src/mcplocal/src/proxymodel/plugins/gate.ts

@@ -21,6 +21,26 @@ import { withTimeout, TimeoutError } from '../../util/with-timeout.js';
  * begin_session — on timeout we fall back to deterministic tag matching. */
 const GATE_LLM_TIMEOUT_MS = Number(process.env['MCPCTL_GATE_LLM_TIMEOUT_MS'] ?? '8000');
 
+/**
+ * Extra request fields for the gate's server-Llm selection call. Prompt
+ * selection is mechanical classification that gains nothing from chain-of-
+ * thought, so we ask reasoning models to skip thinking (they otherwise burn the
+ * whole budget reasoning and blow the gate timeout). Sent verbatim by mcpd's
+ * passthrough adapter → litellm/vLLM. Harmless for models that ignore them, and
+ * if a backend rejects them the selector falls back to the local provider.
+ *   - `chat_template_kwargs.enable_thinking:false` — Qwen3 hard-off.
+ *   - `reasoning_effort:'low'` — OpenAI o-series / newer vLLM.
+ * Override with a JSON object in MCPCTL_GATE_SELECT_EXTRA_BODY, or '' to disable.
+ */
+const GATE_SELECT_EXTRA_BODY: Record<string, unknown> = (() => {
+  const raw = process.env['MCPCTL_GATE_SELECT_EXTRA_BODY'];
+  if (raw === '') return {};
+  if (raw !== undefined) {
+    try { return JSON.parse(raw) as Record<string, unknown>; } catch { /* use default */ }
+  }
+  return { chat_template_kwargs: { enable_thinking: false }, reasoning_effort: 'low' };
+})();
+
 export interface GatePluginConfig {
   gated?: boolean;
   providerRegistry?: ProviderRegistry | null;
@@ -308,6 +328,7 @@ async function handleBeginSession(
               temperature: o.temperature,
               max_tokens: o.maxTokens,
               stream: false,
+              ...GATE_SELECT_EXTRA_BODY, // ask reasoning models for a fast, no-think answer
             });
             return pickCompletionText(resp);
           }