# memledger 2.0.0 — Postgres + pgvector (OSS, in-cluster) smoke test
#
# Date:        2026-05-24
# Cluster:     kagents-mem-eks (EKS, us-west-2)
# Image:       eks-ops-agent:v2-test (memledger 2.0.0 from Test PyPI)
# Auth:        Password auth (memledger user, k8s Secret)
# Postgres:    in-cluster `memledger-pgvector` StatefulSet
#              (Helm chart: memledger-pgvector, PostgreSQL 17.10 + pgvector)
# Embeddings:  Bedrock amazon.titan-embed-text-v2:0 (1024-dim)
# Run mode:    Local docker run via host-gateway port-forward
#
# Test exercises: add() x3 across triage / eks-ops / compliance agents
# with derived_from chain → search() → v2 governance field round-trip →
# delete() x3
# ----------------------------------------------------------------------

OK: connected to backend=pgvector
OK: added 3 records: 03951cfb, 8c1b1a95, 4138869f
OK: search returned 3 hits
   - 8c1b1a95 type=semantic conf=0.699999988079071 agent=eks-ops-agent
   - 4138869f type=procedural conf=0.800000011920929 agent=compliance-agent
   - 03951cfb type=episodic conf=0.8999999761581421 agent=triage-agent
OK: lineage for id3 — derived_records=0, supersedes_chain=0
OK: v2 fields round-tripped — agent_id=eks-ops-agent, confidence=0.699999988079071
OK: cleanup done
SMOKE TEST PASSED