Merge remote-tracking branch 'gitea/develop' into feat/492-incremental-render
This commit is contained in:
@@ -251,6 +251,16 @@ MCP_DOCMOST_PASSWORD=
|
||||
# Default 120000 (2 min).
|
||||
# AI_MCP_CALL_TIMEOUT_MS=120000
|
||||
|
||||
# Kill-switch for the agent API-key feature (#501). Default ON when unset — a
|
||||
# deploy that never sets it must NOT silently kill every agent. STRICT parse:
|
||||
# only the literals `true` / `false` are accepted; a typo like `=0`/`=off`/`=False`
|
||||
# FAILS AT BOOT by design (never silently read as "enabled"), so the switch is
|
||||
# guaranteed to actually flip when an operator flips it during an incident. When
|
||||
# set to `false`: all api-key auth is DENIED (every api-key token is rejected) and
|
||||
# the api-key management endpoints return 404. The resolved state is logged at boot
|
||||
# (`API keys: ENABLED/DISABLED (API_KEYS_ENABLED=...)`) so it is verifiable per deploy.
|
||||
# API_KEYS_ENABLED=true
|
||||
|
||||
# Max JSON/urlencoded request body size (bytes). Fastify's 1 MiB default is too
|
||||
# small for a long AI-chat research turn: the client resends the FULL message
|
||||
# history (every tool call + search result) on each turn, so a deep conversation's
|
||||
|
||||
@@ -226,6 +226,13 @@ jobs:
|
||||
- name: Build mcp
|
||||
run: pnpm --filter @docmost/mcp build
|
||||
|
||||
# apps/server imports @docmost/token-estimate at runtime (history-budget.ts,
|
||||
# #490); its dist/ is gitignored and `test:e2e` type-checks + runs the code,
|
||||
# so build it here or tsc fails with TS2307 Cannot find module
|
||||
# '@docmost/token-estimate' (mirrors the editor-ext / mcp build steps above).
|
||||
- name: Build token-estimate
|
||||
run: pnpm --filter @docmost/token-estimate build
|
||||
|
||||
- name: Run migrations
|
||||
run: pnpm --filter ./apps/server migration:latest
|
||||
|
||||
|
||||
@@ -159,6 +159,14 @@ jobs:
|
||||
- name: Build prosemirror-markdown
|
||||
run: pnpm --filter @docmost/prosemirror-markdown build
|
||||
|
||||
# @docmost/token-estimate is a shared workspace package the client vitest
|
||||
# suite resolves via its dist build (main: ./dist/index.js); dist/ is
|
||||
# gitignored and `pnpm -r test` does NOT honour nx `dependsOn: ^build`, so
|
||||
# build it before the recursive test run or the client suite fails with
|
||||
# "Failed to resolve import '@docmost/token-estimate'" (#490).
|
||||
- name: Build token-estimate
|
||||
run: pnpm --filter @docmost/token-estimate build
|
||||
|
||||
- name: Run unit tests
|
||||
run: pnpm -r test
|
||||
|
||||
|
||||
@@ -135,6 +135,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
new resync path re-reads the live anchor so the suggestion applies against the
|
||||
current text, and orphaned anchors (whose marked run was deleted) are
|
||||
reconciled rather than left blocking. (#496)
|
||||
- **Save intentional page versions.** Press `Cmd/Ctrl+S` (or use the page menu)
|
||||
to save a named version of a page. The history panel now distinguishes
|
||||
intentional versions (a "Saved" / "Agent version" badge) from automatic
|
||||
snapshots, dims autosaves, and offers an "Only versions" filter. Automatic
|
||||
snapshots switched from a fixed interval to a trailing idle-flush with a
|
||||
max-wait ceiling, and a boundary snapshot is pinned whenever the editing source
|
||||
changes (e.g. a person's edits followed by the AI agent). (#370)
|
||||
|
||||
- **Place several images side by side in a row.** A new "Inline (side by
|
||||
side)" alignment mode in the image bubble menu renders consecutive inline
|
||||
@@ -385,6 +392,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
`@docmost/token-estimate` package) so they can never diverge. Deferred-tool
|
||||
activation is also cached in the chat metadata to avoid re-resolving it each
|
||||
turn. (#490)
|
||||
- **Cyrillic (and any non-ASCII) draw.io labels no longer turn into mojibake
|
||||
when a diagram is opened in the draw.io editor.** Agent-created diagrams
|
||||
(`drawioCreate`) and Confluence-imported diagrams stored their model in the
|
||||
SVG's `content=` attribute as base64; the draw.io editor decodes that via
|
||||
Latin-1 `atob` (no UTF-8 step), so every non-ASCII char (e.g. `Старт-бит`,
|
||||
`ё`, `—`) split into garbage and the editor's autosave then persisted the
|
||||
corrupted model, breaking the page preview too. Both write paths
|
||||
(`buildDrawioSvg`, the import service's `createDrawioSvg`) now write `content=`
|
||||
as XML-entity-escaped mxfile XML — draw.io's own native form, decoded by the
|
||||
DOM as UTF-8 — so labels open intact. The decoder reads both the new
|
||||
entity-encoded form and the old base64 form, so existing diagrams still open.
|
||||
*Healing pre-fix diagrams:* only a diagram that still holds its original
|
||||
(correct-UTF-8) base64 — i.e. one not yet opened/autosaved in the draw.io
|
||||
editor — can be repaired in place by `drawioGet` → `drawioUpdate` with the
|
||||
same XML (rewrites the attachment in the new form); no migration script is
|
||||
needed. A diagram that was already opened in the editor persisted the
|
||||
mojibake at rest, so `drawioGet` reads the already-corrupted text and
|
||||
`drawioUpdate` faithfully rewrites it — that text is lost and is not
|
||||
recoverable by a rewrite. (#507)
|
||||
- **A chat with one malformed message part no longer 500s on every turn, and a
|
||||
failed send no longer duplicates the user's message.** Incoming client parts
|
||||
are now whitelisted to `text` (a forged tool-result part can no longer reach
|
||||
|
||||
@@ -59,6 +59,14 @@ COPY --from=builder /app/packages/mcp/data /app/packages/mcp/data
|
||||
COPY --from=builder /app/packages/prosemirror-markdown/build /app/packages/prosemirror-markdown/build
|
||||
COPY --from=builder /app/packages/prosemirror-markdown/package.json /app/packages/prosemirror-markdown/package.json
|
||||
|
||||
# apps/server imports @docmost/token-estimate (workspace:*) at runtime
|
||||
# (history-budget.ts, #490). tsc emits only dist/ and dist/ is gitignored, so the
|
||||
# prod install would resolve a broken workspace symlink and the server would die
|
||||
# with ERR_MODULE_NOT_FOUND on the first history-budget call. Ship the built
|
||||
# package + its manifest, mirroring prosemirror-markdown above.
|
||||
COPY --from=builder /app/packages/token-estimate/dist /app/packages/token-estimate/dist
|
||||
COPY --from=builder /app/packages/token-estimate/package.json /app/packages/token-estimate/package.json
|
||||
|
||||
# Copy root package files
|
||||
COPY --from=builder /app/package.json /app/package.json
|
||||
COPY --from=builder /app/pnpm*.yaml /app/
|
||||
|
||||
@@ -206,6 +206,137 @@ start the new migrations apply on top of your existing schema (`CREATE EXTENSION
|
||||
existing pages are indexed on their next edit. pgvector is still required for the migration to
|
||||
apply at all.
|
||||
|
||||
## Local embeddings server
|
||||
|
||||
The AI agent's semantic (RAG) search needs an **embeddings model**. Instead of paying a cloud
|
||||
provider (e.g. OpenAI `text-embedding-3-*`) to embed every page, you can run a small open-weights
|
||||
model yourself with Hugging Face
|
||||
[Text Embeddings Inference](https://github.com/huggingface/text-embeddings-inference) (TEI), which
|
||||
serves an OpenAI-compatible `/v1/embeddings` endpoint. `intfloat/multilingual-e5-small` is a good
|
||||
default: multilingual, 384-dim, and comfortable on CPU (~1–2 GB RAM, 1–2 vCPU). Point Gitmost at it
|
||||
under **Workspace settings → AI → Embeddings**.
|
||||
|
||||
### Option A — local (same Docker network as Gitmost)
|
||||
|
||||
Run TEI as a container on the network Gitmost is already on. The port is never published, so the
|
||||
endpoint stays internal and needs no authentication.
|
||||
|
||||
```yaml
|
||||
services:
|
||||
embeddings:
|
||||
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 # pin version; use a cuda-* tag for GPU
|
||||
container_name: embeddings
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- gitmost_net # same network Gitmost is on
|
||||
command:
|
||||
- "--model-id"
|
||||
- "intfloat/multilingual-e5-small"
|
||||
- "--auto-truncate" # clamp over-long inputs instead of returning 413
|
||||
volumes:
|
||||
- tei-models:/data # weights are downloaded once and cached here
|
||||
|
||||
networks:
|
||||
gitmost_net:
|
||||
external: true # the network Gitmost already uses
|
||||
|
||||
volumes:
|
||||
tei-models:
|
||||
```
|
||||
|
||||
Gitmost settings (**Workspace settings → AI → Embeddings**):
|
||||
|
||||
| Field | Value |
|
||||
|-------------------|-----------------------------------|
|
||||
| Model | `intfloat/multilingual-e5-small` |
|
||||
| Base URL | `http://embeddings:80/v1/` |
|
||||
| Embedding API key | — (leave empty) |
|
||||
|
||||
> `embeddings` is the container name — Gitmost resolves it over DNS inside the Docker network.
|
||||
> The port is not published, so the endpoint is reachable only by containers on that network and
|
||||
> no authorization is required.
|
||||
|
||||
### Option B — separate host (public via Traefik + Let's Encrypt)
|
||||
|
||||
This assumes the host already runs Traefik with an ACME resolver (the example below uses
|
||||
`letsEncrypt`, the `websecure` entrypoint and a shared `docker_main_net` network). Replace the
|
||||
domain / network / resolver with your own.
|
||||
|
||||
**DNS:** add an A record `embeddings.example.com` → the IP of your Traefik host (same
|
||||
challenge / port 80 as the rest of your sites).
|
||||
|
||||
```yaml
|
||||
services:
|
||||
embeddings:
|
||||
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 # pin version; cuda-* tag for GPU
|
||||
container_name: embeddings
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- docker_main_net # the network Traefik is attached to
|
||||
command:
|
||||
- "--model-id"
|
||||
- "intfloat/multilingual-e5-small"
|
||||
- "--auto-truncate"
|
||||
- "--api-key"
|
||||
- "sk-emb-REPLACE_WITH_YOUR_KEY"
|
||||
volumes:
|
||||
- tei-models:/data
|
||||
labels:
|
||||
traefik.enable: "true"
|
||||
traefik.http.routers.embeddings.rule: "Host(`embeddings.example.com`)"
|
||||
traefik.http.routers.embeddings.entrypoints: "websecure"
|
||||
traefik.http.routers.embeddings.tls: "true"
|
||||
traefik.http.routers.embeddings.tls.certresolver: "letsEncrypt"
|
||||
traefik.http.routers.embeddings.service: "embeddings"
|
||||
traefik.http.services.embeddings.loadbalancer.server.port: "80"
|
||||
# TEI enforces the Bearer key itself; Traefik only rate-limits to protect the CPU
|
||||
traefik.http.routers.embeddings.middlewares: "embeddings-rl"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.average: "20"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.burst: "40"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.period: "1s"
|
||||
|
||||
networks:
|
||||
docker_main_net:
|
||||
external: true
|
||||
|
||||
volumes:
|
||||
tei-models:
|
||||
```
|
||||
|
||||
Gitmost settings (**Workspace settings → AI → Embeddings**):
|
||||
|
||||
| Field | Value |
|
||||
|-------------------|---------------------------------------|
|
||||
| Model | `intfloat/multilingual-e5-small` |
|
||||
| Base URL | `https://embeddings.example.com/v1/` |
|
||||
| Embedding API key | your `sk-emb-…` |
|
||||
|
||||
Check it from outside:
|
||||
|
||||
```bash
|
||||
curl -s https://embeddings.example.com/v1/embeddings \
|
||||
-H "Authorization: Bearer sk-emb-REPLACE_WITH_YOUR_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model":"intfloat/multilingual-e5-small","input":"query: hello"}' \
|
||||
| python3 -c 'import sys,json;print("dims:",len(json.load(sys.stdin)["data"][0]["embedding"]))'
|
||||
# -> dims: 384
|
||||
```
|
||||
|
||||
### Embeddings server notes
|
||||
|
||||
- **Vector dimension is 384.** If this Gitmost was previously embedded with a different model
|
||||
(e.g. `text-embedding-3-large` = 3072-dim), the old pgvector rows won't match the new dimension —
|
||||
clear the existing embeddings / re-index before switching. Gitmost only compares vectors of the
|
||||
same dimension, so mixed-dimension rows are silently ignored rather than searched.
|
||||
- **First start downloads the weights** (hundreds of MB) from `huggingface.co` into the
|
||||
`tei-models` volume; every start after that reads from the volume.
|
||||
- **Pin the version.** Pin the image, and optionally the model: add `--revision <commit-sha>` to
|
||||
`command` (the sha is on the model's page on Hugging Face).
|
||||
- **Air-gapped / no egress:** seed the `tei-models` volume ahead of time and add
|
||||
`environment: [HF_HUB_OFFLINE=1]`.
|
||||
- **GPU:** use the cuda tag of the same release (e.g.
|
||||
`ghcr.io/huggingface/text-embeddings-inference:cuda-1.9`) and start the container with `gpus: all`.
|
||||
|
||||
## Features
|
||||
|
||||
- Real-time collaboration
|
||||
|
||||
+131
@@ -193,6 +193,137 @@ dump/restore, существующий каталог данных переис
|
||||
> неизменным и бэкапьте вместе с базой данных.
|
||||
|
||||
|
||||
## Локальный сервер эмбеддингов
|
||||
|
||||
Семантическому (RAG) поиску AI-агента нужна **модель эмбеддингов**. Вместо оплаты облачного
|
||||
провайдера (например, OpenAI `text-embedding-3-*`) за эмбеддинг каждой страницы можно запустить
|
||||
небольшую open-weights модель у себя через Hugging Face
|
||||
[Text Embeddings Inference](https://github.com/huggingface/text-embeddings-inference) (TEI) — он
|
||||
отдаёт OpenAI-совместимый эндпоинт `/v1/embeddings`. Хороший дефолт — `intfloat/multilingual-e5-small`:
|
||||
многоязычная, 384-мерная, комфортно работает на CPU (~1–2 ГБ RAM, 1–2 vCPU). Пропишите её в
|
||||
**Настройки воркспейса → AI → Эмбеддинги**.
|
||||
|
||||
### Вариант A — локально (та же Docker-сеть, что и Gitmost)
|
||||
|
||||
Запустите TEI контейнером в той же сети, где уже работает Gitmost. Порт наружу не публикуется,
|
||||
поэтому эндпоинт остаётся внутренним и не требует авторизации.
|
||||
|
||||
```yaml
|
||||
services:
|
||||
embeddings:
|
||||
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 # pin version; use a cuda-* tag for GPU
|
||||
container_name: embeddings
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- gitmost_net # same network Gitmost is on
|
||||
command:
|
||||
- "--model-id"
|
||||
- "intfloat/multilingual-e5-small"
|
||||
- "--auto-truncate" # clamp over-long inputs instead of returning 413
|
||||
volumes:
|
||||
- tei-models:/data # weights are downloaded once and cached here
|
||||
|
||||
networks:
|
||||
gitmost_net:
|
||||
external: true # the network Gitmost already uses
|
||||
|
||||
volumes:
|
||||
tei-models:
|
||||
```
|
||||
|
||||
Настройки Gitmost (**Настройки воркспейса → AI → Эмбеддинги**):
|
||||
|
||||
| Поле | Значение |
|
||||
|-------------------|-----------------------------------|
|
||||
| Model | `intfloat/multilingual-e5-small` |
|
||||
| Base URL | `http://embeddings:80/v1/` |
|
||||
| Embedding API key | — (оставить пустым) |
|
||||
|
||||
> `embeddings` — имя контейнера, Gitmost резолвит его по DNS внутри Docker-сети.
|
||||
> Наружу порт не публикуется, эндпоинт доступен только контейнерам этой сети, поэтому
|
||||
> авторизация не нужна.
|
||||
|
||||
### Вариант B — на отдельном хосте (наружу через Traefik + Let's Encrypt)
|
||||
|
||||
Предполагается, что на хосте уже есть Traefik с ACME-резолвером (в примере ниже — `letsEncrypt`,
|
||||
entrypoint `websecure`, общая сеть `docker_main_net`). Замените домен / сеть / резолвер на свои.
|
||||
|
||||
**DNS:** заведите A-запись `embeddings.example.com` → IP хоста с Traefik (тот же challenge / порт 80,
|
||||
что и у остальных сайтов).
|
||||
|
||||
```yaml
|
||||
services:
|
||||
embeddings:
|
||||
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 # pin version; cuda-* tag for GPU
|
||||
container_name: embeddings
|
||||
restart: unless-stopped
|
||||
networks:
|
||||
- docker_main_net # the network Traefik is attached to
|
||||
command:
|
||||
- "--model-id"
|
||||
- "intfloat/multilingual-e5-small"
|
||||
- "--auto-truncate"
|
||||
- "--api-key"
|
||||
- "sk-emb-REPLACE_WITH_YOUR_KEY"
|
||||
volumes:
|
||||
- tei-models:/data
|
||||
labels:
|
||||
traefik.enable: "true"
|
||||
traefik.http.routers.embeddings.rule: "Host(`embeddings.example.com`)"
|
||||
traefik.http.routers.embeddings.entrypoints: "websecure"
|
||||
traefik.http.routers.embeddings.tls: "true"
|
||||
traefik.http.routers.embeddings.tls.certresolver: "letsEncrypt"
|
||||
traefik.http.routers.embeddings.service: "embeddings"
|
||||
traefik.http.services.embeddings.loadbalancer.server.port: "80"
|
||||
# TEI enforces the Bearer key itself; Traefik only rate-limits to protect the CPU
|
||||
traefik.http.routers.embeddings.middlewares: "embeddings-rl"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.average: "20"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.burst: "40"
|
||||
traefik.http.middlewares.embeddings-rl.ratelimit.period: "1s"
|
||||
|
||||
networks:
|
||||
docker_main_net:
|
||||
external: true
|
||||
|
||||
volumes:
|
||||
tei-models:
|
||||
```
|
||||
|
||||
Настройки Gitmost (**Настройки воркспейса → AI → Эмбеддинги**):
|
||||
|
||||
| Поле | Значение |
|
||||
|-------------------|---------------------------------------|
|
||||
| Model | `intfloat/multilingual-e5-small` |
|
||||
| Base URL | `https://embeddings.example.com/v1/` |
|
||||
| Embedding API key | ваш `sk-emb-…` |
|
||||
|
||||
Проверка снаружи:
|
||||
|
||||
```bash
|
||||
curl -s https://embeddings.example.com/v1/embeddings \
|
||||
-H "Authorization: Bearer sk-emb-REPLACE_WITH_YOUR_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model":"intfloat/multilingual-e5-small","input":"query: hello"}' \
|
||||
| python3 -c 'import sys,json;print("dims:",len(json.load(sys.stdin)["data"][0]["embedding"]))'
|
||||
# -> dims: 384
|
||||
```
|
||||
|
||||
### Заметки про сервер эмбеддингов
|
||||
|
||||
- **Размерность вектора — 384.** Если раньше этот Gitmost эмбеддился другой моделью
|
||||
(например, `text-embedding-3-large` = 3072-dim), старые строки в pgvector не совпадут по
|
||||
размерности — очистите существующие эмбеддинги / переиндексируйте перед переключением. Gitmost
|
||||
сравнивает только вектора одной размерности, поэтому строки другой размерности не участвуют в
|
||||
поиске, а не ломают его.
|
||||
- **Первый старт тянет веса** (сотни МБ) с `huggingface.co` в том `tei-models`; дальше — из тома.
|
||||
- **Пин версии.** Пиньте образ, а при желании и модель: добавьте в `command` `--revision <commit-sha>`
|
||||
(sha берётся со страницы модели на Hugging Face).
|
||||
- **Без egress (air-gapped):** засейте том `tei-models` заранее и добавьте
|
||||
`environment: [HF_HUB_OFFLINE=1]`.
|
||||
- **GPU:** возьмите cuda-тег того же релиза (например,
|
||||
`ghcr.io/huggingface/text-embeddings-inference:cuda-1.9`) и запустите контейнер с `gpus: all`.
|
||||
|
||||
|
||||
## Возможности
|
||||
|
||||
- Совместная работа в реальном времени
|
||||
|
||||
@@ -1418,5 +1418,14 @@
|
||||
"The commented text changed since this suggestion was made; it was not applied.": "The commented text changed since this suggestion was made; it was not applied.",
|
||||
"Dismiss": "Dismiss",
|
||||
"Suggestion dismissed": "Suggestion dismissed",
|
||||
"Failed to dismiss suggestion": "Failed to dismiss suggestion"
|
||||
"Failed to dismiss suggestion": "Failed to dismiss suggestion",
|
||||
"Save version": "Save version",
|
||||
"Ctrl+S": "Ctrl+S",
|
||||
"Version saved": "Version saved",
|
||||
"Already saved as the latest version": "Already saved as the latest version",
|
||||
"Agent version": "Agent version",
|
||||
"Boundary": "Boundary",
|
||||
"Autosave": "Autosave",
|
||||
"Only versions": "Only versions",
|
||||
"No saved versions yet.": "No saved versions yet."
|
||||
}
|
||||
|
||||
@@ -1433,5 +1433,14 @@
|
||||
"The commented text changed since this suggestion was made; it was not applied.": "Прокомментированный текст изменился после создания предложения; оно не было применено.",
|
||||
"Dismiss": "Не применять",
|
||||
"Suggestion dismissed": "Предложение отклонено",
|
||||
"Failed to dismiss suggestion": "Не удалось отклонить предложение"
|
||||
"Failed to dismiss suggestion": "Не удалось отклонить предложение",
|
||||
"Save version": "Сохранить версию",
|
||||
"Ctrl+S": "Ctrl+S",
|
||||
"Version saved": "Версия сохранена",
|
||||
"Already saved as the latest version": "Уже сохранено как последняя версия",
|
||||
"Agent version": "Версия агента",
|
||||
"Boundary": "Граница",
|
||||
"Autosave": "Автосейв",
|
||||
"Only versions": "Только версии",
|
||||
"No saved versions yet.": "Пока нет сохранённых версий."
|
||||
}
|
||||
|
||||
@@ -3,11 +3,20 @@ import { atom } from "jotai";
|
||||
// import would drag the whole @tiptap/core engine into the eager graph of every
|
||||
// shell component that reads one of these atoms.
|
||||
import type { Editor } from "@tiptap/core";
|
||||
import type { HocuspocusProvider } from "@hocuspocus/provider";
|
||||
import { PageEditMode } from "@/features/user/types/user.types.ts";
|
||||
import type { DictationUnavailableReason } from "@/features/dictation/dictation-status";
|
||||
|
||||
export const pageEditorAtom = atom<Editor | null>(null);
|
||||
|
||||
// #370 — the active page's collab provider, published by the page editor so the
|
||||
// header menu can emit the "save-version" stateless signal (Cmd+S / button).
|
||||
// Null when the page is read-only / collab isn't connected. A typed initial
|
||||
// value (rather than an explicit generic) keeps jotai's overload resolution on
|
||||
// the writable PrimitiveAtom branch.
|
||||
const initialCollabProvider: HocuspocusProvider | null = null;
|
||||
export const collabProviderAtom = atom(initialCollabProvider);
|
||||
|
||||
export const titleEditorAtom = atom<Editor | null>(null);
|
||||
|
||||
export const readOnlyEditorAtom = atom<Editor | null>(null);
|
||||
|
||||
@@ -31,11 +31,18 @@ import { useAtom, useAtomValue, useSetAtom } from "jotai";
|
||||
import useCollaborationUrl from "@/features/editor/hooks/use-collaboration-url";
|
||||
import { currentUserAtom } from "@/features/user/atoms/current-user-atom";
|
||||
import {
|
||||
collabProviderAtom,
|
||||
currentPageEditModeAtom,
|
||||
dictationAvailabilityAtom,
|
||||
pageEditorAtom,
|
||||
yjsConnectionStatusAtom,
|
||||
} from "@/features/editor/atoms/editor-atoms";
|
||||
import { notifications } from "@mantine/notifications";
|
||||
import {
|
||||
VERSION_SAVED_MESSAGE_TYPE,
|
||||
type VersionSavedMessage,
|
||||
saveVersionPending,
|
||||
} from "@/features/page-history/version-messages";
|
||||
import { asideStateAtom } from "@/components/layouts/global/hooks/atoms/sidebar-atom";
|
||||
import {
|
||||
activeCommentIdAtom,
|
||||
@@ -124,6 +131,7 @@ export default function PageEditor({
|
||||
|
||||
const [currentUser] = useAtom(currentUserAtom);
|
||||
const [, setEditor] = useAtom(pageEditorAtom);
|
||||
const setCollabProvider = useSetAtom(collabProviderAtom);
|
||||
const [, setAsideState] = useAtom(asideStateAtom);
|
||||
const [, setActiveCommentId] = useAtom(activeCommentIdAtom);
|
||||
const [showCommentPopup, setShowCommentPopup] = useAtom(showCommentPopupAtom);
|
||||
@@ -181,6 +189,24 @@ export default function PageEditor({
|
||||
const onStatelessHandler = ({ payload }: onStatelessParameters) => {
|
||||
try {
|
||||
const message = JSON.parse(payload);
|
||||
// #370 — a version was saved somewhere; live-refresh the history panel
|
||||
// on every client. Only the client that pressed Save (tracked by the
|
||||
// module-level flag) shows the confirmation toast.
|
||||
if (message?.type === VERSION_SAVED_MESSAGE_TYPE) {
|
||||
const versionMsg = message as VersionSavedMessage;
|
||||
queryClient.invalidateQueries({
|
||||
queryKey: ["page-history-list"],
|
||||
});
|
||||
if (saveVersionPending.current) {
|
||||
saveVersionPending.current = false;
|
||||
notifications.show({
|
||||
message: versionMsg.alreadySaved
|
||||
? t("Already saved as the latest version")
|
||||
: t("Version saved"),
|
||||
});
|
||||
}
|
||||
return;
|
||||
}
|
||||
if (message?.type !== "page.updated" || !message.updatedAt) return;
|
||||
const pageData = queryClient.getQueryData<IPage>(["pages", slugId]);
|
||||
if (pageData) {
|
||||
@@ -238,12 +264,16 @@ export default function PageEditor({
|
||||
|
||||
local.on("synced", onLocalSyncedHandler);
|
||||
providersRef.current = { socket, local, remote };
|
||||
// #370 — publish the provider so the header menu can emit save-version.
|
||||
setCollabProvider(remote);
|
||||
setProvidersReady(true);
|
||||
} else {
|
||||
setCollabProvider(providersRef.current.remote);
|
||||
setProvidersReady(true);
|
||||
}
|
||||
// Only destroy on final unmount
|
||||
return () => {
|
||||
setCollabProvider(null);
|
||||
providersRef.current?.socket.destroy();
|
||||
providersRef.current?.remote.destroy();
|
||||
providersRef.current?.local.destroy();
|
||||
|
||||
@@ -1,4 +1,11 @@
|
||||
import { Text, Group, UnstyledButton, Avatar, Tooltip } from "@mantine/core";
|
||||
import {
|
||||
Text,
|
||||
Group,
|
||||
UnstyledButton,
|
||||
Avatar,
|
||||
Tooltip,
|
||||
Badge,
|
||||
} from "@mantine/core";
|
||||
import { CustomAvatar } from "@/components/ui/custom-avatar.tsx";
|
||||
import { AgentAvatarStack } from "@/components/ui/agent-avatar-stack.tsx";
|
||||
import { formattedDate } from "@/lib/time";
|
||||
@@ -7,36 +14,59 @@ import clsx from "clsx";
|
||||
import { IPageHistory } from "@/features/page-history/types/page.types";
|
||||
import { memo, useCallback } from "react";
|
||||
import { useSetAtom } from "jotai";
|
||||
import { useTranslation } from "react-i18next";
|
||||
import { historyAtoms } from "@/features/page-history/atoms/history-atoms.ts";
|
||||
|
||||
const MAX_VISIBLE_AVATARS = 5;
|
||||
|
||||
/**
|
||||
* #370 — map a snapshot's intentionality tier to its badge. `version: true`
|
||||
* marks the intentional points (manual / agent); autosaves (boundary / idle /
|
||||
* legacy null) are non-versions and get dimmed in the list.
|
||||
*/
|
||||
type HistoryKindMeta = { labelKey: string; color: string; version: boolean };
|
||||
export function historyKindMeta(kind?: string | null): HistoryKindMeta {
|
||||
switch (kind) {
|
||||
case "manual":
|
||||
return { labelKey: "Saved", color: "blue", version: true };
|
||||
case "agent":
|
||||
return { labelKey: "Agent version", color: "violet", version: true };
|
||||
case "boundary":
|
||||
return { labelKey: "Boundary", color: "gray", version: false };
|
||||
default: // "idle" | null | undefined (legacy autosave)
|
||||
return { labelKey: "Autosave", color: "gray", version: false };
|
||||
}
|
||||
}
|
||||
|
||||
interface HistoryItemProps {
|
||||
historyItem: IPageHistory;
|
||||
index: number;
|
||||
onSelect: (id: string, index: number) => void;
|
||||
onHover?: (id: string, index: number) => void;
|
||||
// The previous snapshot for diff/restore is resolved by id from the FULL list
|
||||
// in the parent (resolvePrevSnapshotId), so the item only needs to report its
|
||||
// own id — never a list index (which would be the filtered-view index).
|
||||
onSelect: (id: string) => void;
|
||||
onHover?: (id: string) => void;
|
||||
onHoverEnd?: () => void;
|
||||
isActive: boolean;
|
||||
}
|
||||
|
||||
const HistoryItem = memo(function HistoryItem({
|
||||
historyItem,
|
||||
index,
|
||||
onSelect,
|
||||
onHover,
|
||||
onHoverEnd,
|
||||
isActive,
|
||||
}: HistoryItemProps) {
|
||||
const setHistoryModalOpen = useSetAtom(historyAtoms);
|
||||
const { t } = useTranslation();
|
||||
const kindMeta = historyKindMeta(historyItem.kind);
|
||||
|
||||
const handleClick = useCallback(() => {
|
||||
onSelect(historyItem.id, index);
|
||||
}, [onSelect, historyItem.id, index]);
|
||||
onSelect(historyItem.id);
|
||||
}, [onSelect, historyItem.id]);
|
||||
|
||||
const handleMouseEnter = useCallback(() => {
|
||||
onHover?.(historyItem.id, index);
|
||||
}, [onHover, historyItem.id, index]);
|
||||
onHover?.(historyItem.id);
|
||||
}, [onHover, historyItem.id]);
|
||||
|
||||
const contributors = historyItem.contributors;
|
||||
const hasContributors = contributors && contributors.length > 0;
|
||||
@@ -49,8 +79,20 @@ const HistoryItem = memo(function HistoryItem({
|
||||
onMouseEnter={handleMouseEnter}
|
||||
onMouseLeave={onHoverEnd}
|
||||
className={clsx(classes.history, { [classes.active]: isActive })}
|
||||
// #370 — dim autosnapshots so intentional versions stand out.
|
||||
style={{ opacity: kindMeta.version ? 1 : 0.55 }}
|
||||
>
|
||||
<Text size="sm">{formattedDate(new Date(historyItem.createdAt))}</Text>
|
||||
<Group gap={6} wrap="nowrap" justify="space-between">
|
||||
<Text size="sm">{formattedDate(new Date(historyItem.createdAt))}</Text>
|
||||
<Badge
|
||||
size="xs"
|
||||
radius="sm"
|
||||
variant={kindMeta.version ? "filled" : "light"}
|
||||
color={kindMeta.color}
|
||||
>
|
||||
{t(kindMeta.labelKey)}
|
||||
</Badge>
|
||||
</Group>
|
||||
|
||||
<Group gap={6} wrap="nowrap" mt={4}>
|
||||
{hasContributors ? (
|
||||
|
||||
@@ -2,14 +2,16 @@ import {
|
||||
usePageHistoryListQuery,
|
||||
prefetchPageHistory,
|
||||
} from "@/features/page-history/queries/page-history-query";
|
||||
import HistoryItem from "@/features/page-history/components/history-item";
|
||||
import HistoryItem, {
|
||||
historyKindMeta,
|
||||
} from "@/features/page-history/components/history-item";
|
||||
import {
|
||||
activeHistoryIdAtom,
|
||||
activeHistoryPrevIdAtom,
|
||||
historyAtoms,
|
||||
} from "@/features/page-history/atoms/history-atoms";
|
||||
import { useAtom, useSetAtom } from "jotai";
|
||||
import { useCallback, useEffect, useMemo, useRef } from "react";
|
||||
import { useCallback, useEffect, useMemo, useRef, useState } from "react";
|
||||
import {
|
||||
Button,
|
||||
ScrollArea,
|
||||
@@ -17,9 +19,12 @@ import {
|
||||
Divider,
|
||||
Loader,
|
||||
Center,
|
||||
Switch,
|
||||
Text,
|
||||
} from "@mantine/core";
|
||||
import { useTranslation } from "react-i18next";
|
||||
import { useHistoryRestore } from "@/features/page-history/hooks";
|
||||
import { resolvePrevSnapshotId } from "@/features/page-history/utils/resolve-prev-snapshot";
|
||||
|
||||
const PREFETCH_DELAY_MS = 150;
|
||||
|
||||
@@ -47,6 +52,22 @@ function HistoryList({ pageId }: Props) {
|
||||
[pageHistoryData],
|
||||
);
|
||||
|
||||
// #370 — "only versions" filter: hide autosnapshots (idle/boundary/legacy
|
||||
// null), keep only intentional points (manual/agent). Filtering is over the
|
||||
// already-loaded pages; the diff/restore still targets the true previous
|
||||
// snapshot, so items carry their index within the FULL list.
|
||||
const [onlyVersions, setOnlyVersions] = useState(false);
|
||||
// Reuse historyKindMeta().version — the SAME predicate the badge (HistoryItem)
|
||||
// uses to mark intentional points — so the "Only versions" filter and the badge
|
||||
// can never drift apart when a future intentional kind is added.
|
||||
const visibleItems = useMemo(
|
||||
() =>
|
||||
onlyVersions
|
||||
? historyItems.filter((item) => historyKindMeta(item.kind).version)
|
||||
: historyItems,
|
||||
[historyItems, onlyVersions],
|
||||
);
|
||||
|
||||
const loadMoreRef = useRef<HTMLDivElement>(null);
|
||||
const prefetchTimeoutRef = useRef<ReturnType<typeof setTimeout> | null>(null);
|
||||
|
||||
@@ -60,11 +81,13 @@ function HistoryList({ pageId }: Props) {
|
||||
}, []);
|
||||
|
||||
const handleHover = useCallback(
|
||||
(historyId: string, index: number) => {
|
||||
(historyId: string) => {
|
||||
clearPrefetchTimeout();
|
||||
prefetchTimeoutRef.current = setTimeout(() => {
|
||||
prefetchPageHistory(historyId);
|
||||
const prevId = historyItems[index + 1]?.id;
|
||||
// The true previous snapshot in the FULL list (not the previous visible
|
||||
// one under the "only versions" filter).
|
||||
const prevId = resolvePrevSnapshotId(historyItems, historyId);
|
||||
if (prevId) {
|
||||
prefetchPageHistory(prevId);
|
||||
}
|
||||
@@ -78,9 +101,11 @@ function HistoryList({ pageId }: Props) {
|
||||
}, [clearPrefetchTimeout]);
|
||||
|
||||
const handleSelect = useCallback(
|
||||
(id: string, index: number) => {
|
||||
(id: string) => {
|
||||
setActiveHistoryId(id);
|
||||
setActiveHistoryPrevId(historyItems[index + 1]?.id ?? "");
|
||||
// Baseline = true previous snapshot in the FULL list, so the "only
|
||||
// versions" filter never diffs/restores against the wrong item.
|
||||
setActiveHistoryPrevId(resolvePrevSnapshotId(historyItems, id));
|
||||
},
|
||||
[historyItems, setActiveHistoryId, setActiveHistoryPrevId],
|
||||
);
|
||||
@@ -128,12 +153,27 @@ function HistoryList({ pageId }: Props) {
|
||||
|
||||
return (
|
||||
<div>
|
||||
<Group px="xs" py={6} justify="flex-end">
|
||||
<Switch
|
||||
size="xs"
|
||||
checked={onlyVersions}
|
||||
onChange={(e) => setOnlyVersions(e.currentTarget.checked)}
|
||||
label={t("Only versions")}
|
||||
/>
|
||||
</Group>
|
||||
|
||||
<ScrollArea h={620} w="100%" type="scroll" scrollbarSize={5}>
|
||||
{historyItems.map((historyItem, index) => (
|
||||
{onlyVersions && visibleItems.length === 0 && (
|
||||
<Center py="md">
|
||||
<Text size="sm" c="dimmed">
|
||||
{t("No saved versions yet.")}
|
||||
</Text>
|
||||
</Center>
|
||||
)}
|
||||
{visibleItems.map((historyItem) => (
|
||||
<HistoryItem
|
||||
key={historyItem.id}
|
||||
historyItem={historyItem}
|
||||
index={index}
|
||||
onSelect={handleSelect}
|
||||
onHover={handleHover}
|
||||
onHoverEnd={clearPrefetchTimeout}
|
||||
|
||||
@@ -24,6 +24,10 @@ export interface IPageHistory {
|
||||
updatedAt: string;
|
||||
lastUpdatedBy: IPageHistoryUser;
|
||||
contributors?: IPageHistoryUser[];
|
||||
// #370 — intentionality tier: 'manual'/'agent' are versions (intentional
|
||||
// points), 'idle'/'boundary' are autosnapshots; null/undefined = legacy
|
||||
// autosave. Derived server-side, drives the history badge + "versions" filter.
|
||||
kind?: "manual" | "agent" | "idle" | "boundary" | null;
|
||||
// Provenance markers copied off the page row when the snapshot was saved.
|
||||
// `'agent'` marks a version written by the AI agent; `lastUpdatedAiChatId`
|
||||
// (when present) deep-links to the chat that produced the edit.
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
import { describe, it, expect } from "vitest";
|
||||
import { resolvePrevSnapshotId } from "./resolve-prev-snapshot";
|
||||
|
||||
// #370 F4 — the risky client path: with the "only versions" filter active, diff
|
||||
// and restore must still baseline against the TRUE previous snapshot in the FULL
|
||||
// list, never the previous VISIBLE version (which would skip the autosnapshots
|
||||
// between two versions). These pin that the resolution is by FULL-list order.
|
||||
describe("resolvePrevSnapshotId", () => {
|
||||
// Newest-first, as the history list stores it: a version, then two autosaves,
|
||||
// then an older version.
|
||||
const full = [
|
||||
{ id: "v2", kind: "manual" },
|
||||
{ id: "a2", kind: "idle" },
|
||||
{ id: "a1", kind: "boundary" },
|
||||
{ id: "v1", kind: "manual" },
|
||||
{ id: "a0", kind: null },
|
||||
];
|
||||
|
||||
it("returns the immediate FULL-list successor, not the previous visible version", () => {
|
||||
// Selecting v2 while filtered to versions-only must baseline against a2 (the
|
||||
// real chronological predecessor), NOT v1 (the previous visible version).
|
||||
expect(resolvePrevSnapshotId(full, "v2")).toBe("a2");
|
||||
});
|
||||
|
||||
it("resolves an autosnapshot's predecessor by full-list order", () => {
|
||||
expect(resolvePrevSnapshotId(full, "a1")).toBe("v1");
|
||||
});
|
||||
|
||||
it("returns '' for the oldest item (no predecessor)", () => {
|
||||
expect(resolvePrevSnapshotId(full, "a0")).toBe("");
|
||||
});
|
||||
|
||||
it("returns '' for an id not in the list", () => {
|
||||
expect(resolvePrevSnapshotId(full, "missing")).toBe("");
|
||||
});
|
||||
|
||||
it("does not depend on a filtered subset — same result whatever is visible", () => {
|
||||
// The helper only ever sees the full list; a filtered view cannot change the
|
||||
// baseline it computes.
|
||||
expect(resolvePrevSnapshotId(full, "v1")).toBe("a0");
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* #370 — resolve the TRUE previous snapshot for a history item.
|
||||
*
|
||||
* The history panel can be filtered to "only versions" (manual/agent), but diff
|
||||
* and restore must always compare against the immediately-preceding snapshot in
|
||||
* the FULL, unfiltered list — NOT the previous VISIBLE item. Comparing against
|
||||
* the previous visible version would silently skip the autosnapshots between two
|
||||
* versions and diff/restore the wrong baseline.
|
||||
*
|
||||
* Given the full (newest-first) list and an item id, this returns the id of the
|
||||
* item right after it in the full list (its chronological predecessor), or "" if
|
||||
* it is the oldest / not found. Pure and list-order-preserving so it can be unit
|
||||
* tested without mounting the component.
|
||||
*/
|
||||
export function resolvePrevSnapshotId(
|
||||
fullItems: ReadonlyArray<{ id: string }>,
|
||||
id: string,
|
||||
): string {
|
||||
const index = fullItems.findIndex((item) => item.id === id);
|
||||
if (index === -1) return "";
|
||||
return fullItems[index + 1]?.id ?? "";
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
/**
|
||||
* #370 — page-version stateless wire formats. Kept in one place so the client
|
||||
* emitter (Save hotkey / button) and the client listener (page-editor) agree
|
||||
* with the server (PersistenceExtension) on the message shapes.
|
||||
*/
|
||||
|
||||
/** Client → server: "save a version now". The server derives the tier
|
||||
* (manual/agent) from the signed connection actor, never from this payload. */
|
||||
export const SAVE_VERSION_MESSAGE_TYPE = "save-version";
|
||||
|
||||
/** Server → all clients: a version was saved (or promoted / already existed). */
|
||||
export const VERSION_SAVED_MESSAGE_TYPE = "version.saved";
|
||||
|
||||
export interface VersionSavedMessage {
|
||||
type: typeof VERSION_SAVED_MESSAGE_TYPE;
|
||||
historyId: string;
|
||||
kind: "manual" | "agent";
|
||||
/** True when the latest snapshot was already a manual version (a no-op save). */
|
||||
alreadySaved: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Cross-component coordination flag so only the client that pressed Save shows
|
||||
* the confirmation toast, while every other client silently refreshes its
|
||||
* history panel on the broadcast. A module-level ref avoids stale-closure
|
||||
* pitfalls in the editor's long-lived stateless handler.
|
||||
*/
|
||||
export const saveVersionPending = { current: false };
|
||||
@@ -3,6 +3,7 @@ import {
|
||||
IconArrowRight,
|
||||
IconArrowsHorizontal,
|
||||
IconClockHour4,
|
||||
IconDeviceFloppy,
|
||||
IconDots,
|
||||
IconEye,
|
||||
IconEyeOff,
|
||||
@@ -17,7 +18,7 @@ import {
|
||||
IconTrash,
|
||||
IconWifiOff,
|
||||
} from "@tabler/icons-react";
|
||||
import React, { useEffect, useRef, useState } from "react";
|
||||
import React, { useCallback, useEffect, useRef, useState } from "react";
|
||||
import { useAsideTriggerProps } from "@/hooks/use-toggle-aside.tsx";
|
||||
import { useAtom, useAtomValue } from "jotai";
|
||||
import { historyAtoms } from "@/features/page-history/atoms/history-atoms.ts";
|
||||
@@ -39,9 +40,14 @@ import { Trans, useTranslation } from "react-i18next";
|
||||
import ExportModal from "@/components/common/export-modal";
|
||||
import { convertProseMirrorToMarkdown } from "@docmost/prosemirror-markdown/browser";
|
||||
import {
|
||||
collabProviderAtom,
|
||||
pageEditorAtom,
|
||||
yjsConnectionStatusAtom,
|
||||
} from "@/features/editor/atoms/editor-atoms.ts";
|
||||
import {
|
||||
SAVE_VERSION_MESSAGE_TYPE,
|
||||
saveVersionPending,
|
||||
} from "@/features/page-history/version-messages.ts";
|
||||
import { formattedDate } from "@/lib/time.ts";
|
||||
import { PageEditModeToggle } from "@/features/user/components/page-state-pref.tsx";
|
||||
import MovePageModal from "@/features/page/components/move-page-modal.tsx";
|
||||
@@ -72,9 +78,34 @@ export default function PageHeaderMenu({ readOnly }: PageHeaderMenuProps) {
|
||||
});
|
||||
const isDeleted = !!page?.deletedAt;
|
||||
const [workspace] = useAtom(workspaceAtom);
|
||||
const collabProvider = useAtomValue(collabProviderAtom);
|
||||
// Community public-sharing entry point (replaces the removed EE PageShareModal)
|
||||
const workspaceSharingDisabled = workspace?.settings?.sharing?.disabled === true;
|
||||
|
||||
// #370 — explicit "save a version" (Cmd+S / Save button). One path for the
|
||||
// human; the server derives the tier from the signed actor. Readers can't save
|
||||
// (the button is hidden and the collab connection is read-only server-side).
|
||||
const handleSaveVersion = useCallback(() => {
|
||||
if (readOnly || !collabProvider) return;
|
||||
// Flag this client as the initiator so only it shows the confirmation toast;
|
||||
// a safety timeout clears it if no broadcast comes back (e.g. offline).
|
||||
saveVersionPending.current = true;
|
||||
window.setTimeout(() => {
|
||||
saveVersionPending.current = false;
|
||||
}, 5000);
|
||||
collabProvider.sendStateless(
|
||||
JSON.stringify({ type: SAVE_VERSION_MESSAGE_TYPE }),
|
||||
);
|
||||
}, [readOnly, collabProvider]);
|
||||
|
||||
// mod+S must also block the browser's "Save page" dialog. `triggerOnContent-
|
||||
// Editable` + empty ignore-list so it fires while typing in the editor/title.
|
||||
useHotkeys(
|
||||
[["mod+S", handleSaveVersion, { preventDefault: true }]],
|
||||
[],
|
||||
true,
|
||||
);
|
||||
|
||||
useHotkeys(
|
||||
[
|
||||
[
|
||||
@@ -133,15 +164,16 @@ export default function PageHeaderMenu({ readOnly }: PageHeaderMenuProps) {
|
||||
</ActionIcon>
|
||||
</Tooltip>
|
||||
|
||||
<PageActionMenu readOnly={readOnly} />
|
||||
<PageActionMenu readOnly={readOnly} onSaveVersion={handleSaveVersion} />
|
||||
</>
|
||||
);
|
||||
}
|
||||
|
||||
interface PageActionMenuProps {
|
||||
readOnly?: boolean;
|
||||
onSaveVersion?: () => void;
|
||||
}
|
||||
function PageActionMenu({ readOnly }: PageActionMenuProps) {
|
||||
function PageActionMenu({ readOnly, onSaveVersion }: PageActionMenuProps) {
|
||||
const { t } = useTranslation();
|
||||
const [, setHistoryModalOpen] = useAtom(historyAtoms);
|
||||
const clipboard = useClipboard({ timeout: 500 });
|
||||
@@ -303,6 +335,20 @@ function PageActionMenu({ readOnly }: PageActionMenuProps) {
|
||||
</Group>
|
||||
</Menu.Item>
|
||||
|
||||
{!readOnly && (
|
||||
<Menu.Item
|
||||
leftSection={<IconDeviceFloppy size={16} />}
|
||||
onClick={onSaveVersion}
|
||||
rightSection={
|
||||
<Text size="xs" c="dimmed">
|
||||
{t("Ctrl+S")}
|
||||
</Text>
|
||||
}
|
||||
>
|
||||
{t("Save version")}
|
||||
</Menu.Item>
|
||||
)}
|
||||
|
||||
<Menu.Item
|
||||
leftSection={<IconHistory size={16} />}
|
||||
onClick={openHistoryModal}
|
||||
|
||||
@@ -281,10 +281,12 @@ const SpaceTree = forwardRef<SpaceTreeApi, SpaceTreeProps>(function SpaceTree(
|
||||
setOpenTreeNodes((prev) => ({ ...prev, [id]: isOpen }));
|
||||
if (isOpen) {
|
||||
const node = treeModel.find(data, id) as SpaceTreeNode | null;
|
||||
if (
|
||||
node?.hasChildren &&
|
||||
(!node.children || node.children.length === 0)
|
||||
) {
|
||||
// Same "unloaded branch" predicate the realtime insert paths use
|
||||
// (`isUnloadedBranch`) so the lazy-load gate and the realtime inserts
|
||||
// (`insertByPosition` / `placeByPosition`) can never disagree about what
|
||||
// counts as unloaded (#525). Note: local raw `insert` (DnD/create-page)
|
||||
// does not yet route through it — see #525 follow-up.
|
||||
if (treeModel.isUnloadedBranch(node)) {
|
||||
const fetched = await fetchAllAncestorChildren({
|
||||
pageId: id,
|
||||
spaceId: node.spaceId,
|
||||
|
||||
@@ -74,6 +74,48 @@ describe("treeModel.isDescendant", () => {
|
||||
});
|
||||
});
|
||||
|
||||
// #525: the single "is this branch unloaded?" predicate shared by the lazy-load
|
||||
// gate and the insert paths. Unloaded == server says hasChildren but none are
|
||||
// present locally (canonical form `children: []`, also `undefined`). A parent
|
||||
// without hasChildren is genuinely empty, not unloaded.
|
||||
describe("treeModel.isUnloadedBranch", () => {
|
||||
type PH = TreeNode<{ name: string; hasChildren?: boolean }>;
|
||||
it("true for hasChildren + empty array (canonical unloaded form)", () => {
|
||||
const n: PH = { id: "p", name: "P", hasChildren: true, children: [] };
|
||||
expect(treeModel.isUnloadedBranch(n)).toBe(true);
|
||||
});
|
||||
it("true for hasChildren + undefined children", () => {
|
||||
const n: PH = { id: "p", name: "P", hasChildren: true };
|
||||
expect(treeModel.isUnloadedBranch(n)).toBe(true);
|
||||
});
|
||||
it("false for hasChildren + already-loaded children", () => {
|
||||
const n: PH = {
|
||||
id: "p",
|
||||
name: "P",
|
||||
hasChildren: true,
|
||||
children: [{ id: "c", name: "C" }],
|
||||
};
|
||||
expect(treeModel.isUnloadedBranch(n)).toBe(false);
|
||||
});
|
||||
it("false for a genuinely-empty parent (no hasChildren)", () => {
|
||||
expect(
|
||||
treeModel.isUnloadedBranch({
|
||||
id: "p",
|
||||
name: "P",
|
||||
hasChildren: false,
|
||||
children: [],
|
||||
} as PH),
|
||||
).toBe(false);
|
||||
expect(
|
||||
treeModel.isUnloadedBranch({ id: "p", name: "P" } as PH),
|
||||
).toBe(false);
|
||||
});
|
||||
it("false for null/undefined", () => {
|
||||
expect(treeModel.isUnloadedBranch(null)).toBe(false);
|
||||
expect(treeModel.isUnloadedBranch(undefined)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("treeModel.visible", () => {
|
||||
it("returns only root nodes when no openIds", () => {
|
||||
const v = treeModel.visible(fixture, new Set());
|
||||
@@ -197,43 +239,64 @@ describe("treeModel.insertByPosition", () => {
|
||||
]);
|
||||
});
|
||||
|
||||
// #159 #1: inserting/moving a node under a parent whose children are NOT
|
||||
// loaded (`children === undefined`, e.g. a collapsed page) must NOT materialize
|
||||
// a partial `[node]` list — that would defeat the lazy-load gate and hide the
|
||||
// parent's other real children. The node is left to be lazy-loaded; only
|
||||
// `hasChildren` is flagged so the chevron appears.
|
||||
it("does NOT materialize a child under an UNLOADED parent (children undefined)", () => {
|
||||
type PH = TreeNode<{
|
||||
name: string;
|
||||
position?: string;
|
||||
hasChildren?: boolean;
|
||||
}>;
|
||||
type PH = TreeNode<{
|
||||
name: string;
|
||||
position?: string;
|
||||
hasChildren?: boolean;
|
||||
}>;
|
||||
|
||||
// #159 #1 / #525: inserting/moving a node under an UNLOADED parent must NOT
|
||||
// materialize a partial `[node]` list — that would defeat the lazy-load gate and
|
||||
// hide the parent's other real children. The canonical unloaded form here is
|
||||
// `children: []` + `hasChildren: true` (from `pageToTreeNode` /
|
||||
// `pruneCollapsedChildren`), which the pre-#525 `=== undefined` guard MISSED.
|
||||
// The node is left to be lazy-loaded; the chevron stays enabled.
|
||||
it("does NOT materialize a child under an UNLOADED parent (children: [], hasChildren: true)", () => {
|
||||
const tree: PH[] = [
|
||||
{ id: "p", name: "P", position: "a0", hasChildren: false }, // children: undefined
|
||||
{ id: "p", name: "P", position: "a0", hasChildren: true, children: [] },
|
||||
];
|
||||
const node: PH = { id: "x", name: "X", position: "a1" };
|
||||
const t = treeModel.insertByPosition(tree, "p", node);
|
||||
const parent = treeModel.find(t, "p");
|
||||
// The node was NOT inserted (children stay unloaded -> lazy-load fetches the
|
||||
// full set, including this node, on expand).
|
||||
expect(parent?.children).toBeUndefined();
|
||||
// full set, including this node, on expand). MUTATION: the pre-#525 predicate
|
||||
// `children === undefined` does not fire for `[]`, so it would insert `[x]`
|
||||
// here and reredden this expectation.
|
||||
expect(parent?.children).toEqual([]);
|
||||
expect(treeModel.find(t, "x")).toBeNull();
|
||||
// ...but the chevron is enabled so the user can expand to load it.
|
||||
// ...and the chevron stays enabled so the user can expand to load it.
|
||||
expect((parent as PH).hasChildren).toBe(true);
|
||||
});
|
||||
|
||||
it("DOES insert under a LOADED-but-empty parent (children: [])", () => {
|
||||
type PH = TreeNode<{
|
||||
name: string;
|
||||
position?: string;
|
||||
hasChildren?: boolean;
|
||||
}>;
|
||||
it("does NOT materialize a child under an UNLOADED parent (children undefined, hasChildren: true)", () => {
|
||||
const tree: PH[] = [
|
||||
{ id: "p", name: "P", position: "a0", hasChildren: true }, // children: undefined
|
||||
];
|
||||
const node: PH = { id: "x", name: "X", position: "a1" };
|
||||
const t = treeModel.insertByPosition(tree, "p", node);
|
||||
const parent = treeModel.find(t, "p");
|
||||
expect(parent?.children).toBeUndefined();
|
||||
expect(treeModel.find(t, "x")).toBeNull();
|
||||
expect((parent as PH).hasChildren).toBe(true);
|
||||
});
|
||||
|
||||
it("DOES insert under a genuinely-empty parent (children: [], hasChildren: false)", () => {
|
||||
const tree: PH[] = [
|
||||
{ id: "p", name: "P", position: "a0", hasChildren: false, children: [] },
|
||||
];
|
||||
const node: PH = { id: "x", name: "X", position: "a1" };
|
||||
const t = treeModel.insertByPosition(tree, "p", node);
|
||||
// A loaded (empty) child list is complete, so the node IS inserted.
|
||||
// No server children (`hasChildren: false`), so materializing the first child
|
||||
// is correct — nothing is hidden.
|
||||
expect(treeModel.find(t, "p")?.children?.map((n) => n.id)).toEqual(["x"]);
|
||||
});
|
||||
|
||||
it("DOES insert under a genuinely-empty parent (children undefined, hasChildren: false)", () => {
|
||||
const tree: PH[] = [
|
||||
{ id: "p", name: "P", position: "a0", hasChildren: false }, // children: undefined
|
||||
];
|
||||
const node: PH = { id: "x", name: "X", position: "a1" };
|
||||
const t = treeModel.insertByPosition(tree, "p", node);
|
||||
expect(treeModel.find(t, "p")?.children?.map((n) => n.id)).toEqual(["x"]);
|
||||
});
|
||||
|
||||
|
||||
@@ -43,6 +43,26 @@ export const treeModel = {
|
||||
};
|
||||
},
|
||||
|
||||
// A branch is "unloaded" when the server says it HAS children (`hasChildren`)
|
||||
// but none are present locally. The canonical unloaded form in this codebase
|
||||
// is `children: []` (produced by `pageToTreeNode` and by `pruneCollapsedChildren`
|
||||
// resetting collapsed branches), NOT `children: undefined` — so a predicate that
|
||||
// only checks `=== undefined` misses the real case and materializes a misleading
|
||||
// partial list (#525). This is the SINGLE source of truth for "should a
|
||||
// fetch/materialize be deferred?", shared by the lazy-load gate (`handleToggle`)
|
||||
// and the realtime insert paths (`insertByPosition` / `placeByPosition`), so they
|
||||
// can never drift apart again. (The local raw `insert` primitive and its DnD/
|
||||
// create-page callers do NOT yet route through this predicate — see #525
|
||||
// follow-up.) A parent WITHOUT `hasChildren` is genuinely empty
|
||||
// (no server children) — inserting its first child is correct, not deferred.
|
||||
isUnloadedBranch<T extends object>(
|
||||
node: TreeNode<T> | null | undefined,
|
||||
): boolean {
|
||||
if (!node) return false;
|
||||
const hasChildren = (node as { hasChildren?: boolean }).hasChildren === true;
|
||||
return hasChildren && (node.children == null || node.children.length === 0);
|
||||
},
|
||||
|
||||
isDescendant<T extends object>(
|
||||
tree: TreeNode<T>[],
|
||||
ancestorId: string,
|
||||
@@ -127,14 +147,15 @@ export const treeModel = {
|
||||
}
|
||||
const parent = treeModel.find(tree, parentId);
|
||||
// The parent is in the tree but its children have NOT been lazy-loaded yet
|
||||
// (`children === undefined`, distinct from a loaded-but-empty `[]`). Inserting
|
||||
// (`hasChildren` set + children absent/empty — see `isUnloadedBranch`; the
|
||||
// canonical unloaded form is `children: []`, NOT just `undefined`). Inserting
|
||||
// here would MATERIALIZE a misleading partial child list (`[node]`) that
|
||||
// defeats the lazy-load gate — which fetches only when children are
|
||||
// absent/empty — so the parent's OTHER real children would never load and the
|
||||
// moved/added node would be the only one shown (a silent data loss, #159 #1).
|
||||
// Instead, leave the children unloaded and just flag `hasChildren` so the
|
||||
// chevron appears; expanding fetches the FULL set (including this node).
|
||||
if (parent && parent.children === undefined) {
|
||||
if (parent && treeModel.isUnloadedBranch(parent)) {
|
||||
return treeModel.update(
|
||||
tree,
|
||||
parentId,
|
||||
|
||||
@@ -82,17 +82,19 @@ describe("applyMoveTreeNode", () => {
|
||||
]);
|
||||
});
|
||||
|
||||
it("does NOT create a partial child list when the destination is loaded-but-collapsed (children unloaded) — keeps it lazy-loadable (#159)", () => {
|
||||
// `dstCollapsed` is in the tree but its children were never lazy-loaded
|
||||
// (children === undefined). The OLD behavior inserted `src` as the ONLY
|
||||
// child ([src]), which defeated the lazy-load gate and HID the parent's
|
||||
// other real children. Now the move leaves children unloaded (so expanding
|
||||
// fetches the FULL set, including src) and just flags hasChildren.
|
||||
it("does NOT create a partial child list when the destination is loaded-but-collapsed (children unloaded) — keeps it lazy-loadable (#159 #525)", () => {
|
||||
// `dstCollapsed` is in the tree but its children were never lazy-loaded. The
|
||||
// CANONICAL unloaded form here is `hasChildren: true` + `children: []` (from
|
||||
// `pageToTreeNode` / `pruneCollapsedChildren`), NOT `children: undefined`.
|
||||
// The pre-#525 predicate (`children === undefined`) missed this form and
|
||||
// inserted `src` as the ONLY child ([src]), defeating the lazy-load gate and
|
||||
// HIDING the parent's other real children. Now the move leaves children
|
||||
// unloaded (so expanding fetches the FULL set, including src).
|
||||
const tree: SpaceTreeNode[] = [
|
||||
node("dstCollapsed", {
|
||||
position: "a0",
|
||||
hasChildren: false,
|
||||
children: undefined as unknown as SpaceTreeNode[],
|
||||
hasChildren: true,
|
||||
children: [],
|
||||
}),
|
||||
node("src", { position: "a9" }),
|
||||
];
|
||||
@@ -105,9 +107,10 @@ describe("applyMoveTreeNode", () => {
|
||||
pageData: {},
|
||||
});
|
||||
const dst = treeModel.find(next, "dstCollapsed");
|
||||
// Children stay unloaded -> the lazy-load gate fetches the FULL set (incl.
|
||||
// src) on expand, rather than showing a misleading partial [src] list.
|
||||
expect(dst?.children).toBeUndefined();
|
||||
// Children stay unloaded ([] not materialized to [src]) -> the lazy-load gate
|
||||
// fetches the FULL set (incl. src) on expand. MUTATION: the pre-#525
|
||||
// `=== undefined` predicate would insert [src] here and redden this.
|
||||
expect(dst?.children).toEqual([]);
|
||||
expect(dst?.hasChildren).toBe(true);
|
||||
// src moved away from its old root slot (it lives under dstCollapsed
|
||||
// server-side and reappears when the parent is expanded/loaded).
|
||||
|
||||
@@ -16,6 +16,7 @@ import { TransclusionService } from '../core/page/transclusion/transclusion.serv
|
||||
import { TransclusionModule } from '../core/page/transclusion/transclusion.module';
|
||||
import { StorageModule } from '../integrations/storage/storage.module';
|
||||
import { EnvironmentModule } from '../integrations/environment/environment.module';
|
||||
import { ApiKeyModule } from '../core/api-key/api-key.module';
|
||||
|
||||
@Module({
|
||||
providers: [
|
||||
@@ -31,6 +32,7 @@ import { EnvironmentModule } from '../integrations/environment/environment.modul
|
||||
exports: [CollaborationGateway],
|
||||
imports: [
|
||||
TokenModule,
|
||||
ApiKeyModule,
|
||||
WatcherModule,
|
||||
StorageModule.forRootAsync({
|
||||
imports: [EnvironmentModule],
|
||||
|
||||
@@ -1,10 +1,36 @@
|
||||
export const HISTORY_INTERVAL = 5 * 60 * 1000;
|
||||
export const HISTORY_FAST_INTERVAL = 60 * 1000;
|
||||
export const HISTORY_FAST_THRESHOLD = 5 * 60 * 1000;
|
||||
|
||||
// #348 — debounce window for the per-page RAG re-embed job. Repeated saves
|
||||
// within this window collapse to a single delayed job (coalesced by a stable
|
||||
// jobId), so active editing does not pile up expensive re-embeds (external API
|
||||
// + page_embeddings rewrite, concurrency 1). The worker reads the CURRENT page
|
||||
// state at run time, so the last content within the window wins.
|
||||
export const EMBED_DEBOUNCE_MS = 30 * 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
|
||||
|
||||
@@ -52,6 +52,7 @@ describe('AuthenticationExtension.onAuthenticate', () => {
|
||||
let pageRepo: { findById: jest.Mock };
|
||||
let spaceMemberRepo: { getUserSpaceRoles: jest.Mock };
|
||||
let pagePermissionRepo: { canUserEditPage: jest.Mock };
|
||||
let apiKeyService: { validate: jest.Mock };
|
||||
|
||||
// Build the hocuspocus onAuthenticate payload. connectionConfig.readOnly
|
||||
// starts false; the extension flips it to true on a read-only downgrade.
|
||||
@@ -79,12 +80,15 @@ describe('AuthenticationExtension.onAuthenticate', () => {
|
||||
}),
|
||||
};
|
||||
|
||||
apiKeyService = { validate: jest.fn().mockResolvedValue({ user: {}, workspace: {} }) };
|
||||
|
||||
ext = new AuthenticationExtension(
|
||||
tokenService as any,
|
||||
userRepo as any,
|
||||
pageRepo as any,
|
||||
spaceMemberRepo as any,
|
||||
pagePermissionRepo as any,
|
||||
apiKeyService as any,
|
||||
);
|
||||
// Silence the extension's logger (it warns/debugs on denial branches).
|
||||
jest.spyOn(ext['logger'], 'warn').mockImplementation(() => undefined);
|
||||
@@ -231,4 +235,73 @@ describe('AuthenticationExtension.onAuthenticate', () => {
|
||||
// No internal ai_chats row for an MCP/service-account collab edit → null.
|
||||
expect(ctx.aiChatId).toBeNull();
|
||||
});
|
||||
|
||||
// --- #501: api-key laundering guard (fail-closed discriminator) ----------
|
||||
describe('api-key laundering guard', () => {
|
||||
it('api_key principal → row-checks the key on connect (valid key proceeds)', async () => {
|
||||
tokenService.verifyJwt.mockResolvedValue(
|
||||
buildJwt({ principal: 'api_key', apiKeyId: 'key-1' }),
|
||||
);
|
||||
const data = buildData();
|
||||
await ext.onAuthenticate(data as any);
|
||||
|
||||
expect(apiKeyService.validate).toHaveBeenCalledTimes(1);
|
||||
expect(apiKeyService.validate).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ apiKeyId: 'key-1', type: JwtType.API_KEY }),
|
||||
);
|
||||
});
|
||||
|
||||
it('REVOKED api_key → Unauthorized on connect, BEFORE any page/user lookup', async () => {
|
||||
tokenService.verifyJwt.mockResolvedValue(
|
||||
buildJwt({ principal: 'api_key', apiKeyId: 'key-1' }),
|
||||
);
|
||||
// The shared validator denies a revoked key.
|
||||
apiKeyService.validate.mockRejectedValue(new UnauthorizedException());
|
||||
|
||||
await expect(ext.onAuthenticate(buildData() as any)).rejects.toThrow(
|
||||
UnauthorizedException,
|
||||
);
|
||||
// No new collab connection: the key check gates before page access.
|
||||
expect(pageRepo.findById).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('api_key principal missing apiKeyId → Unauthorized (malformed)', async () => {
|
||||
tokenService.verifyJwt.mockResolvedValue(buildJwt({ principal: 'api_key' }));
|
||||
await expect(ext.onAuthenticate(buildData() as any)).rejects.toThrow(
|
||||
UnauthorizedException,
|
||||
);
|
||||
expect(apiKeyService.validate).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('session principal → NO api-key check (session-backed, incl. internal agent)', async () => {
|
||||
tokenService.verifyJwt.mockResolvedValue(buildJwt({ principal: 'session' }));
|
||||
await ext.onAuthenticate(buildData() as any);
|
||||
expect(apiKeyService.validate).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('claimless token WITHIN the grace window → trusted (legacy pre-rollout)', async () => {
|
||||
// Default rolloutAt = now, so we are inside the grace window.
|
||||
tokenService.verifyJwt.mockResolvedValue(buildJwt()); // no principal
|
||||
await expect(ext.onAuthenticate(buildData() as any)).resolves.toBeDefined();
|
||||
expect(apiKeyService.validate).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('claimless token AFTER the grace window → Unauthorized (fail-closed)', async () => {
|
||||
// Move the rollout reference far into the past so the grace has elapsed.
|
||||
(ext as any).rolloutAt = Date.now() - 25 * 60 * 60 * 1000;
|
||||
tokenService.verifyJwt.mockResolvedValue(buildJwt()); // no principal
|
||||
await expect(ext.onAuthenticate(buildData() as any)).rejects.toThrow(
|
||||
UnauthorizedException,
|
||||
);
|
||||
});
|
||||
|
||||
it('infra error from the api-key row-check propagates (not masked)', async () => {
|
||||
tokenService.verifyJwt.mockResolvedValue(
|
||||
buildJwt({ principal: 'api_key', apiKeyId: 'key-1' }),
|
||||
);
|
||||
const boom = new Error('db down');
|
||||
apiKeyService.validate.mockRejectedValue(boom);
|
||||
await expect(ext.onAuthenticate(buildData() as any)).rejects.toBe(boom);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -14,20 +14,37 @@ import { findHighestUserSpaceRole } from '@docmost/db/repos/space/utils';
|
||||
import { SpaceRole } from '../../common/helpers/types/permission';
|
||||
import { isUserDisabled } from '../../common/helpers';
|
||||
import { getPageId } from '../collaboration.util';
|
||||
import { JwtCollabPayload, JwtType } from '../../core/auth/dto/jwt-payload';
|
||||
import {
|
||||
JwtApiKeyPayload,
|
||||
JwtCollabPayload,
|
||||
JwtType,
|
||||
} from '../../core/auth/dto/jwt-payload';
|
||||
import { resolveProvenance } from '../../common/decorators/auth-provenance.decorator';
|
||||
import { observeCollabAuth } from '../../integrations/metrics/metrics.registry';
|
||||
import { ApiKeyService } from '../../core/api-key/api-key.service';
|
||||
|
||||
// Max lifetime of a collab token (generateCollabToken uses expiresIn '24h'). Used
|
||||
// as the rollout grace window below: once this long has elapsed since this
|
||||
// process started serving the #501 code, every STILL-VALID collab token was
|
||||
// necessarily minted post-rollout and MUST carry the `principal` discriminator,
|
||||
// so a claimless one is a bug and is rejected (fail-closed) rather than trusted.
|
||||
const COLLAB_TOKEN_GRACE_MS = 24 * 60 * 60 * 1000;
|
||||
|
||||
@Injectable()
|
||||
export class AuthenticationExtension implements Extension {
|
||||
private readonly logger = new Logger(AuthenticationExtension.name);
|
||||
|
||||
// Reference instant for the claimless-rejection grace window. Overridable so a
|
||||
// unit test can drive the pre-/post-grace boundary without wall-clock waits.
|
||||
protected rolloutAt = Date.now();
|
||||
|
||||
constructor(
|
||||
private tokenService: TokenService,
|
||||
private userRepo: UserRepo,
|
||||
private pageRepo: PageRepo,
|
||||
private readonly spaceMemberRepo: SpaceMemberRepo,
|
||||
private readonly pagePermissionRepo: PagePermissionRepo,
|
||||
private readonly apiKeyService: ApiKeyService,
|
||||
) {}
|
||||
|
||||
async onAuthenticate(data: onAuthenticatePayload) {
|
||||
@@ -54,6 +71,36 @@ export class AuthenticationExtension implements Extension {
|
||||
throw new UnauthorizedException('Invalid collab token');
|
||||
}
|
||||
|
||||
// #501 — fail-closed api-key laundering guard. A collab token minted by an
|
||||
// api-key principal carries principal='api_key' + apiKeyId; re-check the key
|
||||
// on connect so a REVOKED key gets NO new collab connections (a collab token
|
||||
// outlives its 24h, but a revoked key can no longer open fresh ones). An
|
||||
// api-key token missing its apiKeyId is malformed → reject. A claimless token
|
||||
// (no recognized principal) is trusted only DURING the rollout grace window
|
||||
// (a legacy pre-rollout session token, which api keys could never mint);
|
||||
// once the grace has elapsed every valid token must carry the discriminator,
|
||||
// so a claimless one is a bug and is rejected (not silently trusted for 24h).
|
||||
const principal = jwtPayload.principal;
|
||||
if (principal === 'api_key') {
|
||||
if (!jwtPayload.apiKeyId) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
// Row-check via the SHARED validator: throws Unauthorized on a revoked/
|
||||
// expired/disabled key; an infra error propagates (not masked). No new
|
||||
// connection for a dead key.
|
||||
await this.apiKeyService.validate({
|
||||
sub: jwtPayload.sub,
|
||||
workspaceId: jwtPayload.workspaceId,
|
||||
apiKeyId: jwtPayload.apiKeyId,
|
||||
type: JwtType.API_KEY,
|
||||
} as JwtApiKeyPayload);
|
||||
} else if (principal !== 'session') {
|
||||
// Unrecognized/absent discriminator: reject once past the grace window.
|
||||
if (Date.now() - this.rolloutAt >= COLLAB_TOKEN_GRACE_MS) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
}
|
||||
|
||||
const userId = jwtPayload.sub;
|
||||
const workspaceId = jwtPayload.workspaceId;
|
||||
|
||||
|
||||
@@ -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('once a burst is armed, delay clamps to the remaining max-wait budget', () => {
|
||||
// 1 minute into the burst the USER interval (60m) far exceeds the remaining
|
||||
// max-wait budget (10m - 1m = 9m), so the delay is clamped DOWN to that
|
||||
// remaining budget — the full interval is NOT used once a ceiling applies.
|
||||
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
|
||||
@@ -479,4 +533,231 @@ 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[(document as any).broadcastStateless.mock.calls.length - 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[pageHistoryRepo.saveHistory.mock.calls.length - 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[(document as any).broadcastStateless.mock.calls.length - 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[(document as any).broadcastStateless.mock.calls.length - 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();
|
||||
});
|
||||
|
||||
// #370 F8-twin — a COMMIT abort (serialization/deadlock/conn-drop) rejects
|
||||
// OUTSIDE the tx callback, AFTER the destructive popContributors (SPOP) and
|
||||
// saveHistory ran but the INSERT rolled back. onStateless has no retry, so
|
||||
// the outer catch MUST re-add (SADD) the popped set or attribution is lost
|
||||
// irrecoverably. MUTATION: drop the outer catch → addContributors is never
|
||||
// called → this reddens.
|
||||
it('restores popped contributors when the commit aborts after the callback', async () => {
|
||||
const document = ydocFor(doc('VERSION ME'));
|
||||
pageRepo.findById.mockResolvedValue(pageMatchingDoc(document));
|
||||
// No matching snapshot → fresh version branch → pops contributors.
|
||||
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
|
||||
collabHistory.popContributors.mockResolvedValue(['u1', 'u2']);
|
||||
|
||||
// A db whose commit REJECTS after the callback body resolved: the SPOP and
|
||||
// saveHistory already ran, then the tx aborts. onStoreDocument's flush uses
|
||||
// the same db but its content matches (no-op branch) and its own retry loop
|
||||
// swallows the throw, so only the versioning tx exercises the restore.
|
||||
const commitFailingDb = {
|
||||
transaction: () => ({
|
||||
execute: async (fn: (trx: any) => Promise<any>) => {
|
||||
await fn(trxStub);
|
||||
throw new Error('commit aborted (serialization_failure)');
|
||||
},
|
||||
}),
|
||||
};
|
||||
const ext2 = new PersistenceExtension(
|
||||
pageRepo as any,
|
||||
pageHistoryRepo as any,
|
||||
commitFailingDb as any,
|
||||
aiQueue as any,
|
||||
historyQueue as any,
|
||||
notificationQueue as any,
|
||||
collabHistory as any,
|
||||
transclusionService as any,
|
||||
);
|
||||
jest.spyOn(ext2['logger'], 'debug').mockImplementation(() => undefined);
|
||||
jest.spyOn(ext2['logger'], 'warn').mockImplementation(() => undefined);
|
||||
jest.spyOn(ext2['logger'], 'error').mockImplementation(() => undefined);
|
||||
|
||||
await expect(
|
||||
ext2.onStateless({
|
||||
connection: {
|
||||
readOnly: false,
|
||||
context: { user: { id: USER_ID, name: 'Alice' }, actor: 'user' },
|
||||
} as any,
|
||||
documentName: `page.${PAGE_ID}`,
|
||||
document: document as any,
|
||||
payload: JSON.stringify({ type: 'save-version' }),
|
||||
} as any),
|
||||
).rejects.toThrow();
|
||||
|
||||
// Attribution preserved: the popped set is SADD-restored, keyed by the page
|
||||
// UUID it was popped under.
|
||||
expect(collabHistory.addContributors).toHaveBeenCalledWith(PAGE_ID, [
|
||||
'u1',
|
||||
'u2',
|
||||
]);
|
||||
});
|
||||
|
||||
// #370 #260 — for a `page.<slugId>` document the idle job is armed under the
|
||||
// page UUID (computeHistoryJob's jobId = page.id), so the supersede-remove
|
||||
// must target page.id, not the raw slugId doc-name id, or it silently misses.
|
||||
it('cancels the superseded idle job by the page UUID for a slugId doc', async () => {
|
||||
const SLUG = 'slug-1'; // persistedHumanPage.slugId
|
||||
const document = ydocFor(doc('VERSION ME'));
|
||||
pageRepo.findById.mockResolvedValue(pageMatchingDoc(document));
|
||||
pageHistoryRepo.findPageLastHistory.mockResolvedValue(null);
|
||||
|
||||
await ext.onStateless({
|
||||
connection: {
|
||||
readOnly: false,
|
||||
context: { user: { id: USER_ID, name: 'Alice' }, actor: 'user' },
|
||||
} as any,
|
||||
documentName: `page.${SLUG}`,
|
||||
document: document as any,
|
||||
payload: JSON.stringify({ type: 'save-version' }),
|
||||
} as any);
|
||||
|
||||
// remove() keyed by the UUID (the real jobId), never the slugId.
|
||||
expect(historyQueue.remove).toHaveBeenCalledWith(PAGE_ID);
|
||||
expect(historyQueue.remove).not.toHaveBeenCalledWith(SLUG);
|
||||
});
|
||||
});
|
||||
|
||||
// #370 — the in-memory idle-burst marker must be dropped on doc unload (like
|
||||
// its sibling per-document maps) or it grows unbounded for every page that was
|
||||
// edited but never manually saved. MUTATION: drop the afterUnloadDocument
|
||||
// delete → the entry survives → this reddens.
|
||||
describe('idleBurstStart housekeeping', () => {
|
||||
it('afterUnloadDocument clears the idle-burst marker armed by a store', async () => {
|
||||
const document = ydocFor(doc('EDIT'));
|
||||
pageRepo.findById.mockResolvedValue(persistedHumanPage('EDIT'));
|
||||
|
||||
await ext.onStoreDocument(buildData(document, 'user') as any);
|
||||
|
||||
const map = ext['idleBurstStart'] as Map<string, number>;
|
||||
// Keyed by documentName (buildData uses `page.${PAGE_ID}`).
|
||||
expect(map.has(`page.${PAGE_ID}`)).toBe(true);
|
||||
|
||||
await ext.afterUnloadDocument({
|
||||
documentName: `page.${PAGE_ID}`,
|
||||
} as any);
|
||||
|
||||
expect(map.has(`page.${PAGE_ID}`)).toBe(false);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -37,9 +37,11 @@ import { Page } from '@docmost/db/types/entity.types';
|
||||
import { CollabHistoryService } from '../services/collab-history.service';
|
||||
import {
|
||||
EMBED_DEBOUNCE_MS,
|
||||
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 {
|
||||
@@ -56,6 +58,16 @@ import { hasTransclusionFamilyNodes } from '../../core/page/transclusion/utils/t
|
||||
*/
|
||||
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
|
||||
@@ -92,35 +104,39 @@ 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()
|
||||
@@ -132,6 +148,28 @@ 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. Keyed by
|
||||
// documentName (like its sibling per-document maps above), NOT by page.id, so
|
||||
// it can be cleaned in afterUnloadDocument alongside `contributors` /
|
||||
// `agentTouched` / `intentionalClear` when the doc unloads — otherwise any page
|
||||
// that was edited but never manually saved (the common case) would keep its
|
||||
// entry forever and the Map would grow unbounded in this long-lived process.
|
||||
// Set when the pending idle job is first armed (empty entry), read to enforce
|
||||
// the max-wait ceiling in computeHistoryJob, and cleared on doc unload or when
|
||||
// a manual save cancels the idle job so the next burst starts a fresh window.
|
||||
//
|
||||
// Single-process assumption (like `contributors` / `agentTouched` above): this
|
||||
// lives only in THIS collab process's memory. A restart, or a page's ownership
|
||||
// moving to another node, loses the burst-start marker. Consequence: a burst
|
||||
// that spans the restart looks like a fresh burst to the surviving process, so
|
||||
// its max-wait ceiling is re-anchored to the first post-restart edit — a single
|
||||
// continuous session straddling a restart can therefore wait up to ~2× the cap
|
||||
// for its idle snapshot (once for the lost pre-restart window, once for the new
|
||||
// one). Bounded and benign (it only DELAYS a safety-net autosnapshot; manual
|
||||
// saves are unaffected and the next quiet period always flushes), but the
|
||||
// assumption and its consequence are recorded here so no one mistakes the
|
||||
// in-memory marker for a durable, cross-process guarantee.
|
||||
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
|
||||
@@ -363,20 +401,19 @@ 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).
|
||||
@@ -384,15 +421,13 @@ 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,
|
||||
});
|
||||
}
|
||||
@@ -522,7 +557,7 @@ export class PersistenceExtension implements Extension {
|
||||
{ jobId: `embed-${page.id}`, delay: EMBED_DEBOUNCE_MS },
|
||||
);
|
||||
|
||||
await this.enqueuePageHistory(page, lastUpdatedSource);
|
||||
await this.enqueuePageHistory(page, documentName, lastUpdatedSource);
|
||||
}
|
||||
|
||||
// #402 — report the serialized size for the store histogram's size_bucket.
|
||||
@@ -554,6 +589,14 @@ 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(
|
||||
@@ -562,6 +605,160 @@ 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;
|
||||
|
||||
// #370 F8-twin — the contributor set popped from Redis (destructive SPOP)
|
||||
// must be restored if the version row does not durably land. The inner
|
||||
// try/catch below only covers a throw INSIDE the callback; but executeTx
|
||||
// COMMITS after the callback, so a commit-abort (serialization/deadlock/
|
||||
// connection drop — the transient class the epic retries in the processor)
|
||||
// rejects OUTSIDE the callback, after saveHistory already ran and the SPOP
|
||||
// already happened, while the INSERT rolls back. onStateless does NOT retry,
|
||||
// so an unrestored pop is a one-shot irrecoverable attribution loss (the
|
||||
// processor got exactly this fix: poppedForRestore + an outer catch). We
|
||||
// track the popped set here (keyed by the page UUID it was popped by — never
|
||||
// the doc-name id, which may be a slugId, #260) and restore it in the outer
|
||||
// catch. addContributors is an idempotent Redis SADD, so a double-restore is
|
||||
// harmless. versionedPageId is also reused below to remove the superseded
|
||||
// idle job by its real jobId (page.id).
|
||||
let poppedForRestore: string[] = [];
|
||||
let versionedPageId: string | undefined;
|
||||
|
||||
try {
|
||||
await executeTx(this.db, async (trx) => {
|
||||
const page = await this.pageRepo.findById(pageId, {
|
||||
withLock: true,
|
||||
includeContent: true,
|
||||
trx,
|
||||
});
|
||||
if (!page) return;
|
||||
versionedPageId = page.id;
|
||||
// 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,
|
||||
);
|
||||
poppedForRestore = contributorIds;
|
||||
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);
|
||||
poppedForRestore = [];
|
||||
throw err;
|
||||
}
|
||||
});
|
||||
} catch (err) {
|
||||
// A throw here means the tx did NOT commit (callback threw, or the commit
|
||||
// itself failed and rolled back). If we popped contributors and the inner
|
||||
// catch did not already restore them, restore now so attribution is not
|
||||
// lost — onStateless has no retry to recover it. Restore by the page UUID
|
||||
// the pop was keyed under (versionedPageId is always set before the pop).
|
||||
if (poppedForRestore.length && versionedPageId) {
|
||||
await this.collabHistory.addContributors(
|
||||
versionedPageId,
|
||||
poppedForRestore,
|
||||
);
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
|
||||
// Housekeeping: this explicit version supersedes the page's pending idle
|
||||
// autosnapshot, so cancel it and end the current idle burst so the next edit
|
||||
// starts a fresh max-wait window. Remove the idle job by its REAL jobId
|
||||
// (page.id UUID — computeHistoryJob arms it under page.id), not the raw
|
||||
// doc-name id which may be a slugId for a `page.<slugId>` doc (#260), or the
|
||||
// remove silently misses. The burst marker is keyed by documentName (like its
|
||||
// sibling per-document maps), and is also cleaned in afterUnloadDocument.
|
||||
if (versionedPageId) {
|
||||
await this.historyQueue.remove(versionedPageId).catch(() => undefined);
|
||||
}
|
||||
this.idleBurstStart.delete(documentName);
|
||||
|
||||
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;
|
||||
@@ -586,6 +783,10 @@ export class PersistenceExtension implements Extension {
|
||||
this.contributors.delete(documentName);
|
||||
this.agentTouched.delete(documentName);
|
||||
this.intentionalClear.delete(documentName);
|
||||
// #370 — drop the idle-burst marker with the other per-document maps so it
|
||||
// cannot accumulate across the process lifetime for never-manually-saved
|
||||
// pages. The pending idle job (if any) is a self-expiring BullMQ delayed job.
|
||||
this.idleBurstStart.delete(documentName);
|
||||
}
|
||||
|
||||
private consumeContributors(documentName: string): string[] {
|
||||
@@ -617,19 +818,80 @@ export class PersistenceExtension implements Extension {
|
||||
|
||||
private async enqueuePageHistory(
|
||||
page: Page,
|
||||
documentName: string,
|
||||
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 THIS TIER's max-wait means the previous idle job
|
||||
// has already fired — start a fresh window instead of firing immediately on
|
||||
// the next edit. Must use the SAME source-specific max-wait computeHistoryJob
|
||||
// uses (agent 5m / user 10m): a hardcoded USER ceiling would leave an agent
|
||||
// burst's marker stale for 5..10m, forcing delay=0 on every store in that
|
||||
// window and writing one idle row per store — exactly the per-store bloat the
|
||||
// debounce exists to prevent, on the continuous-agent path.
|
||||
const maxWait =
|
||||
lastUpdatedSource === 'agent' ? IDLE_MAX_WAIT_AGENT : IDLE_MAX_WAIT_USER;
|
||||
const now = Date.now();
|
||||
// Keyed by documentName (see the map declaration) so afterUnloadDocument can
|
||||
// clean it; the queue jobId stays page.id (computeHistoryJob) as required.
|
||||
let burstStart = this.idleBurstStart.get(documentName);
|
||||
if (burstStart === undefined || now - burstStart >= maxWait) {
|
||||
burstStart = now;
|
||||
this.idleBurstStart.set(documentName, burstStart);
|
||||
}
|
||||
|
||||
const { jobId, delay } = computeHistoryJob(
|
||||
page,
|
||||
lastUpdatedSource,
|
||||
Date.now(),
|
||||
burstStart,
|
||||
now,
|
||||
);
|
||||
|
||||
// remove-then-add trailing-debounce idiom, and its ONE race. We delete the
|
||||
// pending delayed job and re-add it under the same jobId so the timer resets
|
||||
// to the trailing edge of the burst. The race is the small window between
|
||||
// these two awaits: if the delayed job's `delay` elapses in that gap it goes
|
||||
// ACTIVE, and then:
|
||||
// - remove() on an active/locked job is a no-op (BullMQ won't yank a job a
|
||||
// worker holds), and our `.catch(() => undefined)` swallows that too; and
|
||||
// - add() with a jobId that already exists (the now-active job's id) is
|
||||
// DROPPED by BullMQ — a duplicate add is a no-op.
|
||||
// So this store fails to re-arm the trailing job: the just-fired snapshot
|
||||
// captured content up to the moment it went active, and THIS edit is left
|
||||
// without a pending trailing job. It is bounded and self-healing — the NEXT
|
||||
// store re-arms a fresh delayed job (the id is free again once the active job
|
||||
// completes / removeOnComplete frees it), and the processor's
|
||||
// isDeepStrictEqual gate collapses any content-identical duplicate. The only
|
||||
// uncovered case is when the racing store was the LAST in the session: the
|
||||
// tail edits made after the job went active get NO trailing snapshot until
|
||||
// the next edit re-arms one. That is an acceptable safety-net gap (a manual
|
||||
// Save, a source-transition boundary, or simply the next edit all still cover
|
||||
// it), which is why the reviewer accepts documenting it here rather than
|
||||
// adding a post-add "did the add actually arm a job?" re-check.
|
||||
//
|
||||
// NOTE — do NOT "unify" this with the neighbouring embed-debounce idiom
|
||||
// (aiQueue.add of PAGE_CONTENT_UPDATED above): that one uses a STABLE jobId
|
||||
// and NO remove(), relying purely on BullMQ coalescing a repeated add under
|
||||
// the same id, because a re-embed only needs to eventually run once on the
|
||||
// latest content and re-anchoring its delay on every keystroke is undesirable.
|
||||
// THIS idiom deliberately removes-then-adds precisely to PUSH the delay back
|
||||
// to the trailing edge on every store (a true debounce), which coalescing
|
||||
// alone cannot do. Collapsing them would silently change the history cadence.
|
||||
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 },
|
||||
);
|
||||
}
|
||||
|
||||
@@ -66,6 +66,15 @@ describe('HistoryProcessor.process', () => {
|
||||
notificationQueue = { add: jest.fn().mockResolvedValue(undefined) };
|
||||
generalQueue = { add: jest.fn().mockResolvedValue(undefined) };
|
||||
|
||||
// #370 F3 — the processor now serializes its find+save under a page-row lock
|
||||
// via executeTx. A db whose transaction().execute(fn) runs fn with a trx stub
|
||||
// drives the real executeTx() helper without a database.
|
||||
const db = {
|
||||
transaction: () => ({
|
||||
execute: (fn: (trx: any) => Promise<any>) => fn({ __trx: true }),
|
||||
}),
|
||||
};
|
||||
|
||||
// WorkerHost's constructor reads `this.worker`; passing repos positionally
|
||||
// matches the constructor and avoids the Nest DI container.
|
||||
proc = new HistoryProcessor(
|
||||
@@ -73,6 +82,7 @@ describe('HistoryProcessor.process', () => {
|
||||
pageRepo as any,
|
||||
collabHistory as any,
|
||||
watcherService as any,
|
||||
db as any,
|
||||
notificationQueue as any,
|
||||
generalQueue as any,
|
||||
);
|
||||
@@ -126,15 +136,26 @@ describe('HistoryProcessor.process', () => {
|
||||
await proc.process(buildJob());
|
||||
|
||||
expect(collabHistory.popContributors).toHaveBeenCalledWith(PAGE_ID);
|
||||
// #370 F3/F9 — the snapshot decision runs under a page-row lock. Pin the lock
|
||||
// structurally so a refactor that drops withLock/trx (silently reintroducing
|
||||
// the TOCTOU double-insert) turns this red. The tx stub is { __trx: true }.
|
||||
expect(pageRepo.findById).toHaveBeenCalledWith(
|
||||
PAGE_ID,
|
||||
expect.objectContaining({ withLock: true, trx: { __trx: true } }),
|
||||
);
|
||||
// #370 F7 — addPageWatchers MUST receive the trx, or its FK-check runs on a
|
||||
// separate connection and self-deadlocks against our FOR UPDATE. Asserting
|
||||
// the trx arg here is exactly what would have caught that regression.
|
||||
expect(watcherService.addPageWatchers).toHaveBeenCalledWith(
|
||||
['u1', 'u2'],
|
||||
PAGE_ID,
|
||||
SPACE_ID,
|
||||
WORKSPACE_ID,
|
||||
{ __trx: true },
|
||||
);
|
||||
expect(pageHistoryRepo.saveHistory).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ id: PAGE_ID }),
|
||||
{ contributorIds: ['u1', 'u2'] },
|
||||
{ contributorIds: ['u1', 'u2'], kind: 'idle', trx: { __trx: true } },
|
||||
);
|
||||
expect(generalQueue.add).toHaveBeenCalledWith(
|
||||
QueueJob.PAGE_BACKLINKS,
|
||||
@@ -186,6 +207,48 @@ describe('HistoryProcessor.process', () => {
|
||||
]);
|
||||
});
|
||||
|
||||
it('COMMIT failure (throw outside the tx callback) → contributors RESTORED', async () => {
|
||||
// #370 F8 — a commit-time failure throws OUTSIDE the callback, so the inner
|
||||
// try/catch does not run; the outer catch must restore the popped set (else a
|
||||
// BullMQ retry writes an unattributed version). Use a db whose execute() runs
|
||||
// the callback THEN throws, simulating a commit abort.
|
||||
pageHistoryRepo.findPageLastHistory.mockResolvedValue({
|
||||
content: { type: 'doc', content: [] },
|
||||
});
|
||||
const commitFail = {
|
||||
transaction: () => ({
|
||||
execute: async (fn: (trx: any) => Promise<any>) => {
|
||||
await fn({ __trx: true }); // callback succeeds (saveHistory ok)
|
||||
throw new Error('commit aborted'); // ...but the COMMIT fails
|
||||
},
|
||||
}),
|
||||
};
|
||||
const procCommitFail = new HistoryProcessor(
|
||||
pageHistoryRepo as any,
|
||||
pageRepo as any,
|
||||
collabHistory as any,
|
||||
watcherService as any,
|
||||
commitFail as any,
|
||||
notificationQueue as any,
|
||||
generalQueue as any,
|
||||
);
|
||||
jest
|
||||
.spyOn(procCommitFail['logger'], 'error')
|
||||
.mockImplementation(() => undefined);
|
||||
|
||||
await expect(procCommitFail.process(buildJob())).rejects.toThrow(
|
||||
'commit aborted',
|
||||
);
|
||||
// The inner catch did NOT run (save succeeded), so only the outer catch can
|
||||
// restore — assert it did.
|
||||
expect(collabHistory.addContributors).toHaveBeenCalledWith(PAGE_ID, [
|
||||
'u1',
|
||||
'u2',
|
||||
]);
|
||||
// And the post-snapshot queue work must NOT have run (we rethrew).
|
||||
expect(generalQueue.add).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('backlinks + notification queue failures are swallowed (history still committed)', async () => {
|
||||
pageHistoryRepo.findPageLastHistory.mockResolvedValue({
|
||||
content: { type: 'doc', content: [] },
|
||||
|
||||
@@ -19,6 +19,9 @@ import { isDeepStrictEqual } from 'node:util';
|
||||
import { CollabHistoryService } from '../services/collab-history.service';
|
||||
import { WatcherService } from '../../core/watcher/watcher.service';
|
||||
import { isEmptyParagraphDoc } from '../collaboration.util';
|
||||
import { InjectKysely } from 'nestjs-kysely';
|
||||
import { KyselyDB } from '@docmost/db/types/kysely.types';
|
||||
import { executeTx } from '@docmost/db/utils';
|
||||
|
||||
@Processor(QueueName.HISTORY_QUEUE)
|
||||
export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
|
||||
@@ -29,6 +32,7 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
|
||||
private readonly pageRepo: PageRepo,
|
||||
private readonly collabHistory: CollabHistoryService,
|
||||
private readonly watcherService: WatcherService,
|
||||
@InjectKysely() private readonly db: KyselyDB,
|
||||
@InjectQueue(QueueName.NOTIFICATION_QUEUE) private notificationQueue: Queue,
|
||||
@InjectQueue(QueueName.GENERAL_QUEUE) private generalQueue: Queue,
|
||||
) {
|
||||
@@ -41,6 +45,9 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
|
||||
try {
|
||||
const { pageId } = job.data;
|
||||
|
||||
// Read the page WITHOUT a lock first, only to bail early on the two cheap
|
||||
// no-write cases (page gone / empty first snapshot) without opening a
|
||||
// transaction. The authoritative check-then-write happens locked below.
|
||||
const page = await this.pageRepo.findById(pageId, {
|
||||
includeContent: true,
|
||||
});
|
||||
@@ -51,40 +58,109 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
|
||||
return;
|
||||
}
|
||||
|
||||
const lastHistory = await this.pageHistoryRepo.findPageLastHistory(
|
||||
pageId,
|
||||
{ includeContent: true },
|
||||
);
|
||||
// #370 F3 — the snapshot decision (findPageLastHistory → saveHistory) must
|
||||
// be serialized against manual-save/boundary writers, which run under a
|
||||
// page-row lock in onStoreDocument. Without it, this processor and a
|
||||
// concurrent manual-save each read the same lastHistory (MVCC), both see
|
||||
// content != lastHistory, and both insert — producing two page_history rows
|
||||
// with IDENTICAL content (one 'idle', one 'manual'), defeating
|
||||
// promote-not-dup and the version-vs-autosave split. Taking the same
|
||||
// page-row lock makes the second writer observe the first's committed row so
|
||||
// the isDeepStrictEqual gate collapses the duplicate. Only the read+write
|
||||
// is transacted; the post-snapshot queue work stays outside.
|
||||
let contributorIds: string[] = [];
|
||||
let snapshotWritten = false;
|
||||
let lastHistoryContent: unknown;
|
||||
// #370 F8 — the contributor set popped from Redis (destructive SPOP) must be
|
||||
// restored if the snapshot does not durably land. The inner try/catch only
|
||||
// covers a throw INSIDE the callback; a COMMIT failure (connection drop,
|
||||
// serialization/deadlock abort on commit — the transient class the epic
|
||||
// already retries) throws OUTSIDE it, rolling the snapshot back while the
|
||||
// pop is already gone. We track the popped set here and restore it in the
|
||||
// outer catch so a BullMQ retry re-attributes the version. addContributors
|
||||
// is an idempotent Redis SADD, so a double-restore is harmless.
|
||||
let poppedForRestore: string[] = [];
|
||||
|
||||
if (!lastHistory && isEmptyParagraphDoc(page.content as any)) {
|
||||
this.logger.debug(
|
||||
`Skipping first history for page ${pageId}: empty content`,
|
||||
);
|
||||
await this.collabHistory.clearContributors(pageId);
|
||||
try {
|
||||
await executeTx(this.db, async (trx) => {
|
||||
const lockedPage = await this.pageRepo.findById(pageId, {
|
||||
includeContent: true,
|
||||
withLock: true,
|
||||
trx,
|
||||
});
|
||||
if (!lockedPage) return;
|
||||
|
||||
const lastHistory = await this.pageHistoryRepo.findPageLastHistory(
|
||||
pageId,
|
||||
{ includeContent: true, trx },
|
||||
);
|
||||
lastHistoryContent = lastHistory?.content;
|
||||
|
||||
if (!lastHistory && isEmptyParagraphDoc(lockedPage.content as any)) {
|
||||
this.logger.debug(
|
||||
`Skipping first history for page ${pageId}: empty content`,
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
if (
|
||||
lastHistory &&
|
||||
isDeepStrictEqual(lastHistory.content, lockedPage.content)
|
||||
) {
|
||||
return; // already snapshotted at this content — nothing to write
|
||||
}
|
||||
|
||||
contributorIds = await this.collabHistory.popContributors(pageId);
|
||||
poppedForRestore = contributorIds;
|
||||
try {
|
||||
// Pass `trx` so the watcher insert's FK check (FOR KEY SHARE on
|
||||
// pages[pageId]) runs on the SAME connection that already holds the
|
||||
// FOR UPDATE lock from findById — otherwise it takes the FK lock on a
|
||||
// separate pool connection and self-deadlocks against our own tx.
|
||||
await this.watcherService.addPageWatchers(
|
||||
contributorIds,
|
||||
pageId,
|
||||
lockedPage.spaceId,
|
||||
lockedPage.workspaceId,
|
||||
trx,
|
||||
);
|
||||
|
||||
// #370 — every job on this queue is a trailing idle-flush autosnapshot.
|
||||
await this.pageHistoryRepo.saveHistory(lockedPage, {
|
||||
contributorIds,
|
||||
kind: job.data.kind ?? 'idle',
|
||||
trx,
|
||||
});
|
||||
snapshotWritten = true;
|
||||
this.logger.debug(`History created for page: ${pageId}`);
|
||||
} catch (err) {
|
||||
await this.collabHistory.addContributors(pageId, contributorIds);
|
||||
poppedForRestore = [];
|
||||
throw err;
|
||||
}
|
||||
});
|
||||
} catch (err) {
|
||||
// A throw here means the tx did NOT commit (callback threw, or the commit
|
||||
// itself failed and rolled back). If we popped contributors and the inner
|
||||
// catch did not already restore them, restore now so the retry keeps
|
||||
// attribution. snapshotWritten is irrelevant: it is set before commit, so
|
||||
// it can be true even when the commit rolled the snapshot back.
|
||||
if (poppedForRestore.length) {
|
||||
await this.collabHistory.addContributors(pageId, poppedForRestore);
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
|
||||
// No snapshot written (page vanished / empty-first / unchanged content) →
|
||||
// clear the contributor set for the skip cases and stop.
|
||||
if (!snapshotWritten) {
|
||||
if (!lastHistoryContent && isEmptyParagraphDoc(page.content as any)) {
|
||||
await this.collabHistory.clearContributors(pageId);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
if (
|
||||
!lastHistory ||
|
||||
!isDeepStrictEqual(lastHistory.content, page.content)
|
||||
) {
|
||||
const contributorIds = await this.collabHistory.popContributors(pageId);
|
||||
|
||||
try {
|
||||
await this.watcherService.addPageWatchers(
|
||||
contributorIds,
|
||||
pageId,
|
||||
page.spaceId,
|
||||
page.workspaceId,
|
||||
);
|
||||
|
||||
await this.pageHistoryRepo.saveHistory(page, { contributorIds });
|
||||
this.logger.debug(`History created for page: ${pageId}`);
|
||||
} catch (err) {
|
||||
await this.collabHistory.addContributors(pageId, contributorIds);
|
||||
throw err;
|
||||
}
|
||||
|
||||
{
|
||||
const mentions = extractMentions(page.content);
|
||||
const pageMentions = extractPageMentions(mentions);
|
||||
const internalLinkSlugIds = extractInternalLinkSlugIds(page.content);
|
||||
@@ -102,7 +178,7 @@ export class HistoryProcessor extends WorkerHost implements OnModuleDestroy {
|
||||
);
|
||||
});
|
||||
|
||||
if (contributorIds.length > 0 && lastHistory?.content) {
|
||||
if (contributorIds.length > 0 && lastHistoryContent) {
|
||||
await this.notificationQueue
|
||||
.add(QueueJob.PAGE_UPDATED, {
|
||||
pageId,
|
||||
|
||||
@@ -190,10 +190,11 @@ export function stepBudgetWarning(stepNumber: number): string {
|
||||
//
|
||||
// `system` is the in-scope system prompt; we CONCATENATE so the original
|
||||
// persona/context is preserved — a bare `system` override would REPLACE the
|
||||
// whole system prompt for the step. `activatedTools` is PER-TURN mutable state
|
||||
// owned by the streaming loop (a closure Set grown by loadTools); it is passed
|
||||
// in (not module-global, not persisted) so this stays a pure function of its
|
||||
// arguments.
|
||||
// whole system prompt for the step. `activatedTools` is a closure Set grown by
|
||||
// loadTools and owned by the streaming loop; the caller seeds it from and
|
||||
// persists it to the chat's metadata across turns (#490), but this function only
|
||||
// READS the Set it is handed, so it stays a pure function of its arguments (not
|
||||
// module-global).
|
||||
//
|
||||
// NOTE: at AI SDK v7 the per-step `system` field is renamed to `instructions`.
|
||||
// On v6 (`^6.0.134`) `system` is the correct field — adjust when bumping.
|
||||
@@ -1417,10 +1418,11 @@ export class AiChatService implements OnModuleInit, OnModuleDestroy {
|
||||
const baseTools = { ...external.tools, ...docmostTools };
|
||||
|
||||
// Deferred tool loading state (#332), scoped to THIS streaming loop:
|
||||
// - `activatedTools` is per-TURN mutable state — a fresh closure Set created
|
||||
// per streamText call, NOT module-global and NOT persisted, so a new turn
|
||||
// starts cold. loadTools.execute adds to it; prepareAgentStep reads it to
|
||||
// widen `activeTools` on the NEXT step.
|
||||
// - `activatedTools` is a fresh closure Set per streamText call (not
|
||||
// module-global), SEEDED from the chat's persisted metadata.activatedTools
|
||||
// (#490, just below) so activation carries across turns. loadTools.execute
|
||||
// adds to it; prepareAgentStep reads it to widen `activeTools` on the NEXT
|
||||
// step; turn end persists it back.
|
||||
// - `validDeferredNames` = every tool that is NOT core (the in-app deferred
|
||||
// tools + ALL external MCP tools), computed from the ACTUAL toolset so an
|
||||
// external tool is loadable by its namespaced name. loadTools rejects any
|
||||
|
||||
@@ -0,0 +1,193 @@
|
||||
import { ForbiddenException, NotFoundException } from '@nestjs/common';
|
||||
import { ApiKeyController } from './api-key.controller';
|
||||
import {
|
||||
WorkspaceCaslAction,
|
||||
WorkspaceCaslSubject,
|
||||
} from '../casl/interfaces/workspace-ability.type';
|
||||
|
||||
/**
|
||||
* Authorization contract for the /api-keys management surface.
|
||||
*
|
||||
* - A token cannot manage tokens (an api_key PRINCIPAL is 403 on every method)
|
||||
* — GitHub-PAT semantics closing post-revocation laundering.
|
||||
* - admin (CASL Manage on API) sees/revokes all workspace keys; a member only
|
||||
* their own.
|
||||
* - kill-switch OFF -> the surface 404s (looks like the feature does not exist).
|
||||
*/
|
||||
|
||||
function makeController(over: any = {}) {
|
||||
const apiKeyService = {
|
||||
create: jest.fn().mockResolvedValue({
|
||||
token: 'tok',
|
||||
key: { id: 'k1', name: 'n', expiresAt: null, createdAt: new Date() },
|
||||
}),
|
||||
revoke: jest.fn().mockResolvedValue(undefined),
|
||||
...(over.apiKeyService ?? {}),
|
||||
};
|
||||
const apiKeyRepo = {
|
||||
findAllInWorkspace: jest.fn().mockResolvedValue([]),
|
||||
findByCreator: jest.fn().mockResolvedValue([]),
|
||||
findById: jest.fn(),
|
||||
...(over.apiKeyRepo ?? {}),
|
||||
};
|
||||
const workspaceAbility = {
|
||||
createForUser: jest.fn().mockReturnValue({
|
||||
can: (_a: any, _s: any) => over.canManage ?? false,
|
||||
}),
|
||||
...(over.workspaceAbility ?? {}),
|
||||
};
|
||||
const environmentService = {
|
||||
isApiKeysEnabled: jest.fn().mockReturnValue(over.enabled ?? true),
|
||||
...(over.environmentService ?? {}),
|
||||
};
|
||||
const auditService = { log: jest.fn() };
|
||||
const controller = new ApiKeyController(
|
||||
apiKeyService as any,
|
||||
apiKeyRepo as any,
|
||||
workspaceAbility as any,
|
||||
environmentService as any,
|
||||
auditService as any,
|
||||
);
|
||||
return {
|
||||
controller,
|
||||
apiKeyService,
|
||||
apiKeyRepo,
|
||||
workspaceAbility,
|
||||
environmentService,
|
||||
auditService,
|
||||
};
|
||||
}
|
||||
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
const workspace = { id: 'ws-1' } as any;
|
||||
const reqAccess = () => ({ raw: {}, ip: '1.2.3.4', socket: {} }) as any;
|
||||
const reqApiKey = () =>
|
||||
({ raw: { authType: 'api_key', apiKeyId: 'k-self' }, ip: '1.2.3.4', socket: {} }) as any;
|
||||
|
||||
describe('ApiKeyController — a token cannot manage tokens', () => {
|
||||
it('403 on create for an api_key principal', async () => {
|
||||
const { controller, apiKeyService } = makeController();
|
||||
await expect(
|
||||
controller.create({ name: 'x' } as any, user, reqApiKey()),
|
||||
).rejects.toBeInstanceOf(ForbiddenException);
|
||||
expect(apiKeyService.create).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('403 on list for an api_key principal', async () => {
|
||||
const { controller } = makeController();
|
||||
await expect(
|
||||
controller.list(user, workspace, reqApiKey()),
|
||||
).rejects.toBeInstanceOf(ForbiddenException);
|
||||
});
|
||||
|
||||
it('403 on revoke for an api_key principal', async () => {
|
||||
const { controller } = makeController();
|
||||
await expect(
|
||||
controller.revoke({ id: 'k1' } as any, user, workspace, reqApiKey()),
|
||||
).rejects.toBeInstanceOf(ForbiddenException);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ApiKeyController — kill-switch OFF → 404', () => {
|
||||
it('create/list/revoke all 404 when disabled', async () => {
|
||||
const { controller } = makeController({ enabled: false });
|
||||
await expect(
|
||||
controller.create({ name: 'x' } as any, user, reqAccess()),
|
||||
).rejects.toBeInstanceOf(NotFoundException);
|
||||
await expect(
|
||||
controller.list(user, workspace, reqAccess()),
|
||||
).rejects.toBeInstanceOf(NotFoundException);
|
||||
await expect(
|
||||
controller.revoke({ id: 'k1' } as any, user, workspace, reqAccess()),
|
||||
).rejects.toBeInstanceOf(NotFoundException);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ApiKeyController — list scoping', () => {
|
||||
it('admin (Manage on API) lists ALL workspace keys', async () => {
|
||||
const { controller, apiKeyRepo } = makeController({ canManage: true });
|
||||
await controller.list(user, workspace, reqAccess());
|
||||
expect(apiKeyRepo.findAllInWorkspace).toHaveBeenCalledWith('ws-1');
|
||||
expect(apiKeyRepo.findByCreator).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('member lists ONLY their own keys', async () => {
|
||||
const { controller, apiKeyRepo } = makeController({ canManage: false });
|
||||
await controller.list(user, workspace, reqAccess());
|
||||
expect(apiKeyRepo.findByCreator).toHaveBeenCalledWith('u-1', 'ws-1');
|
||||
expect(apiKeyRepo.findAllInWorkspace).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
describe('ApiKeyController — revoke scoping', () => {
|
||||
it("member cannot revoke another user's key (403)", async () => {
|
||||
const { controller, apiKeyRepo, apiKeyService } = makeController({
|
||||
canManage: false,
|
||||
});
|
||||
apiKeyRepo.findById.mockResolvedValue({
|
||||
id: 'k1',
|
||||
creatorId: 'someone-else',
|
||||
workspaceId: 'ws-1',
|
||||
});
|
||||
await expect(
|
||||
controller.revoke({ id: 'k1' } as any, user, workspace, reqAccess()),
|
||||
).rejects.toBeInstanceOf(ForbiddenException);
|
||||
expect(apiKeyService.revoke).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('member CAN revoke their own key', async () => {
|
||||
const { controller, apiKeyRepo, apiKeyService } = makeController({
|
||||
canManage: false,
|
||||
});
|
||||
apiKeyRepo.findById.mockResolvedValue({
|
||||
id: 'k1',
|
||||
creatorId: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
});
|
||||
await controller.revoke({ id: 'k1' } as any, user, workspace, reqAccess());
|
||||
expect(apiKeyService.revoke).toHaveBeenCalledWith('k1', 'ws-1');
|
||||
});
|
||||
|
||||
it("admin CAN revoke another user's key", async () => {
|
||||
const { controller, apiKeyRepo, apiKeyService } = makeController({
|
||||
canManage: true,
|
||||
});
|
||||
apiKeyRepo.findById.mockResolvedValue({
|
||||
id: 'k1',
|
||||
creatorId: 'someone-else',
|
||||
workspaceId: 'ws-1',
|
||||
});
|
||||
await controller.revoke({ id: 'k1' } as any, user, workspace, reqAccess());
|
||||
expect(apiKeyService.revoke).toHaveBeenCalledWith('k1', 'ws-1');
|
||||
});
|
||||
|
||||
it('404 when the key does not exist', async () => {
|
||||
const { controller, apiKeyRepo } = makeController({ canManage: true });
|
||||
apiKeyRepo.findById.mockResolvedValue(undefined);
|
||||
await expect(
|
||||
controller.revoke({ id: 'k1' } as any, user, workspace, reqAccess()),
|
||||
).rejects.toBeInstanceOf(NotFoundException);
|
||||
});
|
||||
});
|
||||
|
||||
describe('ApiKeyController — create emits audit + returns token once', () => {
|
||||
it('logs API_KEY_CREATED and returns the token + computed expiry', async () => {
|
||||
const { controller, auditService } = makeController();
|
||||
const res = await controller.create(
|
||||
{ name: 'ci' } as any,
|
||||
user,
|
||||
reqAccess(),
|
||||
);
|
||||
expect(res.token).toBe('tok');
|
||||
expect(res.apiKey).toMatchObject({ id: 'k1', name: 'n' });
|
||||
expect(auditService.log).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ event: 'api_key.created' }),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
// Sanity: the CASL subject used is the workspace API subject.
|
||||
it('uses WorkspaceCaslSubject.API with the Manage action', () => {
|
||||
expect(WorkspaceCaslSubject.API).toBe('api_key');
|
||||
expect(WorkspaceCaslAction.Manage).toBeDefined();
|
||||
});
|
||||
@@ -0,0 +1,201 @@
|
||||
import {
|
||||
Body,
|
||||
Controller,
|
||||
ForbiddenException,
|
||||
HttpCode,
|
||||
HttpStatus,
|
||||
Inject,
|
||||
Logger,
|
||||
NotFoundException,
|
||||
Post,
|
||||
Req,
|
||||
UseGuards,
|
||||
} from '@nestjs/common';
|
||||
import { Throttle } from '@nestjs/throttler';
|
||||
import { FastifyRequest } from 'fastify';
|
||||
import { ApiKeyService } from './api-key.service';
|
||||
import { ApiKeyRepo } from '@docmost/db/repos/api-key/api-key.repo';
|
||||
import { CreateApiKeyDto } from './dto/create-api-key.dto';
|
||||
import { RevokeApiKeyDto } from './dto/revoke-api-key.dto';
|
||||
import { AuthUser } from '../../common/decorators/auth-user.decorator';
|
||||
import { AuthWorkspace } from '../../common/decorators/auth-workspace.decorator';
|
||||
import { JwtAuthGuard } from '../../common/guards/jwt-auth.guard';
|
||||
import { User, Workspace } from '@docmost/db/types/entity.types';
|
||||
import WorkspaceAbilityFactory from '../casl/abilities/workspace-ability.factory';
|
||||
import {
|
||||
WorkspaceCaslAction,
|
||||
WorkspaceCaslSubject,
|
||||
} from '../casl/interfaces/workspace-ability.type';
|
||||
import { AuditEvent, AuditResource } from '../../common/events/audit-events';
|
||||
import {
|
||||
AUDIT_SERVICE,
|
||||
IAuditService,
|
||||
} from '../../integrations/audit/audit.service';
|
||||
import { EnvironmentService } from '../../integrations/environment/environment.service';
|
||||
import { UserThrottlerGuard } from '../../integrations/throttle/user-throttler.guard';
|
||||
import { AUTH_THROTTLER } from '../../integrations/throttle/throttler-names';
|
||||
|
||||
@UseGuards(JwtAuthGuard)
|
||||
@Controller('api-keys')
|
||||
export class ApiKeyController {
|
||||
private readonly logger = new Logger(ApiKeyController.name);
|
||||
|
||||
constructor(
|
||||
private readonly apiKeyService: ApiKeyService,
|
||||
private readonly apiKeyRepo: ApiKeyRepo,
|
||||
private readonly workspaceAbility: WorkspaceAbilityFactory,
|
||||
private readonly environmentService: EnvironmentService,
|
||||
@Inject(AUDIT_SERVICE) private readonly auditService: IAuditService,
|
||||
) {}
|
||||
|
||||
// Kill-switch OFF: the issuance surface disappears entirely (404), not a 403 —
|
||||
// it must look like the feature does not exist.
|
||||
private assertEnabled(): void {
|
||||
if (!this.environmentService.isApiKeysEnabled()) {
|
||||
throw new NotFoundException();
|
||||
}
|
||||
}
|
||||
|
||||
// A token cannot manage tokens (GitHub-PAT semantics): an api-key principal is
|
||||
// refused on the management surface, so a leaked key cannot mint a replacement
|
||||
// or revoke the keys that would lock it out (closes post-revocation laundering).
|
||||
private rejectApiKeyPrincipal(req: FastifyRequest): void {
|
||||
if ((req.raw as { authType?: string }).authType === 'api_key') {
|
||||
throw new ForbiddenException('API keys cannot manage API keys');
|
||||
}
|
||||
}
|
||||
|
||||
private clientIp(req: FastifyRequest): string {
|
||||
return req.ip ?? req.socket?.remoteAddress ?? 'unknown';
|
||||
}
|
||||
|
||||
@HttpCode(HttpStatus.OK)
|
||||
@UseGuards(JwtAuthGuard, UserThrottlerGuard)
|
||||
@Throttle({ [AUTH_THROTTLER]: { limit: 10, ttl: 60_000 } })
|
||||
@Post('create')
|
||||
async create(
|
||||
@Body() dto: CreateApiKeyDto,
|
||||
@AuthUser() user: User,
|
||||
@Req() req: FastifyRequest,
|
||||
) {
|
||||
this.assertEnabled();
|
||||
this.rejectApiKeyPrincipal(req);
|
||||
|
||||
// undefined -> service default (1 year); null -> unlimited; string -> Date.
|
||||
const expiresAt =
|
||||
dto.expiresAt === undefined
|
||||
? undefined
|
||||
: dto.expiresAt === null
|
||||
? null
|
||||
: new Date(dto.expiresAt);
|
||||
|
||||
const { token, key } = await this.apiKeyService.create(
|
||||
user,
|
||||
dto.name,
|
||||
expiresAt,
|
||||
);
|
||||
|
||||
this.auditService.log({
|
||||
event: AuditEvent.API_KEY_CREATED,
|
||||
resourceType: AuditResource.API_KEY,
|
||||
resourceId: key.id,
|
||||
});
|
||||
// The durable trail lives in container logs (AUDIT_SERVICE is a Noop in this
|
||||
// build). No token material — the JWT is only ever returned in the response.
|
||||
this.logger.log(
|
||||
`API key created: id=${key.id} name=${JSON.stringify(
|
||||
key.name,
|
||||
)} actor=${user.id} expiresAt=${
|
||||
key.expiresAt ? new Date(key.expiresAt).toISOString() : 'never'
|
||||
} ip=${this.clientIp(req)}`,
|
||||
);
|
||||
|
||||
// Return the token ONCE (never retrievable again) and the computed expiry so
|
||||
// the caller/UI can surface "expires <date>" (the year-default time-bomb
|
||||
// early-warning).
|
||||
return {
|
||||
token,
|
||||
apiKey: {
|
||||
id: key.id,
|
||||
name: key.name,
|
||||
expiresAt: key.expiresAt,
|
||||
createdAt: key.createdAt,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
@HttpCode(HttpStatus.OK)
|
||||
@Post('list')
|
||||
async list(
|
||||
@AuthUser() user: User,
|
||||
@AuthWorkspace() workspace: Workspace,
|
||||
@Req() req: FastifyRequest,
|
||||
) {
|
||||
this.assertEnabled();
|
||||
this.rejectApiKeyPrincipal(req);
|
||||
|
||||
const ability = this.workspaceAbility.createForUser(user, workspace);
|
||||
// Admin (CASL Manage on API): every key in the workspace, attributed to its
|
||||
// creator (closes "a leaked key of a departed employee is invisible"). A
|
||||
// member sees only their own.
|
||||
const keys = ability.can(
|
||||
WorkspaceCaslAction.Manage,
|
||||
WorkspaceCaslSubject.API,
|
||||
)
|
||||
? await this.apiKeyRepo.findAllInWorkspace(workspace.id)
|
||||
: await this.apiKeyRepo.findByCreator(user.id, workspace.id);
|
||||
|
||||
return keys.map((k) => ({
|
||||
id: k.id,
|
||||
name: k.name,
|
||||
expiresAt: k.expiresAt,
|
||||
lastUsedAt: k.lastUsedAt,
|
||||
createdAt: k.createdAt,
|
||||
creator: k.creator,
|
||||
}));
|
||||
}
|
||||
|
||||
@HttpCode(HttpStatus.OK)
|
||||
@Post('revoke')
|
||||
async revoke(
|
||||
@Body() dto: RevokeApiKeyDto,
|
||||
@AuthUser() user: User,
|
||||
@AuthWorkspace() workspace: Workspace,
|
||||
@Req() req: FastifyRequest,
|
||||
) {
|
||||
this.assertEnabled();
|
||||
this.rejectApiKeyPrincipal(req);
|
||||
|
||||
const key = await this.apiKeyRepo.findById(dto.id, workspace.id);
|
||||
// Uniform 404 for a missing/already-revoked key regardless of who asks — no
|
||||
// existence oracle for keys the caller may not own.
|
||||
if (!key) {
|
||||
throw new NotFoundException();
|
||||
}
|
||||
|
||||
const ability = this.workspaceAbility.createForUser(user, workspace);
|
||||
const canManageAll = ability.can(
|
||||
WorkspaceCaslAction.Manage,
|
||||
WorkspaceCaslSubject.API,
|
||||
);
|
||||
// Admin may revoke any key in the workspace; a member only their own.
|
||||
if (!canManageAll && key.creatorId !== user.id) {
|
||||
throw new ForbiddenException();
|
||||
}
|
||||
|
||||
await this.apiKeyService.revoke(key.id, workspace.id);
|
||||
|
||||
this.auditService.log({
|
||||
event: AuditEvent.API_KEY_DELETED,
|
||||
resourceType: AuditResource.API_KEY,
|
||||
resourceId: key.id,
|
||||
});
|
||||
this.logger.log(
|
||||
`API key revoked: id=${key.id} name=${JSON.stringify(
|
||||
key.name,
|
||||
)} actor=${user.id} ip=${this.clientIp(req)}`,
|
||||
);
|
||||
|
||||
return { success: true };
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
import { Module } from '@nestjs/common';
|
||||
import { ApiKeyService } from './api-key.service';
|
||||
import { ApiKeyController } from './api-key.controller';
|
||||
import { TokenModule } from '../auth/token.module';
|
||||
|
||||
// Core (non-EE) API-key feature: issuance REST endpoints + the shared validator
|
||||
// consumed by jwt.strategy (REST) and McpService (the /mcp Bearer router).
|
||||
// DatabaseModule (global) provides ApiKeyRepo/UserRepo/WorkspaceRepo; CaslModule
|
||||
// (global) provides WorkspaceAbilityFactory; TokenModule provides TokenService
|
||||
// (the no-exp api-key signer). ApiKeyService is exported so AuthModule (for
|
||||
// jwt.strategy) and McpModule (for the /mcp router) can inject it directly,
|
||||
// replacing the absent EE `ee/api-key` dynamic require.
|
||||
@Module({
|
||||
imports: [TokenModule],
|
||||
controllers: [ApiKeyController],
|
||||
providers: [ApiKeyService],
|
||||
exports: [ApiKeyService],
|
||||
})
|
||||
export class ApiKeyModule {}
|
||||
@@ -0,0 +1,299 @@
|
||||
import { UnauthorizedException } from '@nestjs/common';
|
||||
import { ApiKeyService } from './api-key.service';
|
||||
import { JwtType } from '../auth/dto/jwt-payload';
|
||||
|
||||
/**
|
||||
* Security contract for ApiKeyService.validate — the single validator shared by
|
||||
* jwt.strategy (REST) and the /mcp Bearer router.
|
||||
*
|
||||
* Invariants under test:
|
||||
* - Anti-enumeration: every DEFINITE deny (missing/revoked/expired row, disabled
|
||||
* user, workspace mismatch, kill-switch off) throws the SAME bare
|
||||
* UnauthorizedException — an agent cannot distinguish expired from revoked.
|
||||
* - deny-on-decision / 5xx-on-infra: an UNEXPECTED (infra) error PROPAGATES as
|
||||
* itself (→ 5xx), never masked as a 401.
|
||||
* - Expiry is read from the ROW, never a JWT exp claim.
|
||||
* - No validate cache (each call re-reads the row → immediate revocation).
|
||||
*/
|
||||
|
||||
const APP_SECRET = 'secret';
|
||||
|
||||
function makeDeps(over: Partial<Record<string, any>> = {}) {
|
||||
const apiKeyRepo = {
|
||||
findById: jest.fn(),
|
||||
insert: jest.fn(),
|
||||
softDelete: jest.fn(),
|
||||
touchLastUsed: jest.fn().mockResolvedValue(undefined),
|
||||
...(over.apiKeyRepo ?? {}),
|
||||
};
|
||||
const userRepo = {
|
||||
findById: jest.fn(),
|
||||
...(over.userRepo ?? {}),
|
||||
};
|
||||
const workspaceRepo = {
|
||||
findById: jest.fn().mockResolvedValue({ id: 'ws-1' }),
|
||||
...(over.workspaceRepo ?? {}),
|
||||
};
|
||||
const tokenService = {
|
||||
generateApiToken: jest.fn().mockResolvedValue('minted.jwt.token'),
|
||||
...(over.tokenService ?? {}),
|
||||
};
|
||||
const environmentService = {
|
||||
isApiKeysEnabled: jest.fn().mockReturnValue(true),
|
||||
getApiKeysEnabledRaw: jest.fn().mockReturnValue(undefined),
|
||||
getAppSecret: jest.fn().mockReturnValue(APP_SECRET),
|
||||
...(over.environmentService ?? {}),
|
||||
};
|
||||
const service = new (ApiKeyService as unknown as new (...a: any[]) => ApiKeyService)(
|
||||
apiKeyRepo,
|
||||
userRepo,
|
||||
workspaceRepo,
|
||||
tokenService,
|
||||
environmentService,
|
||||
);
|
||||
return { service, apiKeyRepo, userRepo, workspaceRepo, tokenService, environmentService };
|
||||
}
|
||||
|
||||
const payload = (over: Record<string, any> = {}) => ({
|
||||
sub: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
apiKeyId: 'key-1',
|
||||
type: JwtType.API_KEY,
|
||||
...over,
|
||||
});
|
||||
|
||||
const activeRow = (over: Record<string, any> = {}) => ({
|
||||
id: 'key-1',
|
||||
name: 'k',
|
||||
creatorId: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
expiresAt: null,
|
||||
lastUsedAt: null,
|
||||
deletedAt: null,
|
||||
...over,
|
||||
});
|
||||
|
||||
const activeUser = (over: Record<string, any> = {}) => ({
|
||||
id: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
deactivatedAt: null,
|
||||
deletedAt: null,
|
||||
isAgent: false,
|
||||
...over,
|
||||
});
|
||||
|
||||
describe('ApiKeyService.validate', () => {
|
||||
it('returns { user, workspace } for a valid active key', async () => {
|
||||
const { service, apiKeyRepo, userRepo } = makeDeps();
|
||||
apiKeyRepo.findById.mockResolvedValue(activeRow());
|
||||
userRepo.findById.mockResolvedValue(activeUser());
|
||||
|
||||
const res = await service.validate(payload() as any);
|
||||
|
||||
expect(res.user).toMatchObject({ id: 'u-1' });
|
||||
expect(res.workspace).toMatchObject({ id: 'ws-1' });
|
||||
// Loads isAgent so downstream provenance does not silently degrade.
|
||||
expect(userRepo.findById).toHaveBeenCalledWith('u-1', 'ws-1', {
|
||||
includeIsAgent: true,
|
||||
});
|
||||
});
|
||||
|
||||
// --- Anti-enumeration: every deny is the SAME bare 401 -------------------
|
||||
const denyCases: Array<[string, (d: ReturnType<typeof makeDeps>) => void]> = [
|
||||
[
|
||||
'missing/orphaned row',
|
||||
(d) => d.apiKeyRepo.findById.mockResolvedValue(undefined),
|
||||
],
|
||||
[
|
||||
'revoked (soft-deleted → findById returns undefined)',
|
||||
(d) => d.apiKeyRepo.findById.mockResolvedValue(undefined),
|
||||
],
|
||||
[
|
||||
'expired (expires_at in the past)',
|
||||
(d) => {
|
||||
d.apiKeyRepo.findById.mockResolvedValue(
|
||||
activeRow({ expiresAt: new Date(Date.now() - 1000) }),
|
||||
);
|
||||
d.userRepo.findById.mockResolvedValue(activeUser());
|
||||
},
|
||||
],
|
||||
[
|
||||
'disabled user',
|
||||
(d) => {
|
||||
d.apiKeyRepo.findById.mockResolvedValue(activeRow());
|
||||
d.userRepo.findById.mockResolvedValue(
|
||||
activeUser({ deactivatedAt: new Date() }),
|
||||
);
|
||||
},
|
||||
],
|
||||
[
|
||||
'user not found',
|
||||
(d) => {
|
||||
d.apiKeyRepo.findById.mockResolvedValue(activeRow());
|
||||
d.userRepo.findById.mockResolvedValue(undefined);
|
||||
},
|
||||
],
|
||||
[
|
||||
'creator/sub mismatch',
|
||||
(d) => {
|
||||
d.apiKeyRepo.findById.mockResolvedValue(activeRow({ creatorId: 'other' }));
|
||||
d.userRepo.findById.mockResolvedValue(activeUser());
|
||||
},
|
||||
],
|
||||
[
|
||||
'workspace row missing',
|
||||
(d) => {
|
||||
d.apiKeyRepo.findById.mockResolvedValue(activeRow());
|
||||
d.userRepo.findById.mockResolvedValue(activeUser());
|
||||
d.workspaceRepo.findById.mockResolvedValue(undefined);
|
||||
},
|
||||
],
|
||||
[
|
||||
'kill-switch OFF',
|
||||
(d) => d.environmentService.isApiKeysEnabled.mockReturnValue(false),
|
||||
],
|
||||
[
|
||||
'malformed payload (missing apiKeyId)',
|
||||
() => undefined,
|
||||
],
|
||||
];
|
||||
|
||||
it.each(denyCases)(
|
||||
'throws a bare UnauthorizedException with NO message for: %s',
|
||||
async (label, arrange) => {
|
||||
const deps = makeDeps();
|
||||
arrange(deps);
|
||||
const p =
|
||||
label === 'malformed payload (missing apiKeyId)'
|
||||
? (payload({ apiKeyId: undefined }) as any)
|
||||
: (payload() as any);
|
||||
|
||||
const err = await deps.service.validate(p).catch((e) => e);
|
||||
expect(err).toBeInstanceOf(UnauthorizedException);
|
||||
// Anti-enumeration: identical, class-less message for every failure mode.
|
||||
expect(err.message).toBe('Unauthorized');
|
||||
},
|
||||
);
|
||||
|
||||
it('kill-switch OFF denies BEFORE any DB read', async () => {
|
||||
const { service, apiKeyRepo, environmentService } = makeDeps();
|
||||
environmentService.isApiKeysEnabled.mockReturnValue(false);
|
||||
|
||||
await expect(service.validate(payload() as any)).rejects.toBeInstanceOf(
|
||||
UnauthorizedException,
|
||||
);
|
||||
expect(apiKeyRepo.findById).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
// --- Infra error propagates (5xx), NOT masked as 401 ---------------------
|
||||
it('PROPAGATES an infra (DB) error instead of masking it as 401', async () => {
|
||||
const { service, apiKeyRepo } = makeDeps();
|
||||
const boom = new Error('connection terminated');
|
||||
apiKeyRepo.findById.mockRejectedValue(boom);
|
||||
|
||||
await expect(service.validate(payload() as any)).rejects.toBe(boom);
|
||||
});
|
||||
|
||||
// --- No cache: revocation is immediate on the next call ------------------
|
||||
it('re-reads the row on every call (no validate cache → immediate revocation)', async () => {
|
||||
const { service, apiKeyRepo, userRepo } = makeDeps();
|
||||
apiKeyRepo.findById.mockResolvedValue(activeRow());
|
||||
userRepo.findById.mockResolvedValue(activeUser());
|
||||
await service.validate(payload() as any);
|
||||
|
||||
// Now the key is revoked (row invisible) — the very next call denies.
|
||||
apiKeyRepo.findById.mockResolvedValue(undefined);
|
||||
await expect(service.validate(payload() as any)).rejects.toBeInstanceOf(
|
||||
UnauthorizedException,
|
||||
);
|
||||
expect(apiKeyRepo.findById).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
|
||||
// --- last_used_at is throttled + fire-and-forget -------------------------
|
||||
it('touches last_used_at when stale and skips when fresh', async () => {
|
||||
const { service, apiKeyRepo, userRepo } = makeDeps();
|
||||
userRepo.findById.mockResolvedValue(activeUser());
|
||||
|
||||
// Stale (never used) -> touch.
|
||||
apiKeyRepo.findById.mockResolvedValue(activeRow({ lastUsedAt: null }));
|
||||
await service.validate(payload() as any);
|
||||
expect(apiKeyRepo.touchLastUsed).toHaveBeenCalledTimes(1);
|
||||
|
||||
// Fresh (used 1 minute ago) -> skip.
|
||||
apiKeyRepo.touchLastUsed.mockClear();
|
||||
apiKeyRepo.findById.mockResolvedValue(
|
||||
activeRow({ lastUsedAt: new Date(Date.now() - 60_000) }),
|
||||
);
|
||||
await service.validate(payload() as any);
|
||||
expect(apiKeyRepo.touchLastUsed).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('a failing last_used_at touch never fails the request', async () => {
|
||||
const { service, apiKeyRepo, userRepo } = makeDeps();
|
||||
apiKeyRepo.findById.mockResolvedValue(activeRow({ lastUsedAt: null }));
|
||||
userRepo.findById.mockResolvedValue(activeUser());
|
||||
apiKeyRepo.touchLastUsed.mockRejectedValue(new Error('write failed'));
|
||||
|
||||
await expect(service.validate(payload() as any)).resolves.toMatchObject({
|
||||
user: { id: 'u-1' },
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('ApiKeyService.create (mint-then-insert, no exp)', () => {
|
||||
it('mints the JWT BEFORE inserting the row and returns the token once', async () => {
|
||||
const { service, apiKeyRepo, tokenService } = makeDeps();
|
||||
const order: string[] = [];
|
||||
tokenService.generateApiToken.mockImplementation(async () => {
|
||||
order.push('mint');
|
||||
return 'tok';
|
||||
});
|
||||
apiKeyRepo.insert.mockImplementation(async (row: any) => {
|
||||
order.push('insert');
|
||||
return { ...row, createdAt: new Date() };
|
||||
});
|
||||
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
const res = await service.create(user, 'my key');
|
||||
|
||||
expect(order).toEqual(['mint', 'insert']);
|
||||
expect(res.token).toBe('tok');
|
||||
// The id is generated before minting and reused for the row.
|
||||
const mintArg = tokenService.generateApiToken.mock.calls[0][0];
|
||||
const insertArg = apiKeyRepo.insert.mock.calls[0][0];
|
||||
expect(mintArg.apiKeyId).toBe(insertArg.id);
|
||||
});
|
||||
|
||||
it('applies the 1-year default when expiresAt is undefined', async () => {
|
||||
const { service, apiKeyRepo } = makeDeps();
|
||||
apiKeyRepo.insert.mockImplementation(async (row: any) => row);
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
|
||||
await service.create(user, 'k');
|
||||
|
||||
const insertArg = apiKeyRepo.insert.mock.calls[0][0];
|
||||
const days =
|
||||
(insertArg.expiresAt.getTime() - Date.now()) / (24 * 60 * 60 * 1000);
|
||||
expect(days).toBeGreaterThan(364);
|
||||
expect(days).toBeLessThan(367);
|
||||
});
|
||||
|
||||
it('honors an explicit null (unlimited)', async () => {
|
||||
const { service, apiKeyRepo } = makeDeps();
|
||||
apiKeyRepo.insert.mockImplementation(async (row: any) => row);
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
|
||||
await service.create(user, 'k', null);
|
||||
|
||||
expect(apiKeyRepo.insert.mock.calls[0][0].expiresAt).toBeNull();
|
||||
});
|
||||
|
||||
it('does NOT insert a row when minting fails (mint-then-insert → inert)', async () => {
|
||||
const { service, apiKeyRepo, tokenService } = makeDeps();
|
||||
tokenService.generateApiToken.mockRejectedValue(new Error('mint failed'));
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
|
||||
await expect(service.create(user, 'k')).rejects.toThrow('mint failed');
|
||||
expect(apiKeyRepo.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,191 @@
|
||||
import {
|
||||
Injectable,
|
||||
Logger,
|
||||
OnModuleInit,
|
||||
UnauthorizedException,
|
||||
} from '@nestjs/common';
|
||||
import { v7 as uuid7 } from 'uuid';
|
||||
import { ApiKeyRepo } from '@docmost/db/repos/api-key/api-key.repo';
|
||||
import { UserRepo } from '@docmost/db/repos/user/user.repo';
|
||||
import { WorkspaceRepo } from '@docmost/db/repos/workspace/workspace.repo';
|
||||
import { TokenService } from '../auth/services/token.service';
|
||||
import { EnvironmentService } from '../../integrations/environment/environment.service';
|
||||
import { JwtApiKeyPayload } from '../auth/dto/jwt-payload';
|
||||
import { ApiKey, User, Workspace } from '@docmost/db/types/entity.types';
|
||||
import { isUserDisabled } from '../../common/helpers';
|
||||
|
||||
// Default lifetime for a new key when the caller does not specify one: 1 year.
|
||||
// The owner runs a homelab where agents live for years; forcing rotation is
|
||||
// operational pain, so an explicit `null` (unlimited) is also allowed.
|
||||
const DEFAULT_LIFETIME_MS = 365 * 24 * 60 * 60 * 1000;
|
||||
|
||||
// last_used_at is a best-effort forensics stamp, not an access record; we only
|
||||
// refresh it when it is older than this to avoid a write on every request. The
|
||||
// 1h resolution is a deliberate constant (forensics granularity, not accounting).
|
||||
const LAST_USED_THROTTLE_MS = 60 * 60 * 1000;
|
||||
|
||||
/**
|
||||
* Core API-key lifecycle service. Owns minting (create), the single validator
|
||||
* shared by BOTH the REST jwt.strategy path and the /mcp Bearer path (validate),
|
||||
* and revocation (revoke). The `api_keys` ROW is the sole source of truth for a
|
||||
* key's lifetime and revocation — never the JWT, which carries no `exp` claim.
|
||||
*/
|
||||
@Injectable()
|
||||
export class ApiKeyService implements OnModuleInit {
|
||||
private readonly logger = new Logger(ApiKeyService.name);
|
||||
|
||||
constructor(
|
||||
private readonly apiKeyRepo: ApiKeyRepo,
|
||||
private readonly userRepo: UserRepo,
|
||||
private readonly workspaceRepo: WorkspaceRepo,
|
||||
private readonly tokenService: TokenService,
|
||||
private readonly environmentService: EnvironmentService,
|
||||
) {}
|
||||
|
||||
onModuleInit() {
|
||||
// Boot log so the kill-switch state after each deploy is verifiable in logs.
|
||||
const enabled = this.environmentService.isApiKeysEnabled();
|
||||
const raw = this.environmentService.getApiKeysEnabledRaw();
|
||||
this.logger.log(
|
||||
`API keys: ${enabled ? 'ENABLED' : 'DISABLED'} (API_KEYS_ENABLED=${
|
||||
raw ?? 'unset'
|
||||
})`,
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Mint a new key for `user`. mint-then-insert ordering (R1):
|
||||
* 1. generate the id first — it must be in the JWT payload before the row.
|
||||
* 2. mint the JWT (no `exp` claim). A mint failure aborts before any row is
|
||||
* written (inert), so a half-created key cannot exist.
|
||||
* 3. insert the row last. A lost response leaves an orphaned row that is
|
||||
* visible in `list` and self-heals (the user revokes it).
|
||||
* The token is returned ONCE and never stored — the JWT is self-contained, so
|
||||
* no token material lives in the table.
|
||||
*
|
||||
* `expiresAt`: `undefined` -> default 1 year; `null` -> unlimited (explicit);
|
||||
* a Date -> that instant (a past date is rejected at the DTO layer).
|
||||
*/
|
||||
async create(
|
||||
user: User,
|
||||
name: string,
|
||||
expiresAt?: Date | null,
|
||||
): Promise<{ token: string; key: ApiKey }> {
|
||||
const resolvedExpiresAt =
|
||||
expiresAt === undefined
|
||||
? new Date(Date.now() + DEFAULT_LIFETIME_MS)
|
||||
: expiresAt;
|
||||
|
||||
const apiKeyId = uuid7();
|
||||
|
||||
const token = await this.tokenService.generateApiToken({
|
||||
apiKeyId,
|
||||
user,
|
||||
workspaceId: user.workspaceId,
|
||||
});
|
||||
|
||||
const key = await this.apiKeyRepo.insert({
|
||||
id: apiKeyId,
|
||||
name,
|
||||
creatorId: user.id,
|
||||
workspaceId: user.workspaceId,
|
||||
expiresAt: resolvedExpiresAt,
|
||||
});
|
||||
|
||||
return { token, key };
|
||||
}
|
||||
|
||||
/**
|
||||
* The single validator for an api-key principal, shared by jwt.strategy and the
|
||||
* /mcp Bearer router. Returns `{ user, workspace }` (the same shape the access
|
||||
* path returns) so the AuthUser/AuthWorkspace decorators and MCP identity work
|
||||
* unchanged.
|
||||
*
|
||||
* Failure semantics (R4, anti-enumeration): a DEFINITE negative fact — feature
|
||||
* disabled, missing/revoked/expired row, workspace mismatch, disabled user —
|
||||
* throws a bare `UnauthorizedException` (a single generic 401 for every case;
|
||||
* an agent cannot distinguish expired from revoked, and its reaction is
|
||||
* identical). An UNEXPECTED (infra) error is NOT caught here: it propagates so
|
||||
* the surface returns 5xx, never a masked 401 (deny-on-decision / 5xx-on-infra).
|
||||
* There is NO validate cache: it is 2–3 PK lookups (~1ms), two orders of
|
||||
* magnitude cheaper than the bcrypt it replaces; a cache would only add a
|
||||
* Date-serialization trap and a revocation lag. Revocation is immediate.
|
||||
*/
|
||||
async validate(
|
||||
payload: JwtApiKeyPayload,
|
||||
): Promise<{ user: User; workspace: Workspace }> {
|
||||
// Kill-switch OFF: deny unconditionally (same generic 401). Note the
|
||||
// endpoints additionally 404 at the controller; here we deny the token.
|
||||
if (!this.environmentService.isApiKeysEnabled()) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
if (!payload?.apiKeyId || !payload?.sub || !payload?.workspaceId) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
const row = await this.apiKeyRepo.findById(
|
||||
payload.apiKeyId,
|
||||
payload.workspaceId,
|
||||
);
|
||||
// Absent row = revoked (soft-deleted, invisible to findById), orphaned
|
||||
// (creator/workspace cascade-deleted), or never existed. All terminal deny.
|
||||
if (!row) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
// Expiry is read from the ROW, never an `exp` JWT claim.
|
||||
if (row.expiresAt && row.expiresAt.getTime() <= Date.now()) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
const user = await this.userRepo.findById(
|
||||
payload.sub,
|
||||
payload.workspaceId,
|
||||
{ includeIsAgent: true },
|
||||
);
|
||||
if (!user || isUserDisabled(user)) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
// The key acts only as its creator (defence in depth against a token whose
|
||||
// signed `sub` ever drifted from the row's owner).
|
||||
if (row.creatorId !== user.id) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
const workspace = await this.workspaceRepo.findById(payload.workspaceId);
|
||||
if (!workspace) {
|
||||
throw new UnauthorizedException();
|
||||
}
|
||||
|
||||
// Best-effort, throttled, fire-and-forget forensics stamp AFTER all checks.
|
||||
this.touchLastUsed(row);
|
||||
|
||||
return { user, workspace };
|
||||
}
|
||||
|
||||
/**
|
||||
* Revoke (soft-delete) a key. Authorization/ownership is decided by the caller
|
||||
* (the controller, via CASL); this only performs the terminal write. Idempotent:
|
||||
* a second revoke is a no-op (the row is already invisible).
|
||||
*/
|
||||
async revoke(id: string, workspaceId: string): Promise<void> {
|
||||
await this.apiKeyRepo.softDelete(id, workspaceId);
|
||||
}
|
||||
|
||||
// Throttled best-effort last_used_at bump: skip if it was touched within the
|
||||
// window; otherwise fire-and-forget so a stamp write never fails or slows the
|
||||
// request (mirrors SessionActivityService.trackActivity).
|
||||
private touchLastUsed(row: ApiKey): void {
|
||||
const last = row.lastUsedAt ? new Date(row.lastUsedAt).getTime() : 0;
|
||||
if (Date.now() - last < LAST_USED_THROTTLE_MS) return;
|
||||
void this.apiKeyRepo.touchLastUsed(row.id).catch((err) => {
|
||||
this.logger.warn(
|
||||
`Failed to update api_key last_used_at for ${row.id}: ${
|
||||
(err as Error)?.message ?? err
|
||||
}`,
|
||||
);
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,51 @@
|
||||
import {
|
||||
IsDateString,
|
||||
IsNotEmpty,
|
||||
IsOptional,
|
||||
IsString,
|
||||
MaxLength,
|
||||
registerDecorator,
|
||||
ValidationOptions,
|
||||
} from 'class-validator';
|
||||
|
||||
/**
|
||||
* `expiresAt` must be strictly in the future. Skips validation for `null`
|
||||
* (explicit "unlimited") and `undefined` (server applies the 1-year default),
|
||||
* so only an actually-supplied date is range-checked. Rejecting a PAST date at
|
||||
* the DTO layer means a caller cannot mint an already-dead key.
|
||||
*/
|
||||
function IsFutureDateString(options?: ValidationOptions) {
|
||||
return function (object: object, propertyName: string) {
|
||||
registerDecorator({
|
||||
name: 'isFutureDateString',
|
||||
target: object.constructor,
|
||||
propertyName,
|
||||
options: {
|
||||
message: 'expiresAt must be a date in the future',
|
||||
...options,
|
||||
},
|
||||
validator: {
|
||||
validate(value: unknown) {
|
||||
if (value === null || value === undefined) return true;
|
||||
if (typeof value !== 'string') return false;
|
||||
const t = Date.parse(value);
|
||||
return !Number.isNaN(t) && t > Date.now();
|
||||
},
|
||||
},
|
||||
});
|
||||
};
|
||||
}
|
||||
|
||||
export class CreateApiKeyDto {
|
||||
@IsString()
|
||||
@IsNotEmpty()
|
||||
@MaxLength(255)
|
||||
name: string;
|
||||
|
||||
// undefined -> default 1 year (applied server-side); null -> unlimited
|
||||
// (explicit); an ISO date string -> that instant, which must be in the future.
|
||||
@IsOptional()
|
||||
@IsDateString()
|
||||
@IsFutureDateString()
|
||||
expiresAt?: string | null;
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
import { IsUUID } from 'class-validator';
|
||||
|
||||
export class RevokeApiKeyDto {
|
||||
@IsUUID()
|
||||
id: string;
|
||||
}
|
||||
@@ -20,3 +20,71 @@ describe('AuthController', () => {
|
||||
expect(controller).toBeDefined();
|
||||
});
|
||||
});
|
||||
|
||||
// The collab-token handler is the ARM-SEAM of the #501 anti-laundering defense:
|
||||
// it derives the api-key origin args ({ apiKeyId }) from the SIGNED-derived
|
||||
// `req.raw` fields (stamped by jwt.strategy) and threads them into the collab
|
||||
// token mint, forcing principal='api_key' so a later key revoke rejects NEW
|
||||
// collab connections. A regression here (reading `body`, dropping `apiKeyId`,
|
||||
// or inverting the ternary) would silently mint api-key requests as
|
||||
// principal='session' and reopen the laundering hole with a green suite. These
|
||||
// tests pin the EXACT args the controller passes to authService.getCollabToken.
|
||||
describe('AuthController.collabToken arms the api-key origin (#501)', () => {
|
||||
let controller: AuthController;
|
||||
let getCollabToken: jest.Mock;
|
||||
|
||||
const user = { id: 'u-1', workspaceId: 'ws-1' } as any;
|
||||
const workspace = { id: 'ws-1' } as any;
|
||||
|
||||
beforeEach(() => {
|
||||
getCollabToken = jest.fn().mockResolvedValue({ token: 'ct' });
|
||||
controller = new AuthController(
|
||||
{ getCollabToken } as any, // authService
|
||||
{} as any, // sessionService
|
||||
{} as any, // environmentService
|
||||
{} as any, // moduleRef
|
||||
{} as any, // auditService
|
||||
);
|
||||
});
|
||||
|
||||
it('threads { apiKeyId } when req.raw marks an api_key principal (ARMED)', async () => {
|
||||
const req = { raw: { authType: 'api_key', apiKeyId: 'k-1' } } as any;
|
||||
|
||||
await controller.collabToken(user, workspace, req);
|
||||
|
||||
expect(getCollabToken).toHaveBeenCalledTimes(1);
|
||||
expect(getCollabToken).toHaveBeenCalledWith(user, 'ws-1', {
|
||||
apiKeyId: 'k-1',
|
||||
});
|
||||
});
|
||||
|
||||
it('passes undefined for a normal session request (NOT armed)', async () => {
|
||||
const req = { raw: {} } as any;
|
||||
|
||||
await controller.collabToken(user, workspace, req);
|
||||
|
||||
expect(getCollabToken).toHaveBeenCalledTimes(1);
|
||||
expect(getCollabToken).toHaveBeenCalledWith(user, 'ws-1', undefined);
|
||||
});
|
||||
|
||||
it('does NOT arm when api_key authType lacks an apiKeyId', async () => {
|
||||
const req = { raw: { authType: 'api_key' } } as any;
|
||||
|
||||
await controller.collabToken(user, workspace, req);
|
||||
|
||||
expect(getCollabToken).toHaveBeenCalledWith(user, 'ws-1', undefined);
|
||||
});
|
||||
|
||||
it('reads the SIGNED req.raw, never a spoofable client body', async () => {
|
||||
// A client-supplied body claiming api_key must be ignored: only the
|
||||
// jwt.strategy-stamped req.raw can arm the api-key origin.
|
||||
const req = {
|
||||
raw: {},
|
||||
body: { authType: 'api_key', apiKeyId: 'attacker' },
|
||||
} as any;
|
||||
|
||||
await controller.collabToken(user, workspace, req);
|
||||
|
||||
expect(getCollabToken).toHaveBeenCalledWith(user, 'ws-1', undefined);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -207,8 +207,20 @@ export class AuthController {
|
||||
async collabToken(
|
||||
@AuthUser() user: User,
|
||||
@AuthWorkspace() workspace: Workspace,
|
||||
@Req() req: FastifyRequest,
|
||||
) {
|
||||
return this.authService.getCollabToken(user, workspace.id);
|
||||
// Thread the api-key origin (#501): when the requester authenticated with an
|
||||
// api key (jwt.strategy stamped req.raw.authType/apiKeyId), the minted collab
|
||||
// token carries principal='api_key' + apiKeyId so a later revoke of the key
|
||||
// rejects NEW collab connections. A normal session request mints a
|
||||
// principal='session' token. Reading the SIGNED-derived req.raw fields (never
|
||||
// a client body) keeps it unspoofable.
|
||||
const raw = req.raw as { authType?: string; apiKeyId?: string };
|
||||
const apiKey =
|
||||
raw.authType === 'api_key' && raw.apiKeyId
|
||||
? { apiKeyId: raw.apiKeyId }
|
||||
: undefined;
|
||||
return this.authService.getCollabToken(user, workspace.id, apiKey);
|
||||
}
|
||||
|
||||
@SkipThrottle({ [AUTH_THROTTLER]: true })
|
||||
|
||||
@@ -5,9 +5,13 @@ import { JwtStrategy } from './strategies/jwt.strategy';
|
||||
import { WorkspaceModule } from '../workspace/workspace.module';
|
||||
import { SignupService } from './services/signup.service';
|
||||
import { TokenModule } from './token.module';
|
||||
import { ApiKeyModule } from '../api-key/api-key.module';
|
||||
|
||||
@Module({
|
||||
imports: [TokenModule, WorkspaceModule],
|
||||
// ApiKeyModule supplies ApiKeyService, injected into JwtStrategy so an
|
||||
// api_key Bearer/cookie token is validated directly (replacing the absent EE
|
||||
// `ee/api-key` dynamic require).
|
||||
imports: [TokenModule, WorkspaceModule, ApiKeyModule],
|
||||
controllers: [AuthController],
|
||||
providers: [AuthService, SignupService, JwtStrategy],
|
||||
exports: [SignupService, AuthService],
|
||||
|
||||
@@ -33,6 +33,17 @@ export type JwtPayload = {
|
||||
aiChatId?: string | null;
|
||||
};
|
||||
|
||||
// The AUTH-PRINCIPAL kind behind a collab token — distinct from `actor`
|
||||
// (provenance). Stamped into EVERY newly-minted collab token (#501): 'session'
|
||||
// for a normal user/session (incl. the internal AI agent, which is session-
|
||||
// backed), 'api_key' when the token was minted by an api-key principal (an
|
||||
// external MCP agent). The discriminator keys on the token's ORIGIN, so the
|
||||
// collab seam can re-check a revoked api key on connect and reject a claimless
|
||||
// token after the rollout grace window. NOT keyed on `actor:'agent'` — the
|
||||
// internal agent is 'agent' but session-backed, so it must stay on the no-check
|
||||
// path.
|
||||
export type CollabPrincipal = 'session' | 'api_key';
|
||||
|
||||
export type JwtCollabPayload = {
|
||||
sub: string;
|
||||
workspaceId: string;
|
||||
@@ -44,6 +55,13 @@ export type JwtCollabPayload = {
|
||||
// Nullable: an external MCP agent has no internal ai_chats row, so it carries
|
||||
// an 'agent' actor with a null aiChatId.
|
||||
aiChatId?: string | null;
|
||||
// Auth-principal discriminator (#501). Present on every post-rollout token;
|
||||
// its absence on a still-valid token past the grace window is treated as an
|
||||
// error, not trust (fail-closed).
|
||||
principal?: CollabPrincipal;
|
||||
// Only when principal === 'api_key': the minting key's id, so the collab seam
|
||||
// can row-check (and reject) a revoked key on connect.
|
||||
apiKeyId?: string;
|
||||
};
|
||||
|
||||
export type JwtExchangePayload = {
|
||||
|
||||
@@ -375,10 +375,20 @@ export class AuthService {
|
||||
}
|
||||
}
|
||||
|
||||
async getCollabToken(user: User, workspaceId: string) {
|
||||
async getCollabToken(
|
||||
user: User,
|
||||
workspaceId: string,
|
||||
// Origin of the request minting this collab token (#501). When the caller is
|
||||
// an api-key principal, its apiKeyId is threaded into the token so the collab
|
||||
// seam can re-check the key on connect (closing api-key -> long-lived-collab
|
||||
// laundering). Absent for a normal session/human request.
|
||||
apiKey?: { apiKeyId: string },
|
||||
) {
|
||||
const token = await this.tokenService.generateCollabToken(
|
||||
user,
|
||||
workspaceId,
|
||||
undefined,
|
||||
apiKey,
|
||||
);
|
||||
return { token };
|
||||
}
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { ForbiddenException, UnauthorizedException } from '@nestjs/common';
|
||||
import * as jwt from 'jsonwebtoken';
|
||||
import { TokenService } from './token.service';
|
||||
import { JwtType } from '../dto/jwt-payload';
|
||||
|
||||
@@ -213,4 +214,175 @@ describe('TokenService.generateCollabToken', () => {
|
||||
aiChatId: 'chat-456',
|
||||
});
|
||||
});
|
||||
|
||||
// #501 fail-closed discriminator: EVERY collab token carries a principal.
|
||||
it("defaults principal to 'session' with NO apiKeyId (normal/internal-agent path)", async () => {
|
||||
const { service, jwtService } = makeTokenService();
|
||||
await service.generateCollabToken(makeUser() as never, 'ws-1');
|
||||
const [payload] = jwtService.sign.mock.calls[0];
|
||||
expect(payload.principal).toBe('session');
|
||||
expect(payload).not.toHaveProperty('apiKeyId');
|
||||
});
|
||||
|
||||
it("the internal agent (provenance, NO apiKey) still gets principal='session'", async () => {
|
||||
const { service, jwtService } = makeTokenService();
|
||||
await service.generateCollabToken(
|
||||
makeUser() as never,
|
||||
'ws-1',
|
||||
{ actor: 'agent', aiChatId: 'chat-1' },
|
||||
);
|
||||
const [payload] = jwtService.sign.mock.calls[0];
|
||||
// Keyed on api-key ORIGIN, not actor: an is_agent session token is 'session'.
|
||||
expect(payload.principal).toBe('session');
|
||||
expect(payload).not.toHaveProperty('apiKeyId');
|
||||
});
|
||||
|
||||
it("stamps principal='api_key' + apiKeyId when minted by an api-key principal", async () => {
|
||||
const { service, jwtService } = makeTokenService();
|
||||
await service.generateCollabToken(
|
||||
makeUser() as never,
|
||||
'ws-1',
|
||||
undefined,
|
||||
{ apiKeyId: 'key-9' },
|
||||
);
|
||||
const [payload] = jwtService.sign.mock.calls[0];
|
||||
expect(payload.principal).toBe('api_key');
|
||||
expect(payload.apiKeyId).toBe('key-9');
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* API-key token minting MUST carry NO `exp` claim — the ONLY source of truth for
|
||||
* a key's lifetime/revocation is its `api_keys` row, checked on every request.
|
||||
*
|
||||
* This is a LIVE-bug regression: the shared JwtService is registered with a
|
||||
* global `signOptions.expiresIn` (default '90d') that merges into every sign(),
|
||||
* so an api-key minted through it silently gets exp=now+90d and an "unlimited"
|
||||
* key dies in 90 days. TokenService.generateApiToken mints through a dedicated
|
||||
* no-expiry signer instead. These tests construct the REAL signer (a real secret
|
||||
* via the stubbed EnvironmentService) and decode the produced JWT to assert the
|
||||
* observable property: no `exp`.
|
||||
*/
|
||||
describe('TokenService.generateApiToken (no exp claim ever)', () => {
|
||||
const APP_SECRET_LOCAL = 'apikey-secret';
|
||||
|
||||
function makeRealSignerService() {
|
||||
// Give the SHARED jwtService a global expiresIn so a regression (minting
|
||||
// through it) would show up as an exp claim — the exact live bug.
|
||||
const { JwtService } = require('@nestjs/jwt');
|
||||
const sharedJwt = new JwtService({
|
||||
secret: APP_SECRET_LOCAL,
|
||||
signOptions: { expiresIn: '90d', issuer: 'Docmost' },
|
||||
});
|
||||
const environmentService = {
|
||||
getAppSecret: () => APP_SECRET_LOCAL,
|
||||
};
|
||||
const service = new (TokenService as unknown as new (
|
||||
...args: unknown[]
|
||||
) => TokenService)(sharedJwt, environmentService);
|
||||
return { service };
|
||||
}
|
||||
|
||||
const user = makeUser({ id: 'svc-1', workspaceId: 'ws-1' });
|
||||
|
||||
it('mints an api-key JWT with NO exp claim and issuer Docmost', async () => {
|
||||
const { service } = makeRealSignerService();
|
||||
|
||||
const token = await service.generateApiToken({
|
||||
apiKeyId: 'key-1',
|
||||
user: user as never,
|
||||
workspaceId: 'ws-1',
|
||||
});
|
||||
|
||||
const decoded = jwt.decode(token) as Record<string, unknown>;
|
||||
// The observable security property: no expiry lives in the JWT.
|
||||
expect(decoded.exp).toBeUndefined();
|
||||
expect(decoded).toMatchObject({
|
||||
sub: 'svc-1',
|
||||
apiKeyId: 'key-1',
|
||||
workspaceId: 'ws-1',
|
||||
type: JwtType.API_KEY,
|
||||
iss: 'Docmost',
|
||||
});
|
||||
});
|
||||
|
||||
it('demonstrates the live bug it guards: the SHARED signer WOULD add exp', () => {
|
||||
const { JwtService } = require('@nestjs/jwt');
|
||||
const sharedJwt = new JwtService({
|
||||
secret: APP_SECRET_LOCAL,
|
||||
signOptions: { expiresIn: '90d', issuer: 'Docmost' },
|
||||
});
|
||||
// Even with empty per-call options the global expiresIn merges in.
|
||||
const leaky = sharedJwt.sign({ sub: 'x', type: JwtType.API_KEY }, {});
|
||||
expect((jwt.decode(leaky) as Record<string, unknown>).exp).toBeDefined();
|
||||
});
|
||||
|
||||
it('refuses to mint for a disabled user', async () => {
|
||||
const { service } = makeRealSignerService();
|
||||
await expect(
|
||||
service.generateApiToken({
|
||||
apiKeyId: 'key-1',
|
||||
user: makeUser({ deactivatedAt: new Date() }) as never,
|
||||
workspaceId: 'ws-1',
|
||||
}),
|
||||
).rejects.toBeInstanceOf(ForbiddenException);
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* verifyJwtOneOf is the type-routing primitive: verify the signature once and
|
||||
* assert the token type is on an explicit allowlist. It must NOT degrade into a
|
||||
* "return whatever type" helper — a token whose type is off the allowlist is
|
||||
* rejected with the same generic error as a single-type mismatch.
|
||||
*/
|
||||
describe('TokenService.verifyJwtOneOf (allowlist type-routing)', () => {
|
||||
it('returns the payload when the type is on the allowlist', async () => {
|
||||
const verifyAsync = jest
|
||||
.fn()
|
||||
.mockResolvedValue({ type: JwtType.API_KEY, sub: 'u-1' });
|
||||
const { service } = makeTokenService({ verifyAsync });
|
||||
|
||||
const payload = await service.verifyJwtOneOf(token123(), [
|
||||
JwtType.ACCESS,
|
||||
JwtType.API_KEY,
|
||||
]);
|
||||
|
||||
expect(payload).toMatchObject({ type: JwtType.API_KEY, sub: 'u-1' });
|
||||
expect(verifyAsync).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('accepts the OTHER allowed type too', async () => {
|
||||
const verifyAsync = jest
|
||||
.fn()
|
||||
.mockResolvedValue({ type: JwtType.ACCESS, sub: 'u-1' });
|
||||
const { service } = makeTokenService({ verifyAsync });
|
||||
|
||||
await expect(
|
||||
service.verifyJwtOneOf(token123(), [JwtType.ACCESS, JwtType.API_KEY]),
|
||||
).resolves.toMatchObject({ type: JwtType.ACCESS });
|
||||
});
|
||||
|
||||
it('rejects a token whose type is OFF the allowlist (confused-deputy guard)', async () => {
|
||||
const verifyAsync = jest
|
||||
.fn()
|
||||
.mockResolvedValue({ type: JwtType.COLLAB, sub: 'u-1' });
|
||||
const { service } = makeTokenService({ verifyAsync });
|
||||
|
||||
await expect(
|
||||
service.verifyJwtOneOf(token123(), [JwtType.ACCESS, JwtType.API_KEY]),
|
||||
).rejects.toBeInstanceOf(UnauthorizedException);
|
||||
});
|
||||
|
||||
it('verifies the signature exactly ONCE', async () => {
|
||||
const verifyAsync = jest
|
||||
.fn()
|
||||
.mockResolvedValue({ type: JwtType.ACCESS });
|
||||
const { service } = makeTokenService({ verifyAsync });
|
||||
await service.verifyJwtOneOf(token123(), [JwtType.ACCESS]);
|
||||
expect(verifyAsync).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
});
|
||||
|
||||
function token123(): string {
|
||||
return 'a.b.c';
|
||||
}
|
||||
|
||||
@@ -4,7 +4,6 @@ import {
|
||||
UnauthorizedException,
|
||||
} from '@nestjs/common';
|
||||
import { JwtService } from '@nestjs/jwt';
|
||||
import type { StringValue } from 'ms';
|
||||
import { EnvironmentService } from '../../../integrations/environment/environment.service';
|
||||
import {
|
||||
JwtApiKeyPayload,
|
||||
@@ -62,6 +61,12 @@ export class TokenService {
|
||||
// token carries no actor/aiChatId and is treated as 'user' downstream.
|
||||
// aiChatId is nullable for an external agent with no internal ai_chats row.
|
||||
provenance?: { actor: 'agent'; aiChatId: string | null },
|
||||
// Optional api-key origin (#501). When the collab token is minted by an
|
||||
// api-key principal (an external MCP agent), the caller passes the key id so
|
||||
// the token carries principal='api_key' + apiKeyId and the collab seam can
|
||||
// re-check the key on connect. Absent -> principal='session' (a normal
|
||||
// user/session, including the internal session-backed AI agent).
|
||||
apiKey?: { apiKeyId: string },
|
||||
): Promise<string> {
|
||||
if (isUserDisabled(user)) {
|
||||
throw new ForbiddenException();
|
||||
@@ -71,6 +76,10 @@ export class TokenService {
|
||||
sub: user.id,
|
||||
workspaceId,
|
||||
type: JwtType.COLLAB,
|
||||
// Fail-closed discriminator on EVERY minted token: 'api_key' when minted by
|
||||
// an api-key principal, else 'session'.
|
||||
principal: apiKey ? 'api_key' : 'session',
|
||||
...(apiKey ? { apiKeyId: apiKey.apiKeyId } : {}),
|
||||
...(provenance
|
||||
? { actor: provenance.actor, aiChatId: provenance.aiChatId }
|
||||
: {}),
|
||||
@@ -123,9 +132,8 @@ export class TokenService {
|
||||
apiKeyId: string;
|
||||
user: User;
|
||||
workspaceId: string;
|
||||
expiresIn?: StringValue | number;
|
||||
}): Promise<string> {
|
||||
const { apiKeyId, user, workspaceId, expiresIn } = opts;
|
||||
const { apiKeyId, user, workspaceId } = opts;
|
||||
if (isUserDisabled(user)) {
|
||||
throw new ForbiddenException();
|
||||
}
|
||||
@@ -137,7 +145,32 @@ export class TokenService {
|
||||
type: JwtType.API_KEY,
|
||||
};
|
||||
|
||||
return this.jwtService.sign(payload, expiresIn ? { expiresIn } : {});
|
||||
// API-key tokens carry NO `exp` claim EVER — the ONLY source of truth for a
|
||||
// key's lifetime and revocation is its `api_keys` row (checked on every
|
||||
// request), not the JWT. This CANNOT use `this.jwtService`: TokenModule
|
||||
// registers it with a global `signOptions.expiresIn` (JWT_TOKEN_EXPIRES_IN,
|
||||
// default '90d'), which merges into EVERY sign() call — even `sign(payload,
|
||||
// {})` — and `{ expiresIn: undefined }` THROWS rather than stripping it
|
||||
// (verified empirically). So an "unlimited" key minted through the shared
|
||||
// signer would silently get exp=now+90d and die in 90 days regardless of its
|
||||
// row. We mint through a dedicated no-expiry signer, re-stamping only
|
||||
// `issuer: 'Docmost'` for claim parity with the shared signer.
|
||||
return this.apiKeyJwtService().sign(payload);
|
||||
}
|
||||
|
||||
// Lazily-built JWT signer for API-key tokens: same APP_SECRET, same 'Docmost'
|
||||
// issuer, but WITHOUT the global `expiresIn` — so minted API-key tokens have no
|
||||
// `exp` claim. Built once and cached. Verification still goes through the
|
||||
// shared verifier (same secret); `verifyAsync` does not require an `exp`.
|
||||
private _apiKeyJwtService?: JwtService;
|
||||
private apiKeyJwtService(): JwtService {
|
||||
if (!this._apiKeyJwtService) {
|
||||
this._apiKeyJwtService = new JwtService({
|
||||
secret: this.environmentService.getAppSecret(),
|
||||
signOptions: { issuer: 'Docmost' },
|
||||
});
|
||||
}
|
||||
return this._apiKeyJwtService;
|
||||
}
|
||||
|
||||
async generatePdfRenderToken(
|
||||
@@ -177,4 +210,31 @@ export class TokenService {
|
||||
|
||||
return payload;
|
||||
}
|
||||
|
||||
/**
|
||||
* Verify a token's signature ONCE and assert its `type` is one of `allowed`.
|
||||
*
|
||||
* This is the type-routing primitive for surfaces that legitimately accept
|
||||
* more than one token type on the same Bearer slot (the /mcp Bearer path
|
||||
* accepts both an ACCESS and an API_KEY token). It is deliberately NOT a
|
||||
* "verify-and-return-whatever-type" helper — that would be a reusable
|
||||
* confused-deputy footgun (any caller could then feed an attachment/collab
|
||||
* token where an access token is expected). An explicit allowlist preserves
|
||||
* the type-pinning property of `verifyJwt`: a token whose `type` is not in the
|
||||
* allowlist is rejected with the SAME generic error as a type mismatch, and
|
||||
* the signature is verified exactly once (no double-verify).
|
||||
*/
|
||||
async verifyJwtOneOf(token: string, allowed: JwtType[]) {
|
||||
const payload = await this.jwtService.verifyAsync(token, {
|
||||
secret: this.environmentService.getAppSecret(),
|
||||
});
|
||||
|
||||
if (!allowed.includes(payload.type)) {
|
||||
throw new UnauthorizedException(
|
||||
'Invalid JWT token. Token type does not match.',
|
||||
);
|
||||
}
|
||||
|
||||
return payload;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -22,7 +22,8 @@ describe('JwtStrategy — provenance derivation', () => {
|
||||
const userSessionRepo: any = { findActiveById: jest.fn() };
|
||||
const sessionActivityService: any = { trackActivity: jest.fn() };
|
||||
const environmentService: any = { getAppSecret: () => 'test-secret' };
|
||||
const moduleRef: any = {};
|
||||
// ACCESS-path tests never touch the api-key seam; a bare stub suffices.
|
||||
const apiKeyService: any = { validate: jest.fn() };
|
||||
|
||||
const strategy = new JwtStrategy(
|
||||
userRepo,
|
||||
@@ -30,7 +31,7 @@ describe('JwtStrategy — provenance derivation', () => {
|
||||
userSessionRepo,
|
||||
sessionActivityService,
|
||||
environmentService,
|
||||
moduleRef,
|
||||
apiKeyService,
|
||||
);
|
||||
return { strategy, userRepo };
|
||||
}
|
||||
@@ -122,25 +123,29 @@ describe('JwtStrategy — provenance derivation', () => {
|
||||
});
|
||||
|
||||
/**
|
||||
* Provenance derivation on the API-KEY path (jwt.strategy.validateApiKey, #486).
|
||||
* Provenance derivation on the API-KEY path (jwt.strategy.validateApiKey, #486
|
||||
* + #501).
|
||||
*
|
||||
* The access-token path stamped provenance; the API-key path returned early
|
||||
* WITHOUT it, so an is_agent API key's REST writes recorded no 'agent' marker.
|
||||
* The API-key payload carries no signed claim, so provenance is resolved from the
|
||||
* SERVER-SIDE user returned by ApiKeyService.validateApiKey: isAgent -> 'agent',
|
||||
* SERVER-SIDE user returned by ApiKeyService.validate: isAgent -> 'agent',
|
||||
* otherwise 'user'; aiChatId is always null (an API key has no ai_chats row).
|
||||
*
|
||||
* The enterprise ApiKeyService is not bundled in the OSS build, so the strategy
|
||||
* loads it through an overridable `resolveApiKeyService` seam that we stub here.
|
||||
* #501 wires the CORE ApiKeyService (the EE `ee/api-key` module is absent in the
|
||||
* fork) directly into the strategy — no dynamic require. The strategy also stamps
|
||||
* `req.raw.authType='api_key'` + `req.raw.apiKeyId` for the "a token cannot manage
|
||||
* tokens" guard on the /api-keys surface.
|
||||
*/
|
||||
describe('JwtStrategy — API-key provenance derivation (#486)', () => {
|
||||
function makeApiKeyStrategy(validateApiKeyImpl: (p: any) => Promise<any>) {
|
||||
describe('JwtStrategy — API-key provenance derivation (#486/#501)', () => {
|
||||
function makeApiKeyStrategy(validateImpl: (p: any) => Promise<any>) {
|
||||
const userRepo: any = { findById: jest.fn() };
|
||||
const workspaceRepo: any = { findById: jest.fn() };
|
||||
const userSessionRepo: any = { findActiveById: jest.fn() };
|
||||
const sessionActivityService: any = { trackActivity: jest.fn() };
|
||||
const environmentService: any = { getAppSecret: () => 'test-secret' };
|
||||
const moduleRef: any = {};
|
||||
const validate = jest.fn(validateImpl);
|
||||
const apiKeyService: any = { validate };
|
||||
|
||||
const strategy = new JwtStrategy(
|
||||
userRepo,
|
||||
@@ -148,14 +153,9 @@ describe('JwtStrategy — API-key provenance derivation (#486)', () => {
|
||||
userSessionRepo,
|
||||
sessionActivityService,
|
||||
environmentService,
|
||||
moduleRef,
|
||||
apiKeyService,
|
||||
);
|
||||
// Stub the EE ApiKeyService seam (the real module is not in the OSS build).
|
||||
const validateApiKey = jest.fn(validateApiKeyImpl);
|
||||
jest
|
||||
.spyOn(strategy as any, 'resolveApiKeyService')
|
||||
.mockReturnValue({ validateApiKey });
|
||||
return { strategy, validateApiKey };
|
||||
return { strategy, validate };
|
||||
}
|
||||
|
||||
const makeReq = () => ({ raw: {} as Record<string, any> });
|
||||
@@ -166,22 +166,23 @@ describe('JwtStrategy — API-key provenance derivation (#486)', () => {
|
||||
type: JwtType.API_KEY,
|
||||
});
|
||||
|
||||
it("stamps actor='agent' for an is_agent API key (from the validated user)", async () => {
|
||||
it("stamps actor='agent' + authType/apiKeyId for an is_agent API key", async () => {
|
||||
const validated = {
|
||||
user: { id: 'svc-1', isAgent: true },
|
||||
workspace: { id: 'ws-1' },
|
||||
};
|
||||
const { strategy, validateApiKey } = makeApiKeyStrategy(
|
||||
async () => validated,
|
||||
);
|
||||
const { strategy, validate } = makeApiKeyStrategy(async () => validated);
|
||||
const req = makeReq();
|
||||
|
||||
const result = await strategy.validate(req, apiKeyPayload() as any);
|
||||
|
||||
expect(validateApiKey).toHaveBeenCalledTimes(1);
|
||||
expect(validate).toHaveBeenCalledTimes(1);
|
||||
expect(req.raw.actor).toBe('agent');
|
||||
// API keys carry no internal ai_chats row -> null.
|
||||
expect(req.raw.aiChatId).toBeNull();
|
||||
// Principal-kind markers for the management-surface guard.
|
||||
expect(req.raw.authType).toBe('api_key');
|
||||
expect(req.raw.apiKeyId).toBe('key-1');
|
||||
// The validated auth object is returned unchanged (req.user shape preserved).
|
||||
expect(result).toBe(validated);
|
||||
});
|
||||
@@ -197,25 +198,19 @@ describe('JwtStrategy — API-key provenance derivation (#486)', () => {
|
||||
|
||||
expect(req.raw.actor).toBe('user');
|
||||
expect(req.raw.aiChatId).toBeNull();
|
||||
expect(req.raw.authType).toBe('api_key');
|
||||
});
|
||||
|
||||
it('throws Unauthorized (and stamps nothing) when the EE module is missing', async () => {
|
||||
const userRepo: any = { findById: jest.fn() };
|
||||
const strategy = new JwtStrategy(
|
||||
userRepo,
|
||||
{ findById: jest.fn() } as any,
|
||||
{ findActiveById: jest.fn() } as any,
|
||||
{ trackActivity: jest.fn() } as any,
|
||||
{ getAppSecret: () => 'test-secret' } as any,
|
||||
{} as any,
|
||||
);
|
||||
// EE not bundled: the seam returns null.
|
||||
jest.spyOn(strategy as any, 'resolveApiKeyService').mockReturnValue(null);
|
||||
it('propagates a validate() rejection and stamps nothing', async () => {
|
||||
const { strategy } = makeApiKeyStrategy(async () => {
|
||||
throw new UnauthorizedException();
|
||||
});
|
||||
const req = makeReq();
|
||||
|
||||
await expect(
|
||||
strategy.validate(req, apiKeyPayload() as any),
|
||||
).rejects.toThrow(UnauthorizedException);
|
||||
expect(req.raw.actor).toBeUndefined();
|
||||
expect(req.raw.authType).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { Injectable, Logger, UnauthorizedException } from '@nestjs/common';
|
||||
import { Injectable, UnauthorizedException } from '@nestjs/common';
|
||||
import { PassportStrategy } from '@nestjs/passport';
|
||||
import { Strategy } from 'passport-jwt';
|
||||
import { EnvironmentService } from '../../../integrations/environment/environment.service';
|
||||
@@ -9,20 +9,18 @@ import { UserSessionRepo } from '@docmost/db/repos/session/user-session.repo';
|
||||
import { SessionActivityService } from '../../session/session-activity.service';
|
||||
import { FastifyRequest } from 'fastify';
|
||||
import { extractBearerTokenFromHeader, isUserDisabled } from '../../../common/helpers';
|
||||
import { ModuleRef } from '@nestjs/core';
|
||||
import { resolveProvenance } from '../../../common/decorators/auth-provenance.decorator';
|
||||
import { ApiKeyService } from '../../api-key/api-key.service';
|
||||
|
||||
@Injectable()
|
||||
export class JwtStrategy extends PassportStrategy(Strategy, 'jwt') {
|
||||
private logger = new Logger('JwtStrategy');
|
||||
|
||||
constructor(
|
||||
private userRepo: UserRepo,
|
||||
private workspaceRepo: WorkspaceRepo,
|
||||
private userSessionRepo: UserSessionRepo,
|
||||
private sessionActivityService: SessionActivityService,
|
||||
private readonly environmentService: EnvironmentService,
|
||||
private moduleRef: ModuleRef,
|
||||
private readonly apiKeyService: ApiKeyService,
|
||||
) {
|
||||
super({
|
||||
jwtFromRequest: (req: FastifyRequest) => {
|
||||
@@ -102,12 +100,17 @@ export class JwtStrategy extends PassportStrategy(Strategy, 'jwt') {
|
||||
}
|
||||
|
||||
private async validateApiKey(req: any, payload: JwtApiKeyPayload) {
|
||||
const apiKeyService = this.resolveApiKeyService();
|
||||
if (!apiKeyService) {
|
||||
throw new UnauthorizedException('Enterprise API Key module missing');
|
||||
}
|
||||
// The fork ships the core `ApiKeyService` (the EE `ee/api-key` module is
|
||||
// absent). `validate` throws a bare UnauthorizedException on any definite
|
||||
// deny (missing/revoked/expired row, disabled user, kill-switch off) and
|
||||
// propagates infra errors (→ 5xx) rather than masking them as a 401.
|
||||
const result = await this.apiKeyService.validate(payload);
|
||||
|
||||
const result = await apiKeyService.validateApiKey(payload);
|
||||
// Stamp the principal kind + key id so the /api-keys management surface can
|
||||
// enforce "a token cannot manage tokens". Done in this branch because it
|
||||
// returns before the shared ACCESS-path stamping below.
|
||||
req.raw.authType = 'api_key';
|
||||
req.raw.apiKeyId = payload.apiKeyId;
|
||||
|
||||
// Stamp the agent-edit provenance for the API-KEY path too (#486). Unlike the
|
||||
// access-token path above, it CANNOT be resolved before this point: the
|
||||
@@ -119,32 +122,10 @@ export class JwtStrategy extends PassportStrategy(Strategy, 'jwt') {
|
||||
// SERVER-SIDE user (never a client field), so an 'agent' badge is unspoofable
|
||||
// — mirroring the access-token path. Passing `null` for the claim means the
|
||||
// actor is decided solely by user.isAgent.
|
||||
const provenance = resolveProvenance((result as any)?.user, null);
|
||||
const provenance = resolveProvenance(result.user, null);
|
||||
req.raw.actor = provenance.actor;
|
||||
req.raw.aiChatId = provenance.aiChatId;
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the enterprise ApiKeyService, or `null` when the EE module is not
|
||||
* bundled in this build (community build). Extracted as an overridable seam so
|
||||
* the API-key provenance stamping can be unit-tested without the EE package
|
||||
* present (docmost is OSS + a separate EE bundle; `require` of the EE path
|
||||
* throws here). Any load/resolve error is treated as "module missing".
|
||||
*/
|
||||
protected resolveApiKeyService(): {
|
||||
validateApiKey: (payload: JwtApiKeyPayload) => Promise<unknown>;
|
||||
} | null {
|
||||
try {
|
||||
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
||||
const ApiKeyModule = require('./../../../ee/api-key/api-key.service');
|
||||
return this.moduleRef.get(ApiKeyModule.ApiKeyService, { strict: false });
|
||||
} catch (err) {
|
||||
this.logger.debug(
|
||||
'API Key module requested but enterprise module not bundled in this build',
|
||||
);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@ import {
|
||||
} from '@nestjs/common';
|
||||
import { UserModule } from './user/user.module';
|
||||
import { AuthModule } from './auth/auth.module';
|
||||
import { ApiKeyModule } from './api-key/api-key.module';
|
||||
import { WorkspaceModule } from './workspace/workspace.module';
|
||||
import { PageModule } from './page/page.module';
|
||||
import { AttachmentModule } from './attachment/attachment.module';
|
||||
@@ -29,6 +30,7 @@ import { ClsMiddleware } from 'nestjs-cls';
|
||||
imports: [
|
||||
UserModule,
|
||||
AuthModule,
|
||||
ApiKeyModule,
|
||||
WorkspaceModule,
|
||||
PageModule,
|
||||
AttachmentModule,
|
||||
|
||||
@@ -38,6 +38,7 @@ import { AiProviderCredentialsRepo } from '@docmost/db/repos/ai-chat/ai-provider
|
||||
import { AiMcpServerRepo } from '@docmost/db/repos/ai-chat/ai-mcp-server.repo';
|
||||
import { AiAgentRoleRepo } from '@docmost/db/repos/ai-agent-roles/ai-agent-roles.repo';
|
||||
import { PageEmbeddingRepo } from '@docmost/db/repos/ai-chat/page-embedding.repo';
|
||||
import { ApiKeyRepo } from '@docmost/db/repos/api-key/api-key.repo';
|
||||
import { PageListener } from '@docmost/db/listeners/page.listener';
|
||||
import { PostgresJSDialect } from 'kysely-postgres-js';
|
||||
import * as postgres from 'postgres';
|
||||
@@ -131,6 +132,7 @@ import { firstSqlToken } from '../integrations/metrics/metrics.constants';
|
||||
AiMcpServerRepo,
|
||||
AiAgentRoleRepo,
|
||||
PageEmbeddingRepo,
|
||||
ApiKeyRepo,
|
||||
PageListener,
|
||||
],
|
||||
exports: [
|
||||
@@ -167,6 +169,7 @@ import { firstSqlToken } from '../integrations/metrics/metrics.constants';
|
||||
AiMcpServerRepo,
|
||||
AiAgentRoleRepo,
|
||||
PageEmbeddingRepo,
|
||||
ApiKeyRepo,
|
||||
],
|
||||
})
|
||||
export class DatabaseModule implements OnApplicationBootstrap {
|
||||
|
||||
@@ -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();
|
||||
}
|
||||
@@ -0,0 +1,110 @@
|
||||
import { Injectable } from '@nestjs/common';
|
||||
import { InjectKysely } from 'nestjs-kysely';
|
||||
import { KyselyDB, KyselyTransaction } from '@docmost/db/types/kysely.types';
|
||||
import { DB, Users } from '@docmost/db/types/db';
|
||||
import { dbOrTx } from '@docmost/db/utils';
|
||||
import { ApiKey, InsertableApiKey } from '@docmost/db/types/entity.types';
|
||||
import { jsonObjectFrom } from 'kysely/helpers/postgres';
|
||||
import { ExpressionBuilder } from 'kysely';
|
||||
|
||||
// Public-facing shape: the api_keys row plus a compact creator attribution used
|
||||
// by the admin list (the workspace-wide view attributes each key to its author).
|
||||
export type ApiKeyWithCreator = ApiKey & {
|
||||
creator: Pick<Users, 'id' | 'name' | 'email' | 'avatarUrl'> | null;
|
||||
};
|
||||
|
||||
@Injectable()
|
||||
export class ApiKeyRepo {
|
||||
constructor(@InjectKysely() private readonly db: KyselyDB) {}
|
||||
|
||||
// Compact creator attribution embedded in the admin list rows. A nested
|
||||
// subquery (jsonObjectFrom) keeps it one round-trip; the token material is
|
||||
// never stored, so nothing sensitive is joined in.
|
||||
private withCreator(eb: ExpressionBuilder<DB, 'apiKeys'>) {
|
||||
return jsonObjectFrom(
|
||||
eb
|
||||
.selectFrom('users')
|
||||
.select(['users.id', 'users.name', 'users.email', 'users.avatarUrl'])
|
||||
.whereRef('users.id', '=', 'apiKeys.creatorId'),
|
||||
).as('creator');
|
||||
}
|
||||
|
||||
async findById(
|
||||
id: string,
|
||||
workspaceId: string,
|
||||
trx?: KyselyTransaction,
|
||||
): Promise<ApiKey | undefined> {
|
||||
const db = dbOrTx(this.db, trx);
|
||||
return db
|
||||
.selectFrom('apiKeys')
|
||||
.selectAll()
|
||||
.where('id', '=', id)
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
// Convention (soft-delete): a revoked key is invisible to reads.
|
||||
.where('deletedAt', 'is', null)
|
||||
.executeTakeFirst();
|
||||
}
|
||||
|
||||
async findByCreator(
|
||||
creatorId: string,
|
||||
workspaceId: string,
|
||||
): Promise<ApiKeyWithCreator[]> {
|
||||
return this.db
|
||||
.selectFrom('apiKeys')
|
||||
.selectAll('apiKeys')
|
||||
.select((eb) => this.withCreator(eb))
|
||||
.where('creatorId', '=', creatorId)
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
.where('deletedAt', 'is', null)
|
||||
.orderBy('createdAt', 'desc')
|
||||
.execute() as unknown as Promise<ApiKeyWithCreator[]>;
|
||||
}
|
||||
|
||||
async findAllInWorkspace(
|
||||
workspaceId: string,
|
||||
): Promise<ApiKeyWithCreator[]> {
|
||||
return this.db
|
||||
.selectFrom('apiKeys')
|
||||
.selectAll('apiKeys')
|
||||
.select((eb) => this.withCreator(eb))
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
.where('deletedAt', 'is', null)
|
||||
.orderBy('createdAt', 'desc')
|
||||
.execute() as unknown as Promise<ApiKeyWithCreator[]>;
|
||||
}
|
||||
|
||||
async insert(
|
||||
insertable: InsertableApiKey,
|
||||
trx?: KyselyTransaction,
|
||||
): Promise<ApiKey> {
|
||||
const db = dbOrTx(this.db, trx);
|
||||
return db
|
||||
.insertInto('apiKeys')
|
||||
.values(insertable)
|
||||
.returningAll()
|
||||
.executeTakeFirst();
|
||||
}
|
||||
|
||||
// Soft-delete = revoke. Terminal: the row stays for forensics but is invisible
|
||||
// to every read above, so validate() denies it immediately (no grace window).
|
||||
async softDelete(id: string, workspaceId: string): Promise<void> {
|
||||
await this.db
|
||||
.updateTable('apiKeys')
|
||||
.set({ deletedAt: new Date(), updatedAt: new Date() })
|
||||
.where('id', '=', id)
|
||||
.where('workspaceId', '=', workspaceId)
|
||||
.where('deletedAt', 'is', null)
|
||||
.execute();
|
||||
}
|
||||
|
||||
// Throttled best-effort forensics stamp. Not on the critical path: callers
|
||||
// fire-and-forget and swallow errors, so it never fails a request.
|
||||
async touchLastUsed(id: string): Promise<void> {
|
||||
await this.db
|
||||
.updateTable('apiKeys')
|
||||
.set({ lastUsedAt: new Date() })
|
||||
.where('id', '=', id)
|
||||
.where('deletedAt', 'is', null)
|
||||
.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
@@ -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;
|
||||
|
||||
@@ -70,6 +70,23 @@ export class EnvironmentService {
|
||||
return this.configService.get<string>('JWT_TOKEN_EXPIRES_IN', '90d');
|
||||
}
|
||||
|
||||
// Kill-switch for the agent API-key feature. Default ON (unset -> enabled): a
|
||||
// deploy that never sets the variable must NOT silently kill every agent. The
|
||||
// parse is STRICT — the value is validated by environment.validation to be
|
||||
// exactly 'true' or 'false' (or absent), so a typo like `=0`/`=off`/`=False`
|
||||
// fails at boot rather than being read as "enabled" (which would leave an
|
||||
// operator who yanked the switch during an incident with it still on). When
|
||||
// OFF: validate() denies every api-key token and the issuance endpoints 404.
|
||||
isApiKeysEnabled(): boolean {
|
||||
return this.configService.get<string>('API_KEYS_ENABLED', 'true') !== 'false';
|
||||
}
|
||||
|
||||
// Raw value (or undefined) for the boot log, so the state after each deploy is
|
||||
// verifiable in container logs: `API keys: ENABLED/DISABLED (API_KEYS_ENABLED=...)`.
|
||||
getApiKeysEnabledRaw(): string | undefined {
|
||||
return this.configService.get<string>('API_KEYS_ENABLED');
|
||||
}
|
||||
|
||||
getCookieExpiresIn(): Date {
|
||||
const expiresInStr = this.getJwtTokenExpiresIn();
|
||||
let msUntilExpiry: number;
|
||||
|
||||
@@ -103,6 +103,15 @@ export class EnvironmentVariables {
|
||||
@IsString()
|
||||
TYPESENSE_LOCALE: string;
|
||||
|
||||
// Agent API-key kill-switch. Optional (absent -> default ON). STRICT: only the
|
||||
// literals 'true'/'false' are accepted, so `=0`/`=off`/`=False` fail at boot
|
||||
// instead of being silently read as "enabled" — the switch must actually flip
|
||||
// when an operator flips it. See EnvironmentService.isApiKeysEnabled.
|
||||
@IsOptional()
|
||||
@IsIn(['true', 'false'])
|
||||
@IsString()
|
||||
API_KEYS_ENABLED: string;
|
||||
|
||||
@IsOptional()
|
||||
@ValidateIf((obj) => obj.AI_DRIVER)
|
||||
@IsIn(['openai', 'openai-compatible', 'gemini', 'ollama'])
|
||||
|
||||
+131
@@ -0,0 +1,131 @@
|
||||
// p-limit and @sindresorhus/slugify are ESM-only and not in jest's transform
|
||||
// allowlist; both are irrelevant to createDrawioSvg (a pure fs + string method),
|
||||
// so they are mocked out to keep the module graph loadable under ts-jest.
|
||||
jest.mock('p-limit', () => ({
|
||||
__esModule: true,
|
||||
default: () => (fn: () => unknown) => fn(),
|
||||
}));
|
||||
jest.mock('@sindresorhus/slugify', () => ({
|
||||
__esModule: true,
|
||||
default: (input: string) => String(input),
|
||||
}));
|
||||
|
||||
import { promises as fs } from 'fs';
|
||||
import * as os from 'os';
|
||||
import * as path from 'path';
|
||||
import { ImportAttachmentService } from './import-attachment.service';
|
||||
|
||||
/**
|
||||
* Unit test for ImportAttachmentService.createDrawioSvg (issue #507).
|
||||
*
|
||||
* The Confluence import wraps a `.drawio` file into a `.drawio.svg` attachment.
|
||||
* The `content=` payload MUST be the mxfile XML entity-escaped (draw.io's native
|
||||
* form), NOT base64 — draw.io's editor decodes a base64 content= via Latin-1
|
||||
* atob, mangling every non-ASCII char into mojibake. createDrawioSvg touches no
|
||||
* injected dependency, so the service is built with placeholder deps.
|
||||
*/
|
||||
describe('ImportAttachmentService.createDrawioSvg (#507)', () => {
|
||||
const service = new ImportAttachmentService(
|
||||
{} as any,
|
||||
{} as any,
|
||||
{} as any,
|
||||
);
|
||||
const call = (p: string): Promise<Buffer> =>
|
||||
(service as any).createDrawioSvg(p);
|
||||
|
||||
let tmpDir: string;
|
||||
beforeAll(async () => {
|
||||
tmpDir = await fs.mkdtemp(path.join(os.tmpdir(), 'drawio-507-'));
|
||||
});
|
||||
afterAll(async () => {
|
||||
await fs.rm(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
const writeDrawio = async (name: string, xml: string): Promise<string> => {
|
||||
const p = path.join(tmpDir, name);
|
||||
await fs.writeFile(p, xml, 'utf-8');
|
||||
return p;
|
||||
};
|
||||
|
||||
it('writes content= as entity-encoded XML, not base64', async () => {
|
||||
const drawio =
|
||||
'<mxfile host="Confluence"><diagram name="Схема — ёж">' +
|
||||
'<mxGraphModel><root><mxCell id="0"/>' +
|
||||
'<mxCell id="2" value="Старт-бит" vertex="1" parent="0"/>' +
|
||||
'</root></mxGraphModel></diagram></mxfile>';
|
||||
const p = await writeDrawio('cyrillic.drawio', drawio);
|
||||
|
||||
const svg = (await call(p)).toString('utf-8');
|
||||
const content = /content="([^"]*)"/.exec(svg)?.[1];
|
||||
expect(content).toBeDefined();
|
||||
|
||||
// Entity-encoded XML form, starting with <mxfile — never a base64 blob.
|
||||
expect(content).toMatch(/^<mxfile/);
|
||||
expect(content).toContain('<');
|
||||
// Non-ASCII survives as raw UTF-8, with no Latin-1 mojibake.
|
||||
expect(content).toContain('Старт-бит');
|
||||
expect(content).toContain('Схема — ёж');
|
||||
expect(content).not.toContain('Ð');
|
||||
|
||||
// Decoding the attribute (un-escaping) yields the original drawio file.
|
||||
const decoded = content!
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/&/g, '&');
|
||||
expect(decoded).toBe(drawio);
|
||||
});
|
||||
|
||||
it('encodes literal tab/newline/CR as numeric char-refs, not literal control chars (#507 F1)', async () => {
|
||||
// A literal tab/newline/CR inside the mxfile XML would be collapsed to a
|
||||
// single space by XML attribute-value normalization when the draw.io editor
|
||||
// reads content=, silently flattening multi-line labels and tab-bearing
|
||||
// values. They must be emitted as numeric char-refs instead.
|
||||
const drawio =
|
||||
'<mxfile><diagram name="p">' +
|
||||
'<mxGraphModel><root><mxCell id="0"/>' +
|
||||
'<mxCell id="2" value="col1\tcol2" style="html=1;\nshadow=0" vertex="1" parent="0"/>' +
|
||||
'<mxCell id="3" value="Line1\nLine2\rLine3" vertex="1" parent="0"/>' +
|
||||
'</root></mxGraphModel></diagram></mxfile>';
|
||||
const p = await writeDrawio('ctrl.drawio', drawio);
|
||||
|
||||
const svg = (await call(p)).toString('utf-8');
|
||||
const content = /content="([^"]*)"/.exec(svg)?.[1];
|
||||
expect(content).toBeDefined();
|
||||
// No literal control chars survive in the attribute value.
|
||||
expect(content).not.toMatch(/[\t\n\r]/);
|
||||
// They round-trip as numeric char-refs.
|
||||
expect(content).toContain('	');
|
||||
expect(content).toContain('
');
|
||||
expect(content).toContain('
');
|
||||
// Decoding (char-refs back to literal, entities back) recovers the file.
|
||||
const decoded = content!
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, "'")
|
||||
.replace(/	/gi, '\t')
|
||||
.replace(/
/gi, '\n')
|
||||
.replace(/
/gi, '\r')
|
||||
.replace(/&/g, '&');
|
||||
expect(decoded).toBe(drawio);
|
||||
});
|
||||
|
||||
it('escapes XML metacharacters in the drawio payload', async () => {
|
||||
const drawio = '<mxfile><diagram name="a & b">"q" <x></diagram></mxfile>';
|
||||
const p = await writeDrawio('meta.drawio', drawio);
|
||||
|
||||
const svg = (await call(p)).toString('utf-8');
|
||||
const content = /content="([^"]*)"/.exec(svg)?.[1];
|
||||
expect(content).toBeDefined();
|
||||
// The attribute value must contain no bare `<`, `>` or `"` that would break
|
||||
// out of the content="..." attribute or the SVG element.
|
||||
expect(content).not.toMatch(/[<>"]/);
|
||||
const decoded = content!
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/&/g, '&');
|
||||
expect(decoded).toBe(drawio);
|
||||
});
|
||||
});
|
||||
@@ -8,6 +8,7 @@ import { createReadStream } from 'node:fs';
|
||||
import { promises as fs } from 'fs';
|
||||
import { Readable } from 'stream';
|
||||
import { getMimeType, sanitizeFileName } from '../../../common/helpers';
|
||||
import { htmlEscape } from '../../../common/helpers/html-escaper';
|
||||
import { v7 } from 'uuid';
|
||||
import { FileTask } from '@docmost/db/types/entity.types';
|
||||
import { getAttachmentFolderPath } from '../../../core/attachment/attachment.utils';
|
||||
@@ -849,7 +850,12 @@ export class ImportAttachmentService {
|
||||
): Promise<Buffer> {
|
||||
try {
|
||||
const drawioContent = await fs.readFile(drawioPath, 'utf-8');
|
||||
const drawioBase64 = Buffer.from(drawioContent).toString('base64');
|
||||
// Write the mxfile XML XML-entity-escaped (draw.io's native content= form),
|
||||
// NOT base64. draw.io's editor decodes a base64 content= via Latin-1 atob
|
||||
// (no UTF-8 step), turning every non-ASCII char (Cyrillic, ё, —) into
|
||||
// mojibake; the entity-encoded form is decoded by the DOM as UTF-8 and
|
||||
// opens intact. Docmost's own decoder reads both forms.
|
||||
const drawioEscaped = this.xmlEscapeContent(drawioContent);
|
||||
|
||||
let imageElement = '';
|
||||
// If we have a PNG, include it in the SVG
|
||||
@@ -875,7 +881,7 @@ export class ImportAttachmentService {
|
||||
width="600"
|
||||
height="400"
|
||||
viewBox="0 0 600 400"
|
||||
content="${drawioBase64}">${imageElement}</svg>`;
|
||||
content="${drawioEscaped}">${imageElement}</svg>`;
|
||||
|
||||
return Buffer.from(svgContent, 'utf-8');
|
||||
} catch (error) {
|
||||
@@ -884,6 +890,24 @@ export class ImportAttachmentService {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Escape a string so it is safe as the value of a double-quoted XML attribute
|
||||
* (the `content=` payload of a `.drawio.svg`). The shared `htmlEscape` covers
|
||||
* `& < > " '` (a strict superset of what this attribute needs; the extra `'`
|
||||
* escape is harmless in a `"`-delimited value). On top of that, the numeric
|
||||
* char-refs for tab/newline/CR are required: a literal tab/newline/CR inside
|
||||
* an attribute value is collapsed to a single space by XML attribute-value
|
||||
* normalization on DOM read (both our decoder and the real draw.io editor),
|
||||
* silently flattening multi-line labels and tab-bearing values. Char-refs
|
||||
* survive that normalization (#507).
|
||||
*/
|
||||
private xmlEscapeContent(s: string): string {
|
||||
return htmlEscape(s)
|
||||
.replace(/\t/g, '	')
|
||||
.replace(/\n/g, '
')
|
||||
.replace(/\r/g, '
');
|
||||
}
|
||||
|
||||
private async uploadWithRetry(opts: {
|
||||
abs: string;
|
||||
storageFilePath: string;
|
||||
|
||||
@@ -304,37 +304,102 @@ export function clientIp(req: ClientIpRequest): string {
|
||||
return 'unknown';
|
||||
}
|
||||
|
||||
// Minimal structural shape of the TokenService.verifyJwt method we depend on,
|
||||
// so this module never imports the concrete TokenService (heavy graph).
|
||||
export interface AccessJwtVerifier {
|
||||
verifyJwt: (
|
||||
token: string,
|
||||
type: JwtType,
|
||||
) => Promise<{
|
||||
sub?: string;
|
||||
email?: string;
|
||||
workspaceId?: string;
|
||||
sessionId?: string;
|
||||
}>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Bind a TokenService-like verifier into a one-arg `verifyJwt(token)` that
|
||||
* ALWAYS enforces `JwtType.ACCESS`. This is the single place where the /mcp
|
||||
* Bearer path pins the token type: a Bearer access token must be verified AS an
|
||||
* access token (not refresh/exchange/collab/etc.), so the type literal is fixed
|
||||
* here rather than at the call site. McpService.verifyMcpBearer delegates to
|
||||
* this, keeping the `JwtType.ACCESS` choice testable without the heavy graph.
|
||||
*/
|
||||
export function bindAccessJwtVerifier(
|
||||
tokenService: AccessJwtVerifier,
|
||||
): (token: string) => Promise<{
|
||||
// The decoded payload shared by the /mcp Bearer allowlist. Carries the `type`
|
||||
// discriminator and the API-key `apiKeyId`, on top of the access-token fields.
|
||||
export interface McpBearerPayload {
|
||||
type?: JwtType;
|
||||
sub?: string;
|
||||
email?: string;
|
||||
workspaceId?: string;
|
||||
sessionId?: string;
|
||||
}> {
|
||||
return (token: string) => tokenService.verifyJwt(token, JwtType.ACCESS);
|
||||
apiKeyId?: string;
|
||||
}
|
||||
|
||||
// Minimal structural shape of the TokenService.verifyJwtOneOf method.
|
||||
export interface OneOfJwtVerifier {
|
||||
verifyJwtOneOf: (
|
||||
token: string,
|
||||
allowed: JwtType[],
|
||||
) => Promise<McpBearerPayload>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Bind a TokenService-like verifier into a one-arg `verifyJwtOneOf(token)` that
|
||||
* pins the /mcp Bearer ALLOWLIST to exactly {ACCESS, API_KEY}. This is the single
|
||||
* place the /mcp Bearer path pins the token type: the /mcp Bearer slot
|
||||
* legitimately accepts either an ACCESS token (a
|
||||
* human's session token) OR an API_KEY token (an agent's key), but NOTHING else
|
||||
* (collab/exchange/attachment/etc. are rejected with the generic type error).
|
||||
* The allowlist is fixed here rather than at the call site, and the signature is
|
||||
* verified exactly once (see verifyMcpBearer).
|
||||
*/
|
||||
export function bindMcpBearerVerifier(
|
||||
tokenService: OneOfJwtVerifier,
|
||||
): (token: string) => Promise<McpBearerPayload> {
|
||||
return (token: string) =>
|
||||
tokenService.verifyJwtOneOf(token, [JwtType.ACCESS, JwtType.API_KEY]);
|
||||
}
|
||||
|
||||
// Deps for the /mcp Bearer router. `verifyJwtOneOf` is the one-arg verifier bound
|
||||
// above (allowlist {ACCESS, API_KEY}); the ACCESS-specific revocation/disabled
|
||||
// deps mirror BearerVerifyDeps; `validateApiKey` is the SHARED api-key row-check.
|
||||
export interface McpBearerDeps
|
||||
extends Omit<BearerVerifyDeps, 'verifyJwt'> {
|
||||
verifyJwtOneOf: (token: string) => Promise<McpBearerPayload>;
|
||||
// Row-check for an API_KEY principal — the SAME validator REST uses. Throws
|
||||
// UnauthorizedException on a definite deny; PROPAGATES an infra error (→ 5xx),
|
||||
// never masking it as a 401. Not a login attempt: the Basic limiter is not
|
||||
// involved on this path.
|
||||
validateApiKey: (payload: McpBearerPayload) => Promise<unknown>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Verify a /mcp Bearer token that may be an ACCESS token OR an API_KEY token, and
|
||||
* route by type. The signature is verified EXACTLY ONCE (verifyJwtOneOf); the
|
||||
* result is reused so the ACCESS branch does not re-verify.
|
||||
*
|
||||
* - API_KEY -> bind to THIS instance's workspace FIRST (a token for another
|
||||
* workspace is rejected), THEN run the shared `validateApiKey` row-check.
|
||||
* No session/limiter involvement (an API key is not a login).
|
||||
* - ACCESS -> the unchanged `verifyBearerAccess` (session-active + not-disabled
|
||||
* checks), fed a closure over the already-verified payload so "verify once"
|
||||
* and "helper unchanged" coexist.
|
||||
*
|
||||
* Throws UnauthorizedException on any auth failure (uniform generic message — no
|
||||
* enumeration of why); propagates an infra error from `validateApiKey` as itself.
|
||||
*/
|
||||
export async function verifyMcpBearer(
|
||||
token: string,
|
||||
deps: McpBearerDeps,
|
||||
): Promise<{ sub?: string; email?: string }> {
|
||||
const generic = 'Invalid or expired token';
|
||||
const payload = await deps.verifyJwtOneOf(token);
|
||||
|
||||
if (payload.type === JwtType.API_KEY) {
|
||||
if (!payload.sub || !payload.workspaceId) {
|
||||
throw new UnauthorizedException(generic);
|
||||
}
|
||||
// Instance-binding (mirrors verifyBearerAccess): reject an API_KEY token
|
||||
// minted for a different workspace before touching the DB.
|
||||
if (
|
||||
deps.expectedWorkspaceId &&
|
||||
payload.workspaceId !== deps.expectedWorkspaceId
|
||||
) {
|
||||
throw new UnauthorizedException(generic);
|
||||
}
|
||||
// Shared row-check. A definite deny throws Unauthorized; an infra error
|
||||
// propagates (→ 5xx), which the caller must NOT convert to a 401.
|
||||
await deps.validateApiKey(payload);
|
||||
return { sub: payload.sub };
|
||||
}
|
||||
|
||||
// ACCESS: reuse verifyBearerAccess WITHOUT re-verifying the signature.
|
||||
return verifyBearerAccess(token, {
|
||||
verifyJwt: async () => payload,
|
||||
expectedWorkspaceId: deps.expectedWorkspaceId,
|
||||
findUser: deps.findUser,
|
||||
findActiveSession: deps.findActiveSession,
|
||||
});
|
||||
}
|
||||
|
||||
// Minimal shapes for the Bearer revocation/disabled check. Kept structural so
|
||||
@@ -728,18 +793,24 @@ export async function resolveMcpSessionConfig(
|
||||
};
|
||||
}
|
||||
|
||||
// --- 2) fallback A: Bearer access-JWT (user-supplied token) ---
|
||||
// --- 2) fallback A: Bearer JWT (user-supplied ACCESS or agent API_KEY) ---
|
||||
const bearer = extractBearer(authHeader);
|
||||
if (bearer) {
|
||||
let payload: { sub?: string; email?: string };
|
||||
try {
|
||||
payload = await deps.verifyAccessJwt(bearer);
|
||||
} catch (err) {
|
||||
const message =
|
||||
err instanceof Error && err.message
|
||||
? err.message
|
||||
: 'Invalid or expired token';
|
||||
throw new UnauthorizedException(message);
|
||||
// Anti-enumeration (Bearer leg): EVERY auth failure surfaces the SAME
|
||||
// generic 401 — expired/revoked/wrong-type/unknown are indistinguishable
|
||||
// to the caller (its reaction is identical either way). But an UNEXPECTED
|
||||
// (infra) error is NOT an auth verdict: rethrow it AS ITSELF so the surface
|
||||
// maps it to 5xx (mapAuthResultToResponse), never masking a DB/Redis
|
||||
// outage as a bad token. verifyMcpBearer throws UnauthorizedException on a
|
||||
// definite deny and lets an infra error from validateApiKey propagate.
|
||||
if (err instanceof UnauthorizedException) {
|
||||
throw new UnauthorizedException('Invalid or expired token');
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
return {
|
||||
config: { apiUrl, getToken: async () => bearer },
|
||||
|
||||
@@ -115,6 +115,7 @@ function makeService(opts: {
|
||||
undefined as never, // userRepo
|
||||
undefined as never, // userSessionRepo
|
||||
moduleRef as never, // moduleRef (read by the MFA branch)
|
||||
undefined as never, // apiKeyService (unused by the login-gate path)
|
||||
undefined as never, // sandboxStore (unused by the login-gate path)
|
||||
);
|
||||
// Stop the constructor's unref'd sweep timer leaking across tests.
|
||||
|
||||
@@ -4,13 +4,16 @@ import { McpService } from './mcp.service';
|
||||
import { DatabaseModule } from '@docmost/db/database.module';
|
||||
import { AuthModule } from '../../core/auth/auth.module';
|
||||
import { TokenModule } from '../../core/auth/token.module';
|
||||
import { ApiKeyModule } from '../../core/api-key/api-key.module';
|
||||
|
||||
// Community MCP feature: the server itself serves the Model Context Protocol
|
||||
// over HTTP at /mcp. DatabaseModule (global) provides WorkspaceRepo. AuthModule
|
||||
// supplies AuthService (per-user HTTP-Basic login validation) and TokenModule
|
||||
// supplies TokenService (Bearer access-JWT verification for the token fallback).
|
||||
// supplies TokenService (Bearer JWT verification for the token path). ApiKeyModule
|
||||
// supplies ApiKeyService (the shared api-key row-check for the API_KEY Bearer
|
||||
// branch, so an agent authenticates with a key instead of the bcrypt Basic path).
|
||||
@Module({
|
||||
imports: [DatabaseModule, AuthModule, TokenModule],
|
||||
imports: [DatabaseModule, AuthModule, TokenModule, ApiKeyModule],
|
||||
controllers: [McpController],
|
||||
providers: [McpService],
|
||||
})
|
||||
|
||||
@@ -6,9 +6,10 @@ import {
|
||||
isCredentialsFailure,
|
||||
isInitializeRequestBody,
|
||||
verifyBearerAccess,
|
||||
verifyMcpBearer,
|
||||
bindMcpBearerVerifier,
|
||||
sharedTokenMatches,
|
||||
clientIp,
|
||||
bindAccessJwtVerifier,
|
||||
extractBearer,
|
||||
decideBasicGate,
|
||||
mapAuthResultToResponse,
|
||||
@@ -524,13 +525,28 @@ describe('resolveMcpSessionConfig', () => {
|
||||
expect(resolved.identity).toBe('bearer:user-9');
|
||||
});
|
||||
|
||||
it('Bearer invalid -> specific 401 from verifyAccessJwt', async () => {
|
||||
it('Bearer invalid -> UNIFORM generic 401 (anti-enumeration, reason not leaked)', async () => {
|
||||
// #501: the Bearer leg no longer surfaces the specific reason. Whether the
|
||||
// token is expired, revoked, wrong-type or unknown, the caller sees ONE bare
|
||||
// 'Invalid or expired token' — an agent's reaction is identical, and a leaked
|
||||
// class would be an enumeration oracle.
|
||||
const verifyAccessJwt = jest
|
||||
.fn()
|
||||
.mockRejectedValue(new UnauthorizedException('jwt expired'));
|
||||
await expect(
|
||||
resolveMcpSessionConfig('Bearer expired', makeDeps({ verifyAccessJwt })),
|
||||
).rejects.toThrow('jwt expired');
|
||||
).rejects.toThrow('Invalid or expired token');
|
||||
});
|
||||
|
||||
it('Bearer INFRA error -> propagates (NOT masked as 401)', async () => {
|
||||
// A non-UnauthorizedException (e.g. a DB outage in the api-key row-check) is
|
||||
// not an auth verdict: it must propagate so the surface maps it to 5xx.
|
||||
const verifyAccessJwt = jest
|
||||
.fn()
|
||||
.mockRejectedValue(new Error('connection terminated'));
|
||||
await expect(
|
||||
resolveMcpSessionConfig('Bearer x', makeDeps({ verifyAccessJwt })),
|
||||
).rejects.toThrow('connection terminated');
|
||||
});
|
||||
|
||||
it('no creds + env service account configured -> service-account config', async () => {
|
||||
@@ -1001,48 +1017,104 @@ describe('clientIp (XFF-fallback precedence, item 5)', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('bindAccessJwtVerifier enforces JwtType.ACCESS (item 3)', () => {
|
||||
it('calls TokenService.verifyJwt with JwtType.ACCESS as the second argument', async () => {
|
||||
// Mock TokenService: assert the type literal is pinned to ACCESS so swapping
|
||||
// to REFRESH (or omitting the type) breaks this test.
|
||||
const verifyJwt = jest
|
||||
describe('bindMcpBearerVerifier pins the {ACCESS, API_KEY} allowlist (#501)', () => {
|
||||
it('calls verifyJwtOneOf with exactly [ACCESS, API_KEY]', async () => {
|
||||
const verifyJwtOneOf = jest
|
||||
.fn()
|
||||
.mockResolvedValue({ sub: 'user-1', workspaceId: 'ws-1' });
|
||||
const verify = bindAccessJwtVerifier({ verifyJwt });
|
||||
.mockResolvedValue({ type: JwtType.API_KEY, sub: 'u-1' });
|
||||
await bindMcpBearerVerifier({ verifyJwtOneOf })('the.jwt');
|
||||
expect(verifyJwtOneOf).toHaveBeenCalledWith('the.jwt', [
|
||||
JwtType.ACCESS,
|
||||
JwtType.API_KEY,
|
||||
]);
|
||||
// Pin the concrete enum values too.
|
||||
expect(verifyJwtOneOf.mock.calls[0][1]).toEqual(['access', 'api_key']);
|
||||
});
|
||||
});
|
||||
|
||||
await verify('the.access.jwt');
|
||||
|
||||
expect(verifyJwt).toHaveBeenCalledTimes(1);
|
||||
expect(verifyJwt).toHaveBeenCalledWith('the.access.jwt', JwtType.ACCESS);
|
||||
// Pin the real enum value too, so renaming/repointing the enum member is caught.
|
||||
expect(verifyJwt.mock.calls[0][1]).toBe('access');
|
||||
describe('verifyMcpBearer routes by token type (#501)', () => {
|
||||
const accessDeps = (over: any = {}) => ({
|
||||
verifyJwtOneOf: jest.fn(),
|
||||
expectedWorkspaceId: 'ws-1',
|
||||
findUser: jest.fn().mockResolvedValue({ deactivatedAt: null }),
|
||||
findActiveSession: jest
|
||||
.fn()
|
||||
.mockResolvedValue({ userId: 'u-1', workspaceId: 'ws-1' }),
|
||||
validateApiKey: jest.fn(),
|
||||
...over,
|
||||
});
|
||||
|
||||
it('passes through the verified payload', async () => {
|
||||
const payload = { sub: 'user-9', email: 'u@e.com', workspaceId: 'ws-1' };
|
||||
const verifyJwt = jest.fn().mockResolvedValue(payload);
|
||||
await expect(
|
||||
bindAccessJwtVerifier({ verifyJwt })('t'),
|
||||
).resolves.toBe(payload);
|
||||
it('API_KEY -> row-checks via validateApiKey and does NOT touch session/limiter', async () => {
|
||||
const deps = accessDeps({
|
||||
verifyJwtOneOf: jest.fn().mockResolvedValue({
|
||||
type: JwtType.API_KEY,
|
||||
sub: 'svc-1',
|
||||
workspaceId: 'ws-1',
|
||||
apiKeyId: 'k-1',
|
||||
}),
|
||||
validateApiKey: jest.fn().mockResolvedValue({ user: { id: 'svc-1' } }),
|
||||
});
|
||||
const res = await verifyMcpBearer('tok', deps);
|
||||
expect(deps.validateApiKey).toHaveBeenCalledTimes(1);
|
||||
// No session lookup on the api-key path (not a login).
|
||||
expect(deps.findActiveSession).not.toHaveBeenCalled();
|
||||
expect(res).toEqual({ sub: 'svc-1' });
|
||||
});
|
||||
|
||||
// The Bearer revocation/disabled checks (verifyBearerAccess) are covered above;
|
||||
// this binds the ACCESS-type enforcement that verifyMcpBearer wires in.
|
||||
it('feeds verifyBearerAccess so the whole Bearer chain enforces ACCESS', async () => {
|
||||
const verifyJwt = jest.fn().mockResolvedValue({
|
||||
sub: 'user-1',
|
||||
it('API_KEY for ANOTHER workspace -> rejected before the row-check', async () => {
|
||||
const deps = accessDeps({
|
||||
verifyJwtOneOf: jest.fn().mockResolvedValue({
|
||||
type: JwtType.API_KEY,
|
||||
sub: 'svc-1',
|
||||
workspaceId: 'ws-OTHER',
|
||||
apiKeyId: 'k-1',
|
||||
}),
|
||||
validateApiKey: jest.fn(),
|
||||
});
|
||||
await expect(verifyMcpBearer('tok', deps)).rejects.toBeInstanceOf(
|
||||
UnauthorizedException,
|
||||
);
|
||||
expect(deps.validateApiKey).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it('API_KEY infra error from validateApiKey PROPAGATES (not masked)', async () => {
|
||||
const boom = new Error('db down');
|
||||
const deps = accessDeps({
|
||||
verifyJwtOneOf: jest.fn().mockResolvedValue({
|
||||
type: JwtType.API_KEY,
|
||||
sub: 'svc-1',
|
||||
workspaceId: 'ws-1',
|
||||
apiKeyId: 'k-1',
|
||||
}),
|
||||
validateApiKey: jest.fn().mockRejectedValue(boom),
|
||||
});
|
||||
await expect(verifyMcpBearer('tok', deps)).rejects.toBe(boom);
|
||||
});
|
||||
|
||||
it('ACCESS -> runs the session/disabled checks and does NOT call validateApiKey', async () => {
|
||||
const deps = accessDeps({
|
||||
verifyJwtOneOf: jest.fn().mockResolvedValue({
|
||||
type: JwtType.ACCESS,
|
||||
sub: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
sessionId: 'sess-1',
|
||||
email: 'u@e.com',
|
||||
}),
|
||||
});
|
||||
const res = await verifyMcpBearer('tok', deps);
|
||||
expect(deps.findActiveSession).toHaveBeenCalledWith('sess-1');
|
||||
expect(deps.validateApiKey).not.toHaveBeenCalled();
|
||||
expect(res).toEqual({ sub: 'u-1', email: 'u@e.com' });
|
||||
});
|
||||
|
||||
it('verifies the signature exactly ONCE (single verifyJwtOneOf, no re-verify)', async () => {
|
||||
const verifyJwtOneOf = jest.fn().mockResolvedValue({
|
||||
type: JwtType.ACCESS,
|
||||
sub: 'u-1',
|
||||
workspaceId: 'ws-1',
|
||||
sessionId: 'sess-1',
|
||||
});
|
||||
const res = await verifyBearerAccess('t', {
|
||||
verifyJwt: bindAccessJwtVerifier({ verifyJwt }),
|
||||
findUser: jest.fn().mockResolvedValue({ deactivatedAt: null }),
|
||||
findActiveSession: jest
|
||||
.fn()
|
||||
.mockResolvedValue({ userId: 'user-1', workspaceId: 'ws-1' }),
|
||||
});
|
||||
expect(verifyJwt).toHaveBeenCalledWith('t', JwtType.ACCESS);
|
||||
expect(res).toEqual({ sub: 'user-1', email: undefined });
|
||||
await verifyMcpBearer('tok', accessDeps({ verifyJwtOneOf }));
|
||||
expect(verifyJwtOneOf).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1198,6 +1270,7 @@ describe('McpService.onModuleDestroy — CollabSession teardown (#486)', () => {
|
||||
{} as any,
|
||||
{} as any,
|
||||
{} as any,
|
||||
{} as any,
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -14,16 +14,17 @@ import { UserSessionRepo } from '@docmost/db/repos/session/user-session.repo';
|
||||
import { AuthService } from '../../core/auth/services/auth.service';
|
||||
import { TokenService } from '../../core/auth/services/token.service';
|
||||
import { validateSsoEnforcement } from '../../core/auth/auth.util';
|
||||
import { JwtPayload } from '../../core/auth/dto/jwt-payload';
|
||||
import { JwtApiKeyPayload } from '../../core/auth/dto/jwt-payload';
|
||||
import { Workspace } from '@docmost/db/types/entity.types';
|
||||
import { ApiKeyService } from '../../core/api-key/api-key.service';
|
||||
import {
|
||||
FailedLoginLimiter,
|
||||
resolveMcpSessionConfig,
|
||||
verifyBearerAccess,
|
||||
verifyMcpBearer,
|
||||
isInitializeRequestBody,
|
||||
sharedTokenMatches,
|
||||
clientIp,
|
||||
bindAccessJwtVerifier,
|
||||
bindMcpBearerVerifier,
|
||||
decideBasicGate,
|
||||
mapAuthResultToResponse,
|
||||
DocmostMcpConfig,
|
||||
@@ -105,6 +106,10 @@ export class McpService implements OnModuleDestroy {
|
||||
private readonly userRepo: UserRepo,
|
||||
private readonly userSessionRepo: UserSessionRepo,
|
||||
private readonly moduleRef: ModuleRef,
|
||||
// Shared api-key row-check for the /mcp API_KEY Bearer branch (same validator
|
||||
// REST uses). Also lets an agent authenticate to /mcp with an api key instead
|
||||
// of the bcrypt Basic path, so parallel reads stop starving the limiter.
|
||||
private readonly apiKeyService: ApiKeyService,
|
||||
// Shared singleton in-RAM blob store backing the stash tool.
|
||||
private readonly sandboxStore: SandboxStore,
|
||||
) {
|
||||
@@ -194,37 +199,41 @@ export class McpService implements OnModuleDestroy {
|
||||
}
|
||||
}
|
||||
|
||||
// Bearer access-JWT verification for the /mcp token fallback. verifyJwt only
|
||||
// checks signature/exp/type, but a logged-out (revoked) or disabled user can
|
||||
// still hold an unexpired access JWT. JwtStrategy additionally checks the
|
||||
// session is active and the user is not disabled; we mirror those exact checks
|
||||
// here so the MCP Bearer path is not weaker than the normal cookie/header path.
|
||||
// Bearer verification for the /mcp token path. The Bearer slot accepts EITHER
|
||||
// an ACCESS token (a human session token) OR an API_KEY token (an agent's key)
|
||||
// — the allowlist is pinned in bindMcpBearerVerifier. An ACCESS token is
|
||||
// checked exactly as JwtStrategy does (signature/exp/type + session-active +
|
||||
// not-disabled), so the MCP path is not weaker than the cookie/header path. An
|
||||
// API_KEY token is HMAC-verified (microseconds) then row-checked via the shared
|
||||
// ApiKeyService.validate — NOT a login attempt, so the Basic bcrypt path and
|
||||
// its anti-brute-force limiter are never touched (the parallel-reads fix).
|
||||
private async verifyMcpBearer(
|
||||
token: string,
|
||||
): Promise<{ sub?: string; email?: string }> {
|
||||
// Resolve THIS instance's workspace so verifyBearerAccess can bind the
|
||||
// token's `workspaceId` claim to it (mirrors JwtStrategy). The community
|
||||
// build is single-workspace (findFirst), so this is the default workspace
|
||||
// and the check is a no-op here; it only rejects a foreign-workspace token
|
||||
// in a multi-workspace deployment. Undefined (no workspace configured) means
|
||||
// no check — the credentials path would already have failed with no
|
||||
// workspace, and an undefined here keeps the helper a no-op rather than
|
||||
// rejecting every token.
|
||||
// Resolve THIS instance's workspace so the router can bind the token's
|
||||
// `workspaceId` claim to it (mirrors JwtStrategy). The community build is
|
||||
// single-workspace (findFirst), so this is the default workspace and the
|
||||
// check is a no-op here; it only rejects a foreign-workspace token in a
|
||||
// multi-workspace deployment. Undefined (no workspace configured) means no
|
||||
// check — the credentials path would already have failed with no workspace.
|
||||
const instanceWorkspace = await this.workspaceRepo.findFirst();
|
||||
// The revocation/disabled decision logic lives in the framework-free
|
||||
// verifyBearerAccess helper (unit-testable without the heavy auth graph);
|
||||
// this method only wires in the concrete TokenService + repos.
|
||||
return verifyBearerAccess(token, {
|
||||
// The JwtType.ACCESS enforcement lives in bindAccessJwtVerifier (a pure,
|
||||
// testable seam) so the type literal cannot silently drift to REFRESH.
|
||||
verifyJwt: bindAccessJwtVerifier(this.tokenService) as (
|
||||
t: string,
|
||||
) => Promise<JwtPayload>,
|
||||
// The type-routing + revocation/disabled decision logic lives in the
|
||||
// framework-free verifyMcpBearer helper (unit-testable without the heavy auth
|
||||
// graph); this method only wires in the concrete TokenService + repos + the
|
||||
// shared api-key validator.
|
||||
return verifyMcpBearer(token, {
|
||||
// The {ACCESS, API_KEY} allowlist enforcement lives in bindMcpBearerVerifier
|
||||
// (a pure, testable seam) so the type set cannot silently drift.
|
||||
verifyJwtOneOf: bindMcpBearerVerifier(this.tokenService),
|
||||
expectedWorkspaceId: instanceWorkspace?.id,
|
||||
findUser: (sub, workspaceId) =>
|
||||
this.userRepo.findById(sub, workspaceId),
|
||||
findActiveSession: (sessionId) =>
|
||||
this.userSessionRepo.findActiveById(sessionId),
|
||||
// Shared with REST: a definite deny throws Unauthorized, an infra error
|
||||
// propagates (→ 5xx). The /mcp bearer catch must preserve that distinction.
|
||||
validateApiKey: (payload) =>
|
||||
this.apiKeyService.validate(payload as JwtApiKeyPayload),
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
@@ -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';
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -322,20 +322,21 @@ describe('AiChatService.stream [integration]', () => {
|
||||
});
|
||||
|
||||
/**
|
||||
* #332 deferred tool loading, the ON path. The riskiest property is that the
|
||||
* per-turn `activatedTools` Set is created FRESH inside each stream() call, so a
|
||||
* tool a previous turn activated via loadTools is NOT still active when the next
|
||||
* turn starts — the new turn begins "cold" (CORE + loadTools only). The unit
|
||||
* tests only exercise pure prepareAgentStep with hand-fed Sets; this pins the
|
||||
* real wiring end-to-end (loadTools.execute -> activatedTools -> prepareStep ->
|
||||
* per-step activeTools) against the real streamText loop, and proves there is no
|
||||
* cross-turn leak. We drive a MockLanguageModelV3 whose step 1 calls
|
||||
* loadTools(['createPage']) and assert, via the model's recorded per-step
|
||||
* CallOptions.tools (the AI SDK filters the provider tool list by activeTools),
|
||||
* that the deferred tool becomes active on the SAME turn's next step but NOT on a
|
||||
* fresh turn's first step.
|
||||
* #332 + #490 deferred tool loading, the ON path. Turn 1 starts COLD (CORE +
|
||||
* loadTools only) and activates a deferred tool via loadTools; that activation
|
||||
* is PERSISTED into the chat's metadata.activatedTools (#490) so the NEXT turn
|
||||
* SEEDS from it and the tool is active from the fresh turn's FIRST step — the
|
||||
* model never re-runs loadTools to re-activate the same tool. The unit tests
|
||||
* only exercise pure prepareAgentStep with hand-fed Sets; this pins the real
|
||||
* wiring end-to-end (loadTools.execute -> activatedTools -> persist -> next-turn
|
||||
* seed -> prepareStep -> per-step activeTools) against the real streamText loop.
|
||||
* We drive a MockLanguageModelV3 whose step 1 calls loadTools(['createPage'])
|
||||
* and assert, via the model's recorded per-step CallOptions.tools (the AI SDK
|
||||
* filters the provider tool list by activeTools), that the deferred tool becomes
|
||||
* active on the SAME turn's next step AND, seeded from metadata, on the next
|
||||
* turn's first step.
|
||||
*/
|
||||
describe('deferred tool loading ON — per-turn activation, no leak (#332)', () => {
|
||||
describe('deferred tool loading ON — cross-turn activation persistence (#332 + #490)', () => {
|
||||
// A stub deferred (non-core) tool the agent can activate. Its execute is never
|
||||
// called — the model only needs to SEE it become active — but it must be a
|
||||
// valid AI-SDK tool so the SDK includes it in a step's tool list once active.
|
||||
@@ -451,7 +452,7 @@ describe('AiChatService.stream [integration]', () => {
|
||||
} as any);
|
||||
}
|
||||
|
||||
it('activates a deferred tool for the SAME turn, and a NEW turn starts cold (no leak)', async () => {
|
||||
it('activates a deferred tool for the SAME turn, and a NEW turn SEEDS it from persisted chat metadata (#490)', async () => {
|
||||
const chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
|
||||
// --- Turn 1: loadTools(createPage) on step 1, then answer on step 2. ---
|
||||
@@ -474,7 +475,7 @@ describe('AiChatService.stream [integration]', () => {
|
||||
// Step 2 of the SAME turn sees the just-activated deferred tool.
|
||||
expect(step2Tools).toContain('createPage');
|
||||
|
||||
// --- Turn 2 on the SAME chat: must start cold again. ---
|
||||
// --- Turn 2 on the SAME chat: seeds the persisted activation (#490). ---
|
||||
const model2 = new MockLanguageModelV3({
|
||||
doStream: async () => ({ stream: successStream() }),
|
||||
} as any);
|
||||
@@ -485,9 +486,10 @@ describe('AiChatService.stream [integration]', () => {
|
||||
|
||||
const nextTurnFirstStep = toolNames(model2.doStreamCalls[0]);
|
||||
expect(nextTurnFirstStep).toContain('loadTools');
|
||||
// The activated set is per-turn: the prior turn's createPage did NOT leak,
|
||||
// so the fresh turn's first step sees it deferred again.
|
||||
expect(nextTurnFirstStep).not.toContain('createPage');
|
||||
// #490: activation PERSISTS across turns — turn 1 wrote createPage into the
|
||||
// chat's metadata.activatedTools, so the next turn seeds from it and the
|
||||
// deferred tool is active from the FIRST step (no need to re-run loadTools).
|
||||
expect(nextTurnFirstStep).toContain('createPage');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,162 @@
|
||||
import { randomUUID } from 'node:crypto';
|
||||
import { Queue, Worker } from 'bullmq';
|
||||
import { PersistenceExtension } from '../../src/collaboration/extensions/persistence.extension';
|
||||
|
||||
/**
|
||||
* #370 — integration property of the idle-snapshot pipeline against REAL BullMQ.
|
||||
*
|
||||
* This is deliberately NOT a unit test of computeHistoryJob (that lives in
|
||||
* compute-history-job.spec.ts). The point here is the OBSERVABLE end-to-end
|
||||
* behaviour of the production `enqueuePageHistory` remove-then-add debounce
|
||||
* driving a real Redis-backed delayed queue + worker (the #431→#439 class: a
|
||||
* locally-correct function whose queue/timer property was never exercised):
|
||||
*
|
||||
* - a CONTINUOUS burst of stores lasting several caps yields periodic idle
|
||||
* snapshots — at least one per max-wait cap, NOT one-per-store; and
|
||||
* - an INTERMITTENT burst (a few stores, then quiet) yields exactly ONE
|
||||
* trailing snapshot.
|
||||
*
|
||||
* We shrink the idle windows to milliseconds (jest.mock of collaboration
|
||||
* constants) so real BullMQ delayed jobs actually promote within the test —
|
||||
* fake timers cannot advance Redis's own delayed-set clock, so the intervals
|
||||
* must be real but tiny. The production method under test is called verbatim.
|
||||
*/
|
||||
|
||||
// NOTE: jest.mock is hoisted above the module's const initializers, so its
|
||||
// factory cannot close over MAX_WAIT_MS/INTERVAL_MS — the literals are inlined
|
||||
// here and MUST stay in sync with the consts below (a single source of truth is
|
||||
// impossible across the hoist boundary).
|
||||
jest.mock('../../src/collaboration/constants', () => {
|
||||
const actual = jest.requireActual('../../src/collaboration/constants');
|
||||
return {
|
||||
...actual,
|
||||
IDLE_MAX_WAIT_USER: 300,
|
||||
IDLE_MAX_WAIT_AGENT: 300,
|
||||
IDLE_INTERVAL_USER: 1000,
|
||||
IDLE_INTERVAL_AGENT: 1000,
|
||||
};
|
||||
});
|
||||
|
||||
// Mirrors the mocked IDLE_MAX_WAIT_* above (IDLE_INTERVAL_* is 1000 > this, so
|
||||
// the max-wait ceiling is what actually governs the trailing delay).
|
||||
const MAX_WAIT_MS = 300;
|
||||
|
||||
const REDIS_CONNECTION = {
|
||||
host: process.env.TEST_REDIS_HOST ?? '127.0.0.1',
|
||||
port: Number(process.env.TEST_REDIS_PORT ?? 6379),
|
||||
};
|
||||
|
||||
const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));
|
||||
|
||||
describe('#370 idle-snapshot pipeline (real BullMQ)', () => {
|
||||
let queue: Queue;
|
||||
let worker: Worker;
|
||||
let extension: PersistenceExtension;
|
||||
// Every processed snapshot, tagged by pageId so the two scenarios stay isolated.
|
||||
const processed: Array<{ pageId: string; kind: string; at: number }> = [];
|
||||
const queueName = `history-idle-int-${randomUUID()}`;
|
||||
|
||||
beforeAll(async () => {
|
||||
queue = new Queue(queueName, {
|
||||
connection: REDIS_CONNECTION,
|
||||
// Mirror the production default (BullModule.forRoot removeOnComplete): the
|
||||
// enqueue idiom relies on the jobId being freed once a job completes so the
|
||||
// next burst can re-arm the same id.
|
||||
defaultJobOptions: { removeOnComplete: true, removeOnFail: true },
|
||||
});
|
||||
await queue.waitUntilReady();
|
||||
|
||||
worker = new Worker(
|
||||
queueName,
|
||||
async (job) => {
|
||||
processed.push({
|
||||
pageId: job.data?.pageId,
|
||||
kind: job.data?.kind,
|
||||
at: Date.now(),
|
||||
});
|
||||
},
|
||||
{ connection: REDIS_CONNECTION },
|
||||
);
|
||||
await worker.waitUntilReady();
|
||||
|
||||
// Construct the real extension; only historyQueue (5th ctor arg) and the
|
||||
// internal idleBurstStart map are exercised by enqueuePageHistory, so the
|
||||
// other collaborators can be null — the constructor only assigns fields.
|
||||
extension = new PersistenceExtension(
|
||||
null as any, // pageRepo
|
||||
null as any, // pageHistoryRepo
|
||||
null as any, // db
|
||||
null as any, // aiQueue
|
||||
queue as any, // historyQueue
|
||||
null as any, // notificationQueue
|
||||
null as any, // collabHistory
|
||||
null as any, // transclusionService
|
||||
);
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
// Force-close and fully drain so no BullMQ background activity (delayed-set
|
||||
// polling, blocking BRPOPLPUSH) bleeds into later suites in this single
|
||||
// shared jest worker (maxWorkers: 1).
|
||||
await worker?.close(true).catch(() => undefined);
|
||||
await queue?.obliterate({ force: true }).catch(() => undefined);
|
||||
await queue?.close();
|
||||
// Let the redis sockets settle before the next suite starts.
|
||||
await sleep(150);
|
||||
});
|
||||
|
||||
const arm = (pageId: string) =>
|
||||
(extension as any).enqueuePageHistory({ id: pageId }, 'user');
|
||||
|
||||
it('continuous burst over several caps → periodic idle snapshots (≥1 per cap, not one-per-store)', async () => {
|
||||
const pageId = randomUUID();
|
||||
const runMs = 6 * MAX_WAIT_MS; // ~6 caps of unbroken editing
|
||||
// Store cadence that does NOT evenly divide the cap: real hocuspocus stores
|
||||
// are not aligned to cap boundaries, so a boundary job promotes in the gap
|
||||
// before the next store's remove(). A cap-aligned cadence would instead land
|
||||
// a store exactly on every boundary and lose the snapshot to the documented
|
||||
// remove-vs-active race — an artefact of the test clock, not the pipeline.
|
||||
const stepMs = 70;
|
||||
const stores = Math.floor(runMs / stepMs);
|
||||
|
||||
const start = Date.now();
|
||||
let count = 0;
|
||||
while (Date.now() - start < runMs) {
|
||||
await arm(pageId);
|
||||
count++;
|
||||
await sleep(stepMs);
|
||||
}
|
||||
// Let the final armed job flush.
|
||||
await sleep(2 * MAX_WAIT_MS);
|
||||
|
||||
const snaps = processed.filter((p) => p.pageId === pageId);
|
||||
|
||||
// Every autosnapshot is an idle-kind row.
|
||||
expect(snaps.every((s) => s.kind === 'idle')).toBe(true);
|
||||
// Periodic: at least one per cap over a multi-cap burst (lower-bounded loosely
|
||||
// to stay robust; the property is "fires at least every cap", not a single
|
||||
// trailing snapshot).
|
||||
expect(snaps.length).toBeGreaterThanOrEqual(3);
|
||||
// But NOT one-per-store: ~`stores` stores were issued; the debounce must
|
||||
// collapse them to a small multiple of the cap count, nowhere near per-store.
|
||||
expect(snaps.length).toBeLessThanOrEqual(Math.ceil(stores / 2));
|
||||
});
|
||||
|
||||
it('intermittent burst (a few stores, then quiet) → exactly ONE trailing snapshot', async () => {
|
||||
const pageId = randomUUID();
|
||||
|
||||
// A short burst well within a single cap window, then silence.
|
||||
await arm(pageId);
|
||||
await sleep(40);
|
||||
await arm(pageId);
|
||||
await sleep(40);
|
||||
await arm(pageId);
|
||||
|
||||
// Wait comfortably past the cap so the single pending trailing job fires.
|
||||
await sleep(4 * MAX_WAIT_MS);
|
||||
|
||||
const snaps = processed.filter((p) => p.pageId === pageId);
|
||||
expect(snaps).toHaveLength(1);
|
||||
expect(snaps[0].kind).toBe('idle');
|
||||
});
|
||||
});
|
||||
@@ -387,7 +387,7 @@ bucketByDay(sessions, tz):
|
||||
факты ниже — ground truth, можно дозапросить файлы через gitea MCP по указанному SHA):
|
||||
|
||||
- `page_history.kind` — `varchar(20)`, NULLABLE, БЕЗ дефолта (migration
|
||||
`20260705T120000-page-history-kind.ts`). Домен: `manual`/`agent`/`idle`/`boundary`;
|
||||
`20260707T120000-page-history-kind.ts`). Домен: `manual`/`agent`/`idle`/`boundary`;
|
||||
legacy `null` = автосейв (`collaboration/constants.ts`, `PageHistoryKind`).
|
||||
- `kind` УЖЕ включён в `PageHistoryRepo.baseFields` (`page-history.repo.ts`) — читается всеми
|
||||
выборками истории. `saveHistory({kind})` и `updateHistoryKind(id, kind)` существуют.
|
||||
|
||||
@@ -178,10 +178,11 @@ function sliceModel(xml: string): string | null {
|
||||
// --- decode chain ----------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Read the `content=` attribute out of a `.drawio.svg` string. Docmost stores a
|
||||
* base64 payload there (createDrawioSvg); draw.io's own SVG export may store the
|
||||
* XML entity-encoded instead. The DOM decodes entities for us, so the caller
|
||||
* only has to distinguish "starts with '<'" (raw XML) from base64.
|
||||
* Read the `content=` attribute out of a `.drawio.svg` string. Docmost writes
|
||||
* the mxfile XML entity-encoded there (buildDrawioSvg / createDrawioSvg), which
|
||||
* is also how draw.io's own SVG export stores it; older attachments stored a
|
||||
* base64 payload instead. The DOM decodes entities for us, so the caller only
|
||||
* has to distinguish "starts with '<'" (raw XML) from base64.
|
||||
*/
|
||||
export function extractContentAttr(svg: string): string {
|
||||
const { doc, error } = parseXml(svg);
|
||||
@@ -195,12 +196,23 @@ export function extractContentAttr(svg: string): string {
|
||||
// value itself never contains a double-quote (base64 / entity-encoded XML).
|
||||
const m = /content="([^"]*)"/.exec(svg);
|
||||
if (m) {
|
||||
// Decode the handful of XML entities a raw regex would leave encoded.
|
||||
// Decode the handful of XML entities a raw regex would leave encoded. The
|
||||
// numeric char-refs for tab/newline/CR MUST be decoded here too: the DOM
|
||||
// path above turns them back into the literal control chars, so this
|
||||
// regex fallback has to agree or the two decode paths diverge (#507).
|
||||
// `&` is decoded last so an escaped `&#x9;` reads back as the
|
||||
// literal text `	`, not a tab.
|
||||
return m[1]
|
||||
.replace(/</g, "<")
|
||||
.replace(/>/g, ">")
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, "'")
|
||||
.replace(/	/gi, "\t")
|
||||
.replace(/	/g, "\t")
|
||||
.replace(/
/gi, "\n")
|
||||
.replace(/ /g, "\n")
|
||||
.replace(/
/gi, "\r")
|
||||
.replace(/ /g, "\r")
|
||||
.replace(/&/g, "&");
|
||||
}
|
||||
throw new Error("drawio: SVG has no content= attribute to decode");
|
||||
@@ -307,9 +319,16 @@ export function encodeDrawioFile(modelXml: string, title = "Page-1"): string {
|
||||
/**
|
||||
* Build the `diagram.drawio.svg` attachment. Mirrors the import service's
|
||||
* createDrawioSvg contract exactly:
|
||||
* <svg xmlns=… xmlns:xlink=… content="${base64(drawioFile)}">${inner}</svg>
|
||||
* <svg xmlns=… xmlns:xlink=… content="${xmlEscape(drawioFile)}">${inner}</svg>
|
||||
* plus width/height/viewBox from the diagram bounding box and the schematic
|
||||
* preview as the visible children (`inner`).
|
||||
*
|
||||
* The `content=` value is the mxfile XML XML-entity-escaped (draw.io's own
|
||||
* native form), NOT base64. draw.io's editor decodes a base64 content= via
|
||||
* Latin-1 atob (no UTF-8 step), turning every non-ASCII char (e.g. Cyrillic,
|
||||
* ё, —) into mojibake; the entity-encoded form is decoded by the DOM as UTF-8
|
||||
* and opens intact. Our decoder (decodeDrawioSvg) reads both forms, so old
|
||||
* base64 attachments still round-trip.
|
||||
*/
|
||||
export function buildDrawioSvg(
|
||||
modelXml: string,
|
||||
@@ -318,14 +337,14 @@ export function buildDrawioSvg(
|
||||
title = "Page-1",
|
||||
): string {
|
||||
const file = encodeDrawioFile(modelXml, title);
|
||||
const base64 = Buffer.from(file, "utf-8").toString("base64");
|
||||
const content = xmlEscape(file);
|
||||
const w = Math.max(1, Math.round(bbox.width));
|
||||
const h = Math.max(1, Math.round(bbox.height));
|
||||
return (
|
||||
`<svg xmlns="http://www.w3.org/2000/svg" ` +
|
||||
`xmlns:xlink="http://www.w3.org/1999/xlink" ` +
|
||||
`width="${w}" height="${h}" viewBox="0 0 ${w} ${h}" ` +
|
||||
`content="${base64}">${inner}</svg>`
|
||||
`content="${content}">${inner}</svg>`
|
||||
);
|
||||
}
|
||||
|
||||
@@ -334,7 +353,15 @@ function xmlEscape(s: string): string {
|
||||
.replace(/&/g, "&")
|
||||
.replace(/</g, "<")
|
||||
.replace(/>/g, ">")
|
||||
.replace(/"/g, """);
|
||||
.replace(/"/g, """)
|
||||
// A literal tab/newline/CR inside an attribute value is collapsed to a
|
||||
// single space by XML attribute-value normalization on DOM read (both jsdom
|
||||
// here and the real draw.io editor), silently flattening multi-line labels
|
||||
// and tab-bearing values. Numeric char-refs survive that normalization, so
|
||||
// emit them the way draw.io's own native export does (#507).
|
||||
.replace(/\t/g, "	")
|
||||
.replace(/\n/g, "
")
|
||||
.replace(/\r/g, "
");
|
||||
}
|
||||
|
||||
// --- normalization + hash --------------------------------------------------
|
||||
|
||||
@@ -51,6 +51,14 @@ const hasRule = (issues, rule, cellId) =>
|
||||
(i) => i.rule === rule && (cellId === undefined || i.cellId === cellId),
|
||||
);
|
||||
|
||||
// Reverse the attribute-value XML escaping used in the `content=` payload.
|
||||
const unescapeAttr = (s) =>
|
||||
s
|
||||
.replace(/</g, "<")
|
||||
.replace(/>/g, ">")
|
||||
.replace(/"/g, '"')
|
||||
.replace(/&/g, "&");
|
||||
|
||||
// --- style parsing ---------------------------------------------------------
|
||||
|
||||
test("parseStyle: base stylename + key=value pairs", () => {
|
||||
@@ -335,16 +343,20 @@ test("encode/build: a title with < > \" & round-trips without corrupting the SVG
|
||||
|
||||
// The outer content="..." attribute must not be broken by the title: the raw
|
||||
// title metacharacters never appear literally in the SVG markup (they are
|
||||
// base64-encoded inside content=, and escaped inside the file XML).
|
||||
// entity-escaped inside content=, doubly so where the file XML already escaped
|
||||
// them inside name="...").
|
||||
const contentMatch = /content="([^"]*)"/.exec(svg);
|
||||
assert.ok(contentMatch, "SVG has a single well-formed content= attribute");
|
||||
|
||||
// The diagram model still decodes losslessly despite the exotic title.
|
||||
assert.equal(decodeDrawioSvg(svg), model);
|
||||
|
||||
// content= is now entity-encoded XML (draw.io's native form), never base64.
|
||||
assert.match(contentMatch[1], /^<mxfile/);
|
||||
|
||||
// The file XML is well-formed: the title lives in name="..." as escaped
|
||||
// entities, so unescaping recovers the original title byte-for-byte.
|
||||
const fileXml = Buffer.from(contentMatch[1], "base64").toString("utf-8");
|
||||
const fileXml = unescapeAttr(contentMatch[1]);
|
||||
const nameMatch = /<diagram id="[^"]*" name="([^"]*)">/.exec(fileXml);
|
||||
assert.ok(nameMatch, "the diagram name attribute is intact and quote-safe");
|
||||
const decodedTitle = nameMatch[1]
|
||||
@@ -358,3 +370,112 @@ test("encode/build: a title with < > \" & round-trips without corrupting the SVG
|
||||
const file = encodeDrawioFile(model, title);
|
||||
assert.match(file, /name="A < B > C " D & E">/);
|
||||
});
|
||||
|
||||
// --- #507: content= is entity-encoded XML, never base64 --------------------
|
||||
|
||||
// A model whose cell values carry Cyrillic, ё and an em dash — exactly the
|
||||
// characters draw.io's Latin-1 atob mangles when content= is base64.
|
||||
const CYRILLIC_MODEL =
|
||||
"<mxGraphModel><root>" +
|
||||
'<mxCell id="0"/><mxCell id="1" parent="0"/>' +
|
||||
'<mxCell id="2" value="Старт-бит — ёж" style="rounded=1;html=1;" vertex="1" parent="1">' +
|
||||
'<mxGeometry x="100" y="100" width="120" height="60" as="geometry"/></mxCell>' +
|
||||
"</root></mxGraphModel>";
|
||||
|
||||
test("#507: buildDrawioSvg writes content= as entity-encoded XML (not base64)", () => {
|
||||
const model = normalizeXml(CYRILLIC_MODEL);
|
||||
const svg = buildDrawioSvg(model, "<g/>", { width: 200, height: 120 }, "Диаграмма");
|
||||
|
||||
const contentMatch = /content="([^"]*)"/.exec(svg);
|
||||
assert.ok(contentMatch, "SVG has a single well-formed content= attribute");
|
||||
const content = contentMatch[1];
|
||||
|
||||
// The content= value is the entity-encoded mxfile XML — starts with `<mxfile`.
|
||||
assert.match(content, /^<mxfile/, "content= is entity-encoded mxfile XML");
|
||||
// It must NOT be a base64 blob: base64 has no XML entities and no literal `<`.
|
||||
assert.ok(content.includes("<"), "content= carries XML entities, not base64");
|
||||
|
||||
// Cyrillic / ё / — survive verbatim in the attribute (raw UTF-8, not atob-mangled).
|
||||
assert.ok(content.includes("Старт-бит — ёж"), "non-ASCII value is raw UTF-8 in content=");
|
||||
assert.ok(content.includes("Диаграмма"), "non-ASCII title is raw UTF-8 in content=");
|
||||
// The mojibake that base64+atob would have produced must be absent.
|
||||
assert.ok(!content.includes("Ð"), "no Latin-1 mojibake in content=");
|
||||
});
|
||||
|
||||
test("#507: Cyrillic model round-trips byte-stable through buildDrawioSvg -> decodeDrawioSvg", () => {
|
||||
const model = normalizeXml(CYRILLIC_MODEL);
|
||||
const svg = buildDrawioSvg(model, "<g/>", { width: 200, height: 120 }, "Заголовок — ё");
|
||||
assert.equal(decodeDrawioSvg(svg), model);
|
||||
});
|
||||
|
||||
test("#507 back-compat: an OLD base64-form .drawio.svg still decodes losslessly", () => {
|
||||
const model = normalizeXml(CYRILLIC_MODEL);
|
||||
// Reproduce the pre-fix write path: encodeDrawioFile -> base64 in content=.
|
||||
const file = encodeDrawioFile(model, "Старая диаграмма");
|
||||
const base64 = Buffer.from(file, "utf-8").toString("base64");
|
||||
const svg =
|
||||
`<svg xmlns="http://www.w3.org/2000/svg" content="${base64}"><g/></svg>`;
|
||||
// No XML entities, purely base64 alphabet — this is the legacy form.
|
||||
assert.ok(!base64.includes("<") && !base64.includes("&"));
|
||||
assert.equal(decodeDrawioSvg(svg), model);
|
||||
});
|
||||
|
||||
test("#507 negative: non-ASCII in a cell value AND in the title round-trip clean", () => {
|
||||
const model = normalizeXml(CYRILLIC_MODEL);
|
||||
const title = "Тест — ёмкость № 5";
|
||||
const svg = buildDrawioSvg(model, "<g/>", { width: 200, height: 120 }, title);
|
||||
|
||||
// Model recovered byte-for-byte.
|
||||
assert.equal(decodeDrawioSvg(svg), model);
|
||||
|
||||
// Title lands in the <diagram name="..."> of the decoded file XML, intact.
|
||||
const content = /content="([^"]*)"/.exec(svg)[1];
|
||||
const fileXml = unescapeAttr(content);
|
||||
const nameMatch = /<diagram id="[^"]*" name="([^"]*)">/.exec(fileXml);
|
||||
assert.ok(nameMatch, "diagram name attribute present");
|
||||
assert.equal(unescapeAttr(nameMatch[1]), title);
|
||||
});
|
||||
|
||||
// --- #507 F1: literal tab/newline/CR in an attribute value survive the
|
||||
// content= round-trip. The whole mxfile XML lives in one content="..." attr;
|
||||
// XML attribute-value normalization collapses a LITERAL tab/newline/CR to a
|
||||
// single space on DOM read, so the escape must emit numeric char-refs instead.
|
||||
const CTRL_MODEL =
|
||||
"<mxGraphModel><root>" +
|
||||
'<mxCell id="0"/><mxCell id="1" parent="0"/>' +
|
||||
'<mxCell id="2" value="col1\tcol2" style="html=1;\nshadow=0" vertex="1" parent="1">' +
|
||||
'<mxGeometry x="10" y="10" width="120" height="60" as="geometry"/></mxCell>' +
|
||||
'<mxCell id="3" value="Line1\nLine2\rLine3" vertex="1" parent="1">' +
|
||||
'<mxGeometry x="10" y="100" width="120" height="60" as="geometry"/></mxCell>' +
|
||||
"</root></mxGraphModel>";
|
||||
|
||||
test("#507 F1: literal tab/newline/CR in a value round-trip byte-stable (DOM decode)", () => {
|
||||
const svg = buildDrawioSvg(CTRL_MODEL, "<g/>", { width: 200, height: 200 });
|
||||
const content = /content="([^"]*)"/.exec(svg)[1];
|
||||
// The tab/newline/CR must be emitted as numeric char-refs, never as literal
|
||||
// control chars (which DOM attribute-value normalization would eat).
|
||||
assert.ok(
|
||||
!/[\t\n\r]/.test(content),
|
||||
"no literal tab/newline/CR survive in the content= attribute",
|
||||
);
|
||||
assert.ok(
|
||||
content.includes("	") &&
|
||||
content.includes("
") &&
|
||||
content.includes("
"),
|
||||
"tab/newline/CR are emitted as numeric char-refs",
|
||||
);
|
||||
// Full DOM decode recovers the model byte-for-byte, control chars intact.
|
||||
assert.equal(decodeDrawioSvg(svg), CTRL_MODEL);
|
||||
});
|
||||
|
||||
test("#507 F1: regex fallback decodes tab/newline/CR char-refs (agrees with DOM path)", () => {
|
||||
const svg = buildDrawioSvg(CTRL_MODEL, "<g/>", { width: 200, height: 200 });
|
||||
const content = /content="([^"]*)"/.exec(svg)[1];
|
||||
// A bare `&` makes the SVG wrapper malformed, forcing extractContentAttr onto
|
||||
// its regex fallback branch. That branch must decode the tab/newline/CR
|
||||
// char-refs exactly like the DOM path, or the two decoders diverge.
|
||||
const malformedSvg = `<svg content="${content}">&</svg>`;
|
||||
assert.equal(decodeDrawioSvg(malformedSvg), CTRL_MODEL);
|
||||
// The well-formed (DOM) path yields the identical result.
|
||||
assert.equal(decodeDrawioSvg(svg), CTRL_MODEL);
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user