feat(#370): page-history intentionality tiers — kind column + intentional/idle/boundary triggers (PR-1 core)

PR-1 'core' of #370: introduces page_history.kind ('manual'|'agent'|'idle'|
'boundary'; legacy null = autosave) and rebuilds the snapshot triggers around a
three-tier intentionality model. Draft durability (pages/ydoc hocuspocus
autosave) is unchanged; only the frequency and labelling of history points change.

- Migration 20260705T120000: page_history.kind nullable varchar(20), no default.
- Manual Save: one stateless 'save-version' path for human AND agent; kind is
  derived SERVER-SIDE from the signed context.actor (never the payload), readOnly
  connections rejected, the fresh ydoc runs through the existing store path (no
  REST race), then broadcasts version.saved.
- Idle-flush: trailing debounce (one BullMQ job per page, remove-then-readd) with
  IDLE_INTERVAL_USER=60m / AGENT=15m AND a max-wait ceiling
  (IDLE_MAX_WAIT_USER=10m / AGENT=5m) so a continuous editing session can't starve
  the autosnapshot (review round-1 WARNING).
- Boundary: generalized from the user→agent special-case to ANY lastUpdatedSource
  transition (user↔agent↔git), same isDeepStrictEqual gate — covers git-sync free.
- Removed the agent delay=0 fast path and the old HISTORY_FAST_* constants; the
  agent joins the common idle pipeline.
- Promote-not-dup: a manual save on unchanged content promotes the latest
  autosave's kind in place (or no-ops if already manual) instead of duplicating a
  heavy content row.
- Client: mod+S hotkey + menu button (hidden when readOnly), history-panel kind
  badges, dimmed autosaves, a 'versions only' filter (indices map to the full
  list so diff/restore still target the true previous snapshot), live refresh on
  version.saved.

Internal review: APPROVE-with-suggestions; the round-1 WARNING (idle starvation)
is fixed here via the max-wait ceiling, and the generalized-boundary + ceiling
behaviours are pinned with new tests (115 collab/repo specs green, server tsc 0).

Deferred to later PRs: shares.published_mode (PR-2), the save_page_version MCP
tool + role prompts (PR-3), actor='git' wiring into #359 (PR-4).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
agent_coder
2026-07-05 05:00:12 +03:00
committed by agent_coder
parent 3085ec1b50
commit e10e79c0c4
19 changed files with 788 additions and 135 deletions
+29 -3
View File
@@ -1,3 +1,29 @@
export const HISTORY_INTERVAL = 5 * 60 * 1000;
export const HISTORY_FAST_INTERVAL = 60 * 1000;
export const HISTORY_FAST_THRESHOLD = 5 * 60 * 1000;
/**
* #370 — page-history intentionality tiers. Domain of `page_history.kind`.
* - 'manual' / 'agent' → Tier 1 versions (intentional points)
* - 'idle' / 'boundary' → Tier 0 autosnapshots (safety net)
* A legacy `null` kind is treated as an autosave.
*/
export type PageHistoryKind = 'manual' | 'agent' | 'idle' | 'boundary';
/**
* #370 — trailing idle-flush windows. A page's pending idle snapshot is
* re-armed on every store and fires this long after edits go quiet, so a burst
* of edits collapses into a single autosnapshot instead of one-per-store. Human
* sessions are noisier and less risky, so they flush less often than the agent.
*/
export const IDLE_INTERVAL_USER = 60 * 60 * 1000; // 60m
export const IDLE_INTERVAL_AGENT = 15 * 60 * 1000; // 15m
/**
* #370 — max-wait ceiling for the idle flush. Pure trailing debounce starves the
* safety net: hocuspocus stores at least every ~45s, so a CONTINUOUS editing
* session would re-arm the trailing timer forever and never take an idle
* snapshot until edits finally go quiet (up to IDLE_INTERVAL_USER = 60m). This
* ceiling bounds the actual wait from the FIRST edit of a burst, so an idle
* snapshot fires at least this often during a long unbroken session — restoring
* a recovery point cadence closer to the old heuristic without one-per-store
* noise. Mirrors hocuspocus's own maxDebounce idea.
*/
export const IDLE_MAX_WAIT_USER = 10 * 60 * 1000; // 10m
export const IDLE_MAX_WAIT_AGENT = 5 * 60 * 1000; // 5m
@@ -1,84 +1,93 @@
import { computeHistoryJob, resolveSource } from './persistence.extension';
import {
computeHistoryJob,
resolveSource,
} from './persistence.extension';
import {
HISTORY_FAST_INTERVAL,
HISTORY_FAST_THRESHOLD,
HISTORY_INTERVAL,
IDLE_INTERVAL_AGENT,
IDLE_INTERVAL_USER,
IDLE_MAX_WAIT_AGENT,
IDLE_MAX_WAIT_USER,
} from '../constants';
// A fixed clock + fixed createdAt make pageAge deterministic.
const NOW = 1_700_000_000_000;
const PAGE_ID = '550e8400-e29b-41d4-a716-446655440000';
// Build a minimal page whose age (NOW - createdAt) is exactly `ageMs`.
const pageAged = (ageMs: number) => ({
id: PAGE_ID,
createdAt: new Date(NOW - ageMs),
});
const page = { id: PAGE_ID };
describe('computeHistoryJob', () => {
it('agent edit → delay MUST be 0 and job id is source-keyed', () => {
// INVARIANT (§15 H2 / persistence.extension): the agent delay MUST stay 0.
// The worker re-reads the page row at run time, so any non-zero delay risks
// snapshotting content a later human edit has already overwritten. This is
// the load-bearing assertion of this spec — do not relax it.
const { jobId, delay } = computeHistoryJob(pageAged(0), 'agent', NOW);
expect(delay).toBe(0);
expect(jobId).toBe(`${PAGE_ID}-agent`);
});
it('agent edit on an OLD page is still delay 0 (age never applies to agents)', () => {
// Even when the page is far older than the fast threshold, the agent path
// must short-circuit to 0 — age-based debounce is a human-only concern.
const { jobId, delay } = computeHistoryJob(
pageAged(HISTORY_FAST_THRESHOLD + 60_000),
'agent',
NOW,
);
expect(delay).toBe(0);
expect(jobId).toBe(`${PAGE_ID}-agent`);
});
it('human edit on a YOUNG page (age < threshold) → fast interval, bare job id', () => {
const { jobId, delay } = computeHistoryJob(
pageAged(HISTORY_FAST_THRESHOLD - 1),
'user',
NOW,
);
expect(delay).toBe(HISTORY_FAST_INTERVAL);
describe('computeHistoryJob (#370 — shared trailing idle pipeline)', () => {
it('human edit → user idle window, bare page.id job', () => {
// Humans and the agent now share ONE idle job per page (jobId = page.id).
// The agent's old delay=0 fast path is GONE — intentional agent points now
// arrive via the explicit save-version signal, not a zero-delay snapshot.
const { jobId, delay } = computeHistoryJob(page, 'user');
expect(delay).toBe(IDLE_INTERVAL_USER);
expect(jobId).toBe(PAGE_ID);
});
it('human edit on an OLD page (age > threshold) → standard interval', () => {
const { jobId, delay } = computeHistoryJob(
pageAged(HISTORY_FAST_THRESHOLD + 1),
'user',
NOW,
);
expect(delay).toBe(HISTORY_INTERVAL);
it('agent edit → agent idle window (shorter), still the bare page.id job', () => {
const { jobId, delay } = computeHistoryJob(page, 'agent');
expect(delay).toBe(IDLE_INTERVAL_AGENT);
// No `-agent` suffix anymore: the agent joins the common idle pipeline.
expect(jobId).toBe(PAGE_ID);
});
it('boundary: pageAge EXACTLY === threshold takes the slow branch (the `<` is strict)', () => {
// Off-by-one guard: the condition is `pageAge < HISTORY_FAST_THRESHOLD`, so
// an age of exactly the threshold is NOT "fast" — it must use HISTORY_INTERVAL.
const { delay } = computeHistoryJob(
pageAged(HISTORY_FAST_THRESHOLD),
'user',
NOW,
);
expect(delay).toBe(HISTORY_INTERVAL);
it('agent flushes sooner than a human', () => {
expect(IDLE_INTERVAL_AGENT).toBeLessThan(IDLE_INTERVAL_USER);
});
it('treats any non-"agent" source string as human', () => {
// resolveSource only ever yields 'agent' | 'user', but guard the contract:
// the agent branch keys strictly on === 'agent'.
const { jobId, delay } = computeHistoryJob(pageAged(0), 'user', NOW);
expect(delay).toBe(HISTORY_FAST_INTERVAL);
it('treats any non-"agent" source string as human (keys strictly on === agent)', () => {
const { jobId, delay } = computeHistoryJob(page, 'user');
expect(delay).toBe(IDLE_INTERVAL_USER);
expect(jobId).toBe(PAGE_ID);
});
// #370 review round-1 WARNING: the max-wait ceiling prevents autosnapshot
// starvation during a continuous editing session (the trailing timer would
// otherwise re-arm forever and never fire).
describe('max-wait ceiling', () => {
const T0 = 1_000_000; // arbitrary fixed epoch for deterministic tests
it('early in the burst, the full trailing interval is used', () => {
// 1 minute into the burst: remaining budget (10m - 1m = 9m) still exceeds
// nothing that clamps it below the interval only if interval > remaining.
// For USER, interval 60m > remaining 9m, so delay clamps to the remaining.
const { delay } = computeHistoryJob(page, 'user', T0, T0 + 60_000);
expect(delay).toBe(IDLE_MAX_WAIT_USER - 60_000);
});
it('never waits longer than the max-wait budget from the burst start', () => {
// A store arriving right at the ceiling → delay 0 (fire promptly).
const { delay } = computeHistoryJob(
page,
'user',
T0,
T0 + IDLE_MAX_WAIT_USER,
);
expect(delay).toBe(0);
});
it('past the ceiling never returns a negative delay', () => {
const { delay } = computeHistoryJob(
page,
'user',
T0,
T0 + IDLE_MAX_WAIT_USER + 5 * 60_000,
);
expect(delay).toBe(0);
});
it('the agent ceiling is shorter than the user ceiling', () => {
expect(IDLE_MAX_WAIT_AGENT).toBeLessThan(IDLE_MAX_WAIT_USER);
const { delay } = computeHistoryJob(
page,
'agent',
T0,
T0 + IDLE_MAX_WAIT_AGENT,
);
expect(delay).toBe(0);
});
it('without a burstStart there is no ceiling (backward-compatible)', () => {
expect(computeHistoryJob(page, 'user').delay).toBe(IDLE_INTERVAL_USER);
expect(computeHistoryJob(page, 'agent').delay).toBe(IDLE_INTERVAL_AGENT);
});
});
});
describe('resolveSource (truth table)', () => {
@@ -40,11 +40,12 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
let pageHistoryRepo: {
saveHistory: jest.Mock;
findPageLastHistory: jest.Mock;
updateHistoryKind: jest.Mock;
};
let aiQueue: { add: jest.Mock };
let historyQueue: { add: jest.Mock };
let historyQueue: { add: jest.Mock; remove: jest.Mock };
let notificationQueue: { add: jest.Mock };
let collabHistory: { addContributors: jest.Mock };
let collabHistory: { addContributors: jest.Mock; popContributors: jest.Mock };
let transclusionService: {
syncPageTransclusions: jest.Mock;
syncPageReferences: jest.Mock;
@@ -93,13 +94,22 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
pageHistoryRepo = {
saveHistory: jest.fn().mockImplementation(async () => {
callOrder.push('saveHistory');
return { id: 'history-1' };
}),
findPageLastHistory: jest.fn().mockResolvedValue(null),
updateHistoryKind: jest.fn().mockResolvedValue(undefined),
};
aiQueue = { add: jest.fn().mockResolvedValue(undefined) };
historyQueue = { add: jest.fn().mockResolvedValue(undefined) };
historyQueue = {
add: jest.fn().mockResolvedValue(undefined),
// #370 — enqueuePageHistory now removes any pending idle job before re-adding.
remove: jest.fn().mockResolvedValue(undefined),
};
notificationQueue = { add: jest.fn().mockResolvedValue(undefined) };
collabHistory = { addContributors: jest.fn().mockResolvedValue(undefined) };
collabHistory = {
addContributors: jest.fn().mockResolvedValue(undefined),
popContributors: jest.fn().mockResolvedValue([]),
};
transclusionService = {
syncPageTransclusions: jest.fn().mockResolvedValue(undefined),
syncPageReferences: jest.fn().mockResolvedValue(undefined),
@@ -165,6 +175,50 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
expect(pageRepo.updatePage.mock.calls[0][0].lastUpdatedSource).toBe('user');
});
// #370 review round-1 SUGGESTION: the boundary was GENERALIZED from a
// user→agent special-case to ANY lastUpdatedSource transition. These pin the
// generalized behaviour it was rebuilt for.
describe('generalized boundary — any source transition', () => {
// Same persisted page but with an explicit prior source.
const pageWithPriorSource = (prior: string | null) => ({
...persistedHumanPage('NEW CONTENT'),
lastUpdatedSource: prior,
});
it('agent→user transition fires the boundary (pins the prior agent revision)', async () => {
const document = ydocFor(doc('NEW CONTENT'));
pageRepo.findById.mockResolvedValue(pageWithPriorSource('agent'));
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
await ext.onStoreDocument(buildData(document, 'user') as any);
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledTimes(1);
expect(callOrder).toEqual(['saveHistory', 'updatePage']);
expect(pageRepo.updatePage.mock.calls[0][0].lastUpdatedSource).toBe('user');
});
it('git→user transition fires the boundary (git-sync overwrite is a source change)', async () => {
const document = ydocFor(doc('NEW CONTENT'));
pageRepo.findById.mockResolvedValue(pageWithPriorSource('git'));
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
await ext.onStoreDocument(buildData(document, 'user') as any);
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledTimes(1);
expect(callOrder).toEqual(['saveHistory', 'updatePage']);
});
it('a null prior source (first-ever edit) does NOT fire the boundary', async () => {
const document = ydocFor(doc('NEW CONTENT'));
pageRepo.findById.mockResolvedValue(pageWithPriorSource(null));
await ext.onStoreDocument(buildData(document, 'agent') as any);
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
expect(pageRepo.updatePage).toHaveBeenCalledTimes(1);
});
});
it('idempotency: unchanged content → no updatePage, no history, no queues', async () => {
// The Y.Doc content equals the persisted content deeply → early skip.
// A Y.Doc round-trip normalizes attrs (e.g. paragraph indent), so derive
@@ -469,4 +523,125 @@ describe('PersistenceExtension.onStoreDocument — Approach-A boundary snapshot'
// Contributors keyed by the UUID so they match the PAGE_HISTORY job (page.id).
expect(collabHistory.addContributors.mock.calls[0][0]).toBe(PAGE_ID);
});
// #370 — explicit save-version (Cmd+S / agent save tool) over the stateless
// seam. The tier is derived from the SIGNED connection actor, the store path
// is reused, and promote-not-dup avoids duplicating heavy content rows.
describe('save-version (#370)', () => {
const emitSave = (document: any, actor: 'user' | 'agent') =>
ext.onStateless({
connection: {
readOnly: false,
context: { user: { id: USER_ID, name: 'Alice' }, actor },
} as any,
documentName: `page.${PAGE_ID}`,
document: document as any,
payload: JSON.stringify({ type: 'save-version' }),
} as any);
// findById returns a page whose content already equals the live doc, so the
// store path is a no-op and we isolate the versioning decision.
const pageMatchingDoc = (document: any) => ({
...persistedHumanPage('IGNORED'),
content: TiptapTransformer.fromYdoc(document, 'default'),
});
it('human save with no prior snapshot → writes a manual version + broadcasts', async () => {
const document = ydocFor(doc('VERSION ME'));
pageRepo.findById.mockResolvedValue(pageMatchingDoc(document));
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
await emitSave(document, 'user');
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledTimes(1);
expect(pageHistoryRepo.saveHistory.mock.calls[0][1]).toEqual(
expect.objectContaining({ kind: 'manual' }),
);
// The pending idle autosnapshot is cancelled by the explicit version.
expect(historyQueue.remove).toHaveBeenCalledWith(PAGE_ID);
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
);
expect(msg).toMatchObject({
type: 'version.saved',
kind: 'manual',
alreadySaved: false,
});
});
it('agent save derives kind=agent from the signed actor', async () => {
const document = ydocFor(doc('AGENT VERSION'));
pageRepo.findById.mockResolvedValue(pageMatchingDoc(document));
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
await emitSave(document, 'agent');
expect(pageHistoryRepo.saveHistory.mock.calls.at(-1)[1]).toEqual(
expect.objectContaining({ kind: 'agent' }),
);
});
it('promote-not-dup: latest snapshot is an autosave with identical content → upgrades in place', async () => {
const document = ydocFor(doc('SAME'));
const page = pageMatchingDoc(document);
pageRepo.findById.mockResolvedValue(page);
pageHistoryRepo.findPageLastHistory.mockResolvedValue({
id: 'auto-1',
content: page.content,
kind: 'idle',
});
await emitSave(document, 'user');
// No heavy new content row — the existing autosave is promoted to manual.
expect(pageHistoryRepo.updateHistoryKind).toHaveBeenCalledWith(
'auto-1',
'manual',
expect.anything(),
);
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
);
expect(msg).toMatchObject({ historyId: 'auto-1', alreadySaved: false });
});
it('no-op when the latest snapshot is already a manual version of this content', async () => {
const document = ydocFor(doc('ALREADY SAVED'));
const page = pageMatchingDoc(document);
pageRepo.findById.mockResolvedValue(page);
pageHistoryRepo.findPageLastHistory.mockResolvedValue({
id: 'ver-1',
content: page.content,
kind: 'manual',
});
await emitSave(document, 'user');
expect(pageHistoryRepo.updateHistoryKind).not.toHaveBeenCalled();
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
const msg = JSON.parse(
(document as any).broadcastStateless.mock.calls.at(-1)[0],
);
expect(msg).toMatchObject({ alreadySaved: true, kind: 'manual' });
});
it('a read-only connection cannot save a version', async () => {
const document = ydocFor(doc('READER'));
pageRepo.findById.mockResolvedValue(pageMatchingDoc(document));
await ext.onStateless({
connection: {
readOnly: true,
context: { user: { id: USER_ID }, actor: 'user' },
} as any,
documentName: `page.${PAGE_ID}`,
document: document as any,
payload: JSON.stringify({ type: 'save-version' }),
} as any);
expect(pageHistoryRepo.saveHistory).not.toHaveBeenCalled();
expect(pageHistoryRepo.updateHistoryKind).not.toHaveBeenCalled();
});
});
});
@@ -36,9 +36,11 @@ import {
import { Page } from '@docmost/db/types/entity.types';
import { CollabHistoryService } from '../services/collab-history.service';
import {
HISTORY_FAST_INTERVAL,
HISTORY_FAST_THRESHOLD,
HISTORY_INTERVAL,
IDLE_INTERVAL_AGENT,
IDLE_INTERVAL_USER,
IDLE_MAX_WAIT_AGENT,
IDLE_MAX_WAIT_USER,
PageHistoryKind,
} from '../constants';
import { TransclusionService } from '../../core/page/transclusion/transclusion.service';
import { observeCollabStore } from '../../integrations/metrics/metrics.registry';
@@ -51,6 +53,16 @@ import { observeCollabStore } from '../../integrations/metrics/metrics.registry'
*/
export const INTENTIONAL_CLEAR_MESSAGE_TYPE = 'intentional-clear';
/**
* #370 — wire format of the client→server "save a version" signal. Sent by the
* human (Cmd+S / Save button) and by the agent's explicit save tool over the
* SAME stateless channel. The intentionality tier ('manual' vs 'agent') is
* derived SERVER-SIDE from the signed connection actor, never from this
* payload, so a version's type is unforgeable. The document is taken from the
* connection (not the payload), so the signal cannot be aimed at another page.
*/
export const SAVE_VERSION_MESSAGE_TYPE = 'save-version';
/**
* #251 — how long an intentional-clear signal stays "pending" before it is
* ignored. The signal is set on the clearing keystroke but consumed by the
@@ -87,35 +99,39 @@ export function resolveSource(
}
/**
* Compute the BullMQ job id + delay for a page-history snapshot job. Pure so
* the data-loss-sensitive timing arithmetic is unit-testable; `now` is injected
* (caller passes `Date.now()`) for determinism.
* #370 — compute the BullMQ job id + delay for a page's trailing idle-flush
* autosnapshot. Pure so the timing is unit-testable.
*
* - Agent edits: delay 0 and a source-keyed job id `${page.id}-agent`. The
* delay MUST stay 0 — the worker re-reads the page row at run time, so any
* delay risks reading content a later human edit has already overwritten
* (mis-tagged snapshot). 0 minimizes that window. The `-agent` suffix keeps
* the job from coalescing with the bare-page.id human job.
* - Human edits: age-based debounce so rapid human edits coalesce into one
* snapshot; job id is the bare `page.id`.
*
* BullMQ forbids ':' in custom job ids (Redis key separator), so '-' is used;
* page.id is a UUID, so `${page.id}-agent` cannot collide with a human job.
* Both humans and the agent now share ONE idle pipeline (the agent's old
* `delay=0` fast path is gone — intentional agent points arrive via the
* explicit save-version signal instead). The job id is the bare `page.id`, so a
* page has at most one pending idle job; the caller removes-and-re-adds it on
* every store to keep it debounced to the trailing edge of an edit burst. The
* window differs by source only: the agent flushes sooner than a human.
*/
export function computeHistoryJob(
page: Pick<Page, 'id' | 'createdAt'>,
page: Pick<Page, 'id'>,
source: string,
now: number,
// Epoch ms of the FIRST edit in the current burst (when the pending idle job
// was first armed). Used to enforce the max-wait ceiling so a continuous
// editing session cannot re-arm the trailing timer forever. `now` is injectable
// for tests; both default to a live clock / no ceiling when omitted.
burstStart?: number,
now: number = Date.now(),
): { jobId: string; delay: number } {
const isAgent = source === 'agent';
const pageAge = now - new Date(page.createdAt).getTime();
const delay = isAgent
? 0
: pageAge < HISTORY_FAST_THRESHOLD
? HISTORY_FAST_INTERVAL
: HISTORY_INTERVAL;
const jobId = isAgent ? `${page.id}-agent` : page.id;
return { jobId, delay };
const interval = isAgent ? IDLE_INTERVAL_AGENT : IDLE_INTERVAL_USER;
const maxWait = isAgent ? IDLE_MAX_WAIT_AGENT : IDLE_MAX_WAIT_USER;
let delay = interval;
if (burstStart !== undefined) {
// Time already elapsed since the burst's first edit; the snapshot must fire
// no later than `maxWait` after that, so shrink the trailing delay to the
// remaining budget (never negative, so BullMQ fires it promptly).
const remaining = burstStart + maxWait - now;
delay = Math.max(0, Math.min(interval, remaining));
}
return { jobId: page.id, delay };
}
@Injectable()
@@ -127,6 +143,11 @@ export class PersistenceExtension implements Extension {
// coalescing window" per document and OR it across all edits in the window,
// so the snapshot is marked 'agent' regardless of who wrote last.
private agentTouched: Map<string, boolean> = new Map();
// #370 — epoch ms of the FIRST edit in the current idle-flush burst, per page.
// Set when the pending idle job is first armed (empty entry), read to enforce
// the max-wait ceiling in computeHistoryJob, and cleared when the idle job is
// consumed/cancelled so the next burst starts a fresh window.
private idleBurstStart: Map<string, number> = new Map();
// #251 — per-document "intentional clear pending" flags. Keyed by
// documentName, value = expiry timestamp (ms). Set by onStateless when the
// client reports a deliberate clear; consumed once by the next
@@ -326,20 +347,19 @@ export class PersistenceExtension implements Extension {
//this.logger.debug('Contributors error:' + err?.['message']);
}
// Approach A — boundary snapshot before the agent's first edit.
// When this store is the agent's and the page's currently persisted
// state was authored by a human, pin that human state as its own
// history version BEFORE the agent overwrites it. `page` still holds
// the OLD content/provenance here, so saveHistory(page) captures the
// pre-agent state tagged 'user'. The agent's new content is
// snapshotted later by the debounced PAGE_HISTORY job ('agent'). Skip
// if the prior state is already agent-authored (boundary already
// pinned on the user->agent transition), if the page is effectively
// empty, or if the latest existing snapshot already equals this human
// state (avoid duplicates).
// #370 — boundary snapshot on ANY source transition. When the store
// flips the page's provenance (user↔agent↔git), pin the OUTGOING
// state as its own history version BEFORE the incoming source
// overwrites it. `page` still holds the OLD content/provenance here,
// so saveHistory(page) captures the pre-transition state tagged with
// its own source, kind='boundary'. The incoming content is snapshotted
// later by the debounced idle job. Skip if the page is effectively
// empty or if the latest existing snapshot already equals this state
// (the shared isDeepStrictEqual gate — avoids duplicates). Generalizing
// beyond the old user→agent special-case also covers git-sync for free.
if (
lastUpdatedSource === 'agent' &&
page.lastUpdatedSource !== 'agent'
page.lastUpdatedSource &&
page.lastUpdatedSource !== lastUpdatedSource
) {
// pageHistory.pageId is uuid-typed; use page.id (never the doc-name
// slugId) so a `page.<slugId>` doc cannot throw 22P02 here (#260).
@@ -347,15 +367,13 @@ export class PersistenceExtension implements Extension {
page.id,
{ includeContent: true, trx },
);
const humanBaselineMissing =
const baselineMissing =
!lastHistory ||
!isDeepStrictEqual(lastHistory.content, page.content);
if (
!isEmptyParagraphDoc(page.content as any) &&
humanBaselineMissing
) {
if (!isEmptyParagraphDoc(page.content as any) && baselineMissing) {
await this.pageHistoryRepo.saveHistory(page, {
contributorIds: page.contributorIds ?? undefined,
kind: 'boundary',
trx,
});
}
@@ -480,6 +498,14 @@ export class PersistenceExtension implements Extension {
return; // unrelated / malformed stateless message
}
// #370 — explicit "save a version" (human Cmd+S / agent save tool). Edit
// rights are already enforced by the readOnly reject above (a reader can't
// create a version), exactly as intentional-clear requires.
if (message?.type === SAVE_VERSION_MESSAGE_TYPE) {
await this.handleSaveVersion(data);
return;
}
if (message?.type !== INTENTIONAL_CLEAR_MESSAGE_TYPE) return;
this.intentionalClear.set(
@@ -488,6 +514,117 @@ export class PersistenceExtension implements Extension {
);
}
/**
* #370 — persist an intentional version from the live in-memory ydoc.
*
* One stateless path serves BOTH the human and the agent; the tier is derived
* SERVER-SIDE from the signed connection actor ('agent' → 'agent', anything
* else → 'manual'), so the version type cannot be spoofed by the client. We
* take the fresh ydoc from the collab process memory and run it through the
* EXISTING store path first (so pages.content/ydoc reflect the exact content
* being versioned — a REST endpoint would race the up-to-10s-stale page row),
* then snapshot it into page_history with the intentional kind.
*
* Promote-not-dup: if the latest history row already holds this exact content
* and it is an autosave (idle/boundary/legacy-null), upgrade its kind in place
* instead of duplicating a heavy content row; if it is already 'manual', it is
* a no-op (the client shows an "already saved" toast). Otherwise a fresh
* version row is written, popping the aggregated contributors from Redis.
*/
private async handleSaveVersion(data: onStatelessPayload): Promise<void> {
const { connection, document, documentName } = data;
const context = connection?.context;
const pageId = getPageId(documentName);
// Unforgeable: 'agent' only for a signed agent connection, else 'manual'.
const kind: PageHistoryKind =
context?.actor === 'agent' ? 'agent' : 'manual';
// Flush the live ydoc through the normal store path so the page row + ydoc
// hold exactly what we are about to version (also fires the idle enqueue we
// supersede below, plus any source-transition boundary). onStoreDocument
// only needs document/documentName/context.
await this.onStoreDocument({
document,
documentName,
context,
} as onStoreDocumentPayload);
let result:
| { historyId: string; kind: PageHistoryKind; alreadySaved: boolean }
| undefined;
await executeTx(this.db, async (trx) => {
const page = await this.pageRepo.findById(pageId, {
withLock: true,
includeContent: true,
trx,
});
if (!page) return;
// Never version an effectively-empty page (mirrors the processor's
// first-history guard); there is nothing intentional to pin.
if (isEmptyParagraphDoc(page.content as any)) return;
const lastHistory = await this.pageHistoryRepo.findPageLastHistory(
page.id,
{ includeContent: true, trx },
);
if (
lastHistory &&
isDeepStrictEqual(lastHistory.content, page.content)
) {
// Content is already snapshotted. Promote-not-dup.
if (lastHistory.kind === 'manual') {
result = {
historyId: lastHistory.id,
kind: 'manual',
alreadySaved: true,
};
return;
}
await this.pageHistoryRepo.updateHistoryKind(
lastHistory.id,
kind,
trx,
);
result = { historyId: lastHistory.id, kind, alreadySaved: false };
return;
}
// Fresh version row. Pop the contributors aggregated since the last
// snapshot (SPOP); restore them if the write fails so they aren't lost.
const contributorIds = await this.collabHistory.popContributors(page.id);
try {
const saved = await this.pageHistoryRepo.saveHistory(page, {
contributorIds,
kind,
trx,
});
result = { historyId: saved.id, kind, alreadySaved: false };
} catch (err) {
await this.collabHistory.addContributors(page.id, contributorIds);
throw err;
}
});
// Housekeeping: this explicit version supersedes the page's pending idle
// autosnapshot, so cancel it (delayed job → remove() just deletes it) and
// end the current idle burst so the next edit starts a fresh max-wait window.
await this.historyQueue.remove(pageId).catch(() => undefined);
this.idleBurstStart.delete(pageId);
if (result) {
document.broadcastStateless(
JSON.stringify({
type: 'version.saved',
historyId: result.historyId,
kind: result.kind,
alreadySaved: result.alreadySaved,
}),
);
}
}
async onChange(data: onChangePayload) {
const documentName = data.documentName;
const userId = data.context?.user?.id;
@@ -545,17 +682,39 @@ export class PersistenceExtension implements Extension {
page: Page,
lastUpdatedSource: string,
): Promise<void> {
// Job id + delay arithmetic lives in the pure `computeHistoryJob` (see its
// doc comment for the agent-delay-0 / age-based-debounce invariants).
// #370 — trailing idle debounce with a max-wait ceiling. One pending idle
// job per page (jobId = page.id); on every store we remove the pending
// delayed job and re-add it, so the snapshot lands `delay` after edits go
// quiet rather than once per store (precedent: workspace.service.ts).
// remove() on a delayed job simply deletes it (0 if absent, no throw); if the
// job is already ACTIVE and the remove is a no-op, the add still de-dups and
// the processor's isDeepStrictEqual gate collapses the duplicate content.
//
// The FIRST arm of a burst records `burstStart`; computeHistoryJob shrinks
// the delay to the remaining max-wait budget from that point, so a continuous
// session cannot re-arm the trailing timer forever and starve the snapshot.
// A burst marker older than the (larger, USER) max-wait means the previous
// idle job has already fired — start a fresh window instead of firing
// immediately on the next edit.
const now = Date.now();
let burstStart = this.idleBurstStart.get(page.id);
if (burstStart === undefined || now - burstStart >= IDLE_MAX_WAIT_USER) {
burstStart = now;
this.idleBurstStart.set(page.id, burstStart);
}
const { jobId, delay } = computeHistoryJob(
page,
lastUpdatedSource,
Date.now(),
burstStart,
now,
);
await this.historyQueue.remove(jobId).catch(() => undefined);
await this.historyQueue.add(
QueueJob.PAGE_HISTORY,
{ pageId: page.id } as IPageHistoryJob,
{ pageId: page.id, kind: 'idle' } as IPageHistoryJob,
{ jobId, delay },
);
}
@@ -134,7 +134,7 @@ describe('HistoryProcessor.process', () => {
);
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledWith(
expect.objectContaining({ id: PAGE_ID }),
{ contributorIds: ['u1', 'u2'] },
{ contributorIds: ['u1', 'u2'], kind: 'idle' },
);
expect(generalQueue.add).toHaveBeenCalledWith(
QueueJob.PAGE_BACKLINKS,
@@ -78,7 +78,11 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
page.workspaceId,
);
await this.pageHistoryRepo.saveHistory(page, { contributorIds });
// #370 — every job on this queue is a trailing idle-flush autosnapshot.
await this.pageHistoryRepo.saveHistory(page, {
contributorIds,
kind: job.data.kind ?? 'idle',
});
this.logger.debug(`History created for page: ${pageId}`);
} catch (err) {
await this.collabHistory.addContributors(pageId, contributorIds);
@@ -0,0 +1,27 @@
import { type Kysely } from 'kysely';
/**
* #370 — page-versioning intentionality tier on a history snapshot.
*
* Adds `page_history.kind`, the three-tier "how intentional was this snapshot"
* marker that lets versions (intentional points) be told apart from autosaves:
* - 'manual' — a human explicitly saved a version (Cmd+S / Save button)
* - 'agent' — the AI agent explicitly saved a version
* - 'idle' — trailing idle-flush autosnapshot (safety net)
* - 'boundary' — autosnapshot pinned on a source transition (user↔agent↔git)
*
* Nullable with NO default (mirrors last_updated_source in the agent-provenance
* migration): legacy rows predate the marker and read back as `null`, which the
* client renders as a plain autosave. Stored as a short varchar to stay
* forward-compatible without an enum migration.
*/
export async function up(db: Kysely<any>): Promise<void> {
await db.schema
.alterTable('page_history')
.addColumn('kind', 'varchar(20)', (col) => col)
.execute();
}
export async function down(db: Kysely<any>): Promise<void> {
await db.schema.alterTable('page_history').dropColumn('kind').execute();
}
@@ -13,6 +13,7 @@ import { jsonArrayFrom, jsonObjectFrom } from 'kysely/helpers/postgres';
import { ExpressionBuilder, sql } from 'kysely';
import { DB } from '@docmost/db/types/db';
import { resolveAgentProvenance } from '../agent-provenance';
import { PageHistoryKind } from '../../../collaboration/constants';
/**
* Role-resolution subquery for a page-history row's bound AI chat (#300). Joins
@@ -46,6 +47,9 @@ export class PageHistoryRepo {
'lastUpdatedById',
'lastUpdatedSource',
'lastUpdatedAiChatId',
// #370 — intentionality tier ('manual' | 'agent' | 'idle' | 'boundary');
// null on legacy rows (= autosave). Selected so callers can read/promote it.
'kind',
'contributorIds',
'spaceId',
'workspaceId',
@@ -85,9 +89,15 @@ export class PageHistoryRepo {
async saveHistory(
page: Page,
opts?: { contributorIds?: string[]; trx?: KyselyTransaction },
): Promise<void> {
await this.insertPageHistory(
opts?: {
contributorIds?: string[];
// #370 — intentionality tier for this snapshot. Omitted → null (legacy
// autosave semantics). Callers derive it server-side, never from a client.
kind?: PageHistoryKind;
trx?: KyselyTransaction;
},
): Promise<PageHistory> {
return await this.insertPageHistory(
{
pageId: page.id,
slugId: page.slugId,
@@ -99,6 +109,7 @@ export class PageHistoryRepo {
// Copy the provenance marker off the page row, as for lastUpdatedById.
lastUpdatedSource: page.lastUpdatedSource,
lastUpdatedAiChatId: page.lastUpdatedAiChatId,
kind: opts?.kind ?? null,
contributorIds: opts?.contributorIds,
spaceId: page.spaceId,
workspaceId: page.workspaceId,
@@ -107,6 +118,25 @@ export class PageHistoryRepo {
);
}
/**
* #370 — promote an existing snapshot's intentionality tier in place. Used by
* the manual-save "promote-not-dup" path: when the latest history row already
* holds the exact content being versioned, we upgrade its `kind` instead of
* duplicating a heavy content row.
*/
async updateHistoryKind(
pageHistoryId: string,
kind: PageHistoryKind,
trx?: KyselyTransaction,
): Promise<void> {
const db = dbOrTx(this.db, trx);
await db
.updateTable('pageHistory')
.set({ kind })
.where('id', '=', pageHistoryId)
.execute();
}
async findPageHistoryByPageId(pageId: string, pagination: PaginationOptions) {
const query = this.db
.selectFrom('pageHistory')
+1
View File
@@ -280,6 +280,7 @@ export interface PageHistory {
createdAt: Generated<Timestamp>;
icon: string | null;
id: Generated<string>;
kind: string | null;
lastUpdatedAiChatId: string | null;
lastUpdatedById: string | null;
lastUpdatedSource: string | null;
@@ -20,6 +20,10 @@ export interface IStripeSeatsSyncJob {
export interface IPageHistoryJob {
pageId: string;
// #370 — intentionality tier the worker stamps on the snapshot. All jobs on
// this queue are trailing idle-flush autosnapshots, so this is 'idle' (absent
// → treated as 'idle' by the processor).
kind?: 'idle';
}
/**