An on-device, SQLCipher-encrypted full-text index the app can retrieve from to
feed an LLM ("prompt against"), for the Electron desktop shell only.
Shape: no persistent background worker and no resident credential. Indexing is
a normal request-scoped API route, triggered by the renderer's EXISTING live
JMAP push connection - so it reacts to each delivery/change rather than polling.
- lib/mail-index/binding.ts guarded require of the optional native binding
- lib/mail-index/paths.ts the VNCMAIL_DESKTOP_STORE_DIR gate + hashed paths
- lib/mail-index/store.ts schema, upsert, FTS5 search, encryption assertion
- lib/mail-index/extract.ts PURE JMAP-object -> document extractors
- lib/mail-index/jmap.ts minimal stateless server-side JMAP client
- lib/mail-index/key.ts per-job key fetch over the inherited fd
- lib/mail-index/reindex.ts the job + slot->account resolution
- electron/key-service.ts safeStorage wrap/unwrap, served over fd 3
- app/api/offline/reindex POST, event-driven + catch-up
- app/api/offline/search GET, the retrieval surface (hits + contextBlock)
- lib/mail-index-client.ts renderer client; StateChange -> index call
- components/settings/local-index-settings.tsx status + manual catch-up
Decisions worth knowing:
* `@signalapp/sqlcipher` is an OPTIONAL dependency with a guarded runtime
require. It publishes six N-API prebuilds and NO build sources, and both
Dockerfiles are node:24-alpine (musl, no matching prebuild) - as a hard
dependency it would break the production image and the integration fixture's
webmail container, neither of which wants this feature.
* Credentials come from the existing per-slot encrypted `jmap_stalwart_ctx`
cookie via lib/stalwart/credentials.ts - the same helper /api/settings and
/api/push/preview already use. It carries a ready-made header for basic AND
bearer accounts, so the indexer never touches the OAuth refresh-token cookie;
a server-side refresh would rotate a token into a response nobody reads and
silently log the user out.
* The encryption key crosses main -> server over an INHERITED FILE DESCRIPTOR,
never an environment variable: env is readable by any process running as the
same OS user, which would defeat using the OS keychain at all. Fetched per
job and zeroed after, so there is no long-lived key copy.
* safeStorage's Linux `basic_text` backend (no keyring) is treated as refusal,
not degradation - it "encrypts" with a hardcoded public password, which would
look like an encrypted mailbox while providing nothing.
getSelectedStorageBackend() is Linux-only and platform-guarded.
* Every store open asserts `PRAGMA cipher_version` returns a non-empty STRING,
not merely a row: a non-cipher binding returns ZERO ROWS, so a row-count check
would pass vacuously while writing the mailbox to disk in cleartext.
* Files are indexed by name/path/date/size only - NOT by extracted content.
Text extraction from arbitrary PDFs/office documents is a separate problem.
* Account-scoped composite keys `(jmap_account_id, content_type, id)` are kept
even though there is one file per account: one login exposes delegated/shared
JMAP accounts too, and JMAP ids are unique only within an account.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
118 lines
4.5 KiB
TypeScript
118 lines
4.5 KiB
TypeScript
// GET /api/offline/search?q=...&types=mail,calendar&limit=20
|
|
//
|
|
// THE RETRIEVAL SURFACE. This is what an AI/RAG feature calls to gather
|
|
// relevant context from the user's own mail, calendar, contacts and files
|
|
// before prompting a model - hence the `snippet` on every hit and the
|
|
// `contextBlock` convenience field, which is the same information already
|
|
// flattened into text a prompt can carry directly.
|
|
//
|
|
// Read-only: it never touches the network and never writes. Gated identically
|
|
// to the reindex route.
|
|
import { NextRequest, NextResponse } from 'next/server';
|
|
import { logger } from '@/lib/logger';
|
|
import { isSqlcipherAvailable } from '@/lib/mail-index/binding';
|
|
import { hasKeyChannel, IndexKeyError, withIndexKey } from '@/lib/mail-index/key';
|
|
import { getStoreDir } from '@/lib/mail-index/paths';
|
|
import { IndexSessionError, resolveIndexSession } from '@/lib/mail-index/reindex';
|
|
import {
|
|
isContentType, MailIndex, MailIndexUnavailableError, type ContentType, type SearchHit,
|
|
} from '@/lib/mail-index/store';
|
|
|
|
export const runtime = 'nodejs';
|
|
export const dynamic = 'force-dynamic';
|
|
|
|
/**
|
|
* One hit as a plain text block, ready to be concatenated into a prompt.
|
|
* Kept server-side so every caller (a chat feature, a future agent, a test)
|
|
* formats context the same way rather than each inventing its own.
|
|
*/
|
|
function toContextBlock(hit: SearchHit): string {
|
|
const label: Record<ContentType, string> = {
|
|
mail: 'EMAIL', calendar: 'CALENDAR EVENT', contact: 'CONTACT', file: 'FILE',
|
|
};
|
|
const lines = [`[${label[hit.contentType]}] ${hit.title}`];
|
|
if (hit.occurredAt) lines.push(`Date: ${hit.occurredAt}`);
|
|
if (hit.people) lines.push(`People: ${hit.people}`);
|
|
const path = hit.metadata?.path;
|
|
if (typeof path === 'string' && path) lines.push(`Path: ${path}`);
|
|
if (hit.snippet) lines.push(`Excerpt: ${hit.snippet}`);
|
|
return lines.join('\n');
|
|
}
|
|
|
|
export async function GET(request: NextRequest) {
|
|
if (!getStoreDir()) {
|
|
return new NextResponse(null, { status: 404 });
|
|
}
|
|
if (!hasKeyChannel() || !isSqlcipherAvailable()) {
|
|
return NextResponse.json(
|
|
{ error: 'Encrypted local index is unavailable in this process.', code: 'unavailable' },
|
|
{ status: 503 },
|
|
);
|
|
}
|
|
|
|
const params = request.nextUrl.searchParams;
|
|
const query = (params.get('q') ?? '').trim();
|
|
const wantStats = params.get('stats') === 'true';
|
|
|
|
if (!query && !wantStats) {
|
|
return NextResponse.json({ error: 'Missing q parameter' }, { status: 400 });
|
|
}
|
|
if (query.length > 512) {
|
|
return NextResponse.json({ error: 'Query too long' }, { status: 400 });
|
|
}
|
|
|
|
const types = (params.get('types') ?? '')
|
|
.split(',')
|
|
.map((t) => t.trim())
|
|
.filter(isContentType);
|
|
|
|
const limitRaw = Number(params.get('limit') ?? '20');
|
|
const limit = Number.isFinite(limitRaw) ? Math.min(Math.max(Math.trunc(limitRaw), 1), 100) : 20;
|
|
|
|
try {
|
|
const session = await resolveIndexSession(request);
|
|
const storeDir = getStoreDir();
|
|
if (!storeDir) return new NextResponse(null, { status: 404 });
|
|
|
|
const payload = await withIndexKey(session.accountId, (key) => {
|
|
const index = MailIndex.open({ storeDir, accountId: session.accountId, key });
|
|
try {
|
|
const stats = index.stats();
|
|
if (!query) return { hits: [] as SearchHit[], stats };
|
|
return { hits: index.search({ query, types, limit }), stats: wantStats ? stats : undefined };
|
|
} finally {
|
|
index.close();
|
|
}
|
|
});
|
|
|
|
return NextResponse.json(
|
|
{
|
|
ok: true,
|
|
query,
|
|
types: types.length > 0 ? types : 'all',
|
|
count: payload.hits.length,
|
|
hits: payload.hits,
|
|
// Everything a prompt needs, pre-joined in rank order.
|
|
contextBlock: payload.hits.map(toContextBlock).join('\n\n---\n\n'),
|
|
...(payload.stats ? { stats: payload.stats } : {}),
|
|
},
|
|
{ headers: { 'Cache-Control': 'no-store' } },
|
|
);
|
|
} catch (error) {
|
|
if (error instanceof IndexSessionError) {
|
|
return NextResponse.json({ error: error.message }, { status: error.status });
|
|
}
|
|
if (error instanceof IndexKeyError) {
|
|
const status = error.code === 'no-secure-storage' ? 503 : 500;
|
|
return NextResponse.json({ error: error.message, code: error.code }, { status });
|
|
}
|
|
if (error instanceof MailIndexUnavailableError) {
|
|
return NextResponse.json({ error: error.message, code: 'unavailable' }, { status: 503 });
|
|
}
|
|
logger.error('mail-index search failed', {
|
|
error: error instanceof Error ? error.message : String(error),
|
|
});
|
|
return NextResponse.json({ error: 'Search failed' }, { status: 500 });
|
|
}
|
|
}
|