Project Monitoring

Overview

Guardian's Project Monitoring feature provides real-time oversight of your codebase, identifying issues as you work using AI-powered analysis.

Starting Monitoring

Step 1: Select a Project

Click the Scope field or drag a folder onto the app
Select your project's root directory
The path will appear in the Scope selector

Step 2: Launch Guardian

Once you have:

Selected a valid project path
Configured your AI provider
Signed in with GitHub (device authorization, if required)

Click Launch Guardian to start monitoring.

How Monitoring Works

Guardian watches your project for file changes and analyzes code using your configured AI provider:

File Detection: Monitors for saved changes in your project
Batch Processing: Groups changes for efficient analysis
AI Analysis: Sends code to your configured AI provider for review
Results Display: Shows findings in the activity panel

Snapshot Hydration

If Guardian restarts or reconnects, it now hydrates the monitor view from the local snapshot (.guardian/critiques.json) before merging live updates. This prevents empty dashboards when there are existing findings in the workspace.

Scan Scope Profiles

Guardian includes three scan profiles so you can balance cost vs coverage.

You can change this in Settings > General > Scan Scope. Profile changes apply the next time you start monitoring.

Profile	What it focuses on	Typical use
Source (default)	Source code only. Skips low-signal files like docs/tests/scripts/lockfiles by default.	Day-to-day development monitoring with minimal noise and cost.
Extended	Source code plus infra/security surfaces (Docker/CI/workflows/shell/config/lockfiles). Still skips docs/tests by default.	Security-aware teams that want coverage on deploy/runtime surfaces.
Full	Most text files (including docs/tests/scripts/workflows). More findings, higher cost.	Deep one-off audits when you want maximum coverage.

Tip: If you feel Guardian is "wasting tokens" on the wrong file types, keep the profile on Source and only use Extended/Full when you explicitly need them.

Understanding Findings

Severity Levels

Level	Meaning	Action
Critical	High-risk security vulnerability or major issue	Fix immediately
Warning	Important issue or risky pattern	Address soon
Info	Informational or low-signal note	Optional

Finding Categories

Guardian can identify:

Security Issues: Vulnerabilities, exposed secrets
Code Quality: Anti-patterns, complexity
Performance: Inefficient patterns
Best Practices: Style and convention violations

Working with Findings

Viewing Details

Click any finding to see:

Description of the issue
Affected file and location
Suggested fix (if available)

Applying Fixes

If a finding includes a proposed fix, you'll see a FIX action:

Expand the finding to review the proposed content
Click FIX (or APPLY THIS FIX) to write the updated file
Use Guru to sanity-check the result and decide whether to keep or revert the change

Ask Guru

Click the Ask Guru action (bot icon) on a finding to get:

Detailed explanation of the issue
Alternative solutions
Best practice recommendations

Stopping Monitoring

Click Kill Guardian to stop monitoring:

All file watchers are stopped
Pending analyses are cancelled
The app returns to idle state

Activity Panel

The activity panel shows:

Real-time monitoring status
Recent findings with severity
Guru conversation history
Applied fixes log

Chat History

Guardian maintains chat history per project:

Conversations persist across sessions
Clear history via the chat panel
Export conversations as needed

Troubleshooting

Issue	Solution
No findings appearing	Check that files are being saved
Slow analysis	Consider using a faster AI model
Connection errors	Verify API key and network
High token usage	Reduce monitored file scope

Best Practices

Start Small: Begin with a focused directory
Review Before Apply: Always review suggested fixes
Use Guru: Ask for explanations on unclear findings
Monitor Costs: Track AI provider usage for paid APIs
Ignore Noise: Focus on high-severity issues first