Change default mtree schema from "spock" to "pgedge_ace"

ace.yaml

@@ -36,7 +36,7 @@ mtree:
     publication_name: "ace_mtree_pub"
     cdc_processing_timeout: 30
     cdc_metadata_flush_seconds: 10
-  schema: "spock"
+  schema: "pgedge_ace"
 
   diff:
     min_block_size: 1000

docs/CHANGELOG.md

@@ -18,6 +18,14 @@ All notable changes to ACE will be captured in this document. This project follo
   (unidirectional, bidirectional, fix-nulls, dry-run), Merkle tree operations,
   and origin-tracked replication with repair.
 
+### ⚠️ Breaking Change
+- **Default `mtree.schema` changed from `"spock"` to `"pgedge_ace"`.** If you have
+  been using Merkle tree operations (`mtree build`, `mtree diff`, continuous CDC)
+  in prior versions, your existing metadata tables live in the `spock` schema. To
+  preserve compatibility, set `schema: "spock"` in the following locations:
+  - `ace.yaml` → `mtree.schema`
+  - `visualise.sh` → `-S spock` flag (or edit the default in the script)
+
 ### Changed
 - ACE schema name in SQL templates is now quoted with `pgx.Identifier.Sanitize()`
   to prevent SQL breakage with non-simple schema names (e.g., mixed case,

docs/configuration.md

@@ -37,7 +37,7 @@ The [`ace.yaml` file](https://github.com/pgEdge/ace/blob/main/ace.yaml) defines
 | mtree → cdc --> publication_name | Publication used for mtree CDC. **Default: "ace_mtree_pub"** |
 | mtree → cdc --> cdc_processing_timeout | CDC processing timeout (s). **Default: 30** |
 | mtree → cdc --> cdc_metadata_flush_seconds | How often (s) CDC metadata is flushed to disk. **Default: 10** |
-| mtree --> schema | Schema used for mtree metadata/objects. **Default: "spock"** |
+| mtree --> schema | Schema used for mtree metadata/objects. **Default: "pgedge_ace"** |
 | mtree → diff --> min_block_size | Minimum Merkle diff block size. **Default: 1000** |
 | mtree → diff --> block_size | Target Merkle diff block size. **Default: 100000** |
 | mtree → diff --> max_block_size | Maximum Merkle diff block size. **Default: 1000000** |

internal/cli/default_config.yaml

@@ -35,7 +35,7 @@ mtree:
     publication_name: "ace_mtree_pub"
     cdc_processing_timeout: 30
     cdc_metadata_flush_seconds: 10
-  schema: "spock"
+  schema: "pgedge_ace"
 
   diff:
     min_block_size: 1000

tests/integration/test_env_test.go

@@ -392,22 +392,32 @@ func (e *testEnv) pairKey() string {
 	return e.ServiceN1 + "/" + e.ServiceN2
 }
 
-// awaitDataSync waits until n1 and n2 have the same row count for the given
-// table. This prevents inter-test bleed when a previous subtest's cleanup
-// repair is still replicating.
+// awaitDataSync waits until n1 and n2 have the same row count AND the same
+// content digest for the given table. Counts alone miss UPDATE-only drift
+// (repair replays after UPDATE-based subtests change field values without
+// changing row counts); the hashtext-sum digest is order-independent and
+// PK-agnostic, so it catches that case.
 func (e *testEnv) awaitDataSync(t *testing.T, qualifiedTableName string) {
 	t.Helper()
 	ctx := context.Background()
+	query := fmt.Sprintf(
+		"SELECT count(*), COALESCE(sum(hashtext(t::text)::bigint), 0) FROM %s t",
+		qualifiedTableName,
+	)
 	assertEventually(t, 30*time.Second, func() error {
 		var n1Count, n2Count int
-		if err := e.N1Pool.QueryRow(ctx, fmt.Sprintf("SELECT count(*) FROM %s", qualifiedTableName)).Scan(&n1Count); err != nil {
-			return fmt.Errorf("counting rows on n1: %w", err)
+		var n1Digest, n2Digest int64
+		if err := e.N1Pool.QueryRow(ctx, query).Scan(&n1Count, &n1Digest); err != nil {
+			return fmt.Errorf("digesting rows on n1: %w", err)
 		}
-		if err := e.N2Pool.QueryRow(ctx, fmt.Sprintf("SELECT count(*) FROM %s", qualifiedTableName)).Scan(&n2Count); err != nil {
-			return fmt.Errorf("counting rows on n2: %w", err)
+		if err := e.N2Pool.QueryRow(ctx, query).Scan(&n2Count, &n2Digest); err != nil {
+			return fmt.Errorf("digesting rows on n2: %w", err)
 		}
 		if n1Count != n2Count {
-			return fmt.Errorf("nodes not in sync for %s: n1=%d n2=%d", qualifiedTableName, n1Count, n2Count)
+			return fmt.Errorf("nodes not in sync for %s: n1 count=%d n2 count=%d", qualifiedTableName, n1Count, n2Count)
+		}
+		if n1Digest != n2Digest {
+			return fmt.Errorf("nodes not in sync for %s: count=%d but digest n1=%d n2=%d", qualifiedTableName, n1Count, n1Digest, n2Digest)
 		}
 		return nil
 	})

visualise.sh

@@ -12,6 +12,7 @@
 #!/usr/bin/env bash
 # visualise.sh
 # Flags:
+#   -S <ace_schema> (default: pgedge_ace)  -> schema where ACE mtree objects live
 #   -s <schema>    (default: public)
 #   -t <table>     (required)  -> full table: ace_mtree_<schema>_<table>
 #   -H <host>      (optional)  -> psql -h
@@ -21,20 +22,21 @@
 #   -v             vertical
 #
 # Uses PG* env for user and db Example:
-#   PGUSER=admin PGDATABASE=demo ./visualise.sh -s public -t customers_small -H localhost -v
+#   PGUSER=admin PGDATABASE=demo ./visualise.sh -s public -t customers_small -H localhost -v [-S pgedge_ace]
 
 set -euo pipefail
 
-ace_schema="spock"
+ace_schema="pgedge_ace"
 table_schema="public"
 table=""
 host=""
 user="${PGUSER:-admin}"
 dbname="${PGDATABASE:-demo}"
 orientation="vertical"   # default
 
-while getopts ":s:t:H:U:d:hv" opt; do
+while getopts ":S:s:t:H:U:d:hv" opt; do
   case "$opt" in
+    S) ace_schema="$OPTARG" ;;
     s) table_schema="$OPTARG" ;;
     t) table="$OPTARG" ;;
     H) host="$OPTARG" ;;
@@ -48,7 +50,7 @@ while getopts ":s:t:H:U:d:hv" opt; do
 done
 
 if [[ -z "$table" ]]; then
-  echo "Usage: $0 -t <table> [-s <schema=public>] [-H <host>] [-U <user>] [-d <dbname>] [-h|-v]" >&2
+  echo "Usage: $0 -t <table> [-s <schema=public>] [-S <ace_schema=pgedge_ace>] [-H <host>] [-U <user>] [-d <dbname>] [-h|-v]" >&2
   exit 2
 fi