Module campaign 

End-to-end optimization campaign orchestration.

Ties together the five lab layers into a single pipeline:

1. SearchEngine proposes configurations (Sobol + Bayesian EI)
2. run_experiment_with_quality() executes each trial
3. ParetoFrontier computes the 6-dimensional non-dominated set
4. BeliefGraph records verdicts and cascades confidence
5. Results are persisted to JSONL for reproducibility

The campaign runs in batches: after each batch, the frontier is recomputed and the belief graph is updated. The search engine adapts based on all observations so far.

Structs

CampaignConfig

Configuration for an optimization campaign.

CampaignReport

The result of an optimization campaign.

Functions

default_toggle_space

Build a default configuration space for inference toggle optimization. This covers the main toggle parameters that ExperimentConfig::apply_toggles supports.

run_optimization_campaign

Run an optimization campaign end-to-end.

save_campaign_report

Save a campaign report to a JSON file.