feat(pipelines): record upstream snapshot ids on cascade-dispatched jobs (#9910)

* feat(pipelines): record upstream snapshot ids on cascade-dispatched jobs

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor: batch upstream-snapshot lookup and memoize per subscriber

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Ruben Fiszel
2026-07-04 00:10:18 +02:00
committed by GitHub
co-authored by Claude Fable 5
parent df6e511763
commit af36498432
7 changed files with 452 additions and 3 deletions
@@ -0,0 +1,77 @@
{
"db_name": "PostgreSQL",
"query": "SELECT DISTINCT ON (mp.asset_kind, mp.asset_path)\n mp.asset_kind AS \"asset_kind: AssetKind\", mp.asset_path,\n mp.snapshot_id AS \"snapshot_id!\", mp.partition\n FROM materialized_partition mp\n JOIN unnest($2::ASSET_KIND[], $3::text[]) AS u(kind, path)\n ON mp.asset_kind = u.kind AND mp.asset_path = u.path\n WHERE mp.workspace_id = $1\n AND mp.status = 'materialized' AND mp.snapshot_id IS NOT NULL\n ORDER BY mp.asset_kind, mp.asset_path, mp.snapshot_id DESC",
"describe": {
"columns": [
{
"ordinal": 0,
"name": "asset_kind: AssetKind",
"type_info": {
"Custom": {
"name": "asset_kind",
"kind": {
"Enum": [
"s3object",
"resource",
"variable",
"ducklake",
"datatable",
"volume"
]
}
}
}
},
{
"ordinal": 1,
"name": "asset_path",
"type_info": "Varchar"
},
{
"ordinal": 2,
"name": "snapshot_id!",
"type_info": "Int8"
},
{
"ordinal": 3,
"name": "partition",
"type_info": "Text"
}
],
"parameters": {
"Left": [
"Text",
{
"Custom": {
"name": "asset_kind[]",
"kind": {
"Array": {
"Custom": {
"name": "asset_kind",
"kind": {
"Enum": [
"s3object",
"resource",
"variable",
"ducklake",
"datatable",
"volume"
]
}
}
}
}
}
},
"TextArray"
]
},
"nullable": [
false,
false,
true,
false
]
},
"hash": "0ee4a4dc8c6f09e7027bd99f98d8d1d346f9d67056ef272314dd9b80bee9f285"
}
@@ -0,0 +1,23 @@
{
"db_name": "PostgreSQL",
"query": "SELECT DISTINCT trigger_ref AS \"trigger_ref!\"\n FROM script_trigger\n WHERE workspace_id = $1\n AND runnable_path = $2\n AND trigger_kind = 'asset'\n AND runnable_kind = 'script'\n ORDER BY trigger_ref",
"describe": {
"columns": [
{
"ordinal": 0,
"name": "trigger_ref!",
"type_info": "Text"
}
],
"parameters": {
"Left": [
"Text",
"Text"
]
},
"nullable": [
false
]
},
"hash": "3703847d0cef9df3a480af8b6a5c21b6af282c68f06ce037a11f703284d8980d"
}