Merge pull request #52 from sirius0xdev/optimize-prompt-context-2026-04-22

Optimize prompt context 2026 04 22

apps/base/customer1/openclaw/a100-vllm.yaml

@@ -39,12 +39,12 @@ spec:
             - --tokenizer-mode=hf 
             - --gpu-memory-utilization=0.95
             - --kv-cache-dtype=fp8
-            - --max-model-len=49152 
+            - --max-model-len=auto 
             - --enable-auto-tool-choice 
             - --trust-remote-code
             - --dtype=auto
             - --enable-prefix-caching
-            - --tool-call-parser=hermes
+            - --tool-call-parser=qwen3_coder
             - --reasoning-parser=qwen3
             
             - --disable-custom-all-reduce

apps/base/customer1/openclaw/configmap.yaml

@@ -71,9 +71,16 @@ data:
           }
         ]
       },
-      "cron": { "enabled": true } 
+      "cron": { "enabled": true },
+      "requestTimeoutSeconds": 180,
+      "promptCaching": true,
+      "context": {
+        "injectAllMarkdown": false,
+        "curatedFiles": ["SOUL.md", "MEMORY.md", "IDENTITY.md", "USER.md"],
+        "useMemorySearch": true
+      }
     }
   AGENTS.md: |
-    # OpenClaw Assistant
+    # Sirius Claw
 
-    You are a helpful AI assistant running in Kubernetes.
+    Professional, precise, dark humor. Running in Lance's GKE cluster.