Add tag implication expansion (fox→canine→canid→mammal)

Fix min_why not passed to workers in parallel eval mode

Add --min-why threshold to filter Stage 3 selections by confidence level

Add diagnostic eval metrics, why-distribution tracking, and generic character filter

Add parallel processing to eval pipeline with ThreadPoolExecutor

Add independent character tag metrics to eval pipeline

Improve eval harness: shuffle samples, always write results

Add end-to-end evaluation harness for pipeline metrics