-**Note:** MCP servers are currently only available in **Claude CLI**. Due to a bug in Claude VS Code extension, MCP servers do not work there yet.
+**Note:** MCP servers work in both **Claude CLI** and **Claude Code VS Code extension** (as of January 2026).
 
 ### Sentry/Bugsink MCP Server Setup (ADR-015)
 
@@ -360,3 +447,26 @@ To enable Claude Code to query and analyze application errors from Bugsink:
    - Search by error message or stack trace
    - Update issue status (resolve, ignore)
    - Add comments to issues
+
+### SSH Server Access
+
+Claude Code can execute commands on the production server via SSH:
+
+```bash
+# Basic command execution
+ssh root@projectium.com "command here"
+
+# Examples:
+ssh root@projectium.com "systemctl status logstash"
+ssh root@projectium.com "pm2 list"
+ssh root@projectium.com "tail -50 /var/www/flyer-crawler.projectium.com/logs/app.log"
+```
+
+**Use cases:**
+
+- Managing Logstash, PM2, NGINX, Redis services
+- Viewing server logs
+- Deploying configuration changes
+- Checking service status
+
+**Important:** SSH access requires the host machine to have SSH keys configured for `root@projectium.com`.

DATABASE.md

@@ -149,7 +149,7 @@ SELECT PostGIS_Full_Version();
 
 Example output:
 
-```
+```text
 PostgreSQL 14.19 (Ubuntu 14.19-0ubuntu0.22.04.1)
 POSTGIS="3.2.0 c3e3cc0" GEOS="3.10.2-CAPI-1.16.0" PROJ="8.2.1"
 ```

docs/BARE-METAL-SETUP.md

@@ -244,19 +244,87 @@ For detailed information on secrets management, see [CLAUDE.md](../CLAUDE.md).
 sudo npm install -g pm2
 ```
 
-### Start Application with PM2
+### PM2 Configuration Files
+
+The application uses **separate ecosystem config files** for production and test environments:
+
+| File                        | Purpose               | Processes Started                                                                            |
+| --------------------------- | --------------------- | -------------------------------------------------------------------------------------------- |
+| `ecosystem.config.cjs`      | Production deployment | `flyer-crawler-api`, `flyer-crawler-worker`, `flyer-crawler-analytics-worker`                |
+| `ecosystem-test.config.cjs` | Test deployment       | `flyer-crawler-api-test`, `flyer-crawler-worker-test`, `flyer-crawler-analytics-worker-test` |
+
+**Key Points:**
+
+- Production and test processes run **simultaneously** with distinct names
+- Test processes use `NODE_ENV=test` which enables file logging
+- Test processes use Redis database 1 (isolated from production which uses database 0)
+- Both configs validate required environment variables but only warn (don't exit) if missing
+
+### Start Production Application
 
 ```bash
-cd /opt/flyer-crawler
-npm run start:prod
+cd /var/www/flyer-crawler.projectium.com
+
+# Set required environment variables (usually done via CI/CD)
+export DB_HOST=localhost
+export JWT_SECRET=your-secret
+export GEMINI_API_KEY=your-api-key
+# ... other required variables
+
+pm2 startOrReload ecosystem.config.cjs --update-env && pm2 save
 ```
 
-This starts three processes:
+This starts three production processes:
 
 - `flyer-crawler-api` - Main API server (port 3001)
 - `flyer-crawler-worker` - Background job worker
 - `flyer-crawler-analytics-worker` - Analytics processing worker
 
+### Start Test Application
+
+```bash
+cd /var/www/flyer-crawler-test.projectium.com
+
+# Set required environment variables (usually done via CI/CD)
+export DB_HOST=localhost
+export DB_NAME=flyer-crawler-test
+export JWT_SECRET=your-secret
+export GEMINI_API_KEY=your-test-api-key
+export REDIS_URL=redis://localhost:6379/1  # Use database 1 for isolation
+# ... other required variables
+
+pm2 startOrReload ecosystem-test.config.cjs --update-env && pm2 save
+```
+
+This starts three test processes (running alongside production):
+
+- `flyer-crawler-api-test` - Test API server (port 3001 via different NGINX vhost)
+- `flyer-crawler-worker-test` - Test background job worker
+- `flyer-crawler-analytics-worker-test` - Test analytics worker
+
+### Verify Running Processes
+
+After starting both environments, you should see 6 application processes:
+
+```bash
+pm2 list
+```
+
+Expected output:
+
+```text
+┌────┬───────────────────────────────────┬──────────┬────────┬───────────┐
+│ id │ name                              │ mode     │ status │ cpu       │
+├────┼───────────────────────────────────┼──────────┼────────┼───────────┤
+│ 0  │ flyer-crawler-api                 │ cluster  │ online │ 0%        │
+│ 1  │ flyer-crawler-worker              │ fork     │ online │ 0%        │
+│ 2  │ flyer-crawler-analytics-worker    │ fork     │ online │ 0%        │
+│ 3  │ flyer-crawler-api-test            │ fork     │ online │ 0%        │
+│ 4  │ flyer-crawler-worker-test         │ fork     │ online │ 0%        │
+│ 5  │ flyer-crawler-analytics-worker-test│ fork     │ online │ 0%        │
+└────┴───────────────────────────────────┴──────────┴────────┴───────────┘
+```
+
 ### Configure PM2 Startup
 
 ```bash
@@ -275,6 +343,22 @@ pm2 set pm2-logrotate:retain 14
 pm2 set pm2-logrotate:compress true
 ```
 
+### Useful PM2 Commands
+
+```bash
+# View logs for a specific process
+pm2 logs flyer-crawler-api-test --lines 50
+
+# View environment variables for a process
+pm2 env <process-id>
+
+# Restart only test processes
+pm2 restart flyer-crawler-api-test flyer-crawler-worker-test flyer-crawler-analytics-worker-test
+
+# Delete all test processes (without affecting production)
+pm2 delete flyer-crawler-api-test flyer-crawler-worker-test flyer-crawler-analytics-worker-test
+```
+
 ---
 
 ## NGINX Reverse Proxy
@@ -796,16 +880,18 @@ Logstash aggregates logs from the application and infrastructure, forwarding err
 
 ### Step 1: Create Application Log Directory
 
-Create the log directory and set appropriate permissions:
+The flyer-crawler application automatically creates its log directory on startup, but you need to ensure proper permissions for Logstash to read the logs.
+
+Create the log directories and set appropriate permissions:
 
 ```bash
-# Create log directory for the flyer-crawler application
+# Create log directory for the production application
 sudo mkdir -p /var/www/flyer-crawler.projectium.com/logs
 
-# Set ownership to the user running the application (typically the deploy user or www-data)
-sudo chown -R $USER:$USER /var/www/flyer-crawler.projectium.com/logs
+# Set ownership to root (since PM2 runs as root)
+sudo chown -R root:root /var/www/flyer-crawler.projectium.com/logs
 
-# Ensure logstash user can read the logs
+# Make logs readable by logstash user
 sudo chmod 755 /var/www/flyer-crawler.projectium.com/logs
 ```
 
@@ -813,26 +899,47 @@ For the test environment:
 
 ```bash
 sudo mkdir -p /var/www/flyer-crawler-test.projectium.com/logs
-sudo chown -R $USER:$USER /var/www/flyer-crawler-test.projectium.com/logs
+sudo chown -R root:root /var/www/flyer-crawler-test.projectium.com/logs
 sudo chmod 755 /var/www/flyer-crawler-test.projectium.com/logs
 ```
 
-### Step 2: Configure Application to Write File Logs
+### Step 2: Application File Logging (Already Configured)
 
-The flyer-crawler application uses Pino for logging and currently outputs to stdout (captured by PM2). To enable file-based logging for Logstash, you would need to configure Pino to write to files.
+The flyer-crawler application uses Pino for logging and is configured to write logs to files in production/test environments:
 
-**Current Behavior:** Logs go to stdout → PM2 captures them → `~/.pm2/logs/`
+**Log File Locations:**
 
-**For Logstash Integration:** You would need to either:
+| Environment   | Log File Path                                             |
+| ------------- | --------------------------------------------------------- |
+| Production    | `/var/www/flyer-crawler.projectium.com/logs/app.log`      |
+| Test          | `/var/www/flyer-crawler-test.projectium.com/logs/app.log` |
+| Dev Container | `/app/logs/app.log`                                       |
 
-1. Configure Pino to write directly to files (requires code changes)
-2. Use PM2's log files instead (located at `~/.pm2/logs/flyer-crawler-*.log`)
+**How It Works:**
 
-For now, we'll use PM2's log files which already exist:
+- In production/test: Pino writes JSON logs to both stdout (for PM2) AND `logs/app.log` (for Logstash)
+- In development: Pino uses pino-pretty for human-readable console output only
+- The log directory is created automatically if it doesn't exist
+- You can override the log directory with the `LOG_DIR` environment variable
+
+**Verify Logging After Deployment:**
+
+After deploying the application, verify that logs are being written:
 
 ```bash
-# Check PM2 log location
-ls -la ~/.pm2/logs/
+# Check production logs
+ls -la /var/www/flyer-crawler.projectium.com/logs/
+tail -f /var/www/flyer-crawler.projectium.com/logs/app.log
+
+# Check test logs
+ls -la /var/www/flyer-crawler-test.projectium.com/logs/
+tail -f /var/www/flyer-crawler-test.projectium.com/logs/app.log
+```
+
+You should see JSON-formatted log entries like:
+
+```json
+{ "level": 30, "time": 1704067200000, "msg": "Server started on port 3001", "module": "server" }
 ```
 
 ### Step 3: Install Logstash
@@ -861,14 +968,13 @@ Create the pipeline configuration file:
 sudo nano /etc/logstash/conf.d/bugsink.conf
 ```
 
-Add the following content (adjust paths as needed):
+Add the following content:
 
 ```conf
 input {
-  # PM2 application logs (Pino JSON format)
-  # PM2 stores logs in the home directory of the user running PM2
+  # Production application logs (Pino JSON format)
   file {
-    path => "/root/.pm2/logs/flyer-crawler-api-out.log"
+    path => "/var/www/flyer-crawler.projectium.com/logs/app.log"
     codec => json_lines
     type => "pino"
     tags => ["app", "production"]
@@ -876,18 +982,9 @@ input {
     sincedb_path => "/var/lib/logstash/sincedb_pino_prod"
   }
 
-  # PM2 error logs
+  # Test environment logs
   file {
-    path => "/root/.pm2/logs/flyer-crawler-api-error.log"
-    type => "pm2-error"
-    tags => ["app", "production", "error"]
-    start_position => "end"
-    sincedb_path => "/var/lib/logstash/sincedb_pm2_error_prod"
-  }
-
-  # Test environment logs (if running on same server)
-  file {
-    path => "/root/.pm2/logs/flyer-crawler-api-test-out.log"
+    path => "/var/www/flyer-crawler-test.projectium.com/logs/app.log"
     codec => json_lines
     type => "pino"
     tags => ["app", "test"]
@@ -895,21 +992,61 @@ input {
     sincedb_path => "/var/lib/logstash/sincedb_pino_test"
   }
 
-  # Redis logs
+  # Redis logs (shared by both environments)
   file {
     path => "/var/log/redis/redis-server.log"
     type => "redis"
-    tags => ["redis"]
+    tags => ["infra", "redis", "production"]
     start_position => "end"
     sincedb_path => "/var/lib/logstash/sincedb_redis"
   }
+
+  # NGINX error logs (production)
+  file {
+    path => "/var/log/nginx/error.log"
+    type => "nginx"
+    tags => ["infra", "nginx", "production"]
+    start_position => "end"
+    sincedb_path => "/var/lib/logstash/sincedb_nginx_error"
+  }
+
+  # NGINX access logs - for detecting 5xx errors (production)
+  file {
+    path => "/var/log/nginx/access.log"
+    type => "nginx_access"
+    tags => ["infra", "nginx", "production"]
+    start_position => "end"
+    sincedb_path => "/var/lib/logstash/sincedb_nginx_access"
+  }
+
+  # PM2 error logs - Production (plain text stack traces)
+  file {
+    path => "/home/gitea-runner/.pm2/logs/flyer-crawler-*-error.log"
+    exclude => "*-test-error.log"
+    type => "pm2"
+    tags => ["infra", "pm2", "production"]
+    start_position => "end"
+    sincedb_path => "/var/lib/logstash/sincedb_pm2_prod"
+  }
+
+  # PM2 error logs - Test
+  file {
+    path => "/home/gitea-runner/.pm2/logs/flyer-crawler-*-test-error.log"
+    type => "pm2"
+    tags => ["infra", "pm2", "test"]
+    start_position => "end"
+    sincedb_path => "/var/lib/logstash/sincedb_pm2_test"
+  }
 }
 
 filter {
-  # Pino error detection (level 50 = error, 60 = fatal)
+  # Pino log level detection
+  # Pino levels: 10=trace, 20=debug, 30=info, 40=warn, 50=error, 60=fatal
   if [type] == "pino" and [level] {
     if [level] >= 50 {
       mutate { add_tag => ["error"] }
+    } else if [level] >= 40 {
+      mutate { add_tag => ["warning"] }
     }
   }
 
@@ -923,66 +1060,144 @@ filter {
     }
   }
 
-  # PM2 error logs are always errors
-  if [type] == "pm2-error" {
+  # NGINX error log detection (all entries are errors)
+  if [type] == "nginx" {
     mutate { add_tag => ["error"] }
+    grok {
+      match => { "message" => "%{TIMESTAMP_ISO8601:timestamp} \[%{WORD:severity}\] %{GREEDYDATA:nginx_message}" }
+    }
+  }
+
+  # NGINX access log - detect 5xx errors
+  if [type] == "nginx_access" {
+    grok {
+      match => { "message" => "%{COMBINEDAPACHELOG}" }
+    }
+    if [response] =~ /^5\d{2}$/ {
+      mutate { add_tag => ["error"] }
+    }
+  }
+
+  # PM2 error log detection - tag lines with actual error indicators
+  if [type] == "pm2" {
+    if [message] =~ /Error:|error:|ECONNREFUSED|ENOENT|TypeError|ReferenceError|SyntaxError/ {
+      mutate { add_tag => ["error"] }
+    }
   }
 }
 
 output {
-  # Only send errors to Bugsink
-  if "error" in [tags] {
+  # Production app errors -> flyer-crawler-backend (project 1)
+  if "error" in [tags] and "app" in [tags] and "production" in [tags] {
     http {
       url => "http://localhost:8000/api/1/store/"
       http_method => "post"
       format => "json"
       headers => {
-        "X-Sentry-Auth" => "Sentry sentry_version=7, sentry_client=logstash/1.0, sentry_key=YOUR_BACKEND_DSN_KEY"
+        "X-Sentry-Auth" => "Sentry sentry_version=7, sentry_client=logstash/1.0, sentry_key=YOUR_PROD_BACKEND_DSN_KEY"
       }
     }
   }
 
-  # Debug output (remove in production after confirming it works)
+  # Test app errors -> flyer-crawler-backend-test (project 3)
+  if "error" in [tags] and "app" in [tags] and "test" in [tags] {
+    http {
+      url => "http://localhost:8000/api/3/store/"
+      http_method => "post"
+      format => "json"
+      headers => {
+        "X-Sentry-Auth" => "Sentry sentry_version=7, sentry_client=logstash/1.0, sentry_key=YOUR_TEST_BACKEND_DSN_KEY"
+      }
+    }
+  }
+
+  # Production infrastructure errors (Redis, NGINX, PM2) -> flyer-crawler-infrastructure (project 5)
+  if "error" in [tags] and "infra" in [tags] and "production" in [tags] {
+    http {
+      url => "http://localhost:8000/api/5/store/"
+      http_method => "post"
+      format => "json"
+      headers => {
+        "X-Sentry-Auth" => "Sentry sentry_version=7, sentry_client=logstash/1.0, sentry_key=b083076f94fb461b889d5dffcbef43bf"
+      }
+    }
+  }
+
+  # Test infrastructure errors (PM2 test logs) -> flyer-crawler-test-infrastructure (project 6)
+  if "error" in [tags] and "infra" in [tags] and "test" in [tags] {
+    http {
+      url => "http://localhost:8000/api/6/store/"
+      http_method => "post"
+      format => "json"
+      headers => {
+        "X-Sentry-Auth" => "Sentry sentry_version=7, sentry_client=logstash/1.0, sentry_key=25020dd6c2b74ad78463ec90e90fadab"
+      }
+    }
+  }
+
+  # Debug output (uncomment to troubleshoot)
   # stdout { codec => rubydebug }
 }
 ```
 
-**Important:** Replace `YOUR_BACKEND_DSN_KEY` with the key from your Bugsink backend DSN. The key is the part before the `@` symbol in the DSN URL.
+**Bugsink Project DSNs:**
 
-For example, if your DSN is:
+| Project                             | DSN Key                            | Project ID |
+| ----------------------------------- | ---------------------------------- | ---------- |
+| `flyer-crawler-backend`             | `911aef02b9a548fa8fabb8a3c81abfe5` | 1          |
+| `flyer-crawler-frontend`            | (used by app, not Logstash)        | 2          |
+| `flyer-crawler-backend-test`        | `cdb99c314589431e83d4cc38a809449b` | 3          |
+| `flyer-crawler-frontend-test`       | (used by app, not Logstash)        | 4          |
+| `flyer-crawler-infrastructure`      | `b083076f94fb461b889d5dffcbef43bf` | 5          |
+| `flyer-crawler-test-infrastructure` | `25020dd6c2b74ad78463ec90e90fadab` | 6          |
 
-```text
-https://abc123def456@bugsink.yourdomain.com/1
-```
+**Note:** The DSN key is the part before `@` in the full DSN URL (e.g., `https://KEY@bugsink.projectium.com/PROJECT_ID`).
 
-Then `YOUR_BACKEND_DSN_KEY` is `abc123def456`.
+**Note on PM2 Logs:** PM2 error logs capture stack traces from stderr, which are valuable for debugging startup errors and uncaught exceptions. Production PM2 logs go to project 5 (infrastructure), test PM2 logs go to project 6 (test-infrastructure).
 
-### Step 5: Create Logstash State Directory
+### Step 5: Create Logstash State Directory and Fix Config Path
 
-Logstash needs a directory to track which log lines it has already processed:
+Logstash needs a directory to track which log lines it has already processed, and a symlink so it can find its config files:
 
 ```bash
+# Create state directory for sincedb files
 sudo mkdir -p /var/lib/logstash
 sudo chown logstash:logstash /var/lib/logstash
+
+# Create symlink so Logstash finds its config (avoids "Could not find logstash.yml" warning)
+sudo ln -sf /etc/logstash /usr/share/logstash/config
 ```
 
-### Step 6: Grant Logstash Access to PM2 Logs
+### Step 6: Grant Logstash Access to Application Logs
 
-Logstash runs as the `logstash` user and needs permission to read PM2 logs:
+Logstash runs as the `logstash` user and needs permission to read log files:
 
 ```bash
-# Add logstash user to the group that owns PM2 logs
-# If PM2 runs as root:
-sudo usermod -a -G root logstash
+# Add logstash user to adm group (for nginx and redis logs)
+sudo usermod -aG adm logstash
 
-# Or, make PM2 logs world-readable (less secure but simpler)
-sudo chmod 644 /root/.pm2/logs/*.log
+# Make application log files readable (created automatically when app starts)
+sudo chmod 644 /var/www/flyer-crawler.projectium.com/logs/app.log 2>/dev/null || echo "Production log file not yet created"
+sudo chmod 644 /var/www/flyer-crawler-test.projectium.com/logs/app.log 2>/dev/null || echo "Test log file not yet created"
 
-# For Redis logs
+# Make Redis logs and directory readable
+sudo chmod 755 /var/log/redis/
 sudo chmod 644 /var/log/redis/redis-server.log
+
+# Make NGINX logs readable
+sudo chmod 644 /var/log/nginx/access.log /var/log/nginx/error.log
+
+# Make PM2 logs and directories accessible
+sudo chmod 755 /home/gitea-runner/
+sudo chmod 755 /home/gitea-runner/.pm2/
+sudo chmod 755 /home/gitea-runner/.pm2/logs/
+sudo chmod 644 /home/gitea-runner/.pm2/logs/*.log
+
+# Verify logstash group membership
+groups logstash
 ```
 
-**Note:** If PM2 runs as a different user, adjust the group accordingly.
+**Note:** The application log files are created automatically when the application starts. Run the chmod commands after the first deployment.
 
 ### Step 7: Test Logstash Configuration
 

docs/adr/0019-data-backup-and-recovery-strategy.md

@@ -42,9 +42,9 @@ jobs:
     env:
       DB_HOST: ${{ secrets.DB_HOST }}
       DB_PORT: ${{ secrets.DB_PORT }}
-      DB_USER: ${{ secrets.DB_USER }}
-      DB_PASSWORD: ${{ secrets.DB_PASSWORD }}
-      DB_NAME: ${{ secrets.DB_NAME_PROD }}
+      DB_USER: ${{ secrets.DB_USER_PROD }}
+      DB_PASSWORD: ${{ secrets.DB_PASSWORD_PROD }}
+      DB_NAME: ${{ secrets.DB_DATABASE_PROD }}
 
     steps:
       - name: Validate Secrets

ecosystem-test.config.cjs

@@ -0,0 +1,158 @@
+// ecosystem-test.config.cjs
+// PM2 configuration for the TEST environment only.
+// NOTE: The filename must end with `.config.cjs` for PM2 to recognize it as a config file.
+// This file defines test-specific apps that run alongside production apps.
+//
+// Test apps: flyer-crawler-api-test, flyer-crawler-worker-test, flyer-crawler-analytics-worker-test
+//
+// These apps:
+// - Run from /var/www/flyer-crawler-test.projectium.com
+// - Use NODE_ENV='staging' (enables file logging in logger.server.ts)
+// - Use Redis database 1 (isolated from production which uses database 0)
+// - Have distinct PM2 process names to avoid conflicts with production
+
+// --- Load Environment Variables from .env file ---
+// This allows PM2 to start without requiring the CI/CD pipeline to inject variables.
+// The .env file should be created on the server with the required secrets.
+// NOTE: We implement a simple .env parser since dotenv may not be installed.
+const path = require('path');
+const fs = require('fs');
+
+const envPath = path.join('/var/www/flyer-crawler-test.projectium.com', '.env');
+if (fs.existsSync(envPath)) {
+  console.log('[ecosystem-test.config.cjs] Loading environment from:', envPath);
+  const envContent = fs.readFileSync(envPath, 'utf8');
+  const lines = envContent.split('\n');
+  for (const line of lines) {
+    // Skip comments and empty lines
+    const trimmed = line.trim();
+    if (!trimmed || trimmed.startsWith('#')) continue;
+
+    // Parse KEY=value
+    const eqIndex = trimmed.indexOf('=');
+    if (eqIndex > 0) {
+      const key = trimmed.substring(0, eqIndex);
+      let value = trimmed.substring(eqIndex + 1);
+      // Remove quotes if present
+      if (
+        (value.startsWith('"') && value.endsWith('"')) ||
+        (value.startsWith("'") && value.endsWith("'"))
+      ) {
+        value = value.slice(1, -1);
+      }
+      // Only set if not already in environment (don't override CI/CD vars)
+      if (!process.env[key]) {
+        process.env[key] = value;
+      }
+    }
+  }
+  console.log('[ecosystem-test.config.cjs] Environment loaded successfully');
+} else {
+  console.warn('[ecosystem-test.config.cjs] No .env file found at:', envPath);
+  console.warn(
+    '[ecosystem-test.config.cjs] Environment variables must be provided by the shell or CI/CD.'
+  );
+}
+
+// --- Environment Variable Validation ---
+// NOTE: We only WARN about missing secrets, not exit.
+// Calling process.exit(1) prevents PM2 from reading the apps array.
+// The actual application will fail to start if secrets are missing,
+// which PM2 will handle with its restart logic.
+const requiredSecrets = ['DB_HOST', 'JWT_SECRET', 'GEMINI_API_KEY'];
+const missingSecrets = requiredSecrets.filter(key => !process.env[key]);
+
+if (missingSecrets.length > 0) {
+  console.warn('\n[ecosystem.config.test.cjs] WARNING: The following environment variables are MISSING:');
+  missingSecrets.forEach(key => console.warn(`   - ${key}`));
+  console.warn('[ecosystem.config.test.cjs] The application may fail to start if these are required.\n');
+} else {
+  console.log('[ecosystem.config.test.cjs] Critical environment variables are present.');
+}
+
+// --- Shared Environment Variables ---
+const sharedEnv = {
+  DB_HOST: process.env.DB_HOST,
+  DB_USER: process.env.DB_USER,
+  DB_PASSWORD: process.env.DB_PASSWORD,
+  DB_NAME: process.env.DB_NAME,
+  REDIS_URL: process.env.REDIS_URL,
+  REDIS_PASSWORD: process.env.REDIS_PASSWORD,
+  FRONTEND_URL: process.env.FRONTEND_URL,
+  JWT_SECRET: process.env.JWT_SECRET,
+  GEMINI_API_KEY: process.env.GEMINI_API_KEY,
+  GOOGLE_MAPS_API_KEY: process.env.GOOGLE_MAPS_API_KEY,
+  SMTP_HOST: process.env.SMTP_HOST,
+  SMTP_PORT: process.env.SMTP_PORT,
+  SMTP_SECURE: process.env.SMTP_SECURE,
+  SMTP_USER: process.env.SMTP_USER,
+  SMTP_PASS: process.env.SMTP_PASS,
+  SMTP_FROM_EMAIL: process.env.SMTP_FROM_EMAIL,
+  SENTRY_DSN: process.env.SENTRY_DSN,
+  SENTRY_ENVIRONMENT: process.env.SENTRY_ENVIRONMENT,
+  SENTRY_ENABLED: process.env.SENTRY_ENABLED,
+};
+
+module.exports = {
+  apps: [
+    // =========================================================================
+    // TEST APPS
+    // =========================================================================
+    {
+      // --- Test API Server ---
+      name: 'flyer-crawler-api-test',
+      script: './node_modules/.bin/tsx',
+      args: 'server.ts',
+      cwd: '/var/www/flyer-crawler-test.projectium.com',
+      max_memory_restart: '500M',
+      // Test environment: single instance (no cluster) to conserve resources
+      instances: 1,
+      exec_mode: 'fork',
+      kill_timeout: 5000,
+      log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
+      max_restarts: 40,
+      exp_backoff_restart_delay: 100,
+      min_uptime: '10s',
+      env: {
+        NODE_ENV: 'staging',
+        PORT: 3002,
+        WORKER_LOCK_DURATION: '120000',
+        ...sharedEnv,
+      },
+    },
+    {
+      // --- Test General Worker ---
+      name: 'flyer-crawler-worker-test',
+      script: './node_modules/.bin/tsx',
+      args: 'src/services/worker.ts',
+      cwd: '/var/www/flyer-crawler-test.projectium.com',
+      max_memory_restart: '1G',
+      kill_timeout: 10000,
+      log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
+      max_restarts: 40,
+      exp_backoff_restart_delay: 100,
+      min_uptime: '10s',
+      env: {
+        NODE_ENV: 'staging',
+        ...sharedEnv,
+      },
+    },
+    {
+      // --- Test Analytics Worker ---
+      name: 'flyer-crawler-analytics-worker-test',
+      script: './node_modules/.bin/tsx',
+      args: 'src/services/worker.ts',
+      cwd: '/var/www/flyer-crawler-test.projectium.com',
+      max_memory_restart: '1G',
+      kill_timeout: 10000,
+      log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
+      max_restarts: 40,
+      exp_backoff_restart_delay: 100,
+      min_uptime: '10s',
+      env: {
+        NODE_ENV: 'staging',
+        ...sharedEnv,
+      },
+    },
+  ],
+};

ecosystem.config.cjs

@@ -2,18 +2,28 @@
 // This file is the standard way to configure applications for PM2.
 // It allows us to define all the settings for our application in one place.
 // The .cjs extension is required because the project's package.json has "type": "module".
+//
+// IMPORTANT: This file defines SEPARATE apps for production and test environments.
+// Production apps: flyer-crawler-api, flyer-crawler-worker, flyer-crawler-analytics-worker
+// Test apps: flyer-crawler-api-test, flyer-crawler-worker-test, flyer-crawler-analytics-worker-test
+//
+// Use ecosystem-test.config.cjs for test deployments (contains only test apps).
+// Use this file (ecosystem.config.cjs) for production deployments.
 
 // --- Environment Variable Validation ---
+// NOTE: We only WARN about missing secrets, not exit.
+// Calling process.exit(1) prevents PM2 from reading the apps array.
+// The actual application will fail to start if secrets are missing,
+// which PM2 will handle with its restart logic.
 const requiredSecrets = ['DB_HOST', 'JWT_SECRET', 'GEMINI_API_KEY'];
 const missingSecrets = requiredSecrets.filter(key => !process.env[key]);
 
 if (missingSecrets.length > 0) {
-  console.warn('\n[ecosystem.config.cjs] ⚠️  WARNING: The following environment variables are MISSING in the shell:');
+  console.warn('\n[ecosystem.config.cjs] WARNING: The following environment variables are MISSING:');
   missingSecrets.forEach(key => console.warn(`   - ${key}`));
-  console.warn('[ecosystem.config.cjs] The application may crash if these are required for startup.\n');
-  process.exit(1); // Fail fast so PM2 doesn't attempt to start a broken app
+  console.warn('[ecosystem.config.cjs] The application may fail to start if these are required.\n');
 } else {
-  console.log('[ecosystem.config.cjs] ✅ Critical environment variables are present.');
+  console.log('[ecosystem.config.cjs] Critical environment variables are present.');
 }
 
 // --- Shared Environment Variables ---
@@ -35,125 +45,67 @@ const sharedEnv = {
   SMTP_USER: process.env.SMTP_USER,
   SMTP_PASS: process.env.SMTP_PASS,
   SMTP_FROM_EMAIL: process.env.SMTP_FROM_EMAIL,
+  SENTRY_DSN: process.env.SENTRY_DSN,
+  SENTRY_ENVIRONMENT: process.env.SENTRY_ENVIRONMENT,
+  SENTRY_ENABLED: process.env.SENTRY_ENABLED,
 };
 
 module.exports = {
   apps: [
+    // =========================================================================
+    // PRODUCTION APPS
+    // =========================================================================
     {
-      // --- API Server ---
+      // --- Production API Server ---
       name: 'flyer-crawler-api',
-      // Note: The process names below are referenced in .gitea/workflows/ for status checks.
       script: './node_modules/.bin/tsx',
       args: 'server.ts',
+      cwd: '/var/www/flyer-crawler.projectium.com',
       max_memory_restart: '500M',
-      // Production Optimization: Run in cluster mode to utilize all CPU cores
       instances: 'max',
       exec_mode: 'cluster',
-      kill_timeout: 5000, // Allow 5s for graceful shutdown of API requests
+      kill_timeout: 5000,
       log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
-      
-      // Restart Logic
       max_restarts: 40,
       exp_backoff_restart_delay: 100,
       min_uptime: '10s',
-
-      // Production Environment Settings
-      env_production: {
+      env: {
         NODE_ENV: 'production',
-        name: 'flyer-crawler-api',
-        cwd: '/var/www/flyer-crawler.projectium.com',
-        WORKER_LOCK_DURATION: '120000',
-        ...sharedEnv,
-      },
-      // Test Environment Settings
-      env_test: {
-        NODE_ENV: 'test',
-        name: 'flyer-crawler-api-test',
-        cwd: '/var/www/flyer-crawler-test.projectium.com',
-        WORKER_LOCK_DURATION: '120000',
-        ...sharedEnv,
-      },
-      // Development Environment Settings
-      env_development: {
-        NODE_ENV: 'development',
-        name: 'flyer-crawler-api-dev',
-        watch: true,
-        ignore_watch: ['node_modules', 'logs', '*.log', 'flyer-images', '.git'],
         WORKER_LOCK_DURATION: '120000',
         ...sharedEnv,
       },
     },
     {
-      // --- General Worker ---
+      // --- Production General Worker ---
       name: 'flyer-crawler-worker',
       script: './node_modules/.bin/tsx',
       args: 'src/services/worker.ts',
+      cwd: '/var/www/flyer-crawler.projectium.com',
       max_memory_restart: '1G',
-      kill_timeout: 10000, // Workers may need more time to complete a job
+      kill_timeout: 10000,
       log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
-      
-      // Restart Logic
       max_restarts: 40,
       exp_backoff_restart_delay: 100,
       min_uptime: '10s',
-
-      // Production Environment Settings
-      env_production: {
+      env: {
         NODE_ENV: 'production',
-        name: 'flyer-crawler-worker',
-        cwd: '/var/www/flyer-crawler.projectium.com',
-        ...sharedEnv,
-      },
-      // Test Environment Settings
-      env_test: {
-        NODE_ENV: 'test',
-        name: 'flyer-crawler-worker-test',
-        cwd: '/var/www/flyer-crawler-test.projectium.com',
-        ...sharedEnv,
-      },
-      // Development Environment Settings
-      env_development: {
-        NODE_ENV: 'development',
-        name: 'flyer-crawler-worker-dev',
-        watch: true,
-        ignore_watch: ['node_modules', 'logs', '*.log', 'flyer-images', '.git'],
         ...sharedEnv,
       },
     },
     {
-      // --- Analytics Worker ---
+      // --- Production Analytics Worker ---
       name: 'flyer-crawler-analytics-worker',
       script: './node_modules/.bin/tsx',
       args: 'src/services/worker.ts',
+      cwd: '/var/www/flyer-crawler.projectium.com',
       max_memory_restart: '1G',
       kill_timeout: 10000,
       log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
-      
-      // Restart Logic
       max_restarts: 40,
       exp_backoff_restart_delay: 100,
       min_uptime: '10s',
-
-      // Production Environment Settings
-      env_production: {
+      env: {
         NODE_ENV: 'production',
-        name: 'flyer-crawler-analytics-worker',
-        cwd: '/var/www/flyer-crawler.projectium.com',
-        ...sharedEnv,
-      },
-      // Test Environment Settings
-      env_test: {
-        NODE_ENV: 'test',
-        name: 'flyer-crawler-analytics-worker-test',
-        cwd: '/var/www/flyer-crawler-test.projectium.com',
-        ...sharedEnv,
-      },
-      // Development Environment Settings
-      env_development: {
-        NODE_ENV: 'development',
-        name: 'flyer-crawler-analytics-worker-dev',
-        watch: true,
-        ignore_watch: ['node_modules', 'logs', '*.log', 'flyer-images', '.git'],
         ...sharedEnv,
       },
     },

etc-nginx-sites-available-flyer-crawler-test-projectium-com.txt

@@ -0,0 +1,69 @@
+# HTTPS Server Block (main)
+server {
+    listen 443 ssl;
+    listen [::]:443 ssl;
+    server_name flyer-crawler-test.projectium.com;
+
+    # SSL Configuration (managed by Certbot)
+    ssl_certificate /etc/letsencrypt/live/flyer-crawler-test.projectium.com/fullchain.pem;
+    ssl_certificate_key /etc/letsencrypt/live/flyer-crawler-test.projectium.com/privkey.pem;
+    include /etc/letsencrypt/options-ssl-nginx.conf;
+    ssl_dhparam /etc/letsencrypt/ssl-dhparams.pem;
+
+    # Allow large file uploads (e.g., for flyers)
+    client_max_body_size 100M;
+
+    # Root directory for built application files
+    root /var/www/flyer-crawler-test.projectium.com;
+    index index.html;
+
+    # Deny access to all dotfiles
+    location ~ /\. {
+        deny all;
+        return 404;
+    }
+
+    # Coverage report (must come before generic location /)
+    location /coverage/ {
+        try_files $uri $uri/ =404;
+    }
+
+    # SPA fallback for React Router
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+
+    # Reverse proxy for backend API
+    location /api/ {
+        proxy_connect_timeout 300s;
+        proxy_send_timeout    300s;
+        proxy_read_timeout    300s;
+
+        proxy_pass http://localhost:3002;
+        proxy_http_version 1.1;
+        proxy_set_header Upgrade $http_upgrade;
+        proxy_set_header Connection 'upgrade';
+        proxy_set_header Host $host;
+        proxy_cache_bypass $http_upgrade;
+    }
+
+    # Correct MIME type for .mjs files
+    location ~ \.mjs$ {
+        include /etc/nginx/mime.types;
+        default_type application/javascript;
+    }
+
+    # Security headers
+    add_header X-Frame-Options "SAMEORIGIN" always;
+    add_header X-XSS-Protection "1; mode=block" always;
+    add_header X-Content-Type-Options "nosniff" always;
+}
+
+# HTTP to HTTPS Redirect
+server {
+    listen 80;
+    listen [::]:80;
+    server_name flyer-crawler-test.projectium.com;
+
+    return 301 https://$host$request_uri;
+}

notes-to-ai5.txt

@@ -0,0 +1,196 @@
+What is the correct named pipe address for Podman on Windows if it's not using the default docker_engine pipe?
+
+How do I configure the chrome-devtools-mcp server to connect to an existing Chrome instance using the browser_url input?
+
+
+Unused Input: The browser_url input is defined but not used in any server arguments. If you intend to connect chrome-devtools-mcp to an existing Chrome instance, you would typically pass that URL in the arguments instead of launching a new headless instance.
+
+
+
+
+
+Based on your current configuration and project setup (Gitea, Podman, PostgreSQL, Redis), here are several other valuable MCP servers available for VS Code.
+
+Recommended for Your Stack
+Since you are running a PostgreSQL and Redis stack via Podman, these servers would be immediately useful:
+
+PostgreSQL (@modelcontextprotocol/server-postgres)
+
+Purpose: Allows the AI to query your database directly (inspect schemas, run SELECT queries) without needing to shell into the container.
+Config:
+json
+"postgres": {
+  "command": "npx",
+  "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://postgres:postgres@localhost:5432/flyer_crawler_dev"]
+}
+
+
+
+Redis (@modelcontextprotocol/server-redis)
+
+Purpose: Inspect and modify keys in your Redis instance.
+Config:
+json
+"redis": {
+  "command": "npx",
+  "args": ["-y", "@modelcontextprotocol/server-redis", "redis://localhost:6379"]
+}
+General Utility Servers
+These servers enhance the AI's core capabilities regardless of the specific project:
+
+
+Memory (@modelcontextprotocol/server-memory)
+
+Purpose: Gives the AI a persistent "knowledge graph" to remember context, user preferences, and project details across different chat sessions.
+Config:
+json
+"memory": {
+  "command": "npx",
+  "args": ["-y", "@modelcontextprotocol/server-memory"]
+}
+
+
+Brave Search (@modelcontextprotocol/server-brave-search)
+
+Purpose: Performs actual web searches (finding current docs, libraries, or solutions) rather than just fetching specific URLs like the fetch server does.
+Config:
+json
+ Show full code block 
+"brave-search": {
+  "command": "npx",
+  "args": ["-y", "@modelcontextprotocol/server-brave-search"],
+  "env": {
+    "BRAVE_API_KEY": "YOUR_API_KEY_HERE"
+  }
+}
+
+
+Sequential Thinking (@modelcontextprotocol/server-sequential-thinking)
+
+Purpose: A tool that helps the AI break down complex problems into step-by-step thought processes. It is particularly useful for debugging difficult logic or architectural planning.
+Config:
+json
+"sequential-thinking": {
+  "command": "npx",
+  "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+}
+
+
+Other Popular Servers
+
+GitHub: (@modelcontextprotocol/server-github) - If you ever need to interact with GitHub.com in addition to Gitea.
+
+Google Drive: (@modelcontextprotocol/server-google-drive) - Access files in Google Drive.
+
+Slack: (@modelcontextprotocol/server-slack) - Read and send Slack messages.
+
+Sentry: (@modelcontextprotocol/server-sentry) - Analyze error reports directly from Sentry.
+
+How to Find More
+The community maintains a comprehensive list of servers in the Awesome MCP Servers repository. You can find servers for almost any major tool (AWS, Azure, Linear, Jira, etc.).
+
+To add any of these, you simply add a new entry to the mcpServers object in your mcp.json file, similar to how you configured podman or fetch.
+
+
+
+
+
+
+Create a new ADR for "Worker Health Checks" to monitor stalled background jobs.
+
+Storybook !  for UI
+
+
+
+
+
+
+
+
+
+
+
+{
+  "mcpServers": {
+    "gitea-projectium": {
+      "command": "d:\\gitea-mcp\\gitea-mcp.exe",
+      "args": ["run", "-t", "stdio"],
+      "env": {
+        "GITEA_HOST": "https://gitea.projectium.com",
+        "GITEA_ACCESS_TOKEN": "b111259253aa3cadcb6a37618de03bf388f6235a"
+      }
+    },
+    "gitea-torbonium": {
+      "command": "d:\\gitea-mcp\\gitea-mcp.exe",
+      "args": ["run", "-t", "stdio"],
+      "env": {
+        "GITEA_HOST": "https://gitea.torbonium.com",
+        "GITEA_ACCESS_TOKEN": "563d01f9edc792b6dd09bf4cbd3a98bce45360a4"
+      }
+    },
+    "gitea-lan": {
+      "command": "d:\\gitea-mcp\\gitea-mcp.exe",
+      "args": ["run", "-t", "stdio"],
+      "env": {
+        "GITEA_HOST": "https://gitea.torbolan.com",
+        "GITEA_ACCESS_TOKEN": "YOUR_LAN_TOKEN_HERE"
+      },
+      "disabled": true
+    },
+    "podman": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "podman-mcp-server@latest"],
+      "env": {
+        "DOCKER_HOST": "npipe:////./pipe/podman-machine-default"
+      }
+    },
+    "filesystem": {
+      "command": "d:\\nodejs\\node.exe",
+      "args": [
+        "c:\\Users\\games3\\AppData\\Roaming\\npm\\node_modules\\@modelcontextprotocol\\server-filesystem\\dist\\index.js",
+        "d:\\gitea\\flyer-crawler.projectium.com\\flyer-crawler.projectium.com"
+      ]
+    },
+    "fetch": {
+      "command": "C:\\Users\\games3\\.local\\bin\\uvx.exe",
+      "args": ["mcp-server-fetch"]
+    },
+    "chrome-devtools": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": [
+        "chrome-devtools-mcp@latest",
+        "--headless",
+        "false",
+        "--isolated",
+        "false",
+        "--channel",
+        "stable"
+      ],
+      "disabled": true
+    },
+    "markitdown": {
+      "command": "C:\\Users\\games3\\.local\\bin\\uvx.exe",
+      "args": ["markitdown-mcp"]
+    },
+    "sequential-thinking": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+    },
+    "memory": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "@modelcontextprotocol/server-memory"]
+    },
+    "postgres": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://postgres:postgres@localhost:5432/flyer_crawler_dev"]
+    },
+    "playwright": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "@anthropics/mcp-server-playwright"]
+    },
+    "redis": {
+      "command": "D:\\nodejs\\npx.cmd",
+      "args": ["-y", "@modelcontextprotocol/server-redis", "redis://localhost:6379"]
+    }
+  }
+}

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "flyer-crawler",
-  "version": "0.9.97",
+  "version": "0.11.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "flyer-crawler",
-      "version": "0.9.97",
+      "version": "0.11.0",
       "dependencies": {
         "@bull-board/api": "^6.14.2",
         "@bull-board/express": "^6.14.2",

package.json

@@ -1,7 +1,7 @@
 {
   "name": "flyer-crawler",
   "private": true,
-  "version": "0.9.97",
+  "version": "0.11.0",
   "type": "module",
   "scripts": {
     "dev": "concurrently \"npm:start:dev\" \"vite\"",