Compare commits

..

1 Commits

Author SHA1 Message Date
claude code agent 227 67312a3753 fix(#262): keep polling the reindex counter past the stale pre-reindex snapshot
After "Reindex now" the "Indexed X of Y" counter froze at 0 until a manual
reload. Root cause is purely client-side: right after the mutation the
client still holds the PRE-reindex settings snapshot, which for an already
fully-indexed workspace reads reindexing=false, indexed>=total. The
deadline-clearing effect evaluated isReindexComplete() against that stale
snapshot, read it as "done", and cleared the poll deadline before the first
post-reindex poll ever landed — so polling never ran and the counter stayed
at 0 (a reload just fetched one fresh snapshot).

Gate completion on having actually observed the active run: a
reindexSeenActiveRef, reset on each new reindex (mutation onSuccess, before
setting the deadline) and latched true once a poll reports reindexing=true.
isReindexComplete(status, seenActive) and nextReindexPollInterval now require
seenActive, so the stale fully-indexed snapshot no longer reads as finished.
The server pre-seeds reindexing=true from enqueue time, so seenActive latches
early and a genuine completion still stops polling promptly; the
REINDEX_POLL_CAP_MS cap is checked first and always wins, so polling can
never run away. closes #262

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 09:12:15 +03:00
4 changed files with 108 additions and 424 deletions
@@ -1,206 +0,0 @@
import { describe, it, expect, vi, beforeEach } from "vitest";
import { renderHook, act } from "@testing-library/react";
// Shared, hoisted test state the module mocks write into. `onSpeechEnd` is the
// VAD callback the hook registers on MicVAD.new — capturing it lets us drive
// "a speech segment ended" deterministically. `pending` collects the deferred
// transcription promises so the test controls their resolution order, which is
// the whole point: out-of-order HTTP responses must NOT scramble the emitted
// text (the in-order emitter under test).
const h = vi.hoisted(() => {
return {
onSpeechEnd: null as null | ((audio: Float32Array) => void),
pending: [] as { resolve: (s: string) => void; reject: (e: unknown) => void }[],
notify: null as null | ReturnType<typeof Object>,
};
});
// Lazy-imported VAD: capture the onSpeechEnd handler and hand back a no-op
// instance (start/pause/destroy all resolve).
vi.mock("@ricky0123/vad-web", () => ({
MicVAD: {
new: vi.fn(async (opts: { onSpeechEnd: (a: Float32Array) => void }) => {
h.onSpeechEnd = opts.onSpeechEnd;
return {
start: vi.fn(async () => {}),
pause: vi.fn(async () => {}),
destroy: vi.fn(async () => {}),
};
}),
},
}));
// Each transcribeAudio call returns a promise we resolve/reject by index.
vi.mock("@/features/dictation/services/dictation-service", () => ({
transcribeAudio: vi.fn(
() =>
new Promise<string>((resolve, reject) => {
h.pending.push({ resolve, reject });
}),
),
}));
// Avoid real WAV encoding; the segment payload is irrelevant to ordering.
vi.mock("@/features/dictation/utils/encode-wav", () => ({
encodeWavPcm16: vi.fn(() => new Blob()),
}));
const notifyShow = vi.fn();
vi.mock("@mantine/notifications", () => ({
notifications: { show: (...args: unknown[]) => notifyShow(...args) },
}));
vi.mock("react-i18next", () => ({
useTranslation: () => ({ t: (s: string) => s }),
}));
import { useStreamingDictation } from "./use-streaming-dictation";
// jsdom has no AudioContext; the hook constructs one and calls resume(). A
// trivial stub is enough — the real audio path is irrelevant to ordering.
class FakeAudioContext {
state = "running";
resume() {
return Promise.resolve();
}
close() {
this.state = "closed";
return Promise.resolve();
}
}
async function startRecording(onText: (t: string) => void) {
const hook = renderHook(() => useStreamingDictation({ onText }));
await act(async () => {
await hook.result.current.start();
});
// The VAD registered its onSpeechEnd and start() resolved into "recording".
expect(h.onSpeechEnd).toBeTypeOf("function");
expect(hook.result.current.status).toBe("recording");
return hook;
}
// Fire N ended speech segments (seq 0..N-1), each kicking off one transcription.
async function emitSegments(n: number) {
await act(async () => {
for (let i = 0; i < n; i++) h.onSpeechEnd!(new Float32Array(8));
});
}
describe("useStreamingDictation — in-order segment emitter", () => {
beforeEach(() => {
vi.clearAllMocks();
h.onSpeechEnd = null;
h.pending = [];
notifyShow.mockClear();
(window as unknown as { AudioContext: unknown }).AudioContext =
FakeAudioContext;
});
it("emits transcriptions in segment order even when responses resolve out of order", async () => {
const emitted: string[] = [];
await startRecording((t) => emitted.push(t));
await emitSegments(3);
expect(h.pending).toHaveLength(3);
// Resolve seq 1 FIRST: it must be buffered, not emitted, because seq 0 is
// still outstanding (nextEmit == 0).
await act(async () => {
h.pending[1].resolve("second");
});
expect(emitted).toEqual([]);
// Resolve seq 0: this unblocks the buffer and flushes 0 then 1 in order.
await act(async () => {
h.pending[0].resolve("first");
});
expect(emitted).toEqual(["first", "second"]);
// seq 2 resolves last and flushes immediately (it is now next).
await act(async () => {
h.pending[2].resolve("third");
});
expect(emitted).toEqual(["first", "second", "third"]);
});
it("trims whitespace and drops empty/whitespace-only transcriptions while still advancing", async () => {
const emitted: string[] = [];
await startRecording((t) => emitted.push(t));
await emitSegments(3);
await act(async () => {
h.pending[0].resolve(" hello "); // leading/trailing space trimmed
h.pending[1].resolve(" "); // whitespace-only -> not emitted, but seq advances
h.pending[2].resolve("world");
});
expect(emitted).toEqual(["hello", "world"]);
});
it("a failed segment shows one notification and is skipped so later segments still flush in order", async () => {
const emitted: string[] = [];
await startRecording((t) => emitted.push(t));
await emitSegments(2);
// seq 0 fails: the user sees a notification and the emitter advances past it.
await act(async () => {
h.pending[0].reject({ message: "boom" });
});
expect(notifyShow).toHaveBeenCalledTimes(1);
expect(emitted).toEqual([]);
// seq 1 still flushes (it is now next), proving one failure did not stall.
await act(async () => {
h.pending[1].resolve("survivor");
});
expect(emitted).toEqual(["survivor"]);
});
it("an OUT-OF-ORDER failed segment is buffered as empty and skipped without stalling later text", async () => {
const emitted: string[] = [];
await startRecording((t) => emitted.push(t));
await emitSegments(3);
// seq 1 (NOT next-to-emit) fails first: it takes the else branch — an empty
// placeholder is buffered (resultsRef.set(seq, "")) so the emitter can later
// skip it. One notification, nothing emitted yet (seq 0 still gates).
await act(async () => {
h.pending[1].reject({ message: "boom" });
});
expect(notifyShow).toHaveBeenCalledTimes(1);
expect(emitted).toEqual([]);
// seq 0 flushes; the drain then reaches the buffered empty seq 1 and SKIPS
// past it to seq 2.
await act(async () => {
h.pending[0].resolve("alpha");
});
expect(emitted).toEqual(["alpha"]);
// seq 2 emits — proving the empty placeholder let the emitter advance past
// the failed seq 1. Without the else branch's placeholder the drain would
// stall at the missing seq 1 and "gamma" would never flush.
await act(async () => {
h.pending[2].resolve("gamma");
});
expect(emitted).toEqual(["alpha", "gamma"]);
});
it("ignores a transcription that resolves AFTER cancel() (stale epoch — no emit)", async () => {
const emitted: string[] = [];
const hook = await startRecording((t) => emitted.push(t));
await emitSegments(1);
// Hard discard the session: the in-flight request is now stale.
act(() => {
hook.result.current.cancel();
});
expect(hook.result.current.status).toBe("idle");
// Its late resolution must be dropped (no emit into the new/empty session).
await act(async () => {
h.pending[0].resolve("late");
});
expect(emitted).toEqual([]);
});
});
@@ -1,194 +0,0 @@
import { describe, it, expect, vi, beforeEach } from "vitest";
// Mock the page-service so importing the module under test does not pull in the
// axios/api-client chain. `createMentionAction` is wired to `getPageById`; the
// spy lets us assert that wiring without any network. `vi.hoisted` keeps the spy
// available inside the hoisted vi.mock factory.
const { getPageById } = vi.hoisted(() => ({ getPageById: vi.fn() }));
vi.mock("@/features/page/services/page-service.ts", () => ({
getPageById,
}));
// `uuid` v7 is used for the mention node id; pin only v7 so assertions are
// stable, keeping the rest (e.g. `validate`, used by extractPageSlugId) real.
vi.mock("uuid", async (importOriginal) => ({
...(await importOriginal<typeof import("uuid")>()),
v7: () => "fixed-mention-uuid",
}));
import {
handleInternalLink,
createMentionAction,
} from "./internal-link-paste";
// Minimal ProseMirror-ish EditorView fake. We record what handleInternalLink
// builds and dispatches without standing up a real schema/state.
function makeView() {
const tr = {
replaceWith: vi.fn(function (this: unknown) {
return tr;
}),
insertText: vi.fn(function (this: unknown) {
return tr;
}),
addMark: vi.fn(function (this: unknown) {
return tr;
}),
};
const schema = {
nodes: {
mention: {
// Echo the attrs back so we can assert exactly what was created.
create: vi.fn((attrs: Record<string, unknown>) => ({
type: "mention",
attrs,
})),
},
},
marks: {
link: {
create: vi.fn((attrs: Record<string, unknown>) => ({
type: "link",
attrs,
})),
},
},
};
const view = {
state: { schema, tr },
dispatch: vi.fn(),
};
return { view, tr, schema };
}
describe("handleInternalLink", () => {
beforeEach(() => vi.clearAllMocks());
it("does nothing when validateFn rejects the url (no resolve, no dispatch)", async () => {
const onResolveLink = vi.fn();
const validateFn = vi.fn(() => false);
const { view } = makeView();
await handleInternalLink({ validateFn, onResolveLink })(
"any-url",
view as never,
3,
"creator-1",
);
expect(validateFn).toHaveBeenCalledWith("any-url", view);
expect(onResolveLink).not.toHaveBeenCalled();
expect(view.dispatch).not.toHaveBeenCalled();
});
it("on resolve: inserts a mention node carrying the resolved page + anchor and dispatches replaceWith at pos", async () => {
const page = {
id: "page-id-99",
title: "My Page",
slugId: "slugABC",
};
const onResolveLink = vi.fn().mockResolvedValue(page);
const { view, tr, schema } = makeView();
// extractPageSlugId("doc-slug-xyz789") -> "xyz789" (last hyphen segment).
await handleInternalLink({ validateFn: () => true, onResolveLink })(
"doc-slug-xyz789",
view as never,
5,
"creator-7",
"anchor-42",
);
// The linked page id is the extracted slug-id, not the whole url.
expect(onResolveLink).toHaveBeenCalledWith("xyz789", "creator-7");
expect(schema.nodes.mention.create).toHaveBeenCalledWith({
id: "fixed-mention-uuid",
label: "My Page",
entityType: "page",
entityId: "page-id-99",
slugId: "slugABC",
creatorId: "creator-7",
anchorId: "anchor-42",
});
expect(tr.replaceWith).toHaveBeenCalledWith(5, 5, {
type: "mention",
attrs: expect.objectContaining({ entityId: "page-id-99" }),
});
expect(tr.insertText).not.toHaveBeenCalled();
expect(view.dispatch).toHaveBeenCalledTimes(1);
expect(view.dispatch).toHaveBeenCalledWith(tr);
});
it("falls back to 'Untitled' label when the resolved page has no title", async () => {
const onResolveLink = vi
.fn()
.mockResolvedValue({ id: "p", title: "", slugId: "s" });
const { view, schema } = makeView();
await handleInternalLink({ validateFn: () => true, onResolveLink })(
"abc-id1",
view as never,
0,
"c",
);
expect(schema.nodes.mention.create).toHaveBeenCalledWith(
expect.objectContaining({ label: "Untitled" }),
);
});
it("on reject: inserts the raw url as plain text with a link mark and dispatches", async () => {
const onResolveLink = vi.fn().mockRejectedValue(new Error("not found"));
const { view, tr, schema } = makeView();
await handleInternalLink({ validateFn: () => true, onResolveLink })(
"http://x/page-id2",
view as never,
4,
"creator-1",
);
// No mention node on the failure path.
expect(schema.nodes.mention.create).not.toHaveBeenCalled();
expect(tr.insertText).toHaveBeenCalledWith("http://x/page-id2", 4);
expect(schema.marks.link.create).toHaveBeenCalledWith({
href: "http://x/page-id2",
});
// Mark spans exactly the inserted url text: [pos, pos + url.length].
expect(tr.addMark).toHaveBeenCalledWith(4, 4 + "http://x/page-id2".length, {
type: "link",
attrs: { href: "http://x/page-id2" },
});
expect(view.dispatch).toHaveBeenCalledTimes(1);
});
});
describe("createMentionAction", () => {
beforeEach(() => vi.clearAllMocks());
it("resolves the link via getPageById and inserts the mention", async () => {
getPageById.mockResolvedValue({
id: "real-page",
title: "Real",
slugId: "rslug",
});
const { view, schema } = makeView();
await createMentionAction("ref-pageABC", view as never, 2, "creator-9");
expect(getPageById).toHaveBeenCalledWith({ pageId: "pageABC" });
expect(schema.nodes.mention.create).toHaveBeenCalledWith(
expect.objectContaining({ entityId: "real-page", label: "Real" }),
);
});
it("propagates a getPageById failure to the plain-link fallback", async () => {
getPageById.mockRejectedValue(new Error("404"));
const { view, tr } = makeView();
await createMentionAction("ref-pageABC", view as never, 1, "creator-9");
// Failure path: the url is inserted as text, not as a mention node.
expect(tr.insertText).toHaveBeenCalledWith("ref-pageABC", 1);
});
});
@@ -77,7 +77,9 @@ describe('resolveKeyField (write-only key payload)', () => {
describe('nextReindexPollInterval', () => {
const INTERVAL = 5000;
const base = { now: 1_000, intervalMs: INTERVAL };
// `seenActive: true` is the steady state for most of a run — a poll has
// observed `reindexing === true` (the server pre-seeds it from enqueue time).
const base = { now: 1_000, intervalMs: INTERVAL, seenActive: true };
it('does not poll when no reindex deadline is set', () => {
expect(
@@ -111,7 +113,7 @@ describe('nextReindexPollInterval', () => {
).toBe(INTERVAL);
});
it('stops once the run is finished AND fully indexed', () => {
it('stops once the run is finished AND fully indexed (after having been active)', () => {
expect(
nextReindexPollInterval({
...base,
@@ -121,11 +123,29 @@ describe('nextReindexPollInterval', () => {
).toBe(false);
});
it('does NOT stop on the stale pre-reindex snapshot (fully indexed, never seen active)', () => {
// Regression for #262: right after "Reindex now" the client still holds the
// PRE-reindex settings (an already fully-indexed workspace reads as
// reindexing=false, indexed>=total). Without the seenActive gate this looked
// "done" and stopped polling on the very first tick, freezing the counter at
// 0 until a manual reload. The fresh window has not observed the active run,
// so polling must continue until the first real poll lands.
expect(
nextReindexPollInterval({
...base,
seenActive: false,
deadline: 10_000,
status: { reindexing: false, indexedPages: 478, totalPages: 478 },
}),
).toBe(INTERVAL);
});
it('keeps polling within the deadline when not yet done and no active flag', () => {
// First poll right after enqueue, before the worker publishes progress.
expect(
nextReindexPollInterval({
...base,
seenActive: false,
deadline: 10_000,
status: { reindexing: false, indexedPages: 0, totalPages: 478 },
}),
@@ -138,12 +158,15 @@ describe('nextReindexPollInterval', () => {
deadline: 1_000,
now: 2_000, // past the deadline
intervalMs: INTERVAL,
seenActive: true,
status: { reindexing: true, indexedPages: 200, totalPages: 478 },
}),
).toBe(false);
});
it('stops on an empty workspace (0 of 0) once the run is finished', () => {
// The pre-seed publishes reindexing=true even for 0 pages, so a poll sees the
// run active before the worker clears -> seenActive latches true.
expect(
nextReindexPollInterval({
...base,
@@ -156,26 +179,46 @@ describe('nextReindexPollInterval', () => {
describe('isReindexComplete', () => {
it('false when no status yet', () => {
expect(isReindexComplete(undefined)).toBe(false);
expect(isReindexComplete(undefined, true)).toBe(false);
});
it('false while a run is still active (even at indexed==total)', () => {
expect(
isReindexComplete({ reindexing: true, indexedPages: 478, totalPages: 478 }),
isReindexComplete(
{ reindexing: true, indexedPages: 478, totalPages: 478 },
true,
),
).toBe(false);
});
it('false when finished but not yet fully indexed', () => {
expect(
isReindexComplete({ reindexing: false, indexedPages: 120, totalPages: 478 }),
isReindexComplete(
{ reindexing: false, indexedPages: 120, totalPages: 478 },
true,
),
).toBe(false);
});
it('true once finished and fully indexed', () => {
it('true once finished and fully indexed (after having been active)', () => {
expect(
isReindexComplete({ reindexing: false, indexedPages: 478, totalPages: 478 }),
isReindexComplete(
{ reindexing: false, indexedPages: 478, totalPages: 478 },
true,
),
).toBe(true);
});
it('false on the stale pre-reindex snapshot: finished+fully indexed but never seen active', () => {
// The just-started edge: the gate keeps this from clearing the poll deadline
// before the first post-reindex poll arrives.
expect(
isReindexComplete(
{ reindexing: false, indexedPages: 478, totalPages: 478 },
false,
),
).toBe(false);
});
});
describe('isReindexButtonLoading', () => {
@@ -1,4 +1,4 @@
import { useEffect, useState } from "react";
import { useEffect, useRef, useState } from "react";
import { z } from "zod/v4";
import {
ActionIcon,
@@ -185,14 +185,23 @@ type ReindexStatus = Pick<
* has finished AND everything is indexed (server cleared its progress record and
* fell back to the DB coverage count), or the deadline cap is hit — the cap
* always wins so a stuck/never-clearing progress record can't poll forever.
*
* `seenActive` guards the just-started window: right after "Reindex now" the
* client still holds the PRE-reindex settings snapshot, which for an already
* fully-indexed workspace reads as `reindexing=false, indexed>=total`. Treating
* that stale snapshot as "done" would stop polling before the first post-reindex
* poll ever lands (counter frozen at 0). So completion is only honored once a
* poll has actually observed the active run (the enqueue-time pre-seed makes
* `reindexing=true` visible from the first poll until the run truly clears).
*/
export function nextReindexPollInterval(args: {
deadline: number | null;
now: number;
intervalMs: number;
status?: ReindexStatus;
seenActive: boolean;
}): number | false {
const { deadline, now, intervalMs, status } = args;
const { deadline, now, intervalMs, status, seenActive } = args;
if (deadline === null) return false;
// Cap always wins.
if (now > deadline) return false;
@@ -200,20 +209,33 @@ export function nextReindexPollInterval(args: {
if (status?.reindexing) return intervalMs;
// Finished and fully indexed (incl. an empty workspace, 0 >= 0) → stop. Reuse
// isReindexComplete so the completeness check lives in exactly one place.
if (isReindexComplete(status)) return false;
if (isReindexComplete(status, seenActive)) return false;
// Within the deadline and not yet done → keep polling.
return intervalMs;
}
/**
* Whether the reindex poll deadline should be cleared: the server reports no
* active run AND the count is complete. The single source of truth for the
* "reindex finished" check — `nextReindexPollInterval` reuses it for its stop
* condition (sans the cap, which the effect handles via time).
* Whether the reindex poll deadline should be cleared: a poll has observed the
* active run (`seenActive`) AND the server now reports no active run AND the
* count is complete. The single source of truth for the "reindex finished"
* check — `nextReindexPollInterval` reuses it for its stop condition (sans the
* cap, which the effect handles via time).
*
* The `seenActive` requirement is what keeps the STALE pre-reindex snapshot
* (already fully indexed → `reindexing=false, indexed>=total`) from being read
* as "finished" in the window before the first post-reindex poll arrives. Once
* a poll has seen `reindexing=true` (guaranteed by the server's enqueue-time
* pre-seed for the whole run), this flips to a genuine completion check.
*/
export function isReindexComplete(status?: ReindexStatus): boolean {
export function isReindexComplete(
status: ReindexStatus | undefined,
seenActive: boolean,
): boolean {
return (
!!status && !status.reindexing && status.indexedPages >= status.totalPages
seenActive &&
!!status &&
!status.reindexing &&
status.indexedPages >= status.totalPages
);
}
@@ -290,6 +312,14 @@ export default function AiProviderSettings() {
const REINDEX_POLL_INTERVAL = 5000; // ms between refetches while indexing
const REINDEX_POLL_CAP_MS = 120000; // ~2 min hard cap
const [reindexDeadline, setReindexDeadline] = useState<number | null>(null);
// Whether any poll in the CURRENT window has actually observed the active run
// (`reindexing === true`). Reset when a new reindex is kicked off. Gates the
// completion check so the STALE pre-reindex snapshot (an already fully-indexed
// workspace reads as `reindexing=false, indexed>=total`) can't be mistaken for
// "finished" before the first post-reindex poll lands — which would freeze the
// counter at 0 until a manual reload. A ref (not state) because it must not
// trigger a render and is only ever read where `reindexing` is already false.
const reindexSeenActiveRef = useRef(false);
// Only admins may read the (masked) AI settings; the server enforces this too.
const { data: settings, isLoading } = useAiSettingsQuery(isAdmin, (query) =>
@@ -298,6 +328,7 @@ export default function AiProviderSettings() {
now: Date.now(),
intervalMs: REINDEX_POLL_INTERVAL,
status: query.state.data,
seenActive: reindexSeenActiveRef.current,
}),
);
@@ -305,12 +336,17 @@ export default function AiProviderSettings() {
// unmount because the deadline state goes away with the component.
useEffect(() => {
if (reindexDeadline === null) return;
// "Done" matches the refetchInterval stop condition: the server reports no
// active run AND the count is complete (indexed >= total, incl. an empty
// workspace 0 >= 0), so the deadline clears promptly instead of waiting out
// the cap. While `reindexing` is still true we keep the deadline so polling
// continues for the whole run.
if (isReindexComplete(settings)) {
// Latch "we have seen the active run" the moment a poll reports it, so the
// completion check below (and the refetchInterval's) only fires once the run
// has genuinely started — never on the stale pre-reindex snapshot.
if (settings?.reindexing) reindexSeenActiveRef.current = true;
// "Done" matches the refetchInterval stop condition: a poll has observed the
// active run AND the server now reports no active run AND the count is
// complete (indexed >= total, incl. an empty workspace 0 >= 0), so the
// deadline clears promptly instead of waiting out the cap. While `reindexing`
// is still true (or no poll has seen it active yet) we keep the deadline so
// polling continues for the whole run.
if (isReindexComplete(settings, reindexSeenActiveRef.current)) {
setReindexDeadline(null);
return;
}
@@ -1117,8 +1153,13 @@ export default function AiProviderSettings() {
reindexMutation.mutate(undefined, {
// Begin bounded polling so the counter climbs as the async
// background job indexes (it does not update on its own).
onSuccess: () =>
setReindexDeadline(Date.now() + REINDEX_POLL_CAP_MS),
// Clear the "seen active" latch first so this fresh window
// doesn't inherit a previous run's completion state and stop
// immediately.
onSuccess: () => {
reindexSeenActiveRef.current = false;
setReindexDeadline(Date.now() + REINDEX_POLL_CAP_MS);
},
})
}
>