feat: run actual gumbo code in worker

agents/k8s/gumbo-worker-deployment.yaml

@@ -18,11 +18,24 @@ spec:
         agentic-os.io/agent: gumbo
     spec:
       serviceAccountName: default
+      initContainers:
+        - name: git-clone
+          image: alpine/git
+          command:
+            - "sh"
+            - "-c"
+            - "git clone http://192.168.8.248:3000/deepkoluguri/agentic-os.git /workspace && cp -r /workspace/agents/gumbo/* /app/"
+          volumeMounts:
+            - name: app-code
+              mountPath: /app
       containers:
         - name: gumbo-worker
           image: python:3.11-slim
           imagePullPolicy: Always
-          command: ["sleep", "infinity"]
+          command: ["sh", "-c", "pip install -r /app/requirements.txt && cd /app && python -m gumbo.temporal.worker"]
+          volumeMounts:
+            - name: app-code
+              mountPath: /app
           env:
             - name: TEMPORAL_ADDRESS
               value: "temporal-frontend.ai-core.svc.cluster.local:7233"
@@ -56,3 +69,6 @@ spec:
             limits:
               cpu: "2"
               memory: 2Gi
+      volumes:
+        - name: app-code
+          emptyDir: {}

agents/trigger_gumbo.py

@@ -0,0 +1,47 @@
+import asyncio
+import sys
+
+from temporalio.client import Client
+
+
+async def main():
+    if len(sys.argv) < 2:
+        print("Usage: python trigger_gumbo.py <object_key>")
+        sys.exit(1)
+        
+    object_key = sys.argv[1]
+    
+    # Create Temporal client
+    # Assuming port-forward or executing inside cluster
+    # We will just print instructions to port-forward
+    print("Connecting to Temporal server at localhost:7233...")
+    try:
+        client = await Client.connect("localhost:7233")
+    except Exception as e:
+        print(f"Failed to connect to Temporal: {e}")
+        print("Please ensure you have port-forwarded the Temporal frontend:")
+        print("kubectl port-forward svc/temporal-frontend 7233:7233 -n ai-core")
+        sys.exit(1)
+
+    print(f"Triggering GumboSummarizeWorkflow for object_key: {object_key}")
+    
+    # Execute workflow
+    # Workflow name must match the class name `GumboSummarizeWorkflow`
+    # Task queue is likely 'gumbo-task-queue' based on standard setups
+    handle = await client.start_workflow(
+        "GumboSummarizeWorkflow",
+        object_key,
+        id=f"gumbo-summary-{object_key}",
+        task_queue="gumbo-task-queue"
+    )
+
+    print(f"Workflow started. Workflow ID: {handle.id}, Run ID: {handle.result_run_id}")
+    
+    print("Waiting for workflow to complete...")
+    result = await handle.result()
+    
+    print("\n--- Workflow Result ---")
+    print(result)
+
+if __name__ == "__main__":
+    asyncio.run(main())