Add per-model generation settings to the model selector

Each text and vision harness setting now carries the generation settings
its model takes (temperature, sampling limits, penalties, seed, reasoning
effort), edited in a modal under the model pick so the harness block stays
short. Nothing is set by default, so models keep their provider's own
values until a super admin or admin changes them.

A setting is only offered and only sent when the catalog says the model
takes it: OpenRouter's supported_parameters is now stored on
harness_models and refreshed by the hourly sync. Other providers list no
parameters, so their models get them all.

db/types/db.ts

@@ -941,6 +941,10 @@ export type BUN_SQLITE_COBBLE_HARNESS_MODELS = {
      * JSON array of voice names, for speech models
      */
     voices?: string;
+    /** 
+     * JSON array of the request fields the model takes (OpenRouter's supported_parameters), so only the generation settings it honors are offered
+     */
+    supported_parameters?: string;
     /** 
      * Artificial Analysis intelligence index
      */