The config_defaults comment still described the unknown-model template as
"vision/reasoning off", which is exactly the synthesized-False behaviour
#112649 reports and the preceding commit removes. State the new contract
where users read it (config_defaults, providers docs): a context_window-only
override for an uncatalogued model keeps supports_vision / supports_reasoning
unknown so vision_analyze, video_analyze and the reasoning-effort picker stay
available; only an explicit false in the override marks the model text-only.