mcp-server/observer.ts

@@ -275,12 +275,18 @@ async function escalateFailureClusterToLLMTeam(sigHash: string, cluster: Observe
   const prompt = `${kbPreamble}sig_hash=${sigHash} · ${cluster.length} failures on the same signature:\n\n${context}\n\nReview this failure cluster. Identify:\n1. Likely root cause (single sentence).\n2. Files most likely responsible (path hints).\n3. Concrete fix direction (under 3 sentences).\n4. Confidence: NN%\n\nBe specific, not generic.`;
 
   try {
+    // 2026-04-26: switched from ollama_cloud/qwen3-coder:480b (weekly
+    // 429 quota was blocking escalations) to paid OpenRouter
+    // deepseek-v3.1-terminus — 671B reasoning specialist, $0.21 in /
+    // $0.79 out per M tokens (under the $0.85/M ceiling J set), 164K
+    // ctx. Per-escalation cost: ~$0.0006 (typical 500-token prompt +
+    // 300-token completion).
     const resp = await fetch(`${LAKEHOUSE}/v1/chat`, {
       method: "POST",
       headers: { "Content-Type": "application/json" },
       body: JSON.stringify({
-        provider: "ollama_cloud",
-        model: "qwen3-coder:480b",
+        provider: "openrouter",
+        model: "deepseek/deepseek-v3.1-terminus",
         messages: [{ role: "user", content: prompt }],
         max_tokens: 800,
         temperature: 0.2,
@@ -302,7 +308,7 @@ async function escalateFailureClusterToLLMTeam(sigHash: string, cluster: Observe
     const row = {
       ts: new Date().toISOString(),
       source: "observer_escalation",
-      mode: "direct_chat_qwen3_coder_480b",
+      mode: "direct_chat_deepseek_v3_1_terminus",
       sig_hash: sigHash,
       cluster_size: cluster.length,
       cluster_staffer: cluster[0]?.staffer_id,