Files
platform/scripts/migrate-emails-to-sqlite.ts
T
pastilhasandClaude Opus 5 af56eb36ff email: move the mail store and every route into the sidecar
Email was the one sidecar built inside out. The platform held ~1,800 lines — the per-account
SQLite store, all 14 HTTP routes, account CRUD, resync, IMAP validation — while the 314-line
sidecar was a scheduler that reached BACK into the platform to do anything
(`import { performResync } from '../../api/email/resync'`).

The sidecar now serves its own HTTP listener and announces `email:server`, and
/api/email/* on the platform is createSidecarProxy like every other one: 1,801 lines down
to 22, with no mail knowledge left in it — not a message, not a folder, not a credential.

The routes moved verbatim, Hono and all. http.ts only reconstructs what the platform's
middleware used to provide: `user` on the context, from the X-Officer-User header the proxy
injects (trusted because this server binds loopback), and an error handler that turns
custom-errors into status codes.

The /email/events SSE stream went with them, which removes a whole round trip: the IDLE
watcher used to send `email:new` over the registration socket so the platform could push to
its SSE clients. Those clients are here now, so it calls broadcastEmailNew in-process and
`email:new` is gone from the wire protocol.

DELIBERATELY NOT DONE YET, and left backwards on purpose rather than half-moved:

- The two sync handlers (email-sync 381 lines, gmail-sync 712) still run in the platform's
  queue and now import the store from its new home — a platform → sidecar import, which is
  the wrong direction and is temporary. Moving them is option (A) from the plan: the sidecar
  schedules its own syncs, independent of the platform Jobs list.
- accounts.ts still imports queue/init to enqueue a sync and to report sync status, and
  index.ts still carries the queue-over-WS shim that inversion needs.
- The three channel handlers still open the mail store directly rather than asking over HTTP.

Two things worth knowing while testing: a from-scratch sync holds a proxied request open
well past the 60s idle default, hence timeoutSeconds on the proxy; and `gmail-sync` is
hardcoded in all three channel handlers even though the only account is provider=gmail with
auth_type=password, which routes to IMAP — so "sync emails" from a chat channel is
almost certainly already broken, and folds into the next stage.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 12:10:35 +00:00

82 lines
2.5 KiB
TypeScript

import { readdirSync, readFileSync } from 'node:fs';
import { join } from 'node:path';
import { openEmailDb, upsertFromRawEml, setSyncMeta } from '../src/servers/sidecar/email/store';
const DATA_PATH = process.env.DATA_PATH ?? join(process.cwd(), 'data');
// Find all user directories that have Gmail emails
const targetEmail = process.argv[2];
if (targetEmail) {
migrate(targetEmail);
} else {
const entries = readdirSync(DATA_PATH, { withFileTypes: true });
for (const entry of entries) {
if (!entry.isDirectory()) continue;
if (!entry.name.includes('@')) continue;
const emailDir = join(DATA_PATH, entry.name, 'Gmail', 'emails');
try {
const files = readdirSync(emailDir).filter((f) => f.endsWith('.eml'));
if (files.length > 0) migrate(entry.name);
} catch {
// no Gmail dir for this user
}
}
}
function migrate(userEmail: string): void {
console.log(`Migrating ${userEmail}...`);
const emailDir = join(DATA_PATH, userEmail, 'Gmail', 'emails');
// Obsolete one-off migration (old .eml-file store → SQLite); kept only to compile.
const db = openEmailDb(userEmail, userEmail);
let filenames: string[];
try {
filenames = readdirSync(emailDir).filter((f) => f.endsWith('.eml'));
} catch {
console.log(' No .eml files found');
db.close();
return;
}
const existingIds = new Set<string>();
const rows = db.query('SELECT id FROM emails').all() as Array<{ id: string }>;
for (const row of rows) existingIds.add(row.id);
let added = 0;
let skipped = 0;
let errors = 0;
db.exec('BEGIN');
try {
for (const filename of filenames) {
const id = filename.replace(/\.eml$/, '');
if (existingIds.has(id)) {
skipped++;
continue;
}
try {
const raw = readFileSync(join(emailDir, filename), 'utf-8');
upsertFromRawEml({ db, id, raw, integration: 'gmail', emailAccount: userEmail, labels: ['INBOX'] });
added++;
} catch {
errors++;
}
}
db.exec('COMMIT');
} catch (err) {
db.exec('ROLLBACK');
throw err;
}
console.log(` ${filenames.length} .eml files — ${added} added, ${skipped} skipped, ${errors} errors`);
// Store the latest email date so the next sync only fetches emails after it
const row = db.query('SELECT date FROM emails ORDER BY date DESC LIMIT 1').get() as { date: string } | null;
if (row?.date) {
setSyncMeta(db, 'last_sync_date', row.date);
console.log(` Stored last_sync_date: ${row.date}`);
}
db.close();
}