Inject architecture diagram by heading and ignore runtime timing log

Update docs diagrams, evaluation labels, and analysis artifacts

Consolidate probe configs and eval artifacts on main

Refine UI guidance, tag toggle cues, and hover tooltip metadata

Polish Gradio UI layout/tooltips and remove dead helper code

Refine tag toggle UI ordering/colors and add category assignment analysis artifacts

Switch Stage3 to explicit-only no-why selection, drop bear probe, and set k=1 defaults