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/api/admin/bots/save-harness-settings.ts

@@ -4,6 +4,7 @@ import grabBotHarnessOverview from "@/src/functions/backend/db/harness/grab-bot-
 import grabHarnessSetting from "@/src/functions/backend/db/harness/grab-harness-setting";
 import saveBotHarnessSetting from "@/src/functions/backend/db/harness/save-bot-harness-setting";
 import logEvent, { grabRequestIP } from "@/src/functions/backend/logger";
+import { withHarnessParameters } from "@/src/dict/harness-parameter-dict";
 import { SaveBotHarnessSettingsRequestSchema } from "@/src/schemas/harness-schema";
 import type { BotHarnessOverviewPayload } from "@/src/types";
 import AppError from "@/src/utils/app-error";
@@ -71,7 +72,13 @@ export const handler: BunextAPIRouteHandler<
                 provider_id: setting.provider_id,
                 fallback: setting.fallback,
                 enabled: setting.enabled,
-                options: setting.voice ? { ...options, voice: setting.voice } : options,
+                options: withHarnessParameters({
+                    options: {
+                        ...options,
+                        ...(setting.voice ? { voice: setting.voice } : {}),
+                    },
+                    params: setting.params || {},
+                }),
             });
         }