feat: dx improvements 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

Improves the developer experience when using the SDK and fixes a bug where the global model was being ignored for judges.

Describe alternatives you've considered

This is a QoL change for folks consuming this SDK method. Weren't really alternatives considered.

Additional context

the TLDR; here is that when implementing this against multiple frameworks I found myself falling into the pattern of specifying the same handler for both agents and judges. Since that's the case, I've updated it so that handle_judge_call is optional and defaults to handle_agent_call if it's not specified. With this change, the optimization config when using an LD-built config is reduced to just this:

OptimizationFromConfigOptions(
    project_key="default",
    handle_agent_call=handle_agent_call,
)

Additionally just adds an is_evaluation flag as the final argument for handle_agent_call so that if you're using the singular method you can still discern which is which if necessary.

---

Note

Medium Risk
Public callback signatures change (extra is_evaluation arg) and judge-model selection behavior is corrected, which can break existing integrations or alter evaluation results if consumers relied on per-judge model overrides.

Overview
Improves the optimization SDK callback ergonomics by making handle_judge_call optional (defaults to handle_agent_call) and adding an is_evaluation boolean argument to both agent/judge call handlers so a shared implementation can differentiate evaluation vs generation.

Fixes judge execution to always use the globally configured judge_model (while still forwarding judge-flag model parameters like temperature/tools) and routes judge calls through a single internal _judge_call fallback. Tests are updated to reflect the new callback signature and defaulting behavior.

^{Reviewed by Cursor Bugbot for commit 7074cfa. Bugbot is set up for automated code reviews on this repo. Configure here.}