fix: agent.py — bruk riktig import-path for VertexAiRagRetrieval (ADK 1.x)

agents/core-logic/agent.py

@@ -1,48 +1,54 @@
 #!/usr/bin/env python3
 """
-agent.py — OSVauco root agent using ADK 2.0.
-Requires: google-adk >= 1.29, google-cloud-aiplatform >= 1.111.0
+agent.py — OSVauco root agent using ADK 1.x.
+Requires: google-adk >= 1.0.0,<2.0.0
+         google-cloud-aiplatform >= 1.112.0
 """
 
 import os
+import logging
+
 from google.adk.agents import Agent
-from google.adk.integrations.secret_manager.secret_client import SecretManagerClient
-from vertexai.preview import rag
 
-PROJECT_ID = "propane-will-491900-m5"
-LOCATION = "us-central1"
+logger = logging.getLogger(__name__)
 
-# --- Secret Manager integration (ADK >= 1.29) ---
-_sm = SecretManagerClient()
-def _get_secret(name: str) -> str:
-    return _sm.get_secret(
-        f"projects/{PROJECT_ID}/secrets/{name}/versions/latest"
-    )
+PROJECT_ID = os.environ.get("GOOGLE_CLOUD_PROJECT", "propane-will-491900-m5")
+LOCATION   = os.environ.get("GOOGLE_CLOUD_LOCATION", "us-central1")
 
-# --- RAG retrieval tool ---
-RAG_CORPUS = os.environ.get("RAG_CORPUS", "")  # set via Secret Manager or env
+# RAG corpus resource name — injected via Secret Manager as env-var RAG_CORPUS
+RAG_CORPUS = os.environ.get("RAG_CORPUS", "")
 
 rag_tool = None
 if RAG_CORPUS:
-    from google.adk.tools import VertexAiRagRetrieval
-    rag_tool = VertexAiRagRetrieval(
-        name="retrieve_knowledge",
-        description="Retrieve relevant documentation from the knowledge base.",
-        rag_resources=[rag.RagResource(rag_corpus=RAG_CORPUS)],
-        similarity_top_k=10,
-        vector_distance_threshold=0.6,
-    )
+    try:
+        # ADK 1.x: VertexAiRagRetrieval lives in google.adk.tools.retrieval
+        from google.adk.tools.retrieval.vertex_ai_rag_retrieval import VertexAiRagRetrieval
+        from vertexai.preview import rag
 
-# --- Root agent ---
+        rag_tool = VertexAiRagRetrieval(
+            name="retrieve_knowledge",
+            description="Retrieve relevant documentation and context from the OSVauco knowledge base.",
+            rag_resources=[rag.RagResource(rag_corpus=RAG_CORPUS)],
+            similarity_top_k=10,
+            vector_distance_threshold=0.6,
+        )
+        logger.info(f"RAG tool initialised with corpus: {RAG_CORPUS}")
+    except ImportError as e:
+        logger.warning(f"VertexAiRagRetrieval not available — running without RAG: {e}")
+        rag_tool = None
+else:
+    logger.warning("RAG_CORPUS env var not set — running without RAG retrieval")
+
+# Root agent
 root_agent = Agent(
-    model="gemini-2.5-flash",   # cost-optimized default
-    name="oavauco_root",
+    model="gemini-2.5-flash",
+    name="osvauco_root",
     description="OSVauco enterprise agent for propane-will-491900-m5",
     instruction=(
         "You are OSVauco, a GCP knowledge and workflow agent. "
         "Use the retrieve_knowledge tool to answer questions from the knowledge base. "
-        "Always prefer grounded, documented answers over speculation."
-                "Always respond in Norwegian (Bokmål) regardless of the language used in the query."
+        "Always prefer grounded, documented answers over speculation. "
+        "Always respond in Norwegian (Bokmål) regardless of the language used in the query."
     ),
     tools=[rag_tool] if rag_tool else [],
 )