Lessons: the accretion reflex, and telemetry that can see across projects (#4195, #4196, #3735) #170

Merged
bvandeusen merged 3 commits from dev into main 2026-09-19 23:36:31 -04:00
3 changed files with 45 additions and 2 deletions
Showing only changes of commit 97867d47ff - Show all commits
+7 -1
View File
@@ -333,7 +333,7 @@ def _usage_event_rows(rows) -> list[dict]:
return [
{
"user_id": r.user_id, "note_id": r.note_id, "event": r.event,
"source": r.source,
"source": r.source, "project_id": r.project_id,
"created_at": r.created_at.isoformat() if r.created_at else None,
}
for r in rows
@@ -1548,6 +1548,12 @@ async def _restore_v2(data: dict) -> dict:
note_id=mapped_nid,
event=ev.get("event", ""),
source=ev.get("source", ""),
# Degrades to None rather than dropping the row: unlike a shape
# event, a usage event without a project is still a real pull,
# and discarding it would deflate the pull-through this table
# exists to report. Null already means "not reported".
project_id=(project_id_map.get(ev["project_id"])
if ev.get("project_id") else None),
created_at=_dt(ev.get("created_at")),
))
stats["note_usage_events"] += 1
+2 -1
View File
@@ -41,7 +41,8 @@ async def test_record_pulled_writes_a_single_row():
record_pulled(user_id=7, note_id=11, source="mcp_get_snippet")
rows = sched.call_args[0][0]
assert rows == [
{"user_id": 7, "note_id": 11, "event": "pulled", "source": "mcp_get_snippet"}
{"user_id": 7, "note_id": 11, "event": "pulled",
"source": "mcp_get_snippet", "project_id": None}
]
+36
View File
@@ -245,6 +245,42 @@ def test_every_column_is_exported_or_declared_excluded(table):
)
def test_the_usage_importer_restores_the_reading_project():
"""The column guard above checks the EXPORT side only.
A column can be exported faithfully and then dropped on the way back in,
which restores a backup that reports success and has quietly lost a
dimension — #3182's failure mode, one direction over. There is no general
import-side guard yet; this covers the column #4196 added, by source
inspection, because the behavioural path needs Postgres.
It also pins the DEGRADE. `code_shape_events` skips a row whose project
will not map, because a shape event without its project says nothing. A
usage event is not like that: the project is optional by design and null
already means "not reported", so an unmappable one must restore as
unreported rather than vanish — dropping it would lose a real pull and
deflate the very pull-through this table exists to report.
"""
import inspect
src = inspect.getsource(backup._restore_v2)
marker = 'for ev in data.get("note_usage_events", []):'
assert marker in src, "the usage import loop moved; this guard is blind"
block = src[src.index(marker):][:1200]
assert 'ev.get("project_id")' in block, (
"the usage importer drops project_id — a restore would report success "
"and come back without the reading project"
)
assert "project_id_map" in block, (
"project_id must be re-mapped; a raw id points at whatever project "
"happens to hold that number in the destination install"
)
assert "continue" not in block.split('project_id=')[1][:200], (
"an unmappable project must degrade to None, not skip the row"
)
def test_the_column_guard_covers_every_table_with_a_row_helper():
"""The guard is only as good as its registry — a table added to _BACKED_UP
with a new helper, and not to the registry, would be unguarded and look