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.
2026-10-22 04:52:55 +01:00
parent fe502b38fe
commit c2553a4746
25 changed files with 644 additions and 13 deletions
@@ -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),