Inference device management

[A-Artemis]

Summary

Adds inference device selection to pipeline configuration.

How to test

PATCH /api/projects/{project_id}/pipeline with {"device": "xpu"} in the body.

Checklist

• The PR title and description are clear and descriptive
• I have manually tested the changes
• All changes are covered by automated tests
• All related issues are linked to this PR (if applicable)
• Documentation has been updated (if applicable)

[Copilot]

Pull request overview

This PR adds device selection functionality for inference pipelines, allowing users to specify which hardware device (CPU, XPU, or CUDA) should be used for model inference.

• Adds device validation to ensure selected devices are available on the system
• Implements device configuration in pipeline settings with proper validation and event emission
• Adds comprehensive test coverage for device validation logic

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
application/backend/app/models/pipeline.py	Adds device field with regex pattern validation
application/backend/app/db/schema.py	Adds device column to pipelines table
application/backend/app/alembic/versions/2786b50eb5a4_schema.py	Migration to add device column with default value
application/backend/app/api/schemas/pipeline.py	Adds device field to API schema with description
application/backend/app/api/routers/pipelines.py	Adds device validation before pipeline updates
application/backend/app/services/pipeline_service.py	Persists device field and emits device change events
application/backend/app/services/event/event_bus.py	Adds DEVICE_CHANGED event type
application/backend/app/services/system_service.py	Implements validate_device method to check device availability
application/backend/tests/unit/services/test_system_service.py	Adds comprehensive tests for device validation

---

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

[github-actions]

📊 Test coverage report

Metric	Coverage
Lines	40.2%
Functions	34.9%
Branches	84.8%
Statements	40.2%

[github-actions]

Docker Image Sizes

CPU

Image	Size
geti-tune-cpu:pr-5058	2.80G
geti-tune-cpu:sha-b42ee2d	2.80G

GPU

Image	Size
geti-tune-gpu:pr-5058	10.56G
geti-tune-gpu:sha-b42ee2d	10.56G

XPU

Image	Size
geti-tune-xpu:pr-5058	8.63G
geti-tune-xpu:sha-b42ee2d	8.63G