ai: bump hybridRouter connection timeout 8s → 30s

Manual fire of bb-company-coverage-scan tonight failed because the
8s connect timeout was tripping on llama3.1:70b cold-load when
another model was resident in VRAM on AI_001. Bumped to 30s so
the orchestrator can wait through a model swap.

Also bumped background request timeout 120s → 180s for the same
reason — story generation against the 70B can take >2 min on a
saturated GPU.

Coolify env OLLAMA_ENDPOINT was simultaneously flipped from
AI_001 (10.10.0.66) to AI_002 (10.10.0.67) since AI_002 is less
loaded — AI_001 is doing author enrichment and scrubber work.

src/lib/ai/hybridRouter.ts

@@ -65,8 +65,11 @@ async function callOllama(
   endpoint: string,
   options: HybridOptions
 ): Promise<string> {
-  const requestTimeout = options.isBackground ? 120_000 : 60_000;
-  const connectionTimeout = 8_000;
+  const requestTimeout = options.isBackground ? 180_000 : 60_000;
+  // 30s connection timeout (was 8s) — large models like llama3.1:70b
+  // may need to swap into VRAM on AI_001/AI_002, which can exceed 10s
+  // when another model is currently loaded.
+  const connectionTimeout = 30_000;
 
   // Build Ollama OpenAI-compatible payload
   const payload = {