4b7343d5ec
isTransientFailure() checks the driver's error code first, and 57014
(statement timeout) is already in its transient set. But the wrapping idiom
across the codebase was `throw new Error(\`Database error: ${err.message}\`)`,
which keeps the prose and drops the code. A retryable timeout therefore
arrived anonymous and resolved to UNKNOWN_ERROR: "Något gick fel. Försök
igen." An agent cannot dispatch on that, so it retried.
On production over 60 days, with the two bot integrations excluded: 1024 real
agent failures, 645 of them UNKNOWN_ERROR across 60 actors and 57 companies.
82 retry streaks of three or more identical failures, 462 wasted repeat calls,
53.1% of all agent error calls sitting inside a streak.
The worst offender traces to one line in core. gnubok_query_journal failed 164
times at a p50 of 8110ms while every other failing tool sat between 1 and
315ms, and its path is fetchEntryLines -> fetchAllRows, where
lib/supabase/fetch-all.ts threw `new Error(error.message)`. That is the
highest-traffic strip point in the repo: 31 callers, every paginated read.
query_journal already had a correct TRANSIENT_ERROR branch offering "retry, or
narrow with date_from/date_to" which could never fire, because by the time it
looked, the code was gone.
fetch-all keeps the driver message verbatim: callers match on the existing
text, and this adds the code rather than rewording anything.
Attaching the code is safe. extractCode() only accepts /^[A-Z_]+$/ and every
SQLSTATE contains digits, so it cannot be mistaken for one of our own stable
codes. There is a test for that, and one asserting the old bare-Error shape
still resolves to UNKNOWN_ERROR so the fix cannot silently regress.
Also stops rendering the literal "undefined" when a driver-level failure
carries no message, which is the string that made these unsearchable.
Co-authored-by: Jakob Wennberg <311770904+jakobwennberg-oss@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
114 lines
4.6 KiB
TypeScript
114 lines
4.6 KiB
TypeScript
import { describe, it, expect } from 'vitest'
|
|
import { fetchAllRows } from '../fetch-all'
|
|
|
|
const PAGE_SIZE = 1000
|
|
|
|
type Row = { id: string; value?: number }
|
|
|
|
/**
|
|
* Build a queryFn that serves predefined pages keyed by the `from` offset.
|
|
* Mirrors how `fetchAllRows` drives PostgREST `.range(from, to)`.
|
|
*/
|
|
function pagedQuery(pages: Record<number, Row[]>) {
|
|
return ({ from }: { from: number; to: number }) =>
|
|
Promise.resolve({ data: pages[from] ?? [], error: null })
|
|
}
|
|
|
|
function makeRows(start: number, count: number): Row[] {
|
|
return Array.from({ length: count }, (_, i) => ({ id: String(start + i), value: 1 }))
|
|
}
|
|
|
|
describe('fetchAllRows', () => {
|
|
it('returns a single page as-is and stops (page < PAGE_SIZE)', async () => {
|
|
const rows = makeRows(0, 3)
|
|
const out = await fetchAllRows<Row>(pagedQuery({ 0: rows }))
|
|
expect(out).toHaveLength(3)
|
|
expect(out.map((r) => r.id)).toEqual(['0', '1', '2'])
|
|
})
|
|
|
|
it('paginates across multiple pages and concatenates in order', async () => {
|
|
const page1 = makeRows(0, PAGE_SIZE) // full page → fetch continues
|
|
const page2 = makeRows(PAGE_SIZE, 5) // partial page → stop
|
|
const out = await fetchAllRows<Row>(pagedQuery({ 0: page1, [PAGE_SIZE]: page2 }))
|
|
expect(out).toHaveLength(PAGE_SIZE + 5)
|
|
expect(out[0].id).toBe('0')
|
|
expect(out[out.length - 1].id).toBe(String(PAGE_SIZE + 4))
|
|
})
|
|
|
|
it('throws when the query returns an error', async () => {
|
|
await expect(
|
|
fetchAllRows<Row>(() => Promise.resolve({ data: null, error: { message: 'boom' } })),
|
|
).rejects.toThrow('boom')
|
|
})
|
|
|
|
it('propagates the driver SQLSTATE so a timeout stays dispatchable', async () => {
|
|
// This is the highest-traffic error strip point in the codebase: every
|
|
// paginated read goes through it. It used to throw `new Error(msg)`, which
|
|
// dropped `code`, so a statement timeout (57014) reached the structured
|
|
// error layer anonymous and resolved to UNKNOWN_ERROR instead of the
|
|
// retryable TRANSIENT_ERROR. gnubok_query_journal failed this way 164
|
|
// times in 60 days at a p50 of 8 110 ms.
|
|
const failure = fetchAllRows<Row>(() =>
|
|
Promise.resolve({
|
|
data: null,
|
|
error: { message: 'canceling statement due to statement timeout', code: '57014' },
|
|
}),
|
|
)
|
|
await expect(failure).rejects.toMatchObject({ code: '57014' })
|
|
// And the message stays verbatim: query_journal's sanitizeDbError matches
|
|
// on the existing text.
|
|
await expect(failure).rejects.toThrow('canceling statement due to statement timeout')
|
|
})
|
|
|
|
it('does not render "undefined" when the driver sends no message', async () => {
|
|
await expect(
|
|
fetchAllRows<Row>(() => Promise.resolve({ data: null, error: { code: '08006' } as never })),
|
|
).rejects.toThrow(/^(?!.*undefined).*$/)
|
|
})
|
|
|
|
it('returns [] when the first page is empty', async () => {
|
|
const out = await fetchAllRows<Row>(pagedQuery({ 0: [] }))
|
|
expect(out).toEqual([])
|
|
})
|
|
|
|
// ── The regression-critical behaviour: an unstable cross-page order ──
|
|
// (a query missing a stable .order()) can return the same row on two
|
|
// pages. This is the mechanism behind the doubled-balance bugs (#790/#791).
|
|
|
|
it('dedupeBy drops a row duplicated across page boundaries (keeps first)', async () => {
|
|
const page1 = makeRows(0, PAGE_SIZE) // ids 0..999
|
|
// Unstable order: page 2 re-serves id "999" (already on page 1) plus a new id.
|
|
const page2: Row[] = [
|
|
{ id: '999', value: 1 },
|
|
{ id: '1000', value: 1 },
|
|
]
|
|
const out = await fetchAllRows<Row>(
|
|
pagedQuery({ 0: page1, [PAGE_SIZE]: page2 }),
|
|
{ dedupeBy: (r) => r.id },
|
|
)
|
|
// 1001 unique ids (0..1000), the duplicate "999" removed → no doubling.
|
|
expect(out).toHaveLength(PAGE_SIZE + 1)
|
|
const ids = out.map((r) => r.id)
|
|
expect(ids.filter((id) => id === '999')).toHaveLength(1)
|
|
expect(new Set(ids).size).toBe(out.length)
|
|
})
|
|
|
|
it('without dedupeBy, cross-page duplicates pass through (unsafe default)', async () => {
|
|
const page1 = makeRows(0, PAGE_SIZE)
|
|
const page2: Row[] = [{ id: '999', value: 1 }]
|
|
const out = await fetchAllRows<Row>(pagedQuery({ 0: page1, [PAGE_SIZE]: page2 }))
|
|
expect(out).toHaveLength(PAGE_SIZE + 1)
|
|
expect(out.map((r) => r.id).filter((id) => id === '999')).toHaveLength(2)
|
|
})
|
|
|
|
it('dedupeBy is a no-op for a single page (no cross-page duplicates possible)', async () => {
|
|
const rows: Row[] = [
|
|
{ id: 'a' },
|
|
{ id: 'b' },
|
|
{ id: 'a' }, // an intra-page repeat is left untouched: single page is trusted
|
|
]
|
|
const out = await fetchAllRows<Row>(pagedQuery({ 0: rows }), { dedupeBy: (r) => r.id })
|
|
expect(out).toHaveLength(3)
|
|
})
|
|
})
|