feat: Implement resource requirements for components

[Copilot]

Summary

Adds resource specification support for components to enable Ray actor resource allocation and Tuner placement group optimization.

Changes

Core Schema

• Added Resource Pydantic class in plugboard_schemas.component with fields: cpu, gpu, memory, resources (custom dict)
• Supports Kubernetes-style string formats: "250m" → 0.25 CPU, "10Mi" → 10,485,760 bytes
• Default: cpu=0.001, others zero
• Implements to_ray_options() for Ray actor configuration

Component Integration

• Extended Component.__init__() with optional resources parameter
• Updated ComponentArgsDict, ComponentArgsSpec for YAML support
• Resources auto-exported and reconstructed from configuration

Ray Execution

• Modified RayProcess._create_component_actor() to apply resource requirements via ray.remote(**ray_options)
• Falls back to default Resource() when unspecified

Tuner Optimization

• Added Tuner._calculate_placement_bundles() to aggregate component resources
• Creates PlacementGroupFactory with tuner overhead (0.5 CPU) + component bundle

Usage Example

from plugboard.schemas import Resource

# Python API
component = MyComponent(
    name="worker",
    resources=Resource(cpu=2.0, gpu=1, memory="512Mi")
)

# YAML config
resources:
  cpu: "500m"
  gpu: 1
  memory: "100Mi"
  resources:
    custom_accelerator: 2

Tests

• Unit tests: Resource parsing, validation, Ray conversion
• Integration tests: Component/ProcessSpec/Tuner scenarios
• Manual verification (full test suite requires Ray dependencies)

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: /usr/bin/curl curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>feat: Implement resource requirements for components</issue_title>
<issue_description>### Summary

Users would like to be able to specify custom resource requirements on Component objects. These can be passed to Ray when a RayProcess is used or a Tuner object is run.

Requirements:

• Must be able to specify Resource requirements for cpu, gpu, memory, resources. These should be defined as a Pydantic class in plugboard_schemas.
• Must be able to specify resources as a numerical value, or as a string (to be validated by Pydantic), e.g. 250m for 0.25 or 10Mi for 1024 * 1024 * 10. resources should be a dictionary of string key, numerical value pairs.
• Must be able to convert these requirements to their Ray equivalents, see https://docs.ray.io/en/latest/ray-core/api/doc/ray.actor.ActorClass.options.html, i.e. cpu = "250m" gets converted to num_cpus=0.25.
• Must be able to pass a Resource to a Component when instantiating it. This will require changes to the Component and its schema, so that we can specify resource requirements in YAML config.
• The default requirement should be {"cpu": 0.001}, to be used if the user does not provide anything.
• Resource requirements should be passed to the actor options in RayProcess.
• They should be used in the resource placement group inside Tuner.

Example

No response

Alternatives

No response</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes feat: Implement resource requirements for components #193

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[toby-coleman]

@copilot Can you make this more general? For example by using/supporting any of the following suffixes:

    suffixes = {
        'n': 1e-9, 'u': 1e-6, 'm': 1e-3,  # Decimal SI
        'k': 1e3, 'M': 1e6, 'G': 1e9, 'T': 1e12, 'P': 1e15, 'E': 1e18,
        'Ki': 1024, 'Mi': 1024**2, 'Gi': 1024**3, 'Ti': 1024**4, 'Pi': 1024**5, 'Ei': 1024**6
    }

[toby-coleman]

Memory should be specified as an integer number of bytes

[toby-coleman]

Suggested change

	resources: _t.NotRequired["Resource | None"]
	resources: _t.NotRequired[Resource | None]

[toby-coleman]

Move this import to the top