diff --git a/stacks/gateway-chat/conf/index.html b/stacks/gateway-chat/conf/index.html index df7ae53..75c386f 100644 --- a/stacks/gateway-chat/conf/index.html +++ b/stacks/gateway-chat/conf/index.html @@ -249,7 +249,12 @@ async function send(){ model: $('model').value.trim() || 'gen', messages, temperature: parseFloat($('temp').value), - max_tokens: parseInt($('max').value, 10), + // Guarded: an empty or non-numeric field makes parseInt return NaN, and + // JSON.stringify serialises NaN as `null` -- which the server reads as + // "no max_tokens supplied" and silently substitutes its own default. + // That is indistinguishable from the field being ignored. Fall back to the + // same 4096 the input defaults to. + max_tokens: parseInt($('max').value, 10) || 4096, stream: true // intentionally NO `tools` — vLLM 400s on an empty array. };