feat(documents): route vault AI surfaces through document provider order

Repoint suggest/summary/extract/index/reindex routes and the content-index
backfill job to the document-scoped resolvers (local-first, codex last) and the
pick-based document-egress consent gate. Labs OCR and Coach/insights untouched.

Co-Authored-By: Marc-André Bombeck
This commit is contained in:
Marc-André BombeckandMarc-André Bombeck committed 2026-07-08 23:49:30 +02:00
1 parent f7ad2339ae
commit 8e5f5f04ae
6 files changed
+79 -41

No files matched your search

@@ -31,7 +31,7 @@ import {
safeJson,
} from "@/lib/api-response";
import { AI_BUDGETS } from "@/lib/ai/ai-budgets";
import { assertConsentForChain } from "@/lib/ai/consent-guard";
import { assertDocumentEgressConsent } from "@/lib/ai/consent-guard";
import {
buildDateKey,
reconcileSpend,
@@ -52,9 +52,9 @@ import {
serialiseDocumentDetail,
} from "@/lib/documents/store";
import {
resolveTextProvider,
resolveVisionProvider,
} from "@/lib/labs/ocr-capability";
resolveDocumentTextProvider,
resolveDocumentVisionProvider,
} from "@/lib/documents/provider-order";
import { detectOcrMimeType } from "@/lib/labs/ocr-upload";
import { annotate } from "@/lib/logging/context";
import { requireModuleEnabled } from "@/lib/modules/gate";
@@ -200,14 +200,18 @@ async function handleTextExtract(
});
}
const { chain, pick } = await resolveTextProvider(userId);
const { pick } = await resolveDocumentTextProvider(userId);
if (!pick) {
return apiError("No AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`documents-inbound:${userId}`,
@@ -298,14 +302,18 @@ async function handleVisionExtract(
userId: string,
document: LoadedDocument,
): Promise<Response> {
const { chain, pick } = await resolveVisionProvider(userId);
const { pick } = await resolveDocumentVisionProvider(userId);
if (!pick) {
return apiError("No vision-capable AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`documents-inbound:${userId}`,
@@ -14,8 +14,9 @@
* Decision (maintainer, 2026-07-07): content indexing is gated on the EXISTING
* AI consent / provider gate — there is NO separate `documentsContentIndexEnabled`
* toggle (the plan's P2-D8 opt-in was refused to avoid toggle sprawl). The vision
* path runs `assertConsentForChain`; the text path rides the local-OCR opt-in the
* lab / extract text mode already uses.
* path runs `assertDocumentEgressConsent` (any external provider needs an active
* receipt; a local pick stays ungated); the text path rides the local-OCR opt-in
* the lab / extract text mode already uses — no provider egress at all.
*
* Persists ONLY AES-256-GCM ciphertext text + opaque HMAC token hashes (A4).
*/
@@ -29,7 +30,7 @@ import {
safeJson,
} from "@/lib/api-response";
import { AI_BUDGETS } from "@/lib/ai/ai-budgets";
import { assertConsentForChain } from "@/lib/ai/consent-guard";
import { assertDocumentEgressConsent } from "@/lib/ai/consent-guard";
import {
buildDateKey,
reconcileSpend,
@@ -51,7 +52,7 @@ import {
DocumentDescribeError,
transcribeDocument,
} from "@/lib/documents/describe";
import { resolveVisionProvider } from "@/lib/labs/ocr-capability";
import { resolveDocumentVisionProvider } from "@/lib/documents/provider-order";
import { annotate } from "@/lib/logging/context";
import { requireModuleEnabled } from "@/lib/modules/gate";
import { prisma } from "@/lib/db";
@@ -164,13 +165,17 @@ async function handleVisionIndex(
userId: string,
document: LoadedDocument,
): Promise<Response> {
const { chain, pick } = await resolveVisionProvider(userId);
const { pick } = await resolveDocumentVisionProvider(userId);
if (!pick) {
return apiError("No vision-capable AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`${DOCUMENT_AI_BUCKET}:${userId}`,
@@ -22,7 +22,7 @@ import {
safeJson,
} from "@/lib/api-response";
import { AI_BUDGETS } from "@/lib/ai/ai-budgets";
import { assertConsentForChain } from "@/lib/ai/consent-guard";
import { assertDocumentEgressConsent } from "@/lib/ai/consent-guard";
import {
buildDateKey,
reconcileSpend,
@@ -45,9 +45,9 @@ import {
type LoadedDocument,
} from "@/lib/documents/ai-route-support";
import {
resolveTextProvider,
resolveVisionProvider,
} from "@/lib/labs/ocr-capability";
resolveDocumentTextProvider,
resolveDocumentVisionProvider,
} from "@/lib/documents/provider-order";
import { annotate } from "@/lib/logging/context";
import { requireModuleEnabled } from "@/lib/modules/gate";
import { prisma } from "@/lib/db";
@@ -133,14 +133,18 @@ async function handleTextSuggest(
});
}
const { chain, pick } = await resolveTextProvider(userId);
const { pick } = await resolveDocumentTextProvider(userId);
if (!pick) {
return apiError("No AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`${DOCUMENT_AI_BUCKET}:${userId}`,
@@ -209,14 +213,18 @@ async function handleVisionSuggest(
userId: string,
document: LoadedDocument,
): Promise<Response> {
const { chain, pick } = await resolveVisionProvider(userId);
const { pick } = await resolveDocumentVisionProvider(userId);
if (!pick) {
return apiError("No vision-capable AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`${DOCUMENT_AI_BUCKET}:${userId}`,
@@ -23,7 +23,7 @@ import {
safeJson,
} from "@/lib/api-response";
import { AI_BUDGETS } from "@/lib/ai/ai-budgets";
import { assertConsentForChain } from "@/lib/ai/consent-guard";
import { assertDocumentEgressConsent } from "@/lib/ai/consent-guard";
import {
buildDateKey,
reconcileSpend,
@@ -47,9 +47,9 @@ import {
type DescribeInput,
} from "@/lib/documents/describe";
import {
resolveTextProvider,
resolveVisionProvider,
} from "@/lib/labs/ocr-capability";
resolveDocumentTextProvider,
resolveDocumentVisionProvider,
} from "@/lib/documents/provider-order";
import { annotate } from "@/lib/logging/context";
import { requireModuleEnabled } from "@/lib/modules/gate";
import { prisma } from "@/lib/db";
@@ -188,13 +188,17 @@ async function handleTextSummary(
return finishSummary(request, userId, document.id, "text", mode, result);
}
const { chain, pick } = await resolveTextProvider(userId);
const { pick } = await resolveDocumentTextProvider(userId);
if (!pick) {
return apiError("No AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const dateKey = buildDateKey();
const reservation = await reserveBudget(
@@ -235,13 +239,17 @@ async function handleVisionSummary(
document: LoadedDocument,
mode: DocumentSummaryMode,
): Promise<Response> {
const { chain, pick } = await resolveVisionProvider(userId);
const { pick } = await resolveDocumentVisionProvider(userId);
if (!pick) {
return apiError("No vision-capable AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
const rl = await checkRateLimit(
`${DOCUMENT_AI_BUCKET}:${userId}`,
@@ -9,10 +9,10 @@
*/
import { apiHandler, requireAuth } from "@/lib/api-handler";
import { apiError, apiSuccess, getClientIp } from "@/lib/api-response";
import { assertConsentForChain } from "@/lib/ai/consent-guard";
import { assertDocumentEgressConsent } from "@/lib/ai/consent-guard";
import { auditLog } from "@/lib/auth/audit";
import { enqueueContentIndexBackfill } from "@/lib/jobs/document-content-index-backfill";
import { resolveVisionProvider } from "@/lib/labs/ocr-capability";
import { resolveDocumentVisionProvider } from "@/lib/documents/provider-order";
import { annotate } from "@/lib/logging/context";
import { requireModuleEnabled } from "@/lib/modules/gate";
import { checkRateLimit, rateLimitHeaders } from "@/lib/rate-limit";
@@ -46,13 +46,17 @@ export const POST = apiHandler(async (request) => {
// Fail fast when the precondition is not met so the UI gets immediate
// feedback rather than a silently no-op'd job.
const { chain, pick } = await resolveVisionProvider(user.id);
const { pick } = await resolveDocumentVisionProvider(user.id);
if (!pick) {
return apiError("No vision-capable AI provider is configured", 422, {
errorCode: "documents.inbound.providerUnsupported",
});
}
await assertConsentForChain({ userId: user.id, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId: user.id,
providerType: pick.providerType,
surface: "insights",
});
const { enqueued } = await enqueueContentIndexBackfill(user.id);
@@ -8,9 +8,10 @@
* indexing egresses to a provider under the user's key + budget, so it must be
* a deliberate, consented act, exactly like the per-document index route.
*
* Consent: gated on the EXISTING AI consent (`assertConsentForChain`), the same
* gate the extract / index routes use — there is no separate per-user toggle
* (maintainer decision, 2026-07-07).
* Consent: gated on the document-egress consent (`assertDocumentEgressConsent`),
* the same gate the extract / index routes use — any external provider needs an
* active receipt; a local pick stays ungated. There is no separate per-user
* toggle (maintainer decision, 2026-07-07).
*
* Bounded + resumable: an id-cursor forward walk over the not-yet-indexed set,
* capped at `MAX_DOCS_PER_RUN` provider calls per job and stopped the moment the
@@ -24,7 +25,7 @@
*/
import { AI_BUDGETS } from "@/lib/ai/ai-budgets";
import {
assertConsentForChain,
assertDocumentEgressConsent,
ConsentRequiredError,
} from "@/lib/ai/consent-guard";
import {
@@ -41,7 +42,7 @@ import {
import { upsertContentIndex } from "@/lib/documents/content-index";
import { transcribeDocument } from "@/lib/documents/describe";
import { getGlobalBoss } from "@/lib/jobs/boss-instance";
import { resolveVisionProvider } from "@/lib/labs/ocr-capability";
import { resolveDocumentVisionProvider } from "@/lib/documents/provider-order";
import { annotate } from "@/lib/logging/context";
export const CONTENT_INDEX_BACKFILL_QUEUE = "document-content-index-backfill";
@@ -76,10 +77,14 @@ export interface ContentIndexBackfillSummary {
export async function runContentIndexBackfillForUser(
userId: string,
): Promise<ContentIndexBackfillSummary> {
const { chain, pick } = await resolveVisionProvider(userId);
const { pick } = await resolveDocumentVisionProvider(userId);
if (!pick) return { indexed: 0, reason: "no-provider" };
try {
await assertConsentForChain({ userId, chain, surface: "insights" });
await assertDocumentEgressConsent({
userId,
providerType: pick.providerType,
surface: "insights",
});
} catch (err) {
if (err instanceof ConsentRequiredError) {
return { indexed: 0, reason: "no-consent" };