mirror of
https://github.com/langgenius/dify.git
synced 2026-01-19 13:40:07 +00:00
Compare commits
18 Commits
feature/ta
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
62ac02a568 | ||
|
|
2d4289a925 | ||
|
|
88780c7eb7 | ||
|
|
0f1db88dcb | ||
|
|
92dbc94f2f | ||
|
|
9f09414dbe | ||
|
|
b3902374ac | ||
|
|
3b225c01da | ||
|
|
72ce6ca437 | ||
|
|
269c85d5a3 | ||
|
|
b0545635b8 | ||
|
|
13d648cf7b | ||
|
|
e8397ae7a8 | ||
|
|
8893913b3a | ||
|
|
14f123802d | ||
|
|
7b66bbc35a | ||
|
|
77366f33a4 | ||
|
|
e3b0918dd9 |
@@ -1,11 +1,4 @@
|
||||
{
|
||||
"enabledPlugins": {
|
||||
"feature-dev@claude-plugins-official": true,
|
||||
"context7@claude-plugins-official": true,
|
||||
"typescript-lsp@claude-plugins-official": true,
|
||||
"pyright-lsp@claude-plugins-official": true,
|
||||
"ralph-loop@claude-plugins-official": true
|
||||
},
|
||||
"hooks": {
|
||||
"PreToolUse": [
|
||||
{
|
||||
@@ -18,5 +11,10 @@
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"enabledPlugins": {
|
||||
"feature-dev@claude-plugins-official": true,
|
||||
"context7@claude-plugins-official": true,
|
||||
"ralph-loop@claude-plugins-official": true
|
||||
}
|
||||
}
|
||||
|
||||
@@ -83,6 +83,9 @@ vi.mock('next/navigation', () => ({
|
||||
usePathname: () => '/test',
|
||||
}))
|
||||
|
||||
// ✅ Zustand stores: Use real stores (auto-mocked globally)
|
||||
// Set test state with: useAppStore.setState({ ... })
|
||||
|
||||
// Shared state for mocks (if needed)
|
||||
let mockSharedState = false
|
||||
|
||||
@@ -296,7 +299,7 @@ For each test file generated, aim for:
|
||||
For more detailed information, refer to:
|
||||
|
||||
- `references/workflow.md` - **Incremental testing workflow** (MUST READ for multi-file testing)
|
||||
- `references/mocking.md` - Mock patterns and best practices
|
||||
- `references/mocking.md` - Mock patterns, Zustand store testing, and best practices
|
||||
- `references/async-testing.md` - Async operations and API calls
|
||||
- `references/domain-components.md` - Workflow, Dataset, Configuration testing
|
||||
- `references/common-patterns.md` - Frequently used testing patterns
|
||||
|
||||
@@ -37,16 +37,36 @@ Only mock these categories:
|
||||
1. **Third-party libraries with side effects** - `next/navigation`, external SDKs
|
||||
1. **i18n** - Always mock to return keys
|
||||
|
||||
### Zustand Stores - DO NOT Mock Manually
|
||||
|
||||
**Zustand is globally mocked** in `web/vitest.setup.ts`. Use real stores with `setState()`:
|
||||
|
||||
```typescript
|
||||
// ✅ CORRECT: Use real store, set test state
|
||||
import { useAppStore } from '@/app/components/app/store'
|
||||
|
||||
useAppStore.setState({ appDetail: { id: 'test', name: 'Test' } })
|
||||
render(<MyComponent />)
|
||||
|
||||
// ❌ WRONG: Don't mock the store module
|
||||
vi.mock('@/app/components/app/store', () => ({ ... }))
|
||||
```
|
||||
|
||||
See [Zustand Store Testing](#zustand-store-testing) section for full details.
|
||||
|
||||
## Mock Placement
|
||||
|
||||
| Location | Purpose |
|
||||
|----------|---------|
|
||||
| `web/vitest.setup.ts` | Global mocks shared by all tests (for example `react-i18next`, `next/image`) |
|
||||
| `web/vitest.setup.ts` | Global mocks shared by all tests (`react-i18next`, `next/image`, `zustand`) |
|
||||
| `web/__mocks__/zustand.ts` | Zustand mock implementation (auto-resets stores after each test) |
|
||||
| `web/__mocks__/` | Reusable mock factories shared across multiple test files |
|
||||
| Test file | Test-specific mocks, inline with `vi.mock()` |
|
||||
|
||||
Modules are not mocked automatically. Use `vi.mock` in test files, or add global mocks in `web/vitest.setup.ts`.
|
||||
|
||||
**Note**: Zustand is special - it's globally mocked but you should NOT mock store modules manually. See [Zustand Store Testing](#zustand-store-testing).
|
||||
|
||||
## Essential Mocks
|
||||
|
||||
### 1. i18n (Auto-loaded via Global Mock)
|
||||
@@ -276,6 +296,7 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
|
||||
|
||||
1. **Use real base components** - Import from `@/app/components/base/` directly
|
||||
1. **Use real project components** - Prefer importing over mocking
|
||||
1. **Use real Zustand stores** - Set test state via `store.setState()`
|
||||
1. **Reset mocks in `beforeEach`**, not `afterEach`
|
||||
1. **Match actual component behavior** in mocks (when mocking is necessary)
|
||||
1. **Use factory functions** for complex mock data
|
||||
@@ -285,6 +306,7 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
|
||||
### ❌ DON'T
|
||||
|
||||
1. **Don't mock base components** (`Loading`, `Button`, `Tooltip`, etc.)
|
||||
1. **Don't mock Zustand store modules** - Use real stores with `setState()`
|
||||
1. Don't mock components you can import directly
|
||||
1. Don't create overly simplified mocks that miss conditional logic
|
||||
1. Don't forget to clean up nock after each test
|
||||
@@ -308,10 +330,151 @@ Need to use a component in test?
|
||||
├─ Is it a third-party lib with side effects?
|
||||
│ └─ YES → Mock it (next/navigation, external SDKs)
|
||||
│
|
||||
├─ Is it a Zustand store?
|
||||
│ └─ YES → DO NOT mock the module!
|
||||
│ Use real store + setState() to set test state
|
||||
│ (Global mock handles auto-reset)
|
||||
│
|
||||
└─ Is it i18n?
|
||||
└─ YES → Uses shared mock (auto-loaded). Override only for custom translations
|
||||
```
|
||||
|
||||
## Zustand Store Testing
|
||||
|
||||
### Global Zustand Mock (Auto-loaded)
|
||||
|
||||
Zustand is globally mocked in `web/vitest.setup.ts` following the [official Zustand testing guide](https://zustand.docs.pmnd.rs/guides/testing). The mock in `web/__mocks__/zustand.ts` provides:
|
||||
|
||||
- Real store behavior with `getState()`, `setState()`, `subscribe()` methods
|
||||
- Automatic store reset after each test via `afterEach`
|
||||
- Proper test isolation between tests
|
||||
|
||||
### ✅ Recommended: Use Real Stores (Official Best Practice)
|
||||
|
||||
**DO NOT mock store modules manually.** Import and use the real store, then use `setState()` to set test state:
|
||||
|
||||
```typescript
|
||||
// ✅ CORRECT: Use real store with setState
|
||||
import { useAppStore } from '@/app/components/app/store'
|
||||
|
||||
describe('MyComponent', () => {
|
||||
it('should render app details', () => {
|
||||
// Arrange: Set test state via setState
|
||||
useAppStore.setState({
|
||||
appDetail: {
|
||||
id: 'test-app',
|
||||
name: 'Test App',
|
||||
mode: 'chat',
|
||||
},
|
||||
})
|
||||
|
||||
// Act
|
||||
render(<MyComponent />)
|
||||
|
||||
// Assert
|
||||
expect(screen.getByText('Test App')).toBeInTheDocument()
|
||||
// Can also verify store state directly
|
||||
expect(useAppStore.getState().appDetail?.name).toBe('Test App')
|
||||
})
|
||||
|
||||
// No cleanup needed - global mock auto-resets after each test
|
||||
})
|
||||
```
|
||||
|
||||
### ❌ Avoid: Manual Store Module Mocking
|
||||
|
||||
Manual mocking conflicts with the global Zustand mock and loses store functionality:
|
||||
|
||||
```typescript
|
||||
// ❌ WRONG: Don't mock the store module
|
||||
vi.mock('@/app/components/app/store', () => ({
|
||||
useStore: (selector) => mockSelector(selector), // Missing getState, setState!
|
||||
}))
|
||||
|
||||
// ❌ WRONG: This conflicts with global zustand mock
|
||||
vi.mock('@/app/components/workflow/store', () => ({
|
||||
useWorkflowStore: vi.fn(() => mockState),
|
||||
}))
|
||||
```
|
||||
|
||||
**Problems with manual mocking:**
|
||||
|
||||
1. Loses `getState()`, `setState()`, `subscribe()` methods
|
||||
1. Conflicts with global Zustand mock behavior
|
||||
1. Requires manual maintenance of store API
|
||||
1. Tests don't reflect actual store behavior
|
||||
|
||||
### When Manual Store Mocking is Necessary
|
||||
|
||||
In rare cases where the store has complex initialization or side effects, you can mock it, but ensure you provide the full store API:
|
||||
|
||||
```typescript
|
||||
// If you MUST mock (rare), include full store API
|
||||
const mockStore = {
|
||||
appDetail: { id: 'test', name: 'Test' },
|
||||
setAppDetail: vi.fn(),
|
||||
}
|
||||
|
||||
vi.mock('@/app/components/app/store', () => ({
|
||||
useStore: Object.assign(
|
||||
(selector: (state: typeof mockStore) => unknown) => selector(mockStore),
|
||||
{
|
||||
getState: () => mockStore,
|
||||
setState: vi.fn(),
|
||||
subscribe: vi.fn(),
|
||||
},
|
||||
),
|
||||
}))
|
||||
```
|
||||
|
||||
### Store Testing Decision Tree
|
||||
|
||||
```
|
||||
Need to test a component using Zustand store?
|
||||
│
|
||||
├─ Can you use the real store?
|
||||
│ └─ YES → Use real store + setState (RECOMMENDED)
|
||||
│ useAppStore.setState({ ... })
|
||||
│
|
||||
├─ Does the store have complex initialization/side effects?
|
||||
│ └─ YES → Consider mocking, but include full API
|
||||
│ (getState, setState, subscribe)
|
||||
│
|
||||
└─ Are you testing the store itself (not a component)?
|
||||
└─ YES → Test store directly with getState/setState
|
||||
const store = useMyStore
|
||||
store.setState({ count: 0 })
|
||||
store.getState().increment()
|
||||
expect(store.getState().count).toBe(1)
|
||||
```
|
||||
|
||||
### Example: Testing Store Actions
|
||||
|
||||
```typescript
|
||||
import { useCounterStore } from '@/stores/counter'
|
||||
|
||||
describe('Counter Store', () => {
|
||||
it('should increment count', () => {
|
||||
// Initial state (auto-reset by global mock)
|
||||
expect(useCounterStore.getState().count).toBe(0)
|
||||
|
||||
// Call action
|
||||
useCounterStore.getState().increment()
|
||||
|
||||
// Verify state change
|
||||
expect(useCounterStore.getState().count).toBe(1)
|
||||
})
|
||||
|
||||
it('should reset to initial state', () => {
|
||||
// Set some state
|
||||
useCounterStore.setState({ count: 100 })
|
||||
expect(useCounterStore.getState().count).toBe(100)
|
||||
|
||||
// After this test, global mock will reset to initial state
|
||||
})
|
||||
})
|
||||
```
|
||||
|
||||
## Factory Function Pattern
|
||||
|
||||
```typescript
|
||||
|
||||
2410
.claude/skills/vercel-react-best-practices/AGENTS.md
Normal file
2410
.claude/skills/vercel-react-best-practices/AGENTS.md
Normal file
File diff suppressed because it is too large
Load Diff
125
.claude/skills/vercel-react-best-practices/SKILL.md
Normal file
125
.claude/skills/vercel-react-best-practices/SKILL.md
Normal file
@@ -0,0 +1,125 @@
|
||||
---
|
||||
name: vercel-react-best-practices
|
||||
description: React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
|
||||
license: MIT
|
||||
metadata:
|
||||
author: vercel
|
||||
version: "1.0.0"
|
||||
---
|
||||
|
||||
# Vercel React Best Practices
|
||||
|
||||
Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 45 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
|
||||
|
||||
## When to Apply
|
||||
|
||||
Reference these guidelines when:
|
||||
- Writing new React components or Next.js pages
|
||||
- Implementing data fetching (client or server-side)
|
||||
- Reviewing code for performance issues
|
||||
- Refactoring existing React/Next.js code
|
||||
- Optimizing bundle size or load times
|
||||
|
||||
## Rule Categories by Priority
|
||||
|
||||
| Priority | Category | Impact | Prefix |
|
||||
|----------|----------|--------|--------|
|
||||
| 1 | Eliminating Waterfalls | CRITICAL | `async-` |
|
||||
| 2 | Bundle Size Optimization | CRITICAL | `bundle-` |
|
||||
| 3 | Server-Side Performance | HIGH | `server-` |
|
||||
| 4 | Client-Side Data Fetching | MEDIUM-HIGH | `client-` |
|
||||
| 5 | Re-render Optimization | MEDIUM | `rerender-` |
|
||||
| 6 | Rendering Performance | MEDIUM | `rendering-` |
|
||||
| 7 | JavaScript Performance | LOW-MEDIUM | `js-` |
|
||||
| 8 | Advanced Patterns | LOW | `advanced-` |
|
||||
|
||||
## Quick Reference
|
||||
|
||||
### 1. Eliminating Waterfalls (CRITICAL)
|
||||
|
||||
- `async-defer-await` - Move await into branches where actually used
|
||||
- `async-parallel` - Use Promise.all() for independent operations
|
||||
- `async-dependencies` - Use better-all for partial dependencies
|
||||
- `async-api-routes` - Start promises early, await late in API routes
|
||||
- `async-suspense-boundaries` - Use Suspense to stream content
|
||||
|
||||
### 2. Bundle Size Optimization (CRITICAL)
|
||||
|
||||
- `bundle-barrel-imports` - Import directly, avoid barrel files
|
||||
- `bundle-dynamic-imports` - Use next/dynamic for heavy components
|
||||
- `bundle-defer-third-party` - Load analytics/logging after hydration
|
||||
- `bundle-conditional` - Load modules only when feature is activated
|
||||
- `bundle-preload` - Preload on hover/focus for perceived speed
|
||||
|
||||
### 3. Server-Side Performance (HIGH)
|
||||
|
||||
- `server-cache-react` - Use React.cache() for per-request deduplication
|
||||
- `server-cache-lru` - Use LRU cache for cross-request caching
|
||||
- `server-serialization` - Minimize data passed to client components
|
||||
- `server-parallel-fetching` - Restructure components to parallelize fetches
|
||||
- `server-after-nonblocking` - Use after() for non-blocking operations
|
||||
|
||||
### 4. Client-Side Data Fetching (MEDIUM-HIGH)
|
||||
|
||||
- `client-swr-dedup` - Use SWR for automatic request deduplication
|
||||
- `client-event-listeners` - Deduplicate global event listeners
|
||||
|
||||
### 5. Re-render Optimization (MEDIUM)
|
||||
|
||||
- `rerender-defer-reads` - Don't subscribe to state only used in callbacks
|
||||
- `rerender-memo` - Extract expensive work into memoized components
|
||||
- `rerender-dependencies` - Use primitive dependencies in effects
|
||||
- `rerender-derived-state` - Subscribe to derived booleans, not raw values
|
||||
- `rerender-functional-setstate` - Use functional setState for stable callbacks
|
||||
- `rerender-lazy-state-init` - Pass function to useState for expensive values
|
||||
- `rerender-transitions` - Use startTransition for non-urgent updates
|
||||
|
||||
### 6. Rendering Performance (MEDIUM)
|
||||
|
||||
- `rendering-animate-svg-wrapper` - Animate div wrapper, not SVG element
|
||||
- `rendering-content-visibility` - Use content-visibility for long lists
|
||||
- `rendering-hoist-jsx` - Extract static JSX outside components
|
||||
- `rendering-svg-precision` - Reduce SVG coordinate precision
|
||||
- `rendering-hydration-no-flicker` - Use inline script for client-only data
|
||||
- `rendering-activity` - Use Activity component for show/hide
|
||||
- `rendering-conditional-render` - Use ternary, not && for conditionals
|
||||
|
||||
### 7. JavaScript Performance (LOW-MEDIUM)
|
||||
|
||||
- `js-batch-dom-css` - Group CSS changes via classes or cssText
|
||||
- `js-index-maps` - Build Map for repeated lookups
|
||||
- `js-cache-property-access` - Cache object properties in loops
|
||||
- `js-cache-function-results` - Cache function results in module-level Map
|
||||
- `js-cache-storage` - Cache localStorage/sessionStorage reads
|
||||
- `js-combine-iterations` - Combine multiple filter/map into one loop
|
||||
- `js-length-check-first` - Check array length before expensive comparison
|
||||
- `js-early-exit` - Return early from functions
|
||||
- `js-hoist-regexp` - Hoist RegExp creation outside loops
|
||||
- `js-min-max-loop` - Use loop for min/max instead of sort
|
||||
- `js-set-map-lookups` - Use Set/Map for O(1) lookups
|
||||
- `js-tosorted-immutable` - Use toSorted() for immutability
|
||||
|
||||
### 8. Advanced Patterns (LOW)
|
||||
|
||||
- `advanced-event-handler-refs` - Store event handlers in refs
|
||||
- `advanced-use-latest` - useLatest for stable callback refs
|
||||
|
||||
## How to Use
|
||||
|
||||
Read individual rule files for detailed explanations and code examples:
|
||||
|
||||
```
|
||||
rules/async-parallel.md
|
||||
rules/bundle-barrel-imports.md
|
||||
rules/_sections.md
|
||||
```
|
||||
|
||||
Each rule file contains:
|
||||
- Brief explanation of why it matters
|
||||
- Incorrect code example with explanation
|
||||
- Correct code example with explanation
|
||||
- Additional context and references
|
||||
|
||||
## Full Compiled Document
|
||||
|
||||
For the complete guide with all rules expanded: `AGENTS.md`
|
||||
@@ -0,0 +1,55 @@
|
||||
---
|
||||
title: Store Event Handlers in Refs
|
||||
impact: LOW
|
||||
impactDescription: stable subscriptions
|
||||
tags: advanced, hooks, refs, event-handlers, optimization
|
||||
---
|
||||
|
||||
## Store Event Handlers in Refs
|
||||
|
||||
Store callbacks in refs when used in effects that shouldn't re-subscribe on callback changes.
|
||||
|
||||
**Incorrect (re-subscribes on every render):**
|
||||
|
||||
```tsx
|
||||
function useWindowEvent(event: string, handler: (e) => void) {
|
||||
useEffect(() => {
|
||||
window.addEventListener(event, handler)
|
||||
return () => window.removeEventListener(event, handler)
|
||||
}, [event, handler])
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (stable subscription):**
|
||||
|
||||
```tsx
|
||||
function useWindowEvent(event: string, handler: (e) => void) {
|
||||
const handlerRef = useRef(handler)
|
||||
useEffect(() => {
|
||||
handlerRef.current = handler
|
||||
}, [handler])
|
||||
|
||||
useEffect(() => {
|
||||
const listener = (e) => handlerRef.current(e)
|
||||
window.addEventListener(event, listener)
|
||||
return () => window.removeEventListener(event, listener)
|
||||
}, [event])
|
||||
}
|
||||
```
|
||||
|
||||
**Alternative: use `useEffectEvent` if you're on latest React:**
|
||||
|
||||
```tsx
|
||||
import { useEffectEvent } from 'react'
|
||||
|
||||
function useWindowEvent(event: string, handler: (e) => void) {
|
||||
const onEvent = useEffectEvent(handler)
|
||||
|
||||
useEffect(() => {
|
||||
window.addEventListener(event, onEvent)
|
||||
return () => window.removeEventListener(event, onEvent)
|
||||
}, [event])
|
||||
}
|
||||
```
|
||||
|
||||
`useEffectEvent` provides a cleaner API for the same pattern: it creates a stable function reference that always calls the latest version of the handler.
|
||||
@@ -0,0 +1,49 @@
|
||||
---
|
||||
title: useLatest for Stable Callback Refs
|
||||
impact: LOW
|
||||
impactDescription: prevents effect re-runs
|
||||
tags: advanced, hooks, useLatest, refs, optimization
|
||||
---
|
||||
|
||||
## useLatest for Stable Callback Refs
|
||||
|
||||
Access latest values in callbacks without adding them to dependency arrays. Prevents effect re-runs while avoiding stale closures.
|
||||
|
||||
**Implementation:**
|
||||
|
||||
```typescript
|
||||
function useLatest<T>(value: T) {
|
||||
const ref = useRef(value)
|
||||
useLayoutEffect(() => {
|
||||
ref.current = value
|
||||
}, [value])
|
||||
return ref
|
||||
}
|
||||
```
|
||||
|
||||
**Incorrect (effect re-runs on every callback change):**
|
||||
|
||||
```tsx
|
||||
function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
|
||||
const [query, setQuery] = useState('')
|
||||
|
||||
useEffect(() => {
|
||||
const timeout = setTimeout(() => onSearch(query), 300)
|
||||
return () => clearTimeout(timeout)
|
||||
}, [query, onSearch])
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (stable effect, fresh callback):**
|
||||
|
||||
```tsx
|
||||
function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
|
||||
const [query, setQuery] = useState('')
|
||||
const onSearchRef = useLatest(onSearch)
|
||||
|
||||
useEffect(() => {
|
||||
const timeout = setTimeout(() => onSearchRef.current(query), 300)
|
||||
return () => clearTimeout(timeout)
|
||||
}, [query])
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
title: Prevent Waterfall Chains in API Routes
|
||||
impact: CRITICAL
|
||||
impactDescription: 2-10× improvement
|
||||
tags: api-routes, server-actions, waterfalls, parallelization
|
||||
---
|
||||
|
||||
## Prevent Waterfall Chains in API Routes
|
||||
|
||||
In API routes and Server Actions, start independent operations immediately, even if you don't await them yet.
|
||||
|
||||
**Incorrect (config waits for auth, data waits for both):**
|
||||
|
||||
```typescript
|
||||
export async function GET(request: Request) {
|
||||
const session = await auth()
|
||||
const config = await fetchConfig()
|
||||
const data = await fetchData(session.user.id)
|
||||
return Response.json({ data, config })
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (auth and config start immediately):**
|
||||
|
||||
```typescript
|
||||
export async function GET(request: Request) {
|
||||
const sessionPromise = auth()
|
||||
const configPromise = fetchConfig()
|
||||
const session = await sessionPromise
|
||||
const [config, data] = await Promise.all([
|
||||
configPromise,
|
||||
fetchData(session.user.id)
|
||||
])
|
||||
return Response.json({ data, config })
|
||||
}
|
||||
```
|
||||
|
||||
For operations with more complex dependency chains, use `better-all` to automatically maximize parallelism (see Dependency-Based Parallelization).
|
||||
@@ -0,0 +1,80 @@
|
||||
---
|
||||
title: Defer Await Until Needed
|
||||
impact: HIGH
|
||||
impactDescription: avoids blocking unused code paths
|
||||
tags: async, await, conditional, optimization
|
||||
---
|
||||
|
||||
## Defer Await Until Needed
|
||||
|
||||
Move `await` operations into the branches where they're actually used to avoid blocking code paths that don't need them.
|
||||
|
||||
**Incorrect (blocks both branches):**
|
||||
|
||||
```typescript
|
||||
async function handleRequest(userId: string, skipProcessing: boolean) {
|
||||
const userData = await fetchUserData(userId)
|
||||
|
||||
if (skipProcessing) {
|
||||
// Returns immediately but still waited for userData
|
||||
return { skipped: true }
|
||||
}
|
||||
|
||||
// Only this branch uses userData
|
||||
return processUserData(userData)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (only blocks when needed):**
|
||||
|
||||
```typescript
|
||||
async function handleRequest(userId: string, skipProcessing: boolean) {
|
||||
if (skipProcessing) {
|
||||
// Returns immediately without waiting
|
||||
return { skipped: true }
|
||||
}
|
||||
|
||||
// Fetch only when needed
|
||||
const userData = await fetchUserData(userId)
|
||||
return processUserData(userData)
|
||||
}
|
||||
```
|
||||
|
||||
**Another example (early return optimization):**
|
||||
|
||||
```typescript
|
||||
// Incorrect: always fetches permissions
|
||||
async function updateResource(resourceId: string, userId: string) {
|
||||
const permissions = await fetchPermissions(userId)
|
||||
const resource = await getResource(resourceId)
|
||||
|
||||
if (!resource) {
|
||||
return { error: 'Not found' }
|
||||
}
|
||||
|
||||
if (!permissions.canEdit) {
|
||||
return { error: 'Forbidden' }
|
||||
}
|
||||
|
||||
return await updateResourceData(resource, permissions)
|
||||
}
|
||||
|
||||
// Correct: fetches only when needed
|
||||
async function updateResource(resourceId: string, userId: string) {
|
||||
const resource = await getResource(resourceId)
|
||||
|
||||
if (!resource) {
|
||||
return { error: 'Not found' }
|
||||
}
|
||||
|
||||
const permissions = await fetchPermissions(userId)
|
||||
|
||||
if (!permissions.canEdit) {
|
||||
return { error: 'Forbidden' }
|
||||
}
|
||||
|
||||
return await updateResourceData(resource, permissions)
|
||||
}
|
||||
```
|
||||
|
||||
This optimization is especially valuable when the skipped branch is frequently taken, or when the deferred operation is expensive.
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
title: Dependency-Based Parallelization
|
||||
impact: CRITICAL
|
||||
impactDescription: 2-10× improvement
|
||||
tags: async, parallelization, dependencies, better-all
|
||||
---
|
||||
|
||||
## Dependency-Based Parallelization
|
||||
|
||||
For operations with partial dependencies, use `better-all` to maximize parallelism. It automatically starts each task at the earliest possible moment.
|
||||
|
||||
**Incorrect (profile waits for config unnecessarily):**
|
||||
|
||||
```typescript
|
||||
const [user, config] = await Promise.all([
|
||||
fetchUser(),
|
||||
fetchConfig()
|
||||
])
|
||||
const profile = await fetchProfile(user.id)
|
||||
```
|
||||
|
||||
**Correct (config and profile run in parallel):**
|
||||
|
||||
```typescript
|
||||
import { all } from 'better-all'
|
||||
|
||||
const { user, config, profile } = await all({
|
||||
async user() { return fetchUser() },
|
||||
async config() { return fetchConfig() },
|
||||
async profile() {
|
||||
return fetchProfile((await this.$.user).id)
|
||||
}
|
||||
})
|
||||
```
|
||||
|
||||
Reference: [https://github.com/shuding/better-all](https://github.com/shuding/better-all)
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
title: Promise.all() for Independent Operations
|
||||
impact: CRITICAL
|
||||
impactDescription: 2-10× improvement
|
||||
tags: async, parallelization, promises, waterfalls
|
||||
---
|
||||
|
||||
## Promise.all() for Independent Operations
|
||||
|
||||
When async operations have no interdependencies, execute them concurrently using `Promise.all()`.
|
||||
|
||||
**Incorrect (sequential execution, 3 round trips):**
|
||||
|
||||
```typescript
|
||||
const user = await fetchUser()
|
||||
const posts = await fetchPosts()
|
||||
const comments = await fetchComments()
|
||||
```
|
||||
|
||||
**Correct (parallel execution, 1 round trip):**
|
||||
|
||||
```typescript
|
||||
const [user, posts, comments] = await Promise.all([
|
||||
fetchUser(),
|
||||
fetchPosts(),
|
||||
fetchComments()
|
||||
])
|
||||
```
|
||||
@@ -0,0 +1,99 @@
|
||||
---
|
||||
title: Strategic Suspense Boundaries
|
||||
impact: HIGH
|
||||
impactDescription: faster initial paint
|
||||
tags: async, suspense, streaming, layout-shift
|
||||
---
|
||||
|
||||
## Strategic Suspense Boundaries
|
||||
|
||||
Instead of awaiting data in async components before returning JSX, use Suspense boundaries to show the wrapper UI faster while data loads.
|
||||
|
||||
**Incorrect (wrapper blocked by data fetching):**
|
||||
|
||||
```tsx
|
||||
async function Page() {
|
||||
const data = await fetchData() // Blocks entire page
|
||||
|
||||
return (
|
||||
<div>
|
||||
<div>Sidebar</div>
|
||||
<div>Header</div>
|
||||
<div>
|
||||
<DataDisplay data={data} />
|
||||
</div>
|
||||
<div>Footer</div>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
The entire layout waits for data even though only the middle section needs it.
|
||||
|
||||
**Correct (wrapper shows immediately, data streams in):**
|
||||
|
||||
```tsx
|
||||
function Page() {
|
||||
return (
|
||||
<div>
|
||||
<div>Sidebar</div>
|
||||
<div>Header</div>
|
||||
<div>
|
||||
<Suspense fallback={<Skeleton />}>
|
||||
<DataDisplay />
|
||||
</Suspense>
|
||||
</div>
|
||||
<div>Footer</div>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
async function DataDisplay() {
|
||||
const data = await fetchData() // Only blocks this component
|
||||
return <div>{data.content}</div>
|
||||
}
|
||||
```
|
||||
|
||||
Sidebar, Header, and Footer render immediately. Only DataDisplay waits for data.
|
||||
|
||||
**Alternative (share promise across components):**
|
||||
|
||||
```tsx
|
||||
function Page() {
|
||||
// Start fetch immediately, but don't await
|
||||
const dataPromise = fetchData()
|
||||
|
||||
return (
|
||||
<div>
|
||||
<div>Sidebar</div>
|
||||
<div>Header</div>
|
||||
<Suspense fallback={<Skeleton />}>
|
||||
<DataDisplay dataPromise={dataPromise} />
|
||||
<DataSummary dataPromise={dataPromise} />
|
||||
</Suspense>
|
||||
<div>Footer</div>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
function DataDisplay({ dataPromise }: { dataPromise: Promise<Data> }) {
|
||||
const data = use(dataPromise) // Unwraps the promise
|
||||
return <div>{data.content}</div>
|
||||
}
|
||||
|
||||
function DataSummary({ dataPromise }: { dataPromise: Promise<Data> }) {
|
||||
const data = use(dataPromise) // Reuses the same promise
|
||||
return <div>{data.summary}</div>
|
||||
}
|
||||
```
|
||||
|
||||
Both components share the same promise, so only one fetch occurs. Layout renders immediately while both components wait together.
|
||||
|
||||
**When NOT to use this pattern:**
|
||||
|
||||
- Critical data needed for layout decisions (affects positioning)
|
||||
- SEO-critical content above the fold
|
||||
- Small, fast queries where suspense overhead isn't worth it
|
||||
- When you want to avoid layout shift (loading → content jump)
|
||||
|
||||
**Trade-off:** Faster initial paint vs potential layout shift. Choose based on your UX priorities.
|
||||
@@ -0,0 +1,59 @@
|
||||
---
|
||||
title: Avoid Barrel File Imports
|
||||
impact: CRITICAL
|
||||
impactDescription: 200-800ms import cost, slow builds
|
||||
tags: bundle, imports, tree-shaking, barrel-files, performance
|
||||
---
|
||||
|
||||
## Avoid Barrel File Imports
|
||||
|
||||
Import directly from source files instead of barrel files to avoid loading thousands of unused modules. **Barrel files** are entry points that re-export multiple modules (e.g., `index.js` that does `export * from './module'`).
|
||||
|
||||
Popular icon and component libraries can have **up to 10,000 re-exports** in their entry file. For many React packages, **it takes 200-800ms just to import them**, affecting both development speed and production cold starts.
|
||||
|
||||
**Why tree-shaking doesn't help:** When a library is marked as external (not bundled), the bundler can't optimize it. If you bundle it to enable tree-shaking, builds become substantially slower analyzing the entire module graph.
|
||||
|
||||
**Incorrect (imports entire library):**
|
||||
|
||||
```tsx
|
||||
import { Check, X, Menu } from 'lucide-react'
|
||||
// Loads 1,583 modules, takes ~2.8s extra in dev
|
||||
// Runtime cost: 200-800ms on every cold start
|
||||
|
||||
import { Button, TextField } from '@mui/material'
|
||||
// Loads 2,225 modules, takes ~4.2s extra in dev
|
||||
```
|
||||
|
||||
**Correct (imports only what you need):**
|
||||
|
||||
```tsx
|
||||
import Check from 'lucide-react/dist/esm/icons/check'
|
||||
import X from 'lucide-react/dist/esm/icons/x'
|
||||
import Menu from 'lucide-react/dist/esm/icons/menu'
|
||||
// Loads only 3 modules (~2KB vs ~1MB)
|
||||
|
||||
import Button from '@mui/material/Button'
|
||||
import TextField from '@mui/material/TextField'
|
||||
// Loads only what you use
|
||||
```
|
||||
|
||||
**Alternative (Next.js 13.5+):**
|
||||
|
||||
```js
|
||||
// next.config.js - use optimizePackageImports
|
||||
module.exports = {
|
||||
experimental: {
|
||||
optimizePackageImports: ['lucide-react', '@mui/material']
|
||||
}
|
||||
}
|
||||
|
||||
// Then you can keep the ergonomic barrel imports:
|
||||
import { Check, X, Menu } from 'lucide-react'
|
||||
// Automatically transformed to direct imports at build time
|
||||
```
|
||||
|
||||
Direct imports provide 15-70% faster dev boot, 28% faster builds, 40% faster cold starts, and significantly faster HMR.
|
||||
|
||||
Libraries commonly affected: `lucide-react`, `@mui/material`, `@mui/icons-material`, `@tabler/icons-react`, `react-icons`, `@headlessui/react`, `@radix-ui/react-*`, `lodash`, `ramda`, `date-fns`, `rxjs`, `react-use`.
|
||||
|
||||
Reference: [How we optimized package imports in Next.js](https://vercel.com/blog/how-we-optimized-package-imports-in-next-js)
|
||||
@@ -0,0 +1,31 @@
|
||||
---
|
||||
title: Conditional Module Loading
|
||||
impact: HIGH
|
||||
impactDescription: loads large data only when needed
|
||||
tags: bundle, conditional-loading, lazy-loading
|
||||
---
|
||||
|
||||
## Conditional Module Loading
|
||||
|
||||
Load large data or modules only when a feature is activated.
|
||||
|
||||
**Example (lazy-load animation frames):**
|
||||
|
||||
```tsx
|
||||
function AnimationPlayer({ enabled, setEnabled }: { enabled: boolean; setEnabled: React.Dispatch<React.SetStateAction<boolean>> }) {
|
||||
const [frames, setFrames] = useState<Frame[] | null>(null)
|
||||
|
||||
useEffect(() => {
|
||||
if (enabled && !frames && typeof window !== 'undefined') {
|
||||
import('./animation-frames.js')
|
||||
.then(mod => setFrames(mod.frames))
|
||||
.catch(() => setEnabled(false))
|
||||
}
|
||||
}, [enabled, frames, setEnabled])
|
||||
|
||||
if (!frames) return <Skeleton />
|
||||
return <Canvas frames={frames} />
|
||||
}
|
||||
```
|
||||
|
||||
The `typeof window !== 'undefined'` check prevents bundling this module for SSR, optimizing server bundle size and build speed.
|
||||
@@ -0,0 +1,49 @@
|
||||
---
|
||||
title: Defer Non-Critical Third-Party Libraries
|
||||
impact: MEDIUM
|
||||
impactDescription: loads after hydration
|
||||
tags: bundle, third-party, analytics, defer
|
||||
---
|
||||
|
||||
## Defer Non-Critical Third-Party Libraries
|
||||
|
||||
Analytics, logging, and error tracking don't block user interaction. Load them after hydration.
|
||||
|
||||
**Incorrect (blocks initial bundle):**
|
||||
|
||||
```tsx
|
||||
import { Analytics } from '@vercel/analytics/react'
|
||||
|
||||
export default function RootLayout({ children }) {
|
||||
return (
|
||||
<html>
|
||||
<body>
|
||||
{children}
|
||||
<Analytics />
|
||||
</body>
|
||||
</html>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (loads after hydration):**
|
||||
|
||||
```tsx
|
||||
import dynamic from 'next/dynamic'
|
||||
|
||||
const Analytics = dynamic(
|
||||
() => import('@vercel/analytics/react').then(m => m.Analytics),
|
||||
{ ssr: false }
|
||||
)
|
||||
|
||||
export default function RootLayout({ children }) {
|
||||
return (
|
||||
<html>
|
||||
<body>
|
||||
{children}
|
||||
<Analytics />
|
||||
</body>
|
||||
</html>
|
||||
)
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,35 @@
|
||||
---
|
||||
title: Dynamic Imports for Heavy Components
|
||||
impact: CRITICAL
|
||||
impactDescription: directly affects TTI and LCP
|
||||
tags: bundle, dynamic-import, code-splitting, next-dynamic
|
||||
---
|
||||
|
||||
## Dynamic Imports for Heavy Components
|
||||
|
||||
Use `next/dynamic` to lazy-load large components not needed on initial render.
|
||||
|
||||
**Incorrect (Monaco bundles with main chunk ~300KB):**
|
||||
|
||||
```tsx
|
||||
import { MonacoEditor } from './monaco-editor'
|
||||
|
||||
function CodePanel({ code }: { code: string }) {
|
||||
return <MonacoEditor value={code} />
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (Monaco loads on demand):**
|
||||
|
||||
```tsx
|
||||
import dynamic from 'next/dynamic'
|
||||
|
||||
const MonacoEditor = dynamic(
|
||||
() => import('./monaco-editor').then(m => m.MonacoEditor),
|
||||
{ ssr: false }
|
||||
)
|
||||
|
||||
function CodePanel({ code }: { code: string }) {
|
||||
return <MonacoEditor value={code} />
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: Preload Based on User Intent
|
||||
impact: MEDIUM
|
||||
impactDescription: reduces perceived latency
|
||||
tags: bundle, preload, user-intent, hover
|
||||
---
|
||||
|
||||
## Preload Based on User Intent
|
||||
|
||||
Preload heavy bundles before they're needed to reduce perceived latency.
|
||||
|
||||
**Example (preload on hover/focus):**
|
||||
|
||||
```tsx
|
||||
function EditorButton({ onClick }: { onClick: () => void }) {
|
||||
const preload = () => {
|
||||
if (typeof window !== 'undefined') {
|
||||
void import('./monaco-editor')
|
||||
}
|
||||
}
|
||||
|
||||
return (
|
||||
<button
|
||||
onMouseEnter={preload}
|
||||
onFocus={preload}
|
||||
onClick={onClick}
|
||||
>
|
||||
Open Editor
|
||||
</button>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Example (preload when feature flag is enabled):**
|
||||
|
||||
```tsx
|
||||
function FlagsProvider({ children, flags }: Props) {
|
||||
useEffect(() => {
|
||||
if (flags.editorEnabled && typeof window !== 'undefined') {
|
||||
void import('./monaco-editor').then(mod => mod.init())
|
||||
}
|
||||
}, [flags.editorEnabled])
|
||||
|
||||
return <FlagsContext.Provider value={flags}>
|
||||
{children}
|
||||
</FlagsContext.Provider>
|
||||
}
|
||||
```
|
||||
|
||||
The `typeof window !== 'undefined'` check prevents bundling preloaded modules for SSR, optimizing server bundle size and build speed.
|
||||
@@ -0,0 +1,74 @@
|
||||
---
|
||||
title: Deduplicate Global Event Listeners
|
||||
impact: LOW
|
||||
impactDescription: single listener for N components
|
||||
tags: client, swr, event-listeners, subscription
|
||||
---
|
||||
|
||||
## Deduplicate Global Event Listeners
|
||||
|
||||
Use `useSWRSubscription()` to share global event listeners across component instances.
|
||||
|
||||
**Incorrect (N instances = N listeners):**
|
||||
|
||||
```tsx
|
||||
function useKeyboardShortcut(key: string, callback: () => void) {
|
||||
useEffect(() => {
|
||||
const handler = (e: KeyboardEvent) => {
|
||||
if (e.metaKey && e.key === key) {
|
||||
callback()
|
||||
}
|
||||
}
|
||||
window.addEventListener('keydown', handler)
|
||||
return () => window.removeEventListener('keydown', handler)
|
||||
}, [key, callback])
|
||||
}
|
||||
```
|
||||
|
||||
When using the `useKeyboardShortcut` hook multiple times, each instance will register a new listener.
|
||||
|
||||
**Correct (N instances = 1 listener):**
|
||||
|
||||
```tsx
|
||||
import useSWRSubscription from 'swr/subscription'
|
||||
|
||||
// Module-level Map to track callbacks per key
|
||||
const keyCallbacks = new Map<string, Set<() => void>>()
|
||||
|
||||
function useKeyboardShortcut(key: string, callback: () => void) {
|
||||
// Register this callback in the Map
|
||||
useEffect(() => {
|
||||
if (!keyCallbacks.has(key)) {
|
||||
keyCallbacks.set(key, new Set())
|
||||
}
|
||||
keyCallbacks.get(key)!.add(callback)
|
||||
|
||||
return () => {
|
||||
const set = keyCallbacks.get(key)
|
||||
if (set) {
|
||||
set.delete(callback)
|
||||
if (set.size === 0) {
|
||||
keyCallbacks.delete(key)
|
||||
}
|
||||
}
|
||||
}
|
||||
}, [key, callback])
|
||||
|
||||
useSWRSubscription('global-keydown', () => {
|
||||
const handler = (e: KeyboardEvent) => {
|
||||
if (e.metaKey && keyCallbacks.has(e.key)) {
|
||||
keyCallbacks.get(e.key)!.forEach(cb => cb())
|
||||
}
|
||||
}
|
||||
window.addEventListener('keydown', handler)
|
||||
return () => window.removeEventListener('keydown', handler)
|
||||
})
|
||||
}
|
||||
|
||||
function Profile() {
|
||||
// Multiple shortcuts will share the same listener
|
||||
useKeyboardShortcut('p', () => { /* ... */ })
|
||||
useKeyboardShortcut('k', () => { /* ... */ })
|
||||
// ...
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,71 @@
|
||||
---
|
||||
title: Version and Minimize localStorage Data
|
||||
impact: MEDIUM
|
||||
impactDescription: prevents schema conflicts, reduces storage size
|
||||
tags: client, localStorage, storage, versioning, data-minimization
|
||||
---
|
||||
|
||||
## Version and Minimize localStorage Data
|
||||
|
||||
Add version prefix to keys and store only needed fields. Prevents schema conflicts and accidental storage of sensitive data.
|
||||
|
||||
**Incorrect:**
|
||||
|
||||
```typescript
|
||||
// No version, stores everything, no error handling
|
||||
localStorage.setItem('userConfig', JSON.stringify(fullUserObject))
|
||||
const data = localStorage.getItem('userConfig')
|
||||
```
|
||||
|
||||
**Correct:**
|
||||
|
||||
```typescript
|
||||
const VERSION = 'v2'
|
||||
|
||||
function saveConfig(config: { theme: string; language: string }) {
|
||||
try {
|
||||
localStorage.setItem(`userConfig:${VERSION}`, JSON.stringify(config))
|
||||
} catch {
|
||||
// Throws in incognito/private browsing, quota exceeded, or disabled
|
||||
}
|
||||
}
|
||||
|
||||
function loadConfig() {
|
||||
try {
|
||||
const data = localStorage.getItem(`userConfig:${VERSION}`)
|
||||
return data ? JSON.parse(data) : null
|
||||
} catch {
|
||||
return null
|
||||
}
|
||||
}
|
||||
|
||||
// Migration from v1 to v2
|
||||
function migrate() {
|
||||
try {
|
||||
const v1 = localStorage.getItem('userConfig:v1')
|
||||
if (v1) {
|
||||
const old = JSON.parse(v1)
|
||||
saveConfig({ theme: old.darkMode ? 'dark' : 'light', language: old.lang })
|
||||
localStorage.removeItem('userConfig:v1')
|
||||
}
|
||||
} catch {}
|
||||
}
|
||||
```
|
||||
|
||||
**Store minimal fields from server responses:**
|
||||
|
||||
```typescript
|
||||
// User object has 20+ fields, only store what UI needs
|
||||
function cachePrefs(user: FullUser) {
|
||||
try {
|
||||
localStorage.setItem('prefs:v1', JSON.stringify({
|
||||
theme: user.preferences.theme,
|
||||
notifications: user.preferences.notifications
|
||||
}))
|
||||
} catch {}
|
||||
}
|
||||
```
|
||||
|
||||
**Always wrap in try-catch:** `getItem()` and `setItem()` throw in incognito/private browsing (Safari, Firefox), when quota exceeded, or when disabled.
|
||||
|
||||
**Benefits:** Schema evolution via versioning, reduced storage size, prevents storing tokens/PII/internal flags.
|
||||
@@ -0,0 +1,48 @@
|
||||
---
|
||||
title: Use Passive Event Listeners for Scrolling Performance
|
||||
impact: MEDIUM
|
||||
impactDescription: eliminates scroll delay caused by event listeners
|
||||
tags: client, event-listeners, scrolling, performance, touch, wheel
|
||||
---
|
||||
|
||||
## Use Passive Event Listeners for Scrolling Performance
|
||||
|
||||
Add `{ passive: true }` to touch and wheel event listeners to enable immediate scrolling. Browsers normally wait for listeners to finish to check if `preventDefault()` is called, causing scroll delay.
|
||||
|
||||
**Incorrect:**
|
||||
|
||||
```typescript
|
||||
useEffect(() => {
|
||||
const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX)
|
||||
const handleWheel = (e: WheelEvent) => console.log(e.deltaY)
|
||||
|
||||
document.addEventListener('touchstart', handleTouch)
|
||||
document.addEventListener('wheel', handleWheel)
|
||||
|
||||
return () => {
|
||||
document.removeEventListener('touchstart', handleTouch)
|
||||
document.removeEventListener('wheel', handleWheel)
|
||||
}
|
||||
}, [])
|
||||
```
|
||||
|
||||
**Correct:**
|
||||
|
||||
```typescript
|
||||
useEffect(() => {
|
||||
const handleTouch = (e: TouchEvent) => console.log(e.touches[0].clientX)
|
||||
const handleWheel = (e: WheelEvent) => console.log(e.deltaY)
|
||||
|
||||
document.addEventListener('touchstart', handleTouch, { passive: true })
|
||||
document.addEventListener('wheel', handleWheel, { passive: true })
|
||||
|
||||
return () => {
|
||||
document.removeEventListener('touchstart', handleTouch)
|
||||
document.removeEventListener('wheel', handleWheel)
|
||||
}
|
||||
}, [])
|
||||
```
|
||||
|
||||
**Use passive when:** tracking/analytics, logging, any listener that doesn't call `preventDefault()`.
|
||||
|
||||
**Don't use passive when:** implementing custom swipe gestures, custom zoom controls, or any listener that needs `preventDefault()`.
|
||||
@@ -0,0 +1,56 @@
|
||||
---
|
||||
title: Use SWR for Automatic Deduplication
|
||||
impact: MEDIUM-HIGH
|
||||
impactDescription: automatic deduplication
|
||||
tags: client, swr, deduplication, data-fetching
|
||||
---
|
||||
|
||||
## Use SWR for Automatic Deduplication
|
||||
|
||||
SWR enables request deduplication, caching, and revalidation across component instances.
|
||||
|
||||
**Incorrect (no deduplication, each instance fetches):**
|
||||
|
||||
```tsx
|
||||
function UserList() {
|
||||
const [users, setUsers] = useState([])
|
||||
useEffect(() => {
|
||||
fetch('/api/users')
|
||||
.then(r => r.json())
|
||||
.then(setUsers)
|
||||
}, [])
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (multiple instances share one request):**
|
||||
|
||||
```tsx
|
||||
import useSWR from 'swr'
|
||||
|
||||
function UserList() {
|
||||
const { data: users } = useSWR('/api/users', fetcher)
|
||||
}
|
||||
```
|
||||
|
||||
**For immutable data:**
|
||||
|
||||
```tsx
|
||||
import { useImmutableSWR } from '@/lib/swr'
|
||||
|
||||
function StaticContent() {
|
||||
const { data } = useImmutableSWR('/api/config', fetcher)
|
||||
}
|
||||
```
|
||||
|
||||
**For mutations:**
|
||||
|
||||
```tsx
|
||||
import { useSWRMutation } from 'swr/mutation'
|
||||
|
||||
function UpdateButton() {
|
||||
const { trigger } = useSWRMutation('/api/user', updateUser)
|
||||
return <button onClick={() => trigger()}>Update</button>
|
||||
}
|
||||
```
|
||||
|
||||
Reference: [https://swr.vercel.app](https://swr.vercel.app)
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: Batch DOM CSS Changes
|
||||
impact: MEDIUM
|
||||
impactDescription: reduces reflows/repaints
|
||||
tags: javascript, dom, css, performance, reflow
|
||||
---
|
||||
|
||||
## Batch DOM CSS Changes
|
||||
|
||||
Avoid interleaving style writes with layout reads. When you read a layout property (like `offsetWidth`, `getBoundingClientRect()`, or `getComputedStyle()`) between style changes, the browser is forced to trigger a synchronous reflow.
|
||||
|
||||
**Incorrect (interleaved reads and writes force reflows):**
|
||||
|
||||
```typescript
|
||||
function updateElementStyles(element: HTMLElement) {
|
||||
element.style.width = '100px'
|
||||
const width = element.offsetWidth // Forces reflow
|
||||
element.style.height = '200px'
|
||||
const height = element.offsetHeight // Forces another reflow
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (batch writes, then read once):**
|
||||
|
||||
```typescript
|
||||
function updateElementStyles(element: HTMLElement) {
|
||||
// Batch all writes together
|
||||
element.style.width = '100px'
|
||||
element.style.height = '200px'
|
||||
element.style.backgroundColor = 'blue'
|
||||
element.style.border = '1px solid black'
|
||||
|
||||
// Read after all writes are done (single reflow)
|
||||
const { width, height } = element.getBoundingClientRect()
|
||||
}
|
||||
```
|
||||
|
||||
**Better: use CSS classes**
|
||||
|
||||
```css
|
||||
.highlighted-box {
|
||||
width: 100px;
|
||||
height: 200px;
|
||||
background-color: blue;
|
||||
border: 1px solid black;
|
||||
}
|
||||
```
|
||||
|
||||
```typescript
|
||||
function updateElementStyles(element: HTMLElement) {
|
||||
element.classList.add('highlighted-box')
|
||||
|
||||
const { width, height } = element.getBoundingClientRect()
|
||||
}
|
||||
```
|
||||
|
||||
Prefer CSS classes over inline styles when possible. CSS files are cached by the browser, and classes provide better separation of concerns and are easier to maintain.
|
||||
@@ -0,0 +1,80 @@
|
||||
---
|
||||
title: Cache Repeated Function Calls
|
||||
impact: MEDIUM
|
||||
impactDescription: avoid redundant computation
|
||||
tags: javascript, cache, memoization, performance
|
||||
---
|
||||
|
||||
## Cache Repeated Function Calls
|
||||
|
||||
Use a module-level Map to cache function results when the same function is called repeatedly with the same inputs during render.
|
||||
|
||||
**Incorrect (redundant computation):**
|
||||
|
||||
```typescript
|
||||
function ProjectList({ projects }: { projects: Project[] }) {
|
||||
return (
|
||||
<div>
|
||||
{projects.map(project => {
|
||||
// slugify() called 100+ times for same project names
|
||||
const slug = slugify(project.name)
|
||||
|
||||
return <ProjectCard key={project.id} slug={slug} />
|
||||
})}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (cached results):**
|
||||
|
||||
```typescript
|
||||
// Module-level cache
|
||||
const slugifyCache = new Map<string, string>()
|
||||
|
||||
function cachedSlugify(text: string): string {
|
||||
if (slugifyCache.has(text)) {
|
||||
return slugifyCache.get(text)!
|
||||
}
|
||||
const result = slugify(text)
|
||||
slugifyCache.set(text, result)
|
||||
return result
|
||||
}
|
||||
|
||||
function ProjectList({ projects }: { projects: Project[] }) {
|
||||
return (
|
||||
<div>
|
||||
{projects.map(project => {
|
||||
// Computed only once per unique project name
|
||||
const slug = cachedSlugify(project.name)
|
||||
|
||||
return <ProjectCard key={project.id} slug={slug} />
|
||||
})}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Simpler pattern for single-value functions:**
|
||||
|
||||
```typescript
|
||||
let isLoggedInCache: boolean | null = null
|
||||
|
||||
function isLoggedIn(): boolean {
|
||||
if (isLoggedInCache !== null) {
|
||||
return isLoggedInCache
|
||||
}
|
||||
|
||||
isLoggedInCache = document.cookie.includes('auth=')
|
||||
return isLoggedInCache
|
||||
}
|
||||
|
||||
// Clear cache when auth changes
|
||||
function onAuthChange() {
|
||||
isLoggedInCache = null
|
||||
}
|
||||
```
|
||||
|
||||
Use a Map (not a hook) so it works everywhere: utilities, event handlers, not just React components.
|
||||
|
||||
Reference: [How we made the Vercel Dashboard twice as fast](https://vercel.com/blog/how-we-made-the-vercel-dashboard-twice-as-fast)
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
title: Cache Property Access in Loops
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: reduces lookups
|
||||
tags: javascript, loops, optimization, caching
|
||||
---
|
||||
|
||||
## Cache Property Access in Loops
|
||||
|
||||
Cache object property lookups in hot paths.
|
||||
|
||||
**Incorrect (3 lookups × N iterations):**
|
||||
|
||||
```typescript
|
||||
for (let i = 0; i < arr.length; i++) {
|
||||
process(obj.config.settings.value)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (1 lookup total):**
|
||||
|
||||
```typescript
|
||||
const value = obj.config.settings.value
|
||||
const len = arr.length
|
||||
for (let i = 0; i < len; i++) {
|
||||
process(value)
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,70 @@
|
||||
---
|
||||
title: Cache Storage API Calls
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: reduces expensive I/O
|
||||
tags: javascript, localStorage, storage, caching, performance
|
||||
---
|
||||
|
||||
## Cache Storage API Calls
|
||||
|
||||
`localStorage`, `sessionStorage`, and `document.cookie` are synchronous and expensive. Cache reads in memory.
|
||||
|
||||
**Incorrect (reads storage on every call):**
|
||||
|
||||
```typescript
|
||||
function getTheme() {
|
||||
return localStorage.getItem('theme') ?? 'light'
|
||||
}
|
||||
// Called 10 times = 10 storage reads
|
||||
```
|
||||
|
||||
**Correct (Map cache):**
|
||||
|
||||
```typescript
|
||||
const storageCache = new Map<string, string | null>()
|
||||
|
||||
function getLocalStorage(key: string) {
|
||||
if (!storageCache.has(key)) {
|
||||
storageCache.set(key, localStorage.getItem(key))
|
||||
}
|
||||
return storageCache.get(key)
|
||||
}
|
||||
|
||||
function setLocalStorage(key: string, value: string) {
|
||||
localStorage.setItem(key, value)
|
||||
storageCache.set(key, value) // keep cache in sync
|
||||
}
|
||||
```
|
||||
|
||||
Use a Map (not a hook) so it works everywhere: utilities, event handlers, not just React components.
|
||||
|
||||
**Cookie caching:**
|
||||
|
||||
```typescript
|
||||
let cookieCache: Record<string, string> | null = null
|
||||
|
||||
function getCookie(name: string) {
|
||||
if (!cookieCache) {
|
||||
cookieCache = Object.fromEntries(
|
||||
document.cookie.split('; ').map(c => c.split('='))
|
||||
)
|
||||
}
|
||||
return cookieCache[name]
|
||||
}
|
||||
```
|
||||
|
||||
**Important (invalidate on external changes):**
|
||||
|
||||
If storage can change externally (another tab, server-set cookies), invalidate cache:
|
||||
|
||||
```typescript
|
||||
window.addEventListener('storage', (e) => {
|
||||
if (e.key) storageCache.delete(e.key)
|
||||
})
|
||||
|
||||
document.addEventListener('visibilitychange', () => {
|
||||
if (document.visibilityState === 'visible') {
|
||||
storageCache.clear()
|
||||
}
|
||||
})
|
||||
```
|
||||
@@ -0,0 +1,32 @@
|
||||
---
|
||||
title: Combine Multiple Array Iterations
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: reduces iterations
|
||||
tags: javascript, arrays, loops, performance
|
||||
---
|
||||
|
||||
## Combine Multiple Array Iterations
|
||||
|
||||
Multiple `.filter()` or `.map()` calls iterate the array multiple times. Combine into one loop.
|
||||
|
||||
**Incorrect (3 iterations):**
|
||||
|
||||
```typescript
|
||||
const admins = users.filter(u => u.isAdmin)
|
||||
const testers = users.filter(u => u.isTester)
|
||||
const inactive = users.filter(u => !u.isActive)
|
||||
```
|
||||
|
||||
**Correct (1 iteration):**
|
||||
|
||||
```typescript
|
||||
const admins: User[] = []
|
||||
const testers: User[] = []
|
||||
const inactive: User[] = []
|
||||
|
||||
for (const user of users) {
|
||||
if (user.isAdmin) admins.push(user)
|
||||
if (user.isTester) testers.push(user)
|
||||
if (!user.isActive) inactive.push(user)
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: Early Return from Functions
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: avoids unnecessary computation
|
||||
tags: javascript, functions, optimization, early-return
|
||||
---
|
||||
|
||||
## Early Return from Functions
|
||||
|
||||
Return early when result is determined to skip unnecessary processing.
|
||||
|
||||
**Incorrect (processes all items even after finding answer):**
|
||||
|
||||
```typescript
|
||||
function validateUsers(users: User[]) {
|
||||
let hasError = false
|
||||
let errorMessage = ''
|
||||
|
||||
for (const user of users) {
|
||||
if (!user.email) {
|
||||
hasError = true
|
||||
errorMessage = 'Email required'
|
||||
}
|
||||
if (!user.name) {
|
||||
hasError = true
|
||||
errorMessage = 'Name required'
|
||||
}
|
||||
// Continues checking all users even after error found
|
||||
}
|
||||
|
||||
return hasError ? { valid: false, error: errorMessage } : { valid: true }
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (returns immediately on first error):**
|
||||
|
||||
```typescript
|
||||
function validateUsers(users: User[]) {
|
||||
for (const user of users) {
|
||||
if (!user.email) {
|
||||
return { valid: false, error: 'Email required' }
|
||||
}
|
||||
if (!user.name) {
|
||||
return { valid: false, error: 'Name required' }
|
||||
}
|
||||
}
|
||||
|
||||
return { valid: true }
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: Hoist RegExp Creation
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: avoids recreation
|
||||
tags: javascript, regexp, optimization, memoization
|
||||
---
|
||||
|
||||
## Hoist RegExp Creation
|
||||
|
||||
Don't create RegExp inside render. Hoist to module scope or memoize with `useMemo()`.
|
||||
|
||||
**Incorrect (new RegExp every render):**
|
||||
|
||||
```tsx
|
||||
function Highlighter({ text, query }: Props) {
|
||||
const regex = new RegExp(`(${query})`, 'gi')
|
||||
const parts = text.split(regex)
|
||||
return <>{parts.map((part, i) => ...)}</>
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (memoize or hoist):**
|
||||
|
||||
```tsx
|
||||
const EMAIL_REGEX = /^[^\s@]+@[^\s@]+\.[^\s@]+$/
|
||||
|
||||
function Highlighter({ text, query }: Props) {
|
||||
const regex = useMemo(
|
||||
() => new RegExp(`(${escapeRegex(query)})`, 'gi'),
|
||||
[query]
|
||||
)
|
||||
const parts = text.split(regex)
|
||||
return <>{parts.map((part, i) => ...)}</>
|
||||
}
|
||||
```
|
||||
|
||||
**Warning (global regex has mutable state):**
|
||||
|
||||
Global regex (`/g`) has mutable `lastIndex` state:
|
||||
|
||||
```typescript
|
||||
const regex = /foo/g
|
||||
regex.test('foo') // true, lastIndex = 3
|
||||
regex.test('foo') // false, lastIndex = 0
|
||||
```
|
||||
@@ -0,0 +1,37 @@
|
||||
---
|
||||
title: Build Index Maps for Repeated Lookups
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: 1M ops to 2K ops
|
||||
tags: javascript, map, indexing, optimization, performance
|
||||
---
|
||||
|
||||
## Build Index Maps for Repeated Lookups
|
||||
|
||||
Multiple `.find()` calls by the same key should use a Map.
|
||||
|
||||
**Incorrect (O(n) per lookup):**
|
||||
|
||||
```typescript
|
||||
function processOrders(orders: Order[], users: User[]) {
|
||||
return orders.map(order => ({
|
||||
...order,
|
||||
user: users.find(u => u.id === order.userId)
|
||||
}))
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (O(1) per lookup):**
|
||||
|
||||
```typescript
|
||||
function processOrders(orders: Order[], users: User[]) {
|
||||
const userById = new Map(users.map(u => [u.id, u]))
|
||||
|
||||
return orders.map(order => ({
|
||||
...order,
|
||||
user: userById.get(order.userId)
|
||||
}))
|
||||
}
|
||||
```
|
||||
|
||||
Build map once (O(n)), then all lookups are O(1).
|
||||
For 1000 orders × 1000 users: 1M ops → 2K ops.
|
||||
@@ -0,0 +1,49 @@
|
||||
---
|
||||
title: Early Length Check for Array Comparisons
|
||||
impact: MEDIUM-HIGH
|
||||
impactDescription: avoids expensive operations when lengths differ
|
||||
tags: javascript, arrays, performance, optimization, comparison
|
||||
---
|
||||
|
||||
## Early Length Check for Array Comparisons
|
||||
|
||||
When comparing arrays with expensive operations (sorting, deep equality, serialization), check lengths first. If lengths differ, the arrays cannot be equal.
|
||||
|
||||
In real-world applications, this optimization is especially valuable when the comparison runs in hot paths (event handlers, render loops).
|
||||
|
||||
**Incorrect (always runs expensive comparison):**
|
||||
|
||||
```typescript
|
||||
function hasChanges(current: string[], original: string[]) {
|
||||
// Always sorts and joins, even when lengths differ
|
||||
return current.sort().join() !== original.sort().join()
|
||||
}
|
||||
```
|
||||
|
||||
Two O(n log n) sorts run even when `current.length` is 5 and `original.length` is 100. There is also overhead of joining the arrays and comparing the strings.
|
||||
|
||||
**Correct (O(1) length check first):**
|
||||
|
||||
```typescript
|
||||
function hasChanges(current: string[], original: string[]) {
|
||||
// Early return if lengths differ
|
||||
if (current.length !== original.length) {
|
||||
return true
|
||||
}
|
||||
// Only sort when lengths match
|
||||
const currentSorted = current.toSorted()
|
||||
const originalSorted = original.toSorted()
|
||||
for (let i = 0; i < currentSorted.length; i++) {
|
||||
if (currentSorted[i] !== originalSorted[i]) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
```
|
||||
|
||||
This new approach is more efficient because:
|
||||
- It avoids the overhead of sorting and joining the arrays when lengths differ
|
||||
- It avoids consuming memory for the joined strings (especially important for large arrays)
|
||||
- It avoids mutating the original arrays
|
||||
- It returns early when a difference is found
|
||||
@@ -0,0 +1,82 @@
|
||||
---
|
||||
title: Use Loop for Min/Max Instead of Sort
|
||||
impact: LOW
|
||||
impactDescription: O(n) instead of O(n log n)
|
||||
tags: javascript, arrays, performance, sorting, algorithms
|
||||
---
|
||||
|
||||
## Use Loop for Min/Max Instead of Sort
|
||||
|
||||
Finding the smallest or largest element only requires a single pass through the array. Sorting is wasteful and slower.
|
||||
|
||||
**Incorrect (O(n log n) - sort to find latest):**
|
||||
|
||||
```typescript
|
||||
interface Project {
|
||||
id: string
|
||||
name: string
|
||||
updatedAt: number
|
||||
}
|
||||
|
||||
function getLatestProject(projects: Project[]) {
|
||||
const sorted = [...projects].sort((a, b) => b.updatedAt - a.updatedAt)
|
||||
return sorted[0]
|
||||
}
|
||||
```
|
||||
|
||||
Sorts the entire array just to find the maximum value.
|
||||
|
||||
**Incorrect (O(n log n) - sort for oldest and newest):**
|
||||
|
||||
```typescript
|
||||
function getOldestAndNewest(projects: Project[]) {
|
||||
const sorted = [...projects].sort((a, b) => a.updatedAt - b.updatedAt)
|
||||
return { oldest: sorted[0], newest: sorted[sorted.length - 1] }
|
||||
}
|
||||
```
|
||||
|
||||
Still sorts unnecessarily when only min/max are needed.
|
||||
|
||||
**Correct (O(n) - single loop):**
|
||||
|
||||
```typescript
|
||||
function getLatestProject(projects: Project[]) {
|
||||
if (projects.length === 0) return null
|
||||
|
||||
let latest = projects[0]
|
||||
|
||||
for (let i = 1; i < projects.length; i++) {
|
||||
if (projects[i].updatedAt > latest.updatedAt) {
|
||||
latest = projects[i]
|
||||
}
|
||||
}
|
||||
|
||||
return latest
|
||||
}
|
||||
|
||||
function getOldestAndNewest(projects: Project[]) {
|
||||
if (projects.length === 0) return { oldest: null, newest: null }
|
||||
|
||||
let oldest = projects[0]
|
||||
let newest = projects[0]
|
||||
|
||||
for (let i = 1; i < projects.length; i++) {
|
||||
if (projects[i].updatedAt < oldest.updatedAt) oldest = projects[i]
|
||||
if (projects[i].updatedAt > newest.updatedAt) newest = projects[i]
|
||||
}
|
||||
|
||||
return { oldest, newest }
|
||||
}
|
||||
```
|
||||
|
||||
Single pass through the array, no copying, no sorting.
|
||||
|
||||
**Alternative (Math.min/Math.max for small arrays):**
|
||||
|
||||
```typescript
|
||||
const numbers = [5, 2, 8, 1, 9]
|
||||
const min = Math.min(...numbers)
|
||||
const max = Math.max(...numbers)
|
||||
```
|
||||
|
||||
This works for small arrays, but can be slower or just throw an error for very large arrays due to spread operator limitations. Maximal array length is approximately 124000 in Chrome 143 and 638000 in Safari 18; exact numbers may vary - see [the fiddle](https://jsfiddle.net/qw1jabsx/4/). Use the loop approach for reliability.
|
||||
@@ -0,0 +1,24 @@
|
||||
---
|
||||
title: Use Set/Map for O(1) Lookups
|
||||
impact: LOW-MEDIUM
|
||||
impactDescription: O(n) to O(1)
|
||||
tags: javascript, set, map, data-structures, performance
|
||||
---
|
||||
|
||||
## Use Set/Map for O(1) Lookups
|
||||
|
||||
Convert arrays to Set/Map for repeated membership checks.
|
||||
|
||||
**Incorrect (O(n) per check):**
|
||||
|
||||
```typescript
|
||||
const allowedIds = ['a', 'b', 'c', ...]
|
||||
items.filter(item => allowedIds.includes(item.id))
|
||||
```
|
||||
|
||||
**Correct (O(1) per check):**
|
||||
|
||||
```typescript
|
||||
const allowedIds = new Set(['a', 'b', 'c', ...])
|
||||
items.filter(item => allowedIds.has(item.id))
|
||||
```
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: Use toSorted() Instead of sort() for Immutability
|
||||
impact: MEDIUM-HIGH
|
||||
impactDescription: prevents mutation bugs in React state
|
||||
tags: javascript, arrays, immutability, react, state, mutation
|
||||
---
|
||||
|
||||
## Use toSorted() Instead of sort() for Immutability
|
||||
|
||||
`.sort()` mutates the array in place, which can cause bugs with React state and props. Use `.toSorted()` to create a new sorted array without mutation.
|
||||
|
||||
**Incorrect (mutates original array):**
|
||||
|
||||
```typescript
|
||||
function UserList({ users }: { users: User[] }) {
|
||||
// Mutates the users prop array!
|
||||
const sorted = useMemo(
|
||||
() => users.sort((a, b) => a.name.localeCompare(b.name)),
|
||||
[users]
|
||||
)
|
||||
return <div>{sorted.map(renderUser)}</div>
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (creates new array):**
|
||||
|
||||
```typescript
|
||||
function UserList({ users }: { users: User[] }) {
|
||||
// Creates new sorted array, original unchanged
|
||||
const sorted = useMemo(
|
||||
() => users.toSorted((a, b) => a.name.localeCompare(b.name)),
|
||||
[users]
|
||||
)
|
||||
return <div>{sorted.map(renderUser)}</div>
|
||||
}
|
||||
```
|
||||
|
||||
**Why this matters in React:**
|
||||
|
||||
1. Props/state mutations break React's immutability model - React expects props and state to be treated as read-only
|
||||
2. Causes stale closure bugs - Mutating arrays inside closures (callbacks, effects) can lead to unexpected behavior
|
||||
|
||||
**Browser support (fallback for older browsers):**
|
||||
|
||||
`.toSorted()` is available in all modern browsers (Chrome 110+, Safari 16+, Firefox 115+, Node.js 20+). For older environments, use spread operator:
|
||||
|
||||
```typescript
|
||||
// Fallback for older browsers
|
||||
const sorted = [...items].sort((a, b) => a.value - b.value)
|
||||
```
|
||||
|
||||
**Other immutable array methods:**
|
||||
|
||||
- `.toSorted()` - immutable sort
|
||||
- `.toReversed()` - immutable reverse
|
||||
- `.toSpliced()` - immutable splice
|
||||
- `.with()` - immutable element replacement
|
||||
@@ -0,0 +1,26 @@
|
||||
---
|
||||
title: Use Activity Component for Show/Hide
|
||||
impact: MEDIUM
|
||||
impactDescription: preserves state/DOM
|
||||
tags: rendering, activity, visibility, state-preservation
|
||||
---
|
||||
|
||||
## Use Activity Component for Show/Hide
|
||||
|
||||
Use React's `<Activity>` to preserve state/DOM for expensive components that frequently toggle visibility.
|
||||
|
||||
**Usage:**
|
||||
|
||||
```tsx
|
||||
import { Activity } from 'react'
|
||||
|
||||
function Dropdown({ isOpen }: Props) {
|
||||
return (
|
||||
<Activity mode={isOpen ? 'visible' : 'hidden'}>
|
||||
<ExpensiveMenu />
|
||||
</Activity>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
Avoids expensive re-renders and state loss.
|
||||
@@ -0,0 +1,47 @@
|
||||
---
|
||||
title: Animate SVG Wrapper Instead of SVG Element
|
||||
impact: LOW
|
||||
impactDescription: enables hardware acceleration
|
||||
tags: rendering, svg, css, animation, performance
|
||||
---
|
||||
|
||||
## Animate SVG Wrapper Instead of SVG Element
|
||||
|
||||
Many browsers don't have hardware acceleration for CSS3 animations on SVG elements. Wrap SVG in a `<div>` and animate the wrapper instead.
|
||||
|
||||
**Incorrect (animating SVG directly - no hardware acceleration):**
|
||||
|
||||
```tsx
|
||||
function LoadingSpinner() {
|
||||
return (
|
||||
<svg
|
||||
className="animate-spin"
|
||||
width="24"
|
||||
height="24"
|
||||
viewBox="0 0 24 24"
|
||||
>
|
||||
<circle cx="12" cy="12" r="10" stroke="currentColor" />
|
||||
</svg>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (animating wrapper div - hardware accelerated):**
|
||||
|
||||
```tsx
|
||||
function LoadingSpinner() {
|
||||
return (
|
||||
<div className="animate-spin">
|
||||
<svg
|
||||
width="24"
|
||||
height="24"
|
||||
viewBox="0 0 24 24"
|
||||
>
|
||||
<circle cx="12" cy="12" r="10" stroke="currentColor" />
|
||||
</svg>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
This applies to all CSS transforms and transitions (`transform`, `opacity`, `translate`, `scale`, `rotate`). The wrapper div allows browsers to use GPU acceleration for smoother animations.
|
||||
@@ -0,0 +1,40 @@
|
||||
---
|
||||
title: Use Explicit Conditional Rendering
|
||||
impact: LOW
|
||||
impactDescription: prevents rendering 0 or NaN
|
||||
tags: rendering, conditional, jsx, falsy-values
|
||||
---
|
||||
|
||||
## Use Explicit Conditional Rendering
|
||||
|
||||
Use explicit ternary operators (`? :`) instead of `&&` for conditional rendering when the condition can be `0`, `NaN`, or other falsy values that render.
|
||||
|
||||
**Incorrect (renders "0" when count is 0):**
|
||||
|
||||
```tsx
|
||||
function Badge({ count }: { count: number }) {
|
||||
return (
|
||||
<div>
|
||||
{count && <span className="badge">{count}</span>}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
// When count = 0, renders: <div>0</div>
|
||||
// When count = 5, renders: <div><span class="badge">5</span></div>
|
||||
```
|
||||
|
||||
**Correct (renders nothing when count is 0):**
|
||||
|
||||
```tsx
|
||||
function Badge({ count }: { count: number }) {
|
||||
return (
|
||||
<div>
|
||||
{count > 0 ? <span className="badge">{count}</span> : null}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
// When count = 0, renders: <div></div>
|
||||
// When count = 5, renders: <div><span class="badge">5</span></div>
|
||||
```
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
title: CSS content-visibility for Long Lists
|
||||
impact: HIGH
|
||||
impactDescription: faster initial render
|
||||
tags: rendering, css, content-visibility, long-lists
|
||||
---
|
||||
|
||||
## CSS content-visibility for Long Lists
|
||||
|
||||
Apply `content-visibility: auto` to defer off-screen rendering.
|
||||
|
||||
**CSS:**
|
||||
|
||||
```css
|
||||
.message-item {
|
||||
content-visibility: auto;
|
||||
contain-intrinsic-size: 0 80px;
|
||||
}
|
||||
```
|
||||
|
||||
**Example:**
|
||||
|
||||
```tsx
|
||||
function MessageList({ messages }: { messages: Message[] }) {
|
||||
return (
|
||||
<div className="overflow-y-auto h-screen">
|
||||
{messages.map(msg => (
|
||||
<div key={msg.id} className="message-item">
|
||||
<Avatar user={msg.author} />
|
||||
<div>{msg.content}</div>
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
For 1000 messages, browser skips layout/paint for ~990 off-screen items (10× faster initial render).
|
||||
@@ -0,0 +1,46 @@
|
||||
---
|
||||
title: Hoist Static JSX Elements
|
||||
impact: LOW
|
||||
impactDescription: avoids re-creation
|
||||
tags: rendering, jsx, static, optimization
|
||||
---
|
||||
|
||||
## Hoist Static JSX Elements
|
||||
|
||||
Extract static JSX outside components to avoid re-creation.
|
||||
|
||||
**Incorrect (recreates element every render):**
|
||||
|
||||
```tsx
|
||||
function LoadingSkeleton() {
|
||||
return <div className="animate-pulse h-20 bg-gray-200" />
|
||||
}
|
||||
|
||||
function Container() {
|
||||
return (
|
||||
<div>
|
||||
{loading && <LoadingSkeleton />}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (reuses same element):**
|
||||
|
||||
```tsx
|
||||
const loadingSkeleton = (
|
||||
<div className="animate-pulse h-20 bg-gray-200" />
|
||||
)
|
||||
|
||||
function Container() {
|
||||
return (
|
||||
<div>
|
||||
{loading && loadingSkeleton}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
This is especially helpful for large and static SVG nodes, which can be expensive to recreate on every render.
|
||||
|
||||
**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, the compiler automatically hoists static JSX elements and optimizes component re-renders, making manual hoisting unnecessary.
|
||||
@@ -0,0 +1,82 @@
|
||||
---
|
||||
title: Prevent Hydration Mismatch Without Flickering
|
||||
impact: MEDIUM
|
||||
impactDescription: avoids visual flicker and hydration errors
|
||||
tags: rendering, ssr, hydration, localStorage, flicker
|
||||
---
|
||||
|
||||
## Prevent Hydration Mismatch Without Flickering
|
||||
|
||||
When rendering content that depends on client-side storage (localStorage, cookies), avoid both SSR breakage and post-hydration flickering by injecting a synchronous script that updates the DOM before React hydrates.
|
||||
|
||||
**Incorrect (breaks SSR):**
|
||||
|
||||
```tsx
|
||||
function ThemeWrapper({ children }: { children: ReactNode }) {
|
||||
// localStorage is not available on server - throws error
|
||||
const theme = localStorage.getItem('theme') || 'light'
|
||||
|
||||
return (
|
||||
<div className={theme}>
|
||||
{children}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
Server-side rendering will fail because `localStorage` is undefined.
|
||||
|
||||
**Incorrect (visual flickering):**
|
||||
|
||||
```tsx
|
||||
function ThemeWrapper({ children }: { children: ReactNode }) {
|
||||
const [theme, setTheme] = useState('light')
|
||||
|
||||
useEffect(() => {
|
||||
// Runs after hydration - causes visible flash
|
||||
const stored = localStorage.getItem('theme')
|
||||
if (stored) {
|
||||
setTheme(stored)
|
||||
}
|
||||
}, [])
|
||||
|
||||
return (
|
||||
<div className={theme}>
|
||||
{children}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
Component first renders with default value (`light`), then updates after hydration, causing a visible flash of incorrect content.
|
||||
|
||||
**Correct (no flicker, no hydration mismatch):**
|
||||
|
||||
```tsx
|
||||
function ThemeWrapper({ children }: { children: ReactNode }) {
|
||||
return (
|
||||
<>
|
||||
<div id="theme-wrapper">
|
||||
{children}
|
||||
</div>
|
||||
<script
|
||||
dangerouslySetInnerHTML={{
|
||||
__html: `
|
||||
(function() {
|
||||
try {
|
||||
var theme = localStorage.getItem('theme') || 'light';
|
||||
var el = document.getElementById('theme-wrapper');
|
||||
if (el) el.className = theme;
|
||||
} catch (e) {}
|
||||
})();
|
||||
`,
|
||||
}}
|
||||
/>
|
||||
</>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
The inline script executes synchronously before showing the element, ensuring the DOM already has the correct value. No flickering, no hydration mismatch.
|
||||
|
||||
This pattern is especially useful for theme toggles, user preferences, authentication states, and any client-only data that should render immediately without flashing default values.
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
title: Optimize SVG Precision
|
||||
impact: LOW
|
||||
impactDescription: reduces file size
|
||||
tags: rendering, svg, optimization, svgo
|
||||
---
|
||||
|
||||
## Optimize SVG Precision
|
||||
|
||||
Reduce SVG coordinate precision to decrease file size. The optimal precision depends on the viewBox size, but in general reducing precision should be considered.
|
||||
|
||||
**Incorrect (excessive precision):**
|
||||
|
||||
```svg
|
||||
<path d="M 10.293847 20.847362 L 30.938472 40.192837" />
|
||||
```
|
||||
|
||||
**Correct (1 decimal place):**
|
||||
|
||||
```svg
|
||||
<path d="M 10.3 20.8 L 30.9 40.2" />
|
||||
```
|
||||
|
||||
**Automate with SVGO:**
|
||||
|
||||
```bash
|
||||
npx svgo --precision=1 --multipass icon.svg
|
||||
```
|
||||
@@ -0,0 +1,39 @@
|
||||
---
|
||||
title: Defer State Reads to Usage Point
|
||||
impact: MEDIUM
|
||||
impactDescription: avoids unnecessary subscriptions
|
||||
tags: rerender, searchParams, localStorage, optimization
|
||||
---
|
||||
|
||||
## Defer State Reads to Usage Point
|
||||
|
||||
Don't subscribe to dynamic state (searchParams, localStorage) if you only read it inside callbacks.
|
||||
|
||||
**Incorrect (subscribes to all searchParams changes):**
|
||||
|
||||
```tsx
|
||||
function ShareButton({ chatId }: { chatId: string }) {
|
||||
const searchParams = useSearchParams()
|
||||
|
||||
const handleShare = () => {
|
||||
const ref = searchParams.get('ref')
|
||||
shareChat(chatId, { ref })
|
||||
}
|
||||
|
||||
return <button onClick={handleShare}>Share</button>
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (reads on demand, no subscription):**
|
||||
|
||||
```tsx
|
||||
function ShareButton({ chatId }: { chatId: string }) {
|
||||
const handleShare = () => {
|
||||
const params = new URLSearchParams(window.location.search)
|
||||
const ref = params.get('ref')
|
||||
shareChat(chatId, { ref })
|
||||
}
|
||||
|
||||
return <button onClick={handleShare}>Share</button>
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: Narrow Effect Dependencies
|
||||
impact: LOW
|
||||
impactDescription: minimizes effect re-runs
|
||||
tags: rerender, useEffect, dependencies, optimization
|
||||
---
|
||||
|
||||
## Narrow Effect Dependencies
|
||||
|
||||
Specify primitive dependencies instead of objects to minimize effect re-runs.
|
||||
|
||||
**Incorrect (re-runs on any user field change):**
|
||||
|
||||
```tsx
|
||||
useEffect(() => {
|
||||
console.log(user.id)
|
||||
}, [user])
|
||||
```
|
||||
|
||||
**Correct (re-runs only when id changes):**
|
||||
|
||||
```tsx
|
||||
useEffect(() => {
|
||||
console.log(user.id)
|
||||
}, [user.id])
|
||||
```
|
||||
|
||||
**For derived state, compute outside effect:**
|
||||
|
||||
```tsx
|
||||
// Incorrect: runs on width=767, 766, 765...
|
||||
useEffect(() => {
|
||||
if (width < 768) {
|
||||
enableMobileMode()
|
||||
}
|
||||
}, [width])
|
||||
|
||||
// Correct: runs only on boolean transition
|
||||
const isMobile = width < 768
|
||||
useEffect(() => {
|
||||
if (isMobile) {
|
||||
enableMobileMode()
|
||||
}
|
||||
}, [isMobile])
|
||||
```
|
||||
@@ -0,0 +1,29 @@
|
||||
---
|
||||
title: Subscribe to Derived State
|
||||
impact: MEDIUM
|
||||
impactDescription: reduces re-render frequency
|
||||
tags: rerender, derived-state, media-query, optimization
|
||||
---
|
||||
|
||||
## Subscribe to Derived State
|
||||
|
||||
Subscribe to derived boolean state instead of continuous values to reduce re-render frequency.
|
||||
|
||||
**Incorrect (re-renders on every pixel change):**
|
||||
|
||||
```tsx
|
||||
function Sidebar() {
|
||||
const width = useWindowWidth() // updates continuously
|
||||
const isMobile = width < 768
|
||||
return <nav className={isMobile ? 'mobile' : 'desktop'} />
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (re-renders only when boolean changes):**
|
||||
|
||||
```tsx
|
||||
function Sidebar() {
|
||||
const isMobile = useMediaQuery('(max-width: 767px)')
|
||||
return <nav className={isMobile ? 'mobile' : 'desktop'} />
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,74 @@
|
||||
---
|
||||
title: Use Functional setState Updates
|
||||
impact: MEDIUM
|
||||
impactDescription: prevents stale closures and unnecessary callback recreations
|
||||
tags: react, hooks, useState, useCallback, callbacks, closures
|
||||
---
|
||||
|
||||
## Use Functional setState Updates
|
||||
|
||||
When updating state based on the current state value, use the functional update form of setState instead of directly referencing the state variable. This prevents stale closures, eliminates unnecessary dependencies, and creates stable callback references.
|
||||
|
||||
**Incorrect (requires state as dependency):**
|
||||
|
||||
```tsx
|
||||
function TodoList() {
|
||||
const [items, setItems] = useState(initialItems)
|
||||
|
||||
// Callback must depend on items, recreated on every items change
|
||||
const addItems = useCallback((newItems: Item[]) => {
|
||||
setItems([...items, ...newItems])
|
||||
}, [items]) // ❌ items dependency causes recreations
|
||||
|
||||
// Risk of stale closure if dependency is forgotten
|
||||
const removeItem = useCallback((id: string) => {
|
||||
setItems(items.filter(item => item.id !== id))
|
||||
}, []) // ❌ Missing items dependency - will use stale items!
|
||||
|
||||
return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
|
||||
}
|
||||
```
|
||||
|
||||
The first callback is recreated every time `items` changes, which can cause child components to re-render unnecessarily. The second callback has a stale closure bug—it will always reference the initial `items` value.
|
||||
|
||||
**Correct (stable callbacks, no stale closures):**
|
||||
|
||||
```tsx
|
||||
function TodoList() {
|
||||
const [items, setItems] = useState(initialItems)
|
||||
|
||||
// Stable callback, never recreated
|
||||
const addItems = useCallback((newItems: Item[]) => {
|
||||
setItems(curr => [...curr, ...newItems])
|
||||
}, []) // ✅ No dependencies needed
|
||||
|
||||
// Always uses latest state, no stale closure risk
|
||||
const removeItem = useCallback((id: string) => {
|
||||
setItems(curr => curr.filter(item => item.id !== id))
|
||||
}, []) // ✅ Safe and stable
|
||||
|
||||
return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
|
||||
}
|
||||
```
|
||||
|
||||
**Benefits:**
|
||||
|
||||
1. **Stable callback references** - Callbacks don't need to be recreated when state changes
|
||||
2. **No stale closures** - Always operates on the latest state value
|
||||
3. **Fewer dependencies** - Simplifies dependency arrays and reduces memory leaks
|
||||
4. **Prevents bugs** - Eliminates the most common source of React closure bugs
|
||||
|
||||
**When to use functional updates:**
|
||||
|
||||
- Any setState that depends on the current state value
|
||||
- Inside useCallback/useMemo when state is needed
|
||||
- Event handlers that reference state
|
||||
- Async operations that update state
|
||||
|
||||
**When direct updates are fine:**
|
||||
|
||||
- Setting state to a static value: `setCount(0)`
|
||||
- Setting state from props/arguments only: `setName(newName)`
|
||||
- State doesn't depend on previous value
|
||||
|
||||
**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, the compiler can automatically optimize some cases, but functional updates are still recommended for correctness and to prevent stale closure bugs.
|
||||
@@ -0,0 +1,58 @@
|
||||
---
|
||||
title: Use Lazy State Initialization
|
||||
impact: MEDIUM
|
||||
impactDescription: wasted computation on every render
|
||||
tags: react, hooks, useState, performance, initialization
|
||||
---
|
||||
|
||||
## Use Lazy State Initialization
|
||||
|
||||
Pass a function to `useState` for expensive initial values. Without the function form, the initializer runs on every render even though the value is only used once.
|
||||
|
||||
**Incorrect (runs on every render):**
|
||||
|
||||
```tsx
|
||||
function FilteredList({ items }: { items: Item[] }) {
|
||||
// buildSearchIndex() runs on EVERY render, even after initialization
|
||||
const [searchIndex, setSearchIndex] = useState(buildSearchIndex(items))
|
||||
const [query, setQuery] = useState('')
|
||||
|
||||
// When query changes, buildSearchIndex runs again unnecessarily
|
||||
return <SearchResults index={searchIndex} query={query} />
|
||||
}
|
||||
|
||||
function UserProfile() {
|
||||
// JSON.parse runs on every render
|
||||
const [settings, setSettings] = useState(
|
||||
JSON.parse(localStorage.getItem('settings') || '{}')
|
||||
)
|
||||
|
||||
return <SettingsForm settings={settings} onChange={setSettings} />
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (runs only once):**
|
||||
|
||||
```tsx
|
||||
function FilteredList({ items }: { items: Item[] }) {
|
||||
// buildSearchIndex() runs ONLY on initial render
|
||||
const [searchIndex, setSearchIndex] = useState(() => buildSearchIndex(items))
|
||||
const [query, setQuery] = useState('')
|
||||
|
||||
return <SearchResults index={searchIndex} query={query} />
|
||||
}
|
||||
|
||||
function UserProfile() {
|
||||
// JSON.parse runs only on initial render
|
||||
const [settings, setSettings] = useState(() => {
|
||||
const stored = localStorage.getItem('settings')
|
||||
return stored ? JSON.parse(stored) : {}
|
||||
})
|
||||
|
||||
return <SettingsForm settings={settings} onChange={setSettings} />
|
||||
}
|
||||
```
|
||||
|
||||
Use lazy initialization when computing initial values from localStorage/sessionStorage, building data structures (indexes, maps), reading from the DOM, or performing heavy transformations.
|
||||
|
||||
For simple primitives (`useState(0)`), direct references (`useState(props.value)`), or cheap literals (`useState({})`), the function form is unnecessary.
|
||||
@@ -0,0 +1,44 @@
|
||||
---
|
||||
title: Extract to Memoized Components
|
||||
impact: MEDIUM
|
||||
impactDescription: enables early returns
|
||||
tags: rerender, memo, useMemo, optimization
|
||||
---
|
||||
|
||||
## Extract to Memoized Components
|
||||
|
||||
Extract expensive work into memoized components to enable early returns before computation.
|
||||
|
||||
**Incorrect (computes avatar even when loading):**
|
||||
|
||||
```tsx
|
||||
function Profile({ user, loading }: Props) {
|
||||
const avatar = useMemo(() => {
|
||||
const id = computeAvatarId(user)
|
||||
return <Avatar id={id} />
|
||||
}, [user])
|
||||
|
||||
if (loading) return <Skeleton />
|
||||
return <div>{avatar}</div>
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (skips computation when loading):**
|
||||
|
||||
```tsx
|
||||
const UserAvatar = memo(function UserAvatar({ user }: { user: User }) {
|
||||
const id = useMemo(() => computeAvatarId(user), [user])
|
||||
return <Avatar id={id} />
|
||||
})
|
||||
|
||||
function Profile({ user, loading }: Props) {
|
||||
if (loading) return <Skeleton />
|
||||
return (
|
||||
<div>
|
||||
<UserAvatar user={user} />
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, manual memoization with `memo()` and `useMemo()` is not necessary. The compiler automatically optimizes re-renders.
|
||||
@@ -0,0 +1,40 @@
|
||||
---
|
||||
title: Use Transitions for Non-Urgent Updates
|
||||
impact: MEDIUM
|
||||
impactDescription: maintains UI responsiveness
|
||||
tags: rerender, transitions, startTransition, performance
|
||||
---
|
||||
|
||||
## Use Transitions for Non-Urgent Updates
|
||||
|
||||
Mark frequent, non-urgent state updates as transitions to maintain UI responsiveness.
|
||||
|
||||
**Incorrect (blocks UI on every scroll):**
|
||||
|
||||
```tsx
|
||||
function ScrollTracker() {
|
||||
const [scrollY, setScrollY] = useState(0)
|
||||
useEffect(() => {
|
||||
const handler = () => setScrollY(window.scrollY)
|
||||
window.addEventListener('scroll', handler, { passive: true })
|
||||
return () => window.removeEventListener('scroll', handler)
|
||||
}, [])
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (non-blocking updates):**
|
||||
|
||||
```tsx
|
||||
import { startTransition } from 'react'
|
||||
|
||||
function ScrollTracker() {
|
||||
const [scrollY, setScrollY] = useState(0)
|
||||
useEffect(() => {
|
||||
const handler = () => {
|
||||
startTransition(() => setScrollY(window.scrollY))
|
||||
}
|
||||
window.addEventListener('scroll', handler, { passive: true })
|
||||
return () => window.removeEventListener('scroll', handler)
|
||||
}, [])
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,73 @@
|
||||
---
|
||||
title: Use after() for Non-Blocking Operations
|
||||
impact: MEDIUM
|
||||
impactDescription: faster response times
|
||||
tags: server, async, logging, analytics, side-effects
|
||||
---
|
||||
|
||||
## Use after() for Non-Blocking Operations
|
||||
|
||||
Use Next.js's `after()` to schedule work that should execute after a response is sent. This prevents logging, analytics, and other side effects from blocking the response.
|
||||
|
||||
**Incorrect (blocks response):**
|
||||
|
||||
```tsx
|
||||
import { logUserAction } from '@/app/utils'
|
||||
|
||||
export async function POST(request: Request) {
|
||||
// Perform mutation
|
||||
await updateDatabase(request)
|
||||
|
||||
// Logging blocks the response
|
||||
const userAgent = request.headers.get('user-agent') || 'unknown'
|
||||
await logUserAction({ userAgent })
|
||||
|
||||
return new Response(JSON.stringify({ status: 'success' }), {
|
||||
status: 200,
|
||||
headers: { 'Content-Type': 'application/json' }
|
||||
})
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (non-blocking):**
|
||||
|
||||
```tsx
|
||||
import { after } from 'next/server'
|
||||
import { headers, cookies } from 'next/headers'
|
||||
import { logUserAction } from '@/app/utils'
|
||||
|
||||
export async function POST(request: Request) {
|
||||
// Perform mutation
|
||||
await updateDatabase(request)
|
||||
|
||||
// Log after response is sent
|
||||
after(async () => {
|
||||
const userAgent = (await headers()).get('user-agent') || 'unknown'
|
||||
const sessionCookie = (await cookies()).get('session-id')?.value || 'anonymous'
|
||||
|
||||
logUserAction({ sessionCookie, userAgent })
|
||||
})
|
||||
|
||||
return new Response(JSON.stringify({ status: 'success' }), {
|
||||
status: 200,
|
||||
headers: { 'Content-Type': 'application/json' }
|
||||
})
|
||||
}
|
||||
```
|
||||
|
||||
The response is sent immediately while logging happens in the background.
|
||||
|
||||
**Common use cases:**
|
||||
|
||||
- Analytics tracking
|
||||
- Audit logging
|
||||
- Sending notifications
|
||||
- Cache invalidation
|
||||
- Cleanup tasks
|
||||
|
||||
**Important notes:**
|
||||
|
||||
- `after()` runs even if the response fails or redirects
|
||||
- Works in Server Actions, Route Handlers, and Server Components
|
||||
|
||||
Reference: [https://nextjs.org/docs/app/api-reference/functions/after](https://nextjs.org/docs/app/api-reference/functions/after)
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: Cross-Request LRU Caching
|
||||
impact: HIGH
|
||||
impactDescription: caches across requests
|
||||
tags: server, cache, lru, cross-request
|
||||
---
|
||||
|
||||
## Cross-Request LRU Caching
|
||||
|
||||
`React.cache()` only works within one request. For data shared across sequential requests (user clicks button A then button B), use an LRU cache.
|
||||
|
||||
**Implementation:**
|
||||
|
||||
```typescript
|
||||
import { LRUCache } from 'lru-cache'
|
||||
|
||||
const cache = new LRUCache<string, any>({
|
||||
max: 1000,
|
||||
ttl: 5 * 60 * 1000 // 5 minutes
|
||||
})
|
||||
|
||||
export async function getUser(id: string) {
|
||||
const cached = cache.get(id)
|
||||
if (cached) return cached
|
||||
|
||||
const user = await db.user.findUnique({ where: { id } })
|
||||
cache.set(id, user)
|
||||
return user
|
||||
}
|
||||
|
||||
// Request 1: DB query, result cached
|
||||
// Request 2: cache hit, no DB query
|
||||
```
|
||||
|
||||
Use when sequential user actions hit multiple endpoints needing the same data within seconds.
|
||||
|
||||
**With Vercel's [Fluid Compute](https://vercel.com/docs/fluid-compute):** LRU caching is especially effective because multiple concurrent requests can share the same function instance and cache. This means the cache persists across requests without needing external storage like Redis.
|
||||
|
||||
**In traditional serverless:** Each invocation runs in isolation, so consider Redis for cross-process caching.
|
||||
|
||||
Reference: [https://github.com/isaacs/node-lru-cache](https://github.com/isaacs/node-lru-cache)
|
||||
@@ -0,0 +1,76 @@
|
||||
---
|
||||
title: Per-Request Deduplication with React.cache()
|
||||
impact: MEDIUM
|
||||
impactDescription: deduplicates within request
|
||||
tags: server, cache, react-cache, deduplication
|
||||
---
|
||||
|
||||
## Per-Request Deduplication with React.cache()
|
||||
|
||||
Use `React.cache()` for server-side request deduplication. Authentication and database queries benefit most.
|
||||
|
||||
**Usage:**
|
||||
|
||||
```typescript
|
||||
import { cache } from 'react'
|
||||
|
||||
export const getCurrentUser = cache(async () => {
|
||||
const session = await auth()
|
||||
if (!session?.user?.id) return null
|
||||
return await db.user.findUnique({
|
||||
where: { id: session.user.id }
|
||||
})
|
||||
})
|
||||
```
|
||||
|
||||
Within a single request, multiple calls to `getCurrentUser()` execute the query only once.
|
||||
|
||||
**Avoid inline objects as arguments:**
|
||||
|
||||
`React.cache()` uses shallow equality (`Object.is`) to determine cache hits. Inline objects create new references each call, preventing cache hits.
|
||||
|
||||
**Incorrect (always cache miss):**
|
||||
|
||||
```typescript
|
||||
const getUser = cache(async (params: { uid: number }) => {
|
||||
return await db.user.findUnique({ where: { id: params.uid } })
|
||||
})
|
||||
|
||||
// Each call creates new object, never hits cache
|
||||
getUser({ uid: 1 })
|
||||
getUser({ uid: 1 }) // Cache miss, runs query again
|
||||
```
|
||||
|
||||
**Correct (cache hit):**
|
||||
|
||||
```typescript
|
||||
const getUser = cache(async (uid: number) => {
|
||||
return await db.user.findUnique({ where: { id: uid } })
|
||||
})
|
||||
|
||||
// Primitive args use value equality
|
||||
getUser(1)
|
||||
getUser(1) // Cache hit, returns cached result
|
||||
```
|
||||
|
||||
If you must pass objects, pass the same reference:
|
||||
|
||||
```typescript
|
||||
const params = { uid: 1 }
|
||||
getUser(params) // Query runs
|
||||
getUser(params) // Cache hit (same reference)
|
||||
```
|
||||
|
||||
**Next.js-Specific Note:**
|
||||
|
||||
In Next.js, the `fetch` API is automatically extended with request memoization. Requests with the same URL and options are automatically deduplicated within a single request, so you don't need `React.cache()` for `fetch` calls. However, `React.cache()` is still essential for other async tasks:
|
||||
|
||||
- Database queries (Prisma, Drizzle, etc.)
|
||||
- Heavy computations
|
||||
- Authentication checks
|
||||
- File system operations
|
||||
- Any non-fetch async work
|
||||
|
||||
Use `React.cache()` to deduplicate these operations across your component tree.
|
||||
|
||||
Reference: [React.cache documentation](https://react.dev/reference/react/cache)
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: Parallel Data Fetching with Component Composition
|
||||
impact: CRITICAL
|
||||
impactDescription: eliminates server-side waterfalls
|
||||
tags: server, rsc, parallel-fetching, composition
|
||||
---
|
||||
|
||||
## Parallel Data Fetching with Component Composition
|
||||
|
||||
React Server Components execute sequentially within a tree. Restructure with composition to parallelize data fetching.
|
||||
|
||||
**Incorrect (Sidebar waits for Page's fetch to complete):**
|
||||
|
||||
```tsx
|
||||
export default async function Page() {
|
||||
const header = await fetchHeader()
|
||||
return (
|
||||
<div>
|
||||
<div>{header}</div>
|
||||
<Sidebar />
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
async function Sidebar() {
|
||||
const items = await fetchSidebarItems()
|
||||
return <nav>{items.map(renderItem)}</nav>
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (both fetch simultaneously):**
|
||||
|
||||
```tsx
|
||||
async function Header() {
|
||||
const data = await fetchHeader()
|
||||
return <div>{data}</div>
|
||||
}
|
||||
|
||||
async function Sidebar() {
|
||||
const items = await fetchSidebarItems()
|
||||
return <nav>{items.map(renderItem)}</nav>
|
||||
}
|
||||
|
||||
export default function Page() {
|
||||
return (
|
||||
<div>
|
||||
<Header />
|
||||
<Sidebar />
|
||||
</div>
|
||||
)
|
||||
}
|
||||
```
|
||||
|
||||
**Alternative with children prop:**
|
||||
|
||||
```tsx
|
||||
async function Header() {
|
||||
const data = await fetchHeader()
|
||||
return <div>{data}</div>
|
||||
}
|
||||
|
||||
async function Sidebar() {
|
||||
const items = await fetchSidebarItems()
|
||||
return <nav>{items.map(renderItem)}</nav>
|
||||
}
|
||||
|
||||
function Layout({ children }: { children: ReactNode }) {
|
||||
return (
|
||||
<div>
|
||||
<Header />
|
||||
{children}
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
export default function Page() {
|
||||
return (
|
||||
<Layout>
|
||||
<Sidebar />
|
||||
</Layout>
|
||||
)
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,38 @@
|
||||
---
|
||||
title: Minimize Serialization at RSC Boundaries
|
||||
impact: HIGH
|
||||
impactDescription: reduces data transfer size
|
||||
tags: server, rsc, serialization, props
|
||||
---
|
||||
|
||||
## Minimize Serialization at RSC Boundaries
|
||||
|
||||
The React Server/Client boundary serializes all object properties into strings and embeds them in the HTML response and subsequent RSC requests. This serialized data directly impacts page weight and load time, so **size matters a lot**. Only pass fields that the client actually uses.
|
||||
|
||||
**Incorrect (serializes all 50 fields):**
|
||||
|
||||
```tsx
|
||||
async function Page() {
|
||||
const user = await fetchUser() // 50 fields
|
||||
return <Profile user={user} />
|
||||
}
|
||||
|
||||
'use client'
|
||||
function Profile({ user }: { user: User }) {
|
||||
return <div>{user.name}</div> // uses 1 field
|
||||
}
|
||||
```
|
||||
|
||||
**Correct (serializes only 1 field):**
|
||||
|
||||
```tsx
|
||||
async function Page() {
|
||||
const user = await fetchUser()
|
||||
return <Profile name={user.name} />
|
||||
}
|
||||
|
||||
'use client'
|
||||
function Profile({ name }: { name: string }) {
|
||||
return <div>{name}</div>
|
||||
}
|
||||
```
|
||||
2
.github/workflows/autofix.yml
vendored
2
.github/workflows/autofix.yml
vendored
@@ -82,6 +82,6 @@ jobs:
|
||||
# mdformat breaks YAML front matter in markdown files. Add --exclude for directories containing YAML front matter.
|
||||
- name: mdformat
|
||||
run: |
|
||||
uvx --python 3.13 mdformat . --exclude ".claude/skills/**/SKILL.md"
|
||||
uvx --python 3.13 mdformat . --exclude ".claude/skills/**"
|
||||
|
||||
- uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27
|
||||
|
||||
10
.github/workflows/style.yml
vendored
10
.github/workflows/style.yml
vendored
@@ -106,8 +106,9 @@ jobs:
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
working-directory: ./web
|
||||
run: |
|
||||
pnpm run lint:report
|
||||
continue-on-error: true
|
||||
pnpm run lint:ci
|
||||
# pnpm run lint:report
|
||||
# continue-on-error: true
|
||||
|
||||
# - name: Annotate Code
|
||||
# if: steps.changed-files.outputs.any_changed == 'true' && github.event_name == 'pull_request'
|
||||
@@ -126,11 +127,6 @@ jobs:
|
||||
working-directory: ./web
|
||||
run: pnpm run knip
|
||||
|
||||
- name: Web build check
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
working-directory: ./web
|
||||
run: pnpm run build
|
||||
|
||||
superlinter:
|
||||
name: SuperLinter
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
45
.github/workflows/web-tests.yml
vendored
45
.github/workflows/web-tests.yml
vendored
@@ -366,3 +366,48 @@ jobs:
|
||||
path: web/coverage
|
||||
retention-days: 30
|
||||
if-no-files-found: error
|
||||
|
||||
web-build:
|
||||
name: Web Build
|
||||
runs-on: ubuntu-latest
|
||||
defaults:
|
||||
run:
|
||||
working-directory: ./web
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v6
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Check changed files
|
||||
id: changed-files
|
||||
uses: tj-actions/changed-files@v47
|
||||
with:
|
||||
files: |
|
||||
web/**
|
||||
.github/workflows/web-tests.yml
|
||||
|
||||
- name: Install pnpm
|
||||
uses: pnpm/action-setup@v4
|
||||
with:
|
||||
package_json_file: web/package.json
|
||||
run_install: false
|
||||
|
||||
- name: Setup NodeJS
|
||||
uses: actions/setup-node@v6
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
with:
|
||||
node-version: 24
|
||||
cache: pnpm
|
||||
cache-dependency-path: ./web/pnpm-lock.yaml
|
||||
|
||||
- name: Web dependencies
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
working-directory: ./web
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Web build check
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
working-directory: ./web
|
||||
run: pnpm run build
|
||||
|
||||
@@ -0,0 +1,52 @@
|
||||
## Purpose
|
||||
|
||||
`api/controllers/console/datasets/datasets_document.py` contains the console (authenticated) APIs for managing dataset documents (list/create/update/delete, processing controls, estimates, etc.).
|
||||
|
||||
## Storage model (uploaded files)
|
||||
|
||||
- For local file uploads into a knowledge base, the binary is stored via `extensions.ext_storage.storage` under the key:
|
||||
- `upload_files/<tenant_id>/<uuid>.<ext>`
|
||||
- File metadata is stored in the `upload_files` table (`UploadFile` model), keyed by `UploadFile.id`.
|
||||
- Dataset `Document` records reference the uploaded file via:
|
||||
- `Document.data_source_info.upload_file_id`
|
||||
|
||||
## Download endpoint
|
||||
|
||||
- `GET /datasets/<dataset_id>/documents/<document_id>/download`
|
||||
|
||||
- Only supported when `Document.data_source_type == "upload_file"`.
|
||||
- Performs dataset permission + tenant checks via `DocumentResource.get_document(...)`.
|
||||
- Delegates `Document -> UploadFile` validation and signed URL generation to `DocumentService.get_document_download_url(...)`.
|
||||
- Applies `cloud_edition_billing_rate_limit_check("knowledge")` to match other KB operations.
|
||||
- Response body is **only**: `{ "url": "<signed-url>" }`.
|
||||
|
||||
- `POST /datasets/<dataset_id>/documents/download-zip`
|
||||
|
||||
- Accepts `{ "document_ids": ["..."] }` (upload-file only).
|
||||
- Returns `application/zip` as a single attachment download.
|
||||
- Rationale: browsers often block multiple automatic downloads; a ZIP avoids that limitation.
|
||||
- Applies `cloud_edition_billing_rate_limit_check("knowledge")`.
|
||||
- Delegates dataset permission checks, document/upload-file validation, and download-name generation to
|
||||
`DocumentService.prepare_document_batch_download_zip(...)` before streaming the ZIP.
|
||||
|
||||
## Verification plan
|
||||
|
||||
- Upload a document from a local file into a dataset.
|
||||
- Call the download endpoint and confirm it returns a signed URL.
|
||||
- Open the URL and confirm:
|
||||
- Response headers force download (`Content-Disposition`), and
|
||||
- Downloaded bytes match the uploaded file.
|
||||
- Select multiple uploaded-file documents and download as ZIP; confirm all selected files exist in the archive.
|
||||
|
||||
## Shared helper
|
||||
|
||||
- `DocumentService.get_document_download_url(document)` resolves the `UploadFile` and signs a download URL.
|
||||
- `DocumentService.prepare_document_batch_download_zip(...)` performs dataset permission checks, batches
|
||||
document + upload file lookups, preserves request order, and generates the client-visible ZIP filename.
|
||||
- Internal helpers now live in `DocumentService` (`_get_upload_file_id_for_upload_file_document(...)`,
|
||||
`_get_upload_file_for_upload_file_document(...)`, `_get_upload_files_by_document_id_for_zip_download(...)`).
|
||||
- ZIP packing is handled by `FileService.build_upload_files_zip_tempfile(...)`, which also:
|
||||
- sanitizes entry names to avoid path traversal, and
|
||||
- deduplicates names while preserving extensions (e.g., `doc.txt` → `doc (1).txt`).
|
||||
Streaming the response and deferring cleanup is handled by the route via `send_file(path, ...)` + `ExitStack` +
|
||||
`response.call_on_close(...)` (the file is deleted when the response is closed).
|
||||
18
api/agent-notes/services/dataset_service.py.md
Normal file
18
api/agent-notes/services/dataset_service.py.md
Normal file
@@ -0,0 +1,18 @@
|
||||
## Purpose
|
||||
|
||||
`api/services/dataset_service.py` hosts dataset/document service logic used by console and API controllers.
|
||||
|
||||
## Batch document operations
|
||||
|
||||
- Batch document workflows should avoid N+1 database queries by using set-based lookups.
|
||||
- Tenant checks must be enforced consistently across dataset/document operations.
|
||||
- `DocumentService.get_documents_by_ids(...)` fetches documents for a dataset using `id.in_(...)`.
|
||||
- `FileService.get_upload_files_by_ids(...)` performs tenant-scoped batch lookup for `UploadFile` (dedupes ids with `set(...)`).
|
||||
- `DocumentService.get_document_download_url(...)` and `prepare_document_batch_download_zip(...)` handle
|
||||
dataset/document permission checks plus `Document -> UploadFile` validation for download endpoints.
|
||||
|
||||
## Verification plan
|
||||
|
||||
- Exercise document list and download endpoints that use the service helpers.
|
||||
- Confirm batch download uses constant query count for documents + upload files.
|
||||
- Request a ZIP with a missing document id and confirm a 404 is returned.
|
||||
35
api/agent-notes/services/file_service.py.md
Normal file
35
api/agent-notes/services/file_service.py.md
Normal file
@@ -0,0 +1,35 @@
|
||||
## Purpose
|
||||
|
||||
`api/services/file_service.py` owns business logic around `UploadFile` objects: upload validation, storage persistence,
|
||||
previews/generators, and deletion.
|
||||
|
||||
## Key invariants
|
||||
|
||||
- All storage I/O goes through `extensions.ext_storage.storage`.
|
||||
- Uploaded file keys follow: `upload_files/<tenant_id>/<uuid>.<ext>`.
|
||||
- Upload validation is enforced in `FileService.upload_file(...)` (blocked extensions, size limits, dataset-only types).
|
||||
|
||||
## Batch lookup helpers
|
||||
|
||||
- `FileService.get_upload_files_by_ids(tenant_id, upload_file_ids)` is the canonical tenant-scoped batch loader for
|
||||
`UploadFile`.
|
||||
|
||||
## Dataset document download helpers
|
||||
|
||||
The dataset document download/ZIP endpoints now delegate “Document → UploadFile” validation and permission checks to
|
||||
`DocumentService` (`api/services/dataset_service.py`). `FileService` stays focused on generic `UploadFile` operations
|
||||
(uploading, previews, deletion), plus generic ZIP serving.
|
||||
|
||||
### ZIP serving
|
||||
|
||||
- `FileService.build_upload_files_zip_tempfile(...)` builds a ZIP from `UploadFile` objects and yields a seeked
|
||||
tempfile **path** so callers can stream it (e.g., `send_file(path, ...)`) without hitting "read of closed file"
|
||||
issues from file-handle lifecycle during streamed responses.
|
||||
- Flask `send_file(...)` and the `ExitStack`/`call_on_close(...)` cleanup pattern are handled in the route layer.
|
||||
|
||||
## Verification plan
|
||||
|
||||
- Unit: `api/tests/unit_tests/controllers/console/datasets/test_datasets_document_download.py`
|
||||
- Verify signed URL generation for upload-file documents and ZIP download behavior for multiple documents.
|
||||
- Unit: `api/tests/unit_tests/services/test_file_service_zip_and_lookup.py`
|
||||
- Verify ZIP packing produces a valid, openable archive and preserves file content.
|
||||
@@ -0,0 +1,28 @@
|
||||
## Purpose
|
||||
|
||||
Unit tests for the console dataset document download endpoint:
|
||||
|
||||
- `GET /datasets/<dataset_id>/documents/<document_id>/download`
|
||||
|
||||
## Testing approach
|
||||
|
||||
- Uses `Flask.test_request_context()` and calls the `Resource.get(...)` method directly.
|
||||
- Monkeypatches console decorators (`login_required`, `setup_required`, rate limit) to no-ops to keep the test focused.
|
||||
- Mocks:
|
||||
- `DatasetService.get_dataset` / `check_dataset_permission`
|
||||
- `DocumentService.get_document` for single-file download tests
|
||||
- `DocumentService.get_documents_by_ids` + `FileService.get_upload_files_by_ids` for ZIP download tests
|
||||
- `FileService.get_upload_files_by_ids` for `UploadFile` lookups in single-file tests
|
||||
- `services.dataset_service.file_helpers.get_signed_file_url` to return a deterministic URL
|
||||
- Document mocks include `id` fields so batch lookups can map documents by id.
|
||||
|
||||
## Covered cases
|
||||
|
||||
- Success returns `{ "url": "<signed>" }` for upload-file documents.
|
||||
- 404 when document is not `upload_file`.
|
||||
- 404 when `upload_file_id` is missing.
|
||||
- 404 when referenced `UploadFile` row does not exist.
|
||||
- 403 when document tenant does not match current tenant.
|
||||
- Batch ZIP download returns `application/zip` for upload-file documents.
|
||||
- Batch ZIP download rejects non-upload-file documents.
|
||||
- Batch ZIP download uses a random `.zip` attachment name (`download_name`), so tests only assert the suffix.
|
||||
@@ -0,0 +1,18 @@
|
||||
## Purpose
|
||||
|
||||
Unit tests for `api/services/file_service.py` helper methods that are not covered by higher-level controller tests.
|
||||
|
||||
## What’s covered
|
||||
|
||||
- `FileService.build_upload_files_zip_tempfile(...)`
|
||||
- ZIP entry name sanitization (no directory components / traversal)
|
||||
- name deduplication while preserving extensions
|
||||
- writing streamed bytes from `storage.load(...)` into ZIP entries
|
||||
- yields a tempfile path so callers can open/stream the ZIP without holding a live file handle
|
||||
- `FileService.get_upload_files_by_ids(...)`
|
||||
- returns `{}` for empty id lists
|
||||
- returns an id-keyed mapping for non-empty lists
|
||||
|
||||
## Notes
|
||||
|
||||
- These tests intentionally stub `storage.load` and `db.session.scalars(...).all()` to avoid needing a real DB/storage.
|
||||
@@ -71,6 +71,8 @@ def create_app() -> DifyApp:
|
||||
|
||||
|
||||
def initialize_extensions(app: DifyApp):
|
||||
# Initialize Flask context capture for workflow execution
|
||||
from context.flask_app_context import init_flask_context
|
||||
from extensions import (
|
||||
ext_app_metrics,
|
||||
ext_blueprints,
|
||||
@@ -100,6 +102,8 @@ def initialize_extensions(app: DifyApp):
|
||||
ext_warnings,
|
||||
)
|
||||
|
||||
init_flask_context()
|
||||
|
||||
extensions = [
|
||||
ext_timezone,
|
||||
ext_logging,
|
||||
|
||||
@@ -862,8 +862,27 @@ def clear_free_plan_tenant_expired_logs(days: int, batch: int, tenant_ids: list[
|
||||
|
||||
|
||||
@click.command("clean-workflow-runs", help="Clean expired workflow runs and related data for free tenants.")
|
||||
@click.option("--days", default=30, show_default=True, help="Delete workflow runs created before N days ago.")
|
||||
@click.option(
|
||||
"--before-days",
|
||||
"--days",
|
||||
default=30,
|
||||
show_default=True,
|
||||
type=click.IntRange(min=0),
|
||||
help="Delete workflow runs created before N days ago.",
|
||||
)
|
||||
@click.option("--batch-size", default=200, show_default=True, help="Batch size for selecting workflow runs.")
|
||||
@click.option(
|
||||
"--from-days-ago",
|
||||
default=None,
|
||||
type=click.IntRange(min=0),
|
||||
help="Lower bound in days ago (older). Must be paired with --to-days-ago.",
|
||||
)
|
||||
@click.option(
|
||||
"--to-days-ago",
|
||||
default=None,
|
||||
type=click.IntRange(min=0),
|
||||
help="Upper bound in days ago (newer). Must be paired with --from-days-ago.",
|
||||
)
|
||||
@click.option(
|
||||
"--start-from",
|
||||
type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
|
||||
@@ -882,8 +901,10 @@ def clear_free_plan_tenant_expired_logs(days: int, batch: int, tenant_ids: list[
|
||||
help="Preview cleanup results without deleting any workflow run data.",
|
||||
)
|
||||
def clean_workflow_runs(
|
||||
days: int,
|
||||
before_days: int,
|
||||
batch_size: int,
|
||||
from_days_ago: int | None,
|
||||
to_days_ago: int | None,
|
||||
start_from: datetime.datetime | None,
|
||||
end_before: datetime.datetime | None,
|
||||
dry_run: bool,
|
||||
@@ -894,11 +915,24 @@ def clean_workflow_runs(
|
||||
if (start_from is None) ^ (end_before is None):
|
||||
raise click.UsageError("--start-from and --end-before must be provided together.")
|
||||
|
||||
if (from_days_ago is None) ^ (to_days_ago is None):
|
||||
raise click.UsageError("--from-days-ago and --to-days-ago must be provided together.")
|
||||
|
||||
if from_days_ago is not None and to_days_ago is not None:
|
||||
if start_from or end_before:
|
||||
raise click.UsageError("Choose either day offsets or explicit dates, not both.")
|
||||
if from_days_ago <= to_days_ago:
|
||||
raise click.UsageError("--from-days-ago must be greater than --to-days-ago.")
|
||||
now = datetime.datetime.now()
|
||||
start_from = now - datetime.timedelta(days=from_days_ago)
|
||||
end_before = now - datetime.timedelta(days=to_days_ago)
|
||||
before_days = 0
|
||||
|
||||
start_time = datetime.datetime.now(datetime.UTC)
|
||||
click.echo(click.style(f"Starting workflow run cleanup at {start_time.isoformat()}.", fg="white"))
|
||||
|
||||
WorkflowRunCleanup(
|
||||
days=days,
|
||||
days=before_days,
|
||||
batch_size=batch_size,
|
||||
start_from=start_from,
|
||||
end_before=end_before,
|
||||
|
||||
74
api/context/__init__.py
Normal file
74
api/context/__init__.py
Normal file
@@ -0,0 +1,74 @@
|
||||
"""
|
||||
Core Context - Framework-agnostic context management.
|
||||
|
||||
This module provides context management that is independent of any specific
|
||||
web framework. Framework-specific implementations register their context
|
||||
capture functions at application initialization time.
|
||||
|
||||
This ensures the workflow layer remains completely decoupled from Flask
|
||||
or any other web framework.
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
from collections.abc import Callable
|
||||
|
||||
from core.workflow.context.execution_context import (
|
||||
ExecutionContext,
|
||||
IExecutionContext,
|
||||
NullAppContext,
|
||||
)
|
||||
|
||||
# Global capturer function - set by framework-specific modules
|
||||
_capturer: Callable[[], IExecutionContext] | None = None
|
||||
|
||||
|
||||
def register_context_capturer(capturer: Callable[[], IExecutionContext]) -> None:
|
||||
"""
|
||||
Register a context capture function.
|
||||
|
||||
This should be called by framework-specific modules (e.g., Flask)
|
||||
during application initialization.
|
||||
|
||||
Args:
|
||||
capturer: Function that captures current context and returns IExecutionContext
|
||||
"""
|
||||
global _capturer
|
||||
_capturer = capturer
|
||||
|
||||
|
||||
def capture_current_context() -> IExecutionContext:
|
||||
"""
|
||||
Capture current execution context.
|
||||
|
||||
This function uses the registered context capturer. If no capturer
|
||||
is registered, it returns a minimal context with only contextvars
|
||||
(suitable for non-framework environments like tests or standalone scripts).
|
||||
|
||||
Returns:
|
||||
IExecutionContext with captured context
|
||||
"""
|
||||
if _capturer is None:
|
||||
# No framework registered - return minimal context
|
||||
return ExecutionContext(
|
||||
app_context=NullAppContext(),
|
||||
context_vars=contextvars.copy_context(),
|
||||
)
|
||||
|
||||
return _capturer()
|
||||
|
||||
|
||||
def reset_context_provider() -> None:
|
||||
"""
|
||||
Reset the context capturer.
|
||||
|
||||
This is primarily useful for testing to ensure a clean state.
|
||||
"""
|
||||
global _capturer
|
||||
_capturer = None
|
||||
|
||||
|
||||
__all__ = [
|
||||
"capture_current_context",
|
||||
"register_context_capturer",
|
||||
"reset_context_provider",
|
||||
]
|
||||
198
api/context/flask_app_context.py
Normal file
198
api/context/flask_app_context.py
Normal file
@@ -0,0 +1,198 @@
|
||||
"""
|
||||
Flask App Context - Flask implementation of AppContext interface.
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
from collections.abc import Generator
|
||||
from contextlib import contextmanager
|
||||
from typing import Any, final
|
||||
|
||||
from flask import Flask, current_app, g
|
||||
|
||||
from context import register_context_capturer
|
||||
from core.workflow.context.execution_context import (
|
||||
AppContext,
|
||||
IExecutionContext,
|
||||
)
|
||||
|
||||
|
||||
@final
|
||||
class FlaskAppContext(AppContext):
|
||||
"""
|
||||
Flask implementation of AppContext.
|
||||
|
||||
This adapts Flask's app context to the AppContext interface.
|
||||
"""
|
||||
|
||||
def __init__(self, flask_app: Flask) -> None:
|
||||
"""
|
||||
Initialize Flask app context.
|
||||
|
||||
Args:
|
||||
flask_app: The Flask application instance
|
||||
"""
|
||||
self._flask_app = flask_app
|
||||
|
||||
def get_config(self, key: str, default: Any = None) -> Any:
|
||||
"""Get configuration value from Flask app config."""
|
||||
return self._flask_app.config.get(key, default)
|
||||
|
||||
def get_extension(self, name: str) -> Any:
|
||||
"""Get Flask extension by name."""
|
||||
return self._flask_app.extensions.get(name)
|
||||
|
||||
@contextmanager
|
||||
def enter(self) -> Generator[None, None, None]:
|
||||
"""Enter Flask app context."""
|
||||
with self._flask_app.app_context():
|
||||
yield
|
||||
|
||||
@property
|
||||
def flask_app(self) -> Flask:
|
||||
"""Get the underlying Flask app instance."""
|
||||
return self._flask_app
|
||||
|
||||
|
||||
def capture_flask_context(user: Any = None) -> IExecutionContext:
|
||||
"""
|
||||
Capture current Flask execution context.
|
||||
|
||||
This function captures the Flask app context and contextvars from the
|
||||
current environment. It should be called from within a Flask request or
|
||||
app context.
|
||||
|
||||
Args:
|
||||
user: Optional user object to include in context
|
||||
|
||||
Returns:
|
||||
IExecutionContext with captured Flask context
|
||||
|
||||
Raises:
|
||||
RuntimeError: If called outside Flask context
|
||||
"""
|
||||
# Get Flask app instance
|
||||
flask_app = current_app._get_current_object() # type: ignore
|
||||
|
||||
# Save current user if available
|
||||
saved_user = user
|
||||
if saved_user is None:
|
||||
# Check for user in g (flask-login)
|
||||
if hasattr(g, "_login_user"):
|
||||
saved_user = g._login_user
|
||||
|
||||
# Capture contextvars
|
||||
context_vars = contextvars.copy_context()
|
||||
|
||||
return FlaskExecutionContext(
|
||||
flask_app=flask_app,
|
||||
context_vars=context_vars,
|
||||
user=saved_user,
|
||||
)
|
||||
|
||||
|
||||
@final
|
||||
class FlaskExecutionContext:
|
||||
"""
|
||||
Flask-specific execution context.
|
||||
|
||||
This is a specialized version of ExecutionContext that includes Flask app
|
||||
context. It provides the same interface as ExecutionContext but with
|
||||
Flask-specific implementation.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
flask_app: Flask,
|
||||
context_vars: contextvars.Context,
|
||||
user: Any = None,
|
||||
) -> None:
|
||||
"""
|
||||
Initialize Flask execution context.
|
||||
|
||||
Args:
|
||||
flask_app: Flask application instance
|
||||
context_vars: Python contextvars
|
||||
user: Optional user object
|
||||
"""
|
||||
self._app_context = FlaskAppContext(flask_app)
|
||||
self._context_vars = context_vars
|
||||
self._user = user
|
||||
self._flask_app = flask_app
|
||||
|
||||
@property
|
||||
def app_context(self) -> FlaskAppContext:
|
||||
"""Get Flask app context."""
|
||||
return self._app_context
|
||||
|
||||
@property
|
||||
def context_vars(self) -> contextvars.Context:
|
||||
"""Get context variables."""
|
||||
return self._context_vars
|
||||
|
||||
@property
|
||||
def user(self) -> Any:
|
||||
"""Get user object."""
|
||||
return self._user
|
||||
|
||||
def __enter__(self) -> "FlaskExecutionContext":
|
||||
"""Enter the Flask execution context."""
|
||||
# Restore context variables
|
||||
for var, val in self._context_vars.items():
|
||||
var.set(val)
|
||||
|
||||
# Save current user from g if available
|
||||
saved_user = None
|
||||
if hasattr(g, "_login_user"):
|
||||
saved_user = g._login_user
|
||||
|
||||
# Enter Flask app context
|
||||
self._cm = self._app_context.enter()
|
||||
self._cm.__enter__()
|
||||
|
||||
# Restore user in new app context
|
||||
if saved_user is not None:
|
||||
g._login_user = saved_user
|
||||
|
||||
return self
|
||||
|
||||
def __exit__(self, *args: Any) -> None:
|
||||
"""Exit the Flask execution context."""
|
||||
if hasattr(self, "_cm"):
|
||||
self._cm.__exit__(*args)
|
||||
|
||||
@contextmanager
|
||||
def enter(self) -> Generator[None, None, None]:
|
||||
"""Enter Flask execution context as context manager."""
|
||||
# Restore context variables
|
||||
for var, val in self._context_vars.items():
|
||||
var.set(val)
|
||||
|
||||
# Save current user from g if available
|
||||
saved_user = None
|
||||
if hasattr(g, "_login_user"):
|
||||
saved_user = g._login_user
|
||||
|
||||
# Enter Flask app context
|
||||
with self._flask_app.app_context():
|
||||
# Restore user in new app context
|
||||
if saved_user is not None:
|
||||
g._login_user = saved_user
|
||||
yield
|
||||
|
||||
|
||||
def init_flask_context() -> None:
|
||||
"""
|
||||
Initialize Flask context capture by registering the capturer.
|
||||
|
||||
This function should be called during Flask application initialization
|
||||
to register the Flask-specific context capturer with the core context module.
|
||||
|
||||
Example:
|
||||
app = Flask(__name__)
|
||||
init_flask_context() # Register Flask context capturer
|
||||
|
||||
Note:
|
||||
This function does not need the app instance as it uses Flask's
|
||||
`current_app` to get the app when capturing context.
|
||||
"""
|
||||
register_context_capturer(capture_flask_context)
|
||||
@@ -1,4 +1,3 @@
|
||||
import re
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
from typing import Any, Literal, TypeAlias
|
||||
@@ -68,48 +67,6 @@ class AppListQuery(BaseModel):
|
||||
raise ValueError("Invalid UUID format in tag_ids.") from exc
|
||||
|
||||
|
||||
# XSS prevention: patterns that could lead to XSS attacks
|
||||
# Includes: script tags, iframe tags, javascript: protocol, SVG with onload, etc.
|
||||
_XSS_PATTERNS = [
|
||||
r"<script[^>]*>.*?</script>", # Script tags
|
||||
r"<iframe\b[^>]*?(?:/>|>.*?</iframe>)", # Iframe tags (including self-closing)
|
||||
r"javascript:", # JavaScript protocol
|
||||
r"<svg[^>]*?\s+onload\s*=[^>]*>", # SVG with onload handler (attribute-aware, flexible whitespace)
|
||||
r"<.*?on\s*\w+\s*=", # Event handlers like onclick, onerror, etc.
|
||||
r"<object\b[^>]*(?:\s*/>|>.*?</object\s*>)", # Object tags (opening tag)
|
||||
r"<embed[^>]*>", # Embed tags (self-closing)
|
||||
r"<link[^>]*>", # Link tags with javascript
|
||||
]
|
||||
|
||||
|
||||
def _validate_xss_safe(value: str | None, field_name: str = "Field") -> str | None:
|
||||
"""
|
||||
Validate that a string value doesn't contain potential XSS payloads.
|
||||
|
||||
Args:
|
||||
value: The string value to validate
|
||||
field_name: Name of the field for error messages
|
||||
|
||||
Returns:
|
||||
The original value if safe
|
||||
|
||||
Raises:
|
||||
ValueError: If the value contains XSS patterns
|
||||
"""
|
||||
if value is None:
|
||||
return None
|
||||
|
||||
value_lower = value.lower()
|
||||
for pattern in _XSS_PATTERNS:
|
||||
if re.search(pattern, value_lower, re.DOTALL | re.IGNORECASE):
|
||||
raise ValueError(
|
||||
f"{field_name} contains invalid characters or patterns. "
|
||||
"HTML tags, JavaScript, and other potentially dangerous content are not allowed."
|
||||
)
|
||||
|
||||
return value
|
||||
|
||||
|
||||
class CreateAppPayload(BaseModel):
|
||||
name: str = Field(..., min_length=1, description="App name")
|
||||
description: str | None = Field(default=None, description="App description (max 400 chars)", max_length=400)
|
||||
@@ -118,11 +75,6 @@ class CreateAppPayload(BaseModel):
|
||||
icon: str | None = Field(default=None, description="Icon")
|
||||
icon_background: str | None = Field(default=None, description="Icon background color")
|
||||
|
||||
@field_validator("name", "description", mode="before")
|
||||
@classmethod
|
||||
def validate_xss_safe(cls, value: str | None, info) -> str | None:
|
||||
return _validate_xss_safe(value, info.field_name)
|
||||
|
||||
|
||||
class UpdateAppPayload(BaseModel):
|
||||
name: str = Field(..., min_length=1, description="App name")
|
||||
@@ -133,11 +85,6 @@ class UpdateAppPayload(BaseModel):
|
||||
use_icon_as_answer_icon: bool | None = Field(default=None, description="Use icon as answer icon")
|
||||
max_active_requests: int | None = Field(default=None, description="Maximum active requests")
|
||||
|
||||
@field_validator("name", "description", mode="before")
|
||||
@classmethod
|
||||
def validate_xss_safe(cls, value: str | None, info) -> str | None:
|
||||
return _validate_xss_safe(value, info.field_name)
|
||||
|
||||
|
||||
class CopyAppPayload(BaseModel):
|
||||
name: str | None = Field(default=None, description="Name for the copied app")
|
||||
@@ -146,11 +93,6 @@ class CopyAppPayload(BaseModel):
|
||||
icon: str | None = Field(default=None, description="Icon")
|
||||
icon_background: str | None = Field(default=None, description="Icon background color")
|
||||
|
||||
@field_validator("name", "description", mode="before")
|
||||
@classmethod
|
||||
def validate_xss_safe(cls, value: str | None, info) -> str | None:
|
||||
return _validate_xss_safe(value, info.field_name)
|
||||
|
||||
|
||||
class AppExportQuery(BaseModel):
|
||||
include_secret: bool = Field(default=False, description="Include secrets in export")
|
||||
|
||||
@@ -69,6 +69,13 @@ class ActivateCheckApi(Resource):
|
||||
if invitation:
|
||||
data = invitation.get("data", {})
|
||||
tenant = invitation.get("tenant", None)
|
||||
|
||||
# Check workspace permission
|
||||
if tenant:
|
||||
from libs.workspace_permission import check_workspace_member_invite_permission
|
||||
|
||||
check_workspace_member_invite_permission(tenant.id)
|
||||
|
||||
workspace_name = tenant.name if tenant else None
|
||||
workspace_id = tenant.id if tenant else None
|
||||
invitee_email = data.get("email") if data else None
|
||||
|
||||
@@ -2,10 +2,12 @@ import json
|
||||
import logging
|
||||
from argparse import ArgumentTypeError
|
||||
from collections.abc import Sequence
|
||||
from typing import Literal, cast
|
||||
from contextlib import ExitStack
|
||||
from typing import Any, Literal, cast
|
||||
from uuid import UUID
|
||||
|
||||
import sqlalchemy as sa
|
||||
from flask import request
|
||||
from flask import request, send_file
|
||||
from flask_restx import Resource, fields, marshal, marshal_with
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy import asc, desc, select
|
||||
@@ -42,6 +44,7 @@ from models import DatasetProcessRule, Document, DocumentSegment, UploadFile
|
||||
from models.dataset import DocumentPipelineExecutionLog
|
||||
from services.dataset_service import DatasetService, DocumentService
|
||||
from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig, ProcessRule, RetrievalModel
|
||||
from services.file_service import FileService
|
||||
|
||||
from ..app.error import (
|
||||
ProviderModelCurrentlyNotSupportError,
|
||||
@@ -65,6 +68,9 @@ from ..wraps import (
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# NOTE: Keep constants near the top of the module for discoverability.
|
||||
DOCUMENT_BATCH_DOWNLOAD_ZIP_MAX_DOCS = 100
|
||||
|
||||
|
||||
def _get_or_create_model(model_name: str, field_def):
|
||||
existing = console_ns.models.get(model_name)
|
||||
@@ -104,6 +110,12 @@ class DocumentRenamePayload(BaseModel):
|
||||
name: str
|
||||
|
||||
|
||||
class DocumentBatchDownloadZipPayload(BaseModel):
|
||||
"""Request payload for bulk downloading documents as a zip archive."""
|
||||
|
||||
document_ids: list[UUID] = Field(..., min_length=1, max_length=DOCUMENT_BATCH_DOWNLOAD_ZIP_MAX_DOCS)
|
||||
|
||||
|
||||
class DocumentDatasetListParam(BaseModel):
|
||||
page: int = Field(1, title="Page", description="Page number.")
|
||||
limit: int = Field(20, title="Limit", description="Page size.")
|
||||
@@ -120,6 +132,7 @@ register_schema_models(
|
||||
RetrievalModel,
|
||||
DocumentRetryPayload,
|
||||
DocumentRenamePayload,
|
||||
DocumentBatchDownloadZipPayload,
|
||||
)
|
||||
|
||||
|
||||
@@ -853,6 +866,62 @@ class DocumentApi(DocumentResource):
|
||||
return {"result": "success"}, 204
|
||||
|
||||
|
||||
@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/download")
|
||||
class DocumentDownloadApi(DocumentResource):
|
||||
"""Return a signed download URL for a dataset document's original uploaded file."""
|
||||
|
||||
@console_ns.doc("get_dataset_document_download_url")
|
||||
@console_ns.doc(description="Get a signed download URL for a dataset document's original uploaded file")
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
@cloud_edition_billing_rate_limit_check("knowledge")
|
||||
def get(self, dataset_id: str, document_id: str) -> dict[str, Any]:
|
||||
# Reuse the shared permission/tenant checks implemented in DocumentResource.
|
||||
document = self.get_document(str(dataset_id), str(document_id))
|
||||
return {"url": DocumentService.get_document_download_url(document)}
|
||||
|
||||
|
||||
@console_ns.route("/datasets/<uuid:dataset_id>/documents/download-zip")
|
||||
class DocumentBatchDownloadZipApi(DocumentResource):
|
||||
"""Download multiple uploaded-file documents as a single ZIP (avoids browser multi-download limits)."""
|
||||
|
||||
@console_ns.doc("download_dataset_documents_as_zip")
|
||||
@console_ns.doc(description="Download selected dataset documents as a single ZIP archive (upload-file only)")
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
@cloud_edition_billing_rate_limit_check("knowledge")
|
||||
@console_ns.expect(console_ns.models[DocumentBatchDownloadZipPayload.__name__])
|
||||
def post(self, dataset_id: str):
|
||||
"""Stream a ZIP archive containing the requested uploaded documents."""
|
||||
# Parse and validate request payload.
|
||||
payload = DocumentBatchDownloadZipPayload.model_validate(console_ns.payload or {})
|
||||
|
||||
current_user, current_tenant_id = current_account_with_tenant()
|
||||
dataset_id = str(dataset_id)
|
||||
document_ids: list[str] = [str(document_id) for document_id in payload.document_ids]
|
||||
upload_files, download_name = DocumentService.prepare_document_batch_download_zip(
|
||||
dataset_id=dataset_id,
|
||||
document_ids=document_ids,
|
||||
tenant_id=current_tenant_id,
|
||||
current_user=current_user,
|
||||
)
|
||||
|
||||
# Delegate ZIP packing to FileService, but keep Flask response+cleanup in the route.
|
||||
with ExitStack() as stack:
|
||||
zip_path = stack.enter_context(FileService.build_upload_files_zip_tempfile(upload_files=upload_files))
|
||||
response = send_file(
|
||||
zip_path,
|
||||
mimetype="application/zip",
|
||||
as_attachment=True,
|
||||
download_name=download_name,
|
||||
)
|
||||
cleanup = stack.pop_all()
|
||||
response.call_on_close(cleanup.close)
|
||||
return response
|
||||
|
||||
|
||||
@console_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/<string:action>")
|
||||
class DocumentProcessingApi(DocumentResource):
|
||||
@console_ns.doc("update_document_processing")
|
||||
|
||||
@@ -107,6 +107,12 @@ class MemberInviteEmailApi(Resource):
|
||||
inviter = current_user
|
||||
if not inviter.current_tenant:
|
||||
raise ValueError("No current tenant")
|
||||
|
||||
# Check workspace permission for member invitations
|
||||
from libs.workspace_permission import check_workspace_member_invite_permission
|
||||
|
||||
check_workspace_member_invite_permission(inviter.current_tenant.id)
|
||||
|
||||
invitation_results = []
|
||||
console_web_url = dify_config.CONSOLE_WEB_URL
|
||||
|
||||
|
||||
@@ -20,6 +20,7 @@ from controllers.console.error import AccountNotLinkTenantError
|
||||
from controllers.console.wraps import (
|
||||
account_initialization_required,
|
||||
cloud_edition_billing_resource_check,
|
||||
only_edition_enterprise,
|
||||
setup_required,
|
||||
)
|
||||
from enums.cloud_plan import CloudPlan
|
||||
@@ -28,6 +29,7 @@ from libs.helper import TimestampField
|
||||
from libs.login import current_account_with_tenant, login_required
|
||||
from models.account import Tenant, TenantStatus
|
||||
from services.account_service import TenantService
|
||||
from services.enterprise.enterprise_service import EnterpriseService
|
||||
from services.feature_service import FeatureService
|
||||
from services.file_service import FileService
|
||||
from services.workspace_service import WorkspaceService
|
||||
@@ -288,3 +290,31 @@ class WorkspaceInfoApi(Resource):
|
||||
db.session.commit()
|
||||
|
||||
return {"result": "success", "tenant": marshal(WorkspaceService.get_tenant_info(tenant), tenant_fields)}
|
||||
|
||||
|
||||
@console_ns.route("/workspaces/current/permission")
|
||||
class WorkspacePermissionApi(Resource):
|
||||
"""Get workspace permissions for the current workspace."""
|
||||
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
@only_edition_enterprise
|
||||
def get(self):
|
||||
"""
|
||||
Get workspace permission settings.
|
||||
Returns permission flags that control workspace features like member invitations and owner transfer.
|
||||
"""
|
||||
_, current_tenant_id = current_account_with_tenant()
|
||||
|
||||
if not current_tenant_id:
|
||||
raise ValueError("No current tenant")
|
||||
|
||||
# Get workspace permissions from enterprise service
|
||||
permission = EnterpriseService.WorkspacePermissionService.get_permission(current_tenant_id)
|
||||
|
||||
return {
|
||||
"workspace_id": permission.workspace_id,
|
||||
"allow_member_invite": permission.allow_member_invite,
|
||||
"allow_owner_transfer": permission.allow_owner_transfer,
|
||||
}, 200
|
||||
|
||||
@@ -286,13 +286,12 @@ def enable_change_email(view: Callable[P, R]):
|
||||
def is_allow_transfer_owner(view: Callable[P, R]):
|
||||
@wraps(view)
|
||||
def decorated(*args: P.args, **kwargs: P.kwargs):
|
||||
_, current_tenant_id = current_account_with_tenant()
|
||||
features = FeatureService.get_features(current_tenant_id)
|
||||
if features.is_allow_transfer_workspace:
|
||||
return view(*args, **kwargs)
|
||||
from libs.workspace_permission import check_workspace_owner_transfer_permission
|
||||
|
||||
# otherwise, return 403
|
||||
abort(403)
|
||||
_, current_tenant_id = current_account_with_tenant()
|
||||
# Check both billing/plan level and workspace policy level permissions
|
||||
check_workspace_owner_transfer_permission(current_tenant_id)
|
||||
return view(*args, **kwargs)
|
||||
|
||||
return decorated
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ from typing import Any, Literal, Union, overload
|
||||
from flask import Flask, current_app
|
||||
from pydantic import ValidationError
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session, sessionmaker
|
||||
from sqlalchemy.orm import sessionmaker
|
||||
|
||||
import contexts
|
||||
from configs import dify_config
|
||||
@@ -23,6 +23,7 @@ from core.app.apps.workflow.generate_response_converter import WorkflowAppGenera
|
||||
from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
|
||||
from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerateEntity
|
||||
from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
|
||||
from core.db.session_factory import session_factory
|
||||
from core.helper.trace_id_helper import extract_external_trace_id_from_args
|
||||
from core.model_runtime.errors.invoke import InvokeAuthorizationError
|
||||
from core.ops.ops_trace_manager import TraceQueueManager
|
||||
@@ -476,7 +477,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
|
||||
:return:
|
||||
"""
|
||||
with preserve_flask_contexts(flask_app, context_vars=context):
|
||||
with Session(db.engine, expire_on_commit=False) as session:
|
||||
with session_factory.create_session() as session:
|
||||
workflow = session.scalar(
|
||||
select(Workflow).where(
|
||||
Workflow.tenant_id == application_generate_entity.app_config.tenant_id,
|
||||
|
||||
@@ -320,18 +320,17 @@ class BasePluginClient:
|
||||
case PluginInvokeError.__name__:
|
||||
error_object = json.loads(message)
|
||||
invoke_error_type = error_object.get("error_type")
|
||||
args = error_object.get("args")
|
||||
match invoke_error_type:
|
||||
case InvokeRateLimitError.__name__:
|
||||
raise InvokeRateLimitError(description=args.get("description"))
|
||||
raise InvokeRateLimitError(description=error_object.get("message"))
|
||||
case InvokeAuthorizationError.__name__:
|
||||
raise InvokeAuthorizationError(description=args.get("description"))
|
||||
raise InvokeAuthorizationError(description=error_object.get("message"))
|
||||
case InvokeBadRequestError.__name__:
|
||||
raise InvokeBadRequestError(description=args.get("description"))
|
||||
raise InvokeBadRequestError(description=error_object.get("message"))
|
||||
case InvokeConnectionError.__name__:
|
||||
raise InvokeConnectionError(description=args.get("description"))
|
||||
raise InvokeConnectionError(description=error_object.get("message"))
|
||||
case InvokeServerUnavailableError.__name__:
|
||||
raise InvokeServerUnavailableError(description=args.get("description"))
|
||||
raise InvokeServerUnavailableError(description=error_object.get("message"))
|
||||
case CredentialsValidateFailedError.__name__:
|
||||
raise CredentialsValidateFailedError(error_object.get("message"))
|
||||
case EndpointSetupFailedError.__name__:
|
||||
@@ -339,11 +338,11 @@ class BasePluginClient:
|
||||
case TriggerProviderCredentialValidationError.__name__:
|
||||
raise TriggerProviderCredentialValidationError(error_object.get("message"))
|
||||
case TriggerPluginInvokeError.__name__:
|
||||
raise TriggerPluginInvokeError(description=error_object.get("description"))
|
||||
raise TriggerPluginInvokeError(description=error_object.get("message"))
|
||||
case TriggerInvokeError.__name__:
|
||||
raise TriggerInvokeError(error_object.get("message"))
|
||||
case EventIgnoreError.__name__:
|
||||
raise EventIgnoreError(description=error_object.get("description"))
|
||||
raise EventIgnoreError(description=error_object.get("message"))
|
||||
case _:
|
||||
raise PluginInvokeError(description=message)
|
||||
case PluginDaemonInternalServerError.__name__:
|
||||
|
||||
@@ -5,7 +5,6 @@ import logging
|
||||
from collections.abc import Generator, Mapping, Sequence
|
||||
from typing import Any, cast
|
||||
|
||||
from flask import has_request_context
|
||||
from sqlalchemy import select
|
||||
|
||||
from core.db.session_factory import session_factory
|
||||
@@ -29,6 +28,21 @@ from models.workflow import Workflow
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _try_resolve_user_from_request() -> Account | EndUser | None:
|
||||
"""
|
||||
Try to resolve user from Flask request context.
|
||||
|
||||
Returns None if not in a request context or if user is not available.
|
||||
"""
|
||||
# Note: `current_user` is a LocalProxy. Never compare it with None directly.
|
||||
# Use _get_current_object() to dereference the proxy
|
||||
user = getattr(current_user, "_get_current_object", lambda: current_user)()
|
||||
# Check if we got a valid user object
|
||||
if user is not None and hasattr(user, "id"):
|
||||
return user
|
||||
return None
|
||||
|
||||
|
||||
class WorkflowTool(Tool):
|
||||
"""
|
||||
Workflow tool.
|
||||
@@ -209,21 +223,13 @@ class WorkflowTool(Tool):
|
||||
Returns:
|
||||
Account | EndUser | None: The resolved user object, or None if resolution fails.
|
||||
"""
|
||||
if has_request_context():
|
||||
return self._resolve_user_from_request()
|
||||
else:
|
||||
return self._resolve_user_from_database(user_id=user_id)
|
||||
# Try to resolve user from request context first
|
||||
user = _try_resolve_user_from_request()
|
||||
if user is not None:
|
||||
return user
|
||||
|
||||
def _resolve_user_from_request(self) -> Account | EndUser | None:
|
||||
"""
|
||||
Resolve user from Flask request context.
|
||||
"""
|
||||
try:
|
||||
# Note: `current_user` is a LocalProxy. Never compare it with None directly.
|
||||
return getattr(current_user, "_get_current_object", lambda: current_user)()
|
||||
except Exception as e:
|
||||
logger.warning("Failed to resolve user from request context: %s", e)
|
||||
return None
|
||||
# Fall back to database resolution
|
||||
return self._resolve_user_from_database(user_id=user_id)
|
||||
|
||||
def _resolve_user_from_database(self, user_id: str) -> Account | EndUser | None:
|
||||
"""
|
||||
|
||||
22
api/core/workflow/context/__init__.py
Normal file
22
api/core/workflow/context/__init__.py
Normal file
@@ -0,0 +1,22 @@
|
||||
"""
|
||||
Execution Context - Context management for workflow execution.
|
||||
|
||||
This package provides Flask-independent context management for workflow
|
||||
execution in multi-threaded environments.
|
||||
"""
|
||||
|
||||
from core.workflow.context.execution_context import (
|
||||
AppContext,
|
||||
ExecutionContext,
|
||||
IExecutionContext,
|
||||
NullAppContext,
|
||||
capture_current_context,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"AppContext",
|
||||
"ExecutionContext",
|
||||
"IExecutionContext",
|
||||
"NullAppContext",
|
||||
"capture_current_context",
|
||||
]
|
||||
216
api/core/workflow/context/execution_context.py
Normal file
216
api/core/workflow/context/execution_context.py
Normal file
@@ -0,0 +1,216 @@
|
||||
"""
|
||||
Execution Context - Abstracted context management for workflow execution.
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
from abc import ABC, abstractmethod
|
||||
from collections.abc import Generator
|
||||
from contextlib import AbstractContextManager, contextmanager
|
||||
from typing import Any, Protocol, final, runtime_checkable
|
||||
|
||||
|
||||
class AppContext(ABC):
|
||||
"""
|
||||
Abstract application context interface.
|
||||
|
||||
This abstraction allows workflow execution to work with or without Flask
|
||||
by providing a common interface for application context management.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def get_config(self, key: str, default: Any = None) -> Any:
|
||||
"""Get configuration value by key."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_extension(self, name: str) -> Any:
|
||||
"""Get Flask extension by name (e.g., 'db', 'cache')."""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def enter(self) -> AbstractContextManager[None]:
|
||||
"""Enter the application context."""
|
||||
pass
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class IExecutionContext(Protocol):
|
||||
"""
|
||||
Protocol for execution context.
|
||||
|
||||
This protocol defines the interface that all execution contexts must implement,
|
||||
allowing both ExecutionContext and FlaskExecutionContext to be used interchangeably.
|
||||
"""
|
||||
|
||||
def __enter__(self) -> "IExecutionContext":
|
||||
"""Enter the execution context."""
|
||||
...
|
||||
|
||||
def __exit__(self, *args: Any) -> None:
|
||||
"""Exit the execution context."""
|
||||
...
|
||||
|
||||
@property
|
||||
def user(self) -> Any:
|
||||
"""Get user object."""
|
||||
...
|
||||
|
||||
|
||||
@final
|
||||
class ExecutionContext:
|
||||
"""
|
||||
Execution context for workflow execution in worker threads.
|
||||
|
||||
This class encapsulates all context needed for workflow execution:
|
||||
- Application context (Flask app or standalone)
|
||||
- Context variables for Python contextvars
|
||||
- User information (optional)
|
||||
|
||||
It is designed to be serializable and passable to worker threads.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
app_context: AppContext | None = None,
|
||||
context_vars: contextvars.Context | None = None,
|
||||
user: Any = None,
|
||||
) -> None:
|
||||
"""
|
||||
Initialize execution context.
|
||||
|
||||
Args:
|
||||
app_context: Application context (Flask or standalone)
|
||||
context_vars: Python contextvars to preserve
|
||||
user: User object (optional)
|
||||
"""
|
||||
self._app_context = app_context
|
||||
self._context_vars = context_vars
|
||||
self._user = user
|
||||
|
||||
@property
|
||||
def app_context(self) -> AppContext | None:
|
||||
"""Get application context."""
|
||||
return self._app_context
|
||||
|
||||
@property
|
||||
def context_vars(self) -> contextvars.Context | None:
|
||||
"""Get context variables."""
|
||||
return self._context_vars
|
||||
|
||||
@property
|
||||
def user(self) -> Any:
|
||||
"""Get user object."""
|
||||
return self._user
|
||||
|
||||
@contextmanager
|
||||
def enter(self) -> Generator[None, None, None]:
|
||||
"""
|
||||
Enter this execution context.
|
||||
|
||||
This is a convenience method that creates a context manager.
|
||||
"""
|
||||
# Restore context variables if provided
|
||||
if self._context_vars:
|
||||
for var, val in self._context_vars.items():
|
||||
var.set(val)
|
||||
|
||||
# Enter app context if available
|
||||
if self._app_context is not None:
|
||||
with self._app_context.enter():
|
||||
yield
|
||||
else:
|
||||
yield
|
||||
|
||||
def __enter__(self) -> "ExecutionContext":
|
||||
"""Enter the execution context."""
|
||||
self._cm = self.enter()
|
||||
self._cm.__enter__()
|
||||
return self
|
||||
|
||||
def __exit__(self, *args: Any) -> None:
|
||||
"""Exit the execution context."""
|
||||
if hasattr(self, "_cm"):
|
||||
self._cm.__exit__(*args)
|
||||
|
||||
|
||||
class NullAppContext(AppContext):
|
||||
"""
|
||||
Null implementation of AppContext for non-Flask environments.
|
||||
|
||||
This is used when running without Flask (e.g., in tests or standalone mode).
|
||||
"""
|
||||
|
||||
def __init__(self, config: dict[str, Any] | None = None) -> None:
|
||||
"""
|
||||
Initialize null app context.
|
||||
|
||||
Args:
|
||||
config: Optional configuration dictionary
|
||||
"""
|
||||
self._config = config or {}
|
||||
self._extensions: dict[str, Any] = {}
|
||||
|
||||
def get_config(self, key: str, default: Any = None) -> Any:
|
||||
"""Get configuration value by key."""
|
||||
return self._config.get(key, default)
|
||||
|
||||
def get_extension(self, name: str) -> Any:
|
||||
"""Get extension by name."""
|
||||
return self._extensions.get(name)
|
||||
|
||||
def set_extension(self, name: str, extension: Any) -> None:
|
||||
"""Set extension by name."""
|
||||
self._extensions[name] = extension
|
||||
|
||||
@contextmanager
|
||||
def enter(self) -> Generator[None, None, None]:
|
||||
"""Enter null context (no-op)."""
|
||||
yield
|
||||
|
||||
|
||||
class ExecutionContextBuilder:
|
||||
"""
|
||||
Builder for creating ExecutionContext instances.
|
||||
|
||||
This provides a fluent API for building execution contexts.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._app_context: AppContext | None = None
|
||||
self._context_vars: contextvars.Context | None = None
|
||||
self._user: Any = None
|
||||
|
||||
def with_app_context(self, app_context: AppContext) -> "ExecutionContextBuilder":
|
||||
"""Set application context."""
|
||||
self._app_context = app_context
|
||||
return self
|
||||
|
||||
def with_context_vars(self, context_vars: contextvars.Context) -> "ExecutionContextBuilder":
|
||||
"""Set context variables."""
|
||||
self._context_vars = context_vars
|
||||
return self
|
||||
|
||||
def with_user(self, user: Any) -> "ExecutionContextBuilder":
|
||||
"""Set user."""
|
||||
self._user = user
|
||||
return self
|
||||
|
||||
def build(self) -> ExecutionContext:
|
||||
"""Build the execution context."""
|
||||
return ExecutionContext(
|
||||
app_context=self._app_context,
|
||||
context_vars=self._context_vars,
|
||||
user=self._user,
|
||||
)
|
||||
|
||||
|
||||
def capture_current_context() -> IExecutionContext:
|
||||
"""
|
||||
Capture current execution context from the calling environment.
|
||||
|
||||
Returns:
|
||||
IExecutionContext with captured context
|
||||
"""
|
||||
from context import capture_current_context
|
||||
|
||||
return capture_current_context()
|
||||
@@ -7,15 +7,13 @@ Domain-Driven Design principles for improved maintainability and testability.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import contextvars
|
||||
import logging
|
||||
import queue
|
||||
import threading
|
||||
from collections.abc import Generator
|
||||
from typing import TYPE_CHECKING, cast, final
|
||||
|
||||
from flask import Flask, current_app
|
||||
|
||||
from core.workflow.context import capture_current_context
|
||||
from core.workflow.enums import NodeExecutionType
|
||||
from core.workflow.graph import Graph
|
||||
from core.workflow.graph_events import (
|
||||
@@ -159,17 +157,8 @@ class GraphEngine:
|
||||
self._layers: list[GraphEngineLayer] = []
|
||||
|
||||
# === Worker Pool Setup ===
|
||||
# Capture Flask app context for worker threads
|
||||
flask_app: Flask | None = None
|
||||
try:
|
||||
app = current_app._get_current_object() # type: ignore
|
||||
if isinstance(app, Flask):
|
||||
flask_app = app
|
||||
except RuntimeError:
|
||||
pass
|
||||
|
||||
# Capture context variables for worker threads
|
||||
context_vars = contextvars.copy_context()
|
||||
# Capture execution context for worker threads
|
||||
execution_context = capture_current_context()
|
||||
|
||||
# Create worker pool for parallel node execution
|
||||
self._worker_pool = WorkerPool(
|
||||
@@ -177,8 +166,7 @@ class GraphEngine:
|
||||
event_queue=self._event_queue,
|
||||
graph=self._graph,
|
||||
layers=self._layers,
|
||||
flask_app=flask_app,
|
||||
context_vars=context_vars,
|
||||
execution_context=execution_context,
|
||||
min_workers=self._min_workers,
|
||||
max_workers=self._max_workers,
|
||||
scale_up_threshold=self._scale_up_threshold,
|
||||
|
||||
@@ -5,26 +5,27 @@ Workers pull node IDs from the ready_queue, execute nodes, and push events
|
||||
to the event_queue for the dispatcher to process.
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
import queue
|
||||
import threading
|
||||
import time
|
||||
from collections.abc import Sequence
|
||||
from datetime import datetime
|
||||
from typing import final
|
||||
from typing import TYPE_CHECKING, final
|
||||
from uuid import uuid4
|
||||
|
||||
from flask import Flask
|
||||
from typing_extensions import override
|
||||
|
||||
from core.workflow.context import IExecutionContext
|
||||
from core.workflow.graph import Graph
|
||||
from core.workflow.graph_engine.layers.base import GraphEngineLayer
|
||||
from core.workflow.graph_events import GraphNodeEventBase, NodeRunFailedEvent
|
||||
from core.workflow.nodes.base.node import Node
|
||||
from libs.flask_utils import preserve_flask_contexts
|
||||
|
||||
from .ready_queue import ReadyQueue
|
||||
|
||||
if TYPE_CHECKING:
|
||||
pass
|
||||
|
||||
|
||||
@final
|
||||
class Worker(threading.Thread):
|
||||
@@ -44,8 +45,7 @@ class Worker(threading.Thread):
|
||||
layers: Sequence[GraphEngineLayer],
|
||||
stop_event: threading.Event,
|
||||
worker_id: int = 0,
|
||||
flask_app: Flask | None = None,
|
||||
context_vars: contextvars.Context | None = None,
|
||||
execution_context: IExecutionContext | None = None,
|
||||
) -> None:
|
||||
"""
|
||||
Initialize worker thread.
|
||||
@@ -56,19 +56,17 @@ class Worker(threading.Thread):
|
||||
graph: Graph containing nodes to execute
|
||||
layers: Graph engine layers for node execution hooks
|
||||
worker_id: Unique identifier for this worker
|
||||
flask_app: Optional Flask application for context preservation
|
||||
context_vars: Optional context variables to preserve in worker thread
|
||||
execution_context: Optional execution context for context preservation
|
||||
"""
|
||||
super().__init__(name=f"GraphWorker-{worker_id}", daemon=True)
|
||||
self._ready_queue = ready_queue
|
||||
self._event_queue = event_queue
|
||||
self._graph = graph
|
||||
self._worker_id = worker_id
|
||||
self._flask_app = flask_app
|
||||
self._context_vars = context_vars
|
||||
self._last_task_time = time.time()
|
||||
self._execution_context = execution_context
|
||||
self._stop_event = stop_event
|
||||
self._layers = layers if layers is not None else []
|
||||
self._last_task_time = time.time()
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Worker is controlled via shared stop_event from GraphEngine.
|
||||
@@ -135,11 +133,9 @@ class Worker(threading.Thread):
|
||||
|
||||
error: Exception | None = None
|
||||
|
||||
if self._flask_app and self._context_vars:
|
||||
with preserve_flask_contexts(
|
||||
flask_app=self._flask_app,
|
||||
context_vars=self._context_vars,
|
||||
):
|
||||
# Execute the node with preserved context if execution context is provided
|
||||
if self._execution_context is not None:
|
||||
with self._execution_context:
|
||||
self._invoke_node_run_start_hooks(node)
|
||||
try:
|
||||
node_events = node.run()
|
||||
|
||||
@@ -8,9 +8,10 @@ DynamicScaler, and WorkerFactory into a single class.
|
||||
import logging
|
||||
import queue
|
||||
import threading
|
||||
from typing import TYPE_CHECKING, final
|
||||
from typing import final
|
||||
|
||||
from configs import dify_config
|
||||
from core.workflow.context import IExecutionContext
|
||||
from core.workflow.graph import Graph
|
||||
from core.workflow.graph_events import GraphNodeEventBase
|
||||
|
||||
@@ -20,11 +21,6 @@ from ..worker import Worker
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from contextvars import Context
|
||||
|
||||
from flask import Flask
|
||||
|
||||
|
||||
@final
|
||||
class WorkerPool:
|
||||
@@ -42,8 +38,7 @@ class WorkerPool:
|
||||
graph: Graph,
|
||||
layers: list[GraphEngineLayer],
|
||||
stop_event: threading.Event,
|
||||
flask_app: "Flask | None" = None,
|
||||
context_vars: "Context | None" = None,
|
||||
execution_context: IExecutionContext | None = None,
|
||||
min_workers: int | None = None,
|
||||
max_workers: int | None = None,
|
||||
scale_up_threshold: int | None = None,
|
||||
@@ -57,8 +52,7 @@ class WorkerPool:
|
||||
event_queue: Queue for worker events
|
||||
graph: The workflow graph
|
||||
layers: Graph engine layers for node execution hooks
|
||||
flask_app: Optional Flask app for context preservation
|
||||
context_vars: Optional context variables
|
||||
execution_context: Optional execution context for context preservation
|
||||
min_workers: Minimum number of workers
|
||||
max_workers: Maximum number of workers
|
||||
scale_up_threshold: Queue depth to trigger scale up
|
||||
@@ -67,8 +61,7 @@ class WorkerPool:
|
||||
self._ready_queue = ready_queue
|
||||
self._event_queue = event_queue
|
||||
self._graph = graph
|
||||
self._flask_app = flask_app
|
||||
self._context_vars = context_vars
|
||||
self._execution_context = execution_context
|
||||
self._layers = layers
|
||||
|
||||
# Scaling parameters with defaults
|
||||
@@ -152,8 +145,7 @@ class WorkerPool:
|
||||
graph=self._graph,
|
||||
layers=self._layers,
|
||||
worker_id=worker_id,
|
||||
flask_app=self._flask_app,
|
||||
context_vars=self._context_vars,
|
||||
execution_context=self._execution_context,
|
||||
stop_event=self._stop_event,
|
||||
)
|
||||
|
||||
|
||||
@@ -1,11 +1,9 @@
|
||||
import contextvars
|
||||
import logging
|
||||
from collections.abc import Generator, Mapping, Sequence
|
||||
from concurrent.futures import Future, ThreadPoolExecutor, as_completed
|
||||
from datetime import UTC, datetime
|
||||
from typing import TYPE_CHECKING, Any, NewType, cast
|
||||
|
||||
from flask import Flask, current_app
|
||||
from typing_extensions import TypeIs
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMUsage
|
||||
@@ -39,7 +37,6 @@ from core.workflow.nodes.base.node import Node
|
||||
from core.workflow.nodes.iteration.entities import ErrorHandleMode, IterationNodeData
|
||||
from core.workflow.runtime import VariablePool
|
||||
from libs.datetime_utils import naive_utc_now
|
||||
from libs.flask_utils import preserve_flask_contexts
|
||||
|
||||
from .exc import (
|
||||
InvalidIteratorValueError,
|
||||
@@ -51,6 +48,7 @@ from .exc import (
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from core.workflow.context import IExecutionContext
|
||||
from core.workflow.graph_engine import GraphEngine
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -252,8 +250,7 @@ class IterationNode(LLMUsageTrackingMixin, Node[IterationNodeData]):
|
||||
self._execute_single_iteration_parallel,
|
||||
index=index,
|
||||
item=item,
|
||||
flask_app=current_app._get_current_object(), # type: ignore
|
||||
context_vars=contextvars.copy_context(),
|
||||
execution_context=self._capture_execution_context(),
|
||||
)
|
||||
future_to_index[future] = index
|
||||
|
||||
@@ -306,11 +303,10 @@ class IterationNode(LLMUsageTrackingMixin, Node[IterationNodeData]):
|
||||
self,
|
||||
index: int,
|
||||
item: object,
|
||||
flask_app: Flask,
|
||||
context_vars: contextvars.Context,
|
||||
execution_context: "IExecutionContext",
|
||||
) -> tuple[datetime, list[GraphNodeEventBase], object | None, dict[str, Variable], LLMUsage]:
|
||||
"""Execute a single iteration in parallel mode and return results."""
|
||||
with preserve_flask_contexts(flask_app=flask_app, context_vars=context_vars):
|
||||
with execution_context:
|
||||
iter_start_at = datetime.now(UTC).replace(tzinfo=None)
|
||||
events: list[GraphNodeEventBase] = []
|
||||
outputs_temp: list[object] = []
|
||||
@@ -339,6 +335,12 @@ class IterationNode(LLMUsageTrackingMixin, Node[IterationNodeData]):
|
||||
graph_engine.graph_runtime_state.llm_usage,
|
||||
)
|
||||
|
||||
def _capture_execution_context(self) -> "IExecutionContext":
|
||||
"""Capture current execution context for parallel iterations."""
|
||||
from core.workflow.context import capture_current_context
|
||||
|
||||
return capture_current_context()
|
||||
|
||||
def _handle_iteration_success(
|
||||
self,
|
||||
started_at: datetime,
|
||||
|
||||
74
api/libs/workspace_permission.py
Normal file
74
api/libs/workspace_permission.py
Normal file
@@ -0,0 +1,74 @@
|
||||
"""
|
||||
Workspace permission helper functions.
|
||||
|
||||
These helpers check both billing/plan level and workspace-specific policy level permissions.
|
||||
Checks are performed at two levels:
|
||||
1. Billing/plan level - via FeatureService (e.g., SANDBOX plan restrictions)
|
||||
2. Workspace policy level - via EnterpriseService (admin-configured per workspace)
|
||||
"""
|
||||
|
||||
import logging
|
||||
|
||||
from werkzeug.exceptions import Forbidden
|
||||
|
||||
from configs import dify_config
|
||||
from services.enterprise.enterprise_service import EnterpriseService
|
||||
from services.feature_service import FeatureService
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def check_workspace_member_invite_permission(workspace_id: str) -> None:
|
||||
"""
|
||||
Check if workspace allows member invitations at both billing and policy levels.
|
||||
|
||||
Checks performed:
|
||||
1. Billing/plan level - For future expansion (currently no plan-level restriction)
|
||||
2. Enterprise policy level - Admin-configured workspace permission
|
||||
|
||||
Args:
|
||||
workspace_id: The workspace ID to check permissions for
|
||||
|
||||
Raises:
|
||||
Forbidden: If either billing plan or workspace policy prohibits member invitations
|
||||
"""
|
||||
# Check enterprise workspace policy level (only if enterprise enabled)
|
||||
if dify_config.ENTERPRISE_ENABLED:
|
||||
try:
|
||||
permission = EnterpriseService.WorkspacePermissionService.get_permission(workspace_id)
|
||||
if not permission.allow_member_invite:
|
||||
raise Forbidden("Workspace policy prohibits member invitations")
|
||||
except Forbidden:
|
||||
raise
|
||||
except Exception:
|
||||
logger.exception("Failed to check workspace invite permission for %s", workspace_id)
|
||||
|
||||
|
||||
def check_workspace_owner_transfer_permission(workspace_id: str) -> None:
|
||||
"""
|
||||
Check if workspace allows owner transfer at both billing and policy levels.
|
||||
|
||||
Checks performed:
|
||||
1. Billing/plan level - SANDBOX plan blocks owner transfer
|
||||
2. Enterprise policy level - Admin-configured workspace permission
|
||||
|
||||
Args:
|
||||
workspace_id: The workspace ID to check permissions for
|
||||
|
||||
Raises:
|
||||
Forbidden: If either billing plan or workspace policy prohibits ownership transfer
|
||||
"""
|
||||
features = FeatureService.get_features(workspace_id)
|
||||
if not features.is_allow_transfer_workspace:
|
||||
raise Forbidden("Your current plan does not allow workspace ownership transfer")
|
||||
|
||||
# Check enterprise workspace policy level (only if enterprise enabled)
|
||||
if dify_config.ENTERPRISE_ENABLED:
|
||||
try:
|
||||
permission = EnterpriseService.WorkspacePermissionService.get_permission(workspace_id)
|
||||
if not permission.allow_owner_transfer:
|
||||
raise Forbidden("Workspace policy prohibits ownership transfer")
|
||||
except Forbidden:
|
||||
raise
|
||||
except Exception:
|
||||
logger.exception("Failed to check workspace transfer permission for %s", workspace_id)
|
||||
@@ -0,0 +1,35 @@
|
||||
"""change workflow node execution workflow_run index
|
||||
|
||||
Revision ID: 288345cd01d1
|
||||
Revises: 3334862ee907
|
||||
Create Date: 2026-01-16 17:15:00.000000
|
||||
|
||||
"""
|
||||
from alembic import op
|
||||
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision = "288345cd01d1"
|
||||
down_revision = "3334862ee907"
|
||||
branch_labels = None
|
||||
depends_on = None
|
||||
|
||||
|
||||
def upgrade():
|
||||
with op.batch_alter_table("workflow_node_executions", schema=None) as batch_op:
|
||||
batch_op.drop_index("workflow_node_execution_workflow_run_idx")
|
||||
batch_op.create_index(
|
||||
"workflow_node_execution_workflow_run_id_idx",
|
||||
["workflow_run_id"],
|
||||
unique=False,
|
||||
)
|
||||
|
||||
|
||||
def downgrade():
|
||||
with op.batch_alter_table("workflow_node_executions", schema=None) as batch_op:
|
||||
batch_op.drop_index("workflow_node_execution_workflow_run_id_idx")
|
||||
batch_op.create_index(
|
||||
"workflow_node_execution_workflow_run_idx",
|
||||
["tenant_id", "app_id", "workflow_id", "triggered_from", "workflow_run_id"],
|
||||
unique=False,
|
||||
)
|
||||
@@ -781,11 +781,7 @@ class WorkflowNodeExecutionModel(Base): # This model is expected to have `offlo
|
||||
return (
|
||||
PrimaryKeyConstraint("id", name="workflow_node_execution_pkey"),
|
||||
Index(
|
||||
"workflow_node_execution_workflow_run_idx",
|
||||
"tenant_id",
|
||||
"app_id",
|
||||
"workflow_id",
|
||||
"triggered_from",
|
||||
"workflow_node_execution_workflow_run_id_idx",
|
||||
"workflow_run_id",
|
||||
),
|
||||
Index(
|
||||
|
||||
@@ -13,6 +13,8 @@ from collections.abc import Sequence
|
||||
from datetime import datetime
|
||||
from typing import Protocol
|
||||
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
|
||||
from models.workflow import WorkflowNodeExecutionModel
|
||||
|
||||
@@ -130,6 +132,18 @@ class DifyAPIWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository, Pr
|
||||
"""
|
||||
...
|
||||
|
||||
def count_by_runs(self, session: Session, run_ids: Sequence[str]) -> tuple[int, int]:
|
||||
"""
|
||||
Count node executions and offloads for the given workflow run ids.
|
||||
"""
|
||||
...
|
||||
|
||||
def delete_by_runs(self, session: Session, run_ids: Sequence[str]) -> tuple[int, int]:
|
||||
"""
|
||||
Delete node executions and offloads for the given workflow run ids.
|
||||
"""
|
||||
...
|
||||
|
||||
def delete_executions_by_app(
|
||||
self,
|
||||
tenant_id: str,
|
||||
|
||||
@@ -7,17 +7,15 @@ using SQLAlchemy 2.0 style queries for WorkflowNodeExecutionModel operations.
|
||||
|
||||
from collections.abc import Sequence
|
||||
from datetime import datetime
|
||||
from typing import TypedDict, cast
|
||||
from typing import cast
|
||||
|
||||
from sqlalchemy import asc, delete, desc, func, select, tuple_
|
||||
from sqlalchemy import asc, delete, desc, func, select
|
||||
from sqlalchemy.engine import CursorResult
|
||||
from sqlalchemy.orm import Session, sessionmaker
|
||||
|
||||
from models.enums import WorkflowRunTriggeredFrom
|
||||
from models.workflow import (
|
||||
WorkflowNodeExecutionModel,
|
||||
WorkflowNodeExecutionOffload,
|
||||
WorkflowNodeExecutionTriggeredFrom,
|
||||
)
|
||||
from repositories.api_workflow_node_execution_repository import DifyAPIWorkflowNodeExecutionRepository
|
||||
|
||||
@@ -49,26 +47,6 @@ class DifyAPISQLAlchemyWorkflowNodeExecutionRepository(DifyAPIWorkflowNodeExecut
|
||||
"""
|
||||
self._session_maker = session_maker
|
||||
|
||||
@staticmethod
|
||||
def _map_run_triggered_from_to_node_triggered_from(triggered_from: str) -> str:
|
||||
"""
|
||||
Map workflow run triggered_from values to workflow node execution triggered_from values.
|
||||
"""
|
||||
if triggered_from in {
|
||||
WorkflowRunTriggeredFrom.APP_RUN.value,
|
||||
WorkflowRunTriggeredFrom.DEBUGGING.value,
|
||||
WorkflowRunTriggeredFrom.SCHEDULE.value,
|
||||
WorkflowRunTriggeredFrom.PLUGIN.value,
|
||||
WorkflowRunTriggeredFrom.WEBHOOK.value,
|
||||
}:
|
||||
return WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value
|
||||
if triggered_from in {
|
||||
WorkflowRunTriggeredFrom.RAG_PIPELINE_RUN.value,
|
||||
WorkflowRunTriggeredFrom.RAG_PIPELINE_DEBUGGING.value,
|
||||
}:
|
||||
return WorkflowNodeExecutionTriggeredFrom.RAG_PIPELINE_RUN.value
|
||||
return ""
|
||||
|
||||
def get_node_last_execution(
|
||||
self,
|
||||
tenant_id: str,
|
||||
@@ -316,51 +294,16 @@ class DifyAPISQLAlchemyWorkflowNodeExecutionRepository(DifyAPIWorkflowNodeExecut
|
||||
session.commit()
|
||||
return result.rowcount
|
||||
|
||||
class RunContext(TypedDict):
|
||||
run_id: str
|
||||
tenant_id: str
|
||||
app_id: str
|
||||
workflow_id: str
|
||||
triggered_from: str
|
||||
|
||||
@staticmethod
|
||||
def delete_by_runs(session: Session, runs: Sequence[RunContext]) -> tuple[int, int]:
|
||||
def delete_by_runs(self, session: Session, run_ids: Sequence[str]) -> tuple[int, int]:
|
||||
"""
|
||||
Delete node executions (and offloads) for the given workflow runs using indexed columns.
|
||||
|
||||
Uses the composite index on (tenant_id, app_id, workflow_id, triggered_from, workflow_run_id)
|
||||
by filtering on those columns with tuple IN.
|
||||
Delete node executions (and offloads) for the given workflow runs using workflow_run_id.
|
||||
"""
|
||||
if not runs:
|
||||
if not run_ids:
|
||||
return 0, 0
|
||||
|
||||
tuple_values = [
|
||||
(
|
||||
run["tenant_id"],
|
||||
run["app_id"],
|
||||
run["workflow_id"],
|
||||
DifyAPISQLAlchemyWorkflowNodeExecutionRepository._map_run_triggered_from_to_node_triggered_from(
|
||||
run["triggered_from"]
|
||||
),
|
||||
run["run_id"],
|
||||
)
|
||||
for run in runs
|
||||
]
|
||||
|
||||
node_execution_ids = session.scalars(
|
||||
select(WorkflowNodeExecutionModel.id).where(
|
||||
tuple_(
|
||||
WorkflowNodeExecutionModel.tenant_id,
|
||||
WorkflowNodeExecutionModel.app_id,
|
||||
WorkflowNodeExecutionModel.workflow_id,
|
||||
WorkflowNodeExecutionModel.triggered_from,
|
||||
WorkflowNodeExecutionModel.workflow_run_id,
|
||||
).in_(tuple_values)
|
||||
)
|
||||
).all()
|
||||
|
||||
if not node_execution_ids:
|
||||
return 0, 0
|
||||
run_ids = list(run_ids)
|
||||
run_id_filter = WorkflowNodeExecutionModel.workflow_run_id.in_(run_ids)
|
||||
node_execution_ids = select(WorkflowNodeExecutionModel.id).where(run_id_filter)
|
||||
|
||||
offloads_deleted = (
|
||||
cast(
|
||||
@@ -377,55 +320,32 @@ class DifyAPISQLAlchemyWorkflowNodeExecutionRepository(DifyAPIWorkflowNodeExecut
|
||||
node_executions_deleted = (
|
||||
cast(
|
||||
CursorResult,
|
||||
session.execute(
|
||||
delete(WorkflowNodeExecutionModel).where(WorkflowNodeExecutionModel.id.in_(node_execution_ids))
|
||||
),
|
||||
session.execute(delete(WorkflowNodeExecutionModel).where(run_id_filter)),
|
||||
).rowcount
|
||||
or 0
|
||||
)
|
||||
|
||||
return node_executions_deleted, offloads_deleted
|
||||
|
||||
@staticmethod
|
||||
def count_by_runs(session: Session, runs: Sequence[RunContext]) -> tuple[int, int]:
|
||||
def count_by_runs(self, session: Session, run_ids: Sequence[str]) -> tuple[int, int]:
|
||||
"""
|
||||
Count node executions (and offloads) for the given workflow runs using indexed columns.
|
||||
Count node executions (and offloads) for the given workflow runs using workflow_run_id.
|
||||
"""
|
||||
if not runs:
|
||||
if not run_ids:
|
||||
return 0, 0
|
||||
|
||||
tuple_values = [
|
||||
(
|
||||
run["tenant_id"],
|
||||
run["app_id"],
|
||||
run["workflow_id"],
|
||||
DifyAPISQLAlchemyWorkflowNodeExecutionRepository._map_run_triggered_from_to_node_triggered_from(
|
||||
run["triggered_from"]
|
||||
),
|
||||
run["run_id"],
|
||||
)
|
||||
for run in runs
|
||||
]
|
||||
tuple_filter = tuple_(
|
||||
WorkflowNodeExecutionModel.tenant_id,
|
||||
WorkflowNodeExecutionModel.app_id,
|
||||
WorkflowNodeExecutionModel.workflow_id,
|
||||
WorkflowNodeExecutionModel.triggered_from,
|
||||
WorkflowNodeExecutionModel.workflow_run_id,
|
||||
).in_(tuple_values)
|
||||
run_ids = list(run_ids)
|
||||
run_id_filter = WorkflowNodeExecutionModel.workflow_run_id.in_(run_ids)
|
||||
|
||||
node_executions_count = (
|
||||
session.scalar(select(func.count()).select_from(WorkflowNodeExecutionModel).where(tuple_filter)) or 0
|
||||
session.scalar(select(func.count()).select_from(WorkflowNodeExecutionModel).where(run_id_filter)) or 0
|
||||
)
|
||||
node_execution_ids = select(WorkflowNodeExecutionModel.id).where(run_id_filter)
|
||||
offloads_count = (
|
||||
session.scalar(
|
||||
select(func.count())
|
||||
.select_from(WorkflowNodeExecutionOffload)
|
||||
.join(
|
||||
WorkflowNodeExecutionModel,
|
||||
WorkflowNodeExecutionOffload.node_execution_id == WorkflowNodeExecutionModel.id,
|
||||
)
|
||||
.where(tuple_filter)
|
||||
.where(WorkflowNodeExecutionOffload.node_execution_id.in_(node_execution_ids))
|
||||
)
|
||||
or 0
|
||||
)
|
||||
|
||||
@@ -1381,6 +1381,11 @@ class RegisterService:
|
||||
normalized_email = email.lower()
|
||||
|
||||
"""Invite new member"""
|
||||
# Check workspace permission for member invitations
|
||||
from libs.workspace_permission import check_workspace_member_invite_permission
|
||||
|
||||
check_workspace_member_invite_permission(tenant.id)
|
||||
|
||||
with Session(db.engine) as session:
|
||||
account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
|
||||
|
||||
|
||||
@@ -13,10 +13,11 @@ import sqlalchemy as sa
|
||||
from redis.exceptions import LockNotOwnedError
|
||||
from sqlalchemy import exists, func, select
|
||||
from sqlalchemy.orm import Session
|
||||
from werkzeug.exceptions import NotFound
|
||||
from werkzeug.exceptions import Forbidden, NotFound
|
||||
|
||||
from configs import dify_config
|
||||
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
|
||||
from core.file import helpers as file_helpers
|
||||
from core.helper.name_generator import generate_incremental_name
|
||||
from core.model_manager import ModelManager
|
||||
from core.model_runtime.entities.model_entities import ModelFeature, ModelType
|
||||
@@ -73,6 +74,7 @@ from services.errors.document import DocumentIndexingError
|
||||
from services.errors.file import FileNotExistsError
|
||||
from services.external_knowledge_service import ExternalDatasetService
|
||||
from services.feature_service import FeatureModel, FeatureService
|
||||
from services.file_service import FileService
|
||||
from services.rag_pipeline.rag_pipeline import RagPipelineService
|
||||
from services.tag_service import TagService
|
||||
from services.vector_service import VectorService
|
||||
@@ -1162,6 +1164,7 @@ class DocumentService:
|
||||
Document.archived.is_(True),
|
||||
),
|
||||
}
|
||||
DOCUMENT_BATCH_DOWNLOAD_ZIP_FILENAME_EXTENSION = ".zip"
|
||||
|
||||
@classmethod
|
||||
def normalize_display_status(cls, status: str | None) -> str | None:
|
||||
@@ -1288,6 +1291,143 @@ class DocumentService:
|
||||
else:
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def get_documents_by_ids(dataset_id: str, document_ids: Sequence[str]) -> Sequence[Document]:
|
||||
"""Fetch documents for a dataset in a single batch query."""
|
||||
if not document_ids:
|
||||
return []
|
||||
document_id_list: list[str] = [str(document_id) for document_id in document_ids]
|
||||
# Fetch all requested documents in one query to avoid N+1 lookups.
|
||||
documents: Sequence[Document] = db.session.scalars(
|
||||
select(Document).where(
|
||||
Document.dataset_id == dataset_id,
|
||||
Document.id.in_(document_id_list),
|
||||
)
|
||||
).all()
|
||||
return documents
|
||||
|
||||
@staticmethod
|
||||
def get_document_download_url(document: Document) -> str:
|
||||
"""
|
||||
Return a signed download URL for an upload-file document.
|
||||
"""
|
||||
upload_file = DocumentService._get_upload_file_for_upload_file_document(document)
|
||||
return file_helpers.get_signed_file_url(upload_file_id=upload_file.id, as_attachment=True)
|
||||
|
||||
@staticmethod
|
||||
def prepare_document_batch_download_zip(
|
||||
*,
|
||||
dataset_id: str,
|
||||
document_ids: Sequence[str],
|
||||
tenant_id: str,
|
||||
current_user: Account,
|
||||
) -> tuple[list[UploadFile], str]:
|
||||
"""
|
||||
Resolve upload files for batch ZIP downloads and generate a client-visible filename.
|
||||
"""
|
||||
dataset = DatasetService.get_dataset(dataset_id)
|
||||
if not dataset:
|
||||
raise NotFound("Dataset not found.")
|
||||
try:
|
||||
DatasetService.check_dataset_permission(dataset, current_user)
|
||||
except NoPermissionError as e:
|
||||
raise Forbidden(str(e))
|
||||
|
||||
upload_files_by_document_id = DocumentService._get_upload_files_by_document_id_for_zip_download(
|
||||
dataset_id=dataset_id,
|
||||
document_ids=document_ids,
|
||||
tenant_id=tenant_id,
|
||||
)
|
||||
upload_files = [upload_files_by_document_id[document_id] for document_id in document_ids]
|
||||
download_name = DocumentService._generate_document_batch_download_zip_filename()
|
||||
return upload_files, download_name
|
||||
|
||||
@staticmethod
|
||||
def _generate_document_batch_download_zip_filename() -> str:
|
||||
"""
|
||||
Generate a random attachment filename for the batch download ZIP.
|
||||
"""
|
||||
return f"{uuid.uuid4().hex}{DocumentService.DOCUMENT_BATCH_DOWNLOAD_ZIP_FILENAME_EXTENSION}"
|
||||
|
||||
@staticmethod
|
||||
def _get_upload_file_id_for_upload_file_document(
|
||||
document: Document,
|
||||
*,
|
||||
invalid_source_message: str,
|
||||
missing_file_message: str,
|
||||
) -> str:
|
||||
"""
|
||||
Normalize and validate `Document -> UploadFile` linkage for download flows.
|
||||
"""
|
||||
if document.data_source_type != "upload_file":
|
||||
raise NotFound(invalid_source_message)
|
||||
|
||||
data_source_info: dict[str, Any] = document.data_source_info_dict or {}
|
||||
upload_file_id: str | None = data_source_info.get("upload_file_id")
|
||||
if not upload_file_id:
|
||||
raise NotFound(missing_file_message)
|
||||
|
||||
return str(upload_file_id)
|
||||
|
||||
@staticmethod
|
||||
def _get_upload_file_for_upload_file_document(document: Document) -> UploadFile:
|
||||
"""
|
||||
Load the `UploadFile` row for an upload-file document.
|
||||
"""
|
||||
upload_file_id = DocumentService._get_upload_file_id_for_upload_file_document(
|
||||
document,
|
||||
invalid_source_message="Document does not have an uploaded file to download.",
|
||||
missing_file_message="Uploaded file not found.",
|
||||
)
|
||||
upload_files_by_id = FileService.get_upload_files_by_ids(document.tenant_id, [upload_file_id])
|
||||
upload_file = upload_files_by_id.get(upload_file_id)
|
||||
if not upload_file:
|
||||
raise NotFound("Uploaded file not found.")
|
||||
return upload_file
|
||||
|
||||
@staticmethod
|
||||
def _get_upload_files_by_document_id_for_zip_download(
|
||||
*,
|
||||
dataset_id: str,
|
||||
document_ids: Sequence[str],
|
||||
tenant_id: str,
|
||||
) -> dict[str, UploadFile]:
|
||||
"""
|
||||
Batch load upload files keyed by document id for ZIP downloads.
|
||||
"""
|
||||
document_id_list: list[str] = [str(document_id) for document_id in document_ids]
|
||||
|
||||
documents = DocumentService.get_documents_by_ids(dataset_id, document_id_list)
|
||||
documents_by_id: dict[str, Document] = {str(document.id): document for document in documents}
|
||||
|
||||
missing_document_ids: set[str] = set(document_id_list) - set(documents_by_id.keys())
|
||||
if missing_document_ids:
|
||||
raise NotFound("Document not found.")
|
||||
|
||||
upload_file_ids: list[str] = []
|
||||
upload_file_ids_by_document_id: dict[str, str] = {}
|
||||
for document_id, document in documents_by_id.items():
|
||||
if document.tenant_id != tenant_id:
|
||||
raise Forbidden("No permission.")
|
||||
|
||||
upload_file_id = DocumentService._get_upload_file_id_for_upload_file_document(
|
||||
document,
|
||||
invalid_source_message="Only uploaded-file documents can be downloaded as ZIP.",
|
||||
missing_file_message="Only uploaded-file documents can be downloaded as ZIP.",
|
||||
)
|
||||
upload_file_ids.append(upload_file_id)
|
||||
upload_file_ids_by_document_id[document_id] = upload_file_id
|
||||
|
||||
upload_files_by_id = FileService.get_upload_files_by_ids(tenant_id, upload_file_ids)
|
||||
missing_upload_file_ids: set[str] = set(upload_file_ids) - set(upload_files_by_id.keys())
|
||||
if missing_upload_file_ids:
|
||||
raise NotFound("Only uploaded-file documents can be downloaded as ZIP.")
|
||||
|
||||
return {
|
||||
document_id: upload_files_by_id[upload_file_id]
|
||||
for document_id, upload_file_id in upload_file_ids_by_document_id.items()
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def get_document_by_id(document_id: str) -> Document | None:
|
||||
document = db.session.query(Document).where(Document.id == document_id).first()
|
||||
|
||||
@@ -13,6 +13,23 @@ class WebAppSettings(BaseModel):
|
||||
)
|
||||
|
||||
|
||||
class WorkspacePermission(BaseModel):
|
||||
workspace_id: str = Field(
|
||||
description="The ID of the workspace.",
|
||||
alias="workspaceId",
|
||||
)
|
||||
allow_member_invite: bool = Field(
|
||||
description="Whether to allow members to invite new members to the workspace.",
|
||||
default=False,
|
||||
alias="allowMemberInvite",
|
||||
)
|
||||
allow_owner_transfer: bool = Field(
|
||||
description="Whether to allow owners to transfer ownership of the workspace.",
|
||||
default=False,
|
||||
alias="allowOwnerTransfer",
|
||||
)
|
||||
|
||||
|
||||
class EnterpriseService:
|
||||
@classmethod
|
||||
def get_info(cls):
|
||||
@@ -44,6 +61,16 @@ class EnterpriseService:
|
||||
except ValueError as e:
|
||||
raise ValueError(f"Invalid date format: {data}") from e
|
||||
|
||||
class WorkspacePermissionService:
|
||||
@classmethod
|
||||
def get_permission(cls, workspace_id: str):
|
||||
if not workspace_id:
|
||||
raise ValueError("workspace_id must be provided.")
|
||||
data = EnterpriseRequest.send_request("GET", f"/workspaces/{workspace_id}/permission")
|
||||
if not data or "permission" not in data:
|
||||
raise ValueError("No data found.")
|
||||
return WorkspacePermission.model_validate(data["permission"])
|
||||
|
||||
class WebAppAuth:
|
||||
@classmethod
|
||||
def is_user_allowed_to_access_webapp(cls, user_id: str, app_id: str):
|
||||
|
||||
@@ -2,7 +2,11 @@ import base64
|
||||
import hashlib
|
||||
import os
|
||||
import uuid
|
||||
from collections.abc import Iterator, Sequence
|
||||
from contextlib import contextmanager, suppress
|
||||
from tempfile import NamedTemporaryFile
|
||||
from typing import Literal, Union
|
||||
from zipfile import ZIP_DEFLATED, ZipFile
|
||||
|
||||
from sqlalchemy import Engine, select
|
||||
from sqlalchemy.orm import Session, sessionmaker
|
||||
@@ -17,6 +21,7 @@ from constants import (
|
||||
)
|
||||
from core.file import helpers as file_helpers
|
||||
from core.rag.extractor.extract_processor import ExtractProcessor
|
||||
from extensions.ext_database import db
|
||||
from extensions.ext_storage import storage
|
||||
from libs.datetime_utils import naive_utc_now
|
||||
from libs.helper import extract_tenant_id
|
||||
@@ -167,6 +172,9 @@ class FileService:
|
||||
return upload_file
|
||||
|
||||
def get_file_preview(self, file_id: str):
|
||||
"""
|
||||
Return a short text preview extracted from a document file.
|
||||
"""
|
||||
with self._session_maker(expire_on_commit=False) as session:
|
||||
upload_file = session.query(UploadFile).where(UploadFile.id == file_id).first()
|
||||
|
||||
@@ -253,3 +261,101 @@ class FileService:
|
||||
return
|
||||
storage.delete(upload_file.key)
|
||||
session.delete(upload_file)
|
||||
|
||||
@staticmethod
|
||||
def get_upload_files_by_ids(tenant_id: str, upload_file_ids: Sequence[str]) -> dict[str, UploadFile]:
|
||||
"""
|
||||
Fetch `UploadFile` rows for a tenant in a single batch query.
|
||||
|
||||
This is a generic `UploadFile` lookup helper (not dataset/document specific), so it lives in `FileService`.
|
||||
"""
|
||||
if not upload_file_ids:
|
||||
return {}
|
||||
|
||||
# Normalize and deduplicate ids before using them in the IN clause.
|
||||
upload_file_id_list: list[str] = [str(upload_file_id) for upload_file_id in upload_file_ids]
|
||||
unique_upload_file_ids: list[str] = list(set(upload_file_id_list))
|
||||
|
||||
# Fetch upload files in one query for efficient batch access.
|
||||
upload_files: Sequence[UploadFile] = db.session.scalars(
|
||||
select(UploadFile).where(
|
||||
UploadFile.tenant_id == tenant_id,
|
||||
UploadFile.id.in_(unique_upload_file_ids),
|
||||
)
|
||||
).all()
|
||||
return {str(upload_file.id): upload_file for upload_file in upload_files}
|
||||
|
||||
@staticmethod
|
||||
def _sanitize_zip_entry_name(name: str) -> str:
|
||||
"""
|
||||
Sanitize a ZIP entry name to avoid path traversal and weird separators.
|
||||
|
||||
We keep this conservative: the upload flow already rejects `/` and `\\`, but older rows (or imported data)
|
||||
could still contain unsafe names.
|
||||
"""
|
||||
# Drop any directory components and prevent empty names.
|
||||
base = os.path.basename(name).strip() or "file"
|
||||
|
||||
# ZIP uses forward slashes as separators; remove any residual separator characters.
|
||||
return base.replace("/", "_").replace("\\", "_")
|
||||
|
||||
@staticmethod
|
||||
def _dedupe_zip_entry_name(original_name: str, used_names: set[str]) -> str:
|
||||
"""
|
||||
Return a unique ZIP entry name, inserting suffixes before the extension.
|
||||
"""
|
||||
# Keep the original name when it's not already used.
|
||||
if original_name not in used_names:
|
||||
return original_name
|
||||
|
||||
# Insert suffixes before the extension (e.g., "doc.txt" -> "doc (1).txt").
|
||||
stem, extension = os.path.splitext(original_name)
|
||||
suffix = 1
|
||||
while True:
|
||||
candidate = f"{stem} ({suffix}){extension}"
|
||||
if candidate not in used_names:
|
||||
return candidate
|
||||
suffix += 1
|
||||
|
||||
@staticmethod
|
||||
@contextmanager
|
||||
def build_upload_files_zip_tempfile(
|
||||
*,
|
||||
upload_files: Sequence[UploadFile],
|
||||
) -> Iterator[str]:
|
||||
"""
|
||||
Build a ZIP from `UploadFile`s and yield a tempfile path.
|
||||
|
||||
We yield a path (rather than an open file handle) to avoid "read of closed file" issues when Flask/Werkzeug
|
||||
streams responses. The caller is expected to keep this context open until the response is fully sent, then
|
||||
close it (e.g., via `response.call_on_close(...)`) to delete the tempfile.
|
||||
"""
|
||||
used_names: set[str] = set()
|
||||
|
||||
# Build a ZIP in a temp file and keep it on disk until the caller finishes streaming it.
|
||||
tmp_path: str | None = None
|
||||
try:
|
||||
with NamedTemporaryFile(mode="w+b", suffix=".zip", delete=False) as tmp:
|
||||
tmp_path = tmp.name
|
||||
with ZipFile(tmp, mode="w", compression=ZIP_DEFLATED) as zf:
|
||||
for upload_file in upload_files:
|
||||
# Ensure the entry name is safe and unique.
|
||||
safe_name = FileService._sanitize_zip_entry_name(upload_file.name)
|
||||
arcname = FileService._dedupe_zip_entry_name(safe_name, used_names)
|
||||
used_names.add(arcname)
|
||||
|
||||
# Stream file bytes from storage into the ZIP entry.
|
||||
with zf.open(arcname, "w") as entry:
|
||||
for chunk in storage.load(upload_file.key, stream=True):
|
||||
entry.write(chunk)
|
||||
|
||||
# Flush so `send_file(path, ...)` can re-open it safely on all platforms.
|
||||
tmp.flush()
|
||||
|
||||
assert tmp_path is not None
|
||||
yield tmp_path
|
||||
finally:
|
||||
# Remove the temp file when the context is closed (typically after the response finishes streaming).
|
||||
if tmp_path is not None:
|
||||
with suppress(FileNotFoundError):
|
||||
os.remove(tmp_path)
|
||||
|
||||
@@ -10,9 +10,7 @@ from enums.cloud_plan import CloudPlan
|
||||
from extensions.ext_database import db
|
||||
from models.workflow import WorkflowRun
|
||||
from repositories.api_workflow_run_repository import APIWorkflowRunRepository
|
||||
from repositories.sqlalchemy_api_workflow_node_execution_repository import (
|
||||
DifyAPISQLAlchemyWorkflowNodeExecutionRepository,
|
||||
)
|
||||
from repositories.factory import DifyAPIRepositoryFactory
|
||||
from repositories.sqlalchemy_workflow_trigger_log_repository import SQLAlchemyWorkflowTriggerLogRepository
|
||||
from services.billing_service import BillingService, SubscriptionPlan
|
||||
|
||||
@@ -92,9 +90,12 @@ class WorkflowRunCleanup:
|
||||
paid_or_skipped = len(run_rows) - len(free_runs)
|
||||
|
||||
if not free_runs:
|
||||
skipped_message = (
|
||||
f"[batch #{batch_index}] skipped (no sandbox runs in batch, {paid_or_skipped} paid/unknown)"
|
||||
)
|
||||
click.echo(
|
||||
click.style(
|
||||
f"[batch #{batch_index}] skipped (no sandbox runs in batch, {paid_or_skipped} paid/unknown)",
|
||||
skipped_message,
|
||||
fg="yellow",
|
||||
)
|
||||
)
|
||||
@@ -255,21 +256,6 @@ class WorkflowRunCleanup:
|
||||
trigger_repo = SQLAlchemyWorkflowTriggerLogRepository(session)
|
||||
return trigger_repo.count_by_run_ids(run_ids)
|
||||
|
||||
@staticmethod
|
||||
def _build_run_contexts(
|
||||
runs: Sequence[WorkflowRun],
|
||||
) -> list[DifyAPISQLAlchemyWorkflowNodeExecutionRepository.RunContext]:
|
||||
return [
|
||||
{
|
||||
"run_id": run.id,
|
||||
"tenant_id": run.tenant_id,
|
||||
"app_id": run.app_id,
|
||||
"workflow_id": run.workflow_id,
|
||||
"triggered_from": run.triggered_from,
|
||||
}
|
||||
for run in runs
|
||||
]
|
||||
|
||||
@staticmethod
|
||||
def _empty_related_counts() -> dict[str, int]:
|
||||
return {
|
||||
@@ -293,9 +279,15 @@ class WorkflowRunCleanup:
|
||||
)
|
||||
|
||||
def _count_node_executions(self, session: Session, runs: Sequence[WorkflowRun]) -> tuple[int, int]:
|
||||
run_contexts = self._build_run_contexts(runs)
|
||||
return DifyAPISQLAlchemyWorkflowNodeExecutionRepository.count_by_runs(session, run_contexts)
|
||||
run_ids = [run.id for run in runs]
|
||||
repo = DifyAPIRepositoryFactory.create_api_workflow_node_execution_repository(
|
||||
session_maker=sessionmaker(bind=session.get_bind(), expire_on_commit=False)
|
||||
)
|
||||
return repo.count_by_runs(session, run_ids)
|
||||
|
||||
def _delete_node_executions(self, session: Session, runs: Sequence[WorkflowRun]) -> tuple[int, int]:
|
||||
run_contexts = self._build_run_contexts(runs)
|
||||
return DifyAPISQLAlchemyWorkflowNodeExecutionRepository.delete_by_runs(session, run_contexts)
|
||||
run_ids = [run.id for run in runs]
|
||||
repo = DifyAPIRepositoryFactory.create_api_workflow_node_execution_repository(
|
||||
session_maker=sessionmaker(bind=session.get_bind(), expire_on_commit=False)
|
||||
)
|
||||
return repo.delete_by_runs(session, run_ids)
|
||||
|
||||
@@ -83,7 +83,30 @@
|
||||
<p class="content1">Dear {{ to }},</p>
|
||||
<p class="content2">{{ inviter_name }} is pleased to invite you to join our workspace on Dify, a platform specifically designed for LLM application development. On Dify, you can explore, create, and collaborate to build and operate AI applications.</p>
|
||||
<p class="content2">Click the button below to log in to Dify and join the workspace.</p>
|
||||
<p style="text-align: center; margin: 0; margin-bottom: 32px;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">Login Here</a></p>
|
||||
<div style="text-align: center; margin-bottom: 32px;">
|
||||
<a href="{{ url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">Login Here</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
If the button doesn't work, copy and paste this link into your browser:<br>
|
||||
<a href="{{ url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="content2">Best regards,</p>
|
||||
<p class="content2">Dify Team</p>
|
||||
</div>
|
||||
|
||||
@@ -83,7 +83,30 @@
|
||||
<p class="content1">尊敬的 {{ to }},</p>
|
||||
<p class="content2">{{ inviter_name }} 现邀请您加入我们在 Dify 的工作区,这是一个专为 LLM 应用开发而设计的平台。在 Dify 上,您可以探索、创造和合作,构建和运营 AI 应用。</p>
|
||||
<p class="content2">点击下方按钮即可登录 Dify 并且加入空间。</p>
|
||||
<p style="text-align: center; margin: 0; margin-bottom: 32px;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">在此登录</a></p>
|
||||
<div style="text-align: center; margin-bottom: 32px;">
|
||||
<a href="{{ url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">在此登录</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
如果按钮无法使用,请将以下链接复制到浏览器打开:<br>
|
||||
<a href="{{ url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="content2">此致,</p>
|
||||
<p class="content2">Dify 团队</p>
|
||||
</div>
|
||||
|
||||
@@ -115,7 +115,30 @@
|
||||
We noticed you tried to sign up, but this email is already registered with an existing account.
|
||||
|
||||
Please log in here: </p>
|
||||
<a href="{{ login_url }}" class="button">Log In</a>
|
||||
<div style="text-align: center; margin-bottom: 20px;">
|
||||
<a href="{{ login_url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">Log In</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
If the button doesn't work, copy and paste this link into your browser:<br>
|
||||
<a href="{{ login_url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ login_url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="description">
|
||||
If you forgot your password, you can reset it here: <a href="{{ reset_password_url }}"
|
||||
class="reset-btn">Reset Password</a>
|
||||
|
||||
@@ -115,7 +115,30 @@
|
||||
我们注意到您尝试注册,但此电子邮件已注册。
|
||||
|
||||
请在此登录: </p>
|
||||
<a href="{{ login_url }}" class="button">登录</a>
|
||||
<div style="text-align: center; margin-bottom: 20px;">
|
||||
<a href="{{ login_url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">登录</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
如果按钮无法使用,请将以下链接复制到浏览器打开:<br>
|
||||
<a href="{{ login_url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ login_url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="description">
|
||||
如果您忘记了密码,可以在此重置: <a href="{{ reset_password_url }}" class="reset-btn">重置密码</a>
|
||||
</p>
|
||||
|
||||
@@ -92,12 +92,34 @@
|
||||
platform specifically designed for LLM application development. On {{application_title}}, you can explore,
|
||||
create, and collaborate to build and operate AI applications.</p>
|
||||
<p class="content2">Click the button below to log in to {{application_title}} and join the workspace.</p>
|
||||
<p style="text-align: center; margin: 0; margin-bottom: 32px;"><a style="color: #fff; text-decoration: none"
|
||||
class="button" href="{{ url }}">Login Here</a></p>
|
||||
<div style="text-align: center; margin-bottom: 32px;">
|
||||
<a href="{{ url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">Login Here</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
If the button doesn't work, copy and paste this link into your browser:<br>
|
||||
<a href="{{ url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="content2">Best regards,</p>
|
||||
<p class="content2">{{application_title}} Team</p>
|
||||
</div>
|
||||
</div>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
</html>
|
||||
|
||||
@@ -81,7 +81,30 @@
|
||||
<p class="content1">尊敬的 {{ to }},</p>
|
||||
<p class="content2">{{ inviter_name }} 现邀请您加入我们在 {{application_title}} 的工作区,这是一个专为 LLM 应用开发而设计的平台。在 {{application_title}} 上,您可以探索、创造和合作,构建和运营 AI 应用。</p>
|
||||
<p class="content2">点击下方按钮即可登录 {{application_title}} 并且加入空间。</p>
|
||||
<p style="text-align: center; margin: 0; margin-bottom: 32px;"><a style="color: #fff; text-decoration: none" class="button" href="{{ url }}">在此登录</a></p>
|
||||
<div style="text-align: center; margin-bottom: 32px;">
|
||||
<a href="{{ url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">在此登录</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
如果按钮无法使用,请将以下链接复制到浏览器打开:<br>
|
||||
<a href="{{ url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="content2">此致,</p>
|
||||
<p class="content2">{{application_title}} 团队</p>
|
||||
</div>
|
||||
|
||||
@@ -111,7 +111,30 @@
|
||||
We noticed you tried to sign up, but this email is already registered with an existing account.
|
||||
|
||||
Please log in here: </p>
|
||||
<a href="{{ login_url }}" class="button">Log In</a>
|
||||
<div style="text-align: center; margin-bottom: 20px;">
|
||||
<a href="{{ login_url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">Log In</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
If the button doesn't work, copy and paste this link into your browser:<br>
|
||||
<a href="{{ login_url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ login_url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="description">
|
||||
If you forgot your password, you can reset it here: <a href="{{ reset_password_url }}"
|
||||
class="reset-btn">Reset Password</a>
|
||||
|
||||
@@ -111,7 +111,30 @@
|
||||
我们注意到您尝试注册,但此电子邮件已注册。
|
||||
|
||||
请在此登录: </p>
|
||||
<a href="{{ login_url }}" class="button">登录</a>
|
||||
<div style="text-align: center; margin-bottom: 20px;">
|
||||
<a href="{{ login_url }}"
|
||||
style="background-color:#2563eb;
|
||||
color:#ffffff !important;
|
||||
text-decoration:none;
|
||||
display:inline-block;
|
||||
font-weight:600;
|
||||
border-radius:4px;
|
||||
font-size:14px;
|
||||
line-height:18px;
|
||||
font-family: Helvetica, Arial, sans-serif;
|
||||
text-align:center;
|
||||
border-top: 10px solid #2563eb;
|
||||
border-bottom: 10px solid #2563eb;
|
||||
border-left: 20px solid #2563eb;
|
||||
border-right: 20px solid #2563eb;
|
||||
">登录</a>
|
||||
<p style="font-size: 12px; color: #666666; margin-top: 20px; margin-bottom: 0;">
|
||||
如果按钮无法使用,请将以下链接复制到浏览器打开:<br>
|
||||
<a href="{{ login_url }}" style="color: #2563eb; text-decoration: underline; word-break: break-all;">
|
||||
{{ login_url }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
<p class="description">
|
||||
如果您忘记了密码,可以在此重置: <a href="{{ reset_password_url }}" class="reset-btn">重置密码</a>
|
||||
</p>
|
||||
|
||||
@@ -1,254 +0,0 @@
|
||||
"""
|
||||
Unit tests for XSS prevention in App payloads.
|
||||
|
||||
This test module validates that HTML tags, JavaScript, and other potentially
|
||||
dangerous content are rejected in App names and descriptions.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
|
||||
from controllers.console.app.app import CopyAppPayload, CreateAppPayload, UpdateAppPayload
|
||||
|
||||
|
||||
class TestXSSPreventionUnit:
|
||||
"""Unit tests for XSS prevention in App payloads."""
|
||||
|
||||
def test_create_app_valid_names(self):
|
||||
"""Test CreateAppPayload with valid app names."""
|
||||
# Normal app names should be valid
|
||||
valid_names = [
|
||||
"My App",
|
||||
"Test App 123",
|
||||
"App with - dash",
|
||||
"App with _ underscore",
|
||||
"App with + plus",
|
||||
"App with () parentheses",
|
||||
"App with [] brackets",
|
||||
"App with {} braces",
|
||||
"App with ! exclamation",
|
||||
"App with @ at",
|
||||
"App with # hash",
|
||||
"App with $ dollar",
|
||||
"App with % percent",
|
||||
"App with ^ caret",
|
||||
"App with & ampersand",
|
||||
"App with * asterisk",
|
||||
"Unicode: 测试应用",
|
||||
"Emoji: 🤖",
|
||||
"Mixed: Test 测试 123",
|
||||
]
|
||||
|
||||
for name in valid_names:
|
||||
payload = CreateAppPayload(
|
||||
name=name,
|
||||
mode="chat",
|
||||
)
|
||||
assert payload.name == name
|
||||
|
||||
def test_create_app_xss_script_tags(self):
|
||||
"""Test CreateAppPayload rejects script tags."""
|
||||
xss_payloads = [
|
||||
"<script>alert(document.cookie)</script>",
|
||||
"<Script>alert(1)</Script>",
|
||||
"<SCRIPT>alert('XSS')</SCRIPT>",
|
||||
"<script>alert(String.fromCharCode(88,83,83))</script>",
|
||||
"<script src='evil.js'></script>",
|
||||
"<script>document.location='http://evil.com'</script>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_iframe_tags(self):
|
||||
"""Test CreateAppPayload rejects iframe tags."""
|
||||
xss_payloads = [
|
||||
"<iframe src='evil.com'></iframe>",
|
||||
"<Iframe srcdoc='<script>alert(1)</script>'></iframe>",
|
||||
"<IFRAME src='javascript:alert(1)'></iframe>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_javascript_protocol(self):
|
||||
"""Test CreateAppPayload rejects javascript: protocol."""
|
||||
xss_payloads = [
|
||||
"javascript:alert(1)",
|
||||
"JAVASCRIPT:alert(1)",
|
||||
"JavaScript:alert(document.cookie)",
|
||||
"javascript:void(0)",
|
||||
"javascript://comment%0Aalert(1)",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_svg_onload(self):
|
||||
"""Test CreateAppPayload rejects SVG with onload."""
|
||||
xss_payloads = [
|
||||
"<svg onload=alert(1)>",
|
||||
"<SVG ONLOAD=alert(1)>",
|
||||
"<svg/x/onload=alert(1)>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_event_handlers(self):
|
||||
"""Test CreateAppPayload rejects HTML event handlers."""
|
||||
xss_payloads = [
|
||||
"<div onclick=alert(1)>",
|
||||
"<img onerror=alert(1)>",
|
||||
"<body onload=alert(1)>",
|
||||
"<input onfocus=alert(1)>",
|
||||
"<a onmouseover=alert(1)>",
|
||||
"<DIV ONCLICK=alert(1)>",
|
||||
"<img src=x onerror=alert(1)>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_object_embed(self):
|
||||
"""Test CreateAppPayload rejects object and embed tags."""
|
||||
xss_payloads = [
|
||||
"<object data='evil.swf'></object>",
|
||||
"<embed src='evil.swf'>",
|
||||
"<OBJECT data='javascript:alert(1)'></OBJECT>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_link_javascript(self):
|
||||
"""Test CreateAppPayload rejects link tags with javascript."""
|
||||
xss_payloads = [
|
||||
"<link href='javascript:alert(1)'>",
|
||||
"<LINK HREF='javascript:alert(1)'>",
|
||||
]
|
||||
|
||||
for name in xss_payloads:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_xss_in_description(self):
|
||||
"""Test CreateAppPayload rejects XSS in description."""
|
||||
xss_descriptions = [
|
||||
"<script>alert(1)</script>",
|
||||
"javascript:alert(1)",
|
||||
"<img onerror=alert(1)>",
|
||||
]
|
||||
|
||||
for description in xss_descriptions:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(
|
||||
name="Valid Name",
|
||||
mode="chat",
|
||||
description=description,
|
||||
)
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_create_app_valid_descriptions(self):
|
||||
"""Test CreateAppPayload with valid descriptions."""
|
||||
valid_descriptions = [
|
||||
"A simple description",
|
||||
"Description with < and > symbols",
|
||||
"Description with & ampersand",
|
||||
"Description with 'quotes' and \"double quotes\"",
|
||||
"Description with / slashes",
|
||||
"Description with \\ backslashes",
|
||||
"Description with ; semicolons",
|
||||
"Unicode: 这是一个描述",
|
||||
"Emoji: 🎉🚀",
|
||||
]
|
||||
|
||||
for description in valid_descriptions:
|
||||
payload = CreateAppPayload(
|
||||
name="Valid App Name",
|
||||
mode="chat",
|
||||
description=description,
|
||||
)
|
||||
assert payload.description == description
|
||||
|
||||
def test_create_app_none_description(self):
|
||||
"""Test CreateAppPayload with None description."""
|
||||
payload = CreateAppPayload(
|
||||
name="Valid App Name",
|
||||
mode="chat",
|
||||
description=None,
|
||||
)
|
||||
assert payload.description is None
|
||||
|
||||
def test_update_app_xss_prevention(self):
|
||||
"""Test UpdateAppPayload also prevents XSS."""
|
||||
xss_names = [
|
||||
"<script>alert(1)</script>",
|
||||
"javascript:alert(1)",
|
||||
"<img onerror=alert(1)>",
|
||||
]
|
||||
|
||||
for name in xss_names:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
UpdateAppPayload(name=name)
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_update_app_valid_names(self):
|
||||
"""Test UpdateAppPayload with valid names."""
|
||||
payload = UpdateAppPayload(name="Valid Updated Name")
|
||||
assert payload.name == "Valid Updated Name"
|
||||
|
||||
def test_copy_app_xss_prevention(self):
|
||||
"""Test CopyAppPayload also prevents XSS."""
|
||||
xss_names = [
|
||||
"<script>alert(1)</script>",
|
||||
"javascript:alert(1)",
|
||||
"<img onerror=alert(1)>",
|
||||
]
|
||||
|
||||
for name in xss_names:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CopyAppPayload(name=name)
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
|
||||
def test_copy_app_valid_names(self):
|
||||
"""Test CopyAppPayload with valid names."""
|
||||
payload = CopyAppPayload(name="Valid Copy Name")
|
||||
assert payload.name == "Valid Copy Name"
|
||||
|
||||
def test_copy_app_none_name(self):
|
||||
"""Test CopyAppPayload with None name (should be allowed)."""
|
||||
payload = CopyAppPayload(name=None)
|
||||
assert payload.name is None
|
||||
|
||||
def test_edge_case_angle_brackets_content(self):
|
||||
"""Test that angle brackets with actual content are rejected."""
|
||||
# Angle brackets without valid HTML-like patterns should be checked
|
||||
# The regex pattern <.*?on\w+\s*= should catch event handlers
|
||||
# But let's verify other patterns too
|
||||
|
||||
# Valid: angle brackets used as symbols (not matched by our patterns)
|
||||
# Our patterns specifically look for dangerous constructs
|
||||
|
||||
# Invalid: actual HTML tags with event handlers
|
||||
invalid_names = [
|
||||
"<div onclick=xss>",
|
||||
"<img src=x onerror=alert(1)>",
|
||||
]
|
||||
|
||||
for name in invalid_names:
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
CreateAppPayload(name=name, mode="chat")
|
||||
assert "invalid characters or patterns" in str(exc_info.value).lower()
|
||||
@@ -0,0 +1,430 @@
|
||||
"""
|
||||
Unit tests for the dataset document download endpoint.
|
||||
|
||||
These tests validate that the controller returns a signed download URL for
|
||||
upload-file documents, and rejects unsupported or missing file cases.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib
|
||||
import sys
|
||||
from collections import UserDict
|
||||
from io import BytesIO
|
||||
from types import SimpleNamespace
|
||||
from typing import Any
|
||||
from zipfile import ZipFile
|
||||
|
||||
import pytest
|
||||
from flask import Flask
|
||||
from werkzeug.exceptions import Forbidden, NotFound
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def app() -> Flask:
|
||||
"""Create a minimal Flask app for request-context based controller tests."""
|
||||
app = Flask(__name__)
|
||||
app.config["TESTING"] = True
|
||||
return app
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def datasets_document_module(monkeypatch: pytest.MonkeyPatch):
|
||||
"""
|
||||
Reload `controllers.console.datasets.datasets_document` with lightweight decorators.
|
||||
|
||||
We patch auth / setup / rate-limit decorators to no-ops so we can unit test the
|
||||
controller logic without requiring the full console stack.
|
||||
"""
|
||||
|
||||
from controllers.console import console_ns, wraps
|
||||
from libs import login
|
||||
|
||||
def _noop(func): # type: ignore[no-untyped-def]
|
||||
return func
|
||||
|
||||
# Bypass login/setup/account checks in unit tests.
|
||||
monkeypatch.setattr(login, "login_required", _noop)
|
||||
monkeypatch.setattr(wraps, "setup_required", _noop)
|
||||
monkeypatch.setattr(wraps, "account_initialization_required", _noop)
|
||||
|
||||
# Bypass billing-related decorators used by other endpoints in this module.
|
||||
monkeypatch.setattr(wraps, "cloud_edition_billing_resource_check", lambda *_args, **_kwargs: (lambda f: f))
|
||||
monkeypatch.setattr(wraps, "cloud_edition_billing_rate_limit_check", lambda *_args, **_kwargs: (lambda f: f))
|
||||
|
||||
# Avoid Flask-RESTX route registration side effects during import.
|
||||
def _noop_route(*_args, **_kwargs): # type: ignore[override]
|
||||
def _decorator(cls):
|
||||
return cls
|
||||
|
||||
return _decorator
|
||||
|
||||
monkeypatch.setattr(console_ns, "route", _noop_route)
|
||||
|
||||
module_name = "controllers.console.datasets.datasets_document"
|
||||
sys.modules.pop(module_name, None)
|
||||
return importlib.import_module(module_name)
|
||||
|
||||
|
||||
def _mock_user(*, is_dataset_editor: bool = True) -> SimpleNamespace:
|
||||
"""Build a minimal user object compatible with dataset permission checks."""
|
||||
return SimpleNamespace(is_dataset_editor=is_dataset_editor, id="user-123")
|
||||
|
||||
|
||||
def _mock_document(
|
||||
*,
|
||||
document_id: str,
|
||||
tenant_id: str,
|
||||
data_source_type: str,
|
||||
upload_file_id: str | None,
|
||||
) -> SimpleNamespace:
|
||||
"""Build a minimal document object used by the controller."""
|
||||
data_source_info_dict: dict[str, Any] | None = None
|
||||
if upload_file_id is not None:
|
||||
data_source_info_dict = {"upload_file_id": upload_file_id}
|
||||
else:
|
||||
data_source_info_dict = {}
|
||||
|
||||
return SimpleNamespace(
|
||||
id=document_id,
|
||||
tenant_id=tenant_id,
|
||||
data_source_type=data_source_type,
|
||||
data_source_info_dict=data_source_info_dict,
|
||||
)
|
||||
|
||||
|
||||
def _wire_common_success_mocks(
|
||||
*,
|
||||
module,
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
current_tenant_id: str,
|
||||
document_tenant_id: str,
|
||||
data_source_type: str,
|
||||
upload_file_id: str | None,
|
||||
upload_file_exists: bool,
|
||||
signed_url: str,
|
||||
) -> None:
|
||||
"""Patch controller dependencies to create a deterministic test environment."""
|
||||
import services.dataset_service as dataset_service_module
|
||||
|
||||
# Make `current_account_with_tenant()` return a known user + tenant id.
|
||||
monkeypatch.setattr(module, "current_account_with_tenant", lambda: (_mock_user(), current_tenant_id))
|
||||
|
||||
# Return a dataset object and allow permission checks to pass.
|
||||
monkeypatch.setattr(module.DatasetService, "get_dataset", lambda _dataset_id: SimpleNamespace(id="ds-1"))
|
||||
monkeypatch.setattr(module.DatasetService, "check_dataset_permission", lambda *_args, **_kwargs: None)
|
||||
|
||||
# Return a document that will be validated inside DocumentResource.get_document.
|
||||
document = _mock_document(
|
||||
document_id="doc-1",
|
||||
tenant_id=document_tenant_id,
|
||||
data_source_type=data_source_type,
|
||||
upload_file_id=upload_file_id,
|
||||
)
|
||||
monkeypatch.setattr(module.DocumentService, "get_document", lambda *_args, **_kwargs: document)
|
||||
|
||||
# Mock UploadFile lookup via FileService batch helper.
|
||||
upload_files_by_id: dict[str, Any] = {}
|
||||
if upload_file_exists and upload_file_id is not None:
|
||||
upload_files_by_id[str(upload_file_id)] = SimpleNamespace(id=str(upload_file_id))
|
||||
monkeypatch.setattr(module.FileService, "get_upload_files_by_ids", lambda *_args, **_kwargs: upload_files_by_id)
|
||||
|
||||
# Mock signing helper so the returned URL is deterministic.
|
||||
monkeypatch.setattr(dataset_service_module.file_helpers, "get_signed_file_url", lambda **_kwargs: signed_url)
|
||||
|
||||
|
||||
def _mock_send_file(obj, **kwargs): # type: ignore[no-untyped-def]
|
||||
"""Return a lightweight representation of `send_file(...)` for unit tests."""
|
||||
|
||||
class _ResponseMock(UserDict):
|
||||
def __init__(self, sent_file: object, send_file_kwargs: dict[str, object]) -> None:
|
||||
super().__init__({"_sent_file": sent_file, "_send_file_kwargs": send_file_kwargs})
|
||||
self._on_close: object | None = None
|
||||
|
||||
def call_on_close(self, func): # type: ignore[no-untyped-def]
|
||||
self._on_close = func
|
||||
return func
|
||||
|
||||
return _ResponseMock(obj, kwargs)
|
||||
|
||||
|
||||
def test_batch_download_zip_returns_send_file(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure batch ZIP download returns a zip attachment via `send_file`."""
|
||||
|
||||
# Arrange common permission mocks.
|
||||
monkeypatch.setattr(datasets_document_module, "current_account_with_tenant", lambda: (_mock_user(), "tenant-123"))
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "get_dataset", lambda _dataset_id: SimpleNamespace(id="ds-1")
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "check_dataset_permission", lambda *_args, **_kwargs: None
|
||||
)
|
||||
|
||||
# Two upload-file documents, each referencing an UploadFile.
|
||||
doc1 = _mock_document(
|
||||
document_id="11111111-1111-1111-1111-111111111111",
|
||||
tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-1",
|
||||
)
|
||||
doc2 = _mock_document(
|
||||
document_id="22222222-2222-2222-2222-222222222222",
|
||||
tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-2",
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DocumentService,
|
||||
"get_documents_by_ids",
|
||||
lambda *_args, **_kwargs: [doc1, doc2],
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.FileService,
|
||||
"get_upload_files_by_ids",
|
||||
lambda *_args, **_kwargs: {
|
||||
"file-1": SimpleNamespace(id="file-1", name="a.txt", key="k1"),
|
||||
"file-2": SimpleNamespace(id="file-2", name="b.txt", key="k2"),
|
||||
},
|
||||
)
|
||||
|
||||
# Mock storage streaming content.
|
||||
import services.file_service as file_service_module
|
||||
|
||||
monkeypatch.setattr(file_service_module.storage, "load", lambda _key, stream=True: [b"hello"])
|
||||
|
||||
# Replace send_file used by the controller to avoid a real Flask response object.
|
||||
monkeypatch.setattr(datasets_document_module, "send_file", _mock_send_file)
|
||||
|
||||
# Act
|
||||
with app.test_request_context(
|
||||
"/datasets/ds-1/documents/download-zip",
|
||||
method="POST",
|
||||
json={"document_ids": ["11111111-1111-1111-1111-111111111111", "22222222-2222-2222-2222-222222222222"]},
|
||||
):
|
||||
api = datasets_document_module.DocumentBatchDownloadZipApi()
|
||||
result = api.post(dataset_id="ds-1")
|
||||
|
||||
# Assert: we returned via send_file with correct mime type and attachment.
|
||||
assert result["_send_file_kwargs"]["mimetype"] == "application/zip"
|
||||
assert result["_send_file_kwargs"]["as_attachment"] is True
|
||||
assert isinstance(result["_send_file_kwargs"]["download_name"], str)
|
||||
assert result["_send_file_kwargs"]["download_name"].endswith(".zip")
|
||||
# Ensure our cleanup hook is registered and execute it to avoid temp file leaks in unit tests.
|
||||
assert getattr(result, "_on_close", None) is not None
|
||||
result._on_close() # type: ignore[attr-defined]
|
||||
|
||||
|
||||
def test_batch_download_zip_response_is_openable_zip(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure the real Flask `send_file` response body is a valid ZIP that can be opened."""
|
||||
|
||||
# Arrange: same controller mocks as the lightweight send_file test, but we keep the real `send_file`.
|
||||
monkeypatch.setattr(datasets_document_module, "current_account_with_tenant", lambda: (_mock_user(), "tenant-123"))
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "get_dataset", lambda _dataset_id: SimpleNamespace(id="ds-1")
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "check_dataset_permission", lambda *_args, **_kwargs: None
|
||||
)
|
||||
|
||||
doc1 = _mock_document(
|
||||
document_id="33333333-3333-3333-3333-333333333333",
|
||||
tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-1",
|
||||
)
|
||||
doc2 = _mock_document(
|
||||
document_id="44444444-4444-4444-4444-444444444444",
|
||||
tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-2",
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DocumentService,
|
||||
"get_documents_by_ids",
|
||||
lambda *_args, **_kwargs: [doc1, doc2],
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.FileService,
|
||||
"get_upload_files_by_ids",
|
||||
lambda *_args, **_kwargs: {
|
||||
"file-1": SimpleNamespace(id="file-1", name="a.txt", key="k1"),
|
||||
"file-2": SimpleNamespace(id="file-2", name="b.txt", key="k2"),
|
||||
},
|
||||
)
|
||||
|
||||
# Stream distinct bytes per key so we can verify both ZIP entries.
|
||||
import services.file_service as file_service_module
|
||||
|
||||
monkeypatch.setattr(
|
||||
file_service_module.storage, "load", lambda key, stream=True: [b"one"] if key == "k1" else [b"two"]
|
||||
)
|
||||
|
||||
# Act
|
||||
with app.test_request_context(
|
||||
"/datasets/ds-1/documents/download-zip",
|
||||
method="POST",
|
||||
json={"document_ids": ["33333333-3333-3333-3333-333333333333", "44444444-4444-4444-4444-444444444444"]},
|
||||
):
|
||||
api = datasets_document_module.DocumentBatchDownloadZipApi()
|
||||
response = api.post(dataset_id="ds-1")
|
||||
|
||||
# Assert: response body is a valid ZIP and contains the expected entries.
|
||||
response.direct_passthrough = False
|
||||
data = response.get_data()
|
||||
response.close()
|
||||
|
||||
with ZipFile(BytesIO(data), mode="r") as zf:
|
||||
assert zf.namelist() == ["a.txt", "b.txt"]
|
||||
assert zf.read("a.txt") == b"one"
|
||||
assert zf.read("b.txt") == b"two"
|
||||
|
||||
|
||||
def test_batch_download_zip_rejects_non_upload_file_document(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure batch ZIP download rejects non upload-file documents."""
|
||||
|
||||
monkeypatch.setattr(datasets_document_module, "current_account_with_tenant", lambda: (_mock_user(), "tenant-123"))
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "get_dataset", lambda _dataset_id: SimpleNamespace(id="ds-1")
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DatasetService, "check_dataset_permission", lambda *_args, **_kwargs: None
|
||||
)
|
||||
|
||||
doc = _mock_document(
|
||||
document_id="55555555-5555-5555-5555-555555555555",
|
||||
tenant_id="tenant-123",
|
||||
data_source_type="website_crawl",
|
||||
upload_file_id="file-1",
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
datasets_document_module.DocumentService,
|
||||
"get_documents_by_ids",
|
||||
lambda *_args, **_kwargs: [doc],
|
||||
)
|
||||
|
||||
with app.test_request_context(
|
||||
"/datasets/ds-1/documents/download-zip",
|
||||
method="POST",
|
||||
json={"document_ids": ["55555555-5555-5555-5555-555555555555"]},
|
||||
):
|
||||
api = datasets_document_module.DocumentBatchDownloadZipApi()
|
||||
with pytest.raises(NotFound):
|
||||
api.post(dataset_id="ds-1")
|
||||
|
||||
|
||||
def test_document_download_returns_url_for_upload_file_document(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure upload-file documents return a `{url}` JSON payload."""
|
||||
|
||||
_wire_common_success_mocks(
|
||||
module=datasets_document_module,
|
||||
monkeypatch=monkeypatch,
|
||||
current_tenant_id="tenant-123",
|
||||
document_tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-123",
|
||||
upload_file_exists=True,
|
||||
signed_url="https://example.com/signed",
|
||||
)
|
||||
|
||||
# Build a request context then call the resource method directly.
|
||||
with app.test_request_context("/datasets/ds-1/documents/doc-1/download", method="GET"):
|
||||
api = datasets_document_module.DocumentDownloadApi()
|
||||
result = api.get(dataset_id="ds-1", document_id="doc-1")
|
||||
|
||||
assert result == {"url": "https://example.com/signed"}
|
||||
|
||||
|
||||
def test_document_download_rejects_non_upload_file_document(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure non-upload documents raise 404 (no file to download)."""
|
||||
|
||||
_wire_common_success_mocks(
|
||||
module=datasets_document_module,
|
||||
monkeypatch=monkeypatch,
|
||||
current_tenant_id="tenant-123",
|
||||
document_tenant_id="tenant-123",
|
||||
data_source_type="website_crawl",
|
||||
upload_file_id="file-123",
|
||||
upload_file_exists=True,
|
||||
signed_url="https://example.com/signed",
|
||||
)
|
||||
|
||||
with app.test_request_context("/datasets/ds-1/documents/doc-1/download", method="GET"):
|
||||
api = datasets_document_module.DocumentDownloadApi()
|
||||
with pytest.raises(NotFound):
|
||||
api.get(dataset_id="ds-1", document_id="doc-1")
|
||||
|
||||
|
||||
def test_document_download_rejects_missing_upload_file_id(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure missing `upload_file_id` raises 404."""
|
||||
|
||||
_wire_common_success_mocks(
|
||||
module=datasets_document_module,
|
||||
monkeypatch=monkeypatch,
|
||||
current_tenant_id="tenant-123",
|
||||
document_tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id=None,
|
||||
upload_file_exists=False,
|
||||
signed_url="https://example.com/signed",
|
||||
)
|
||||
|
||||
with app.test_request_context("/datasets/ds-1/documents/doc-1/download", method="GET"):
|
||||
api = datasets_document_module.DocumentDownloadApi()
|
||||
with pytest.raises(NotFound):
|
||||
api.get(dataset_id="ds-1", document_id="doc-1")
|
||||
|
||||
|
||||
def test_document_download_rejects_when_upload_file_record_missing(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure missing UploadFile row raises 404."""
|
||||
|
||||
_wire_common_success_mocks(
|
||||
module=datasets_document_module,
|
||||
monkeypatch=monkeypatch,
|
||||
current_tenant_id="tenant-123",
|
||||
document_tenant_id="tenant-123",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-123",
|
||||
upload_file_exists=False,
|
||||
signed_url="https://example.com/signed",
|
||||
)
|
||||
|
||||
with app.test_request_context("/datasets/ds-1/documents/doc-1/download", method="GET"):
|
||||
api = datasets_document_module.DocumentDownloadApi()
|
||||
with pytest.raises(NotFound):
|
||||
api.get(dataset_id="ds-1", document_id="doc-1")
|
||||
|
||||
|
||||
def test_document_download_rejects_tenant_mismatch(
|
||||
app: Flask, datasets_document_module, monkeypatch: pytest.MonkeyPatch
|
||||
) -> None:
|
||||
"""Ensure tenant mismatch is rejected by the shared `get_document()` permission check."""
|
||||
|
||||
_wire_common_success_mocks(
|
||||
module=datasets_document_module,
|
||||
monkeypatch=monkeypatch,
|
||||
current_tenant_id="tenant-123",
|
||||
document_tenant_id="tenant-999",
|
||||
data_source_type="upload_file",
|
||||
upload_file_id="file-123",
|
||||
upload_file_exists=True,
|
||||
signed_url="https://example.com/signed",
|
||||
)
|
||||
|
||||
with app.test_request_context("/datasets/ds-1/documents/doc-1/download", method="GET"):
|
||||
api = datasets_document_module.DocumentDownloadApi()
|
||||
with pytest.raises(Forbidden):
|
||||
api.get(dataset_id="ds-1", document_id="doc-1")
|
||||
@@ -346,6 +346,7 @@ class TestPluginRuntimeErrorHandling:
|
||||
mock_response.status_code = 200
|
||||
invoke_error = {
|
||||
"error_type": "InvokeRateLimitError",
|
||||
"message": "Rate limit exceeded",
|
||||
"args": {"description": "Rate limit exceeded"},
|
||||
}
|
||||
error_message = json.dumps({"error_type": "PluginInvokeError", "message": json.dumps(invoke_error)})
|
||||
@@ -364,6 +365,7 @@ class TestPluginRuntimeErrorHandling:
|
||||
mock_response.status_code = 200
|
||||
invoke_error = {
|
||||
"error_type": "InvokeAuthorizationError",
|
||||
"message": "Invalid credentials",
|
||||
"args": {"description": "Invalid credentials"},
|
||||
}
|
||||
error_message = json.dumps({"error_type": "PluginInvokeError", "message": json.dumps(invoke_error)})
|
||||
@@ -382,6 +384,7 @@ class TestPluginRuntimeErrorHandling:
|
||||
mock_response.status_code = 200
|
||||
invoke_error = {
|
||||
"error_type": "InvokeBadRequestError",
|
||||
"message": "Invalid parameters",
|
||||
"args": {"description": "Invalid parameters"},
|
||||
}
|
||||
error_message = json.dumps({"error_type": "PluginInvokeError", "message": json.dumps(invoke_error)})
|
||||
@@ -400,6 +403,7 @@ class TestPluginRuntimeErrorHandling:
|
||||
mock_response.status_code = 200
|
||||
invoke_error = {
|
||||
"error_type": "InvokeConnectionError",
|
||||
"message": "Connection to external service failed",
|
||||
"args": {"description": "Connection to external service failed"},
|
||||
}
|
||||
error_message = json.dumps({"error_type": "PluginInvokeError", "message": json.dumps(invoke_error)})
|
||||
@@ -418,6 +422,7 @@ class TestPluginRuntimeErrorHandling:
|
||||
mock_response.status_code = 200
|
||||
invoke_error = {
|
||||
"error_type": "InvokeServerUnavailableError",
|
||||
"message": "Service temporarily unavailable",
|
||||
"args": {"description": "Service temporarily unavailable"},
|
||||
}
|
||||
error_message = json.dumps({"error_type": "PluginInvokeError", "message": json.dumps(invoke_error)})
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user