Merge branch 'main' into feat/grouping-branching

# Conflicts:
#	web/package.json

.agents/skills/orpc-contract-first/SKILL.md

@@ -1,46 +0,0 @@
----
-name: orpc-contract-first
-description: Guide for implementing oRPC contract-first API patterns in Dify frontend. Triggers when creating new API contracts, adding service endpoints, integrating TanStack Query with typed contracts, or migrating legacy service calls to oRPC. Use for all API layer work in web/contract and web/service directories.
----
-
-# oRPC Contract-First Development
-
-## Project Structure
-
-```
-web/contract/
-├── base.ts           # Base contract (inputStructure: 'detailed')
-├── router.ts         # Router composition & type exports
-├── marketplace.ts    # Marketplace contracts
-└── console/          # Console contracts by domain
-    ├── system.ts
-    └── billing.ts
-```
-
-## Workflow
-
-1. **Create contract** in `web/contract/console/{domain}.ts`
-   - Import `base` from `../base` and `type` from `@orpc/contract`
-   - Define route with `path`, `method`, `input`, `output`
-
-2. **Register in router** at `web/contract/router.ts`
-   - Import directly from domain file (no barrel files)
-   - Nest by API prefix: `billing: { invoices, bindPartnerStack }`
-
-3. **Create hooks** in `web/service/use-{domain}.ts`
-   - Use `consoleQuery.{group}.{contract}.queryKey()` for query keys
-   - Use `consoleClient.{group}.{contract}()` for API calls
-
-## Key Rules
-
-- **Input structure**: Always use `{ params, query?, body? }` format
-- **Path params**: Use `{paramName}` in path, match in `params` object
-- **Router nesting**: Group by API prefix (e.g., `/billing/*` → `billing: {}`)
-- **No barrel files**: Import directly from specific files
-- **Types**: Import from `@/types/`, use `type<T>()` helper
-
-## Type Export
-
-```typescript
-export type ConsoleInputs = InferContractRouterInputs<typeof consoleRouterContract>
-```

.claude/settings.json

@@ -1,15 +1,9 @@
 {
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "npx -y block-no-verify@1.1.1"
-          }
-        ]
-      }
-    ]
+  "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
   }
 }

.claude/skills/component-refactoring

@@ -1 +0,0 @@
-../../.agents/skills/component-refactoring

.claude/skills/frontend-code-review

@@ -1 +0,0 @@
-../../.agents/skills/frontend-code-review

.claude/skills/frontend-testing

@@ -1 +0,0 @@
-../../.agents/skills/frontend-testing

.claude/skills/frontend-testing/SKILL.md

@@ -83,9 +83,6 @@ 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
 
@@ -299,7 +296,7 @@ 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, Zustand store testing, and best practices
+- `references/mocking.md` - Mock patterns 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

.claude/skills/frontend-testing/references/mocking.md

@@ -37,36 +37,16 @@ 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 (`react-i18next`, `next/image`, `zustand`) |
-| `web/__mocks__/zustand.ts` | Zustand mock implementation (auto-resets stores after each test) |
+| `web/vitest.setup.ts` | Global mocks shared by all tests (for example `react-i18next`, `next/image`) |
 | `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)
@@ -296,7 +276,6 @@ 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
@@ -306,7 +285,6 @@ 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
@@ -330,151 +308,10 @@ 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

.claude/skills/orpc-contract-first

@@ -1 +0,0 @@
-../../.agents/skills/orpc-contract-first

.claude/skills/skill-creator/SKILL.md

@@ -0,0 +1,355 @@
+---
+name: skill-creator
+description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
+---
+
+# Skill Creator
+
+This skill provides guidance for creating effective skills.
+
+## About Skills
+
+Skills are modular, self-contained packages that extend Claude's capabilities by providing
+specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
+domains or tasks—they transform Claude from a general-purpose agent into a specialized agent
+equipped with procedural knowledge that no model can fully possess.
+
+### What Skills Provide
+
+1. Specialized workflows - Multi-step procedures for specific domains
+2. Tool integrations - Instructions for working with specific file formats or APIs
+3. Domain expertise - Company-specific knowledge, schemas, business logic
+4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
+
+## Core Principles
+
+### Concise is Key
+
+The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
+
+**Default assumption: Claude is already very smart.** Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"
+
+Prefer concise examples over verbose explanations.
+
+### Set Appropriate Degrees of Freedom
+
+Match the level of specificity to the task's fragility and variability:
+
+**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
+
+**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
+
+**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
+
+Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
+
+### Anatomy of a Skill
+
+Every skill consists of a required SKILL.md file and optional bundled resources:
+
+```
+skill-name/
+├── SKILL.md (required)
+│   ├── YAML frontmatter metadata (required)
+│   │   ├── name: (required)
+│   │   └── description: (required)
+│   └── Markdown instructions (required)
+└── Bundled Resources (optional)
+    ├── scripts/          - Executable code (Python/Bash/etc.)
+    ├── references/       - Documentation intended to be loaded into context as needed
+    └── assets/           - Files used in output (templates, icons, fonts, etc.)
+```
+
+#### SKILL.md (required)
+
+Every SKILL.md consists of:
+
+- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
+- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).
+
+#### Bundled Resources (optional)
+
+##### Scripts (`scripts/`)
+
+Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
+
+- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed
+- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks
+- **Benefits**: Token efficient, deterministic, may be executed without loading into context
+- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments
+
+##### References (`references/`)
+
+Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
+
+- **When to include**: For documentation that Claude should reference while working
+- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications
+- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
+- **Benefits**: Keeps SKILL.md lean, loaded only when Claude determines it's needed
+- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md
+- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.
+
+##### Assets (`assets/`)
+
+Files not intended to be loaded into context, but rather used within the output Claude produces.
+
+- **When to include**: When the skill needs files that will be used in the final output
+- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography
+- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
+- **Benefits**: Separates output resources from documentation, enables Claude to use files without loading them into context
+
+#### What to Not Include in a Skill
+
+A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
+
+- README.md
+- INSTALLATION_GUIDE.md
+- QUICK_REFERENCE.md
+- CHANGELOG.md
+- etc.
+
+The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
+
+### Progressive Disclosure Design Principle
+
+Skills use a three-level loading system to manage context efficiently:
+
+1. **Metadata (name + description)** - Always in context (~100 words)
+2. **SKILL.md body** - When skill triggers (<5k words)
+3. **Bundled resources** - As needed by Claude (Unlimited because scripts can be executed without reading into context window)
+
+#### Progressive Disclosure Patterns
+
+Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.
+
+**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.
+
+**Pattern 1: High-level guide with references**
+
+```markdown
+# PDF Processing
+
+## Quick start
+
+Extract text with pdfplumber:
+[code example]
+
+## Advanced features
+
+- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
+- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
+- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns
+```
+
+Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.
+
+**Pattern 2: Domain-specific organization**
+
+For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:
+
+```
+bigquery-skill/
+├── SKILL.md (overview and navigation)
+└── reference/
+    ├── finance.md (revenue, billing metrics)
+    ├── sales.md (opportunities, pipeline)
+    ├── product.md (API usage, features)
+    └── marketing.md (campaigns, attribution)
+```
+
+When a user asks about sales metrics, Claude only reads sales.md.
+
+Similarly, for skills supporting multiple frameworks or variants, organize by variant:
+
+```
+cloud-deploy/
+├── SKILL.md (workflow + provider selection)
+└── references/
+    ├── aws.md (AWS deployment patterns)
+    ├── gcp.md (GCP deployment patterns)
+    └── azure.md (Azure deployment patterns)
+```
+
+When the user chooses AWS, Claude only reads aws.md.
+
+**Pattern 3: Conditional details**
+
+Show basic content, link to advanced content:
+
+```markdown
+# DOCX Processing
+
+## Creating documents
+
+Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).
+
+## Editing documents
+
+For simple edits, modify the XML directly.
+
+**For tracked changes**: See [REDLINING.md](REDLINING.md)
+**For OOXML details**: See [OOXML.md](OOXML.md)
+```
+
+Claude reads REDLINING.md or OOXML.md only when the user needs those features.
+
+**Important guidelines:**
+
+- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
+- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing.
+
+## Skill Creation Process
+
+Skill creation involves these steps:
+
+1. Understand the skill with concrete examples
+2. Plan reusable skill contents (scripts, references, assets)
+3. Initialize the skill (run init_skill.py)
+4. Edit the skill (implement resources and write SKILL.md)
+5. Package the skill (run package_skill.py)
+6. Iterate based on real usage
+
+Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
+
+### Step 1: Understanding the Skill with Concrete Examples
+
+Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
+
+To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
+
+For example, when building an image-editor skill, relevant questions include:
+
+- "What functionality should the image-editor skill support? Editing, rotating, anything else?"
+- "Can you give some examples of how this skill would be used?"
+- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
+- "What would a user say that should trigger this skill?"
+
+To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
+
+Conclude this step when there is a clear sense of the functionality the skill should support.
+
+### Step 2: Planning the Reusable Skill Contents
+
+To turn concrete examples into an effective skill, analyze each example by:
+
+1. Considering how to execute on the example from scratch
+2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly
+
+Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows:
+
+1. Rotating a PDF requires re-writing the same code each time
+2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill
+
+Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
+
+1. Writing a frontend webapp requires the same boilerplate HTML/React each time
+2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill
+
+Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows:
+
+1. Querying BigQuery requires re-discovering the table schemas and relationships each time
+2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill
+
+To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
+
+### Step 3: Initializing the Skill
+
+At this point, it is time to actually create the skill.
+
+Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
+
+When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
+
+Usage:
+
+```bash
+scripts/init_skill.py <skill-name> --path <output-directory>
+```
+
+The script:
+
+- Creates the skill directory at the specified path
+- Generates a SKILL.md template with proper frontmatter and TODO placeholders
+- Creates example resource directories: `scripts/`, `references/`, and `assets/`
+- Adds example files in each directory that can be customized or deleted
+
+After initialization, customize or remove the generated SKILL.md and example files as needed.
+
+### Step 4: Edit the Skill
+
+When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
+
+#### Learn Proven Design Patterns
+
+Consult these helpful guides based on your skill's needs:
+
+- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic
+- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns
+
+These files contain established best practices for effective skill design.
+
+#### Start with Reusable Skill Contents
+
+To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.
+
+Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
+
+Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.
+
+#### Update SKILL.md
+
+**Writing Guidelines:** Always use imperative/infinitive form.
+
+##### Frontmatter
+
+Write the YAML frontmatter with `name` and `description`:
+
+- `name`: The skill name
+- `description`: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.
+  - Include both what the Skill does and specific triggers/contexts for when to use it.
+  - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Claude.
+  - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
+
+Do not include any other fields in YAML frontmatter.
+
+##### Body
+
+Write instructions for using the skill and its bundled resources.
+
+### Step 5: Packaging a Skill
+
+Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:
+
+```bash
+scripts/package_skill.py <path/to/skill-folder>
+```
+
+Optional output directory specification:
+
+```bash
+scripts/package_skill.py <path/to/skill-folder> ./dist
+```
+
+The packaging script will:
+
+1. **Validate** the skill automatically, checking:
+
+   - YAML frontmatter format and required fields
+   - Skill naming conventions and directory structure
+   - Description completeness and quality
+   - File organization and resource references
+
+2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
+
+If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
+
+### Step 6: Iterate
+
+After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
+
+**Iteration workflow:**
+
+1. Use the skill on real tasks
+2. Notice struggles or inefficiencies
+3. Identify how SKILL.md or bundled resources should be updated
+4. Implement changes and test again

.claude/skills/skill-creator/references/output-patterns.md

@@ -0,0 +1,86 @@
+# Output Patterns
+
+Use these patterns when skills need to produce consistent, high-quality output.
+
+## Template Pattern
+
+Provide templates for output format. Match the level of strictness to your needs.
+
+**For strict requirements (like API responses or data formats):**
+
+```markdown
+## Report structure
+
+ALWAYS use this exact template structure:
+
+# [Analysis Title]
+
+## Executive summary
+[One-paragraph overview of key findings]
+
+## Key findings
+- Finding 1 with supporting data
+- Finding 2 with supporting data
+- Finding 3 with supporting data
+
+## Recommendations
+1. Specific actionable recommendation
+2. Specific actionable recommendation
+```
+
+**For flexible guidance (when adaptation is useful):**
+
+```markdown
+## Report structure
+
+Here is a sensible default format, but use your best judgment:
+
+# [Analysis Title]
+
+## Executive summary
+[Overview]
+
+## Key findings
+[Adapt sections based on what you discover]
+
+## Recommendations
+[Tailor to the specific context]
+
+Adjust sections as needed for the specific analysis type.
+```
+
+## Examples Pattern
+
+For skills where output quality depends on seeing examples, provide input/output pairs:
+
+```markdown
+## Commit message format
+
+Generate commit messages following these examples:
+
+**Example 1:**
+Input: Added user authentication with JWT tokens
+Output:
+```
+
+feat(auth): implement JWT-based authentication
+
+Add login endpoint and token validation middleware
+
+```
+
+**Example 2:**
+Input: Fixed bug where dates displayed incorrectly in reports
+Output:
+```
+
+fix(reports): correct date formatting in timezone conversion
+
+Use UTC timestamps consistently across report generation
+
+```
+
+Follow this style: type(scope): brief description, then detailed explanation.
+```
+
+Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.

.claude/skills/skill-creator/references/workflows.md

@@ -0,0 +1,28 @@
+# Workflow Patterns
+
+## Sequential Workflows
+
+For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md:
+
+```markdown
+Filling a PDF form involves these steps:
+
+1. Analyze the form (run analyze_form.py)
+2. Create field mapping (edit fields.json)
+3. Validate mapping (run validate_fields.py)
+4. Fill the form (run fill_form.py)
+5. Verify output (run verify_output.py)
+```
+
+## Conditional Workflows
+
+For tasks with branching logic, guide Claude through decision points:
+
+```markdown
+1. Determine the modification type:
+   **Creating new content?** → Follow "Creation workflow" below
+   **Editing existing content?** → Follow "Editing workflow" below
+
+2. Creation workflow: [steps]
+3. Editing workflow: [steps]
+```

.claude/skills/skill-creator/scripts/init_skill.py

@@ -0,0 +1,300 @@
+#!/usr/bin/env python3
+"""
+Skill Initializer - Creates a new skill from template
+
+Usage:
+    init_skill.py <skill-name> --path <path>
+
+Examples:
+    init_skill.py my-new-skill --path skills/public
+    init_skill.py my-api-helper --path skills/private
+    init_skill.py custom-skill --path /custom/location
+"""
+
+import sys
+from pathlib import Path
+
+
+SKILL_TEMPLATE = """---
+name: {skill_name}
+description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
+---
+
+# {skill_title}
+
+## Overview
+
+[TODO: 1-2 sentences explaining what this skill enables]
+
+## Structuring This Skill
+
+[TODO: Choose the structure that best fits this skill's purpose. Common patterns:
+
+**1. Workflow-Based** (best for sequential processes)
+- Works well when there are clear step-by-step procedures
+- Example: DOCX skill with "Workflow Decision Tree" → "Reading" → "Creating" → "Editing"
+- Structure: ## Overview → ## Workflow Decision Tree → ## Step 1 → ## Step 2...
+
+**2. Task-Based** (best for tool collections)
+- Works well when the skill offers different operations/capabilities
+- Example: PDF skill with "Quick Start" → "Merge PDFs" → "Split PDFs" → "Extract Text"
+- Structure: ## Overview → ## Quick Start → ## Task Category 1 → ## Task Category 2...
+
+**3. Reference/Guidelines** (best for standards or specifications)
+- Works well for brand guidelines, coding standards, or requirements
+- Example: Brand styling with "Brand Guidelines" → "Colors" → "Typography" → "Features"
+- Structure: ## Overview → ## Guidelines → ## Specifications → ## Usage...
+
+**4. Capabilities-Based** (best for integrated systems)
+- Works well when the skill provides multiple interrelated features
+- Example: Product Management with "Core Capabilities" → numbered capability list
+- Structure: ## Overview → ## Core Capabilities → ### 1. Feature → ### 2. Feature...
+
+Patterns can be mixed and matched as needed. Most skills combine patterns (e.g., start with task-based, add workflow for complex operations).
+
+Delete this entire "Structuring This Skill" section when done - it's just guidance.]
+
+## [TODO: Replace with the first main section based on chosen structure]
+
+[TODO: Add content here. See examples in existing skills:
+- Code samples for technical skills
+- Decision trees for complex workflows
+- Concrete examples with realistic user requests
+- References to scripts/templates/references as needed]
+
+## Resources
+
+This skill includes example resource directories that demonstrate how to organize different types of bundled resources:
+
+### scripts/
+Executable code (Python/Bash/etc.) that can be run directly to perform specific operations.
+
+**Examples from other skills:**
+- PDF skill: `fill_fillable_fields.py`, `extract_form_field_info.py` - utilities for PDF manipulation
+- DOCX skill: `document.py`, `utilities.py` - Python modules for document processing
+
+**Appropriate for:** Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations.
+
+**Note:** Scripts may be executed without loading into context, but can still be read by Claude for patching or environment adjustments.
+
+### references/
+Documentation and reference material intended to be loaded into context to inform Claude's process and thinking.
+
+**Examples from other skills:**
+- Product management: `communication.md`, `context_building.md` - detailed workflow guides
+- BigQuery: API reference documentation and query examples
+- Finance: Schema documentation, company policies
+
+**Appropriate for:** In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Claude should reference while working.
+
+### assets/
+Files not intended to be loaded into context, but rather used within the output Claude produces.
+
+**Examples from other skills:**
+- Brand styling: PowerPoint template files (.pptx), logo files
+- Frontend builder: HTML/React boilerplate project directories
+- Typography: Font files (.ttf, .woff2)
+
+**Appropriate for:** Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output.
+
+---
+
+**Any unneeded directories can be deleted.** Not every skill requires all three types of resources.
+"""
+
+EXAMPLE_SCRIPT = '''#!/usr/bin/env python3
+"""
+Example helper script for {skill_name}
+
+This is a placeholder script that can be executed directly.
+Replace with actual implementation or delete if not needed.
+
+Example real scripts from other skills:
+- pdf/scripts/fill_fillable_fields.py - Fills PDF form fields
+- pdf/scripts/convert_pdf_to_images.py - Converts PDF pages to images
+"""
+
+def main():
+    print("This is an example script for {skill_name}")
+    # TODO: Add actual script logic here
+    # This could be data processing, file conversion, API calls, etc.
+
+if __name__ == "__main__":
+    main()
+'''
+
+EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title}
+
+This is a placeholder for detailed reference documentation.
+Replace with actual reference content or delete if not needed.
+
+Example real reference docs from other skills:
+- product-management/references/communication.md - Comprehensive guide for status updates
+- product-management/references/context_building.md - Deep-dive on gathering context
+- bigquery/references/ - API references and query examples
+
+## When Reference Docs Are Useful
+
+Reference docs are ideal for:
+- Comprehensive API documentation
+- Detailed workflow guides
+- Complex multi-step processes
+- Information too lengthy for main SKILL.md
+- Content that's only needed for specific use cases
+
+## Structure Suggestions
+
+### API Reference Example
+- Overview
+- Authentication
+- Endpoints with examples
+- Error codes
+- Rate limits
+
+### Workflow Guide Example
+- Prerequisites
+- Step-by-step instructions
+- Common patterns
+- Troubleshooting
+- Best practices
+"""
+
+EXAMPLE_ASSET = """# Example Asset File
+
+This placeholder represents where asset files would be stored.
+Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed.
+
+Asset files are NOT intended to be loaded into context, but rather used within
+the output Claude produces.
+
+Example asset files from other skills:
+- Brand guidelines: logo.png, slides_template.pptx
+- Frontend builder: hello-world/ directory with HTML/React boilerplate
+- Typography: custom-font.ttf, font-family.woff2
+- Data: sample_data.csv, test_dataset.json
+
+## Common Asset Types
+
+- Templates: .pptx, .docx, boilerplate directories
+- Images: .png, .jpg, .svg, .gif
+- Fonts: .ttf, .otf, .woff, .woff2
+- Boilerplate code: Project directories, starter files
+- Icons: .ico, .svg
+- Data files: .csv, .json, .xml, .yaml
+
+Note: This is a text placeholder. Actual assets can be any file type.
+"""
+
+
+def title_case_skill_name(skill_name):
+    """Convert hyphenated skill name to Title Case for display."""
+    return " ".join(word.capitalize() for word in skill_name.split("-"))
+
+
+def init_skill(skill_name, path):
+    """
+    Initialize a new skill directory with template SKILL.md.
+
+    Args:
+        skill_name: Name of the skill
+        path: Path where the skill directory should be created
+
+    Returns:
+        Path to created skill directory, or None if error
+    """
+    # Determine skill directory path
+    skill_dir = Path(path).resolve() / skill_name
+
+    # Check if directory already exists
+    if skill_dir.exists():
+        print(f"❌ Error: Skill directory already exists: {skill_dir}")
+        return None
+
+    # Create skill directory
+    try:
+        skill_dir.mkdir(parents=True, exist_ok=False)
+        print(f"✅ Created skill directory: {skill_dir}")
+    except Exception as e:
+        print(f"❌ Error creating directory: {e}")
+        return None
+
+    # Create SKILL.md from template
+    skill_title = title_case_skill_name(skill_name)
+    skill_content = SKILL_TEMPLATE.format(skill_name=skill_name, skill_title=skill_title)
+
+    skill_md_path = skill_dir / "SKILL.md"
+    try:
+        skill_md_path.write_text(skill_content)
+        print("✅ Created SKILL.md")
+    except Exception as e:
+        print(f"❌ Error creating SKILL.md: {e}")
+        return None
+
+    # Create resource directories with example files
+    try:
+        # Create scripts/ directory with example script
+        scripts_dir = skill_dir / "scripts"
+        scripts_dir.mkdir(exist_ok=True)
+        example_script = scripts_dir / "example.py"
+        example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name))
+        example_script.chmod(0o755)
+        print("✅ Created scripts/example.py")
+
+        # Create references/ directory with example reference doc
+        references_dir = skill_dir / "references"
+        references_dir.mkdir(exist_ok=True)
+        example_reference = references_dir / "api_reference.md"
+        example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title))
+        print("✅ Created references/api_reference.md")
+
+        # Create assets/ directory with example asset placeholder
+        assets_dir = skill_dir / "assets"
+        assets_dir.mkdir(exist_ok=True)
+        example_asset = assets_dir / "example_asset.txt"
+        example_asset.write_text(EXAMPLE_ASSET)
+        print("✅ Created assets/example_asset.txt")
+    except Exception as e:
+        print(f"❌ Error creating resource directories: {e}")
+        return None
+
+    # Print next steps
+    print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}")
+    print("\nNext steps:")
+    print("1. Edit SKILL.md to complete the TODO items and update the description")
+    print("2. Customize or delete the example files in scripts/, references/, and assets/")
+    print("3. Run the validator when ready to check the skill structure")
+
+    return skill_dir
+
+
+def main():
+    if len(sys.argv) < 4 or sys.argv[2] != "--path":
+        print("Usage: init_skill.py <skill-name> --path <path>")
+        print("\nSkill name requirements:")
+        print("  - Hyphen-case identifier (e.g., 'data-analyzer')")
+        print("  - Lowercase letters, digits, and hyphens only")
+        print("  - Max 40 characters")
+        print("  - Must match directory name exactly")
+        print("\nExamples:")
+        print("  init_skill.py my-new-skill --path skills/public")
+        print("  init_skill.py my-api-helper --path skills/private")
+        print("  init_skill.py custom-skill --path /custom/location")
+        sys.exit(1)
+
+    skill_name = sys.argv[1]
+    path = sys.argv[3]
+
+    print(f"🚀 Initializing skill: {skill_name}")
+    print(f"   Location: {path}")
+    print()
+
+    result = init_skill(skill_name, path)
+
+    if result:
+        sys.exit(0)
+    else:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

.claude/skills/skill-creator/scripts/package_skill.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+"""
+Skill Packager - Creates a distributable .skill file of a skill folder
+
+Usage:
+    python utils/package_skill.py <path/to/skill-folder> [output-directory]
+
+Example:
+    python utils/package_skill.py skills/public/my-skill
+    python utils/package_skill.py skills/public/my-skill ./dist
+"""
+
+import sys
+import zipfile
+from pathlib import Path
+from quick_validate import validate_skill
+
+
+def package_skill(skill_path, output_dir=None):
+    """
+    Package a skill folder into a .skill file.
+
+    Args:
+        skill_path: Path to the skill folder
+        output_dir: Optional output directory for the .skill file (defaults to current directory)
+
+    Returns:
+        Path to the created .skill file, or None if error
+    """
+    skill_path = Path(skill_path).resolve()
+
+    # Validate skill folder exists
+    if not skill_path.exists():
+        print(f"❌ Error: Skill folder not found: {skill_path}")
+        return None
+
+    if not skill_path.is_dir():
+        print(f"❌ Error: Path is not a directory: {skill_path}")
+        return None
+
+    # Validate SKILL.md exists
+    skill_md = skill_path / "SKILL.md"
+    if not skill_md.exists():
+        print(f"❌ Error: SKILL.md not found in {skill_path}")
+        return None
+
+    # Run validation before packaging
+    print("🔍 Validating skill...")
+    valid, message = validate_skill(skill_path)
+    if not valid:
+        print(f"❌ Validation failed: {message}")
+        print("   Please fix the validation errors before packaging.")
+        return None
+    print(f"✅ {message}\n")
+
+    # Determine output location
+    skill_name = skill_path.name
+    if output_dir:
+        output_path = Path(output_dir).resolve()
+        output_path.mkdir(parents=True, exist_ok=True)
+    else:
+        output_path = Path.cwd()
+
+    skill_filename = output_path / f"{skill_name}.skill"
+
+    # Create the .skill file (zip format)
+    try:
+        with zipfile.ZipFile(skill_filename, "w", zipfile.ZIP_DEFLATED) as zipf:
+            # Walk through the skill directory
+            for file_path in skill_path.rglob("*"):
+                if file_path.is_file():
+                    # Calculate the relative path within the zip
+                    arcname = file_path.relative_to(skill_path.parent)
+                    zipf.write(file_path, arcname)
+                    print(f"  Added: {arcname}")
+
+        print(f"\n✅ Successfully packaged skill to: {skill_filename}")
+        return skill_filename
+
+    except Exception as e:
+        print(f"❌ Error creating .skill file: {e}")
+        return None
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python utils/package_skill.py <path/to/skill-folder> [output-directory]")
+        print("\nExample:")
+        print("  python utils/package_skill.py skills/public/my-skill")
+        print("  python utils/package_skill.py skills/public/my-skill ./dist")
+        sys.exit(1)
+
+    skill_path = sys.argv[1]
+    output_dir = sys.argv[2] if len(sys.argv) > 2 else None
+
+    print(f"📦 Packaging skill: {skill_path}")
+    if output_dir:
+        print(f"   Output directory: {output_dir}")
+    print()
+
+    result = package_skill(skill_path, output_dir)
+
+    if result:
+        sys.exit(0)
+    else:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

.claude/skills/skill-creator/scripts/quick_validate.py

@@ -0,0 +1,97 @@
+#!/usr/bin/env python3
+"""
+Quick validation script for skills - minimal version
+"""
+
+import sys
+import os
+import re
+import yaml
+from pathlib import Path
+
+
+def validate_skill(skill_path):
+    """Basic validation of a skill"""
+    skill_path = Path(skill_path)
+
+    # Check SKILL.md exists
+    skill_md = skill_path / "SKILL.md"
+    if not skill_md.exists():
+        return False, "SKILL.md not found"
+
+    # Read and validate frontmatter
+    content = skill_md.read_text()
+    if not content.startswith("---"):
+        return False, "No YAML frontmatter found"
+
+    # Extract frontmatter
+    match = re.match(r"^---\n(.*?)\n---", content, re.DOTALL)
+    if not match:
+        return False, "Invalid frontmatter format"
+
+    frontmatter_text = match.group(1)
+
+    # Parse YAML frontmatter
+    try:
+        frontmatter = yaml.safe_load(frontmatter_text)
+        if not isinstance(frontmatter, dict):
+            return False, "Frontmatter must be a YAML dictionary"
+    except yaml.YAMLError as e:
+        return False, f"Invalid YAML in frontmatter: {e}"
+
+    # Define allowed properties
+    ALLOWED_PROPERTIES = {"name", "description", "license", "allowed-tools", "metadata"}
+
+    # Check for unexpected properties (excluding nested keys under metadata)
+    unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES
+    if unexpected_keys:
+        return False, (
+            f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. "
+            f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}"
+        )
+
+    # Check required fields
+    if "name" not in frontmatter:
+        return False, "Missing 'name' in frontmatter"
+    if "description" not in frontmatter:
+        return False, "Missing 'description' in frontmatter"
+
+    # Extract name for validation
+    name = frontmatter.get("name", "")
+    if not isinstance(name, str):
+        return False, f"Name must be a string, got {type(name).__name__}"
+    name = name.strip()
+    if name:
+        # Check naming convention (hyphen-case: lowercase with hyphens)
+        if not re.match(r"^[a-z0-9-]+$", name):
+            return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)"
+        if name.startswith("-") or name.endswith("-") or "--" in name:
+            return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens"
+        # Check name length (max 64 characters per spec)
+        if len(name) > 64:
+            return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters."
+
+    # Extract and validate description
+    description = frontmatter.get("description", "")
+    if not isinstance(description, str):
+        return False, f"Description must be a string, got {type(description).__name__}"
+    description = description.strip()
+    if description:
+        # Check for angle brackets
+        if "<" in description or ">" in description:
+            return False, "Description cannot contain angle brackets (< or >)"
+        # Check description length (max 1024 characters per spec)
+        if len(description) > 1024:
+            return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters."
+
+    return True, "Skill is valid!"
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python quick_validate.py <skill_directory>")
+        sys.exit(1)
+
+    valid, message = validate_skill(sys.argv[1])
+    print(message)
+    sys.exit(0 if valid else 1)

.codex/skills

@@ -0,0 +1 @@
+../.claude/skills

.codex/skills/component-refactoring

@@ -1 +0,0 @@
-../../.agents/skills/component-refactoring

.codex/skills/frontend-code-review

@@ -1 +0,0 @@
-../../.agents/skills/frontend-code-review

.codex/skills/frontend-testing

@@ -1 +0,0 @@
-../../.agents/skills/frontend-testing

.codex/skills/orpc-contract-first

@@ -1 +0,0 @@
-../../.agents/skills/orpc-contract-first

.devcontainer/post_create_command.sh

@@ -8,7 +8,7 @@ pipx install uv
 
 echo "alias start-api=\"cd $WORKSPACE_ROOT/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug\"" >> ~/.bashrc
 echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention\"" >> ~/.bashrc
-echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev:inspect\"" >> ~/.bashrc
+echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev\"" >> ~/.bashrc
 echo "alias start-web-prod=\"cd $WORKSPACE_ROOT/web && pnpm build && pnpm start\"" >> ~/.bashrc
 echo "alias start-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d\"" >> ~/.bashrc
 echo "alias stop-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env down\"" >> ~/.bashrc

.github/labeler.yml

@@ -1,3 +0,0 @@
-web:
-  - changed-files:
-      - any-glob-to-any-file: 'web/**'

.github/workflows/api-tests.yml

@@ -39,6 +39,12 @@ jobs:
       - name: Install dependencies
         run: uv sync --project api --dev
 
+      - name: Run pyrefly check
+        run: |
+          cd api
+          uv add --dev pyrefly
+          uv run pyrefly check || true
+
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
 

.github/workflows/autofix.yml

@@ -16,14 +16,14 @@ jobs:
 
       - name: Check Docker Compose inputs
         id: docker-compose-changes
-        uses: tj-actions/changed-files@v47
+        uses: tj-actions/changed-files@v46
         with:
           files: |
             docker/generate_docker_compose
             docker/.env.example
             docker/docker-compose-template.yaml
             docker/docker-compose.yaml
-      - uses: actions/setup-python@v6
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
 
@@ -79,32 +79,9 @@ jobs:
           find . -name "*.py" -type f -exec sed -i.bak -E 's/"([^"]+)" \| None/Optional["\1"]/g; s/'"'"'([^'"'"']+)'"'"' \| None/Optional['"'"'\1'"'"']/g' {} \;
           find . -name "*.py.bak" -type f -delete
 
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Install web dependencies
-        run: |
-          cd web
-          pnpm install --frozen-lockfile
-
-      - name: ESLint autofix
-        run: |
-          cd web
-          pnpm lint:fix || true
-
       # 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 ".agents/skills/**"
+          uvx --python 3.13 mdformat . --exclude ".claude/skills/**/SKILL.md"
 
       - uses: autofix-ci/action@635ffb0c9798bd160680f18fd73371e355b85f27

.github/workflows/build-push.yml

@@ -112,7 +112,7 @@ jobs:
             context: "web"
     steps:
       - name: Download digests
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v4
         with:
           path: /tmp/digests
           pattern: digests-${{ matrix.context }}-*

.github/workflows/deploy-dev.yml

@@ -16,7 +16,7 @@ jobs:
       github.event.workflow_run.head_branch == 'deploy/dev'
     steps:
       - name: Deploy to server
-        uses: appleboy/ssh-action@v1
+        uses: appleboy/ssh-action@v0.1.8
         with:
           host: ${{ secrets.SSH_HOST }}
           username: ${{ secrets.SSH_USER }}

.github/workflows/deploy-hitl.yml

@@ -1,29 +0,0 @@
-name: Deploy HITL
-
-on:
-  workflow_run:
-    workflows: ["Build and Push API & Web"]
-    branches:
-      - "feat/hitl-frontend"
-      - "feat/hitl-backend"
-    types:
-      - completed
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    if: |
-      github.event.workflow_run.conclusion == 'success' &&
-      (
-        github.event.workflow_run.head_branch == 'feat/hitl-frontend' ||
-        github.event.workflow_run.head_branch == 'feat/hitl-backend'
-      )
-    steps:
-      - name: Deploy to server
-        uses: appleboy/ssh-action@v1
-        with:
-          host: ${{ secrets.HITL_SSH_HOST }}
-          username: ${{ secrets.SSH_USER }}
-          key: ${{ secrets.SSH_PRIVATE_KEY }}
-          script: |
-            ${{ vars.SSH_SCRIPT || secrets.SSH_SCRIPT }}

.github/workflows/deploy-trigger-dev.yml

@@ -1,4 +1,4 @@
-name: Deploy Agent Dev
+name: Deploy Trigger Dev
 
 permissions:
   contents: read
@@ -7,7 +7,7 @@ on:
   workflow_run:
     workflows: ["Build and Push API & Web"]
     branches:
-      - "deploy/agent-dev"
+      - "deploy/trigger-dev"
     types:
       - completed
 
@@ -16,12 +16,12 @@ jobs:
     runs-on: ubuntu-latest
     if: |
       github.event.workflow_run.conclusion == 'success' &&
-      github.event.workflow_run.head_branch == 'deploy/agent-dev'
+      github.event.workflow_run.head_branch == 'deploy/trigger-dev'
     steps:
       - name: Deploy to server
-        uses: appleboy/ssh-action@v1
+        uses: appleboy/ssh-action@v0.1.8
         with:
-          host: ${{ secrets.AGENT_DEV_SSH_HOST }}
+          host: ${{ secrets.TRIGGER_SSH_HOST }}
           username: ${{ secrets.SSH_USER }}
           key: ${{ secrets.SSH_PRIVATE_KEY }}
           script: |

.github/workflows/labeler.yml

@@ -1,14 +0,0 @@
-name: "Pull Request Labeler"
-on:
-  pull_request_target:
-
-jobs:
-  labeler:
-    permissions:
-      contents: read
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/labeler@v6
-        with:
-          sync-labels: true

.github/workflows/stale.yml

@@ -18,7 +18,7 @@ jobs:
       pull-requests: write
 
     steps:
-      - uses: actions/stale@v10
+      - uses: actions/stale@v5
         with:
           days-before-issue-stale: 15
           days-before-issue-close: 3

.github/workflows/style.yml

@@ -65,9 +65,6 @@ jobs:
     defaults:
       run:
         working-directory: ./web
-    permissions:
-      checks: write
-      pull-requests: read
 
     steps:
       - name: Checkout code
@@ -93,7 +90,7 @@ jobs:
         uses: actions/setup-node@v6
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
-          node-version: 24
+          node-version: 22
           cache: pnpm
           cache-dependency-path: ./web/pnpm-lock.yaml
 
@@ -106,32 +103,23 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
         run: |
-          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'
-      #   uses: DerLev/eslint-annotations@51347b3a0abfb503fc8734d5ae31c4b151297fae
-      #   with:
-      #     eslint-report: web/eslint_report.json
-      #     github-token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Web tsslint
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: pnpm run lint:tss
+          pnpm run lint
 
       - name: Web type check
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
-        run: pnpm run type-check
+        run: pnpm run type-check:tsgo
 
       - name: Web dead code check
         if: steps.changed-files.outputs.any_changed == 'true'
         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

.github/workflows/tool-test-sdks.yaml

@@ -16,6 +16,10 @@ jobs:
     name: unit test for Node.js SDK
     runs-on: ubuntu-latest
 
+    strategy:
+      matrix:
+        node-version: [16, 18, 20, 22]
+
     defaults:
       run:
         working-directory: sdks/nodejs-client
@@ -25,10 +29,10 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Use Node.js
+      - name: Use Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v6
         with:
-          node-version: 24
+          node-version: ${{ matrix.node-version }}
           cache: ''
           cache-dependency-path: 'pnpm-lock.yaml'
 

.github/workflows/translate-i18n-base-on-english.yml

@@ -0,0 +1,94 @@
+name: Translate i18n Files Based on English
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'web/i18n/en-US/*.json'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  check-and-update:
+    if: github.repository == 'langgenius/dify'
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: web
+    steps:
+      # Keep use old checkout action version for https://github.com/peter-evans/create-pull-request/issues/4272
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Check for file changes in i18n/en-US
+        id: check_files
+        run: |
+          # Skip check for manual trigger, translate all files
+          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+            echo "FILES_CHANGED=true" >> $GITHUB_ENV
+            echo "FILE_ARGS=" >> $GITHUB_ENV
+            echo "Manual trigger: translating all files"
+          else
+            git fetch origin "${{ github.event.before }}" || true
+            git fetch origin "${{ github.sha }}" || true
+            changed_files=$(git diff --name-only "${{ github.event.before }}" "${{ github.sha }}" -- 'i18n/en-US/*.json')
+            echo "Changed files: $changed_files"
+            if [ -n "$changed_files" ]; then
+              echo "FILES_CHANGED=true" >> $GITHUB_ENV
+              file_args=""
+              for file in $changed_files; do
+                filename=$(basename "$file" .json)
+                file_args="$file_args --file $filename"
+              done
+              echo "FILE_ARGS=$file_args" >> $GITHUB_ENV
+              echo "File arguments: $file_args"
+            else
+              echo "FILES_CHANGED=false" >> $GITHUB_ENV
+            fi
+          fi
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          package_json_file: web/package.json
+          run_install: false
+
+      - name: Set up Node.js
+        if: env.FILES_CHANGED == 'true'
+        uses: actions/setup-node@v6
+        with:
+          node-version: 'lts/*'
+          cache: pnpm
+          cache-dependency-path: ./web/pnpm-lock.yaml
+
+      - name: Install dependencies
+        if: env.FILES_CHANGED == 'true'
+        working-directory: ./web
+        run: pnpm install --frozen-lockfile
+
+      - name: Generate i18n translations
+        if: env.FILES_CHANGED == 'true'
+        working-directory: ./web
+        run: pnpm run i18n:gen ${{ env.FILE_ARGS }}
+
+      - name: Create Pull Request
+        if: env.FILES_CHANGED == 'true'
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: 'chore(i18n): update translations based on en-US changes'
+          title: 'chore(i18n): translate i18n files based on en-US changes'
+          body: |
+            This PR was automatically created to update i18n translation files based on changes in en-US locale.
+
+            **Triggered by:** ${{ github.sha }}
+
+            **Changes included:**
+            - Updated translation files for all locales
+          branch: chore/automated-i18n-updates-${{ github.sha }}
+          delete-branch: true

.github/workflows/translate-i18n-claude.yml

@@ -1,440 +0,0 @@
-name: Translate i18n Files with Claude Code
-
-# Note: claude-code-action doesn't support push events directly.
-# Push events are handled by trigger-i18n-sync.yml which sends repository_dispatch.
-# See: https://github.com/langgenius/dify/issues/30743
-
-on:
-  repository_dispatch:
-    types: [i18n-sync]
-  workflow_dispatch:
-    inputs:
-      files:
-        description: 'Specific files to translate (space-separated, e.g., "app common"). Leave empty for all files.'
-        required: false
-        type: string
-      languages:
-        description: 'Specific languages to translate (space-separated, e.g., "zh-Hans ja-JP"). Leave empty for all supported languages.'
-        required: false
-        type: string
-      mode:
-        description: 'Sync mode: incremental (only changes) or full (re-check all keys)'
-        required: false
-        default: 'incremental'
-        type: choice
-        options:
-          - incremental
-          - full
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  translate:
-    if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
-    timeout-minutes: 60
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Configure Git
-        run: |
-          git config --global user.name "github-actions[bot]"
-          git config --global user.email "github-actions[bot]@users.noreply.github.com"
-
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          package_json_file: web/package.json
-          run_install: false
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: ./web/pnpm-lock.yaml
-
-      - name: Detect changed files and generate diff
-        id: detect_changes
-        run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            # Manual trigger
-            if [ -n "${{ github.event.inputs.files }}" ]; then
-              echo "CHANGED_FILES=${{ github.event.inputs.files }}" >> $GITHUB_OUTPUT
-            else
-              # Get all JSON files in en-US directory
-              files=$(ls web/i18n/en-US/*.json 2>/dev/null | xargs -n1 basename | sed 's/.json$//' | tr '\n' ' ')
-              echo "CHANGED_FILES=$files" >> $GITHUB_OUTPUT
-            fi
-            echo "TARGET_LANGS=${{ github.event.inputs.languages }}" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.inputs.mode || 'incremental' }}" >> $GITHUB_OUTPUT
-
-            # For manual trigger with incremental mode, get diff from last commit
-            # For full mode, we'll do a complete check anyway
-            if [ "${{ github.event.inputs.mode }}" == "full" ]; then
-              echo "Full mode: will check all keys" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-            else
-              git diff HEAD~1..HEAD -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-              if [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
-            fi
-          elif [ "${{ github.event_name }}" == "repository_dispatch" ]; then
-            # Triggered by push via trigger-i18n-sync.yml workflow
-            # Validate required payload fields
-            if [ -z "${{ github.event.client_payload.changed_files }}" ]; then
-              echo "Error: repository_dispatch payload missing required 'changed_files' field" >&2
-              exit 1
-            fi
-            echo "CHANGED_FILES=${{ github.event.client_payload.changed_files }}" >> $GITHUB_OUTPUT
-            echo "TARGET_LANGS=" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.client_payload.sync_mode || 'incremental' }}" >> $GITHUB_OUTPUT
-
-            # Decode the base64-encoded diff from the trigger workflow
-            if [ -n "${{ github.event.client_payload.diff_base64 }}" ]; then
-              if ! echo "${{ github.event.client_payload.diff_base64 }}" | base64 -d > /tmp/i18n-diff.txt 2>&1; then
-                echo "Warning: Failed to decode base64 diff payload" >&2
-                echo "" > /tmp/i18n-diff.txt
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              elif [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
-            else
-              echo "" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-            fi
-          else
-            echo "Unsupported event type: ${{ github.event_name }}"
-            exit 1
-          fi
-
-          # Truncate diff if too large (keep first 50KB)
-          if [ -f /tmp/i18n-diff.txt ]; then
-            head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-            mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
-          fi
-
-          echo "Detected files: $(cat $GITHUB_OUTPUT | grep CHANGED_FILES || echo 'none')"
-
-      - name: Run Claude Code for Translation Sync
-        if: steps.detect_changes.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@v1
-        with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          # Allow github-actions bot to trigger this workflow via repository_dispatch
-          # See: https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
-          allowed_bots: 'github-actions[bot]'
-          prompt: |
-            You are a professional i18n synchronization engineer for the Dify project.
-            Your task is to keep all language translations in sync with the English source (en-US).
-
-            ## CRITICAL TOOL RESTRICTIONS
-            - Use **Read** tool to read files (NOT cat or bash)
-            - Use **Edit** tool to modify JSON files (NOT node, jq, or bash scripts)
-            - Use **Bash** ONLY for: git commands, gh commands, pnpm commands
-            - Run bash commands ONE BY ONE, never combine with && or ||
-            - NEVER use `$()` command substitution - it's not supported. Split into separate commands instead.
-
-            ## WORKING DIRECTORY & ABSOLUTE PATHS
-            Claude Code sandbox working directory may vary. Always use absolute paths:
-            - For pnpm: `pnpm --dir ${{ github.workspace }}/web <command>`
-            - For git: `git -C ${{ github.workspace }} <command>`
-            - For gh: `gh --repo ${{ github.repository }} <command>`
-            - For file paths: `${{ github.workspace }}/web/i18n/`
-
-            ## EFFICIENCY RULES
-            - **ONE Edit per language file** - batch all key additions into a single Edit
-            - Insert new keys at the beginning of JSON (after `{`), lint:fix will sort them
-            - Translate ALL keys for a language mentally first, then do ONE Edit
-
-            ## Context
-            - Changed/target files: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-            - Target languages (empty means all supported): ${{ steps.detect_changes.outputs.TARGET_LANGS }}
-            - Sync mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Translation files are located in: ${{ github.workspace }}/web/i18n/{locale}/{filename}.json
-            - Language configuration is in: ${{ github.workspace }}/web/i18n-config/languages.ts
-            - Git diff is available: ${{ steps.detect_changes.outputs.DIFF_AVAILABLE }}
-
-            ## CRITICAL DESIGN: Verify First, Then Sync
-
-            You MUST follow this three-phase approach:
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 1: VERIFY - Analyze and Generate Change Report       ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 1.1: Analyze Git Diff (for incremental mode)
-            Use the Read tool to read `/tmp/i18n-diff.txt` to see the git diff.
-
-            Parse the diff to categorize changes:
-            - Lines with `+` (not `+++`): Added or modified values
-            - Lines with `-` (not `---`): Removed or old values
-            - Identify specific keys for each category:
-              * ADD: Keys that appear only in `+` lines (new keys)
-              * UPDATE: Keys that appear in both `-` and `+` lines (value changed)
-              * DELETE: Keys that appear only in `-` lines (removed keys)
-
-            ### Step 1.2: Read Language Configuration
-            Use the Read tool to read `${{ github.workspace }}/web/i18n-config/languages.ts`.
-            Extract all languages with `supported: true`.
-
-            ### Step 1.3: Run i18n:check for Each Language
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web install --frozen-lockfile
-            ```
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            This will report:
-            - Missing keys (need to ADD)
-            - Extra keys (need to DELETE)
-
-            ### Step 1.4: Generate Change Report
-
-            Create a structured report identifying:
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    I18N SYNC CHANGE REPORT                   ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Files to process: [list]                                     ║
-            ║ Languages to sync: [list]                                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ ADD (New Keys):                                              ║
-            ║   - [filename].[key]: "English value"                        ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ UPDATE (Modified Keys - MUST re-translate):                  ║
-            ║   - [filename].[key]: "Old value" → "New value"              ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ DELETE (Extra Keys):                                         ║
-            ║   - [language]/[filename].[key]                              ║
-            ║   ...                                                        ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            **IMPORTANT**: For UPDATE detection, compare git diff to find keys where
-            the English value changed. These MUST be re-translated even if target
-            language already has a translation (it's now stale!).
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 2: SYNC - Execute Changes Based on Report            ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 2.1: Process ADD Operations (BATCH per language file)
-
-            **CRITICAL WORKFLOW for efficiency:**
-            1. First, translate ALL new keys for ALL languages mentally
-            2. Then, for EACH language file, do ONE Edit operation:
-               - Read the file once
-               - Insert ALL new keys at the beginning (right after the opening `{`)
-               - Don't worry about alphabetical order - lint:fix will sort them later
-
-            Example Edit (adding 3 keys to zh-Hans/app.json):
-            ```
-            old_string: '{\n  "accessControl"'
-            new_string: '{\n  "newKey1": "translation1",\n  "newKey2": "translation2",\n  "newKey3": "translation3",\n  "accessControl"'
-            ```
-
-            **IMPORTANT**:
-            - ONE Edit per language file (not one Edit per key!)
-            - Always use the Edit tool. NEVER use bash scripts, node, or jq.
-
-            ### Step 2.2: Process UPDATE Operations
-
-            **IMPORTANT: Special handling for zh-Hans and ja-JP**
-            If zh-Hans or ja-JP files were ALSO modified in the same push:
-            - Run: `git -C ${{ github.workspace }} diff HEAD~1 --name-only` and check for zh-Hans or ja-JP files
-            - If found, it means someone manually translated them. Apply these rules:
-
-            1. **Missing keys**: Still ADD them (completeness required)
-            2. **Existing translations**: Compare with the NEW English value:
-               - If translation is **completely wrong** or **unrelated** → Update it
-               - If translation is **roughly correct** (captures the meaning) → Keep it, respect manual work
-               - When in doubt, **keep the manual translation**
-
-            Example:
-            - English changed: "Save" → "Save Changes"
-            - Manual translation: "保存更改" → Keep it (correct meaning)
-            - Manual translation: "删除" → Update it (completely wrong)
-
-            For other languages:
-            Use Edit tool to replace the old value with the new translation.
-            You can batch multiple updates in one Edit if they are adjacent.
-
-            ### Step 2.3: Process DELETE Operations
-            For extra keys reported by i18n:check:
-            - Run: `pnpm --dir ${{ github.workspace }}/web run i18n:check --auto-remove`
-            - Or manually remove from target language JSON files
-
-            ## Translation Guidelines
-
-            - PRESERVE all placeholders exactly as-is:
-              - `{{variable}}` - Mustache interpolation
-              - `${variable}` - Template literal
-              - `<tag>content</tag>` - HTML tags
-              - `_one`, `_other` - Pluralization suffixes (these are KEY suffixes, not values)
-
-              **CRITICAL: Variable names and tag names MUST stay in English - NEVER translate them**
-
-              ✅ CORRECT examples:
-              - English: "{{count}} items" → Japanese: "{{count}} 個のアイテム"
-              - English: "{{name}} updated" → Korean: "{{name}} 업데이트됨"
-              - English: "<email>{{email}}</email>" → Chinese: "<email>{{email}}</email>"
-              - English: "<CustomLink>Marketplace</CustomLink>" → Japanese: "<CustomLink>マーケットプレイス</CustomLink>"
-
-              ❌ WRONG examples (NEVER do this - will break the application):
-              - "{{count}}" → "{{カウント}}" ❌ (variable name translated to Japanese)
-              - "{{name}}" → "{{이름}}" ❌ (variable name translated to Korean)
-              - "{{email}}" → "{{邮箱}}" ❌ (variable name translated to Chinese)
-              - "<email>" → "<メール>" ❌ (tag name translated)
-              - "<CustomLink>" → "<自定义链接>" ❌ (component name translated)
-
-            - Use appropriate language register (formal/informal) based on existing translations
-            - Match existing translation style in each language
-            - Technical terms: check existing conventions per language
-            - For CJK languages: no spaces between characters unless necessary
-            - For RTL languages (ar-TN, fa-IR): ensure proper text handling
-
-            ## Output Format Requirements
-            - Alphabetical key ordering (if original file uses it)
-            - 2-space indentation
-            - Trailing newline at end of file
-            - Valid JSON (use proper escaping for special characters)
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 3: RE-VERIFY - Confirm All Issues Resolved           ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 3.1: Run Lint Fix (IMPORTANT!)
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web lint:fix --quiet -- 'i18n/**/*.json'
-            ```
-            This ensures:
-            - JSON keys are sorted alphabetically (jsonc/sort-keys rule)
-            - Valid i18n keys (dify-i18n/valid-i18n-keys rule)
-            - No extra keys (dify-i18n/no-extra-keys rule)
-
-            ### Step 3.2: Run Final i18n Check
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            ### Step 3.3: Fix Any Remaining Issues
-            If check reports issues:
-            - Go back to PHASE 2 for unresolved items
-            - Repeat until check passes
-
-            ### Step 3.4: Generate Final Summary
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    SYNC COMPLETED SUMMARY                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Language      │ Added │ Updated │ Deleted │ Status          ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ zh-Hans       │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ja-JP         │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ...           │ ...   │  ...    │   ...   │ ...             ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ i18n:check    │ PASSED - All keys in sync                   ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            ## Mode-Specific Behavior
-
-            **SYNC_MODE = "incremental"** (default):
-            - Focus on keys identified from git diff
-            - Also check i18n:check output for any missing/extra keys
-            - Efficient for small changes
-
-            **SYNC_MODE = "full"**:
-            - Compare ALL keys between en-US and each language
-            - Run i18n:check to identify all discrepancies
-            - Use for first-time sync or fixing historical issues
-
-            ## Important Notes
-
-            1. Always run i18n:check BEFORE and AFTER making changes
-            2. The check script is the source of truth for missing/extra keys
-            3. For UPDATE scenario: git diff is the source of truth for changed values
-            4. Create a single commit with all translation changes
-            5. If any translation fails, continue with others and report failures
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 4: COMMIT AND CREATE PR                              ║
-            ═══════════════════════════════════════════════════════════════
-
-            After all translations are complete and verified:
-
-            ### Step 4.1: Check for changes
-            ```bash
-            git -C ${{ github.workspace }} status --porcelain
-            ```
-
-            If there are changes:
-
-            ### Step 4.2: Create a new branch and commit
-            Run these git commands ONE BY ONE (not combined with &&).
-            **IMPORTANT**: Do NOT use `$()` command substitution. Use two separate commands:
-
-            1. First, get the timestamp:
-            ```bash
-            date +%Y%m%d-%H%M%S
-            ```
-            (Note the output, e.g., "20260115-143052")
-
-            2. Then create branch using the timestamp value:
-            ```bash
-            git -C ${{ github.workspace }} checkout -b chore/i18n-sync-20260115-143052
-            ```
-            (Replace "20260115-143052" with the actual timestamp from step 1)
-
-            3. Stage changes:
-            ```bash
-            git -C ${{ github.workspace }} add web/i18n/
-            ```
-
-            4. Commit:
-            ```bash
-            git -C ${{ github.workspace }} commit -m "chore(i18n): sync translations with en-US - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}"
-            ```
-
-            5. Push:
-            ```bash
-            git -C ${{ github.workspace }} push origin HEAD
-            ```
-
-            ### Step 4.3: Create Pull Request
-            ```bash
-            gh pr create --repo ${{ github.repository }} --title "chore(i18n): sync translations with en-US" --body "## Summary
-
-            This PR was automatically generated to sync i18n translation files.
-
-            ### Changes
-            - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Files processed: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-
-            ### Verification
-            - [x] \`i18n:check\` passed
-            - [x] \`lint:fix\` applied
-
-            🤖 Generated with Claude Code GitHub Action" --base main
-            ```
-
-          claude_args: |
-            --max-turns 150
-            --allowedTools "Read,Write,Edit,Bash(git *),Bash(git:*),Bash(gh *),Bash(gh:*),Bash(pnpm *),Bash(pnpm:*),Bash(date *),Bash(date:*),Glob,Grep"

.github/workflows/trigger-i18n-sync.yml

@@ -1,66 +0,0 @@
-name: Trigger i18n Sync on Push
-
-# This workflow bridges the push event to repository_dispatch
-# because claude-code-action doesn't support push events directly.
-# See: https://github.com/langgenius/dify/issues/30743
-
-on:
-  push:
-    branches: [main]
-    paths:
-      - 'web/i18n/en-US/*.json'
-
-permissions:
-  contents: write
-
-jobs:
-  trigger:
-    if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
-    timeout-minutes: 5
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Detect changed files and generate diff
-        id: detect
-        run: |
-          BEFORE_SHA="${{ github.event.before }}"
-          # Handle edge case: force push may have null/zero SHA
-          if [ -z "$BEFORE_SHA" ] || [ "$BEFORE_SHA" = "0000000000000000000000000000000000000000" ]; then
-            BEFORE_SHA="HEAD~1"
-          fi
-
-          # Detect changed i18n files
-          changed=$(git diff --name-only "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' 2>/dev/null | xargs -n1 basename 2>/dev/null | sed 's/.json$//' | tr '\n' ' ' || echo "")
-          echo "changed_files=$changed" >> $GITHUB_OUTPUT
-
-          # Generate diff for context
-          git diff "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-
-          # Truncate if too large (keep first 50KB to match receiving workflow)
-          head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-          mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
-
-          # Base64 encode the diff for safe JSON transport (portable, single-line)
-          diff_base64=$(base64 < /tmp/i18n-diff.txt | tr -d '\n')
-          echo "diff_base64=$diff_base64" >> $GITHUB_OUTPUT
-
-          if [ -n "$changed" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            echo "Detected changed files: $changed"
-          else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-            echo "No i18n changes detected"
-          fi
-
-      - name: Trigger i18n sync workflow
-        if: steps.detect.outputs.has_changes == 'true'
-        uses: peter-evans/repository-dispatch@v3
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          event-type: i18n-sync
-          client-payload: '{"changed_files": "${{ steps.detect.outputs.changed_files }}", "diff_base64": "${{ steps.detect.outputs.diff_base64 }}", "sync_mode": "incremental", "trigger_sha": "${{ github.sha }}"}'

.github/workflows/web-tests.yml

@@ -31,7 +31,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: 24
+          node-version: 22
           cache: pnpm
           cache-dependency-path: ./web/pnpm-lock.yaml
 
@@ -366,48 +366,3 @@ 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

.gitignore

@@ -209,6 +209,7 @@ api/.vscode
 .history
 
 .idea/
+web/migration/
 
 # pnpm
 /.pnpm-store

.nvmrc

@@ -0,0 +1 @@
+22.11.0

AGENTS.md

@@ -12,8 +12,12 @@ The codebase is split into:
 
 ## Backend Workflow
 
-- Read `api/AGENTS.md` for details
 - Run backend CLI commands through `uv run --project api <command>`.
+
+- Before submission, all backend modifications must pass local checks: `make lint`, `make type-check`, and `uv run --project api --dev dev/pytest/pytest_unit_tests.sh`.
+
+- Use Makefile targets for linting and formatting; `make lint` and `make type-check` cover the required checks.
+
 - Integration tests are CI-only and are not expected to run in the local environment.
 
 ## Frontend Workflow
@@ -25,30 +29,6 @@ pnpm type-check:tsgo
 pnpm test
 ```
 
-### Frontend Linting
-
-ESLint is used for frontend code quality. Available commands:
-
-```bash
-# Lint all files (report only)
-pnpm lint
-
-# Lint and auto-fix issues
-pnpm lint:fix
-
-# Lint specific files or directories
-pnpm lint:fix app/components/base/button/
-pnpm lint:fix app/components/base/button/index.tsx
-
-# Lint quietly (errors only, no warnings)
-pnpm lint:quiet
-
-# Check code complexity
-pnpm lint:complexity
-```
-
-**Important**: Always run `pnpm lint:fix` before committing. The pre-commit hook runs `lint-staged` which only lints staged files.
-
 ## Testing & Quality Practices
 
 - Follow TDD: red → green → refactor.

Makefile

@@ -61,8 +61,7 @@ check:
 
 lint:
 	@echo "🔧 Running ruff format, check with fixes, import linter, and dotenv-linter..."
-	@uv run --project api --dev ruff format ./api
-	@uv run --project api --dev ruff check --fix ./api
+	@uv run --project api --dev sh -c 'ruff format ./api && ruff check --fix ./api'
 	@uv run --directory api --dev lint-imports
 	@uv run --project api --dev dotenv-linter ./api/.env.example ./web/.env.example
 	@echo "✅ Linting complete"
@@ -74,12 +73,7 @@ type-check:
 
 test:
 	@echo "🧪 Running backend unit tests..."
-	@if [ -n "$(TARGET_TESTS)" ]; then \
-		echo "Target: $(TARGET_TESTS)"; \
-		uv run --project api --dev pytest $(TARGET_TESTS); \
-	else \
-		uv run --project api --dev dev/pytest/pytest_unit_tests.sh; \
-	fi
+	@uv run --project api --dev dev/pytest/pytest_unit_tests.sh
 	@echo "✅ Tests complete"
 
 # Build Docker images
@@ -131,7 +125,7 @@ help:
 	@echo "  make check          - Check code with ruff"
 	@echo "  make lint           - Format, fix, and lint code (ruff, imports, dotenv)"
 	@echo "  make type-check     - Run type checking with basedpyright"
-	@echo "  make test           - Run backend unit tests (or TARGET_TESTS=./api/tests/<target_tests>)"
+	@echo "  make test           - Run backend unit tests"
 	@echo ""
 	@echo "Docker Build Targets:"
 	@echo "  make build-web      - Build web Docker image"

api/.env.example

@@ -417,8 +417,6 @@ SMTP_USERNAME=123
 SMTP_PASSWORD=abc
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
-# Optional: override the local hostname used for SMTP HELO/EHLO
-SMTP_LOCAL_HOSTNAME=
 # Sendgid configuration
 SENDGRID_API_KEY=
 # Sentry configuration
@@ -591,7 +589,6 @@ ENABLE_CLEAN_UNUSED_DATASETS_TASK=false
 ENABLE_CREATE_TIDB_SERVERLESS_TASK=false
 ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK=false
 ENABLE_CLEAN_MESSAGES=false
-ENABLE_WORKFLOW_RUN_CLEANUP_TASK=false
 ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK=false
 ENABLE_DATASETS_QUEUE_MONITOR=false
 ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK=true
@@ -715,5 +712,3 @@ ANNOTATION_IMPORT_MAX_CONCURRENT=5
 SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD=21
 SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE=1000
 SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS=30
-SANDBOX_EXPIRED_RECORDS_CLEAN_TASK_LOCK_TTL=90000
-

api/.importlinter

@@ -27,9 +27,7 @@ ignore_imports =
     core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_events
     core.workflow.nodes.loop.loop_node -> core.workflow.graph_events
 
-    core.workflow.nodes.iteration.iteration_node -> core.app.workflow.node_factory
-    core.workflow.nodes.loop.loop_node -> core.app.workflow.node_factory
-
+    core.workflow.nodes.node_factory -> core.workflow.graph
     core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine
     core.workflow.nodes.iteration.iteration_node -> core.workflow.graph
     core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine.command_channels
@@ -59,248 +57,6 @@ ignore_imports =
     core.workflow.graph_engine.manager -> extensions.ext_redis
     core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_redis
 
-[importlinter:contract:workflow-external-imports]
-name = Workflow External Imports
-type = forbidden
-source_modules =
-    core.workflow
-forbidden_modules =
-    configs
-    controllers
-    extensions
-    models
-    services
-    tasks
-    core.agent
-    core.app
-    core.base
-    core.callback_handler
-    core.datasource
-    core.db
-    core.entities
-    core.errors
-    core.extension
-    core.external_data_tool
-    core.file
-    core.helper
-    core.hosting_configuration
-    core.indexing_runner
-    core.llm_generator
-    core.logging
-    core.mcp
-    core.memory
-    core.model_manager
-    core.moderation
-    core.ops
-    core.plugin
-    core.prompt
-    core.provider_manager
-    core.rag
-    core.repositories
-    core.schemas
-    core.tools
-    core.trigger
-    core.variables
-ignore_imports =
-    core.workflow.nodes.loop.loop_node -> core.app.workflow.node_factory
-    core.workflow.graph_engine.command_channels.redis_channel -> extensions.ext_redis
-    core.workflow.workflow_entry -> core.app.workflow.layers.observability
-    core.workflow.graph_engine.worker_management.worker_pool -> configs
-    core.workflow.nodes.agent.agent_node -> core.model_manager
-    core.workflow.nodes.agent.agent_node -> core.provider_manager
-    core.workflow.nodes.agent.agent_node -> core.tools.tool_manager
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.code_executor
-    core.workflow.nodes.datasource.datasource_node -> models.model
-    core.workflow.nodes.datasource.datasource_node -> models.tools
-    core.workflow.nodes.datasource.datasource_node -> services.datasource_provider_service
-    core.workflow.nodes.document_extractor.node -> configs
-    core.workflow.nodes.document_extractor.node -> core.file.file_manager
-    core.workflow.nodes.document_extractor.node -> core.helper.ssrf_proxy
-    core.workflow.nodes.http_request.entities -> configs
-    core.workflow.nodes.http_request.executor -> configs
-    core.workflow.nodes.http_request.executor -> core.file.file_manager
-    core.workflow.nodes.http_request.node -> configs
-    core.workflow.nodes.http_request.node -> core.tools.tool_file_manager
-    core.workflow.nodes.iteration.iteration_node -> core.app.workflow.node_factory
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.rag.index_processor.index_processor_factory
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.datasource.retrieval_service
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.retrieval.dataset_retrieval
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> models.dataset
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> services.feature_service
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.llm.llm_utils -> configs
-    core.workflow.nodes.llm.llm_utils -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.llm.llm_utils -> core.file.models
-    core.workflow.nodes.llm.llm_utils -> core.model_manager
-    core.workflow.nodes.llm.llm_utils -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.llm.llm_utils -> models.model
-    core.workflow.nodes.llm.llm_utils -> models.provider
-    core.workflow.nodes.llm.llm_utils -> services.credit_pool_service
-    core.workflow.nodes.llm.node -> core.tools.signature
-    core.workflow.nodes.template_transform.template_transform_node -> configs
-    core.workflow.nodes.tool.tool_node -> core.callback_handler.workflow_tool_callback_handler
-    core.workflow.nodes.tool.tool_node -> core.tools.tool_engine
-    core.workflow.nodes.tool.tool_node -> core.tools.tool_manager
-    core.workflow.workflow_entry -> configs
-    core.workflow.workflow_entry -> models.workflow
-    core.workflow.nodes.agent.agent_node -> core.agent.entities
-    core.workflow.nodes.agent.agent_node -> core.agent.plugin_entities
-    core.workflow.nodes.base.node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.app_config.entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.llm.node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.advanced_prompt_transform
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.model_runtime.model_providers.__base.large_language_model
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.app.entities.app_invoke_entities
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.advanced_prompt_transform
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.start.entities -> core.app.app_config.entities
-    core.workflow.nodes.start.start_node -> core.app.app_config.entities
-    core.workflow.workflow_entry -> core.app.apps.exc
-    core.workflow.workflow_entry -> core.app.entities.app_invoke_entities
-    core.workflow.workflow_entry -> core.app.workflow.node_factory
-    core.workflow.nodes.datasource.datasource_node -> core.datasource.datasource_manager
-    core.workflow.nodes.datasource.datasource_node -> core.datasource.utils.message_transformer
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.entities.agent_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.entities.model_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.model_manager
-    core.workflow.nodes.llm.llm_utils -> core.entities.provider_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.model_manager
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.model_manager
-    core.workflow.node_events.node -> core.file
-    core.workflow.nodes.agent.agent_node -> core.file
-    core.workflow.nodes.datasource.datasource_node -> core.file
-    core.workflow.nodes.datasource.datasource_node -> core.file.enums
-    core.workflow.nodes.document_extractor.node -> core.file
-    core.workflow.nodes.http_request.executor -> core.file.enums
-    core.workflow.nodes.http_request.node -> core.file
-    core.workflow.nodes.http_request.node -> core.file.file_manager
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.file.models
-    core.workflow.nodes.list_operator.node -> core.file
-    core.workflow.nodes.llm.file_saver -> core.file
-    core.workflow.nodes.llm.llm_utils -> core.variables.segments
-    core.workflow.nodes.llm.node -> core.file
-    core.workflow.nodes.llm.node -> core.file.file_manager
-    core.workflow.nodes.llm.node -> core.file.models
-    core.workflow.nodes.loop.entities -> core.variables.types
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.file
-    core.workflow.nodes.protocols -> core.file
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.file.models
-    core.workflow.nodes.tool.tool_node -> core.file
-    core.workflow.nodes.tool.tool_node -> core.tools.utils.message_transformer
-    core.workflow.nodes.tool.tool_node -> models
-    core.workflow.nodes.trigger_webhook.node -> core.file
-    core.workflow.runtime.variable_pool -> core.file
-    core.workflow.runtime.variable_pool -> core.file.file_manager
-    core.workflow.system_variable -> core.file.models
-    core.workflow.utils.condition.processor -> core.file
-    core.workflow.utils.condition.processor -> core.file.file_manager
-    core.workflow.workflow_entry -> core.file.models
-    core.workflow.workflow_type_encoder -> core.file.models
-    core.workflow.nodes.agent.agent_node -> models.model
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.code_node_provider
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.javascript.javascript_code_provider
-    core.workflow.nodes.code.code_node -> core.helper.code_executor.python3.python3_code_provider
-    core.workflow.nodes.code.entities -> core.helper.code_executor.code_executor
-    core.workflow.nodes.datasource.datasource_node -> core.variables.variables
-    core.workflow.nodes.http_request.executor -> core.helper.ssrf_proxy
-    core.workflow.nodes.http_request.node -> core.helper.ssrf_proxy
-    core.workflow.nodes.llm.file_saver -> core.helper.ssrf_proxy
-    core.workflow.nodes.llm.node -> core.helper.code_executor
-    core.workflow.nodes.template_transform.template_renderer -> core.helper.code_executor.code_executor
-    core.workflow.nodes.llm.node -> core.llm_generator.output_parser.errors
-    core.workflow.nodes.llm.node -> core.llm_generator.output_parser.structured_output
-    core.workflow.nodes.llm.node -> core.model_manager
-    core.workflow.nodes.agent.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.prompt.simple_prompt_transform
-    core.workflow.nodes.llm.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.llm_utils -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.node -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.llm.node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.parameter_extractor.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.question_classifier.entities -> core.prompt.entities.advanced_prompt_entities
-    core.workflow.nodes.question_classifier.question_classifier_node -> core.prompt.utils.prompt_message_util
-    core.workflow.nodes.knowledge_index.entities -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> models.dataset
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.rag.retrieval.retrieval_methods
-    core.workflow.nodes.llm.node -> models.dataset
-    core.workflow.nodes.agent.agent_node -> core.tools.utils.message_transformer
-    core.workflow.nodes.llm.file_saver -> core.tools.signature
-    core.workflow.nodes.llm.file_saver -> core.tools.tool_file_manager
-    core.workflow.nodes.tool.tool_node -> core.tools.errors
-    core.workflow.conversation_variable_updater -> core.variables
-    core.workflow.graph_engine.entities.commands -> core.variables.variables
-    core.workflow.nodes.agent.agent_node -> core.variables.segments
-    core.workflow.nodes.answer.answer_node -> core.variables
-    core.workflow.nodes.code.code_node -> core.variables.segments
-    core.workflow.nodes.code.code_node -> core.variables.types
-    core.workflow.nodes.code.entities -> core.variables.types
-    core.workflow.nodes.datasource.datasource_node -> core.variables.segments
-    core.workflow.nodes.document_extractor.node -> core.variables
-    core.workflow.nodes.document_extractor.node -> core.variables.segments
-    core.workflow.nodes.http_request.executor -> core.variables.segments
-    core.workflow.nodes.http_request.node -> core.variables.segments
-    core.workflow.nodes.iteration.iteration_node -> core.variables
-    core.workflow.nodes.iteration.iteration_node -> core.variables.segments
-    core.workflow.nodes.iteration.iteration_node -> core.variables.variables
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.variables
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> core.variables.segments
-    core.workflow.nodes.list_operator.node -> core.variables
-    core.workflow.nodes.list_operator.node -> core.variables.segments
-    core.workflow.nodes.llm.node -> core.variables
-    core.workflow.nodes.loop.loop_node -> core.variables
-    core.workflow.nodes.parameter_extractor.entities -> core.variables.types
-    core.workflow.nodes.parameter_extractor.exc -> core.variables.types
-    core.workflow.nodes.parameter_extractor.parameter_extractor_node -> core.variables.types
-    core.workflow.nodes.tool.tool_node -> core.variables.segments
-    core.workflow.nodes.tool.tool_node -> core.variables.variables
-    core.workflow.nodes.trigger_webhook.node -> core.variables.types
-    core.workflow.nodes.trigger_webhook.node -> core.variables.variables
-    core.workflow.nodes.variable_aggregator.entities -> core.variables.types
-    core.workflow.nodes.variable_aggregator.variable_aggregator_node -> core.variables.segments
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables.consts
-    core.workflow.nodes.variable_assigner.common.helpers -> core.variables.types
-    core.workflow.nodes.variable_assigner.v1.node -> core.variables
-    core.workflow.nodes.variable_assigner.v2.helpers -> core.variables
-    core.workflow.nodes.variable_assigner.v2.node -> core.variables
-    core.workflow.nodes.variable_assigner.v2.node -> core.variables.consts
-    core.workflow.runtime.graph_runtime_state_protocol -> core.variables.segments
-    core.workflow.runtime.read_only_wrappers -> core.variables.segments
-    core.workflow.runtime.variable_pool -> core.variables
-    core.workflow.runtime.variable_pool -> core.variables.consts
-    core.workflow.runtime.variable_pool -> core.variables.segments
-    core.workflow.runtime.variable_pool -> core.variables.variables
-    core.workflow.utils.condition.processor -> core.variables
-    core.workflow.utils.condition.processor -> core.variables.segments
-    core.workflow.variable_loader -> core.variables
-    core.workflow.variable_loader -> core.variables.consts
-    core.workflow.workflow_type_encoder -> core.variables
-    core.workflow.graph_engine.manager -> extensions.ext_redis
-    core.workflow.nodes.agent.agent_node -> extensions.ext_database
-    core.workflow.nodes.datasource.datasource_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_index.knowledge_index_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_database
-    core.workflow.nodes.knowledge_retrieval.knowledge_retrieval_node -> extensions.ext_redis
-    core.workflow.nodes.llm.file_saver -> extensions.ext_database
-    core.workflow.nodes.llm.llm_utils -> extensions.ext_database
-    core.workflow.nodes.llm.node -> extensions.ext_database
-    core.workflow.nodes.tool.tool_node -> extensions.ext_database
-    core.workflow.workflow_entry -> extensions.otel.runtime
-    core.workflow.nodes.agent.agent_node -> models
-    core.workflow.nodes.base.node -> models.enums
-    core.workflow.nodes.llm.llm_utils -> models.provider_ids
-    core.workflow.nodes.llm.node -> models.model
-    core.workflow.workflow_entry -> models.enums
-    core.workflow.nodes.agent.agent_node -> services
-    core.workflow.nodes.tool.tool_node -> services
-
 [importlinter:contract:rsc]
 name = RSC
 type = layers

api/AGENTS.md

@@ -1,186 +1,62 @@
-# API Agent Guide
+# Agent Skill Index
 
-## Notes for Agent (must-check)
+Start with the section that best matches your need. Each entry lists the problems it solves plus key files/concepts so you know what to expect before opening it.
 
-Before changing any backend code under `api/`, you MUST read the surrounding docstrings and comments. These notes contain required context (invariants, edge cases, trade-offs) and are treated as part of the spec.
+______________________________________________________________________
 
-Look for:
+## Platform Foundations
 
-- The module (file) docstring at the top of a source code file
-- Docstrings on classes and functions/methods
-- Paragraph/block comments for non-obvious logic
+- **[Infrastructure Overview](agent_skills/infra.md)**\
+  When to read this:
 
-### What to write where
+  - You need to understand where a feature belongs in the architecture.
+  - You’re wiring storage, Redis, vector stores, or OTEL.
+  - You’re about to add CLI commands or async jobs.\
+    What it covers: configuration stack (`configs/app_config.py`, remote settings), storage entry points (`extensions/ext_storage.py`, `core/file/file_manager.py`), Redis conventions (`extensions/ext_redis.py`), plugin runtime topology, vector-store factory (`core/rag/datasource/vdb/*`), observability hooks, SSRF proxy usage, and core CLI commands.
 
-- Keep notes scoped: module notes cover module-wide context, class notes cover class-wide context, function/method notes cover behavioural contracts, and paragraph/block comments cover local “why”. Avoid duplicating the same content across scopes unless repetition prevents misuse.
-- **Module (file) docstring**: purpose, boundaries, key invariants, and “gotchas” that a new reader must know before editing.
-  - Include cross-links to the key collaborators (modules/services) when discovery is otherwise hard.
-  - Prefer stable facts (invariants, contracts) over ephemeral “today we…” notes.
-- **Class docstring**: responsibility, lifecycle, invariants, and how it should be used (or not used).
-  - If the class is intentionally stateful, note what state exists and what methods mutate it.
-  - If concurrency/async assumptions matter, state them explicitly.
-- **Function/method docstring**: behavioural contract.
-  - Document arguments, return shape, side effects (DB writes, external I/O, task dispatch), and raised domain exceptions.
-  - Add examples only when they prevent misuse.
-- **Paragraph/block comments**: explain *why* (trade-offs, historical constraints, surprising edge cases), not what the code already states.
-  - Keep comments adjacent to the logic they justify; delete or rewrite comments that no longer match reality.
+- **[Coding Style](agent_skills/coding_style.md)**\
+  When to read this:
 
-### Rules (must follow)
+  - You’re writing or reviewing backend code and need the authoritative checklist.
+  - You’re unsure about Pydantic validators, SQLAlchemy session usage, or logging patterns.
+  - You want the exact lint/type/test commands used in PRs.\
+    Includes: Ruff & BasedPyright commands, no-annotation policy, session examples (`with Session(db.engine, ...)`), `@field_validator` usage, logging expectations, and the rule set for file size, helpers, and package management.
 
-In this section, “notes” means module/class/function docstrings plus any relevant paragraph/block comments.
+______________________________________________________________________
 
-- **Before working**
-  - Read the notes in the area you’ll touch; treat them as part of the spec.
-  - If a docstring or comment conflicts with the current code, treat the **code as the single source of truth** and update the docstring or comment to match reality.
-  - If important intent/invariants/edge cases are missing, add them in the closest docstring or comment (module for overall scope, function for behaviour).
-- **During working**
-  - Keep the notes in sync as you discover constraints, make decisions, or change approach.
-  - If you move/rename responsibilities across modules/classes, update the affected docstrings and comments so readers can still find the “why” and the invariants.
-  - Record non-obvious edge cases, trade-offs, and the test/verification plan in the nearest docstring or comment that will stay correct.
-  - Keep the notes **coherent**: integrate new findings into the relevant docstrings and comments; avoid append-only “recent fix” / changelog-style additions.
-- **When finishing**
-  - Update the notes to reflect what changed, why, and any new edge cases/tests.
-  - Remove or rewrite any comments that could be mistaken as current guidance but no longer apply.
-  - Keep docstrings and comments concise and accurate; they are meant to prevent repeated rediscovery.
+## Plugin & Extension Development
 
-## Coding Style
+- **[Plugin Systems](agent_skills/plugin.md)**\
+  When to read this:
 
-This is the default standard for backend code in this repo. Follow it for new code and use it as the checklist when reviewing changes.
+  - You’re building or debugging a marketplace plugin.
+  - You need to know how manifests, providers, daemons, and migrations fit together.\
+    What it covers: plugin manifests (`core/plugin/entities/plugin.py`), installation/upgrade flows (`services/plugin/plugin_service.py`, CLI commands), runtime adapters (`core/plugin/impl/*` for tool/model/datasource/trigger/endpoint/agent), daemon coordination (`core/plugin/entities/plugin_daemon.py`), and how provider registries surface capabilities to the rest of the platform.
 
-### Linting & Formatting
+- **[Plugin OAuth](agent_skills/plugin_oauth.md)**\
+  When to read this:
 
-- Use Ruff for formatting and linting (follow `.ruff.toml`).
-- Keep each line under 120 characters (including spaces).
+  - You must integrate OAuth for a plugin or datasource.
+  - You’re handling credential encryption or refresh flows.\
+    Topics: credential storage, encryption helpers (`core/helper/provider_encryption.py`), OAuth client bootstrap (`services/plugin/oauth_service.py`, `services/plugin/plugin_parameter_service.py`), and how console/API layers expose the flows.
 
-### Naming Conventions
+______________________________________________________________________
 
-- Use `snake_case` for variables and functions.
-- Use `PascalCase` for classes.
-- Use `UPPER_CASE` for constants.
+## Workflow Entry & Execution
 
-### Typing & Class Layout
+- **[Trigger Concepts](agent_skills/trigger.md)**\
+  When to read this:
+  - You’re debugging why a workflow didn’t start.
+  - You’re adding a new trigger type or hook.
+  - You need to trace async execution, draft debugging, or webhook/schedule pipelines.\
+    Details: Start-node taxonomy, webhook & schedule internals (`core/workflow/nodes/trigger_*`, `services/trigger/*`), async orchestration (`services/async_workflow_service.py`, Celery queues), debug event bus, and storage/logging interactions.
 
-- Code should usually include type annotations that match the repo’s current Python version (avoid untyped public APIs and “mystery” values).
-- Prefer modern typing forms (e.g. `list[str]`, `dict[str, int]`) and avoid `Any` unless there’s a strong reason.
-- For classes, declare member variables at the top of the class body (before `__init__`) so the class shape is obvious at a glance:
+______________________________________________________________________
 
-```python
-from datetime import datetime
+## Additional Notes for Agents
 
-
-class Example:
-    user_id: str
-    created_at: datetime
-
-    def __init__(self, user_id: str, created_at: datetime) -> None:
-        self.user_id = user_id
-        self.created_at = created_at
-```
-
-### General Rules
-
-- Use Pydantic v2 conventions.
-- Use `uv` for Python package management in this repo (usually with `--project api`).
-- Prefer simple functions over small “utility classes” for lightweight helpers.
-- Avoid implementing dunder methods unless it’s clearly needed and matches existing patterns.
-- Never start long-running services as part of agent work (`uv run app.py`, `flask run`, etc.); running tests is allowed.
-- Keep files below ~800 lines; split when necessary.
-- Keep code readable and explicit—avoid clever hacks.
-
-### Architecture & Boundaries
-
-- Mirror the layered architecture: controller → service → core/domain.
-- Reuse existing helpers in `core/`, `services/`, and `libs/` before creating new abstractions.
-- Optimise for observability: deterministic control flow, clear logging, actionable errors.
-
-### Logging & Errors
-
-- Never use `print`; use a module-level logger:
-  - `logger = logging.getLogger(__name__)`
-- Include tenant/app/workflow identifiers in log context when relevant.
-- Raise domain-specific exceptions (`services/errors`, `core/errors`) and translate them into HTTP responses in controllers.
-- Log retryable events at `warning`, terminal failures at `error`.
-
-### SQLAlchemy Patterns
-
-- Models inherit from `models.base.TypeBase`; do not create ad-hoc metadata or engines.
-- Open sessions with context managers:
-
-```python
-from sqlalchemy.orm import Session
-
-with Session(db.engine, expire_on_commit=False) as session:
-    stmt = select(Workflow).where(
-        Workflow.id == workflow_id,
-        Workflow.tenant_id == tenant_id,
-    )
-    workflow = session.execute(stmt).scalar_one_or_none()
-```
-
-- Prefer SQLAlchemy expressions; avoid raw SQL unless necessary.
-- Always scope queries by `tenant_id` and protect write paths with safeguards (`FOR UPDATE`, row counts, etc.).
-- Introduce repository abstractions only for very large tables (e.g., workflow executions) or when alternative storage strategies are required.
-
-### Storage & External I/O
-
-- Access storage via `extensions.ext_storage.storage`.
-- Use `core.helper.ssrf_proxy` for outbound HTTP fetches.
-- Background tasks that touch storage must be idempotent, and should log relevant object identifiers.
-
-### Pydantic Usage
-
-- Define DTOs with Pydantic v2 models and forbid extras by default.
-- Use `@field_validator` / `@model_validator` for domain rules.
-
-Example:
-
-```python
-from pydantic import BaseModel, ConfigDict, HttpUrl, field_validator
-
-
-class TriggerConfig(BaseModel):
-    endpoint: HttpUrl
-    secret: str
-
-    model_config = ConfigDict(extra="forbid")
-
-    @field_validator("secret")
-    def ensure_secret_prefix(cls, value: str) -> str:
-        if not value.startswith("dify_"):
-            raise ValueError("secret must start with dify_")
-        return value
-```
-
-### Generics & Protocols
-
-- Use `typing.Protocol` to define behavioural contracts (e.g., cache interfaces).
-- Apply generics (`TypeVar`, `Generic`) for reusable utilities like caches or providers.
-- Validate dynamic inputs at runtime when generics cannot enforce safety alone.
-
-### Tooling & Checks
-
-Quick checks while iterating:
-
-- Format: `make format`
-- Lint (includes auto-fix): `make lint`
-- Type check: `make type-check`
-- Targeted tests: `make test TARGET_TESTS=./api/tests/<target_tests>`
-
-Before opening a PR / submitting:
-
-- `make lint`
-- `make type-check`
-- `make test`
-
-### Controllers & Services
-
-- Controllers: parse input via Pydantic, invoke services, return serialised responses; no business logic.
-- Services: coordinate repositories, providers, background tasks; keep side effects explicit.
-- Document non-obvious behaviour with concise docstrings and comments.
-
-### Miscellaneous
-
-- Use `configs.dify_config` for configuration—never read environment variables directly.
-- Maintain tenant awareness end-to-end; `tenant_id` must flow through every layer touching shared resources.
-- Queue async work through `services/async_workflow_service`; implement tasks under `tasks/` with explicit queue selection.
-- Keep experimental scripts under `dev/`; do not ship them in production builds.
+- All skill docs assume you follow the coding style guide—run Ruff/BasedPyright/tests listed there before submitting changes.
+- When you cannot find an answer in these briefs, search the codebase using the paths referenced (e.g., `core/plugin/impl/tool.py`, `services/dataset_service.py`).
+- If you run into cross-cutting concerns (tenancy, configuration, storage), check the infrastructure guide first; it links to most supporting modules.
+- Keep multi-tenancy and configuration central: everything flows through `configs.dify_config` and `tenant_id`.
+- When touching plugins or triggers, consult both the system overview and the specialised doc to ensure you adjust lifecycle, storage, and observability consistently.

api/README.md

@@ -1,6 +1,6 @@
 # Dify Backend API
 
-## Setup and Run
+## Usage
 
 > [!IMPORTANT]
 >
@@ -8,77 +8,48 @@
 > [`uv`](https://docs.astral.sh/uv/) as the package manager
 > for Dify API backend service.
 
-`uv` and `pnpm` are required to run the setup and development commands below.
+1. Start the docker-compose stack
 
-### Using scripts (recommended)
-
-The scripts resolve paths relative to their location, so you can run them from anywhere.
-
-1. Run setup (copies env files and installs dependencies).
+   The backend require some middleware, including PostgreSQL, Redis, and Weaviate, which can be started together using `docker-compose`.
 
    ```bash
-   ./dev/setup
+   cd ../docker
+   cp middleware.env.example middleware.env
+   # change the profile to mysql if you are not using postgres,change the profile to other vector database if you are not using weaviate
+   docker compose -f docker-compose.middleware.yaml --profile postgresql --profile weaviate -p dify up -d
+   cd ../api
    ```
 
-1. Review `api/.env`, `web/.env.local`, and `docker/middleware.env` values (see the `SECRET_KEY` note below).
+1. Copy `.env.example` to `.env`
 
-1. Start middleware (PostgreSQL/Redis/Weaviate).
-
-   ```bash
-   ./dev/start-docker-compose
+   ```cli
+   cp .env.example .env
    ```
 
-1. Start backend (runs migrations first).
+> [!IMPORTANT]
+>
+> When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the site’s top-level domain (e.g., `example.com`). The frontend and backend must be under the same top-level domain in order to share authentication cookies.
 
-   ```bash
-   ./dev/start-api
+1. Generate a `SECRET_KEY` in the `.env` file.
+
+   bash for Linux
+
+   ```bash for Linux
+   sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env
    ```
 
-1. Start Dify [web](../web) service.
+   bash for Mac
 
-   ```bash
-   ./dev/start-web
+   ```bash for Mac
+   secret_key=$(openssl rand -base64 42)
+   sed -i '' "/^SECRET_KEY=/c\\
+   SECRET_KEY=${secret_key}" .env
    ```
 
-1. Set up your application by visiting `http://localhost:3000`.
+1. Create environment.
 
-1. Optional: start the worker service (async tasks, runs from `api`).
-
-   ```bash
-   ./dev/start-worker
-   ```
-
-1. Optional: start Celery Beat (scheduled tasks).
-
-   ```bash
-   ./dev/start-beat
-   ```
-
-### Manual commands
-
-<details>
-<summary>Show manual setup and run steps</summary>
-
-These commands assume you start from the repository root.
-
-1. Start the docker-compose stack.
-
-   The backend requires middleware, including PostgreSQL, Redis, and Weaviate, which can be started together using `docker-compose`.
-
-   ```bash
-   cp docker/middleware.env.example docker/middleware.env
-   # Use mysql or another vector database profile if you are not using postgres/weaviate.
-   docker compose -f docker/docker-compose.middleware.yaml --profile postgresql --profile weaviate -p dify up -d
-   ```
-
-1. Copy env files.
-
-   ```bash
-   cp api/.env.example api/.env
-   cp web/.env.example web/.env.local
-   ```
-
-1. Install UV if needed.
+   Dify API service uses [UV](https://docs.astral.sh/uv/) to manage dependencies.
+   First, you need to add the uv package manager, if you don't have it already.
 
    ```bash
    pip install uv
@@ -86,96 +57,60 @@ These commands assume you start from the repository root.
    brew install uv
    ```
 
-1. Install API dependencies.
+1. Install dependencies
 
    ```bash
-   cd api
-   uv sync --group dev
+   uv sync --dev
    ```
 
-1. Install web dependencies.
+1. Run migrate
+
+   Before the first launch, migrate the database to the latest version.
 
    ```bash
-   cd web
-   pnpm install
-   cd ..
-   ```
-
-1. Start backend (runs migrations first, in a new terminal).
-
-   ```bash
-   cd api
    uv run flask db upgrade
+   ```
+
+1. Start backend
+
+   ```bash
    uv run flask run --host 0.0.0.0 --port=5001 --debug
    ```
 
-1. Start Dify [web](../web) service (in a new terminal).
+1. Start Dify [web](../web) service.
 
-   ```bash
-   cd web
-   pnpm dev:inspect
-   ```
+1. Setup your application by visiting `http://localhost:3000`.
 
-1. Set up your application by visiting `http://localhost:3000`.
+1. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.
 
-1. Optional: start the worker service (async tasks, in a new terminal).
+```bash
+uv run celery -A app.celery worker -P threads -c 2 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention
+```
 
-   ```bash
-   cd api
-   uv run celery -A app.celery worker -P threads -c 2 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor,retention
-   ```
+Additionally, if you want to debug the celery scheduled tasks, you can run the following command in another terminal to start the beat service:
 
-1. Optional: start Celery Beat (scheduled tasks, in a new terminal).
-
-   ```bash
-   cd api
-   uv run celery -A app.celery beat
-   ```
-
-</details>
-
-### Environment notes
-
-> [!IMPORTANT]
->
-> When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the site’s top-level domain (e.g., `example.com`). The frontend and backend must be under the same top-level domain in order to share authentication cookies.
-
-- Generate a `SECRET_KEY` in the `.env` file.
-
-  bash for Linux
-
-  ```bash
-  sed -i "/^SECRET_KEY=/c\\SECRET_KEY=$(openssl rand -base64 42)" .env
-  ```
-
-  bash for Mac
-
-  ```bash
-  secret_key=$(openssl rand -base64 42)
-  sed -i '' "/^SECRET_KEY=/c\\
-  SECRET_KEY=${secret_key}" .env
-  ```
+```bash
+uv run celery -A app.celery beat
+```
 
 ## Testing
 
 1. Install dependencies for both the backend and the test environment
 
    ```bash
-   cd api
-   uv sync --group dev
+   uv sync --dev
    ```
 
 1. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`, more can check [Claude.md](../CLAUDE.md)
 
    ```bash
-   cd api
    uv run pytest                           # Run all tests
    uv run pytest tests/unit_tests/         # Unit tests only
    uv run pytest tests/integration_tests/  # Integration tests
 
    # Code quality
-   ./dev/reformat               # Run all formatters and linters
-   uv run ruff check --fix ./   # Fix linting issues
-   uv run ruff format ./        # Format code
-   uv run basedpyright .        # Type checking
+   ../dev/reformat               # Run all formatters and linters
+   uv run ruff check --fix ./    # Fix linting issues
+   uv run ruff format ./         # Format code
+   uv run basedpyright .         # Type checking
    ```

api/agent_skills/coding_style.md

@@ -0,0 +1,115 @@
+## Linter
+
+- Always follow `.ruff.toml`.
+- Run `uv run ruff check --fix --unsafe-fixes`.
+- Keep each line under 100 characters (including spaces).
+
+## Code Style
+
+- `snake_case` for variables and functions.
+- `PascalCase` for classes.
+- `UPPER_CASE` for constants.
+
+## Rules
+
+- Use Pydantic v2 standard.
+- Use `uv` for package management.
+- Do not override dunder methods like `__init__`, `__iadd__`, etc.
+- Never launch services (`uv run app.py`, `flask run`, etc.); running tests under `tests/` is allowed.
+- Prefer simple functions over classes for lightweight helpers.
+- Keep files below 800 lines; split when necessary.
+- Keep code readable—no clever hacks.
+- Never use `print`; log with `logger = logging.getLogger(__name__)`.
+
+## Guiding Principles
+
+- Mirror the project’s layered architecture: controller → service → core/domain.
+- Reuse existing helpers in `core/`, `services/`, and `libs/` before creating new abstractions.
+- Optimise for observability: deterministic control flow, clear logging, actionable errors.
+
+## SQLAlchemy Patterns
+
+- Models inherit from `models.base.Base`; never create ad-hoc metadata or engines.
+
+- Open sessions with context managers:
+
+  ```python
+  from sqlalchemy.orm import Session
+
+  with Session(db.engine, expire_on_commit=False) as session:
+      stmt = select(Workflow).where(
+          Workflow.id == workflow_id,
+          Workflow.tenant_id == tenant_id,
+      )
+      workflow = session.execute(stmt).scalar_one_or_none()
+  ```
+
+- Use SQLAlchemy expressions; avoid raw SQL unless necessary.
+
+- Introduce repository abstractions only for very large tables (e.g., workflow executions) to support alternative storage strategies.
+
+- Always scope queries by `tenant_id` and protect write paths with safeguards (`FOR UPDATE`, row counts, etc.).
+
+## Storage & External IO
+
+- Access storage via `extensions.ext_storage.storage`.
+- Use `core.helper.ssrf_proxy` for outbound HTTP fetches.
+- Background tasks that touch storage must be idempotent and log the relevant object identifiers.
+
+## Pydantic Usage
+
+- Define DTOs with Pydantic v2 models and forbid extras by default.
+
+- Use `@field_validator` / `@model_validator` for domain rules.
+
+- Example:
+
+  ```python
+  from pydantic import BaseModel, ConfigDict, HttpUrl, field_validator
+
+  class TriggerConfig(BaseModel):
+      endpoint: HttpUrl
+      secret: str
+
+      model_config = ConfigDict(extra="forbid")
+
+      @field_validator("secret")
+      def ensure_secret_prefix(cls, value: str) -> str:
+          if not value.startswith("dify_"):
+              raise ValueError("secret must start with dify_")
+          return value
+  ```
+
+## Generics & Protocols
+
+- Use `typing.Protocol` to define behavioural contracts (e.g., cache interfaces).
+- Apply generics (`TypeVar`, `Generic`) for reusable utilities like caches or providers.
+- Validate dynamic inputs at runtime when generics cannot enforce safety alone.
+
+## Error Handling & Logging
+
+- Raise domain-specific exceptions (`services/errors`, `core/errors`) and translate to HTTP responses in controllers.
+- Declare `logger = logging.getLogger(__name__)` at module top.
+- Include tenant/app/workflow identifiers in log context.
+- Log retryable events at `warning`, terminal failures at `error`.
+
+## Tooling & Checks
+
+- Format/lint: `uv run --project api --dev ruff format ./api` and `uv run --project api --dev ruff check --fix --unsafe-fixes ./api`.
+- Type checks: `uv run --directory api --dev basedpyright`.
+- Tests: `uv run --project api --dev dev/pytest/pytest_unit_tests.sh`.
+- Run all of the above before submitting your work.
+
+## Controllers & Services
+
+- Controllers: parse input via Pydantic, invoke services, return serialised responses; no business logic.
+- Services: coordinate repositories, providers, background tasks; keep side effects explicit.
+- Avoid repositories unless necessary; direct SQLAlchemy usage is preferred for typical tables.
+- Document non-obvious behaviour with concise comments.
+
+## Miscellaneous
+
+- Use `configs.dify_config` for configuration—never read environment variables directly.
+- Maintain tenant awareness end-to-end; `tenant_id` must flow through every layer touching shared resources.
+- Queue async work through `services/async_workflow_service`; implement tasks under `tasks/` with explicit queue selection.
+- Keep experimental scripts under `dev/`; do not ship them in production builds.

api/agent_skills/infra.md

@@ -0,0 +1,96 @@
+## Configuration
+
+- Import `configs.dify_config` for every runtime toggle. Do not read environment variables directly.
+- Add new settings to the proper mixin inside `configs/` (deployment, feature, middleware, etc.) so they load through `DifyConfig`.
+- Remote overrides come from the optional providers in `configs/remote_settings_sources`; keep defaults in code safe when the value is missing.
+- Example: logging pulls targets from `extensions/ext_logging.py`, and model provider URLs are assembled in `services/entities/model_provider_entities.py`.
+
+## Dependencies
+
+- Runtime dependencies live in `[project].dependencies` inside `pyproject.toml`. Optional clients go into the `storage`, `tools`, or `vdb` groups under `[dependency-groups]`.
+- Always pin versions and keep the list alphabetised. Shared tooling (lint, typing, pytest) belongs in the `dev` group.
+- When code needs a new package, explain why in the PR and run `uv lock` so the lockfile stays current.
+
+## Storage & Files
+
+- Use `extensions.ext_storage.storage` for all blob IO; it already respects the configured backend.
+- Convert files for workflows with helpers in `core/file/file_manager.py`; they handle signed URLs and multimodal payloads.
+- When writing controller logic, delegate upload quotas and metadata to `services/file_service.py` instead of touching storage directly.
+- All outbound HTTP fetches (webhooks, remote files) must go through the SSRF-safe client in `core/helper/ssrf_proxy.py`; it wraps `httpx` with the allow/deny rules configured for the platform.
+
+## Redis & Shared State
+
+- Access Redis through `extensions.ext_redis.redis_client`. For locking, reuse `redis_client.lock`.
+- Prefer higher-level helpers when available: rate limits use `libs.helper.RateLimiter`, provider metadata uses caches in `core/helper/provider_cache.py`.
+
+## Models
+
+- SQLAlchemy models sit in `models/` and inherit from the shared declarative `Base` defined in `models/base.py` (metadata configured via `models/engine.py`).
+- `models/__init__.py` exposes grouped aggregates: account/tenant models, app and conversation tables, datasets, providers, workflow runs, triggers, etc. Import from there to avoid deep path churn.
+- Follow the DDD boundary: persistence objects live in `models/`, repositories under `repositories/` translate them into domain entities, and services consume those repositories.
+- When adding a table, create the model class, register it in `models/__init__.py`, wire a repository if needed, and generate an Alembic migration as described below.
+
+## Vector Stores
+
+- Vector client implementations live in `core/rag/datasource/vdb/<provider>`, with a common factory in `core/rag/datasource/vdb/vector_factory.py` and enums in `core/rag/datasource/vdb/vector_type.py`.
+- Retrieval pipelines call these providers through `core/rag/datasource/retrieval_service.py` and dataset ingestion flows in `services/dataset_service.py`.
+- The CLI helper `flask vdb-migrate` orchestrates bulk migrations using routines in `commands.py`; reuse that pattern when adding new backend transitions.
+- To add another store, mirror the provider layout, register it with the factory, and include any schema changes in Alembic migrations.
+
+## Observability & OTEL
+
+- OpenTelemetry settings live under the observability mixin in `configs/observability`. Toggle exporters and sampling via `dify_config`, not ad-hoc env reads.
+- HTTP, Celery, Redis, SQLAlchemy, and httpx instrumentation is initialised in `extensions/ext_app_metrics.py` and `extensions/ext_request_logging.py`; reuse these hooks when adding new workers or entrypoints.
+- When creating background tasks or external calls, propagate tracing context with helpers in the existing instrumented clients (e.g. use the shared `httpx` session from `core/helper/http_client_pooling.py`).
+- If you add a new external integration, ensure spans and metrics are emitted by wiring the appropriate OTEL instrumentation package in `pyproject.toml` and configuring it in `extensions/`.
+
+## Ops Integrations
+
+- Langfuse support and other tracing bridges live under `core/ops/opik_trace`. Config toggles sit in `configs/observability`, while exporters are initialised in the OTEL extensions mentioned above.
+- External monitoring services should follow this pattern: keep client code in `core/ops`, expose switches via `dify_config`, and hook initialisation in `extensions/ext_app_metrics.py` or sibling modules.
+- Before instrumenting new code paths, check whether existing context helpers (e.g. `extensions/ext_request_logging.py`) already capture the necessary metadata.
+
+## Controllers, Services, Core
+
+- Controllers only parse HTTP input and call a service method. Keep business rules in `services/`.
+- Services enforce tenant rules, quotas, and orchestration, then call into `core/` engines (workflow execution, tools, LLMs).
+- When adding a new endpoint, search for an existing service to extend before introducing a new layer. Example: workflow APIs pipe through `services/workflow_service.py` into `core/workflow`.
+
+## Plugins, Tools, Providers
+
+- In Dify a plugin is a tenant-installable bundle that declares one or more providers (tool, model, datasource, trigger, endpoint, agent strategy) plus its resource needs and version metadata. The manifest (`core/plugin/entities/plugin.py`) mirrors what you see in the marketplace documentation.
+- Installation, upgrades, and migrations are orchestrated by `services/plugin/plugin_service.py` together with helpers such as `services/plugin/plugin_migration.py`.
+- Runtime loading happens through the implementations under `core/plugin/impl/*` (tool/model/datasource/trigger/endpoint/agent). These modules normalise plugin providers so that downstream systems (`core/tools/tool_manager.py`, `services/model_provider_service.py`, `services/trigger/*`) can treat builtin and plugin capabilities the same way.
+- For remote execution, plugin daemons (`core/plugin/entities/plugin_daemon.py`, `core/plugin/impl/plugin.py`) manage lifecycle hooks, credential forwarding, and background workers that keep plugin processes in sync with the main application.
+- Acquire tool implementations through `core/tools/tool_manager.py`; it resolves builtin, plugin, and workflow-as-tool providers uniformly, injecting the right context (tenant, credentials, runtime config).
+- To add a new plugin capability, extend the relevant `core/plugin/entities` schema and register the implementation in the matching `core/plugin/impl` module rather than importing the provider directly.
+
+## Async Workloads
+
+see `agent_skills/trigger.md` for more detailed documentation.
+
+- Enqueue background work through `services/async_workflow_service.py`. It routes jobs to the tiered Celery queues defined in `tasks/`.
+- Workers boot from `celery_entrypoint.py` and execute functions in `tasks/workflow_execution_tasks.py`, `tasks/trigger_processing_tasks.py`, etc.
+- Scheduled workflows poll from `schedule/workflow_schedule_tasks.py`. Follow the same pattern if you need new periodic jobs.
+
+## Database & Migrations
+
+- SQLAlchemy models live under `models/` and map directly to migration files in `migrations/versions`.
+- Generate migrations with `uv run --project api flask db revision --autogenerate -m "<summary>"`, then review the diff; never hand-edit the database outside Alembic.
+- Apply migrations locally using `uv run --project api flask db upgrade`; production deploys expect the same history.
+- If you add tenant-scoped data, confirm the upgrade includes tenant filters or defaults consistent with the service logic touching those tables.
+
+## CLI Commands
+
+- Maintenance commands from `commands.py` are registered on the Flask CLI. Run them via `uv run --project api flask <command>`.
+- Use the built-in `db` commands from Flask-Migrate for schema operations (`flask db upgrade`, `flask db stamp`, etc.). Only fall back to custom helpers if you need their extra behaviour.
+- Custom entries such as `flask reset-password`, `flask reset-email`, and `flask vdb-migrate` handle self-hosted account recovery and vector database migrations.
+- Before adding a new command, check whether an existing service can be reused and ensure the command guards edition-specific behaviour (many enforce `SELF_HOSTED`). Document any additions in the PR.
+- Ruff helpers are run directly with `uv`: `uv run --project api --dev ruff format ./api` for formatting and `uv run --project api --dev ruff check ./api` (add `--fix` if you want automatic fixes).
+
+## When You Add Features
+
+- Check for an existing helper or service before writing a new util.
+- Uphold tenancy: every service method should receive the tenant ID from controller wrappers such as `controllers/console/wraps.py`.
+- Update or create tests alongside behaviour changes (`tests/unit_tests` for fast coverage, `tests/integration_tests` when touching orchestrations).
+- Run `uv run --project api --dev ruff check ./api`, `uv run --directory api --dev basedpyright`, and `uv run --project api --dev dev/pytest/pytest_unit_tests.sh` before submitting changes.

api/agent_skills/plugin.md

@@ -0,0 +1 @@
+// TBD

api/agent_skills/plugin_oauth.md

@@ -0,0 +1 @@
+// TBD

api/agent_skills/trigger.md

@@ -0,0 +1,53 @@
+## Overview
+
+Trigger is a collection of nodes that we called `Start` nodes, also, the concept of `Start` is the same as `RootNode` in the workflow engine `core/workflow/graph_engine`, On the other hand, `Start` node is the entry point of workflows, every workflow run always starts from a `Start` node.
+
+## Trigger nodes
+
+- `UserInput`
+- `Trigger Webhook`
+- `Trigger Schedule`
+- `Trigger Plugin`
+
+### UserInput
+
+Before `Trigger` concept is introduced, it's what we called `Start` node, but now, to avoid confusion, it was renamed to `UserInput` node, has a strong relation with `ServiceAPI` in `controllers/service_api/app`
+
+1. `UserInput` node introduces a list of arguments that need to be provided by the user, finally it will be converted into variables in the workflow variable pool.
+1. `ServiceAPI` accept those arguments, and pass through them into `UserInput` node.
+1. For its detailed implementation, please refer to `core/workflow/nodes/start`
+
+### Trigger Webhook
+
+Inside Webhook Node, Dify provided a UI panel that allows user define a HTTP manifest `core/workflow/nodes/trigger_webhook/entities.py`.`WebhookData`, also, Dify generates a random webhook id for each `Trigger Webhook` node, the implementation was implemented in `core/trigger/utils/endpoint.py`, as you can see, `webhook-debug` is a debug mode for webhook, you may find it in `controllers/trigger/webhook.py`.
+
+Finally, requests to `webhook` endpoint will be converted into variables in workflow variable pool during workflow execution.
+
+### Trigger Schedule
+
+`Trigger Schedule` node is a node that allows user define a schedule to trigger the workflow, detailed manifest is here `core/workflow/nodes/trigger_schedule/entities.py`, we have a poller and executor to handle millions of schedules, see `docker/entrypoint.sh` / `schedule/workflow_schedule_task.py` for help.
+
+To Achieve this, a `WorkflowSchedulePlan` model was introduced in `models/trigger.py`, and a `events/event_handlers/sync_workflow_schedule_when_app_published.py` was used to sync workflow schedule plans when app is published.
+
+### Trigger Plugin
+
+`Trigger Plugin` node allows user define there own distributed trigger plugin, whenever a request was received, Dify forwards it to the plugin and wait for parsed variables from it.
+
+1. Requests were saved in storage by `services/trigger/trigger_request_service.py`, referenced by `services/trigger/trigger_service.py`.`TriggerService`.`process_endpoint`
+1. Plugins accept those requests and parse variables from it, see `core/plugin/impl/trigger.py` for details.
+
+A `subscription` concept was out here by Dify, it means an endpoint address from Dify was bound to thirdparty webhook service like `Github` `Slack` `Linear` `GoogleDrive` `Gmail` etc. Once a subscription was created, Dify continually receives requests from the platforms and handle them one by one.
+
+## Worker Pool / Async Task
+
+All the events that triggered a new workflow run is always in async mode, a unified entrypoint can be found here `services/async_workflow_service.py`.`AsyncWorkflowService`.`trigger_workflow_async`.
+
+The infrastructure we used is `celery`, we've already configured it in `docker/entrypoint.sh`, and the consumers are in `tasks/async_workflow_tasks.py`, 3 queues were used to handle different tiers of users, `PROFESSIONAL_QUEUE` `TEAM_QUEUE` `SANDBOX_QUEUE`.
+
+## Debug Strategy
+
+Dify divided users into 2 groups: builders / end users.
+
+Builders are the users who create workflows, in this stage, debugging a workflow becomes a critical part of the workflow development process, as the start node in workflows, trigger nodes can `listen` to the events from `WebhookDebug` `Schedule` `Plugin`, debugging process was created in `controllers/console/app/workflow.py`.`DraftWorkflowTriggerNodeApi`.
+
+A polling process can be considered as combine of few single `poll` operations, each `poll` operation fetches events cached in `Redis`, returns `None` if no event was found, more detailed implemented: `core/trigger/debug/event_bus.py` was used to handle the polling process, and `core/trigger/debug/event_selectors.py` was used to select the event poller based on the trigger type.

api/app_factory.py

@@ -71,8 +71,6 @@ 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,
@@ -81,7 +79,6 @@ def initialize_extensions(app: DifyApp):
         ext_commands,
         ext_compress,
         ext_database,
-        ext_fastopenapi,
         ext_forward_refs,
         ext_hosting_provider,
         ext_import_modules,
@@ -103,8 +100,6 @@ def initialize_extensions(app: DifyApp):
         ext_warnings,
     )
 
-    init_flask_context()
-
     extensions = [
         ext_timezone,
         ext_logging,
@@ -129,7 +124,6 @@ def initialize_extensions(app: DifyApp):
         ext_proxy_fix,
         ext_blueprints,
         ext_commands,
-        ext_fastopenapi,
         ext_otel,
         ext_request_logging,
         ext_session_factory,

api/commands.py

@@ -1,9 +1,7 @@
 import base64
-import datetime
 import json
 import logging
 import secrets
-import time
 from typing import Any
 
 import click
@@ -22,7 +20,7 @@ from core.plugin.impl.plugin import PluginInstaller
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.index_processor.constant.built_in_field import BuiltInField
-from core.rag.models.document import ChildDocument, Document
+from core.rag.models.document import Document
 from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_params
 from events.app_event import app_was_created
 from extensions.ext_database import db
@@ -36,7 +34,7 @@ from libs.rsa import generate_key_pair
 from models import Tenant
 from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, DatasetMetadataBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
-from models.model import App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation, UploadFile
+from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation, UploadFile
 from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
 from models.provider import Provider, ProviderModel
 from models.provider_ids import DatasourceProviderID, ToolProviderID
@@ -47,9 +45,6 @@ from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpi
 from services.plugin.data_migration import PluginDataMigration
 from services.plugin.plugin_migration import PluginMigration
 from services.plugin.plugin_service import PluginService
-from services.retention.conversation.messages_clean_policy import create_message_clean_policy
-from services.retention.conversation.messages_clean_service import MessagesCleanService
-from services.retention.workflow_run.clear_free_plan_expired_workflow_run_logs import WorkflowRunCleanup
 from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 
 logger = logging.getLogger(__name__)
@@ -67,10 +62,8 @@ def reset_password(email, new_password, password_confirm):
     if str(new_password).strip() != str(password_confirm).strip():
         click.echo(click.style("Passwords do not match.", fg="red"))
         return
-    normalized_email = email.strip().lower()
-
     with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
-        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
         if not account:
             click.echo(click.style(f"Account not found for email: {email}", fg="red"))
@@ -91,7 +84,7 @@ def reset_password(email, new_password, password_confirm):
         base64_password_hashed = base64.b64encode(password_hashed).decode()
         account.password = base64_password_hashed
         account.password_salt = base64_salt
-        AccountService.reset_login_error_rate_limit(normalized_email)
+        AccountService.reset_login_error_rate_limit(email)
         click.echo(click.style("Password reset successfully.", fg="green"))
 
 
@@ -107,22 +100,20 @@ def reset_email(email, new_email, email_confirm):
     if str(new_email).strip() != str(email_confirm).strip():
         click.echo(click.style("New emails do not match.", fg="red"))
         return
-    normalized_new_email = new_email.strip().lower()
-
     with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
-        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
         if not account:
             click.echo(click.style(f"Account not found for email: {email}", fg="red"))
             return
 
         try:
-            email_validate(normalized_new_email)
+            email_validate(new_email)
         except:
             click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
             return
 
-        account.email = normalized_new_email
+        account.email = new_email
         click.echo(click.style("Email updated successfully.", fg="green"))
 
 
@@ -418,22 +409,6 @@ def migrate_knowledge_vector_database():
                                 "dataset_id": segment.dataset_id,
                             },
                         )
-                        if dataset_document.doc_form == "hierarchical_model":
-                            child_chunks = segment.get_child_chunks()
-                            if child_chunks:
-                                child_documents = []
-                                for child_chunk in child_chunks:
-                                    child_document = ChildDocument(
-                                        page_content=child_chunk.content,
-                                        metadata={
-                                            "doc_id": child_chunk.index_node_id,
-                                            "doc_hash": child_chunk.index_node_hash,
-                                            "document_id": segment.document_id,
-                                            "dataset_id": segment.dataset_id,
-                                        },
-                                    )
-                                    child_documents.append(child_document)
-                                document.children = child_documents
 
                         documents.append(document)
                         segments_count = segments_count + 1
@@ -447,13 +422,7 @@ def migrate_knowledge_vector_database():
                                 fg="green",
                             )
                         )
-                        all_child_documents = []
-                        for doc in documents:
-                            if doc.children:
-                                all_child_documents.extend(doc.children)
                         vector.create(documents)
-                        if all_child_documents:
-                            vector.create(all_child_documents)
                         click.echo(click.style(f"Created vector index for dataset {dataset.id}.", fg="green"))
                     except Exception as e:
                         click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
@@ -689,7 +658,7 @@ def create_tenant(email: str, language: str | None = None, name: str | None = No
         return
 
     # Create account
-    email = email.strip().lower()
+    email = email.strip()
 
     if "@" not in email:
         click.echo(click.style("Invalid email address.", fg="red"))
@@ -883,435 +852,6 @@ def clear_free_plan_tenant_expired_logs(days: int, batch: int, tenant_ids: list[
     click.echo(click.style("Clear free plan tenant expired logs completed.", fg="green"))
 
 
-@click.command("clean-workflow-runs", help="Clean expired workflow runs and related data for free tenants.")
-@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"]),
-    default=None,
-    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
-)
-@click.option(
-    "--end-before",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
-)
-@click.option(
-    "--dry-run",
-    is_flag=True,
-    help="Preview cleanup results without deleting any workflow run data.",
-)
-def clean_workflow_runs(
-    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,
-):
-    """
-    Clean workflow runs and related workflow data for free tenants.
-    """
-    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=before_days,
-        batch_size=batch_size,
-        start_from=start_from,
-        end_before=end_before,
-        dry_run=dry_run,
-    ).run()
-
-    end_time = datetime.datetime.now(datetime.UTC)
-    elapsed = end_time - start_time
-    click.echo(
-        click.style(
-            f"Workflow run cleanup completed. start={start_time.isoformat()} "
-            f"end={end_time.isoformat()} duration={elapsed}",
-            fg="green",
-        )
-    )
-
-
-@click.command(
-    "archive-workflow-runs",
-    help="Archive workflow runs for paid plan tenants to S3-compatible storage.",
-)
-@click.option("--tenant-ids", default=None, help="Optional comma-separated tenant IDs for grayscale rollout.")
-@click.option("--before-days", default=90, show_default=True, help="Archive runs older than N days.")
-@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"]),
-    default=None,
-    help="Archive runs created at or after this timestamp (UTC if no timezone).",
-)
-@click.option(
-    "--end-before",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Archive runs created before this timestamp (UTC if no timezone).",
-)
-@click.option("--batch-size", default=100, show_default=True, help="Batch size for processing.")
-@click.option("--workers", default=1, show_default=True, type=int, help="Concurrent workflow runs to archive.")
-@click.option("--limit", default=None, type=int, help="Maximum number of runs to archive.")
-@click.option("--dry-run", is_flag=True, help="Preview without archiving.")
-@click.option("--delete-after-archive", is_flag=True, help="Delete runs and related data after archiving.")
-def archive_workflow_runs(
-    tenant_ids: str | None,
-    before_days: int,
-    from_days_ago: int | None,
-    to_days_ago: int | None,
-    start_from: datetime.datetime | None,
-    end_before: datetime.datetime | None,
-    batch_size: int,
-    workers: int,
-    limit: int | None,
-    dry_run: bool,
-    delete_after_archive: bool,
-):
-    """
-    Archive workflow runs for paid plan tenants older than the specified days.
-
-    This command archives the following tables to storage:
-    - workflow_node_executions
-    - workflow_node_execution_offload
-    - workflow_pauses
-    - workflow_pause_reasons
-    - workflow_trigger_logs
-
-    The workflow_runs and workflow_app_logs tables are preserved for UI listing.
-    """
-    from services.retention.workflow_run.archive_paid_plan_workflow_run import WorkflowRunArchiver
-
-    run_started_at = datetime.datetime.now(datetime.UTC)
-    click.echo(
-        click.style(
-            f"Starting workflow run archiving at {run_started_at.isoformat()}.",
-            fg="white",
-        )
-    )
-
-    if (start_from is None) ^ (end_before is None):
-        click.echo(click.style("start-from and end-before must be provided together.", fg="red"))
-        return
-
-    if (from_days_ago is None) ^ (to_days_ago is None):
-        click.echo(click.style("from-days-ago and to-days-ago must be provided together.", fg="red"))
-        return
-
-    if from_days_ago is not None and to_days_ago is not None:
-        if start_from or end_before:
-            click.echo(click.style("Choose either day offsets or explicit dates, not both.", fg="red"))
-            return
-        if from_days_ago <= to_days_ago:
-            click.echo(click.style("from-days-ago must be greater than to-days-ago.", fg="red"))
-            return
-        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
-
-    if start_from and end_before and start_from >= end_before:
-        click.echo(click.style("start-from must be earlier than end-before.", fg="red"))
-        return
-    if workers < 1:
-        click.echo(click.style("workers must be at least 1.", fg="red"))
-        return
-
-    archiver = WorkflowRunArchiver(
-        days=before_days,
-        batch_size=batch_size,
-        start_from=start_from,
-        end_before=end_before,
-        workers=workers,
-        tenant_ids=[tid.strip() for tid in tenant_ids.split(",")] if tenant_ids else None,
-        limit=limit,
-        dry_run=dry_run,
-        delete_after_archive=delete_after_archive,
-    )
-    summary = archiver.run()
-    click.echo(
-        click.style(
-            f"Summary: processed={summary.total_runs_processed}, archived={summary.runs_archived}, "
-            f"skipped={summary.runs_skipped}, failed={summary.runs_failed}, "
-            f"time={summary.total_elapsed_time:.2f}s",
-            fg="cyan",
-        )
-    )
-
-    run_finished_at = datetime.datetime.now(datetime.UTC)
-    elapsed = run_finished_at - run_started_at
-    click.echo(
-        click.style(
-            f"Workflow run archiving completed. start={run_started_at.isoformat()} "
-            f"end={run_finished_at.isoformat()} duration={elapsed}",
-            fg="green",
-        )
-    )
-
-
-@click.command(
-    "restore-workflow-runs",
-    help="Restore archived workflow runs from S3-compatible storage.",
-)
-@click.option(
-    "--tenant-ids",
-    required=False,
-    help="Tenant IDs (comma-separated).",
-)
-@click.option("--run-id", required=False, help="Workflow run ID to restore.")
-@click.option(
-    "--start-from",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
-)
-@click.option(
-    "--end-before",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
-)
-@click.option("--workers", default=1, show_default=True, type=int, help="Concurrent workflow runs to restore.")
-@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of runs to restore.")
-@click.option("--dry-run", is_flag=True, help="Preview without restoring.")
-def restore_workflow_runs(
-    tenant_ids: str | None,
-    run_id: str | None,
-    start_from: datetime.datetime | None,
-    end_before: datetime.datetime | None,
-    workers: int,
-    limit: int,
-    dry_run: bool,
-):
-    """
-    Restore an archived workflow run from storage to the database.
-
-    This restores the following tables:
-    - workflow_node_executions
-    - workflow_node_execution_offload
-    - workflow_pauses
-    - workflow_pause_reasons
-    - workflow_trigger_logs
-    """
-    from services.retention.workflow_run.restore_archived_workflow_run import WorkflowRunRestore
-
-    parsed_tenant_ids = None
-    if tenant_ids:
-        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
-        if not parsed_tenant_ids:
-            raise click.BadParameter("tenant-ids must not be empty")
-
-    if (start_from is None) ^ (end_before is None):
-        raise click.UsageError("--start-from and --end-before must be provided together.")
-    if run_id is None and (start_from is None or end_before is None):
-        raise click.UsageError("--start-from and --end-before are required for batch restore.")
-    if workers < 1:
-        raise click.BadParameter("workers must be at least 1")
-
-    start_time = datetime.datetime.now(datetime.UTC)
-    click.echo(
-        click.style(
-            f"Starting restore of workflow run {run_id} at {start_time.isoformat()}.",
-            fg="white",
-        )
-    )
-
-    restorer = WorkflowRunRestore(dry_run=dry_run, workers=workers)
-    if run_id:
-        results = [restorer.restore_by_run_id(run_id)]
-    else:
-        assert start_from is not None
-        assert end_before is not None
-        results = restorer.restore_batch(
-            parsed_tenant_ids,
-            start_date=start_from,
-            end_date=end_before,
-            limit=limit,
-        )
-
-    end_time = datetime.datetime.now(datetime.UTC)
-    elapsed = end_time - start_time
-
-    successes = sum(1 for result in results if result.success)
-    failures = len(results) - successes
-
-    if failures == 0:
-        click.echo(
-            click.style(
-                f"Restore completed successfully. success={successes} duration={elapsed}",
-                fg="green",
-            )
-        )
-    else:
-        click.echo(
-            click.style(
-                f"Restore completed with failures. success={successes} failed={failures} duration={elapsed}",
-                fg="red",
-            )
-        )
-
-
-@click.command(
-    "delete-archived-workflow-runs",
-    help="Delete archived workflow runs from the database.",
-)
-@click.option(
-    "--tenant-ids",
-    required=False,
-    help="Tenant IDs (comma-separated).",
-)
-@click.option("--run-id", required=False, help="Workflow run ID to delete.")
-@click.option(
-    "--start-from",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Optional lower bound (inclusive) for created_at; must be paired with --end-before.",
-)
-@click.option(
-    "--end-before",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    default=None,
-    help="Optional upper bound (exclusive) for created_at; must be paired with --start-from.",
-)
-@click.option("--limit", type=int, default=100, show_default=True, help="Maximum number of runs to delete.")
-@click.option("--dry-run", is_flag=True, help="Preview without deleting.")
-def delete_archived_workflow_runs(
-    tenant_ids: str | None,
-    run_id: str | None,
-    start_from: datetime.datetime | None,
-    end_before: datetime.datetime | None,
-    limit: int,
-    dry_run: bool,
-):
-    """
-    Delete archived workflow runs from the database.
-    """
-    from services.retention.workflow_run.delete_archived_workflow_run import ArchivedWorkflowRunDeletion
-
-    parsed_tenant_ids = None
-    if tenant_ids:
-        parsed_tenant_ids = [tid.strip() for tid in tenant_ids.split(",") if tid.strip()]
-        if not parsed_tenant_ids:
-            raise click.BadParameter("tenant-ids must not be empty")
-
-    if (start_from is None) ^ (end_before is None):
-        raise click.UsageError("--start-from and --end-before must be provided together.")
-    if run_id is None and (start_from is None or end_before is None):
-        raise click.UsageError("--start-from and --end-before are required for batch delete.")
-
-    start_time = datetime.datetime.now(datetime.UTC)
-    target_desc = f"workflow run {run_id}" if run_id else "workflow runs"
-    click.echo(
-        click.style(
-            f"Starting delete of {target_desc} at {start_time.isoformat()}.",
-            fg="white",
-        )
-    )
-
-    deleter = ArchivedWorkflowRunDeletion(dry_run=dry_run)
-    if run_id:
-        results = [deleter.delete_by_run_id(run_id)]
-    else:
-        assert start_from is not None
-        assert end_before is not None
-        results = deleter.delete_batch(
-            parsed_tenant_ids,
-            start_date=start_from,
-            end_date=end_before,
-            limit=limit,
-        )
-
-    for result in results:
-        if result.success:
-            click.echo(
-                click.style(
-                    f"{'[DRY RUN] Would delete' if dry_run else 'Deleted'} "
-                    f"workflow run {result.run_id} (tenant={result.tenant_id})",
-                    fg="green",
-                )
-            )
-        else:
-            click.echo(
-                click.style(
-                    f"Failed to delete workflow run {result.run_id}: {result.error}",
-                    fg="red",
-                )
-            )
-
-    end_time = datetime.datetime.now(datetime.UTC)
-    elapsed = end_time - start_time
-
-    successes = sum(1 for result in results if result.success)
-    failures = len(results) - successes
-
-    if failures == 0:
-        click.echo(
-            click.style(
-                f"Delete completed successfully. success={successes} duration={elapsed}",
-                fg="green",
-            )
-        )
-    else:
-        click.echo(
-            click.style(
-                f"Delete completed with failures. success={successes} failed={failures} duration={elapsed}",
-                fg="red",
-            )
-        )
-
-
 @click.option("-f", "--force", is_flag=True, help="Skip user confirmation and force the command to execute.")
 @click.command("clear-orphaned-file-records", help="Clear orphaned file records.")
 def clear_orphaned_file_records(force: bool):
@@ -2571,79 +2111,3 @@ def migrate_oss(
             except Exception as e:
                 db.session.rollback()
                 click.echo(click.style(f"Failed to update DB storage_type: {str(e)}", fg="red"))
-
-
-@click.command("clean-expired-messages", help="Clean expired messages.")
-@click.option(
-    "--start-from",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    required=True,
-    help="Lower bound (inclusive) for created_at.",
-)
-@click.option(
-    "--end-before",
-    type=click.DateTime(formats=["%Y-%m-%d", "%Y-%m-%dT%H:%M:%S"]),
-    required=True,
-    help="Upper bound (exclusive) for created_at.",
-)
-@click.option("--batch-size", default=1000, show_default=True, help="Batch size for selecting messages.")
-@click.option(
-    "--graceful-period",
-    default=21,
-    show_default=True,
-    help="Graceful period in days after subscription expiration, will be ignored when billing is disabled.",
-)
-@click.option("--dry-run", is_flag=True, default=False, help="Show messages logs would be cleaned without deleting")
-def clean_expired_messages(
-    batch_size: int,
-    graceful_period: int,
-    start_from: datetime.datetime,
-    end_before: datetime.datetime,
-    dry_run: bool,
-):
-    """
-    Clean expired messages and related data for tenants based on clean policy.
-    """
-    click.echo(click.style("clean_messages: start clean messages.", fg="green"))
-
-    start_at = time.perf_counter()
-
-    try:
-        # Create policy based on billing configuration
-        # NOTE: graceful_period will be ignored when billing is disabled.
-        policy = create_message_clean_policy(graceful_period_days=graceful_period)
-
-        # Create and run the cleanup service
-        service = MessagesCleanService.from_time_range(
-            policy=policy,
-            start_from=start_from,
-            end_before=end_before,
-            batch_size=batch_size,
-            dry_run=dry_run,
-        )
-        stats = service.run()
-
-        end_at = time.perf_counter()
-        click.echo(
-            click.style(
-                f"clean_messages: completed successfully\n"
-                f"  - Latency: {end_at - start_at:.2f}s\n"
-                f"  - Batches processed: {stats['batches']}\n"
-                f"  - Total messages scanned: {stats['total_messages']}\n"
-                f"  - Messages filtered: {stats['filtered_messages']}\n"
-                f"  - Messages deleted: {stats['total_deleted']}",
-                fg="green",
-            )
-        )
-    except Exception as e:
-        end_at = time.perf_counter()
-        logger.exception("clean_messages failed")
-        click.echo(
-            click.style(
-                f"clean_messages: failed after {end_at - start_at:.2f}s - {str(e)}",
-                fg="red",
-            )
-        )
-        raise
-
-    click.echo(click.style("messages cleanup completed.", fg="green"))

api/configs/feature/__init__.py

@@ -949,12 +949,6 @@ class MailConfig(BaseSettings):
         default=False,
     )
 
-    SMTP_LOCAL_HOSTNAME: str | None = Field(
-        description="Override the local hostname used in SMTP HELO/EHLO. "
-        "Useful behind NAT or when the default hostname causes rejections.",
-        default=None,
-    )
-
     EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
         description="Maximum number of emails allowed to be sent from the same IP address in a minute",
         default=50,
@@ -965,16 +959,6 @@ class MailConfig(BaseSettings):
         default=None,
     )
 
-    ENABLE_TRIAL_APP: bool = Field(
-        description="Enable trial app",
-        default=False,
-    )
-
-    ENABLE_EXPLORE_BANNER: bool = Field(
-        description="Enable explore banner",
-        default=False,
-    )
-
 
 class RagEtlConfig(BaseSettings):
     """
@@ -1117,10 +1101,6 @@ class CeleryScheduleTasksConfig(BaseSettings):
         description="Enable clean messages task",
         default=False,
     )
-    ENABLE_WORKFLOW_RUN_CLEANUP_TASK: bool = Field(
-        description="Enable scheduled workflow run cleanup task",
-        default=False,
-    )
     ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK: bool = Field(
         description="Enable mail clean document notify task",
         default=False,
@@ -1308,10 +1288,6 @@ class SandboxExpiredRecordsCleanConfig(BaseSettings):
         description="Retention days for sandbox expired workflow_run records and message records",
         default=30,
     )
-    SANDBOX_EXPIRED_RECORDS_CLEAN_TASK_LOCK_TTL: PositiveInt = Field(
-        description="Lock TTL for sandbox expired records clean task in seconds",
-        default=90000,
-    )
 
 
 class FeatureConfig(

api/configs/feature/hosted_service/__init__.py

@@ -8,11 +8,6 @@ class HostedCreditConfig(BaseSettings):
         default="",
     )
 
-    HOSTED_POOL_CREDITS: int = Field(
-        description="Pool credits for hosted service",
-        default=200,
-    )
-
     def get_model_credits(self, model_name: str) -> int:
         """
         Get credit value for a specific model name.
@@ -65,46 +60,19 @@ class HostedOpenAiConfig(BaseSettings):
 
     HOSTED_OPENAI_TRIAL_MODELS: str = Field(
         description="Comma-separated list of available models for trial access",
-        default="gpt-4,"
-        "gpt-4-turbo-preview,"
-        "gpt-4-turbo-2024-04-09,"
-        "gpt-4-1106-preview,"
-        "gpt-4-0125-preview,"
-        "gpt-4-turbo,"
-        "gpt-4.1,"
-        "gpt-4.1-2025-04-14,"
-        "gpt-4.1-mini,"
-        "gpt-4.1-mini-2025-04-14,"
-        "gpt-4.1-nano,"
-        "gpt-4.1-nano-2025-04-14,"
-        "gpt-3.5-turbo,"
+        default="gpt-3.5-turbo,"
+        "gpt-3.5-turbo-1106,"
+        "gpt-3.5-turbo-instruct,"
         "gpt-3.5-turbo-16k,"
         "gpt-3.5-turbo-16k-0613,"
-        "gpt-3.5-turbo-1106,"
         "gpt-3.5-turbo-0613,"
         "gpt-3.5-turbo-0125,"
-        "gpt-3.5-turbo-instruct,"
-        "text-davinci-003,"
-        "chatgpt-4o-latest,"
-        "gpt-4o,"
-        "gpt-4o-2024-05-13,"
-        "gpt-4o-2024-08-06,"
-        "gpt-4o-2024-11-20,"
-        "gpt-4o-audio-preview,"
-        "gpt-4o-audio-preview-2025-06-03,"
-        "gpt-4o-mini,"
-        "gpt-4o-mini-2024-07-18,"
-        "o3-mini,"
-        "o3-mini-2025-01-31,"
-        "gpt-5-mini-2025-08-07,"
-        "gpt-5-mini,"
-        "o4-mini,"
-        "o4-mini-2025-04-16,"
-        "gpt-5-chat-latest,"
-        "gpt-5,"
-        "gpt-5-2025-08-07,"
-        "gpt-5-nano,"
-        "gpt-5-nano-2025-08-07",
+        "text-davinci-003",
+    )
+
+    HOSTED_OPENAI_QUOTA_LIMIT: NonNegativeInt = Field(
+        description="Quota limit for hosted OpenAI service usage",
+        default=200,
     )
 
     HOSTED_OPENAI_PAID_ENABLED: bool = Field(
@@ -119,13 +87,6 @@ class HostedOpenAiConfig(BaseSettings):
         "gpt-4-turbo-2024-04-09,"
         "gpt-4-1106-preview,"
         "gpt-4-0125-preview,"
-        "gpt-4-turbo,"
-        "gpt-4.1,"
-        "gpt-4.1-2025-04-14,"
-        "gpt-4.1-mini,"
-        "gpt-4.1-mini-2025-04-14,"
-        "gpt-4.1-nano,"
-        "gpt-4.1-nano-2025-04-14,"
         "gpt-3.5-turbo,"
         "gpt-3.5-turbo-16k,"
         "gpt-3.5-turbo-16k-0613,"
@@ -133,150 +94,7 @@ class HostedOpenAiConfig(BaseSettings):
         "gpt-3.5-turbo-0613,"
         "gpt-3.5-turbo-0125,"
         "gpt-3.5-turbo-instruct,"
-        "text-davinci-003,"
-        "chatgpt-4o-latest,"
-        "gpt-4o,"
-        "gpt-4o-2024-05-13,"
-        "gpt-4o-2024-08-06,"
-        "gpt-4o-2024-11-20,"
-        "gpt-4o-audio-preview,"
-        "gpt-4o-audio-preview-2025-06-03,"
-        "gpt-4o-mini,"
-        "gpt-4o-mini-2024-07-18,"
-        "o3-mini,"
-        "o3-mini-2025-01-31,"
-        "gpt-5-mini-2025-08-07,"
-        "gpt-5-mini,"
-        "o4-mini,"
-        "o4-mini-2025-04-16,"
-        "gpt-5-chat-latest,"
-        "gpt-5,"
-        "gpt-5-2025-08-07,"
-        "gpt-5-nano,"
-        "gpt-5-nano-2025-08-07",
-    )
-
-
-class HostedGeminiConfig(BaseSettings):
-    """
-    Configuration for fetching Gemini service
-    """
-
-    HOSTED_GEMINI_API_KEY: str | None = Field(
-        description="API key for hosted Gemini service",
-        default=None,
-    )
-
-    HOSTED_GEMINI_API_BASE: str | None = Field(
-        description="Base URL for hosted Gemini API",
-        default=None,
-    )
-
-    HOSTED_GEMINI_API_ORGANIZATION: str | None = Field(
-        description="Organization ID for hosted Gemini service",
-        default=None,
-    )
-
-    HOSTED_GEMINI_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted Gemini service",
-        default=False,
-    )
-
-    HOSTED_GEMINI_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for trial access",
-        default="gemini-2.5-flash,gemini-2.0-flash,gemini-2.0-flash-lite,",
-    )
-
-    HOSTED_GEMINI_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted gemini service",
-        default=False,
-    )
-
-    HOSTED_GEMINI_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="gemini-2.5-flash,gemini-2.0-flash,gemini-2.0-flash-lite,",
-    )
-
-
-class HostedXAIConfig(BaseSettings):
-    """
-    Configuration for fetching XAI service
-    """
-
-    HOSTED_XAI_API_KEY: str | None = Field(
-        description="API key for hosted XAI service",
-        default=None,
-    )
-
-    HOSTED_XAI_API_BASE: str | None = Field(
-        description="Base URL for hosted XAI API",
-        default=None,
-    )
-
-    HOSTED_XAI_API_ORGANIZATION: str | None = Field(
-        description="Organization ID for hosted XAI service",
-        default=None,
-    )
-
-    HOSTED_XAI_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted XAI service",
-        default=False,
-    )
-
-    HOSTED_XAI_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for trial access",
-        default="grok-3,grok-3-mini,grok-3-mini-fast",
-    )
-
-    HOSTED_XAI_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted XAI service",
-        default=False,
-    )
-
-    HOSTED_XAI_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="grok-3,grok-3-mini,grok-3-mini-fast",
-    )
-
-
-class HostedDeepseekConfig(BaseSettings):
-    """
-    Configuration for fetching Deepseek service
-    """
-
-    HOSTED_DEEPSEEK_API_KEY: str | None = Field(
-        description="API key for hosted Deepseek service",
-        default=None,
-    )
-
-    HOSTED_DEEPSEEK_API_BASE: str | None = Field(
-        description="Base URL for hosted Deepseek API",
-        default=None,
-    )
-
-    HOSTED_DEEPSEEK_API_ORGANIZATION: str | None = Field(
-        description="Organization ID for hosted Deepseek service",
-        default=None,
-    )
-
-    HOSTED_DEEPSEEK_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted Deepseek service",
-        default=False,
-    )
-
-    HOSTED_DEEPSEEK_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for trial access",
-        default="deepseek-chat,deepseek-reasoner",
-    )
-
-    HOSTED_DEEPSEEK_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted Deepseek service",
-        default=False,
-    )
-
-    HOSTED_DEEPSEEK_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="deepseek-chat,deepseek-reasoner",
+        "text-davinci-003",
     )
 
 
@@ -326,66 +144,16 @@ class HostedAnthropicConfig(BaseSettings):
         default=False,
     )
 
+    HOSTED_ANTHROPIC_QUOTA_LIMIT: NonNegativeInt = Field(
+        description="Quota limit for hosted Anthropic service usage",
+        default=600000,
+    )
+
     HOSTED_ANTHROPIC_PAID_ENABLED: bool = Field(
         description="Enable paid access to hosted Anthropic service",
         default=False,
     )
 
-    HOSTED_ANTHROPIC_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="claude-opus-4-20250514,"
-        "claude-sonnet-4-20250514,"
-        "claude-3-5-haiku-20241022,"
-        "claude-3-opus-20240229,"
-        "claude-3-7-sonnet-20250219,"
-        "claude-3-haiku-20240307",
-    )
-    HOSTED_ANTHROPIC_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="claude-opus-4-20250514,"
-        "claude-sonnet-4-20250514,"
-        "claude-3-5-haiku-20241022,"
-        "claude-3-opus-20240229,"
-        "claude-3-7-sonnet-20250219,"
-        "claude-3-haiku-20240307",
-    )
-
-
-class HostedTongyiConfig(BaseSettings):
-    """
-    Configuration for hosted Tongyi service
-    """
-
-    HOSTED_TONGYI_API_KEY: str | None = Field(
-        description="API key for hosted Tongyi service",
-        default=None,
-    )
-
-    HOSTED_TONGYI_USE_INTERNATIONAL_ENDPOINT: bool = Field(
-        description="Use international endpoint for hosted Tongyi service",
-        default=False,
-    )
-
-    HOSTED_TONGYI_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted Tongyi service",
-        default=False,
-    )
-
-    HOSTED_TONGYI_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted Anthropic service",
-        default=False,
-    )
-
-    HOSTED_TONGYI_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for trial access",
-        default="",
-    )
-
-    HOSTED_TONGYI_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
-        default="",
-    )
-
 
 class HostedMinmaxConfig(BaseSettings):
     """
@@ -478,13 +246,9 @@ class HostedServiceConfig(
     HostedOpenAiConfig,
     HostedSparkConfig,
     HostedZhipuAIConfig,
-    HostedTongyiConfig,
     # moderation
     HostedModerationConfig,
     # credit config
     HostedCreditConfig,
-    HostedGeminiConfig,
-    HostedXAIConfig,
-    HostedDeepseekConfig,
 ):
     pass

api/configs/middleware/storage/volcengine_tos_storage_config.py

@@ -4,7 +4,7 @@ from pydantic_settings import BaseSettings
 
 class VolcengineTOSStorageConfig(BaseSettings):
     """
-    Configuration settings for Volcengine Torch Object Storage (TOS)
+    Configuration settings for Volcengine Tinder Object Storage (TOS)
     """
 
     VOLCENGINE_TOS_BUCKET_NAME: str | None = Field(

api/context/__init__.py

@@ -1,74 +0,0 @@
-"""
-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",
-]

api/context/flask_app_context.py

@@ -1,192 +0,0 @@
-"""
-Flask App Context - Flask implementation of AppContext interface.
-"""
-
-import contextvars
-import threading
-from collections.abc import Generator
-from contextlib import contextmanager
-from typing import Any, final
-
-from flask import Flask, current_app, g
-
-from core.workflow.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
-        self._local = threading.local()
-
-    @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 non-Flask context variables to avoid leaking Flask tokens across threads
-        for var, val in self._context_vars.items():
-            var.set(val)
-
-        # Enter Flask app context
-        cm = self._app_context.enter()
-        self._local.cm = cm
-        cm.__enter__()
-
-        # Restore user in new app context
-        if self._user is not None:
-            g._login_user = self._user
-
-        return self
-
-    def __exit__(self, *args: Any) -> None:
-        """Exit the Flask execution context."""
-        cm = getattr(self._local, "cm", None)
-        if cm is not None:
-            cm.__exit__(*args)
-
-    @contextmanager
-    def enter(self) -> Generator[None, None, None]:
-        """Enter Flask execution context as context manager."""
-        # Restore non-Flask context variables to avoid leaking Flask tokens across threads
-        for var, val in self._context_vars.items():
-            var.set(val)
-
-        # Enter Flask app context
-        with self._flask_app.app_context():
-            # Restore user in new app context
-            if self._user is not None:
-                g._login_user = self._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)

api/controllers/common/schema.py

@@ -1,11 +1,7 @@
 """Helpers for registering Pydantic models with Flask-RESTX namespaces."""
 
-from enum import StrEnum
-
 from flask_restx import Namespace
-from pydantic import BaseModel, TypeAdapter
-
-from controllers.console import console_ns
+from pydantic import BaseModel
 
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
@@ -23,25 +19,8 @@ def register_schema_models(namespace: Namespace, *models: type[BaseModel]) -> No
         register_schema_model(namespace, model)
 
 
-def get_or_create_model(model_name: str, field_def):
-    existing = console_ns.models.get(model_name)
-    if existing is None:
-        existing = console_ns.model(model_name, field_def)
-    return existing
-
-
-def register_enum_models(namespace: Namespace, *models: type[StrEnum]) -> None:
-    """Register multiple StrEnum with a namespace."""
-    for model in models:
-        namespace.schema_model(
-            model.__name__, TypeAdapter(model).json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
-        )
-
-
 __all__ = [
     "DEFAULT_REF_TEMPLATE_SWAGGER_2_0",
-    "get_or_create_model",
-    "register_enum_models",
     "register_schema_model",
     "register_schema_models",
 ]

api/controllers/console/__init__.py

@@ -107,12 +107,10 @@ from .datasets.rag_pipeline import (
 
 # Import explore controllers
 from .explore import (
-    banner,
     installed_app,
     parameter,
     recommended_app,
     saved_message,
-    trial,
 )
 
 # Import tag controllers
@@ -147,7 +145,6 @@ __all__ = [
     "apikey",
     "app",
     "audio",
-    "banner",
     "billing",
     "bp",
     "completion",
@@ -201,7 +198,6 @@ __all__ = [
     "statistic",
     "tags",
     "tool_providers",
-    "trial",
     "trigger_providers",
     "version",
     "website",

api/controllers/console/admin.py

@@ -15,7 +15,7 @@ from controllers.console.wraps import only_edition_cloud
 from core.db.session_factory import session_factory
 from extensions.ext_database import db
 from libs.token import extract_access_token
-from models.model import App, ExporleBanner, InstalledApp, RecommendedApp, TrialApp
+from models.model import App, InstalledApp, RecommendedApp
 
 P = ParamSpec("P")
 R = TypeVar("R")
@@ -32,8 +32,6 @@ class InsertExploreAppPayload(BaseModel):
     language: str = Field(...)
     category: str = Field(...)
     position: int = Field(...)
-    can_trial: bool = Field(default=False)
-    trial_limit: int = Field(default=0)
 
     @field_validator("language")
     @classmethod
@@ -41,33 +39,11 @@ class InsertExploreAppPayload(BaseModel):
         return supported_language(value)
 
 
-class InsertExploreBannerPayload(BaseModel):
-    category: str = Field(...)
-    title: str = Field(...)
-    description: str = Field(...)
-    img_src: str = Field(..., alias="img-src")
-    language: str = Field(default="en-US")
-    link: str = Field(...)
-    sort: int = Field(...)
-
-    @field_validator("language")
-    @classmethod
-    def validate_language(cls, value: str) -> str:
-        return supported_language(value)
-
-    model_config = {"populate_by_name": True}
-
-
 console_ns.schema_model(
     InsertExploreAppPayload.__name__,
     InsertExploreAppPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
 )
 
-console_ns.schema_model(
-    InsertExploreBannerPayload.__name__,
-    InsertExploreBannerPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
-)
-
 
 def admin_required(view: Callable[P, R]):
     @wraps(view)
@@ -133,20 +109,6 @@ class InsertExploreAppListApi(Resource):
                 )
 
                 db.session.add(recommended_app)
-                if payload.can_trial:
-                    trial_app = db.session.execute(
-                        select(TrialApp).where(TrialApp.app_id == payload.app_id)
-                    ).scalar_one_or_none()
-                    if not trial_app:
-                        db.session.add(
-                            TrialApp(
-                                app_id=payload.app_id,
-                                tenant_id=app.tenant_id,
-                                trial_limit=payload.trial_limit,
-                            )
-                        )
-                    else:
-                        trial_app.trial_limit = payload.trial_limit
 
                 app.is_public = True
                 db.session.commit()
@@ -161,20 +123,6 @@ class InsertExploreAppListApi(Resource):
                 recommended_app.category = payload.category
                 recommended_app.position = payload.position
 
-                if payload.can_trial:
-                    trial_app = db.session.execute(
-                        select(TrialApp).where(TrialApp.app_id == payload.app_id)
-                    ).scalar_one_or_none()
-                    if not trial_app:
-                        db.session.add(
-                            TrialApp(
-                                app_id=payload.app_id,
-                                tenant_id=app.tenant_id,
-                                trial_limit=payload.trial_limit,
-                            )
-                        )
-                    else:
-                        trial_app.trial_limit = payload.trial_limit
                 app.is_public = True
 
                 db.session.commit()
@@ -220,62 +168,7 @@ class InsertExploreAppApi(Resource):
             for installed_app in installed_apps:
                 session.delete(installed_app)
 
-            trial_app = session.execute(
-                select(TrialApp).where(TrialApp.app_id == recommended_app.app_id)
-            ).scalar_one_or_none()
-            if trial_app:
-                session.delete(trial_app)
-
         db.session.delete(recommended_app)
         db.session.commit()
 
         return {"result": "success"}, 204
-
-
-@console_ns.route("/admin/insert-explore-banner")
-class InsertExploreBannerApi(Resource):
-    @console_ns.doc("insert_explore_banner")
-    @console_ns.doc(description="Insert an explore banner")
-    @console_ns.expect(console_ns.models[InsertExploreBannerPayload.__name__])
-    @console_ns.response(201, "Banner inserted successfully")
-    @only_edition_cloud
-    @admin_required
-    def post(self):
-        payload = InsertExploreBannerPayload.model_validate(console_ns.payload)
-
-        content = {
-            "category": payload.category,
-            "title": payload.title,
-            "description": payload.description,
-            "img-src": payload.img_src,
-        }
-
-        banner = ExporleBanner(
-            content=content,
-            link=payload.link,
-            sort=payload.sort,
-            language=payload.language,
-        )
-        db.session.add(banner)
-        db.session.commit()
-
-        return {"result": "success"}, 201
-
-
-@console_ns.route("/admin/delete-explore-banner/<uuid:banner_id>")
-class DeleteExploreBannerApi(Resource):
-    @console_ns.doc("delete_explore_banner")
-    @console_ns.doc(description="Delete an explore banner")
-    @console_ns.doc(params={"banner_id": "Banner ID to delete"})
-    @console_ns.response(204, "Banner deleted successfully")
-    @only_edition_cloud
-    @admin_required
-    def delete(self, banner_id):
-        banner = db.session.execute(select(ExporleBanner).where(ExporleBanner.id == banner_id)).scalar_one_or_none()
-        if not banner:
-            raise NotFound(f"Banner '{banner_id}' is not found")
-
-        db.session.delete(banner)
-        db.session.commit()
-
-        return {"result": "success"}, 204

api/controllers/console/apikey.py

@@ -22,9 +22,9 @@ api_key_fields = {
     "created_at": TimestampField,
 }
 
-api_key_item_model = console_ns.model("ApiKeyItem", api_key_fields)
+api_key_list = {"data": fields.List(fields.Nested(api_key_fields), attribute="items")}
 
-api_key_list = {"data": fields.List(fields.Nested(api_key_item_model), attribute="items")}
+api_key_item_model = console_ns.model("ApiKeyItem", api_key_fields)
 
 api_key_list_model = console_ns.model(
     "ApiKeyList", {"data": fields.List(fields.Nested(api_key_item_model), attribute="items")}

api/controllers/console/app/app.py

@@ -1,3 +1,4 @@
+import re
 import uuid
 from datetime import datetime
 from typing import Any, Literal, TypeAlias
@@ -9,11 +10,9 @@ from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest
 
-from controllers.common.helpers import FileInfo
-from controllers.common.schema import register_enum_models, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
-from controllers.console.workspace.models import LoadBalancingPayload
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_resource_check,
@@ -24,36 +23,18 @@ from controllers.console.wraps import (
 )
 from core.file import helpers as file_helpers
 from core.ops.ops_trace_manager import OpsTraceManager
-from core.rag.retrieval.retrieval_methods import RetrievalMethod
-from core.workflow.enums import NodeType, WorkflowExecutionStatus
+from core.workflow.enums import NodeType
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
-from models import App, DatasetPermissionEnum, Workflow
+from models import App, Workflow
 from models.model import IconType
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
 from services.enterprise.enterprise_service import EnterpriseService
-from services.entities.knowledge_entities.knowledge_entities import (
-    DataSource,
-    InfoList,
-    NotionIcon,
-    NotionInfo,
-    NotionPage,
-    PreProcessingRule,
-    RerankingModel,
-    Rule,
-    Segmentation,
-    WebsiteInfo,
-    WeightKeywordSetting,
-    WeightModel,
-    WeightVectorSetting,
-)
 from services.feature_service import FeatureService
 
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
-register_enum_models(console_ns, IconType)
-
 
 class AppListQuery(BaseModel):
     page: int = Field(default=1, ge=1, le=99999, description="Page number (1-99999)")
@@ -87,6 +68,48 @@ 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)
@@ -95,6 +118,11 @@ 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")
@@ -105,6 +133,11 @@ 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")
@@ -113,6 +146,11 @@ 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")
@@ -171,7 +209,7 @@ def _build_icon_url(icon_type: str | IconType | None, icon: str | None) -> str |
     if icon is None or icon_type is None:
         return None
     icon_type_value = icon_type.value if isinstance(icon_type, IconType) else str(icon_type)
-    if icon_type_value.lower() != IconType.IMAGE:
+    if icon_type_value.lower() != IconType.IMAGE.value:
         return None
     return file_helpers.get_signed_file_url(icon)
 
@@ -411,8 +449,6 @@ class AppExportResponse(ResponseModel):
     data: str
 
 
-register_enum_models(console_ns, RetrievalMethod, WorkflowExecutionStatus, DatasetPermissionEnum)
-
 register_schema_models(
     console_ns,
     AppListQuery,
@@ -436,22 +472,6 @@ register_schema_models(
     AppDetailWithSite,
     AppPagination,
     AppExportResponse,
-    Segmentation,
-    PreProcessingRule,
-    Rule,
-    WeightVectorSetting,
-    WeightKeywordSetting,
-    WeightModel,
-    RerankingModel,
-    InfoList,
-    NotionInfo,
-    FileInfo,
-    WebsiteInfo,
-    NotionPage,
-    NotionIcon,
-    RerankingModel,
-    DataSource,
-    LoadBalancingPayload,
 )
 
 

api/controllers/console/app/app_import.py

@@ -41,14 +41,14 @@ DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 class AppImportPayload(BaseModel):
     mode: str = Field(..., description="Import mode")
-    yaml_content: str | None = Field(None)
-    yaml_url: str | None = Field(None)
-    name: str | None = Field(None)
-    description: str | None = Field(None)
-    icon_type: str | None = Field(None)
-    icon: str | None = Field(None)
-    icon_background: str | None = Field(None)
-    app_id: str | None = Field(None)
+    yaml_content: str | None = None
+    yaml_url: str | None = None
+    name: str | None = None
+    description: str | None = None
+    icon_type: str | None = None
+    icon: str | None = None
+    icon_background: str | None = None
+    app_id: str | None = None
 
 
 console_ns.schema_model(

api/controllers/console/app/conversation.py

@@ -592,12 +592,9 @@ def _get_conversation(app_model, conversation_id):
     if not conversation:
         raise NotFound("Conversation Not Exists.")
 
-    db.session.execute(
-        sa.update(Conversation)
-        .where(Conversation.id == conversation_id, Conversation.read_at.is_(None))
-        .values(read_at=naive_utc_now(), read_account_id=current_user.id)
-    )
-    db.session.commit()
-    db.session.refresh(conversation)
+    if not conversation.read_at:
+        conversation.read_at = naive_utc_now()
+        conversation.read_account_id = current_user.id
+        db.session.commit()
 
     return conversation

api/controllers/console/app/error.py

@@ -82,13 +82,13 @@ class ProviderNotSupportSpeechToTextError(BaseHTTPException):
 class DraftWorkflowNotExist(BaseHTTPException):
     error_code = "draft_workflow_not_exist"
     description = "Draft workflow need to be initialized."
-    code = 404
+    code = 400
 
 
 class DraftWorkflowNotSync(BaseHTTPException):
     error_code = "draft_workflow_not_sync"
     description = "Workflow graph might have been modified, please refresh and resubmit."
-    code = 409
+    code = 400
 
 
 class TracingConfigNotExist(BaseHTTPException):
@@ -115,9 +115,3 @@ class InvokeRateLimitError(BaseHTTPException):
     error_code = "rate_limit_error"
     description = "Rate Limit Error"
     code = 429
-
-
-class NeedAddIdsError(BaseHTTPException):
-    error_code = "need_add_ids"
-    description = "Need to add ids."
-    code = 400

api/controllers/console/app/workflow.py

@@ -12,7 +12,6 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.console import console_ns
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
-from controllers.console.app.workflow_run import workflow_run_node_execution_model
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
@@ -36,6 +35,7 @@ from extensions.ext_database import db
 from factories import file_factory, variable_factory
 from fields.member_fields import simple_account_fields
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
+from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
 from libs.datetime_utils import naive_utc_now
 from libs.helper import TimestampField, uuid_value
@@ -88,6 +88,26 @@ workflow_pagination_fields_copy = workflow_pagination_fields.copy()
 workflow_pagination_fields_copy["items"] = fields.List(fields.Nested(workflow_model), attribute="items")
 workflow_pagination_model = console_ns.model("WorkflowPagination", workflow_pagination_fields_copy)
 
+# Reuse workflow_run_node_execution_model from workflow_run.py if already registered
+# Otherwise register it here
+from fields.end_user_fields import simple_end_user_fields
+
+simple_end_user_model = None
+try:
+    simple_end_user_model = console_ns.models.get("SimpleEndUser")
+except AttributeError:
+    pass
+if simple_end_user_model is None:
+    simple_end_user_model = console_ns.model("SimpleEndUser", simple_end_user_fields)
+
+workflow_run_node_execution_model = None
+try:
+    workflow_run_node_execution_model = console_ns.models.get("WorkflowRunNodeExecution")
+except AttributeError:
+    pass
+if workflow_run_node_execution_model is None:
+    workflow_run_node_execution_model = console_ns.model("WorkflowRunNodeExecution", workflow_run_node_execution_fields)
+
 
 class SyncDraftWorkflowPayload(BaseModel):
     graph: dict[str, Any]
@@ -450,7 +470,7 @@ class AdvancedChatDraftRunLoopNodeApi(Resource):
         Run draft workflow loop node
         """
         current_user, _ = current_account_with_tenant()
-        args = LoopNodeRunPayload.model_validate(console_ns.payload or {})
+        args = LoopNodeRunPayload.model_validate(console_ns.payload or {}).model_dump(exclude_none=True)
 
         try:
             response = AppGenerateService.generate_single_loop(
@@ -488,7 +508,7 @@ class WorkflowDraftRunLoopNodeApi(Resource):
         Run draft workflow loop node
         """
         current_user, _ = current_account_with_tenant()
-        args = LoopNodeRunPayload.model_validate(console_ns.payload or {})
+        args = LoopNodeRunPayload.model_validate(console_ns.payload or {}).model_dump(exclude_none=True)
 
         try:
             response = AppGenerateService.generate_single_loop(
@@ -979,7 +999,6 @@ class DraftWorkflowTriggerRunApi(Resource):
             if not event:
                 return jsonable_encoder({"status": "waiting", "retry_in": LISTENING_RETRY_IN})
             workflow_args = dict(event.workflow_args)
-
             workflow_args[SKIP_PREPARE_USER_INPUTS_KEY] = True
             return helper.compact_generate_response(
                 AppGenerateService.generate(
@@ -1128,7 +1147,6 @@ class DraftWorkflowTriggerRunAllApi(Resource):
 
         try:
             workflow_args = dict(trigger_debug_event.workflow_args)
-
             workflow_args[SKIP_PREPARE_USER_INPUTS_KEY] = True
             response = AppGenerateService.generate(
                 app_model=app_model,

api/controllers/console/app/workflow_app_log.py

@@ -11,10 +11,7 @@ from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.workflow.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
-from fields.workflow_app_log_fields import (
-    build_workflow_app_log_pagination_model,
-    build_workflow_archived_log_pagination_model,
-)
+from fields.workflow_app_log_fields import build_workflow_app_log_pagination_model
 from libs.login import login_required
 from models import App
 from models.model import AppMode
@@ -64,7 +61,6 @@ console_ns.schema_model(
 
 # Register model for flask_restx to avoid dict type issues in Swagger
 workflow_app_log_pagination_model = build_workflow_app_log_pagination_model(console_ns)
-workflow_archived_log_pagination_model = build_workflow_archived_log_pagination_model(console_ns)
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-app-logs")
@@ -103,33 +99,3 @@ class WorkflowAppLogApi(Resource):
             )
 
             return workflow_app_log_pagination
-
-
-@console_ns.route("/apps/<uuid:app_id>/workflow-archived-logs")
-class WorkflowArchivedLogApi(Resource):
-    @console_ns.doc("get_workflow_archived_logs")
-    @console_ns.doc(description="Get workflow archived execution logs")
-    @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.expect(console_ns.models[WorkflowAppLogQuery.__name__])
-    @console_ns.response(200, "Workflow archived logs retrieved successfully", workflow_archived_log_pagination_model)
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model(mode=[AppMode.WORKFLOW])
-    @marshal_with(workflow_archived_log_pagination_model)
-    def get(self, app_model: App):
-        """
-        Get workflow archived logs
-        """
-        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
-
-        workflow_app_service = WorkflowAppService()
-        with Session(db.engine) as session:
-            workflow_app_log_pagination = workflow_app_service.get_paginate_workflow_archive_logs(
-                session=session,
-                app_model=app_model,
-                page=args.page,
-                limit=args.limit,
-            )
-
-            return workflow_app_log_pagination

api/controllers/console/app/workflow_run.py

@@ -1,15 +1,12 @@
-from datetime import UTC, datetime, timedelta
 from typing import Literal, cast
 
 from flask import request
 from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field, field_validator
-from sqlalchemy import select
 
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
-from extensions.ext_database import db
 from fields.end_user_fields import simple_end_user_fields
 from fields.member_fields import simple_account_fields
 from fields.workflow_run_fields import (
@@ -22,17 +19,14 @@ from fields.workflow_run_fields import (
     workflow_run_node_execution_list_fields,
     workflow_run_pagination_fields,
 )
-from libs.archive_storage import ArchiveStorageNotConfiguredError, get_archive_storage
 from libs.custom_inputs import time_duration
 from libs.helper import uuid_value
 from libs.login import current_user, login_required
-from models import Account, App, AppMode, EndUser, WorkflowArchiveLog, WorkflowRunTriggeredFrom
-from services.retention.workflow_run.constants import ARCHIVE_BUNDLE_NAME
+from models import Account, App, AppMode, EndUser, WorkflowRunTriggeredFrom
 from services.workflow_run_service import WorkflowRunService
 
 # Workflow run status choices for filtering
 WORKFLOW_RUN_STATUS_CHOICES = ["running", "succeeded", "failed", "stopped", "partial-succeeded"]
-EXPORT_SIGNED_URL_EXPIRE_SECONDS = 3600
 
 # Register models for flask_restx to avoid dict type issues in Swagger
 # Register in dependency order: base models first, then dependent models
@@ -99,15 +93,6 @@ workflow_run_node_execution_list_model = console_ns.model(
     "WorkflowRunNodeExecutionList", workflow_run_node_execution_list_fields_copy
 )
 
-workflow_run_export_fields = console_ns.model(
-    "WorkflowRunExport",
-    {
-        "status": fields.String(description="Export status: success/failed"),
-        "presigned_url": fields.String(description="Pre-signed URL for download", required=False),
-        "presigned_url_expires_at": fields.String(description="Pre-signed URL expiration time", required=False),
-    },
-)
-
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
@@ -196,56 +181,6 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
         return result
 
 
-@console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/export")
-class WorkflowRunExportApi(Resource):
-    @console_ns.doc("get_workflow_run_export_url")
-    @console_ns.doc(description="Generate a download URL for an archived workflow run.")
-    @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
-    @console_ns.response(200, "Export URL generated", workflow_run_export_fields)
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model()
-    def get(self, app_model: App, run_id: str):
-        tenant_id = str(app_model.tenant_id)
-        app_id = str(app_model.id)
-        run_id_str = str(run_id)
-
-        run_created_at = db.session.scalar(
-            select(WorkflowArchiveLog.run_created_at)
-            .where(
-                WorkflowArchiveLog.tenant_id == tenant_id,
-                WorkflowArchiveLog.app_id == app_id,
-                WorkflowArchiveLog.workflow_run_id == run_id_str,
-            )
-            .limit(1)
-        )
-        if not run_created_at:
-            return {"code": "archive_log_not_found", "message": "workflow run archive not found"}, 404
-
-        prefix = (
-            f"{tenant_id}/app_id={app_id}/year={run_created_at.strftime('%Y')}/"
-            f"month={run_created_at.strftime('%m')}/workflow_run_id={run_id_str}"
-        )
-        archive_key = f"{prefix}/{ARCHIVE_BUNDLE_NAME}"
-
-        try:
-            archive_storage = get_archive_storage()
-        except ArchiveStorageNotConfiguredError as e:
-            return {"code": "archive_storage_not_configured", "message": str(e)}, 500
-
-        presigned_url = archive_storage.generate_presigned_url(
-            archive_key,
-            expires_in=EXPORT_SIGNED_URL_EXPIRE_SECONDS,
-        )
-        expires_at = datetime.now(UTC) + timedelta(seconds=EXPORT_SIGNED_URL_EXPIRE_SECONDS)
-        return {
-            "status": "success",
-            "presigned_url": presigned_url,
-            "presigned_url_expires_at": expires_at.isoformat(),
-        }, 200
-
-
 @console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflow-runs/count")
 class AdvancedChatAppWorkflowRunCountApi(Resource):
     @console_ns.doc("get_advanced_chat_workflow_runs_count")

api/controllers/console/app/workflow_trigger.py

@@ -1,14 +1,13 @@
 import logging
 
 from flask import request
-from flask_restx import Resource, fields, marshal_with
+from flask_restx import Resource, marshal_with
 from pydantic import BaseModel
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
-from controllers.common.schema import get_or_create_model
 from extensions.ext_database import db
 from fields.workflow_trigger_fields import trigger_fields, triggers_list_fields, webhook_trigger_fields
 from libs.login import current_user, login_required
@@ -23,14 +22,6 @@ from ..wraps import account_initialization_required, edit_permission_required, s
 logger = logging.getLogger(__name__)
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
-trigger_model = get_or_create_model("WorkflowTrigger", trigger_fields)
-
-triggers_list_fields_copy = triggers_list_fields.copy()
-triggers_list_fields_copy["data"] = fields.List(fields.Nested(trigger_model))
-triggers_list_model = get_or_create_model("WorkflowTriggerList", triggers_list_fields_copy)
-
-webhook_trigger_model = get_or_create_model("WebhookTrigger", webhook_trigger_fields)
-
 
 class Parser(BaseModel):
     node_id: str
@@ -57,7 +48,7 @@ class WebhookTriggerApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.WORKFLOW)
-    @marshal_with(webhook_trigger_model)
+    @marshal_with(webhook_trigger_fields)
     def get(self, app_model: App):
         """Get webhook trigger for a node"""
         args = Parser.model_validate(request.args.to_dict(flat=True))  # type: ignore
@@ -89,7 +80,7 @@ class AppTriggersApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.WORKFLOW)
-    @marshal_with(triggers_list_model)
+    @marshal_with(triggers_list_fields)
     def get(self, app_model: App):
         """Get app triggers list"""
         assert isinstance(current_user, Account)
@@ -129,7 +120,7 @@ class AppTriggerEnableApi(Resource):
     @account_initialization_required
     @edit_permission_required
     @get_app_model(mode=AppMode.WORKFLOW)
-    @marshal_with(trigger_model)
+    @marshal_with(trigger_fields)
     def post(self, app_model: App):
         """Update app trigger (enable/disable)"""
         args = ParserEnable.model_validate(console_ns.payload)

api/controllers/console/app/wraps.py

@@ -23,11 +23,6 @@ def _load_app_model(app_id: str) -> App | None:
     return app_model
 
 
-def _load_app_model_with_trial(app_id: str) -> App | None:
-    app_model = db.session.query(App).where(App.id == app_id, App.status == "normal").first()
-    return app_model
-
-
 def get_app_model(view: Callable[P, R] | None = None, *, mode: Union[AppMode, list[AppMode], None] = None):
     def decorator(view_func: Callable[P1, R1]):
         @wraps(view_func)
@@ -67,44 +62,3 @@ def get_app_model(view: Callable[P, R] | None = None, *, mode: Union[AppMode, li
         return decorator
     else:
         return decorator(view)
-
-
-def get_app_model_with_trial(view: Callable[P, R] | None = None, *, mode: Union[AppMode, list[AppMode], None] = None):
-    def decorator(view_func: Callable[P, R]):
-        @wraps(view_func)
-        def decorated_view(*args: P.args, **kwargs: P.kwargs):
-            if not kwargs.get("app_id"):
-                raise ValueError("missing app_id in path parameters")
-
-            app_id = kwargs.get("app_id")
-            app_id = str(app_id)
-
-            del kwargs["app_id"]
-
-            app_model = _load_app_model_with_trial(app_id)
-
-            if not app_model:
-                raise AppNotFoundError()
-
-            app_mode = AppMode.value_of(app_model.mode)
-
-            if mode is not None:
-                if isinstance(mode, list):
-                    modes = mode
-                else:
-                    modes = [mode]
-
-                if app_mode not in modes:
-                    mode_values = {m.value for m in modes}
-                    raise AppNotFoundError(f"App mode is not in the supported list: {mode_values}")
-
-            kwargs["app_model"] = app_model
-
-            return view_func(*args, **kwargs)
-
-        return decorated_view
-
-    if view is None:
-        return decorator
-    else:
-        return decorator(view)

api/controllers/console/auth/activate.py

@@ -63,19 +63,13 @@ class ActivateCheckApi(Resource):
         args = ActivateCheckQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         workspaceId = args.workspace_id
+        reg_email = args.email
         token = args.token
 
-        invitation = RegisterService.get_invitation_with_case_fallback(workspaceId, args.email, token)
+        invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
         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
@@ -106,12 +100,11 @@ class ActivateApi(Resource):
     def post(self):
         args = ActivatePayload.model_validate(console_ns.payload)
 
-        normalized_request_email = args.email.lower() if args.email else None
-        invitation = RegisterService.get_invitation_with_case_fallback(args.workspace_id, args.email, args.token)
+        invitation = RegisterService.get_invitation_if_token_valid(args.workspace_id, args.email, args.token)
         if invitation is None:
             raise AlreadyActivateError()
 
-        RegisterService.revoke_token(args.workspace_id, normalized_request_email, args.token)
+        RegisterService.revoke_token(args.workspace_id, args.email, args.token)
 
         account = invitation["account"]
         account.name = args.name

api/controllers/console/auth/email_register.py

@@ -1,6 +1,7 @@
 from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
+from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from configs import dify_config
@@ -61,7 +62,6 @@ class EmailRegisterSendEmailApi(Resource):
     @email_register_enabled
     def post(self):
         args = EmailRegisterSendPayload.model_validate(console_ns.payload)
-        normalized_email = args.email.lower()
 
         ip_address = extract_remote_ip(request)
         if AccountService.is_email_send_ip_limit(ip_address):
@@ -70,12 +70,13 @@ class EmailRegisterSendEmailApi(Resource):
         if args.language in languages:
             language = args.language
 
-        if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(normalized_email):
+        if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(args.email):
             raise AccountInFreezeError()
 
         with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(args.email, session=session)
-        token = AccountService.send_email_register_email(email=normalized_email, account=account, language=language)
+            account = session.execute(select(Account).filter_by(email=args.email)).scalar_one_or_none()
+        token = None
+        token = AccountService.send_email_register_email(email=args.email, account=account, language=language)
         return {"result": "success", "data": token}
 
 
@@ -87,9 +88,9 @@ class EmailRegisterCheckApi(Resource):
     def post(self):
         args = EmailRegisterValidityPayload.model_validate(console_ns.payload)
 
-        user_email = args.email.lower()
+        user_email = args.email
 
-        is_email_register_error_rate_limit = AccountService.is_email_register_error_rate_limit(user_email)
+        is_email_register_error_rate_limit = AccountService.is_email_register_error_rate_limit(args.email)
         if is_email_register_error_rate_limit:
             raise EmailRegisterLimitError()
 
@@ -97,14 +98,11 @@ class EmailRegisterCheckApi(Resource):
         if token_data is None:
             raise InvalidTokenError()
 
-        token_email = token_data.get("email")
-        normalized_token_email = token_email.lower() if isinstance(token_email, str) else token_email
-
-        if user_email != normalized_token_email:
+        if user_email != token_data.get("email"):
             raise InvalidEmailError()
 
         if args.code != token_data.get("code"):
-            AccountService.add_email_register_error_rate_limit(user_email)
+            AccountService.add_email_register_error_rate_limit(args.email)
             raise EmailCodeError()
 
         # Verified, revoke the first token
@@ -115,8 +113,8 @@ class EmailRegisterCheckApi(Resource):
             user_email, code=args.code, additional_data={"phase": "register"}
         )
 
-        AccountService.reset_email_register_error_rate_limit(user_email)
-        return {"is_valid": True, "email": normalized_token_email, "token": new_token}
+        AccountService.reset_email_register_error_rate_limit(args.email)
+        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
 
 
 @console_ns.route("/email-register")
@@ -143,23 +141,22 @@ class EmailRegisterResetApi(Resource):
         AccountService.revoke_email_register_token(args.token)
 
         email = register_data.get("email", "")
-        normalized_email = email.lower()
 
         with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+            account = session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
 
             if account:
                 raise EmailAlreadyInUseError()
             else:
-                account = self._create_new_account(normalized_email, args.password_confirm)
+                account = self._create_new_account(email, args.password_confirm)
                 if not account:
                     raise AccountNotFoundError()
                 token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
-                AccountService.reset_login_error_rate_limit(normalized_email)
+                AccountService.reset_login_error_rate_limit(email)
 
         return {"result": "success", "data": token_pair.model_dump()}
 
-    def _create_new_account(self, email: str, password: str) -> Account | None:
+    def _create_new_account(self, email, password) -> Account | None:
         # Create new account if allowed
         account = None
         try:

api/controllers/console/auth/forgot_password.py

@@ -4,6 +4,7 @@ import secrets
 from flask import request
 from flask_restx import Resource, fields
 from pydantic import BaseModel, Field, field_validator
+from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from controllers.console import console_ns
@@ -20,6 +21,7 @@ from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import EmailStr, extract_remote_ip
 from libs.password import hash_password, valid_password
+from models import Account
 from services.account_service import AccountService, TenantService
 from services.feature_service import FeatureService
 
@@ -74,7 +76,6 @@ class ForgotPasswordSendEmailApi(Resource):
     @email_password_login_enabled
     def post(self):
         args = ForgotPasswordSendPayload.model_validate(console_ns.payload)
-        normalized_email = args.email.lower()
 
         ip_address = extract_remote_ip(request)
         if AccountService.is_email_send_ip_limit(ip_address):
@@ -86,11 +87,11 @@ class ForgotPasswordSendEmailApi(Resource):
             language = "en-US"
 
         with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(args.email, session=session)
+            account = session.execute(select(Account).filter_by(email=args.email)).scalar_one_or_none()
 
         token = AccountService.send_reset_password_email(
             account=account,
-            email=normalized_email,
+            email=args.email,
             language=language,
             is_allow_register=FeatureService.get_system_features().is_allow_register,
         )
@@ -121,9 +122,9 @@ class ForgotPasswordCheckApi(Resource):
     def post(self):
         args = ForgotPasswordCheckPayload.model_validate(console_ns.payload)
 
-        user_email = args.email.lower()
+        user_email = args.email
 
-        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(user_email)
+        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args.email)
         if is_forgot_password_error_rate_limit:
             raise EmailPasswordResetLimitError()
 
@@ -131,16 +132,11 @@ class ForgotPasswordCheckApi(Resource):
         if token_data is None:
             raise InvalidTokenError()
 
-        token_email = token_data.get("email")
-        if not isinstance(token_email, str):
-            raise InvalidEmailError()
-        normalized_token_email = token_email.lower()
-
-        if user_email != normalized_token_email:
+        if user_email != token_data.get("email"):
             raise InvalidEmailError()
 
         if args.code != token_data.get("code"):
-            AccountService.add_forgot_password_error_rate_limit(user_email)
+            AccountService.add_forgot_password_error_rate_limit(args.email)
             raise EmailCodeError()
 
         # Verified, revoke the first token
@@ -148,11 +144,11 @@ class ForgotPasswordCheckApi(Resource):
 
         # Refresh token data by generating a new token
         _, new_token = AccountService.generate_reset_password_token(
-            token_email, code=args.code, additional_data={"phase": "reset"}
+            user_email, code=args.code, additional_data={"phase": "reset"}
         )
 
-        AccountService.reset_forgot_password_error_rate_limit(user_email)
-        return {"is_valid": True, "email": normalized_token_email, "token": new_token}
+        AccountService.reset_forgot_password_error_rate_limit(args.email)
+        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
 
 
 @console_ns.route("/forgot-password/resets")
@@ -191,8 +187,9 @@ class ForgotPasswordResetApi(Resource):
         password_hashed = hash_password(args.new_password, salt)
 
         email = reset_data.get("email", "")
+
         with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+            account = session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
 
             if account:
                 self._update_existing_account(account, password_hashed, salt, session)

api/controllers/console/auth/login.py

@@ -90,38 +90,32 @@ class LoginApi(Resource):
     def post(self):
         """Authenticate user and login."""
         args = LoginPayload.model_validate(console_ns.payload)
-        request_email = args.email
-        normalized_email = request_email.lower()
 
-        if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(normalized_email):
+        if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(args.email):
             raise AccountInFreezeError()
 
-        is_login_error_rate_limit = AccountService.is_login_error_rate_limit(normalized_email)
+        is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args.email)
         if is_login_error_rate_limit:
             raise EmailPasswordLoginLimitError()
 
-        invite_token = args.invite_token
         invitation_data: dict[str, Any] | None = None
-        if invite_token:
-            invitation_data = RegisterService.get_invitation_with_case_fallback(None, request_email, invite_token)
-            if invitation_data is None:
-                invite_token = None
+        if args.invite_token:
+            invitation_data = RegisterService.get_invitation_if_token_valid(None, args.email, args.invite_token)
 
         try:
             if invitation_data:
                 data = invitation_data.get("data", {})
                 invitee_email = data.get("email") if data else None
-                invitee_email_normalized = invitee_email.lower() if isinstance(invitee_email, str) else invitee_email
-                if invitee_email_normalized != normalized_email:
+                if invitee_email != args.email:
                     raise InvalidEmailError()
-            account = _authenticate_account_with_case_fallback(
-                request_email, normalized_email, args.password, invite_token
-            )
+                account = AccountService.authenticate(args.email, args.password, args.invite_token)
+            else:
+                account = AccountService.authenticate(args.email, args.password)
         except services.errors.account.AccountLoginError:
             raise AccountBannedError()
-        except services.errors.account.AccountPasswordError as exc:
-            AccountService.add_login_error_rate_limit(normalized_email)
-            raise AuthenticationFailedError() from exc
+        except services.errors.account.AccountPasswordError:
+            AccountService.add_login_error_rate_limit(args.email)
+            raise AuthenticationFailedError()
         # SELF_HOSTED only have one workspace
         tenants = TenantService.get_join_tenants(account)
         if len(tenants) == 0:
@@ -136,7 +130,7 @@ class LoginApi(Resource):
                 }
 
         token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
-        AccountService.reset_login_error_rate_limit(normalized_email)
+        AccountService.reset_login_error_rate_limit(args.email)
 
         # Create response with cookies instead of returning tokens in body
         response = make_response({"result": "success"})
@@ -176,19 +170,18 @@ class ResetPasswordSendEmailApi(Resource):
     @console_ns.expect(console_ns.models[EmailPayload.__name__])
     def post(self):
         args = EmailPayload.model_validate(console_ns.payload)
-        normalized_email = args.email.lower()
 
         if args.language is not None and args.language == "zh-Hans":
             language = "zh-Hans"
         else:
             language = "en-US"
         try:
-            account = _get_account_with_case_fallback(args.email)
+            account = AccountService.get_user_through_email(args.email)
         except AccountRegisterError:
             raise AccountInFreezeError()
 
         token = AccountService.send_reset_password_email(
-            email=normalized_email,
+            email=args.email,
             account=account,
             language=language,
             is_allow_register=FeatureService.get_system_features().is_allow_register,
@@ -203,7 +196,6 @@ class EmailCodeLoginSendEmailApi(Resource):
     @console_ns.expect(console_ns.models[EmailPayload.__name__])
     def post(self):
         args = EmailPayload.model_validate(console_ns.payload)
-        normalized_email = args.email.lower()
 
         ip_address = extract_remote_ip(request)
         if AccountService.is_email_send_ip_limit(ip_address):
@@ -214,13 +206,13 @@ class EmailCodeLoginSendEmailApi(Resource):
         else:
             language = "en-US"
         try:
-            account = _get_account_with_case_fallback(args.email)
+            account = AccountService.get_user_through_email(args.email)
         except AccountRegisterError:
             raise AccountInFreezeError()
 
         if account is None:
             if FeatureService.get_system_features().is_allow_register:
-                token = AccountService.send_email_code_login_email(email=normalized_email, language=language)
+                token = AccountService.send_email_code_login_email(email=args.email, language=language)
             else:
                 raise AccountNotFound()
         else:
@@ -237,17 +229,14 @@ class EmailCodeLoginApi(Resource):
     def post(self):
         args = EmailCodeLoginPayload.model_validate(console_ns.payload)
 
-        original_email = args.email
-        user_email = original_email.lower()
+        user_email = args.email
         language = args.language
 
         token_data = AccountService.get_email_code_login_data(args.token)
         if token_data is None:
             raise InvalidTokenError()
 
-        token_email = token_data.get("email")
-        normalized_token_email = token_email.lower() if isinstance(token_email, str) else token_email
-        if normalized_token_email != user_email:
+        if token_data["email"] != args.email:
             raise InvalidEmailError()
 
         if token_data["code"] != args.code:
@@ -255,7 +244,7 @@ class EmailCodeLoginApi(Resource):
 
         AccountService.revoke_email_code_login_token(args.token)
         try:
-            account = _get_account_with_case_fallback(original_email)
+            account = AccountService.get_user_through_email(user_email)
         except AccountRegisterError:
             raise AccountInFreezeError()
         if account:
@@ -286,7 +275,7 @@ class EmailCodeLoginApi(Resource):
             except WorkspacesLimitExceededError:
                 raise WorkspacesLimitExceeded()
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
-        AccountService.reset_login_error_rate_limit(user_email)
+        AccountService.reset_login_error_rate_limit(args.email)
 
         # Create response with cookies instead of returning tokens in body
         response = make_response({"result": "success"})
@@ -320,22 +309,3 @@ class RefreshTokenApi(Resource):
             return response
         except Exception as e:
             return {"result": "fail", "message": str(e)}, 401
-
-
-def _get_account_with_case_fallback(email: str):
-    account = AccountService.get_user_through_email(email)
-    if account or email == email.lower():
-        return account
-
-    return AccountService.get_user_through_email(email.lower())
-
-
-def _authenticate_account_with_case_fallback(
-    original_email: str, normalized_email: str, password: str, invite_token: str | None
-):
-    try:
-        return AccountService.authenticate(original_email, password, invite_token)
-    except services.errors.account.AccountPasswordError:
-        if original_email == normalized_email:
-            raise
-        return AccountService.authenticate(normalized_email, password, invite_token)

api/controllers/console/auth/oauth.py

@@ -3,6 +3,7 @@ import logging
 import httpx
 from flask import current_app, redirect, request
 from flask_restx import Resource
+from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Unauthorized
 
@@ -117,10 +118,7 @@ class OAuthCallback(Resource):
             invitation = RegisterService.get_invitation_by_token(token=invite_token)
             if invitation:
                 invitation_email = invitation.get("email", None)
-                invitation_email_normalized = (
-                    invitation_email.lower() if isinstance(invitation_email, str) else invitation_email
-                )
-                if invitation_email_normalized != user_info.email.lower():
+                if invitation_email != user_info.email:
                     return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
 
             return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
@@ -177,7 +175,7 @@ def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) ->
 
     if not account:
         with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(user_info.email, session=session)
+            account = session.execute(select(Account).filter_by(email=user_info.email)).scalar_one_or_none()
 
     return account
 
@@ -199,10 +197,9 @@ def _generate_account(provider: str, user_info: OAuthUserInfo) -> tuple[Account,
                 tenant_was_created.send(new_tenant)
 
     if not account:
-        normalized_email = user_info.email.lower()
         oauth_new_user = True
         if not FeatureService.get_system_features().is_allow_register:
-            if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(normalized_email):
+            if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(user_info.email):
                 raise AccountRegisterError(
                     description=(
                         "This email account has been deleted within the past "
@@ -213,11 +210,7 @@ def _generate_account(provider: str, user_info: OAuthUserInfo) -> tuple[Account,
                 raise AccountRegisterError(description=("Invalid email or password"))
         account_name = user_info.name or "Dify"
         account = RegisterService.register(
-            email=normalized_email,
-            name=account_name,
-            password=None,
-            open_id=user_info.id,
-            provider=provider,
+            email=user_info.email, name=account_name, password=None, open_id=user_info.id, provider=provider
         )
 
         # Set interface language

api/controllers/console/datasets/data_source.py

@@ -3,13 +3,13 @@ from collections.abc import Generator
 from typing import Any, cast
 
 from flask import request
-from flask_restx import Resource, fields, marshal_with
+from flask_restx import Resource, marshal_with
 from pydantic import BaseModel, Field
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
-from controllers.common.schema import get_or_create_model, register_schema_model
+from controllers.common.schema import register_schema_model
 from core.datasource.entities.datasource_entities import DatasourceProviderType, OnlineDocumentPagesMessage
 from core.datasource.online_document.online_document_plugin import OnlineDocumentDatasourcePlugin
 from core.indexing_runner import IndexingRunner
@@ -17,14 +17,7 @@ from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo
 from core.rag.extractor.notion_extractor import NotionExtractor
 from extensions.ext_database import db
-from fields.data_source_fields import (
-    integrate_fields,
-    integrate_icon_fields,
-    integrate_list_fields,
-    integrate_notion_info_list_fields,
-    integrate_page_fields,
-    integrate_workspace_fields,
-)
+from fields.data_source_fields import integrate_list_fields, integrate_notion_info_list_fields
 from libs.datetime_utils import naive_utc_now
 from libs.login import current_account_with_tenant, login_required
 from models import DataSourceOauthBinding, Document
@@ -43,62 +36,9 @@ class NotionEstimatePayload(BaseModel):
     doc_language: str = Field(default="English")
 
 
-class DataSourceNotionListQuery(BaseModel):
-    dataset_id: str | None = Field(default=None, description="Dataset ID")
-    credential_id: str = Field(..., description="Credential ID", min_length=1)
-    datasource_parameters: dict[str, Any] | None = Field(default=None, description="Datasource parameters JSON string")
-
-
-class DataSourceNotionPreviewQuery(BaseModel):
-    credential_id: str = Field(..., description="Credential ID", min_length=1)
-
-
 register_schema_model(console_ns, NotionEstimatePayload)
 
 
-integrate_icon_model = get_or_create_model("DataSourceIntegrateIcon", integrate_icon_fields)
-
-integrate_page_fields_copy = integrate_page_fields.copy()
-integrate_page_fields_copy["page_icon"] = fields.Nested(integrate_icon_model, allow_null=True)
-integrate_page_model = get_or_create_model("DataSourceIntegratePage", integrate_page_fields_copy)
-
-integrate_workspace_fields_copy = integrate_workspace_fields.copy()
-integrate_workspace_fields_copy["pages"] = fields.List(fields.Nested(integrate_page_model))
-integrate_workspace_model = get_or_create_model("DataSourceIntegrateWorkspace", integrate_workspace_fields_copy)
-
-integrate_fields_copy = integrate_fields.copy()
-integrate_fields_copy["source_info"] = fields.Nested(integrate_workspace_model)
-integrate_model = get_or_create_model("DataSourceIntegrate", integrate_fields_copy)
-
-integrate_list_fields_copy = integrate_list_fields.copy()
-integrate_list_fields_copy["data"] = fields.List(fields.Nested(integrate_model))
-integrate_list_model = get_or_create_model("DataSourceIntegrateList", integrate_list_fields_copy)
-
-notion_page_fields = {
-    "page_name": fields.String,
-    "page_id": fields.String,
-    "page_icon": fields.Nested(integrate_icon_model, allow_null=True),
-    "is_bound": fields.Boolean,
-    "parent_id": fields.String,
-    "type": fields.String,
-}
-notion_page_model = get_or_create_model("NotionIntegratePage", notion_page_fields)
-
-notion_workspace_fields = {
-    "workspace_name": fields.String,
-    "workspace_id": fields.String,
-    "workspace_icon": fields.String,
-    "pages": fields.List(fields.Nested(notion_page_model)),
-}
-notion_workspace_model = get_or_create_model("NotionIntegrateWorkspace", notion_workspace_fields)
-
-integrate_notion_info_list_fields_copy = integrate_notion_info_list_fields.copy()
-integrate_notion_info_list_fields_copy["notion_info"] = fields.List(fields.Nested(notion_workspace_model))
-integrate_notion_info_list_model = get_or_create_model(
-    "NotionIntegrateInfoList", integrate_notion_info_list_fields_copy
-)
-
-
 @console_ns.route(
     "/data-source/integrates",
     "/data-source/integrates/<uuid:binding_id>/<string:action>",
@@ -107,7 +47,7 @@ class DataSourceApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(integrate_list_model)
+    @marshal_with(integrate_list_fields)
     def get(self):
         _, current_tenant_id = current_account_with_tenant()
 
@@ -192,19 +132,30 @@ class DataSourceNotionListApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(integrate_notion_info_list_model)
+    @marshal_with(integrate_notion_info_list_fields)
     def get(self):
         current_user, current_tenant_id = current_account_with_tenant()
 
-        query = DataSourceNotionListQuery.model_validate(request.args.to_dict())
+        dataset_id = request.args.get("dataset_id", default=None, type=str)
+        credential_id = request.args.get("credential_id", default=None, type=str)
+        if not credential_id:
+            raise ValueError("Credential id is required.")
 
         # Get datasource_parameters from query string (optional, for GitHub and other datasources)
-        datasource_parameters = query.datasource_parameters or {}
+        datasource_parameters_str = request.args.get("datasource_parameters", default=None, type=str)
+        datasource_parameters = {}
+        if datasource_parameters_str:
+            try:
+                datasource_parameters = json.loads(datasource_parameters_str)
+                if not isinstance(datasource_parameters, dict):
+                    raise ValueError("datasource_parameters must be a JSON object.")
+            except json.JSONDecodeError:
+                raise ValueError("Invalid datasource_parameters JSON format.")
 
         datasource_provider_service = DatasourceProviderService()
         credential = datasource_provider_service.get_datasource_credentials(
             tenant_id=current_tenant_id,
-            credential_id=query.credential_id,
+            credential_id=credential_id,
             provider="notion_datasource",
             plugin_id="langgenius/notion_datasource",
         )
@@ -213,8 +164,8 @@ class DataSourceNotionListApi(Resource):
         exist_page_ids = []
         with Session(db.engine) as session:
             # import notion in the exist dataset
-            if query.dataset_id:
-                dataset = DatasetService.get_dataset(query.dataset_id)
+            if dataset_id:
+                dataset = DatasetService.get_dataset(dataset_id)
                 if not dataset:
                     raise NotFound("Dataset not found.")
                 if dataset.data_source_type != "notion_import":
@@ -222,7 +173,7 @@ class DataSourceNotionListApi(Resource):
 
                 documents = session.scalars(
                     select(Document).filter_by(
-                        dataset_id=query.dataset_id,
+                        dataset_id=dataset_id,
                         tenant_id=current_tenant_id,
                         data_source_type="notion_import",
                         enabled=True,
@@ -289,12 +240,13 @@ class DataSourceNotionApi(Resource):
     def get(self, page_id, page_type):
         _, current_tenant_id = current_account_with_tenant()
 
-        query = DataSourceNotionPreviewQuery.model_validate(request.args.to_dict())
-
+        credential_id = request.args.get("credential_id", default=None, type=str)
+        if not credential_id:
+            raise ValueError("Credential id is required.")
         datasource_provider_service = DatasourceProviderService()
         credential = datasource_provider_service.get_datasource_credentials(
             tenant_id=current_tenant_id,
-            credential_id=query.credential_id,
+            credential_id=credential_id,
             provider="notion_datasource",
             plugin_id="langgenius/notion_datasource",
         )

api/controllers/console/datasets/datasets.py

@@ -8,7 +8,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 
 import services
 from configs import dify_config
-from controllers.common.schema import get_or_create_model, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.apikey import (
     api_key_item_model,
@@ -34,7 +34,6 @@ from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from extensions.ext_database import db
 from fields.app_fields import app_detail_kernel_fields, related_app_list
 from fields.dataset_fields import (
-    content_fields,
     dataset_detail_fields,
     dataset_fields,
     dataset_query_detail_fields,
@@ -42,7 +41,6 @@ from fields.dataset_fields import (
     doc_metadata_fields,
     external_knowledge_info_fields,
     external_retrieval_model_fields,
-    file_info_fields,
     icon_info_fields,
     keyword_setting_fields,
     reranking_model_fields,
@@ -57,33 +55,41 @@ from models.dataset import DatasetPermissionEnum
 from models.provider_ids import ModelProviderID
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
+
+def _get_or_create_model(model_name: str, field_def):
+    existing = console_ns.models.get(model_name)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
+
+
 # Register models for flask_restx to avoid dict type issues in Swagger
-dataset_base_model = get_or_create_model("DatasetBase", dataset_fields)
+dataset_base_model = _get_or_create_model("DatasetBase", dataset_fields)
 
-tag_model = get_or_create_model("Tag", tag_fields)
+tag_model = _get_or_create_model("Tag", tag_fields)
 
-keyword_setting_model = get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
-vector_setting_model = get_or_create_model("DatasetVectorSetting", vector_setting_fields)
+keyword_setting_model = _get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
+vector_setting_model = _get_or_create_model("DatasetVectorSetting", vector_setting_fields)
 
 weighted_score_fields_copy = weighted_score_fields.copy()
 weighted_score_fields_copy["keyword_setting"] = fields.Nested(keyword_setting_model)
 weighted_score_fields_copy["vector_setting"] = fields.Nested(vector_setting_model)
-weighted_score_model = get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
+weighted_score_model = _get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
 
-reranking_model = get_or_create_model("DatasetRerankingModel", reranking_model_fields)
+reranking_model = _get_or_create_model("DatasetRerankingModel", reranking_model_fields)
 
 dataset_retrieval_model_fields_copy = dataset_retrieval_model_fields.copy()
 dataset_retrieval_model_fields_copy["reranking_model"] = fields.Nested(reranking_model)
 dataset_retrieval_model_fields_copy["weights"] = fields.Nested(weighted_score_model, allow_null=True)
-dataset_retrieval_model = get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
+dataset_retrieval_model = _get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
 
-external_knowledge_info_model = get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
+external_knowledge_info_model = _get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
 
-external_retrieval_model = get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
+external_retrieval_model = _get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
 
-doc_metadata_model = get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
+doc_metadata_model = _get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
 
-icon_info_model = get_or_create_model("DatasetIconInfo", icon_info_fields)
+icon_info_model = _get_or_create_model("DatasetIconInfo", icon_info_fields)
 
 dataset_detail_fields_copy = dataset_detail_fields.copy()
 dataset_detail_fields_copy["retrieval_model_dict"] = fields.Nested(dataset_retrieval_model)
@@ -92,22 +98,14 @@ dataset_detail_fields_copy["external_knowledge_info"] = fields.Nested(external_k
 dataset_detail_fields_copy["external_retrieval_model"] = fields.Nested(external_retrieval_model, allow_null=True)
 dataset_detail_fields_copy["doc_metadata"] = fields.List(fields.Nested(doc_metadata_model))
 dataset_detail_fields_copy["icon_info"] = fields.Nested(icon_info_model)
-dataset_detail_model = get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
+dataset_detail_model = _get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
 
-file_info_model = get_or_create_model("DatasetFileInfo", file_info_fields)
+dataset_query_detail_model = _get_or_create_model("DatasetQueryDetail", dataset_query_detail_fields)
 
-content_fields_copy = content_fields.copy()
-content_fields_copy["file_info"] = fields.Nested(file_info_model, allow_null=True)
-content_model = get_or_create_model("DatasetContent", content_fields_copy)
-
-dataset_query_detail_fields_copy = dataset_query_detail_fields.copy()
-dataset_query_detail_fields_copy["queries"] = fields.Nested(content_model)
-dataset_query_detail_model = get_or_create_model("DatasetQueryDetail", dataset_query_detail_fields_copy)
-
-app_detail_kernel_model = get_or_create_model("AppDetailKernel", app_detail_kernel_fields)
+app_detail_kernel_model = _get_or_create_model("AppDetailKernel", app_detail_kernel_fields)
 related_app_list_copy = related_app_list.copy()
 related_app_list_copy["data"] = fields.List(fields.Nested(app_detail_kernel_model))
-related_app_list_model = get_or_create_model("RelatedAppList", related_app_list_copy)
+related_app_list_model = _get_or_create_model("RelatedAppList", related_app_list_copy)
 
 
 def _validate_indexing_technique(value: str | None) -> str | None:
@@ -178,18 +176,7 @@ class IndexingEstimatePayload(BaseModel):
         return result
 
 
-class ConsoleDatasetListQuery(BaseModel):
-    page: int = Field(default=1, description="Page number")
-    limit: int = Field(default=20, description="Number of items per page")
-    keyword: str | None = Field(default=None, description="Search keyword")
-    include_all: bool = Field(default=False, description="Include all datasets")
-    ids: list[str] = Field(default_factory=list, description="Filter by dataset IDs")
-    tag_ids: list[str] = Field(default_factory=list, description="Filter by tag IDs")
-
-
-register_schema_models(
-    console_ns, DatasetCreatePayload, DatasetUpdatePayload, IndexingEstimatePayload, ConsoleDatasetListQuery
-)
+register_schema_models(console_ns, DatasetCreatePayload, DatasetUpdatePayload, IndexingEstimatePayload)
 
 
 def _get_retrieval_methods_by_vector_type(vector_type: str | None, is_mock: bool = False) -> dict[str, list[str]]:
@@ -288,19 +275,18 @@ class DatasetListApi(Resource):
     @enterprise_license_required
     def get(self):
         current_user, current_tenant_id = current_account_with_tenant()
-        query = ConsoleDatasetListQuery.model_validate(request.args.to_dict())
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        ids = request.args.getlist("ids")
         # provider = request.args.get("provider", default="vendor")
-        if query.ids:
-            datasets, total = DatasetService.get_datasets_by_ids(query.ids, current_tenant_id)
+        search = request.args.get("keyword", default=None, type=str)
+        tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"
+        if ids:
+            datasets, total = DatasetService.get_datasets_by_ids(ids, current_tenant_id)
         else:
             datasets, total = DatasetService.get_datasets(
-                query.page,
-                query.limit,
-                current_tenant_id,
-                current_user,
-                query.keyword,
-                query.tag_ids,
-                query.include_all,
+                page, limit, current_tenant_id, current_user, search, tag_ids, include_all
             )
 
         # check embedding setting
@@ -332,13 +318,7 @@ class DatasetListApi(Resource):
             else:
                 item.update({"partial_member_list": []})
 
-        response = {
-            "data": data,
-            "has_more": len(datasets) == query.limit,
-            "limit": query.limit,
-            "total": total,
-            "page": query.page,
-        }
+        response = {"data": data, "has_more": len(datasets) == limit, "limit": limit, "total": total, "page": page}
         return response, 200
 
     @console_ns.doc("create_dataset")

api/controllers/console/datasets/datasets_document.py

@@ -2,19 +2,17 @@ import json
 import logging
 from argparse import ArgumentTypeError
 from collections.abc import Sequence
-from contextlib import ExitStack
-from typing import Any, Literal, cast
-from uuid import UUID
+from typing import Literal, cast
 
 import sqlalchemy as sa
-from flask import request, send_file
+from flask import request
 from flask_restx import Resource, fields, marshal, marshal_with
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 from sqlalchemy import asc, desc, select
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
-from controllers.common.schema import get_or_create_model, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from core.errors.error import (
     LLMBadRequestError,
@@ -44,7 +42,6 @@ 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,
@@ -68,31 +65,35 @@ 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)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
 
 
 # Register models for flask_restx to avoid dict type issues in Swagger
-dataset_model = get_or_create_model("Dataset", dataset_fields)
+dataset_model = _get_or_create_model("Dataset", dataset_fields)
 
-document_metadata_model = get_or_create_model("DocumentMetadata", document_metadata_fields)
+document_metadata_model = _get_or_create_model("DocumentMetadata", document_metadata_fields)
 
 document_fields_copy = document_fields.copy()
 document_fields_copy["doc_metadata"] = fields.List(
     fields.Nested(document_metadata_model), attribute="doc_metadata_details"
 )
-document_model = get_or_create_model("Document", document_fields_copy)
+document_model = _get_or_create_model("Document", document_fields_copy)
 
 document_with_segments_fields_copy = document_with_segments_fields.copy()
 document_with_segments_fields_copy["doc_metadata"] = fields.List(
     fields.Nested(document_metadata_model), attribute="doc_metadata_details"
 )
-document_with_segments_model = get_or_create_model("DocumentWithSegments", document_with_segments_fields_copy)
+document_with_segments_model = _get_or_create_model("DocumentWithSegments", document_with_segments_fields_copy)
 
 dataset_and_document_fields_copy = dataset_and_document_fields.copy()
 dataset_and_document_fields_copy["dataset"] = fields.Nested(dataset_model)
 dataset_and_document_fields_copy["documents"] = fields.List(fields.Nested(document_model))
-dataset_and_document_model = get_or_create_model("DatasetAndDocument", dataset_and_document_fields_copy)
+dataset_and_document_model = _get_or_create_model("DatasetAndDocument", dataset_and_document_fields_copy)
 
 
 class DocumentRetryPayload(BaseModel):
@@ -103,21 +104,6 @@ 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.")
-    search: str | None = Field(None, alias="keyword", title="Search", description="Search keyword.")
-    sort_by: str = Field("-created_at", alias="sort", title="SortBy", description="Sort by field.")
-    status: str | None = Field(None, title="Status", description="Document status.")
-    fetch_val: str = Field("false", alias="fetch")
-
-
 register_schema_models(
     console_ns,
     KnowledgeConfig,
@@ -125,7 +111,6 @@ register_schema_models(
     RetrievalModel,
     DocumentRetryPayload,
     DocumentRenamePayload,
-    DocumentBatchDownloadZipPayload,
 )
 
 
@@ -240,16 +225,14 @@ class DatasetDocumentListApi(Resource):
     def get(self, dataset_id):
         current_user, current_tenant_id = current_account_with_tenant()
         dataset_id = str(dataset_id)
-        raw_args = request.args.to_dict()
-        param = DocumentDatasetListParam.model_validate(raw_args)
-        page = param.page
-        limit = param.limit
-        search = param.search
-        sort = param.sort_by
-        status = param.status
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        search = request.args.get("keyword", default=None, type=str)
+        sort = request.args.get("sort", default="-created_at", type=str)
+        status = request.args.get("status", default=None, type=str)
         # "yes", "true", "t", "y", "1" convert to True, while others convert to False.
         try:
-            fetch_val = param.fetch_val
+            fetch_val = request.args.get("fetch", default="false")
             if isinstance(fetch_val, bool):
                 fetch = fetch_val
             else:
@@ -859,62 +842,6 @@ 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")
@@ -1171,7 +1098,7 @@ class DocumentRenameApi(DocumentResource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(document_model)
+    @marshal_with(document_fields)
     @console_ns.expect(console_ns.models[DocumentRenamePayload.__name__])
     def post(self, dataset_id, document_id):
         # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator

api/controllers/console/datasets/datasets_segments.py

@@ -90,7 +90,6 @@ register_schema_models(
     ChildChunkCreatePayload,
     ChildChunkUpdatePayload,
     ChildChunkBatchUpdatePayload,
-    ChildChunkUpdateArgs,
 )
 
 

api/controllers/console/datasets/external.py

@@ -4,7 +4,7 @@ from pydantic import BaseModel, Field
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
-from controllers.common.schema import get_or_create_model, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
@@ -28,27 +28,34 @@ from services.hit_testing_service import HitTestingService
 from services.knowledge_service import ExternalDatasetTestService
 
 
+def _get_or_create_model(model_name: str, field_def):
+    existing = console_ns.models.get(model_name)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
+
+
 def _build_dataset_detail_model():
-    keyword_setting_model = get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
-    vector_setting_model = get_or_create_model("DatasetVectorSetting", vector_setting_fields)
+    keyword_setting_model = _get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
+    vector_setting_model = _get_or_create_model("DatasetVectorSetting", vector_setting_fields)
 
     weighted_score_fields_copy = weighted_score_fields.copy()
     weighted_score_fields_copy["keyword_setting"] = fields.Nested(keyword_setting_model)
     weighted_score_fields_copy["vector_setting"] = fields.Nested(vector_setting_model)
-    weighted_score_model = get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
+    weighted_score_model = _get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
 
-    reranking_model = get_or_create_model("DatasetRerankingModel", reranking_model_fields)
+    reranking_model = _get_or_create_model("DatasetRerankingModel", reranking_model_fields)
 
     dataset_retrieval_model_fields_copy = dataset_retrieval_model_fields.copy()
     dataset_retrieval_model_fields_copy["reranking_model"] = fields.Nested(reranking_model)
     dataset_retrieval_model_fields_copy["weights"] = fields.Nested(weighted_score_model, allow_null=True)
-    dataset_retrieval_model = get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
+    dataset_retrieval_model = _get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
 
-    tag_model = get_or_create_model("Tag", tag_fields)
-    doc_metadata_model = get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
-    external_knowledge_info_model = get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
-    external_retrieval_model = get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
-    icon_info_model = get_or_create_model("DatasetIconInfo", icon_info_fields)
+    tag_model = _get_or_create_model("Tag", tag_fields)
+    doc_metadata_model = _get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
+    external_knowledge_info_model = _get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
+    external_retrieval_model = _get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
+    icon_info_model = _get_or_create_model("DatasetIconInfo", icon_info_fields)
 
     dataset_detail_fields_copy = dataset_detail_fields.copy()
     dataset_detail_fields_copy["retrieval_model_dict"] = fields.Nested(dataset_retrieval_model)
@@ -57,7 +64,7 @@ def _build_dataset_detail_model():
     dataset_detail_fields_copy["external_retrieval_model"] = fields.Nested(external_retrieval_model, allow_null=True)
     dataset_detail_fields_copy["doc_metadata"] = fields.List(fields.Nested(doc_metadata_model))
     dataset_detail_fields_copy["icon_info"] = fields.Nested(icon_info_model)
-    return get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
+    return _get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
 
 
 try:
@@ -74,7 +81,7 @@ class ExternalKnowledgeApiPayload(BaseModel):
 class ExternalDatasetCreatePayload(BaseModel):
     external_knowledge_api_id: str
     external_knowledge_id: str
-    name: str = Field(..., min_length=1, max_length=100)
+    name: str = Field(..., min_length=1, max_length=40)
     description: str | None = Field(None, max_length=400)
     external_retrieval_model: dict[str, object] | None = None
 
@@ -91,19 +98,12 @@ class BedrockRetrievalPayload(BaseModel):
     knowledge_id: str
 
 
-class ExternalApiTemplateListQuery(BaseModel):
-    page: int = Field(default=1, description="Page number")
-    limit: int = Field(default=20, description="Number of items per page")
-    keyword: str | None = Field(default=None, description="Search keyword")
-
-
 register_schema_models(
     console_ns,
     ExternalKnowledgeApiPayload,
     ExternalDatasetCreatePayload,
     ExternalHitTestingPayload,
     BedrockRetrievalPayload,
-    ExternalApiTemplateListQuery,
 )
 
 
@@ -124,17 +124,19 @@ class ExternalApiTemplateListApi(Resource):
     @account_initialization_required
     def get(self):
         _, current_tenant_id = current_account_with_tenant()
-        query = ExternalApiTemplateListQuery.model_validate(request.args.to_dict())
+        page = request.args.get("page", default=1, type=int)
+        limit = request.args.get("limit", default=20, type=int)
+        search = request.args.get("keyword", default=None, type=str)
 
         external_knowledge_apis, total = ExternalDatasetService.get_external_knowledge_apis(
-            query.page, query.limit, current_tenant_id, query.keyword
+            page, limit, current_tenant_id, search
         )
         response = {
             "data": [item.to_dict() for item in external_knowledge_apis],
-            "has_more": len(external_knowledge_apis) == query.limit,
-            "limit": query.limit,
+            "has_more": len(external_knowledge_apis) == limit,
+            "limit": limit,
             "total": total,
-            "page": query.page,
+            "page": page,
         }
         return response, 200
 

api/controllers/console/datasets/metadata.py

@@ -4,16 +4,14 @@ from flask_restx import Resource, marshal_with
 from pydantic import BaseModel
 from werkzeug.exceptions import NotFound
 
-from controllers.common.schema import register_schema_models
+from controllers.common.schema import register_schema_model, register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
 from fields.dataset_fields import dataset_metadata_fields
 from libs.login import current_account_with_tenant, login_required
 from services.dataset_service import DatasetService
 from services.entities.knowledge_entities.knowledge_entities import (
-    DocumentMetadataOperation,
     MetadataArgs,
-    MetadataDetail,
     MetadataOperationData,
 )
 from services.metadata_service import MetadataService
@@ -23,9 +21,8 @@ class MetadataUpdatePayload(BaseModel):
     name: str
 
 
-register_schema_models(
-    console_ns, MetadataArgs, MetadataOperationData, MetadataUpdatePayload, DocumentMetadataOperation, MetadataDetail
-)
+register_schema_models(console_ns, MetadataArgs, MetadataOperationData)
+register_schema_model(console_ns, MetadataUpdatePayload)
 
 
 @console_ns.route("/datasets/<uuid:dataset_id>/metadata")

api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py

@@ -2,7 +2,7 @@ import logging
 from typing import Any, NoReturn
 
 from flask import Response, request
-from flask_restx import Resource, marshal, marshal_with
+from flask_restx import Resource, fields, marshal, marshal_with
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
@@ -14,9 +14,7 @@ from controllers.console.app.error import (
 )
 from controllers.console.app.workflow_draft_variable import (
     _WORKFLOW_DRAFT_VARIABLE_FIELDS,  # type: ignore[private-usage]
-    workflow_draft_variable_list_model,
-    workflow_draft_variable_list_without_value_model,
-    workflow_draft_variable_model,
+    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,  # type: ignore[private-usage]
 )
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import account_initialization_required, setup_required
@@ -29,6 +27,7 @@ from factories.variable_factory import build_segment_with_type
 from libs.login import current_user, login_required
 from models import Account
 from models.dataset import Pipeline
+from models.workflow import WorkflowDraftVariable
 from services.rag_pipeline.rag_pipeline import RagPipelineService
 from services.workflow_draft_variable_service import WorkflowDraftVariableList, WorkflowDraftVariableService
 
@@ -53,6 +52,20 @@ class WorkflowDraftVariablePatchPayload(BaseModel):
 register_schema_models(console_ns, WorkflowDraftVariablePatchPayload)
 
 
+def _get_items(var_list: WorkflowDraftVariableList) -> list[WorkflowDraftVariable]:
+    return var_list.variables
+
+
+_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS = {
+    "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS), attribute=_get_items),
+    "total": fields.Raw(),
+}
+
+_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS = {
+    "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_FIELDS), attribute=_get_items),
+}
+
+
 def _api_prerequisite(f):
     """Common prerequisites for all draft workflow variable APIs.
 
@@ -79,7 +92,7 @@ def _api_prerequisite(f):
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/variables")
 class RagPipelineVariableCollectionApi(Resource):
     @_api_prerequisite
-    @marshal_with(workflow_draft_variable_list_without_value_model)
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
     def get(self, pipeline: Pipeline):
         """
         Get draft workflow
@@ -137,7 +150,7 @@ def validate_node_id(node_id: str) -> NoReturn | None:
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/nodes/<string:node_id>/variables")
 class RagPipelineNodeVariableCollectionApi(Resource):
     @_api_prerequisite
-    @marshal_with(workflow_draft_variable_list_model)
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     def get(self, pipeline: Pipeline, node_id: str):
         validate_node_id(node_id)
         with Session(bind=db.engine, expire_on_commit=False) as session:
@@ -163,7 +176,7 @@ class RagPipelineVariableApi(Resource):
     _PATCH_VALUE_FIELD = "value"
 
     @_api_prerequisite
-    @marshal_with(workflow_draft_variable_model)
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
     def get(self, pipeline: Pipeline, variable_id: str):
         draft_var_srv = WorkflowDraftVariableService(
             session=db.session(),
@@ -176,7 +189,7 @@ class RagPipelineVariableApi(Resource):
         return variable
 
     @_api_prerequisite
-    @marshal_with(workflow_draft_variable_model)
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
     @console_ns.expect(console_ns.models[WorkflowDraftVariablePatchPayload.__name__])
     def patch(self, pipeline: Pipeline, variable_id: str):
         # Request payload for file types:
@@ -294,7 +307,7 @@ def _get_variable_list(pipeline: Pipeline, node_id) -> WorkflowDraftVariableList
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/system-variables")
 class RagPipelineSystemVariableCollectionApi(Resource):
     @_api_prerequisite
-    @marshal_with(workflow_draft_variable_list_model)
+    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
     def get(self, pipeline: Pipeline):
         return _get_variable_list(pipeline, SYSTEM_VARIABLE_NODE_ID)
 

api/controllers/console/datasets/rag_pipeline/rag_pipeline_import.py

@@ -1,9 +1,9 @@
 from flask import request
-from flask_restx import Resource, fields, marshal_with  # type: ignore
+from flask_restx import Resource, marshal_with  # type: ignore
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
 
-from controllers.common.schema import get_or_create_model, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import (
@@ -12,11 +12,7 @@ from controllers.console.wraps import (
     setup_required,
 )
 from extensions.ext_database import db
-from fields.rag_pipeline_fields import (
-    leaked_dependency_fields,
-    pipeline_import_check_dependencies_fields,
-    pipeline_import_fields,
-)
+from fields.rag_pipeline_fields import pipeline_import_check_dependencies_fields, pipeline_import_fields
 from libs.login import current_account_with_tenant, login_required
 from models.dataset import Pipeline
 from services.app_dsl_service import ImportStatus
@@ -42,25 +38,13 @@ class IncludeSecretQuery(BaseModel):
 register_schema_models(console_ns, RagPipelineImportPayload, IncludeSecretQuery)
 
 
-pipeline_import_model = get_or_create_model("RagPipelineImport", pipeline_import_fields)
-
-leaked_dependency_model = get_or_create_model("RagPipelineLeakedDependency", leaked_dependency_fields)
-pipeline_import_check_dependencies_fields_copy = pipeline_import_check_dependencies_fields.copy()
-pipeline_import_check_dependencies_fields_copy["leaked_dependencies"] = fields.List(
-    fields.Nested(leaked_dependency_model)
-)
-pipeline_import_check_dependencies_model = get_or_create_model(
-    "RagPipelineImportCheckDependencies", pipeline_import_check_dependencies_fields_copy
-)
-
-
 @console_ns.route("/rag/pipelines/imports")
 class RagPipelineImportApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
     @edit_permission_required
-    @marshal_with(pipeline_import_model)
+    @marshal_with(pipeline_import_fields)
     @console_ns.expect(console_ns.models[RagPipelineImportPayload.__name__])
     def post(self):
         # Check user role first
@@ -97,7 +81,7 @@ class RagPipelineImportConfirmApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    @marshal_with(pipeline_import_model)
+    @marshal_with(pipeline_import_fields)
     def post(self, import_id):
         current_user, _ = current_account_with_tenant()
 
@@ -122,7 +106,7 @@ class RagPipelineImportCheckDependenciesApi(Resource):
     @get_rag_pipeline
     @account_initialization_required
     @edit_permission_required
-    @marshal_with(pipeline_import_check_dependencies_model)
+    @marshal_with(pipeline_import_check_dependencies_fields)
     def get(self, pipeline: Pipeline):
         with Session(db.engine) as session:
             import_service = RagPipelineDslService(session)

api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py

@@ -17,13 +17,6 @@ from controllers.console.app.error import (
     DraftWorkflowNotExist,
     DraftWorkflowNotSync,
 )
-from controllers.console.app.workflow import workflow_model, workflow_pagination_model
-from controllers.console.app.workflow_run import (
-    workflow_run_detail_model,
-    workflow_run_node_execution_list_model,
-    workflow_run_node_execution_model,
-    workflow_run_pagination_model,
-)
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import (
     account_initialization_required,
@@ -37,6 +30,13 @@ from core.app.entities.app_invoke_entities import InvokeFrom
 from core.model_runtime.utils.encoders import jsonable_encoder
 from extensions.ext_database import db
 from factories import variable_factory
+from fields.workflow_fields import workflow_fields, workflow_pagination_fields
+from fields.workflow_run_fields import (
+    workflow_run_detail_fields,
+    workflow_run_node_execution_fields,
+    workflow_run_node_execution_list_fields,
+    workflow_run_pagination_fields,
+)
 from libs import helper
 from libs.helper import TimestampField
 from libs.login import current_account_with_tenant, current_user, login_required
@@ -145,7 +145,7 @@ class DraftRagPipelineApi(Resource):
     @account_initialization_required
     @get_rag_pipeline
     @edit_permission_required
-    @marshal_with(workflow_model)
+    @marshal_with(workflow_fields)
     def get(self, pipeline: Pipeline):
         """
         Get draft rag pipeline's workflow
@@ -521,7 +521,7 @@ class RagPipelineDraftNodeRunApi(Resource):
     @edit_permission_required
     @account_initialization_required
     @get_rag_pipeline
-    @marshal_with(workflow_run_node_execution_model)
+    @marshal_with(workflow_run_node_execution_fields)
     def post(self, pipeline: Pipeline, node_id: str):
         """
         Run draft workflow node
@@ -569,7 +569,7 @@ class PublishedRagPipelineApi(Resource):
     @account_initialization_required
     @edit_permission_required
     @get_rag_pipeline
-    @marshal_with(workflow_model)
+    @marshal_with(workflow_fields)
     def get(self, pipeline: Pipeline):
         """
         Get published pipeline
@@ -664,7 +664,7 @@ class PublishedAllRagPipelineApi(Resource):
     @account_initialization_required
     @edit_permission_required
     @get_rag_pipeline
-    @marshal_with(workflow_pagination_model)
+    @marshal_with(workflow_pagination_fields)
     def get(self, pipeline: Pipeline):
         """
         Get published workflows
@@ -708,7 +708,7 @@ class RagPipelineByIdApi(Resource):
     @account_initialization_required
     @edit_permission_required
     @get_rag_pipeline
-    @marshal_with(workflow_model)
+    @marshal_with(workflow_fields)
     def patch(self, pipeline: Pipeline, workflow_id: str):
         """
         Update workflow attributes
@@ -830,7 +830,7 @@ class RagPipelineWorkflowRunListApi(Resource):
     @login_required
     @account_initialization_required
     @get_rag_pipeline
-    @marshal_with(workflow_run_pagination_model)
+    @marshal_with(workflow_run_pagination_fields)
     def get(self, pipeline: Pipeline):
         """
         Get workflow run list
@@ -858,7 +858,7 @@ class RagPipelineWorkflowRunDetailApi(Resource):
     @login_required
     @account_initialization_required
     @get_rag_pipeline
-    @marshal_with(workflow_run_detail_model)
+    @marshal_with(workflow_run_detail_fields)
     def get(self, pipeline: Pipeline, run_id):
         """
         Get workflow run detail
@@ -877,7 +877,7 @@ class RagPipelineWorkflowRunNodeExecutionListApi(Resource):
     @login_required
     @account_initialization_required
     @get_rag_pipeline
-    @marshal_with(workflow_run_node_execution_list_model)
+    @marshal_with(workflow_run_node_execution_list_fields)
     def get(self, pipeline: Pipeline, run_id: str):
         """
         Get workflow run node execution list
@@ -911,7 +911,7 @@ class RagPipelineWorkflowLastRunApi(Resource):
     @login_required
     @account_initialization_required
     @get_rag_pipeline
-    @marshal_with(workflow_run_node_execution_model)
+    @marshal_with(workflow_run_node_execution_fields)
     def get(self, pipeline: Pipeline, node_id: str):
         rag_pipeline_service = RagPipelineService()
         workflow = rag_pipeline_service.get_draft_workflow(pipeline=pipeline)
@@ -952,7 +952,7 @@ class RagPipelineDatasourceVariableApi(Resource):
     @account_initialization_required
     @get_rag_pipeline
     @edit_permission_required
-    @marshal_with(workflow_run_node_execution_model)
+    @marshal_with(workflow_run_node_execution_fields)
     def post(self, pipeline: Pipeline):
         """
         Set datasource variables

api/controllers/console/explore/banner.py

@@ -1,43 +0,0 @@
-from flask import request
-from flask_restx import Resource
-
-from controllers.console import api
-from controllers.console.explore.wraps import explore_banner_enabled
-from extensions.ext_database import db
-from models.model import ExporleBanner
-
-
-class BannerApi(Resource):
-    """Resource for banner list."""
-
-    @explore_banner_enabled
-    def get(self):
-        """Get banner list."""
-        language = request.args.get("language", "en-US")
-
-        # Build base query for enabled banners
-        base_query = db.session.query(ExporleBanner).where(ExporleBanner.status == "enabled")
-
-        # Try to get banners in the requested language
-        banners = base_query.where(ExporleBanner.language == language).order_by(ExporleBanner.sort).all()
-
-        # Fallback to en-US if no banners found and language is not en-US
-        if not banners and language != "en-US":
-            banners = base_query.where(ExporleBanner.language == "en-US").order_by(ExporleBanner.sort).all()
-        # Convert banners to serializable format
-        result = []
-        for banner in banners:
-            banner_data = {
-                "id": banner.id,
-                "content": banner.content,  # Already parsed as JSON by SQLAlchemy
-                "link": banner.link,
-                "sort": banner.sort,
-                "status": banner.status,
-                "created_at": banner.created_at.isoformat() if banner.created_at else None,
-            }
-            result.append(banner_data)
-
-        return result
-
-
-api.add_resource(BannerApi, "/explore/banners")

api/controllers/console/explore/error.py

@@ -29,25 +29,3 @@ class AppAccessDeniedError(BaseHTTPException):
     error_code = "access_denied"
     description = "App access denied."
     code = 403
-
-
-class TrialAppNotAllowed(BaseHTTPException):
-    """*403* `Trial App Not Allowed`
-
-    Raise if the user has reached the trial app limit.
-    """
-
-    error_code = "trial_app_not_allowed"
-    code = 403
-    description = "the app is not allowed to be trial."
-
-
-class TrialAppLimitExceeded(BaseHTTPException):
-    """*403* `Trial App Limit Exceeded`
-
-    Raise if the user has exceeded the trial app limit.
-    """
-
-    error_code = "trial_app_limit_exceeded"
-    code = 403
-    description = "The user has exceeded the trial app limit."