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/pages/admin/settings/models/(utils)/changed-harness-settings.ts

@@ -30,6 +30,22 @@ function isSame({ a, b }: { a: HarnessFormValue; b?: HarnessFormValue }) {
         (a.provider_id ?? null) == (b!.provider_id ?? null) &&
         a.fallback == b!.fallback &&
         a.enabled == b!.enabled &&
-        (a.voice || "") == (b!.voice || "")
+        (a.voice || "") == (b!.voice || "") &&
+        paramsKey({ params: a.params }) == paramsKey({ params: b!.params })
     );
 }
+
+/**
+ * The generation settings as one comparable string.
+ */
+export function paramsKey({
+    params,
+}: {
+    params?: Record<string, number | string>;
+}) {
+    const entries = Object.entries(params || {}).sort(([a], [b]) =>
+        a.localeCompare(b),
+    );
+
+    return JSON.stringify(entries);
+}