fix: enforce 150-word hard limit + max_tokens=400 for Poimen responses

app/api/chat/route.ts

@@ -112,33 +112,26 @@ CRDs + operators. Reconciliation loops (leader-election, backoff, finalizers). G
 
 ---
 
-## Response Style — CRITICAL
+## RESPONSE FORMAT — MANDATORY
 
-Be a caveman. Spit facts, not essays. NO filler phrases like "Here's how he did it", "Let me explain", "Rock resolved this by implementing". Kill all fluff.
+You MUST follow these rules. Violating them is a failure.
 
-Rules:
-1. **Lead with the answer** in 1-2 lines max
-2. **Problem → Fix → Result** format for technical stories. 3 bullets max each.
-3. Use \`code\` for commands, **bold** for key terms, ## for headers
-4. Total response: 6-12 lines. If you're writing paragraphs, you're doing it wrong.
-5. No intro sentences. No summary sentences. No "In conclusion". Just facts.
-6. Humble tone — "learned the hard way", "broke it first" — but BRIEF
-
-Example — "How did Rock fix Terraform drift?":
+1. MAX 150 words per response. Hard limit. Count them.
+2. NO intro sentences. NO "Here's how", "Let me explain", "Rock resolved this by". Start with the answer.
+3. Format: **Problem** (1 line) → **Fix** (2-3 bullets) → **Result** (1 line with metric)
+4. Use ## header, **bold**, \`code\`, bullets only. No paragraphs. No numbered lists with sub-bullets.
+5. NO summary. NO "Key Takeaway" section. NO conclusion. The result IS the takeaway.
+6. If asked a simple question, answer in 1-3 lines. Not everything needs Problem/Fix/Result.
 
+GOOD example:
 ## Terraform Drift @ RBC
-
-**Problem**: Engineers hotfixing in cloud console. Code detached from live state. Drift found weeks later.
-
+**Problem**: Engineers hotfixing in cloud console. Code ≠ live state.
 **Fix**:
-- Nightly cron: \`terraform plan -refresh-only -detailed-exitcode\`
-- Exit code 2 → Slack webhook with drift log to platform eng
+- Nightly \`terraform plan -refresh-only -detailed-exitcode\`
+- Exit code 2 → Slack webhook with drift log
+**Result**: **3 weeks → <24hr** drift visibility
 
-**Result**: Drift visibility **3 weeks → <24 hours**
-
----
-
-That's it. No more. Every word must earn its place.`
+BAD: "Rock resolved the Terraform configuration drift issue by implementing automated drift detection and real-time visibility into discrepancies..." — this is garbage. Never do this.`
 
 export async function POST(request: NextRequest) {
   const token = process.env.LLM_API_TOKEN
@@ -166,6 +159,7 @@ export async function POST(request: NextRequest) {
           { role: 'user', content: message },
         ],
         stream: true,
+        max_tokens: 400,
       }),
     })