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.

src/types/index.ts

@@ -258,6 +258,10 @@ export type HarnessModelOption = {
     name: string;
     free: boolean;
     voices?: string[];
+    /**
+     * The generation settings the model takes; undefined: all of them.
+     */
+    supported_parameters?: string[];
 };
 
 /**
@@ -325,6 +329,11 @@ export type HarnessFormValue = {
     fallback: boolean;
     enabled: boolean;
     voice?: string;
+    /**
+     * Generation settings (temperature, reasoning effort, ...), only the
+     * ones the picked model takes.
+     */
+    params?: Record<string, number | string>;
 };
 
 export type HarnessSettingsFormObject = Partial<