Archive every deletion via a bulk SQL retirement
`retireDeletedArtifacts` used to iterate `deleted.slice(0, MAX_BASH_PROJECTED_FILES)` and emit no signal for paths past the cap — a large `rm -r` would leave the 51st row onward visible in the DocumentCenter with no indication anything was missed. The cap was inherited from the registration path, where it bounds file-stat round-trips; retirement is a pure metadata update with no filesystem cost, so the cap was value-free safety theatre. New DB surface `archiveWorkProductsByExternalPaths` runs a single `UPDATE … SET status = 'archived' … WHERE external_id IN (…) AND status <> 'archived' RETURNING id, external_id` per 500-path chunk — one round-trip per chunk instead of one per path. The projector feeds the full `deleted` list in, maps the returned ids back to `retired` outcomes, and no deletion is left behind regardless of the run's cleanup fan-out size.
This commit is contained in:
1 parent
f0c4a66cc1
commit
fe808d13a2
3 files changed
+78
-18
No files matched your search
@@ -451,6 +451,65 @@ export function buildDocumentMethods(
|
||||
return Number(result.changes ?? 0);
|
||||
},
|
||||
|
||||
/**
|
||||
* Archive every `work_products` row whose natural identity matches
|
||||
* one of `paths` under the given `(companyId, workspaceId,
|
||||
* provider)` scope. The change detectors walk the whole workspace
|
||||
* delta, so every detected deletion has to be retired — previously
|
||||
* the projector capped the retire list at a hardcoded budget and
|
||||
* the tail stayed visible in the DocumentCenter.
|
||||
*
|
||||
* Runs as a single `UPDATE … WHERE external_id IN (…)` per chunk
|
||||
* so bulk deletions cost one SQL round-trip per 500 paths instead
|
||||
* of one per path. `RETURNING` carries the archived row ids back
|
||||
* to the projector so it can emit `retired` outcomes without a
|
||||
* follow-up SELECT.
|
||||
*/
|
||||
archiveWorkProductsByExternalPaths(input: {
|
||||
companyId: string;
|
||||
workspaceId: string | null;
|
||||
provider: string;
|
||||
paths: string[];
|
||||
lastTouchedByRunId: string | null;
|
||||
}): Array<{ id: string; externalId: string }> {
|
||||
if (input.paths.length === 0) return [];
|
||||
const ts = nowIso();
|
||||
const CHUNK = 500;
|
||||
const workspaceClause = input.workspaceId
|
||||
? "AND workspace_id = ?"
|
||||
: "AND workspace_id IS NULL";
|
||||
const results: Array<{ id: string; externalId: string }> = [];
|
||||
for (let i = 0; i < input.paths.length; i += CHUNK) {
|
||||
const chunk = input.paths.slice(i, i + CHUNK);
|
||||
const placeholders = chunk.map(() => "?").join(", ");
|
||||
const params: SQLInputValue[] = [
|
||||
input.lastTouchedByRunId ?? null,
|
||||
ts,
|
||||
input.companyId,
|
||||
input.provider,
|
||||
];
|
||||
if (input.workspaceId) params.push(input.workspaceId);
|
||||
params.push(...chunk);
|
||||
const rows = readAll<{ id: string; external_id: string }>(
|
||||
`UPDATE work_products
|
||||
SET status = 'archived',
|
||||
last_touched_by_run_id = ?,
|
||||
updated_at = ?
|
||||
WHERE company_id = ?
|
||||
AND provider = ?
|
||||
${workspaceClause}
|
||||
AND external_id IN (${placeholders})
|
||||
AND status <> 'archived'
|
||||
RETURNING id, external_id`,
|
||||
...params,
|
||||
);
|
||||
for (const row of rows) {
|
||||
results.push({ id: row.id, externalId: row.external_id });
|
||||
}
|
||||
}
|
||||
return results;
|
||||
},
|
||||
|
||||
// ── Task-Document Links ──
|
||||
|
||||
linkDocumentToTask(taskId: string, documentId: string, companyId: string, key: string): string {
|
||||
|
||||
Reference in new issue
Block a user