feat: ability to specify variation key on config or from_options for optimization package

[andrewklatzke]

Requirements

• I have added test coverage for new or changed functionality
• I have followed the repository's pull request submission guidelines
• I have validated my changes against all supported platform versions

Describe the solution you've provided

Adds the ability to specify a specific variation when setting up your configuration within LaunchDarkly, or specify a specific variation key in the from_options method as long as the API key is present. This allows a user to optimize against a specific variation rather than the default.

Describe alternatives you've considered

This is a relatively straightforward feature request. Allowing users to specify a specific variation cuts down on toil of managing your agents in the UI (don't need to change targeting or create a dummy config).

Additional context

This is purely additive. Functionality for configs not using the variation key, or that don't have it set, is unchanged -- it will continue using the default pulled via the SDK.

---

Note

Medium Risk
Introduces a new code path that fetches AI config variations via the LaunchDarkly REST API (including model/tools overrides) and changes validation behavior when variation_key is set, so misconfiguration or API errors can now fail runs earlier.

Overview
Adds support for pinning an optimization run to a specific AI Config variation via a new variation_key option (and variationKey in config-driven runs), instead of always using the SDK-evaluated variation.

When provided, _get_agent_config now fetches the requested variation over the REST API (new LDApiClient.get_ai_config_variation) and uses its instructions, tools, and modelConfigKey as the optimization baseline; callers now enforce that LAUNCHDARKLY_API_KEY and project_key are set for this path. Tests are expanded to cover the new option wiring, API behavior, and error propagation.

^{Reviewed by Cursor Bugbot for commit c5e39eb. Bugbot is set up for automated code reviews on this repo. Configure here.}