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/harness/media/read-image.ts

@@ -3,6 +3,7 @@ import HarnessError from "../harness-error";
 import grabHarnessAdapter from "../providers/grab-harness-adapter";
 import resolveHarnessCandidates from "../resolve/resolve-harness-candidates";
 import withCandidates from "../resolve/with-candidates";
+import grabChatParams from "../text/grab-chat-params";
 
 type Params = {
     /**
@@ -35,6 +36,12 @@ export default async function readImage({ url, focus, signal, bot_id, workspace_
         workspace_id,
     });
 
+    const saved_params = await grabChatParams({
+        harness: "vision",
+        bot_id,
+        workspace_id,
+    });
+
     const { result } = await withCandidates({
         harness: "vision",
         candidates,
@@ -57,7 +64,14 @@ export default async function readImage({ url, focus, signal, bot_id, workspace_
                         ],
                     },
                 ],
-                temperature: 0,
+                /**
+                 * Reading is a lookup, so it stays literal unless a
+                 * temperature was set for the vision harness.
+                 */
+                params: {
+                    temperature: 0,
+                    ...saved_params(candidate.model),
+                },
                 signal: signal || new AbortController().signal,
             });