feat(gate): terse selection prompt so a no-think model answers in ~2s

With the fast (no-think) route, gate-selection latency is now proportional to the
ANSWER length (a no-think model runs ~10-13 tok/s), not hidden thinking. A verbose
"reasoning" field pushed a selection to ~9s (over the 8s budget). Request compact
JSON with a <=8-word reasoning → ~2s (vs ~9s prose, or ~1.2s with no reasoning).
Validated live against vllm-fast (glm-4.6-reap-fast): 2.0s, valid selection JSON,
zero reasoning tokens.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/mcplocal/src/gate/llm-selector.ts

@@ -95,7 +95,11 @@ export class LlmPromptSelector {
   ): Promise<LlmSelectionResult> {
     const { getSystemPromptFn, signal, serverInfer } = opts;
 
-    const DEFAULT_SYSTEM_PROMPT = `You are a context selection assistant. Given a developer's task keywords and a list of available project prompts, select which prompts are relevant to their work. Return a JSON object with "selectedNames" (array of prompt names) and "reasoning" (brief explanation). Priority 10 prompts must always be included.`;
+    // Keep the answer SHORT: latency is proportional to output length (a
+    // no-think model runs ~10-13 tok/s), and a verbose reasoning field pushes a
+    // selection past the gate's responsiveness budget. Ask for compact JSON with
+    // a <=8-word reasoning — ~2s vs ~9s for a prose reasoning.
+    const DEFAULT_SYSTEM_PROMPT = `You are a context selection assistant. Given a developer's task keywords and available project prompts, select the relevant ones. Return ONLY compact JSON: {"selectedNames":[...],"reasoning":"<=8 words"}. No prose outside the JSON. Priority 10 prompts must always be included.`;
     const systemPrompt = getSystemPromptFn
       ? await getSystemPromptFn('llm-gate-context-selector', DEFAULT_SYSTEM_PROMPT)
       : DEFAULT_SYSTEM_PROMPT;