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/functions/backend/db/harness/grab-harness-model-entries.ts

@@ -54,6 +54,7 @@ export default async function grabHarnessModelEntries({
                 name: `${model.name || model.slug}${row.available == 0 ? " (no longer listed)" : ""}`,
                 free: model.free,
                 voices: model.voices,
+                supported_parameters: model.supported_parameters,
             },
         };
     });

src/functions/backend/db/harness/harness-model-row-to-catalog.ts

@@ -23,6 +23,7 @@ export default function harnessModelRowToCatalog({
         context_length: numberOrUndefined(row.context_length),
         max_output_tokens: numberOrUndefined(row.max_output_tokens),
         voices: parseList({ text: row.voices }),
+        supported_parameters: parseList({ text: row.supported_parameters }),
         intelligence_score: numberOrUndefined(row.intelligence_score),
         agentic_score: numberOrUndefined(row.agentic_score),
         released_at: numberOrUndefined(row.released_at),

src/functions/backend/db/harness/upsert-harness-models.ts

@@ -21,6 +21,7 @@ const Columns = [
     "context_length",
     "max_output_tokens",
     "voices",
+    "supported_parameters",
     "intelligence_score",
     "agentic_score",
     "released_at",
@@ -69,6 +70,7 @@ export default async function upsertHarnessModels({
                 model.context_length ?? null,
                 model.max_output_tokens ?? null,
                 model.voices ? JSON.stringify(model.voices) : null,
+                model.supported_parameters ? JSON.stringify(model.supported_parameters) : null,
                 model.intelligence_score ?? null,
                 model.agentic_score ?? null,
                 model.released_at ?? null,