chore: replace x-shared-env anchor with env_file, drop template generator

The 1677-line generated docker-compose.yaml was ~440 lines of YAML-anchor
boilerplate (`x-shared-env: &shared-api-worker-env` populated by
`generate_docker_compose` from `.env.example`). Native compose has had
`env_file:` for years and supports interpolation in env files since 2.24,
so the anchor + generator pair was reimplementing what compose does itself.

This commit:

- Removes the `x-shared-env: &shared-api-worker-env` anchor and all
  `<<: *shared-api-worker-env` merges. Services that need the shared
  config (`api`, `worker`, `worker_beat`, `plugin_daemon`) now use
    env_file:
      - .env.example
      - .env
- Deletes `docker/docker-compose-template.yaml` (no longer needed; the
  generated compose file becomes the single source of truth).
- Deletes `docker/generate_docker_compose` (no template, no generation).

`docker/docker-compose.yaml` now contains the full, hand-readable compose
config in 958 lines (was 1677 — a 43% reduction). The default
`docker compose up -d` brings up exactly the same set of services
(api/web/worker/redis/postgres/weaviate/...) via the existing
profile-gating in COMPOSE_PROFILES.

Suggestion from #35925.

Behavior note: shared-config keys are no longer interpolated through
compose, so passing `KEY=value docker compose up -d` from the shell
no longer overrides container env for those keys — set them in
`docker/.env` instead. Service-specific overrides via the
`environment:` block continue to work as before.

.agents/skills/component-refactoring/SKILL.md

@@ -63,7 +63,7 @@ pnpm analyze-component <path> --json
 
 ```typescript
 // ❌ Before: Complex state logic in component
-function Configuration() {
+const Configuration: FC = () => {
   const [modelConfig, setModelConfig] = useState<ModelConfig>(...)
   const [datasetConfigs, setDatasetConfigs] = useState<DatasetConfigs>(...)
   const [completionParams, setCompletionParams] = useState<FormValue>({})
@@ -85,7 +85,7 @@ export const useModelConfig = (appId: string) => {
 }
 
 // Component becomes cleaner
-function Configuration() {
+const Configuration: FC = () => {
   const { modelConfig, setModelConfig } = useModelConfig(appId)
   return <div>...</div>
 }
@@ -189,6 +189,8 @@ const Template = useMemo(() => {
 
 **Dify Convention**:
 - This skill is for component decomposition, not query/mutation design.
+- When refactoring data fetching, follow `web/AGENTS.md`.
+- Use `frontend-query-mutation` for contracts, query shape, data-fetching wrappers, query/mutation call-site patterns, conditional queries, invalidation, and mutation error handling.
 - Do not introduce deprecated `useInvalid` / `useReset`.
 - Do not add thin passthrough `useQuery` wrappers during refactoring; only extract a custom hook when it truly orchestrates multiple queries/mutations or shared derived state.
 

.agents/skills/component-refactoring/references/complexity-patterns.md

@@ -60,10 +60,8 @@ const Template = useMemo(() => {
 **After** (complexity: ~3):
 
 ```typescript
-import type { ComponentType } from 'react'
-
 // Define lookup table outside component
-const TEMPLATE_MAP: Record<AppModeEnum, Record<string, ComponentType<TemplateProps>>> = {
+const TEMPLATE_MAP: Record<AppModeEnum, Record<string, FC<TemplateProps>>> = {
   [AppModeEnum.CHAT]: {
     [LanguagesSupported[1]]: TemplateChatZh,
     [LanguagesSupported[7]]: TemplateChatJa,

.agents/skills/component-refactoring/references/component-splitting.md

@@ -65,10 +65,10 @@ interface ConfigurationHeaderProps {
   onPublish: () => void
 }
 
-function ConfigurationHeader({
+const ConfigurationHeader: FC<ConfigurationHeaderProps> = ({
   isAdvancedMode,
   onPublish,
-}: ConfigurationHeaderProps) {
+}) => {
   const { t } = useTranslation()
   
   return (
@@ -136,7 +136,7 @@ const AppInfo = () => {
 }
 
 // ✅ After: Separate view components
-function AppInfoExpanded({ appDetail, onAction }: AppInfoViewProps) {
+const AppInfoExpanded: FC<AppInfoViewProps> = ({ appDetail, onAction }) => {
   return (
     <div className="expanded">
       {/* Clean, focused expanded view */}
@@ -144,7 +144,7 @@ function AppInfoExpanded({ appDetail, onAction }: AppInfoViewProps) {
   )
 }
 
-function AppInfoCollapsed({ appDetail, onAction }: AppInfoViewProps) {
+const AppInfoCollapsed: FC<AppInfoViewProps> = ({ appDetail, onAction }) => {
   return (
     <div className="collapsed">
       {/* Clean, focused collapsed view */}
@@ -203,12 +203,12 @@ interface AppInfoModalsProps {
   onSuccess: () => void
 }
 
-function AppInfoModals({
+const AppInfoModals: FC<AppInfoModalsProps> = ({
   appDetail,
   activeModal,
   onClose,
   onSuccess,
-}: AppInfoModalsProps) {
+}) => {
   const handleEdit = async (data) => { /* logic */ }
   const handleDuplicate = async (data) => { /* logic */ }
   const handleDelete = async () => { /* logic */ }
@@ -296,7 +296,7 @@ interface OperationItemProps {
   onAction: (id: string) => void
 }
 
-function OperationItem({ operation, onAction }: OperationItemProps) {
+const OperationItem: FC<OperationItemProps> = ({ operation, onAction }) => {
   return (
     <div className="operation-item">
       <span className="icon">{operation.icon}</span>
@@ -435,7 +435,7 @@ interface ChildProps {
   onSubmit: () => void
 }
 
-function Child({ value, onChange, onSubmit }: ChildProps) {
+const Child: FC<ChildProps> = ({ value, onChange, onSubmit }) => {
   return (
     <div>
       <input value={value} onChange={e => onChange(e.target.value)} />

.agents/skills/component-refactoring/references/hook-extraction.md

@@ -112,13 +112,13 @@ export const useModelConfig = ({
 
 ```typescript
 // Before: 50+ lines of state management
-function Configuration() {
+const Configuration: FC = () => {
   const [modelConfig, setModelConfig] = useState<ModelConfig>(...)
   // ... lots of related state and effects
 }
 
 // After: Clean component
-function Configuration() {
+const Configuration: FC = () => {
   const {
     modelConfig,
     setModelConfig,
@@ -159,6 +159,8 @@ function Configuration() {
 
 When hook extraction touches query or mutation code, do not use this reference as the source of truth for data-layer patterns.
 
+- Follow `web/AGENTS.md` first.
+- Use `frontend-query-mutation` for contracts, query shape, data-fetching wrappers, query/mutation call-site patterns, conditional queries, invalidation, and mutation error handling.
 - Do not introduce deprecated `useInvalid` / `useReset`.
 - Do not extract thin passthrough `useQuery` hooks; only extract orchestration hooks.
 

.agents/skills/e2e-cucumber-playwright/SKILL.md

@@ -23,7 +23,7 @@ Use this skill for Dify's repository-level E2E suite in `e2e/`. Use [`e2e/AGENTS
    - `e2e/scripts/run-cucumber.ts` and `e2e/cucumber.config.ts` when tags or execution flow matter
 3. Read [`references/playwright-best-practices.md`](references/playwright-best-practices.md) only when locator, assertion, isolation, or waiting choices are involved.
 4. Read [`references/cucumber-best-practices.md`](references/cucumber-best-practices.md) only when scenario wording, step granularity, tags, or expression design are involved.
-5. Re-check official Playwright or Cucumber docs with the available documentation tools before introducing a new framework pattern.
+5. Re-check official docs with Context7 before introducing a new Playwright or Cucumber pattern.
 
 ## Local Rules
 

.agents/skills/frontend-code-review/references/performance.md

@@ -9,18 +9,18 @@ Category: Performance
 
 When rendering React Flow, prefer `useNodes`/`useEdges` for UI consumption and rely on `useStoreApi` inside callbacks that mutate or read node/edge state. Avoid manually pulling Flow data outside of these hooks.
 
-## Complex prop stability
+## Complex prop memoization
 
-IsUrgent: False
+IsUrgent: True
 Category: Performance
 
 ### Description
 
-Only require stable object, array, or map props when there is a clear reason: the child is memoized, the value participates in effect/query dependencies, the value is part of a stable-reference API contract, or profiling/local behavior shows avoidable re-renders. Do not request `useMemo` for every inline object by default; `how-to-write-component` treats memoization as a targeted optimization.
+Wrap complex prop values (objects, arrays, maps) in `useMemo` prior to passing them into child components to guarantee stable references and prevent unnecessary renders.
 
 Update this file when adding, editing, or removing Performance rules so the catalog remains accurate.
 
-Risky:
+Wrong:
 
 ```tsx
 <HeavyComp
@@ -31,7 +31,7 @@ Risky:
 />
 ```
 
-Better when stable identity matters:
+Right:
 
 ```tsx
 const config = useMemo(() => ({

.agents/skills/frontend-query-mutation/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: frontend-query-mutation
+description: Guide for implementing Dify frontend query and mutation patterns with TanStack Query and oRPC. Trigger when creating or updating contracts in web/contract, wiring router composition, consuming consoleQuery or marketplaceQuery in components or services, deciding whether to call queryOptions()/mutationOptions() directly or extract a helper or use-* hook, configuring oRPC experimental_defaults/default options, handling conditional queries, cache updates/invalidation, mutation error handling, or migrating legacy service calls to contract-first query and mutation helpers.
+---
+
+# Frontend Query & Mutation
+
+## Intent
+
+- Keep contract as the single source of truth in `web/contract/*`.
+- Prefer contract-shaped `queryOptions()` and `mutationOptions()`.
+- Keep default cache behavior with `consoleQuery`/`marketplaceQuery` setup, and keep business orchestration in feature vertical hooks when direct contract calls are not enough.
+- Treat `web/service/use-*` query or mutation wrappers as legacy migration targets, not the preferred destination.
+- Keep abstractions minimal to preserve TypeScript inference.
+
+## Workflow
+
+1. Identify the change surface.
+   - Read `references/contract-patterns.md` for contract files, router composition, client helpers, and query or mutation call-site shape.
+   - Read `references/runtime-rules.md` for conditional queries, default options, cache updates/invalidation, error handling, and legacy migrations.
+   - Read both references when a task spans contract shape and runtime behavior.
+2. Implement the smallest abstraction that fits the task.
+   - Default to direct `useQuery(...)` or `useMutation(...)` calls with oRPC helpers at the call site.
+   - Extract a small shared query helper only when multiple call sites share the same extra options.
+   - Create or keep feature hooks only for real orchestration or shared domain behavior.
+   - When touching thin `web/service/use-*` wrappers, migrate them away when feasible.
+3. Preserve Dify conventions.
+   - Keep contract inputs in `{ params, query?, body? }` shape.
+   - Bind default cache updates/invalidation in `createTanstackQueryUtils(...experimental_defaults...)`; use feature hooks only for workflows that cannot be expressed as default operation behavior.
+   - Prefer `mutate(...)`; use `mutateAsync(...)` only when Promise semantics are required.
+
+## Files Commonly Touched
+
+- `web/contract/console/*.ts`
+- `web/contract/marketplace.ts`
+- `web/contract/router.ts`
+- `web/service/client.ts`
+- legacy `web/service/use-*.ts` files when migrating wrappers away
+- component and hook call sites using `consoleQuery` or `marketplaceQuery`
+
+## References
+
+- Use `references/contract-patterns.md` for contract shape, router registration, query and mutation helpers, and anti-patterns that degrade inference.
+- Use `references/runtime-rules.md` for conditional queries, invalidation, `mutate` versus `mutateAsync`, and legacy migration rules.
+
+Treat this skill as the single query and mutation entry point for Dify frontend work. Keep detailed rules in the reference files instead of duplicating them in project docs.

.agents/skills/frontend-query-mutation/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Frontend Query & Mutation"
+  short_description: "Dify TanStack Query, oRPC, and default option patterns"
+  default_prompt: "Use this skill when implementing or reviewing Dify frontend contracts, query and mutation call sites, oRPC default options, conditional queries, cache updates/invalidation, or legacy query/mutation migrations."

.agents/skills/frontend-query-mutation/references/contract-patterns.md

@@ -0,0 +1,129 @@
+# Contract Patterns
+
+## Table of Contents
+
+- Intent
+- Minimal structure
+- Core workflow
+- Query usage decision rule
+- Mutation usage decision rule
+- Thin hook decision rule
+- Anti-patterns
+- Contract rules
+- Type export
+
+## Intent
+
+- Keep contract as the single source of truth in `web/contract/*`.
+- Default query usage to call-site `useQuery(consoleQuery|marketplaceQuery.xxx.queryOptions(...))` when endpoint behavior maps 1:1 to the contract.
+- Keep abstractions minimal and preserve TypeScript inference.
+
+## Minimal Structure
+
+```text
+web/contract/
+├── base.ts
+├── router.ts
+├── marketplace.ts
+└── console/
+    ├── billing.ts
+    └── ...other domains
+web/service/client.ts
+```
+
+## Core Workflow
+
+1. Define contract in `web/contract/console/{domain}.ts` or `web/contract/marketplace.ts`.
+   - Use `base.route({...}).output(type<...>())` as the baseline.
+   - Add `.input(type<...>())` only when the request has `params`, `query`, or `body`.
+   - For `GET` without input, omit `.input(...)`; do not use `.input(type<unknown>())`.
+2. Register contract in `web/contract/router.ts`.
+   - Import directly from domain files and nest by API prefix.
+3. Consume from UI call sites via oRPC query utilities.
+
+```typescript
+import { useQuery } from '@tanstack/react-query'
+import { consoleQuery } from '@/service/client'
+
+const invoiceQuery = useQuery(consoleQuery.billing.invoices.queryOptions({
+  staleTime: 5 * 60 * 1000,
+  throwOnError: true,
+  select: invoice => invoice.url,
+}))
+```
+
+## Query Usage Decision Rule
+
+1. Default to direct `*.queryOptions(...)` usage at the call site.
+2. If 3 or more call sites share the same extra options, extract a small query helper, not a `use-*` passthrough hook.
+3. Create or keep feature hooks only for orchestration.
+   - Combine multiple queries or mutations.
+   - Share domain-level derived state or invalidation helpers.
+   - Prefer `web/features/{domain}/hooks/*` for feature-owned workflows.
+4. Treat `web/service/use-{domain}.ts` as legacy.
+   - Do not create new thin service wrappers for oRPC contracts.
+   - When touching existing wrappers, inline direct `consoleQuery` or `marketplaceQuery` consumption when the wrapper is only a passthrough.
+
+```typescript
+const invoicesBaseQueryOptions = () =>
+  consoleQuery.billing.invoices.queryOptions({ retry: false })
+
+const invoiceQuery = useQuery({
+  ...invoicesBaseQueryOptions(),
+  throwOnError: true,
+})
+```
+
+## Mutation Usage Decision Rule
+
+1. Default to mutation helpers from `consoleQuery` or `marketplaceQuery`, for example `useMutation(consoleQuery.billing.bindPartnerStack.mutationOptions(...))`.
+2. If the mutation flow is heavily custom, use oRPC clients as `mutationFn`, for example `consoleClient.xxx` or `marketplaceClient.xxx`, instead of handwritten non-oRPC mutation logic.
+
+```typescript
+const createTagMutation = useMutation(consoleQuery.tags.create.mutationOptions())
+```
+
+## Thin Hook Decision Rule
+
+Remove thin hooks when they only rename a single oRPC query or mutation helper.
+Keep hooks when they orchestrate business behavior across multiple operations, own local workflow state, or normalize a feature-specific API.
+Prefer feature vertical hooks for kept orchestration. Do not move new contract-first wrappers into `web/service/use-*`.
+
+Use:
+
+```typescript
+const deleteTagMutation = useMutation(consoleQuery.tags.delete.mutationOptions())
+```
+
+Keep:
+
+```typescript
+const applyTagBindingsMutation = useApplyTagBindingsMutation()
+```
+
+`useApplyTagBindingsMutation` is acceptable because it coordinates bind and unbind requests, computes deltas, and exposes a feature-level workflow rather than a single endpoint passthrough.
+
+## Anti-Patterns
+
+- Do not wrap `useQuery` with `options?: Partial<UseQueryOptions>`.
+- Do not split local `queryKey` and `queryFn` when oRPC `queryOptions` already exists and fits the use case.
+- Do not create thin `use-*` passthrough hooks for a single endpoint.
+- Do not create business-layer helpers whose only purpose is to call `consoleQuery.xxx.mutationOptions()` or `queryOptions()`.
+- Do not introduce new `web/service/use-*` files for oRPC contract passthroughs.
+- These patterns can degrade inference, especially around `throwOnError` and `select`, and add unnecessary indirection.
+
+## Contract Rules
+
+- Input structure: always use `{ params, query?, body? }`.
+- No-input `GET`: omit `.input(...)`; do not use `.input(type<unknown>())`.
+- Path params: use `{paramName}` in the path and match it in the `params` object.
+- Router nesting: group by API prefix, for example `/billing/*` becomes `billing: {}`.
+- No barrel files: import directly from specific files.
+- Types: import from `@/types/` and use the `type<T>()` helper.
+- Mutations: prefer `mutationOptions`; use explicit `mutationKey` mainly for defaults, filtering, and devtools.
+
+## Type Export
+
+```typescript
+export type ConsoleInputs = InferContractRouterInputs<typeof consoleRouterContract>
+```

.agents/skills/frontend-query-mutation/references/runtime-rules.md

@@ -0,0 +1,172 @@
+# Runtime Rules
+
+## Table of Contents
+
+- Conditional queries
+- oRPC default options
+- Cache invalidation
+- Key API guide
+- `mutate` vs `mutateAsync`
+- Legacy migration
+
+## Conditional Queries
+
+Prefer contract-shaped `queryOptions(...)`.
+When required input is missing, prefer `input: skipToken` instead of placeholder params or non-null assertions.
+Use `enabled` only for extra business gating after the input itself is already valid.
+
+```typescript
+import { skipToken, useQuery } from '@tanstack/react-query'
+
+// Disable the query by skipping input construction.
+function useAccessMode(appId: string | undefined) {
+  return useQuery(consoleQuery.accessControl.appAccessMode.queryOptions({
+    input: appId
+      ? { params: { appId } }
+      : skipToken,
+  }))
+}
+
+// Avoid runtime-only guards that bypass type checking.
+function useBadAccessMode(appId: string | undefined) {
+  return useQuery(consoleQuery.accessControl.appAccessMode.queryOptions({
+    input: { params: { appId: appId! } },
+    enabled: !!appId,
+  }))
+}
+```
+
+## oRPC Default Options
+
+Use `experimental_defaults` in `createTanstackQueryUtils` when a contract operation should always carry shared TanStack Query behavior, such as default stale time, mutation cache writes, or invalidation.
+
+Place defaults at the query utility creation point in `web/service/client.ts`:
+
+```typescript
+export const consoleQuery = createTanstackQueryUtils(consoleClient, {
+  path: ['console'],
+  experimental_defaults: {
+    tags: {
+      create: {
+        mutationOptions: {
+          onSuccess: (tag, _variables, _result, context) => {
+            context.client.setQueryData(
+              consoleQuery.tags.list.queryKey({
+                input: {
+                  query: {
+                    type: tag.type,
+                  },
+                },
+              }),
+              (oldTags: Tag[] | undefined) => oldTags ? [tag, ...oldTags] : oldTags,
+            )
+          },
+        },
+      },
+    },
+  },
+})
+```
+
+Rules:
+
+- Keep defaults inline in the `consoleQuery` or `marketplaceQuery` initialization when they need sibling oRPC key builders.
+- Do not create a wrapper function solely to host `createTanstackQueryUtils`.
+- Do not split defaults into a vertical feature file if that forces handwritten operation paths such as `generateOperationKey(['console', ...])`.
+- Keep feature-level orchestration in the feature vertical; keep query utility lifecycle defaults with the query utility.
+- Prefer call-site callbacks for UI feedback only; shared cache behavior belongs in oRPC defaults when it is tied to a contract operation.
+
+## Cache Invalidation
+
+Bind shared invalidation in oRPC defaults when it is tied to a contract operation.
+Use feature vertical hooks only for multi-operation workflows or domain orchestration that cannot live in a single operation default.
+Components may add UI feedback in call-site callbacks, but they should not decide which queries to invalidate.
+
+Use:
+
+- `.key()` for namespace or prefix invalidation
+- `.queryKey(...)` only for exact cache reads or writes such as `getQueryData` and `setQueryData`
+- `queryClient.invalidateQueries(...)` in mutation `onSuccess`
+
+Do not use deprecated `useInvalid` from `use-base.ts`.
+
+```typescript
+// Feature orchestration owns cache invalidation only when defaults are not enough.
+export const useUpdateAccessMode = () => {
+  const queryClient = useQueryClient()
+
+  return useMutation(consoleQuery.accessControl.updateAccessMode.mutationOptions({
+    onSuccess: () => {
+      queryClient.invalidateQueries({
+        queryKey: consoleQuery.accessControl.appWhitelistSubjects.key(),
+      })
+    },
+  }))
+}
+
+// Component only adds UI behavior.
+updateAccessMode({ appId, mode }, {
+  onSuccess: () => toast.success('...'),
+})
+
+// Avoid putting invalidation knowledge in the component.
+mutate({ appId, mode }, {
+  onSuccess: () => {
+    queryClient.invalidateQueries({
+      queryKey: consoleQuery.accessControl.appWhitelistSubjects.key(),
+    })
+  },
+})
+```
+
+## Key API Guide
+
+- `.key(...)`
+  - Use for partial matching operations.
+  - Prefer it for invalidation, refetch, and cancel patterns.
+  - Example: `queryClient.invalidateQueries({ queryKey: consoleQuery.billing.key() })`
+- `.queryKey(...)`
+  - Use for a specific query's full key.
+  - Prefer it for exact cache addressing and direct reads or writes.
+- `.mutationKey(...)`
+  - Use for a specific mutation's full key.
+  - Prefer it for mutation defaults registration, mutation-status filtering, and devtools grouping.
+
+## `mutate` vs `mutateAsync`
+
+Prefer `mutate` by default.
+Use `mutateAsync` only when Promise semantics are truly required, such as parallel mutations or sequential steps with result dependencies.
+
+Rules:
+
+- Event handlers should usually call `mutate(...)` with `onSuccess` or `onError`.
+- Every `await mutateAsync(...)` must be wrapped in `try/catch`.
+- Do not use `mutateAsync` when callbacks already express the flow clearly.
+
+```typescript
+// Default case.
+mutation.mutate(data, {
+  onSuccess: result => router.push(result.url),
+})
+
+// Promise semantics are required.
+try {
+  const order = await createOrder.mutateAsync(orderData)
+  await confirmPayment.mutateAsync({ orderId: order.id, token })
+  router.push(`/orders/${order.id}`)
+}
+catch (error) {
+  toast.error(error instanceof Error ? error.message : 'Unknown error')
+}
+```
+
+## Legacy Migration
+
+When touching old code, migrate it toward these rules:
+
+| Old pattern | New pattern |
+|---|---|
+| `useInvalid(key)` in service wrappers | oRPC defaults, or a feature vertical hook for real orchestration |
+| component-triggered invalidation after mutation | move invalidation into oRPC defaults or a feature vertical hook |
+| imperative fetch plus manual invalidation | wrap it in `useMutation(...mutationOptions(...))` |
+| `await mutateAsync()` without `try/catch` | switch to `mutate(...)` or add `try/catch` |

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

@@ -5,7 +5,7 @@ description: Generate Vitest + React Testing Library tests for Dify frontend com
 
 # Dify Frontend Testing Skill
 
-This skill enables Codex to generate high-quality, comprehensive frontend tests for the Dify project following established conventions and best practices.
+This skill enables Claude to generate high-quality, comprehensive frontend tests for the Dify project following established conventions and best practices.
 
 > **⚠️ Authoritative Source**: This skill is derived from `web/docs/test.md`. Use Vitest mock/timer APIs (`vi.*`).
 
@@ -24,27 +24,35 @@ Apply this skill when the user:
 **Do NOT apply** when:
 
 - User is asking about backend/API tests (Python/pytest)
-- User is asking about E2E tests (Cucumber + Playwright under `e2e/`)
+- User is asking about E2E tests (Playwright/Cypress)
 - User is only asking conceptual questions without code context
 
 ## Quick Reference
 
-### Key Commands
+### Tech Stack
 
-Run these commands from `web/`. From the repository root, prefix them with `pnpm -C web`.
+| Tool | Version | Purpose |
+|------|---------|---------|
+| Vitest | 4.0.16 | Test runner |
+| React Testing Library | 16.0 | Component testing |
+| jsdom | - | Test environment |
+| nock | 14.0 | HTTP mocking |
+| TypeScript | 5.x | Type safety |
+
+### Key Commands
 
 ```bash
 # Run all tests
 pnpm test
 
 # Watch mode
-pnpm test --watch
+pnpm test:watch
 
 # Run specific file
 pnpm test path/to/file.spec.tsx
 
 # Generate coverage report
-pnpm test --coverage
+pnpm test:coverage
 
 # Analyze component complexity
 pnpm analyze-component <path>
@@ -220,10 +228,7 @@ Every test should clearly separate:
 ### 2. Black-Box Testing
 
 - Test observable behavior, not implementation details
-- Use semantic queries (`getByRole` with accessible `name`, `getByLabelText`, `getByPlaceholderText`, `getByText`, and scoped `within(...)`)
-- Treat `getByTestId` as a last resort. If a control cannot be found by role/name, label, landmark, or dialog scope, fix the component accessibility first instead of adding or relying on `data-testid`.
-- Remove production `data-testid` attributes when semantic selectors can cover the behavior. Keep them only for non-visual mocked boundaries, editor/browser shims such as Monaco, canvas/chart output, or third-party widgets with no accessible DOM in the test environment.
-- Do not assert decorative icons by test id. Assert the named control that contains them, or mark decorative icons `aria-hidden`.
+- Use semantic queries (getByRole, getByLabelText)
 - Avoid testing internal state directly
 - **Prefer pattern matching over hardcoded strings** in assertions:
 

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

@@ -56,7 +56,7 @@ See [Zustand Store Testing](#zustand-store-testing) section for full details.
 
 | Location | Purpose |
 |----------|---------|
-| `web/vitest.setup.ts` | Global mocks shared by all tests (`react-i18next`, `zustand`, clipboard, FloatingPortal, Monaco, localStorage`) |
+| `web/vitest.setup.ts` | Global mocks shared by all tests (`react-i18next`, `next/image`, `zustand`) |
 | `web/__mocks__/zustand.ts` | Zustand mock implementation (auto-resets stores after each test) |
 | `web/__mocks__/` | Reusable mock factories shared across multiple test files |
 | Test file | Test-specific mocks, inline with `vi.mock()` |
@@ -216,21 +216,28 @@ describe('Component', () => {
 })
 ```
 
-### 5. HTTP and `fetch` Mocking
+### 5. HTTP Mocking with Nock
 
 ```typescript
+import nock from 'nock'
+
+const GITHUB_HOST = 'https://api.github.com'
+const GITHUB_PATH = '/repos/owner/repo'
+
+const mockGithubApi = (status: number, body: Record<string, unknown>, delayMs = 0) => {
+  return nock(GITHUB_HOST)
+    .get(GITHUB_PATH)
+    .delay(delayMs)
+    .reply(status, body)
+}
+
 describe('GithubComponent', () => {
-  beforeEach(() => {
-    vi.clearAllMocks()
+  afterEach(() => {
+    nock.cleanAll()
   })
 
   it('should display repo info', async () => {
-    vi.mocked(globalThis.fetch).mockResolvedValueOnce(
-      new Response(JSON.stringify({ name: 'dify', stars: 1000 }), {
-        status: 200,
-        headers: { 'Content-Type': 'application/json' },
-      }),
-    )
+    mockGithubApi(200, { name: 'dify', stars: 1000 })
     
     render(<GithubComponent />)
     
@@ -240,12 +247,7 @@ describe('GithubComponent', () => {
   })
 
   it('should handle API error', async () => {
-    vi.mocked(globalThis.fetch).mockResolvedValueOnce(
-      new Response(JSON.stringify({ message: 'Server error' }), {
-        status: 500,
-        headers: { 'Content-Type': 'application/json' },
-      }),
-    )
+    mockGithubApi(500, { message: 'Server error' })
     
     render(<GithubComponent />)
     
@@ -256,8 +258,6 @@ describe('GithubComponent', () => {
 })
 ```
 
-Prefer mocking `@/service/*` modules or spying on `global.fetch` / `ky` clients with deterministic responses. Do not introduce an HTTP interception dependency such as `nock` or MSW unless it is already declared in the workspace or adding it is part of the task.
-
 ### 6. Context Providers
 
 ```typescript
@@ -332,7 +332,7 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
 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 leave HTTP mocks or service mock state leaking between tests
+1. Don't forget to clean up nock after each test
 1. Don't use `any` types in mocks without necessity
 
 ### Mock Decision Tree

.agents/skills/frontend-testing/references/workflow.md

@@ -227,12 +227,12 @@ Failing tests compound:
 
 **Fix failures immediately before proceeding.**
 
-## Integration with Codex's Todo Feature
+## Integration with Claude's Todo Feature
 
-When using Codex for multi-file testing:
+When using Claude for multi-file testing:
 
-1. **Create a todo list** before starting
-1. **Process one file at a time**
+1. **Ask Claude to create a todo list** before starting
+1. **Request one file at a time** or ensure Claude processes incrementally
 1. **Verify each test passes** before asking for the next
 1. **Mark todos complete** as you progress
 

.agents/skills/how-to-write-component/SKILL.md

@@ -1,71 +0,0 @@
----
-name: how-to-write-component
-description: React/TypeScript component style guide. Use when writing, refactoring, or reviewing React components, especially around props typing, state boundaries, shared local state with Jotai atoms, API types, query/mutation contracts, navigation, memoization, wrappers, and empty-state handling.
----
-
-# How To Write A Component
-
-Use this as the decision guide for React/TypeScript component structure. Existing code is reference material, not automatic precedent; when it conflicts with these rules, adapt the approach instead of reproducing the violation.
-
-## Core Defaults
-
-- Search before adding UI, hooks, helpers, or styling patterns. Reuse existing base components, feature components, hooks, utilities, and design styles when they fit.
-- Group code by feature workflow, route, or ownership area: components, hooks, local types, query helpers, atoms, constants, and small utilities should live near the code that changes with them.
-- Promote code to shared only when multiple verticals need the same stable primitive. Otherwise keep it local and compose shared primitives inside the owning feature.
-- Use Tailwind CSS v4.1+ rules via the `tailwind-css-rules` skill. Prefer v4 utilities, `gap`, `text-size/line-height`, `min-h-dvh`, and avoid deprecated utilities and `@apply`.
-
-## Ownership
-
-- Put local state, queries, mutations, handlers, and derived UI data in the lowest component that uses them. Extract a purpose-built owner component only when the logic has no natural home.
-- Repeated TanStack query calls in sibling components are acceptable when each component independently consumes the data. Do not hoist a query only because it is duplicated; TanStack Query handles deduplication and cache sharing.
-- Hoist state, queries, or callbacks to a parent only when the parent consumes the data, coordinates shared loading/error/empty UI, needs one consistent snapshot, or owns a workflow spanning children.
-- Avoid prop drilling. One pass-through layer is acceptable; repeated forwarding means ownership should move down or into feature-scoped Jotai UI state. Keep server/cache state in query and API data flow.
-- Keep callbacks in a parent only for workflow coordination such as form submission, shared selection, batch behavior, or navigation. Otherwise let the child or row own its action.
-- Prefer uncontrolled DOM state and CSS variables before adding controlled props.
-
-## Components, Props, And Types
-
-- Type component signatures directly; do not use `FC` or `React.FC`.
-- Prefer `function` for top-level components and module helpers. Use arrow functions for local callbacks, handlers, and lambda-style APIs.
-- Prefer named exports. Use default exports only where the framework requires them, such as Next.js route files.
-- Type simple one-off props inline. Use a named `Props` type only when reused, exported, complex, or clearer.
-- Use API-generated or API-returned types at component boundaries. Keep small UI conversion helpers beside the component that needs them.
-- Name values by their domain role and backend API contract, and keep that name stable across the call chain, especially IDs like `appInstanceId`. Normalize framework or route params at the boundary.
-- Keep fallback and invariant checks at the lowest component that already handles that state; callers should pass raw values through instead of duplicating checks.
-
-## Queries And Mutations
-
-- Keep `web/contract/*` as the single source of truth for API shape; follow existing domain/router patterns and the `{ params, query?, body? }` input shape.
-- Consume queries directly with `useQuery(consoleQuery.xxx.queryOptions(...))` or `useQuery(marketplaceQuery.xxx.queryOptions(...))`.
-- Avoid pass-through hooks and thin `web/service/use-*` wrappers that only rename `queryOptions()` or `mutationOptions()`. Extract a small `queryOptions` helper only when repeated call-site options justify it.
-- Keep feature hooks for real orchestration, workflow state, or shared domain behavior.
-- For missing required query input, use `input: skipToken`; use `enabled` only for extra business gating after the input is valid.
-- Consume mutations directly with `useMutation(consoleQuery.xxx.mutationOptions(...))` or `useMutation(marketplaceQuery.xxx.mutationOptions(...))`; use oRPC clients as `mutationFn` only for custom flows.
-- Put shared cache behavior in `createTanstackQueryUtils(...experimental_defaults...)`; components may add UI feedback callbacks, but should not own shared invalidation rules.
-- Do not use deprecated `useInvalid` or `useReset`.
-- Prefer `mutate(...)`; use `mutateAsync(...)` only when Promise semantics are required, and wrap awaited calls in `try/catch`.
-
-## Component Boundaries
-
-- Use the first level below a page or tab to organize independent page sections when it adds real structure. This layer is layout/semantic first, not automatically the data owner.
-- Split deeper components by the data and state each layer actually needs. Each component should access only necessary data, and ownership should stay at the lowest consumer.
-- Keep cohesive forms, menu bodies, and one-off helpers local unless they need their own state, reuse, or semantic boundary.
-- Separate hidden secondary surfaces from the trigger's main flow. For dialogs, dropdowns, popovers, and similar branches, extract a small local component that owns the trigger, open state, and hidden content when it would obscure the parent flow.
-- Preserve composability by separating behavior ownership from layout ownership. A dropdown action may own its trigger, open state, and menu content; the caller owns placement such as slots, offsets, and alignment.
-- Avoid unnecessary DOM hierarchy. Do not add wrapper elements unless they provide layout, semantics, accessibility, state ownership, or integration with a library API; prefer fragments or styling an existing element when possible.
-- Avoid shallow wrappers and prop renaming unless the wrapper adds validation, orchestration, error handling, state ownership, or a real semantic boundary.
-
-## You Might Not Need An Effect
-
-- Use Effects only to synchronize with external systems such as browser APIs, non-React widgets, subscriptions, timers, analytics that must run because the component was shown, or imperative DOM integration.
-- Do not use Effects to transform props or state for rendering. Calculate derived values during render, and use `useMemo` only when the calculation is actually expensive.
-- Do not use Effects to handle user actions. Put action-specific logic in the event handler where the cause is known.
-- Do not use Effects to copy one state value into another state value representing the same concept. Pick one source of truth and derive the rest during render.
-- Do not reset or adjust state from props with an Effect. Prefer a `key` reset, storing a stable ID and deriving the selected object, or guarded same-component render-time adjustment when truly necessary.
-- Prefer framework data APIs or TanStack Query for data fetching instead of writing request Effects in components.
-- If an Effect still seems necessary, first name the external system it synchronizes with. If there is no external system, remove the Effect and restructure the state or event flow.
-
-## Navigation And Performance
-
-- Prefer `Link` for normal navigation. Use router APIs only for command-flow side effects such as mutation success, guarded redirects, or form submission.
-- Avoid `memo`, `useMemo`, and `useCallback` unless there is a clear performance reason.

.agents/skills/tailwind-css-rules/SKILL.md

@@ -1,367 +0,0 @@
----
-name: tailwind-css-rules
-description: Tailwind CSS v4.1+ rules and best practices. Use when writing, reviewing, refactoring, or upgrading Tailwind CSS classes and styles, especially v4 utility migrations, layout spacing, typography, responsive variants, dark mode, gradients, CSS variables, and component styling.
----
-
-# Tailwind CSS Rules and Best Practices
-
-## Core Principles
-
-- **Always use Tailwind CSS v4.1+** - Ensure the codebase is using the latest version
-- **Do not use deprecated or removed utilities** - ALWAYS use the replacement
-- **Never use `@apply`** - Use CSS variables, the `--spacing()` function, or framework components instead
-- **Check for redundant classes** - Remove any classes that aren't necessary
-- **Group elements logically** to simplify responsive tweaks later
-
-## Upgrading to Tailwind CSS v4
-
-### Before Upgrading
-
-- **Always read the upgrade documentation first** - Read https://tailwindcss.com/docs/upgrade-guide and https://tailwindcss.com/blog/tailwindcss-v4 before starting an upgrade.
-- Ensure the git repository is in a clean state before starting
-
-### Upgrade Process
-
-1. Run the upgrade command: `npx @tailwindcss/upgrade@latest` for both major and minor updates
-2. The tool will convert JavaScript config files to the new CSS format
-3. Review all changes extensively to clean up any false positives
-4. Test thoroughly across your application
-
-## Breaking Changes Reference
-
-### Removed Utilities (NEVER use these in v4)
-
-| ❌ Deprecated           | ✅ Replacement                                    |
-| ----------------------- | ------------------------------------------------- |
-| `bg-opacity-*`          | Use opacity modifiers like `bg-black/50`          |
-| `text-opacity-*`        | Use opacity modifiers like `text-black/50`        |
-| `border-opacity-*`      | Use opacity modifiers like `border-black/50`      |
-| `divide-opacity-*`      | Use opacity modifiers like `divide-black/50`      |
-| `ring-opacity-*`        | Use opacity modifiers like `ring-black/50`        |
-| `placeholder-opacity-*` | Use opacity modifiers like `placeholder-black/50` |
-| `flex-shrink-*`         | `shrink-*`                                        |
-| `flex-grow-*`           | `grow-*`                                          |
-| `overflow-ellipsis`     | `text-ellipsis`                                   |
-| `decoration-slice`      | `box-decoration-slice`                            |
-| `decoration-clone`      | `box-decoration-clone`                            |
-
-### Renamed Utilities
-
-Use the v4 name when migrating code that still carries Tailwind v3 semantics. Do not blanket-replace existing v4 classes: classes such as `rounded-sm`, `shadow-sm`, `ring-1`, and `ring-2` are valid in this codebase when they intentionally represent the current design scale.
-
-| ❌ v3 pattern       | ✅ v4 pattern                                      |
-| ------------------- | -------------------------------------------------- |
-| `bg-gradient-*`     | `bg-linear-*`                                      |
-| old shadow scale    | verify against the current Tailwind/design scale   |
-| old blur scale      | verify against the current Tailwind/design scale   |
-| old radius scale    | use the Dify radius token mapping when applicable  |
-| `outline-none`      | `outline-hidden`                                   |
-| bare `ring` utility | use an explicit ring width such as `ring-1`/`ring-2`/`ring-3` |
-
-For Figma radius tokens, follow `packages/dify-ui/AGENTS.md`. For example, `--radius/xs` maps to `rounded-sm`; do not rewrite it to `rounded-xs`.
-
-## Layout and Spacing Rules
-
-### Flexbox and Grid Spacing
-
-#### Always use gap utilities for internal spacing
-
-Gap provides consistent spacing without edge cases (no extra space on last items). It's cleaner and more maintainable than margins on children.
-
-```html
-<!-- ❌ Don't do this -->
-<div class="flex">
-  <div class="mr-4">Item 1</div>
-  <div class="mr-4">Item 2</div>
-  <div>Item 3</div>
-  <!-- No margin on last -->
-</div>
-
-<!-- ✅ Do this instead -->
-<div class="flex gap-4">
-  <div>Item 1</div>
-  <div>Item 2</div>
-  <div>Item 3</div>
-</div>
-```
-
-#### Gap vs Space utilities
-
-- **Never use `space-x-*` or `space-y-*` in flex/grid layouts** - always use gap
-- Space utilities add margins to children and have issues with wrapped items
-- Gap works correctly with flex-wrap and all flex directions
-
-```html
-<!-- ❌ Avoid space utilities in flex containers -->
-<div class="flex flex-wrap space-x-4">
-  <!-- Space utilities break with wrapped items -->
-</div>
-
-<!-- ✅ Use gap for consistent spacing -->
-<div class="flex flex-wrap gap-4">
-  <!-- Gap works perfectly with wrapping -->
-</div>
-```
-
-### General Spacing Guidelines
-
-- **Prefer top and left margins** over bottom and right margins (unless conditionally rendered)
-- **Use padding on parent containers** instead of bottom margins on the last child
-- **Always use `min-h-dvh` instead of `min-h-screen`** - `min-h-screen` is buggy on mobile Safari
-- **Prefer `size-*` utilities** over separate `w-*` and `h-*` when setting equal dimensions
-- For max-widths, prefer the container scale (e.g., `max-w-2xs` over `max-w-72`)
-
-## Typography Rules
-
-### Line Heights
-
-- **Never use `leading-*` classes** - Always use line height modifiers with text size
-- **Always use fixed line heights from the spacing scale** - Don't use named values
-
-```html
-<!-- ❌ Don't do this -->
-<p class="text-base leading-7">Text with separate line height</p>
-<p class="text-lg leading-relaxed">Text with named line height</p>
-
-<!-- ✅ Do this instead -->
-<p class="text-base/7">Text with line height modifier</p>
-<p class="text-lg/8">Text with specific line height</p>
-```
-
-### Font Size Reference
-
-Be precise with font sizes - know the actual pixel values:
-
-- `text-xs` = 12px
-- `text-sm` = 14px
-- `text-base` = 16px
-- `text-lg` = 18px
-- `text-xl` = 20px
-
-## Color and Opacity
-
-### Opacity Modifiers
-
-**Never use `bg-opacity-*`, `text-opacity-*`, etc.** - use the opacity modifier syntax:
-
-```html
-<!-- ❌ Don't do this -->
-<div class="bg-red-500 bg-opacity-60">Old opacity syntax</div>
-
-<!-- ✅ Do this instead -->
-<div class="bg-red-500/60">Modern opacity syntax</div>
-```
-
-## Responsive Design
-
-### Breakpoint Optimization
-
-- **Check for redundant classes across breakpoints**
-- **Only add breakpoint variants when values change**
-
-```html
-<!-- ❌ Redundant breakpoint classes -->
-<div class="px-4 md:px-4 lg:px-4">
-  <!-- md:px-4 and lg:px-4 are redundant -->
-</div>
-
-<!-- ✅ Efficient breakpoint usage -->
-<div class="px-4 lg:px-8">
-  <!-- Only specify when value changes -->
-</div>
-```
-
-## Dark Mode
-
-### Dark Mode Best Practices
-
-- Use the plain `dark:` variant pattern
-- Put light mode styles first, then dark mode styles
-- Ensure `dark:` variant comes before other variants
-
-```html
-<!-- ✅ Correct dark mode pattern -->
-<div class="bg-white text-black dark:bg-black dark:text-white">
-  <button class="hover:bg-gray-100 dark:hover:bg-gray-800">Click me</button>
-</div>
-```
-
-## Gradient Utilities
-
-- **ALWAYS Use `bg-linear-*` instead of `bg-gradient-*` utilities** - The gradient utilities were renamed in v4
-- Use the new `bg-radial` or `bg-radial-[<position>]` to create radial gradients
-- Use the new `bg-conic` or `bg-conic-*` to create conic gradients
-
-```html
-<!-- ✅ Use the new gradient utilities -->
-<div class="h-14 bg-linear-to-br from-violet-500 to-fuchsia-500"></div>
-<div
-  class="size-18 bg-radial-[at_50%_75%] from-sky-200 via-blue-400 to-indigo-900 to-90%"
-></div>
-<div
-  class="size-24 bg-conic-180 from-indigo-600 via-indigo-50 to-indigo-600"
-></div>
-
-<!-- ❌ Do not use bg-gradient-* utilities -->
-<div class="h-14 bg-gradient-to-br from-violet-500 to-fuchsia-500"></div>
-```
-
-## Working with CSS Variables
-
-### Accessing Theme Values
-
-Tailwind CSS v4 exposes all theme values as CSS variables:
-
-```css
-/* Access colors, and other theme values */
-.custom-element {
-  background: var(--color-red-500);
-  border-radius: var(--radius-lg);
-}
-```
-
-### The `--spacing()` Function
-
-Use the dedicated `--spacing()` function for spacing calculations:
-
-```css
-.custom-class {
-  margin-top: calc(100vh - --spacing(16));
-}
-```
-
-### Extending theme values
-
-Use CSS to extend theme values:
-
-```css
-@import "tailwindcss";
-
-@theme {
-  --color-mint-500: oklch(0.72 0.11 178);
-}
-```
-
-```html
-<div class="bg-mint-500">
-  <!-- ... -->
-</div>
-```
-
-## New v4 Features
-
-### Container Queries
-
-Use the `@container` class and size variants:
-
-```html
-<article class="@container">
-  <div class="flex flex-col @md:flex-row @lg:gap-8">
-    <img class="w-full @md:w-48" />
-    <div class="mt-4 @md:mt-0">
-      <!-- Content adapts to container size -->
-    </div>
-  </div>
-</article>
-```
-
-### Container Query Units
-
-Use container-based units like `cqw` for responsive sizing:
-
-```html
-<div class="@container">
-  <h1 class="text-[50cqw]">Responsive to container width</h1>
-</div>
-```
-
-### Text Shadows (v4.1)
-
-Use text-shadow-\* utilities from text-shadow-2xs to text-shadow-lg:
-
-```html
-<!-- ✅ Text shadow examples -->
-<h1 class="text-shadow-lg">Large shadow</h1>
-<p class="text-shadow-sm/50">Small shadow with opacity</p>
-```
-
-### Masking (v4.1)
-
-Use the new composable mask utilities for image and gradient masks:
-
-```html
-<!-- ✅ Linear gradient masks on specific sides -->
-<div class="mask-t-from-50%">Top fade</div>
-<div class="mask-b-from-20% mask-b-to-80%">Bottom gradient</div>
-<div class="mask-linear-from-white mask-linear-to-black/60">
-  Fade from white to black
-</div>
-
-<!-- ✅ Radial gradient masks -->
-<div class="mask-radial-[100%_100%] mask-radial-from-75% mask-radial-at-left">
-  Radial mask
-</div>
-```
-
-## Component Patterns
-
-### Avoiding Utility Inheritance
-
-Don't add utilities to parents that you override in children:
-
-```html
-<!-- ❌ Avoid this pattern -->
-<div class="text-center">
-  <h1>Centered Heading</h1>
-  <div class="text-left">Left-aligned content</div>
-</div>
-
-<!-- ✅ Better approach -->
-<div>
-  <h1 class="text-center">Centered Heading</h1>
-  <div>Left-aligned content</div>
-</div>
-```
-
-### Component Extraction
-
-- Extract repeated patterns into framework components, not CSS classes
-- Keep utility classes in templates/JSX
-- Use data attributes for complex state-based styling
-
-## CSS Best Practices
-
-### Nesting Guidelines
-
-- Use nesting when styling both parent and children
-- Avoid empty parent selectors
-
-```css
-/* ✅ Good nesting - parent has styles */
-.card {
-  padding: --spacing(4);
-
-  > .card-title {
-    font-weight: bold;
-  }
-}
-
-/* ❌ Avoid empty parents */
-ul {
-  > li {
-    /* Parent has no styles */
-  }
-}
-```
-
-## Common Pitfalls to Avoid
-
-1. **Using old opacity utilities** - Always use `/opacity` syntax like `bg-red-500/60`
-2. **Redundant breakpoint classes** - Only specify changes
-3. **Space utilities in flex/grid** - Always use gap
-4. **Leading utilities** - Use line-height modifiers like `text-sm/6`
-5. **Arbitrary values** - Use the design scale
-6. **@apply directive** - Use components or CSS variables
-7. **min-h-screen on mobile** - Use min-h-dvh
-8. **Separate width/height** - Use size utilities when equal
-9. **Arbitrary values** - Always use Tailwind's predefined scale whenever possible (e.g., use `ml-4` over `ml-[16px]`)

.github/workflows/api-tests.yml

@@ -99,7 +99,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/envs/middleware.env.example docker/middleware.env
+          cp docker/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh

.github/workflows/autofix.yml

@@ -116,12 +116,6 @@ jobs:
         if: github.event_name != 'merge_group'
         uses: ./.github/actions/setup-web
 
-      - name: Generate API docs
-        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
-        run: |
-          cd api
-          uv run dev/generate_swagger_markdown_docs.py --swagger-dir openapi --markdown-dir openapi/markdown
-
       - name: ESLint autofix
         if: github.event_name != 'merge_group' && steps.web-changes.outputs.any_changed == 'true'
         run: |

.github/workflows/db-migration-test.yml

@@ -37,7 +37,7 @@ jobs:
       - name: Prepare middleware env
         run: |
           cd docker
-          cp envs/middleware.env.example middleware.env
+          cp middleware.env.example middleware.env
 
       - name: Set up Middlewares
         uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
@@ -87,7 +87,7 @@ jobs:
       - name: Prepare middleware env for MySQL
         run: |
           cd docker
-          cp envs/middleware.env.example middleware.env
+          cp middleware.env.example middleware.env
           sed -i 's/DB_TYPE=postgresql/DB_TYPE=mysql/' middleware.env
           sed -i 's/DB_HOST=db_postgres/DB_HOST=db_mysql/' middleware.env
           sed -i 's/DB_PORT=5432/DB_PORT=3306/' middleware.env

.github/workflows/labeler.yml

@@ -9,6 +9,6 @@ jobs:
       pull-requests: write
     runs-on: depot-ubuntu-24.04
     steps:
-      - uses: actions/labeler@f27b608878404679385c85cfa523b85ccb86e213 # v6.1.0
+      - uses: actions/labeler@634933edcd8ababfe52f92936142cc22ac488b1b # v6.0.1
         with:
           sync-labels: true

.github/workflows/main-ci.yml

@@ -57,7 +57,7 @@ jobs:
               - '.github/workflows/api-tests.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/envs/middleware.env.example'
+              - 'docker/middleware.env.example'
               - 'docker/docker-compose.middleware.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'
@@ -84,7 +84,7 @@ jobs:
               - 'pnpm-workspace.yaml'
               - '.nvmrc'
               - 'docker/docker-compose.middleware.yaml'
-              - 'docker/envs/middleware.env.example'
+              - 'docker/middleware.env.example'
               - '.github/workflows/web-e2e.yml'
               - '.github/actions/setup-web/**'
             vdb:
@@ -94,7 +94,7 @@ jobs:
               - '.github/workflows/vdb-tests.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/envs/middleware.env.example'
+              - 'docker/middleware.env.example'
               - 'docker/docker-compose.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'
@@ -116,7 +116,7 @@ jobs:
               - '.github/workflows/db-migration-test.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/envs/middleware.env.example'
+              - 'docker/middleware.env.example'
               - 'docker/docker-compose.middleware.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'

.github/workflows/pyrefly-diff-comment.yml

@@ -77,28 +77,10 @@ jobs:
             }
 
             if (diff.trim()) {
-              const body = '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>';
-              const marker = '### Pyrefly Diff';
-              const { data: comments } = await github.rest.issues.listComments({
+              await github.rest.issues.createComment({
                 issue_number: prNumber,
                 owner: context.repo.owner,
                 repo: context.repo.repo,
+                body: '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>',
               });
-              const existing = comments.find((comment) => comment.body.startsWith(marker));
-
-              if (existing) {
-                await github.rest.issues.updateComment({
-                  comment_id: existing.id,
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  body,
-                });
-              } else {
-                await github.rest.issues.createComment({
-                  issue_number: prNumber,
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  body,
-                });
-              }
             }

.github/workflows/pyrefly-diff.yml

@@ -103,26 +103,9 @@ jobs:
                 ].join('\n')
               : '### Pyrefly Diff\nNo changes detected.';
 
-            const marker = '### Pyrefly Diff';
-            const { data: comments } = await github.rest.issues.listComments({
+            await github.rest.issues.createComment({
               issue_number: prNumber,
               owner: context.repo.owner,
               repo: context.repo.repo,
+              body,
             });
-            const existing = comments.find((comment) => comment.body.startsWith(marker));
-
-            if (existing) {
-              await github.rest.issues.updateComment({
-                comment_id: existing.id,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body,
-              });
-            } else {
-              await github.rest.issues.createComment({
-                issue_number: prNumber,
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                body,
-              });
-            }

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

@@ -158,7 +158,7 @@ jobs:
 
       - name: Run Claude Code for Translation Sync
         if: steps.context.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@476e359e6203e73dad705c8b322e333fabbd7416 # v1.0.119
+        uses: anthropics/claude-code-action@fefa07e9c665b7320f08c3b525980457f22f58aa # v1.0.111
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/vdb-tests-full.yml

@@ -51,7 +51,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/envs/middleware.env.example docker/middleware.env
+          cp docker/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh

.github/workflows/vdb-tests.yml

@@ -48,7 +48,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/envs/middleware.env.example docker/middleware.env
+          cp docker/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh

Makefile

@@ -3,10 +3,6 @@ DOCKER_REGISTRY=langgenius
 WEB_IMAGE=$(DOCKER_REGISTRY)/dify-web
 API_IMAGE=$(DOCKER_REGISTRY)/dify-api
 VERSION=latest
-DOCKER_DIR=docker
-DOCKER_MIDDLEWARE_ENV=$(DOCKER_DIR)/middleware.env
-DOCKER_MIDDLEWARE_ENV_EXAMPLE=$(DOCKER_DIR)/envs/middleware.env.example
-DOCKER_MIDDLEWARE_PROJECT=dify-middlewares-dev
 
 # Default target - show help
 .DEFAULT_GOAL := help
@@ -21,13 +17,8 @@ dev-setup: prepare-docker prepare-web prepare-api
 # Step 1: Prepare Docker middleware
 prepare-docker:
 	@echo "🐳 Setting up Docker middleware..."
-	@if [ ! -f "$(DOCKER_MIDDLEWARE_ENV)" ]; then \
-		cp "$(DOCKER_MIDDLEWARE_ENV_EXAMPLE)" "$(DOCKER_MIDDLEWARE_ENV)"; \
-		echo "Docker middleware.env created"; \
-	else \
-		echo "Docker middleware.env already exists"; \
-	fi
-	@cd $(DOCKER_DIR) && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p $(DOCKER_MIDDLEWARE_PROJECT) up -d
+	@cp -n docker/middleware.env.example docker/middleware.env 2>/dev/null || echo "Docker middleware.env already exists"
+	@cd docker && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p dify-middlewares-dev up -d
 	@echo "✅ Docker middleware started"
 
 # Step 2: Prepare web environment
@@ -48,18 +39,12 @@ prepare-api:
 # Clean dev environment
 dev-clean:
 	@echo "⚠️  Stopping Docker containers..."
-	@if [ -f "$(DOCKER_MIDDLEWARE_ENV)" ]; then \
-		cd $(DOCKER_DIR) && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p $(DOCKER_MIDDLEWARE_PROJECT) down; \
-	else \
-		echo "Docker middleware.env does not exist, skipping compose down"; \
-	fi
+	@cd docker && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p dify-middlewares-dev down
 	@echo "🗑️  Removing volumes..."
 	@rm -rf docker/volumes/db
-	@rm -rf docker/volumes/mysql
 	@rm -rf docker/volumes/redis
 	@rm -rf docker/volumes/plugin_daemon
 	@rm -rf docker/volumes/weaviate
-	@rm -rf docker/volumes/sandbox/dependencies
 	@rm -rf api/storage
 	@echo "✅ Cleanup complete"
 
@@ -86,13 +71,13 @@ type-check:
 	@echo "📝 Running type checks (basedpyright + pyrefly + mypy)..."
 	@./dev/basedpyright-check $(PATH_TO_CHECK)
 	@./dev/pyrefly-check-local
-	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --exclude 'dev/generate_swagger_specs.py' --check-untyped-defs --disable-error-code=import-untyped .
+	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
 	@echo "✅ Type checks complete"
 
 type-check-core:
 	@echo "📝 Running core type checks (basedpyright + mypy)..."
 	@./dev/basedpyright-check $(PATH_TO_CHECK)
-	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --exclude 'dev/generate_swagger_specs.py'  --exclude 'dev/generate_fastopenapi_specs.py' --check-untyped-defs --disable-error-code=import-untyped .
+	@uv --directory api run mypy --exclude-gitignore --exclude 'tests/' --exclude 'migrations/' --check-untyped-defs --disable-error-code=import-untyped .
 	@echo "✅ Core type checks complete"
 
 test:
@@ -147,7 +132,7 @@ help:
 	@echo "  make prepare-docker - Set up Docker middleware"
 	@echo "  make prepare-web    - Set up web environment"
 	@echo "  make prepare-api    - Set up API environment"
-	@echo "  make dev-clean      - Stop Docker middleware containers and remove dev data"
+	@echo "  make dev-clean      - Stop Docker middleware containers"
 	@echo ""
 	@echo "Backend Code Quality:"
 	@echo "  make format         - Format code with ruff"

README.md

@@ -74,8 +74,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
 The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
 
 ```bash
-cd dify
-cd docker
+cd dify/docker
 cp .env.example .env
 docker compose up -d
 ```
@@ -137,7 +136,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ### Custom configurations
 
-If you need to customize the configuration, edit `docker/.env`. The essential startup defaults live in [`docker/.env.example`](docker/.env.example), and optional advanced variables are split under `docker/envs/` by theme. After making any changes, re-run `docker compose up -d` from the `docker` directory. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 ### Metrics Monitoring with Grafana
 

api/.env.example

@@ -34,7 +34,7 @@ TRIGGER_URL=http://localhost:5001
 FILES_ACCESS_TIMEOUT=300
 
 # Collaboration mode toggle
-ENABLE_COLLABORATION_MODE=true
+ENABLE_COLLABORATION_MODE=false
 
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
@@ -88,10 +88,6 @@ REDIS_HEALTH_CHECK_INTERVAL=30
 CELERY_BROKER_URL=redis://:difyai123456@localhost:${REDIS_PORT}/1
 CELERY_BACKEND=redis
 
-# Ops trace retry configuration
-OPS_TRACE_RETRYABLE_DISPATCH_MAX_RETRIES=60
-OPS_TRACE_RETRYABLE_DISPATCH_DELAY_SECONDS=5
-
 # Database configuration
 DB_TYPE=postgresql
 DB_USERNAME=postgres
@@ -102,8 +98,6 @@ DB_DATABASE=dify
 
 SQLALCHEMY_POOL_PRE_PING=true
 SQLALCHEMY_POOL_TIMEOUT=30
-# Connection pool reset behavior on return
-SQLALCHEMY_POOL_RESET_ON_RETURN=rollback
 
 # Storage configuration
 # use for store upload files, private keys...
@@ -387,7 +381,7 @@ VIKINGDB_ACCESS_KEY=your-ak
 VIKINGDB_SECRET_KEY=your-sk
 VIKINGDB_REGION=cn-shanghai
 VIKINGDB_HOST=api-vikingdb.xxx.volces.com
-VIKINGDB_SCHEME=http
+VIKINGDB_SCHEMA=http
 VIKINGDB_CONNECTION_TIMEOUT=30
 VIKINGDB_SOCKET_TIMEOUT=30
 
@@ -438,6 +432,8 @@ UPLOAD_FILE_EXTENSION_BLACKLIST=
 
 # Model configuration
 MULTIMODAL_SEND_FORMAT=base64
+PROMPT_GENERATION_MAX_TOKENS=512
+CODE_GENERATION_MAX_TOKENS=1024
 PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false
 
 # Mail configuration, support: resend, smtp, sendgrid

api/AGENTS.md

@@ -193,10 +193,6 @@ Before opening a PR / submitting:
 - 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.
-- For Flask-RESTX controller request, query, and response schemas, follow `controllers/API_SCHEMA_GUIDE.md`.
-  In short: use Pydantic models, document GET query params with `query_params_from_model(...)`, register response
-  DTOs with `register_response_schema_models(...)`, serialize with `ResponseModel.model_validate(...).model_dump(...)`,
-  and avoid adding new legacy `ns.model(...)`, `@marshal_with(...)`, or GET `@ns.expect(...)` patterns.
 
 ### Miscellaneous
 

api/app_factory.py

@@ -181,6 +181,7 @@ def initialize_extensions(app: DifyApp):
         ext_import_modules,
         ext_orjson,
         ext_forward_refs,
+        ext_set_secretkey,
         ext_compress,
         ext_code_based_extension,
         ext_database,
@@ -188,7 +189,6 @@ def initialize_extensions(app: DifyApp):
         ext_migrate,
         ext_redis,
         ext_storage,
-        ext_set_secretkey,
         ext_logstore,  # Initialize logstore after storage, before celery
         ext_celery,
         ext_login,

api/configs/feature/__init__.py

@@ -23,9 +23,9 @@ class SecurityConfig(BaseSettings):
     """
 
     SECRET_KEY: str = Field(
-        description="Secret key for secure session cookie signing. "
-        "Leave empty to let Dify generate a persistent key in the storage directory, "
-        "or set a strong value via the `SECRET_KEY` environment variable.",
+        description="Secret key for secure session cookie signing."
+        "Make sure you are changing this key for your deployment with a strong key."
+        "Generate a strong key using `openssl rand -base64 42` or set via the `SECRET_KEY` environment variable.",
         default="",
     )
 
@@ -1137,18 +1137,6 @@ class MultiModalTransferConfig(BaseSettings):
     )
 
 
-class OpsTraceConfig(BaseSettings):
-    OPS_TRACE_RETRYABLE_DISPATCH_MAX_RETRIES: PositiveInt = Field(
-        description="Maximum retry attempts for transient ops trace provider dispatch failures.",
-        default=60,
-    )
-
-    OPS_TRACE_RETRYABLE_DISPATCH_DELAY_SECONDS: PositiveInt = Field(
-        description="Delay in seconds between transient ops trace provider dispatch retry attempts.",
-        default=5,
-    )
-
-
 class CeleryBeatConfig(BaseSettings):
     CELERY_BEAT_SCHEDULER_TIME: int = Field(
         description="Interval in days for Celery Beat scheduler execution, default to 1 day",
@@ -1310,7 +1298,7 @@ class PositionConfig(BaseSettings):
 class CollaborationConfig(BaseSettings):
     ENABLE_COLLABORATION_MODE: bool = Field(
         description="Whether to enable collaboration mode features across the workspace",
-        default=True,
+        default=False,
     )
 
 
@@ -1429,7 +1417,6 @@ class FeatureConfig(
     ModelLoadBalanceConfig,
     ModerationConfig,
     MultiModalTransferConfig,
-    OpsTraceConfig,
     PositionConfig,
     RagEtlConfig,
     RepositoryConfig,

api/configs/middleware/__init__.py

@@ -114,7 +114,7 @@ class SQLAlchemyEngineOptionsDict(TypedDict):
     pool_pre_ping: bool
     connect_args: dict[str, str]
     pool_use_lifo: bool
-    pool_reset_on_return: Literal["commit", "rollback", None]
+    pool_reset_on_return: None
     pool_timeout: int
 
 
@@ -223,11 +223,6 @@ class DatabaseConfig(BaseSettings):
         default=30,
     )
 
-    SQLALCHEMY_POOL_RESET_ON_RETURN: Literal["commit", "rollback", None] = Field(
-        description="Connection pool reset behavior on return. Options: 'commit', 'rollback', or None",
-        default="rollback",
-    )
-
     RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
         description="Number of processes for the retrieval service, default to CPU cores.",
         default=os.cpu_count() or 1,
@@ -257,7 +252,7 @@ class DatabaseConfig(BaseSettings):
             "pool_pre_ping": self.SQLALCHEMY_POOL_PRE_PING,
             "connect_args": connect_args,
             "pool_use_lifo": self.SQLALCHEMY_POOL_USE_LIFO,
-            "pool_reset_on_return": self.SQLALCHEMY_POOL_RESET_ON_RETURN,
+            "pool_reset_on_return": None,
             "pool_timeout": self.SQLALCHEMY_POOL_TIMEOUT,
         }
         return result

api/configs/secret_key.py

@@ -1,38 +0,0 @@
-"""SECRET_KEY persistence helpers for runtime setup."""
-
-from __future__ import annotations
-
-import secrets
-
-from extensions.ext_storage import storage
-
-GENERATED_SECRET_KEY_FILENAME = ".dify_secret_key"
-
-
-def resolve_secret_key(secret_key: str) -> str:
-    """Return an explicit SECRET_KEY or a generated key persisted in storage."""
-    if secret_key:
-        return secret_key
-
-    return _load_or_create_secret_key()
-
-
-def _load_or_create_secret_key() -> str:
-    try:
-        persisted_key = storage.load_once(GENERATED_SECRET_KEY_FILENAME).decode("utf-8").strip()
-        if persisted_key:
-            return persisted_key
-    except FileNotFoundError:
-        pass
-
-    generated_key = secrets.token_urlsafe(48)
-
-    try:
-        storage.save(GENERATED_SECRET_KEY_FILENAME, f"{generated_key}\n".encode())
-    except Exception as exc:
-        raise ValueError(
-            f"SECRET_KEY is not set and could not be generated at {GENERATED_SECRET_KEY_FILENAME}. "
-            "Set SECRET_KEY explicitly or make storage writable."
-        ) from exc
-
-    return generated_key

api/controllers/API_SCHEMA_GUIDE.md

@@ -1,193 +0,0 @@
-# API Schema Guide
-
-This guide describes the expected Flask-RESTX + Pydantic pattern for controller request payloads, query
-parameters, response schemas, and Swagger documentation.
-
-## Principles
-
-- Use Pydantic `BaseModel` for request bodies and query parameters.
-- Use `fields.base.ResponseModel` for response DTOs.
-- Keep runtime validation and Swagger documentation wired to the same Pydantic model.
-- Prefer explicit validation and serialization in controller methods over Flask-RESTX marshalling.
-- Do not add new Flask-RESTX `fields.*` dictionaries, `Namespace.model(...)` exports, or `@marshal_with(...)` for migrated or new endpoints.
-- Do not use `@ns.expect(...)` for GET query parameters. Flask-RESTX documents that as a request body.
-
-## Naming
-
-- Request body models: use a `Payload` suffix.
-  - Example: `WorkflowRunPayload`, `DatasourceVariablesPayload`.
-- Query parameter models: use a `Query` suffix.
-  - Example: `WorkflowRunListQuery`, `MessageListQuery`.
-- Response models: use a `Response` suffix and inherit from `ResponseModel`.
-  - Example: `WorkflowRunDetailResponse`, `WorkflowRunNodeExecutionListResponse`.
-- Use `ListResponse` or `PaginationResponse` for wrapper responses.
-  - Example: `WorkflowRunNodeExecutionListResponse`, `WorkflowRunPaginationResponse`.
-- Keep these models near the controller when they are endpoint-specific. Move them to `fields/*_fields.py` only when shared by multiple controllers.
-
-## Registering Models For Swagger
-
-Use helpers from `controllers.common.schema`.
-
-```python
-from controllers.common.schema import (
-    query_params_from_model,
-    register_response_schema_models,
-    register_schema_models,
-)
-```
-
-Register request payload and query models with `register_schema_models(...)`:
-
-```python
-register_schema_models(
-    console_ns,
-    WorkflowRunPayload,
-    WorkflowRunListQuery,
-)
-```
-
-Register response models with `register_response_schema_models(...)`:
-
-```python
-register_response_schema_models(
-    console_ns,
-    WorkflowRunDetailResponse,
-    WorkflowRunPaginationResponse,
-)
-```
-
-Response models are registered in Pydantic serialization mode. This matters when a response model uses
-`validation_alias` to read internal object attributes but emits public API field names. For example, a response model
-can validate from `inputs_dict` while documenting and serializing `inputs`.
-
-## Request Bodies
-
-For non-GET request bodies:
-
-1. Define a Pydantic `Payload` model.
-2. Register it with `register_schema_models(...)`.
-3. Use `@ns.expect(ns.models[Payload.__name__])` for Swagger documentation.
-4. Validate from `ns.payload or {}` inside the controller.
-
-```python
-class DraftWorkflowNodeRunPayload(BaseModel):
-    inputs: dict[str, Any]
-    query: str = ""
-
-
-register_schema_models(console_ns, DraftWorkflowNodeRunPayload)
-
-
-@console_ns.expect(console_ns.models[DraftWorkflowNodeRunPayload.__name__])
-def post(self, app_model: App, node_id: str):
-    payload = DraftWorkflowNodeRunPayload.model_validate(console_ns.payload or {})
-    result = service.run(..., inputs=payload.inputs, query=payload.query)
-    return WorkflowRunNodeExecutionResponse.model_validate(result, from_attributes=True).model_dump(mode="json")
-```
-
-## Query Parameters
-
-For GET query parameters:
-
-1. Define a Pydantic `Query` model.
-2. Register it with `register_schema_models(...)` if it is referenced elsewhere in docs, or only use
-   `query_params_from_model(...)` if a body schema is not needed.
-3. Use `@ns.doc(params=query_params_from_model(QueryModel))`.
-4. Validate from `request.args.to_dict(flat=True)` or an explicit dict when type coercion is needed.
-
-```python
-class WorkflowRunListQuery(BaseModel):
-    last_id: str | None = Field(default=None, description="Last run ID for pagination")
-    limit: int = Field(default=20, ge=1, le=100, description="Number of items per page (1-100)")
-
-
-@console_ns.doc(params=query_params_from_model(WorkflowRunListQuery))
-def get(self, app_model: App):
-    query = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))
-    result = service.list(..., limit=query.limit, last_id=query.last_id)
-    return WorkflowRunPaginationResponse.model_validate(result, from_attributes=True).model_dump(mode="json")
-```
-
-Do not do this for GET query parameters:
-
-```python
-@console_ns.expect(console_ns.models[WorkflowRunListQuery.__name__])
-def get(...):
-    ...
-```
-
-That documents a GET request body and is not the expected contract.
-
-## Responses
-
-Response models should inherit from `ResponseModel`:
-
-```python
-class WorkflowRunNodeExecutionResponse(ResponseModel):
-    id: str
-    inputs: Any = Field(default=None, validation_alias="inputs_dict")
-    process_data: Any = Field(default=None, validation_alias="process_data_dict")
-    outputs: Any = Field(default=None, validation_alias="outputs_dict")
-```
-
-Document response models with `@ns.response(...)`:
-
-```python
-@console_ns.response(
-    200,
-    "Node run started successfully",
-    console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-)
-def post(...):
-    ...
-```
-
-Serialize explicitly:
-
-```python
-return WorkflowRunNodeExecutionResponse.model_validate(
-    workflow_node_execution,
-    from_attributes=True,
-).model_dump(mode="json")
-```
-
-If the service can return `None`, translate that into the expected HTTP error before validation:
-
-```python
-workflow_run = service.get_workflow_run(...)
-if workflow_run is None:
-    raise NotFound("Workflow run not found")
-
-return WorkflowRunDetailResponse.model_validate(workflow_run, from_attributes=True).model_dump(mode="json")
-```
-
-## Legacy Flask-RESTX Patterns
-
-Avoid adding these patterns to new or migrated endpoints:
-
-- `ns.model(...)` for new request/response DTOs.
-- Module-level exported RESTX model objects such as `workflow_run_detail_model`.
-- `fields.Nested({...})` with raw inline dict field maps.
-- `@marshal_with(...)` for response serialization.
-- `@ns.expect(...)` for GET query params.
-
-Existing legacy field dictionaries may remain where an endpoint has not yet been migrated. Keep that compatibility local
-to the legacy area and avoid importing RESTX model objects from controllers.
-
-## Verifying Swagger
-
-For schema and documentation changes, run focused tests and generate Swagger JSON:
-
-```bash
-uv run --project . pytest tests/unit_tests/controllers/common/test_schema.py
-uv run --project . pytest tests/unit_tests/commands/test_generate_swagger_specs.py tests/unit_tests/controllers/test_swagger.py
-uv run --project . dev/generate_swagger_specs.py --output-dir /tmp/dify-openapi-check
-```
-
-Inspect affected endpoints with `jq`. Check that:
-
-- GET parameters are `in: query`.
-- Request bodies appear only where the endpoint has a body.
-- Responses reference the expected `*Response` schema.
-- Response schemas use public serialized names, not internal validation aliases like `inputs_dict`.
-

api/controllers/common/schema.py

@@ -1,14 +1,6 @@
-"""Helpers for registering Pydantic models with Flask-RESTX namespaces.
+"""Helpers for registering Pydantic models with Flask-RESTX namespaces."""
 
-Flask-RESTX treats `SchemaModel` bodies as opaque JSON schemas; it does not
-promote Pydantic's nested `$defs` into top-level Swagger `definitions`.
-These helpers keep that translation centralized so models registered through
-`register_schema_models` emit resolvable Swagger 2.0 references.
-"""
-
-from collections.abc import Mapping
 from enum import StrEnum
-from typing import Any, Literal, NotRequired, TypedDict
 
 from flask_restx import Namespace
 from pydantic import BaseModel, TypeAdapter
@@ -16,59 +8,10 @@ from pydantic import BaseModel, TypeAdapter
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
-QueryParamDoc = TypedDict(
-    "QueryParamDoc",
-    {
-        "in": NotRequired[str],
-        "type": NotRequired[str],
-        "items": NotRequired[dict[str, object]],
-        "required": NotRequired[bool],
-        "description": NotRequired[str],
-        "enum": NotRequired[list[object]],
-        "default": NotRequired[object],
-        "minimum": NotRequired[int | float],
-        "maximum": NotRequired[int | float],
-        "minLength": NotRequired[int],
-        "maxLength": NotRequired[int],
-        "minItems": NotRequired[int],
-        "maxItems": NotRequired[int],
-    },
-)
-
-
-def _register_json_schema(namespace: Namespace, name: str, schema: dict) -> None:
-    """Register a JSON schema and promote any nested Pydantic `$defs`."""
-
-    nested_definitions = schema.get("$defs")
-    schema_to_register = dict(schema)
-    if isinstance(nested_definitions, dict):
-        schema_to_register.pop("$defs")
-
-    namespace.schema_model(name, schema_to_register)
-
-    if not isinstance(nested_definitions, dict):
-        return
-
-    for nested_name, nested_schema in nested_definitions.items():
-        if isinstance(nested_schema, dict):
-            _register_json_schema(namespace, nested_name, nested_schema)
-
-
-JsonSchemaMode = Literal["validation", "serialization"]
-
-
-def _register_schema_model(namespace: Namespace, model: type[BaseModel], *, mode: JsonSchemaMode) -> None:
-    _register_json_schema(
-        namespace,
-        model.__name__,
-        model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0, mode=mode),
-    )
-
-
 def register_schema_model(namespace: Namespace, model: type[BaseModel]) -> None:
-    """Register a BaseModel and its nested schema definitions for Swagger documentation."""
+    """Register a single BaseModel with a namespace for Swagger documentation."""
 
-    _register_schema_model(namespace, model, mode="validation")
+    namespace.schema_model(model.__name__, model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
 
 
 def register_schema_models(namespace: Namespace, *models: type[BaseModel]) -> None:
@@ -78,19 +21,6 @@ def register_schema_models(namespace: Namespace, *models: type[BaseModel]) -> No
         register_schema_model(namespace, model)
 
 
-def register_response_schema_model(namespace: Namespace, model: type[BaseModel]) -> None:
-    """Register a BaseModel using its serialized response shape."""
-
-    _register_schema_model(namespace, model, mode="serialization")
-
-
-def register_response_schema_models(namespace: Namespace, *models: type[BaseModel]) -> None:
-    """Register multiple response BaseModels using their serialized response shape."""
-
-    for model in models:
-        register_response_schema_model(namespace, model)
-
-
 def get_or_create_model(model_name: str, field_def):
     # Import lazily to avoid circular imports between console controllers and schema helpers.
     from controllers.console import console_ns
@@ -104,114 +34,15 @@ def get_or_create_model(model_name: str, field_def):
 def register_enum_models(namespace: Namespace, *models: type[StrEnum]) -> None:
     """Register multiple StrEnum with a namespace."""
     for model in models:
-        _register_json_schema(
-            namespace,
-            model.__name__,
-            TypeAdapter(model).json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+        namespace.schema_model(
+            model.__name__, TypeAdapter(model).json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
         )
 
 
-def query_params_from_model(model: type[BaseModel]) -> dict[str, QueryParamDoc]:
-    """Build Flask-RESTX query parameter docs from a flat Pydantic model.
-
-    `Namespace.expect()` treats Pydantic schema models as request bodies, so GET
-    endpoints should keep runtime validation on the Pydantic model and feed this
-    derived mapping to `Namespace.doc(params=...)` for Swagger documentation.
-    """
-
-    schema = model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
-    properties = schema.get("properties", {})
-    if not isinstance(properties, Mapping):
-        return {}
-
-    required = schema.get("required", [])
-    required_names = set(required) if isinstance(required, list) else set()
-
-    params: dict[str, QueryParamDoc] = {}
-    for name, property_schema in properties.items():
-        if not isinstance(name, str) or not isinstance(property_schema, Mapping):
-            continue
-
-        params[name] = _query_param_from_property(property_schema, required=name in required_names)
-
-    return params
-
-
-def _query_param_from_property(property_schema: Mapping[str, Any], *, required: bool) -> QueryParamDoc:
-    param_schema = _nullable_property_schema(property_schema)
-    param_doc: QueryParamDoc = {"in": "query", "required": required}
-
-    description = param_schema.get("description")
-    if isinstance(description, str):
-        param_doc["description"] = description
-
-    schema_type = param_schema.get("type")
-    if isinstance(schema_type, str) and schema_type in {"array", "boolean", "integer", "number", "string"}:
-        param_doc["type"] = schema_type
-        if schema_type == "array":
-            items = param_schema.get("items")
-            if isinstance(items, Mapping):
-                item_type = items.get("type")
-                if isinstance(item_type, str):
-                    param_doc["items"] = {"type": item_type}
-
-    enum = param_schema.get("enum")
-    if isinstance(enum, list):
-        param_doc["enum"] = enum
-
-    default = param_schema.get("default")
-    if default is not None:
-        param_doc["default"] = default
-
-    minimum = param_schema.get("minimum")
-    if isinstance(minimum, int | float):
-        param_doc["minimum"] = minimum
-
-    maximum = param_schema.get("maximum")
-    if isinstance(maximum, int | float):
-        param_doc["maximum"] = maximum
-
-    min_length = param_schema.get("minLength")
-    if isinstance(min_length, int):
-        param_doc["minLength"] = min_length
-
-    max_length = param_schema.get("maxLength")
-    if isinstance(max_length, int):
-        param_doc["maxLength"] = max_length
-
-    min_items = param_schema.get("minItems")
-    if isinstance(min_items, int):
-        param_doc["minItems"] = min_items
-
-    max_items = param_schema.get("maxItems")
-    if isinstance(max_items, int):
-        param_doc["maxItems"] = max_items
-
-    return param_doc
-
-
-def _nullable_property_schema(property_schema: Mapping[str, Any]) -> Mapping[str, Any]:
-    any_of = property_schema.get("anyOf")
-    if not isinstance(any_of, list):
-        return property_schema
-
-    non_null_candidates = [
-        candidate for candidate in any_of if isinstance(candidate, Mapping) and candidate.get("type") != "null"
-    ]
-
-    if len(non_null_candidates) == 1:
-        return {**property_schema, **non_null_candidates[0]}
-
-    return property_schema
-
-
 __all__ = [
     "DEFAULT_REF_TEMPLATE_SWAGGER_2_0",
     "get_or_create_model",
-    "query_params_from_model",
     "register_enum_models",
-    "register_response_schema_model",
-    "register_response_schema_models",
     "register_schema_model",
     "register_schema_models",
 ]

api/controllers/console/admin.py

@@ -3,7 +3,6 @@ import io
 from collections.abc import Callable
 from functools import wraps
 from typing import cast
-from uuid import UUID
 
 from flask import request
 from flask_restx import Resource
@@ -13,7 +12,6 @@ from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
 
 from configs import dify_config
 from constants.languages import supported_language
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import only_edition_cloud
 from core.db.session_factory import session_factory
@@ -22,6 +20,8 @@ from libs.token import extract_access_token
 from models.model import App, ExporleBanner, InstalledApp, RecommendedApp, TrialApp
 from services.billing_service import BillingService, LangContentDict
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class InsertExploreAppPayload(BaseModel):
     app_id: str = Field(...)
@@ -58,7 +58,15 @@ class InsertExploreBannerPayload(BaseModel):
     model_config = {"populate_by_name": True}
 
 
-register_schema_models(console_ns, InsertExploreAppPayload, InsertExploreBannerPayload)
+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[**P, R](view: Callable[P, R]) -> Callable[P, R]:
@@ -182,7 +190,7 @@ class InsertExploreAppApi(Resource):
     @console_ns.response(204, "App removed successfully")
     @only_edition_cloud
     @admin_required
-    def delete(self, app_id: UUID):
+    def delete(self, app_id):
         with session_factory.create_session() as session:
             recommended_app = session.execute(
                 select(RecommendedApp).where(RecommendedApp.app_id == str(app_id))
@@ -293,7 +301,15 @@ class BatchAddNotificationAccountsPayload(BaseModel):
     user_email: list[str] = Field(..., description="List of account email addresses")
 
 
-register_schema_models(console_ns, UpsertNotificationPayload, BatchAddNotificationAccountsPayload)
+console_ns.schema_model(
+    UpsertNotificationPayload.__name__,
+    UpsertNotificationPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    BatchAddNotificationAccountsPayload.__name__,
+    BatchAddNotificationAccountsPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 @console_ns.route("/admin/upsert_notification")
@@ -395,11 +411,11 @@ class BatchAddNotificationAccountsApi(Resource):
             raise BadRequest("Invalid file type. Only CSV (.csv) and TXT (.txt) files are allowed.")
 
         try:
-            content = file.stream.read().decode("utf-8")
+            content = file.read().decode("utf-8")
         except UnicodeDecodeError:
             try:
-                file.stream.seek(0)
-                content = file.stream.read().decode("gbk")
+                file.seek(0)
+                content = file.read().decode("gbk")
             except UnicodeDecodeError:
                 raise BadRequest("Unable to decode the file. Please use UTF-8 or GBK encoding.")
 

api/controllers/console/app/advanced_prompt_template.py

@@ -34,7 +34,7 @@ class AdvancedPromptTemplateList(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))
+        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         prompt_args: AdvancedPromptTemplateArgs = {
             "app_mode": args.app_mode,
             "model_mode": args.model_mode,

api/controllers/console/app/agent.py

@@ -2,7 +2,6 @@ from flask import request
 from flask_restx import Resource, fields
 from pydantic import BaseModel, Field, field_validator
 
-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.wraps import account_initialization_required, setup_required
@@ -11,6 +10,8 @@ from libs.login import login_required
 from models.model import AppMode
 from services.agent_service import AgentService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class AgentLogQuery(BaseModel):
     message_id: str = Field(..., description="Message UUID")
@@ -22,7 +23,9 @@ class AgentLogQuery(BaseModel):
         return uuid_value(value)
 
 
-register_schema_models(console_ns, AgentLogQuery)
+console_ns.schema_model(
+    AgentLogQuery.__name__, AgentLogQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @console_ns.route("/apps/<uuid:app_id>/agent/logs")
@@ -41,6 +44,6 @@ class AgentLogApi(Resource):
     @get_app_model(mode=[AppMode.AGENT_CHAT])
     def get(self, app_model):
         """Get agent logs"""
-        args = AgentLogQuery.model_validate(request.args.to_dict(flat=True))
+        args = AgentLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         return AgentService.get_agent_logs(app_model, args.conversation_id, args.message_id)

api/controllers/console/app/annotation.py

@@ -1,5 +1,4 @@
 from typing import Any, Literal
-from uuid import UUID
 
 from flask import abort, make_response, request
 from flask_restx import Resource
@@ -34,6 +33,8 @@ from services.annotation_service import (
     UpsertAnnotationArgs,
 )
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class AnnotationReplyPayload(BaseModel):
     score_threshold: float = Field(..., description="Score threshold for annotation matching")
@@ -86,6 +87,17 @@ class AnnotationFilePayload(BaseModel):
         return uuid_value(value)
 
 
+def reg(model: type[BaseModel]) -> None:
+    console_ns.schema_model(model.__name__, model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(AnnotationReplyPayload)
+reg(AnnotationSettingUpdatePayload)
+reg(AnnotationListQuery)
+reg(CreateAnnotationPayload)
+reg(UpdateAnnotationPayload)
+reg(AnnotationReplyStatusQuery)
+reg(AnnotationFilePayload)
 register_schema_models(
     console_ns,
     Annotation,
@@ -93,13 +105,6 @@ register_schema_models(
     AnnotationExportList,
     AnnotationHitHistory,
     AnnotationHitHistoryList,
-    AnnotationReplyPayload,
-    AnnotationSettingUpdatePayload,
-    AnnotationListQuery,
-    CreateAnnotationPayload,
-    UpdateAnnotationPayload,
-    AnnotationReplyStatusQuery,
-    AnnotationFilePayload,
 )
 
 
@@ -116,7 +121,8 @@ class AnnotationReplyActionApi(Resource):
     @account_initialization_required
     @cloud_edition_billing_resource_check("annotation")
     @edit_permission_required
-    def post(self, app_id: UUID, action: Literal["enable", "disable"]):
+    def post(self, app_id, action: Literal["enable", "disable"]):
+        app_id = str(app_id)
         args = AnnotationReplyPayload.model_validate(console_ns.payload)
         match action:
             case "enable":
@@ -125,9 +131,9 @@ class AnnotationReplyActionApi(Resource):
                     "embedding_provider_name": args.embedding_provider_name,
                     "embedding_model_name": args.embedding_model_name,
                 }
-                result = AppAnnotationService.enable_app_annotation(enable_args, str(app_id))
+                result = AppAnnotationService.enable_app_annotation(enable_args, app_id)
             case "disable":
-                result = AppAnnotationService.disable_app_annotation(str(app_id))
+                result = AppAnnotationService.disable_app_annotation(app_id)
         return result, 200
 
 
@@ -142,8 +148,9 @@ class AppAnnotationSettingDetailApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def get(self, app_id: UUID):
-        result = AppAnnotationService.get_app_annotation_setting_by_app_id(str(app_id))
+    def get(self, app_id):
+        app_id = str(app_id)
+        result = AppAnnotationService.get_app_annotation_setting_by_app_id(app_id)
         return result, 200
 
 
@@ -159,13 +166,14 @@ class AppAnnotationSettingUpdateApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def post(self, app_id: UUID, annotation_setting_id):
+    def post(self, app_id, annotation_setting_id):
+        app_id = str(app_id)
         annotation_setting_id = str(annotation_setting_id)
 
         args = AnnotationSettingUpdatePayload.model_validate(console_ns.payload)
 
         setting_args: UpdateAnnotationSettingArgs = {"score_threshold": args.score_threshold}
-        result = AppAnnotationService.update_app_annotation_setting(str(app_id), annotation_setting_id, setting_args)
+        result = AppAnnotationService.update_app_annotation_setting(app_id, annotation_setting_id, setting_args)
         return result, 200
 
 
@@ -181,7 +189,7 @@ class AnnotationReplyActionStatusApi(Resource):
     @account_initialization_required
     @cloud_edition_billing_resource_check("annotation")
     @edit_permission_required
-    def get(self, app_id: UUID, job_id, action):
+    def get(self, app_id, job_id, action):
         job_id = str(job_id)
         app_annotation_job_key = f"{action}_app_annotation_job_{str(job_id)}"
         cache_result = redis_client.get(app_annotation_job_key)
@@ -209,13 +217,14 @@ class AnnotationApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def get(self, app_id: UUID):
-        args = AnnotationListQuery.model_validate(request.args.to_dict(flat=True))
+    def get(self, app_id):
+        args = AnnotationListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         page = args.page
         limit = args.limit
         keyword = args.keyword
 
-        annotation_list, total = AppAnnotationService.get_annotation_list_by_app_id(str(app_id), page, limit, keyword)
+        app_id = str(app_id)
+        annotation_list, total = AppAnnotationService.get_annotation_list_by_app_id(app_id, page, limit, keyword)
         annotation_models = TypeAdapter(list[Annotation]).validate_python(annotation_list, from_attributes=True)
         response = AnnotationList(
             data=annotation_models,
@@ -237,7 +246,8 @@ class AnnotationApi(Resource):
     @account_initialization_required
     @cloud_edition_billing_resource_check("annotation")
     @edit_permission_required
-    def post(self, app_id: UUID):
+    def post(self, app_id):
+        app_id = str(app_id)
         args = CreateAnnotationPayload.model_validate(console_ns.payload)
         upsert_args: UpsertAnnotationArgs = {}
         if args.answer is not None:
@@ -248,14 +258,15 @@ class AnnotationApi(Resource):
             upsert_args["message_id"] = args.message_id
         if args.question is not None:
             upsert_args["question"] = args.question
-        annotation = AppAnnotationService.up_insert_app_annotation_from_message(upsert_args, str(app_id))
+        annotation = AppAnnotationService.up_insert_app_annotation_from_message(upsert_args, app_id)
         return Annotation.model_validate(annotation, from_attributes=True).model_dump(mode="json")
 
     @setup_required
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def delete(self, app_id: UUID):
+    def delete(self, app_id):
+        app_id = str(app_id)
 
         # Use request.args.getlist to get annotation_ids array directly
         annotation_ids = request.args.getlist("annotation_id")
@@ -269,11 +280,11 @@ class AnnotationApi(Resource):
                     "message": "annotation_ids are required if the parameter is provided.",
                 }, 400
 
-            result = AppAnnotationService.delete_app_annotations_in_batch(str(app_id), annotation_ids)
+            result = AppAnnotationService.delete_app_annotations_in_batch(app_id, annotation_ids)
             return result, 204
         # If no annotation_ids are provided, handle clearing all annotations
         else:
-            AppAnnotationService.clear_all_annotations(str(app_id))
+            AppAnnotationService.clear_all_annotations(app_id)
             return {"result": "success"}, 204
 
 
@@ -292,8 +303,9 @@ class AnnotationExportApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def get(self, app_id: UUID):
-        annotation_list = AppAnnotationService.export_annotation_list_by_app_id(str(app_id))
+    def get(self, app_id):
+        app_id = str(app_id)
+        annotation_list = AppAnnotationService.export_annotation_list_by_app_id(app_id)
         annotation_models = TypeAdapter(list[Annotation]).validate_python(annotation_list, from_attributes=True)
         response_data = AnnotationExportList(data=annotation_models).model_dump(mode="json")
 
@@ -319,22 +331,26 @@ class AnnotationUpdateDeleteApi(Resource):
     @account_initialization_required
     @cloud_edition_billing_resource_check("annotation")
     @edit_permission_required
-    def post(self, app_id: UUID, annotation_id: UUID):
+    def post(self, app_id, annotation_id):
+        app_id = str(app_id)
+        annotation_id = str(annotation_id)
         args = UpdateAnnotationPayload.model_validate(console_ns.payload)
         update_args: UpdateAnnotationArgs = {}
         if args.answer is not None:
             update_args["answer"] = args.answer
         if args.question is not None:
             update_args["question"] = args.question
-        annotation = AppAnnotationService.update_app_annotation_directly(update_args, str(app_id), str(annotation_id))
+        annotation = AppAnnotationService.update_app_annotation_directly(update_args, app_id, annotation_id)
         return Annotation.model_validate(annotation, from_attributes=True).model_dump(mode="json")
 
     @setup_required
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def delete(self, app_id: UUID, annotation_id: UUID):
-        AppAnnotationService.delete_app_annotation(str(app_id), str(annotation_id))
+    def delete(self, app_id, annotation_id):
+        app_id = str(app_id)
+        annotation_id = str(annotation_id)
+        AppAnnotationService.delete_app_annotation(app_id, annotation_id)
         return {"result": "success"}, 204
 
 
@@ -355,9 +371,11 @@ class AnnotationBatchImportApi(Resource):
     @annotation_import_rate_limit
     @annotation_import_concurrency_limit
     @edit_permission_required
-    def post(self, app_id: UUID):
+    def post(self, app_id):
         from configs import dify_config
 
+        app_id = str(app_id)
+
         # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
@@ -373,9 +391,9 @@ class AnnotationBatchImportApi(Resource):
             raise ValueError("Invalid file type. Only CSV files are allowed")
 
         # Check file size before processing
-        file.stream.seek(0, 2)  # Seek to end of file
-        file_size = file.stream.tell()
-        file.stream.seek(0)  # Reset to beginning
+        file.seek(0, 2)  # Seek to end of file
+        file_size = file.tell()
+        file.seek(0)  # Reset to beginning
 
         max_size_bytes = dify_config.ANNOTATION_IMPORT_FILE_SIZE_LIMIT * 1024 * 1024
         if file_size > max_size_bytes:
@@ -388,7 +406,7 @@ class AnnotationBatchImportApi(Resource):
         if file_size == 0:
             raise ValueError("The uploaded file is empty")
 
-        return AppAnnotationService.batch_import_app_annotations(str(app_id), file)
+        return AppAnnotationService.batch_import_app_annotations(app_id, file)
 
 
 @console_ns.route("/apps/<uuid:app_id>/annotations/batch-import-status/<uuid:job_id>")
@@ -403,7 +421,8 @@ class AnnotationBatchImportStatusApi(Resource):
     @account_initialization_required
     @cloud_edition_billing_resource_check("annotation")
     @edit_permission_required
-    def get(self, app_id: UUID, job_id: UUID):
+    def get(self, app_id, job_id):
+        job_id = str(job_id)
         indexing_cache_key = f"app_annotation_batch_import_{str(job_id)}"
         cache_result = redis_client.get(indexing_cache_key)
         if cache_result is None:
@@ -437,11 +456,13 @@ class AnnotationHitHistoryListApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def get(self, app_id: UUID, annotation_id: UUID):
+    def get(self, app_id, annotation_id):
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
+        app_id = str(app_id)
+        annotation_id = str(annotation_id)
         annotation_hit_history_list, total = AppAnnotationService.get_annotation_hit_histories(
-            str(app_id), str(annotation_id), page, limit
+            app_id, annotation_id, page, limit
         )
         history_models = TypeAdapter(list[AnnotationHitHistory]).validate_python(
             annotation_hit_history_list, from_attributes=True

api/controllers/console/app/app.py

@@ -3,7 +3,6 @@ import re
 import uuid
 from datetime import datetime
 from typing import Any, Literal
-from uuid import UUID
 
 from flask import request
 from flask_restx import Resource
@@ -26,7 +25,6 @@ from controllers.console.wraps import (
     is_admin_or_owner_required,
     setup_required,
 )
-from core.db.session_factory import session_factory
 from core.ops.ops_trace_manager import OpsTraceManager
 from core.rag.entities import PreProcessingRule, Rule, Segmentation
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
@@ -39,7 +37,7 @@ from libs.login import current_account_with_tenant, login_required
 from models import App, DatasetPermissionEnum, Workflow
 from models.model import IconType
 from services.app_dsl_service import AppDslService
-from services.app_service import AppListParams, AppService, CreateAppParams
+from services.app_service import AppService
 from services.enterprise.enterprise_service import EnterpriseService
 from services.entities.dsl_entities import ImportMode, ImportStatus
 from services.entities.knowledge_entities.knowledge_entities import (
@@ -478,18 +476,11 @@ class AppListApi(Resource):
         current_user, current_tenant_id = current_account_with_tenant()
 
         args = AppListQuery.model_validate(_normalize_app_list_query_args(request.args))
-        params = AppListParams(
-            page=args.page,
-            limit=args.limit,
-            mode=args.mode,
-            name=args.name,
-            tag_ids=args.tag_ids,
-            is_created_by_me=args.is_created_by_me,
-        )
+        args_dict = args.model_dump()
 
         # get app list
         app_service = AppService()
-        app_pagination = app_service.get_paginate_apps(current_user.id, current_tenant_id, params)
+        app_pagination = app_service.get_paginate_apps(current_user.id, current_tenant_id, args_dict)
         if not app_pagination:
             empty = AppPagination(page=args.page, limit=args.limit, total=0, has_more=False, data=[])
             return empty.model_dump(mode="json"), 200
@@ -553,17 +544,9 @@ class AppListApi(Resource):
         """Create app"""
         current_user, current_tenant_id = current_account_with_tenant()
         args = CreateAppPayload.model_validate(console_ns.payload)
-        params = CreateAppParams(
-            name=args.name,
-            description=args.description,
-            mode=args.mode,
-            icon_type=args.icon_type,
-            icon=args.icon,
-            icon_background=args.icon_background,
-        )
 
         app_service = AppService()
-        app = app_service.create_app(current_tenant_id, params, current_user)
+        app = app_service.create_app(current_tenant_id, args.model_dump(), current_user)
         app_detail = AppDetail.model_validate(app, from_attributes=True)
         return app_detail.model_dump(mode="json"), 201
 
@@ -717,7 +700,7 @@ class AppExportApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         """Export app"""
-        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))
+        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         payload = AppExportResponse(
             data=AppDslService.export_dsl(
@@ -856,10 +839,9 @@ class AppTraceApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id: UUID):
+    def get(self, app_id):
         """Get app trace"""
-        with session_factory.create_session() as session:
-            app_trace_config = OpsTraceManager.get_app_tracing_config(str(app_id), session)
+        app_trace_config = OpsTraceManager.get_app_tracing_config(app_id=app_id)
 
         return app_trace_config
 
@@ -873,12 +855,12 @@ class AppTraceApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def post(self, app_id: UUID):
+    def post(self, app_id):
         # add app trace
         args = AppTracePayload.model_validate(console_ns.payload)
 
         OpsTraceManager.update_app_tracing_config(
-            app_id=str(app_id),
+            app_id=app_id,
             enabled=args.enabled,
             tracing_provider=args.tracing_provider,
         )

api/controllers/console/app/app_import.py

@@ -2,7 +2,7 @@ from flask_restx import Resource
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
 
-from controllers.common.schema import register_enum_models, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import (
     account_initialization_required,
@@ -33,7 +33,6 @@ class AppImportPayload(BaseModel):
     app_id: str | None = Field(None)
 
 
-register_enum_models(console_ns, ImportStatus)
 register_schema_models(console_ns, AppImportPayload, Import, CheckDependenciesResult)
 
 

api/controllers/console/app/audio.py

@@ -173,7 +173,7 @@ class TextModesApi(Resource):
     @account_initialization_required
     def get(self, app_model):
         try:
-            args = TextToSpeechVoiceQuery.model_validate(request.args.to_dict(flat=True))
+            args = TextToSpeechVoiceQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
             response = AudioService.transcript_tts_voices(
                 tenant_id=app_model.tenant_id,

api/controllers/console/app/completion.py

@@ -7,7 +7,6 @@ from pydantic import BaseModel, Field, field_validator
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.error import (
     AppUnavailableError,
@@ -38,6 +37,7 @@ from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
 class BaseMessagePayload(BaseModel):
@@ -65,7 +65,13 @@ class ChatMessagePayload(BaseMessagePayload):
         return uuid_value(value)
 
 
-register_schema_models(console_ns, CompletionMessagePayload, ChatMessagePayload)
+console_ns.schema_model(
+    CompletionMessagePayload.__name__,
+    CompletionMessagePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ChatMessagePayload.__name__, ChatMessagePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 # define completion message api for user

api/controllers/console/app/conversation.py

@@ -39,6 +39,8 @@ from models.model import AppMode
 from services.conversation_service import ConversationService
 from services.errors.conversation import ConversationNotExistsError
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class BaseConversationQuery(BaseModel):
     keyword: str | None = Field(default=None, description="Search keyword")
@@ -68,6 +70,15 @@ class ChatConversationQuery(BaseConversationQuery):
     )
 
 
+console_ns.schema_model(
+    CompletionConversationQuery.__name__,
+    CompletionConversationQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ChatConversationQuery.__name__,
+    ChatConversationQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
 register_schema_models(
     console_ns,
     CompletionConversationQuery,
@@ -78,8 +89,6 @@ register_schema_models(
     ConversationWithSummaryPaginationResponse,
     ConversationDetailResponse,
     ResultResponse,
-    CompletionConversationQuery,
-    ChatConversationQuery,
 )
 
 
@@ -98,7 +107,7 @@ class CompletionConversationApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))
+        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         query = sa.select(Conversation).where(
             Conversation.app_id == app_model.id, Conversation.mode == "completion", Conversation.is_deleted.is_(False)
@@ -212,7 +221,7 @@ class ChatConversationApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))
+        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         subquery = (
             sa.select(Conversation.id.label("conversation_id"), EndUser.session_id.label("from_end_user_session_id"))

api/controllers/console/app/conversation_variables.py

@@ -100,7 +100,7 @@ class ConversationVariablesApi(Resource):
     @account_initialization_required
     @get_app_model(mode=AppMode.ADVANCED_CHAT)
     def get(self, app_model):
-        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))
+        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         stmt = (
             select(ConversationVariable)

api/controllers/console/app/generator.py

@@ -3,7 +3,6 @@ from collections.abc import Sequence
 from flask_restx import Resource
 from pydantic import BaseModel, Field
 
-from controllers.common.schema import register_enum_models, register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.error import (
     CompletionRequestError,
@@ -20,12 +19,13 @@ from core.helper.code_executor.python3.python3_code_provider import Python3CodeP
 from core.llm_generator.entities import RuleCodeGeneratePayload, RuleGeneratePayload, RuleStructuredOutputPayload
 from core.llm_generator.llm_generator import LLMGenerator
 from extensions.ext_database import db
-from graphon.model_runtime.entities.llm_entities import LLMMode
 from graphon.model_runtime.errors.invoke import InvokeError
 from libs.login import current_account_with_tenant, login_required
 from models import App
 from services.workflow_service import WorkflowService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class InstructionGeneratePayload(BaseModel):
     flow_id: str = Field(..., description="Workflow/Flow ID")
@@ -41,16 +41,16 @@ class InstructionTemplatePayload(BaseModel):
     type: str = Field(..., description="Instruction template type")
 
 
-register_enum_models(console_ns, LLMMode)
-register_schema_models(
-    console_ns,
-    RuleGeneratePayload,
-    RuleCodeGeneratePayload,
-    RuleStructuredOutputPayload,
-    InstructionGeneratePayload,
-    InstructionTemplatePayload,
-    ModelConfig,
-)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(RuleGeneratePayload)
+reg(RuleCodeGeneratePayload)
+reg(RuleStructuredOutputPayload)
+reg(InstructionGeneratePayload)
+reg(InstructionTemplatePayload)
+reg(ModelConfig)
 
 
 @console_ns.route("/rule-generate")

api/controllers/console/app/ops_trace.py

@@ -1,18 +1,18 @@
 from typing import Any
-from uuid import UUID
 
 from flask import request
 from flask_restx import Resource, fields
 from pydantic import BaseModel, Field
 from werkzeug.exceptions import BadRequest
 
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
 from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.ops_service import OpsService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class TraceProviderQuery(BaseModel):
     tracing_provider: str = Field(..., description="Tracing provider name")
@@ -23,7 +23,13 @@ class TraceConfigPayload(BaseModel):
     tracing_config: dict[str, Any] = Field(..., description="Tracing configuration data")
 
 
-register_schema_models(console_ns, TraceProviderQuery, TraceConfigPayload)
+console_ns.schema_model(
+    TraceProviderQuery.__name__,
+    TraceProviderQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    TraceConfigPayload.__name__, TraceConfigPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @console_ns.route("/apps/<uuid:app_id>/trace-config")
@@ -43,11 +49,11 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id: UUID):
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))
+    def get(self, app_id):
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            trace_config = OpsService.get_tracing_app_config(app_id=str(app_id), tracing_provider=args.tracing_provider)
+            trace_config = OpsService.get_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
             if not trace_config:
                 return {"has_not_configured": True}
             return trace_config
@@ -65,13 +71,13 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def post(self, app_id: UUID):
+    def post(self, app_id):
         """Create a new trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.create_tracing_app_config(
-                app_id=str(app_id), tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigIsExist()
@@ -90,13 +96,13 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def patch(self, app_id: UUID):
+    def patch(self, app_id):
         """Update an existing trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.update_tracing_app_config(
-                app_id=str(app_id), tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigNotExist()
@@ -113,12 +119,12 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def delete(self, app_id: UUID):
+    def delete(self, app_id):
         """Delete an existing trace app configuration"""
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            result = OpsService.delete_tracing_app_config(app_id=str(app_id), tracing_provider=args.tracing_provider)
+            result = OpsService.delete_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
             if not result:
                 raise TracingConfigNotExist()
             return {"result": "success"}, 204

api/controllers/console/app/statistic.py

@@ -5,7 +5,6 @@ from flask import abort, jsonify, request
 from flask_restx import Resource, fields
 from pydantic import BaseModel, Field, field_validator
 
-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.wraps import account_initialization_required, setup_required
@@ -16,6 +15,8 @@ from libs.helper import convert_datetime_to_date
 from libs.login import current_account_with_tenant, login_required
 from models import AppMode
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class StatisticTimeRangeQuery(BaseModel):
     start: str | None = Field(default=None, description="Start date (YYYY-MM-DD HH:MM)")
@@ -29,7 +30,10 @@ class StatisticTimeRangeQuery(BaseModel):
         return value
 
 
-register_schema_models(console_ns, StatisticTimeRangeQuery)
+console_ns.schema_model(
+    StatisticTimeRangeQuery.__name__,
+    StatisticTimeRangeQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 @console_ns.route("/apps/<uuid:app_id>/statistics/daily-messages")
@@ -50,7 +54,7 @@ class DailyMessageStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -107,7 +111,7 @@ class DailyConversationStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -163,7 +167,7 @@ class DailyTerminalsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -220,7 +224,7 @@ class DailyTokenCostStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -280,7 +284,7 @@ class AverageSessionInteractionStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("c.created_at")
         sql_query = f"""SELECT
@@ -356,7 +360,7 @@ class UserSatisfactionRateStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("m.created_at")
         sql_query = f"""SELECT
@@ -422,7 +426,7 @@ class AverageResponseTimeStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -478,7 +482,7 @@ class TokensPerSecondStatistic(Resource):
     @account_initialization_required
     def get(self, app_model):
         account, _ = current_account_with_tenant()
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT

api/controllers/console/app/workflow.py

@@ -11,9 +11,9 @@ from werkzeug.exceptions import BadRequest, Forbidden, InternalServerError, NotF
 
 import services
 from controllers.common.controller_schemas import DefaultBlockConfigQuery, WorkflowListQuery, WorkflowUpdatePayload
-from controllers.common.schema import register_response_schema_model, register_schema_models
 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
@@ -37,7 +37,6 @@ from factories import file_factory, variable_factory
 from fields.member_fields import simple_account_fields
 from fields.online_user_fields import online_user_list_fields
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
-from fields.workflow_run_fields import WorkflowRunNodeExecutionResponse
 from graphon.enums import NodeType
 from graphon.file import File
 from graphon.file import helpers as file_helpers
@@ -57,10 +56,9 @@ from services.errors.llm import InvokeRateLimitError
 from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseError, WorkflowService
 
 logger = logging.getLogger(__name__)
-
 _file_access_controller = DatabaseFileAccessController()
 LISTENING_RETRY_IN = 2000
-
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 RESTORE_SOURCE_WORKFLOW_MUST_BE_PUBLISHED_MESSAGE = "source workflow must be published"
 MAX_WORKFLOW_ONLINE_USERS_REQUEST_IDS = 1000
 WORKFLOW_ONLINE_USERS_REDIS_BATCH_SIZE = 50
@@ -178,25 +176,25 @@ class DraftWorkflowTriggerRunAllPayload(BaseModel):
     node_ids: list[str]
 
 
-register_schema_models(
-    console_ns,
-    SyncDraftWorkflowPayload,
-    AdvancedChatWorkflowRunPayload,
-    IterationNodeRunPayload,
-    LoopNodeRunPayload,
-    DraftWorkflowRunPayload,
-    DraftWorkflowNodeRunPayload,
-    PublishWorkflowPayload,
-    DefaultBlockConfigQuery,
-    ConvertToWorkflowPayload,
-    WorkflowListQuery,
-    WorkflowUpdatePayload,
-    WorkflowFeaturesPayload,
-    WorkflowOnlineUsersPayload,
-    DraftWorkflowTriggerRunPayload,
-    DraftWorkflowTriggerRunAllPayload,
-)
-register_response_schema_model(console_ns, WorkflowRunNodeExecutionResponse)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(SyncDraftWorkflowPayload)
+reg(AdvancedChatWorkflowRunPayload)
+reg(IterationNodeRunPayload)
+reg(LoopNodeRunPayload)
+reg(DraftWorkflowRunPayload)
+reg(DraftWorkflowNodeRunPayload)
+reg(PublishWorkflowPayload)
+reg(DefaultBlockConfigQuery)
+reg(ConvertToWorkflowPayload)
+reg(WorkflowListQuery)
+reg(WorkflowUpdatePayload)
+reg(WorkflowFeaturesPayload)
+reg(WorkflowOnlineUsersPayload)
+reg(DraftWorkflowTriggerRunPayload)
+reg(DraftWorkflowTriggerRunAllPayload)
 
 
 # TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
@@ -542,12 +540,9 @@ class HumanInputDeliveryTestPayload(BaseModel):
     )
 
 
-register_schema_models(
-    console_ns,
-    HumanInputFormPreviewPayload,
-    HumanInputFormSubmitPayload,
-    HumanInputDeliveryTestPayload,
-)
+reg(HumanInputFormPreviewPayload)
+reg(HumanInputFormSubmitPayload)
+reg(HumanInputDeliveryTestPayload)
 
 
 @console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/human-input/nodes/<string:node_id>/form/preview")
@@ -765,17 +760,14 @@ class DraftWorkflowNodeRunApi(Resource):
     @console_ns.doc(description="Run draft workflow node")
     @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
     @console_ns.expect(console_ns.models[DraftWorkflowNodeRunPayload.__name__])
-    @console_ns.response(
-        200,
-        "Node run started successfully",
-        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-    )
+    @console_ns.response(200, "Node run started successfully", workflow_run_node_execution_model)
     @console_ns.response(403, "Permission denied")
     @console_ns.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_node_execution_model)
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -807,9 +799,7 @@ class DraftWorkflowNodeRunApi(Resource):
             files=files,
         )
 
-        return WorkflowRunNodeExecutionResponse.model_validate(
-            workflow_node_execution, from_attributes=True
-        ).model_dump(mode="json")
+        return workflow_node_execution
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflows/publish")
@@ -912,7 +902,7 @@ class DefaultBlockConfigApi(Resource):
         """
         Get default block config
         """
-        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))
+        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         filters = None
         if args.q:
@@ -1005,7 +995,7 @@ class PublishedAllWorkflowApi(Resource):
         """
         current_user, _ = current_account_with_tenant()
 
-        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         page = args.page
         limit = args.limit
         user_id = args.user_id
@@ -1153,17 +1143,14 @@ class DraftWorkflowNodeLastRunApi(Resource):
     @console_ns.doc("get_draft_workflow_node_last_run")
     @console_ns.doc(description="Get last run result for draft workflow node")
     @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
-    @console_ns.response(
-        200,
-        "Node last run retrieved successfully",
-        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-    )
+    @console_ns.response(200, "Node last run retrieved successfully", workflow_run_node_execution_model)
     @console_ns.response(404, "Node last run not found")
     @console_ns.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_node_execution_model)
     def get(self, app_model: App, node_id: str):
         srv = WorkflowService()
         workflow = srv.get_draft_workflow(app_model)
@@ -1176,7 +1163,7 @@ class DraftWorkflowNodeLastRunApi(Resource):
         )
         if node_exec is None:
             raise NotFound("last run not found")
-        return WorkflowRunNodeExecutionResponse.model_validate(node_exec, from_attributes=True).model_dump(mode="json")
+        return node_exec
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflows/draft/trigger/run")

api/controllers/console/app/workflow_app_log.py

@@ -185,7 +185,7 @@ class WorkflowAppLogApi(Resource):
         """
         Get workflow app logs
         """
-        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         # get paginate workflow app logs
         workflow_app_service = WorkflowAppService()
@@ -228,7 +228,7 @@ class WorkflowArchivedLogApi(Resource):
         """
         Get workflow archived logs
         """
-        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowAppLogQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         workflow_app_service = WorkflowAppService()
         with sessionmaker(db.engine, expire_on_commit=False).begin() as session:

api/controllers/console/app/workflow_comment.py

@@ -23,6 +23,7 @@ from services.account_service import TenantService
 from services.workflow_comment_service import WorkflowCommentService
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
 class WorkflowCommentCreatePayload(BaseModel):
@@ -51,14 +52,13 @@ class WorkflowCommentMentionUsersPayload(BaseModel):
     users: list[AccountWithRole]
 
 
-register_schema_models(
-    console_ns,
-    AccountWithRole,
-    WorkflowCommentMentionUsersPayload,
+for model in (
     WorkflowCommentCreatePayload,
     WorkflowCommentUpdatePayload,
     WorkflowCommentReplyPayload,
-)
+):
+    console_ns.schema_model(model.__name__, model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+register_schema_models(console_ns, AccountWithRole, WorkflowCommentMentionUsersPayload)
 
 workflow_comment_basic_model = console_ns.model("WorkflowCommentBasic", workflow_comment_basic_fields)
 workflow_comment_detail_model = console_ns.model("WorkflowCommentDetail", workflow_comment_detail_fields)

api/controllers/console/app/workflow_draft_variable.py

@@ -8,7 +8,6 @@ from flask_restx import Resource, fields, marshal, marshal_with
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import sessionmaker
 
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.error import (
     DraftWorkflowNotExist,
@@ -34,6 +33,7 @@ from services.workflow_service import WorkflowService
 
 logger = logging.getLogger(__name__)
 _file_access_controller = DatabaseFileAccessController()
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
 class WorkflowDraftVariableListQuery(BaseModel):
@@ -56,12 +56,21 @@ class EnvironmentVariableUpdatePayload(BaseModel):
     environment_variables: list[dict[str, Any]] = Field(..., description="Environment variables for the draft workflow")
 
 
-register_schema_models(
-    console_ns,
-    WorkflowDraftVariableListQuery,
-    WorkflowDraftVariableUpdatePayload,
-    ConversationVariableUpdatePayload,
-    EnvironmentVariableUpdatePayload,
+console_ns.schema_model(
+    WorkflowDraftVariableListQuery.__name__,
+    WorkflowDraftVariableListQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    WorkflowDraftVariableUpdatePayload.__name__,
+    WorkflowDraftVariableUpdatePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ConversationVariableUpdatePayload.__name__,
+    ConversationVariableUpdatePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    EnvironmentVariableUpdatePayload.__name__,
+    EnvironmentVariableUpdatePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
 )
 
 
@@ -251,7 +260,7 @@ class WorkflowVariableCollectionApi(Resource):
         """
         Get draft workflow
         """
-        args = WorkflowDraftVariableListQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowDraftVariableListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         # fetch draft workflow by app_model
         workflow_service = WorkflowService()

api/controllers/console/app/workflow_run.py

@@ -1,28 +1,30 @@
 from datetime import UTC, datetime, timedelta
-from typing import Literal, cast
+from typing import Literal, TypedDict, cast
 
 from flask import request
-from flask_restx import Resource
+from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import select
 from sqlalchemy.orm import sessionmaker
 
 from configs import dify_config
-from controllers.common.schema import query_params_from_model, register_response_schema_models, register_schema_models
 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 controllers.web.error import NotFoundError
 from core.workflow.human_input_forms import load_form_tokens_by_form_id as _load_form_tokens_by_form_id
 from extensions.ext_database import db
-from fields.base import ResponseModel
+from fields.end_user_fields import simple_end_user_fields
+from fields.member_fields import simple_account_fields
 from fields.workflow_run_fields import (
-    AdvancedChatWorkflowRunPaginationResponse,
-    WorkflowRunCountResponse,
-    WorkflowRunDetailResponse,
-    WorkflowRunNodeExecutionListResponse,
-    WorkflowRunNodeExecutionResponse,
-    WorkflowRunPaginationResponse,
+    advanced_chat_workflow_run_for_list_fields,
+    advanced_chat_workflow_run_pagination_fields,
+    workflow_run_count_fields,
+    workflow_run_detail_fields,
+    workflow_run_for_list_fields,
+    workflow_run_node_execution_fields,
+    workflow_run_node_execution_list_fields,
+    workflow_run_pagination_fields,
 )
 from graphon.entities.pause_reason import HumanInputRequired
 from graphon.enums import WorkflowExecutionStatus
@@ -50,6 +52,82 @@ def _build_backstage_input_url(form_token: str | None) -> str | None:
 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
+
+# Base models
+simple_account_model = console_ns.model("SimpleAccount", simple_account_fields)
+
+simple_end_user_model = console_ns.model("SimpleEndUser", simple_end_user_fields)
+
+# Models that depend on simple_account_fields
+workflow_run_for_list_fields_copy = workflow_run_for_list_fields.copy()
+workflow_run_for_list_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_for_list_model = console_ns.model("WorkflowRunForList", workflow_run_for_list_fields_copy)
+
+advanced_chat_workflow_run_for_list_fields_copy = advanced_chat_workflow_run_for_list_fields.copy()
+advanced_chat_workflow_run_for_list_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+advanced_chat_workflow_run_for_list_model = console_ns.model(
+    "AdvancedChatWorkflowRunForList", advanced_chat_workflow_run_for_list_fields_copy
+)
+
+workflow_run_detail_fields_copy = workflow_run_detail_fields.copy()
+workflow_run_detail_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_detail_fields_copy["created_by_end_user"] = fields.Nested(
+    simple_end_user_model, attribute="created_by_end_user", allow_null=True
+)
+workflow_run_detail_model = console_ns.model("WorkflowRunDetail", workflow_run_detail_fields_copy)
+
+workflow_run_node_execution_fields_copy = workflow_run_node_execution_fields.copy()
+workflow_run_node_execution_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_node_execution_fields_copy["created_by_end_user"] = fields.Nested(
+    simple_end_user_model, attribute="created_by_end_user", allow_null=True
+)
+workflow_run_node_execution_model = console_ns.model(
+    "WorkflowRunNodeExecution", workflow_run_node_execution_fields_copy
+)
+
+# Simple models without nested dependencies
+workflow_run_count_model = console_ns.model("WorkflowRunCount", workflow_run_count_fields)
+
+# Pagination models that depend on list models
+advanced_chat_workflow_run_pagination_fields_copy = advanced_chat_workflow_run_pagination_fields.copy()
+advanced_chat_workflow_run_pagination_fields_copy["data"] = fields.List(
+    fields.Nested(advanced_chat_workflow_run_for_list_model), attribute="data"
+)
+advanced_chat_workflow_run_pagination_model = console_ns.model(
+    "AdvancedChatWorkflowRunPagination", advanced_chat_workflow_run_pagination_fields_copy
+)
+
+workflow_run_pagination_fields_copy = workflow_run_pagination_fields.copy()
+workflow_run_pagination_fields_copy["data"] = fields.List(fields.Nested(workflow_run_for_list_model), attribute="data")
+workflow_run_pagination_model = console_ns.model("WorkflowRunPagination", workflow_run_pagination_fields_copy)
+
+workflow_run_node_execution_list_fields_copy = workflow_run_node_execution_list_fields.copy()
+workflow_run_node_execution_list_fields_copy["data"] = fields.List(fields.Nested(workflow_run_node_execution_model))
+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}"
+
 
 class WorkflowRunListQuery(BaseModel):
     last_id: str | None = Field(default=None, description="Last run ID for pagination")
@@ -58,7 +136,7 @@ class WorkflowRunListQuery(BaseModel):
         default=None, description="Workflow run status filter"
     )
     triggered_from: Literal["debugging", "app-run"] | None = Field(
-        default=None, description="Filter by trigger source: debugging or app-run. Default: debugging"
+        default=None, description="Filter by trigger source: debugging or app-run"
     )
 
     @field_validator("last_id")
@@ -73,15 +151,9 @@ class WorkflowRunCountQuery(BaseModel):
     status: Literal["running", "succeeded", "failed", "stopped", "partial-succeeded"] | None = Field(
         default=None, description="Workflow run status filter"
     )
-    time_range: str | None = Field(
-        default=None,
-        description=(
-            "Filter by time range (optional): e.g., 7d (7 days), 4h (4 hours), "
-            "30m (30 minutes), 30s (30 seconds). Filters by created_at field."
-        ),
-    )
+    time_range: str | None = Field(default=None, description="Time range filter (e.g., 7d, 4h, 30m, 30s)")
     triggered_from: Literal["debugging", "app-run"] | None = Field(
-        default=None, description="Filter by trigger source: debugging or app-run. Default: debugging"
+        default=None, description="Filter by trigger source: debugging or app-run"
     )
 
     @field_validator("time_range")
@@ -92,69 +164,56 @@ class WorkflowRunCountQuery(BaseModel):
         return time_duration(value)
 
 
-class WorkflowRunExportResponse(ResponseModel):
-    status: str = Field(description="Export status: success/failed")
-    presigned_url: str | None = Field(default=None, description="Pre-signed URL for download")
-    presigned_url_expires_at: str | None = Field(default=None, description="Pre-signed URL expiration time")
+console_ns.schema_model(
+    WorkflowRunListQuery.__name__, WorkflowRunListQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    WorkflowRunCountQuery.__name__,
+    WorkflowRunCountQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
-class HumanInputPauseTypeResponse(ResponseModel):
+class HumanInputPauseTypeResponse(TypedDict):
     type: Literal["human_input"]
     form_id: str
-    backstage_input_url: str | None = None
+    backstage_input_url: str | None
 
 
-class PausedNodeResponse(ResponseModel):
+class PausedNodeResponse(TypedDict):
     node_id: str
     node_title: str
     pause_type: HumanInputPauseTypeResponse
 
 
-class WorkflowPauseDetailsResponse(ResponseModel):
-    paused_at: str | None = None
+class WorkflowPauseDetailsResponse(TypedDict):
+    paused_at: str | None
     paused_nodes: list[PausedNodeResponse]
 
 
-register_schema_models(
-    console_ns,
-    WorkflowRunListQuery,
-    WorkflowRunCountQuery,
-)
-register_response_schema_models(
-    console_ns,
-    AdvancedChatWorkflowRunPaginationResponse,
-    WorkflowRunPaginationResponse,
-    WorkflowRunCountResponse,
-    WorkflowRunDetailResponse,
-    WorkflowRunNodeExecutionResponse,
-    WorkflowRunNodeExecutionListResponse,
-    WorkflowRunExportResponse,
-    HumanInputPauseTypeResponse,
-    PausedNodeResponse,
-    WorkflowPauseDetailsResponse,
-)
-
-
 @console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflow-runs")
 class AdvancedChatAppWorkflowRunListApi(Resource):
     @console_ns.doc("get_advanced_chat_workflow_runs")
     @console_ns.doc(description="Get advanced chat workflow run list")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.doc(params=query_params_from_model(WorkflowRunListQuery))
-    @console_ns.response(
-        200,
-        "Workflow runs retrieved successfully",
-        console_ns.models[AdvancedChatWorkflowRunPaginationResponse.__name__],
+    @console_ns.doc(params={"last_id": "Last run ID for pagination", "limit": "Number of items per page (1-100)"})
+    @console_ns.doc(
+        params={"status": "Filter by status (optional): running, succeeded, failed, stopped, partial-succeeded"}
     )
+    @console_ns.doc(
+        params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
+    )
+    @console_ns.expect(console_ns.models[WorkflowRunListQuery.__name__])
+    @console_ns.response(200, "Workflow runs retrieved successfully", advanced_chat_workflow_run_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT])
+    @marshal_with(advanced_chat_workflow_run_pagination_model)
     def get(self, app_model: App):
         """
         Get advanced chat app workflow run list
         """
-        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))
+        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         args: WorkflowRunListArgs = {"limit": args_model.limit}
         if args_model.last_id is not None:
             args["last_id"] = args_model.last_id
@@ -173,9 +232,7 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
             app_model=app_model, args=args, triggered_from=triggered_from
         )
 
-        return AdvancedChatWorkflowRunPaginationResponse.model_validate(result, from_attributes=True).model_dump(
-            mode="json"
-        )
+        return result
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/export")
@@ -183,7 +240,7 @@ 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", console_ns.models[WorkflowRunExportResponse.__name__])
+    @console_ns.response(200, "Export URL generated", workflow_run_export_fields)
     @setup_required
     @login_required
     @account_initialization_required
@@ -221,14 +278,11 @@ class WorkflowRunExportApi(Resource):
             expires_in=EXPORT_SIGNED_URL_EXPIRE_SECONDS,
         )
         expires_at = datetime.now(UTC) + timedelta(seconds=EXPORT_SIGNED_URL_EXPIRE_SECONDS)
-        response = WorkflowRunExportResponse.model_validate(
-            {
-                "status": "success",
-                "presigned_url": presigned_url,
-                "presigned_url_expires_at": expires_at.isoformat(),
-            }
-        )
-        return response.model_dump(mode="json"), 200
+        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")
@@ -236,21 +290,32 @@ class AdvancedChatAppWorkflowRunCountApi(Resource):
     @console_ns.doc("get_advanced_chat_workflow_runs_count")
     @console_ns.doc(description="Get advanced chat workflow runs count statistics")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.doc(params=query_params_from_model(WorkflowRunCountQuery))
-    @console_ns.response(
-        200,
-        "Workflow runs count retrieved successfully",
-        console_ns.models[WorkflowRunCountResponse.__name__],
+    @console_ns.doc(
+        params={"status": "Filter by status (optional): running, succeeded, failed, stopped, partial-succeeded"}
     )
+    @console_ns.doc(
+        params={
+            "time_range": (
+                "Filter by time range (optional): e.g., 7d (7 days), 4h (4 hours), "
+                "30m (30 minutes), 30s (30 seconds). Filters by created_at field."
+            )
+        }
+    )
+    @console_ns.doc(
+        params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
+    )
+    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_model)
+    @console_ns.expect(console_ns.models[WorkflowRunCountQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT])
+    @marshal_with(workflow_run_count_model)
     def get(self, app_model: App):
         """
         Get advanced chat workflow runs count statistics
         """
-        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))
+        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING if not specified
@@ -268,7 +333,7 @@ class AdvancedChatAppWorkflowRunCountApi(Resource):
             triggered_from=triggered_from,
         )
 
-        return WorkflowRunCountResponse.model_validate(result).model_dump(mode="json")
+        return result
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-runs")
@@ -276,21 +341,25 @@ class WorkflowRunListApi(Resource):
     @console_ns.doc("get_workflow_runs")
     @console_ns.doc(description="Get workflow run list")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.doc(params=query_params_from_model(WorkflowRunListQuery))
-    @console_ns.response(
-        200,
-        "Workflow runs retrieved successfully",
-        console_ns.models[WorkflowRunPaginationResponse.__name__],
+    @console_ns.doc(params={"last_id": "Last run ID for pagination", "limit": "Number of items per page (1-100)"})
+    @console_ns.doc(
+        params={"status": "Filter by status (optional): running, succeeded, failed, stopped, partial-succeeded"}
     )
+    @console_ns.doc(
+        params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
+    )
+    @console_ns.response(200, "Workflow runs retrieved successfully", workflow_run_pagination_model)
+    @console_ns.expect(console_ns.models[WorkflowRunListQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_pagination_model)
     def get(self, app_model: App):
         """
         Get workflow run list
         """
-        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))
+        args_model = WorkflowRunListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         args: WorkflowRunListArgs = {"limit": args_model.limit}
         if args_model.last_id is not None:
             args["last_id"] = args_model.last_id
@@ -309,7 +378,7 @@ class WorkflowRunListApi(Resource):
             app_model=app_model, args=args, triggered_from=triggered_from
         )
 
-        return WorkflowRunPaginationResponse.model_validate(result, from_attributes=True).model_dump(mode="json")
+        return result
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-runs/count")
@@ -317,21 +386,32 @@ class WorkflowRunCountApi(Resource):
     @console_ns.doc("get_workflow_runs_count")
     @console_ns.doc(description="Get workflow runs count statistics")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.doc(params=query_params_from_model(WorkflowRunCountQuery))
-    @console_ns.response(
-        200,
-        "Workflow runs count retrieved successfully",
-        console_ns.models[WorkflowRunCountResponse.__name__],
+    @console_ns.doc(
+        params={"status": "Filter by status (optional): running, succeeded, failed, stopped, partial-succeeded"}
     )
+    @console_ns.doc(
+        params={
+            "time_range": (
+                "Filter by time range (optional): e.g., 7d (7 days), 4h (4 hours), "
+                "30m (30 minutes), 30s (30 seconds). Filters by created_at field."
+            )
+        }
+    )
+    @console_ns.doc(
+        params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
+    )
+    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_model)
+    @console_ns.expect(console_ns.models[WorkflowRunCountQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_count_model)
     def get(self, app_model: App):
         """
         Get workflow runs count statistics
         """
-        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))
+        args_model = WorkflowRunCountQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         args = args_model.model_dump(exclude_none=True)
 
         # Default to DEBUGGING for workflow if not specified (backward compatibility)
@@ -349,7 +429,7 @@ class WorkflowRunCountApi(Resource):
             triggered_from=triggered_from,
         )
 
-        return WorkflowRunCountResponse.model_validate(result).model_dump(mode="json")
+        return result
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>")
@@ -357,16 +437,13 @@ class WorkflowRunDetailApi(Resource):
     @console_ns.doc("get_workflow_run_detail")
     @console_ns.doc(description="Get workflow run detail")
     @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
-    @console_ns.response(
-        200,
-        "Workflow run detail retrieved successfully",
-        console_ns.models[WorkflowRunDetailResponse.__name__],
-    )
+    @console_ns.response(200, "Workflow run detail retrieved successfully", workflow_run_detail_model)
     @console_ns.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_detail_model)
     def get(self, app_model: App, run_id):
         """
         Get workflow run detail
@@ -375,10 +452,8 @@ class WorkflowRunDetailApi(Resource):
 
         workflow_run_service = WorkflowRunService()
         workflow_run = workflow_run_service.get_workflow_run(app_model=app_model, run_id=run_id)
-        if workflow_run is None:
-            raise NotFoundError("Workflow run not found")
 
-        return WorkflowRunDetailResponse.model_validate(workflow_run, from_attributes=True).model_dump(mode="json")
+        return workflow_run
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-runs/<uuid:run_id>/node-executions")
@@ -386,16 +461,13 @@ class WorkflowRunNodeExecutionListApi(Resource):
     @console_ns.doc("get_workflow_run_node_executions")
     @console_ns.doc(description="Get workflow run node execution list")
     @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
-    @console_ns.response(
-        200,
-        "Node executions retrieved successfully",
-        console_ns.models[WorkflowRunNodeExecutionListResponse.__name__],
-    )
+    @console_ns.response(200, "Node executions retrieved successfully", workflow_run_node_execution_list_model)
     @console_ns.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_node_execution_list_model)
     def get(self, app_model: App, run_id):
         """
         Get workflow run node execution list
@@ -410,24 +482,13 @@ class WorkflowRunNodeExecutionListApi(Resource):
             user=user,
         )
 
-        return WorkflowRunNodeExecutionListResponse.model_validate(
-            {"data": node_executions}, from_attributes=True
-        ).model_dump(mode="json")
+        return {"data": node_executions}
 
 
 @console_ns.route("/workflow/<string:workflow_run_id>/pause-details")
 class ConsoleWorkflowPauseDetailsApi(Resource):
     """Console API for getting workflow pause details."""
 
-    @console_ns.doc("get_workflow_pause_details")
-    @console_ns.doc(description="Get workflow pause details")
-    @console_ns.doc(params={"workflow_run_id": "Workflow run ID"})
-    @console_ns.response(
-        200,
-        "Workflow pause details retrieved successfully",
-        console_ns.models[WorkflowPauseDetailsResponse.__name__],
-    )
-    @console_ns.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
@@ -454,8 +515,11 @@ class ConsoleWorkflowPauseDetailsApi(Resource):
         # Check if workflow is suspended
         is_paused = workflow_run.status == WorkflowExecutionStatus.PAUSED
         if not is_paused:
-            empty_response = WorkflowPauseDetailsResponse(paused_at=None, paused_nodes=[])
-            return empty_response.model_dump(mode="json"), 200
+            empty_response: WorkflowPauseDetailsResponse = {
+                "paused_at": None,
+                "paused_nodes": [],
+            }
+            return empty_response, 200
 
         pause_entity = workflow_run_repo.get_workflow_pause(workflow_run_id)
         pause_reasons = pause_entity.get_pause_reasons() if pause_entity else []
@@ -466,25 +530,27 @@ class ConsoleWorkflowPauseDetailsApi(Resource):
         # Build response
         paused_at = pause_entity.paused_at if pause_entity else None
         paused_nodes: list[PausedNodeResponse] = []
+        response: WorkflowPauseDetailsResponse = {
+            "paused_at": paused_at.isoformat() + "Z" if paused_at else None,
+            "paused_nodes": paused_nodes,
+        }
 
         for reason in pause_reasons:
             if isinstance(reason, HumanInputRequired):
                 paused_nodes.append(
-                    PausedNodeResponse(
-                        node_id=reason.node_id,
-                        node_title=reason.node_title,
-                        pause_type=HumanInputPauseTypeResponse(
-                            type="human_input",
-                            form_id=reason.form_id,
-                            backstage_input_url=_build_backstage_input_url(form_tokens_by_form_id.get(reason.form_id)),
-                        ),
-                    )
+                    {
+                        "node_id": reason.node_id,
+                        "node_title": reason.node_title,
+                        "pause_type": {
+                            "type": "human_input",
+                            "form_id": reason.form_id,
+                            "backstage_input_url": _build_backstage_input_url(
+                                form_tokens_by_form_id.get(reason.form_id)
+                            ),
+                        },
+                    }
                 )
             else:
                 raise AssertionError("unimplemented.")
 
-        response = WorkflowPauseDetailsResponse(
-            paused_at=paused_at.isoformat() + "Z" if paused_at else None,
-            paused_nodes=paused_nodes,
-        )
-        return response.model_dump(mode="json"), 200
+        return response, 200

api/controllers/console/app/workflow_statistic.py

@@ -3,7 +3,6 @@ from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy.orm import sessionmaker
 
-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.wraps import account_initialization_required, setup_required
@@ -14,6 +13,8 @@ from models.enums import WorkflowRunTriggeredFrom
 from models.model import AppMode
 from repositories.factory import DifyAPIRepositoryFactory
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class WorkflowStatisticQuery(BaseModel):
     start: str | None = Field(default=None, description="Start date and time (YYYY-MM-DD HH:MM)")
@@ -27,7 +28,10 @@ class WorkflowStatisticQuery(BaseModel):
         return value
 
 
-register_schema_models(console_ns, WorkflowStatisticQuery)
+console_ns.schema_model(
+    WorkflowStatisticQuery.__name__,
+    WorkflowStatisticQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflow/statistics/daily-conversations")
@@ -49,7 +53,7 @@ class WorkflowDailyRunsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         assert account.timezone is not None
 
@@ -89,7 +93,7 @@ class WorkflowDailyTerminalsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         assert account.timezone is not None
 
@@ -129,7 +133,7 @@ class WorkflowDailyTokenCostStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         assert account.timezone is not None
 
@@ -169,7 +173,7 @@ class WorkflowAverageAppInteractionStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))
+        args = WorkflowStatisticQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         assert account.timezone is not None
 

api/controllers/console/app/workflow_trigger.py

@@ -94,7 +94,7 @@ class WebhookTriggerApi(Resource):
     @console_ns.response(200, "Success", console_ns.models[WebhookTriggerResponse.__name__])
     def get(self, app_model: App):
         """Get webhook trigger for a node"""
-        args = Parser.model_validate(request.args.to_dict(flat=True))
+        args = Parser.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         node_id = args.node_id
 

api/controllers/console/auth/activate.py

@@ -63,7 +63,7 @@ class ActivateCheckApi(Resource):
         console_ns.models[ActivationCheckResponse.__name__],
     )
     def get(self):
-        args = ActivateCheckQuery.model_validate(request.args.to_dict(flat=True))
+        args = ActivateCheckQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         workspaceId = args.workspace_id
         token = args.token

api/controllers/console/auth/data_source_bearer_auth.py

@@ -1,7 +1,6 @@
 from flask_restx import Resource
 from pydantic import BaseModel, Field
 
-from controllers.common.schema import register_schema_models
 from libs.login import current_account_with_tenant, login_required
 from services.auth.api_key_auth_service import ApiKeyAuthService
 
@@ -9,6 +8,8 @@ from .. import console_ns
 from ..auth.error import ApiKeyAuthFailedError
 from ..wraps import account_initialization_required, is_admin_or_owner_required, setup_required
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class ApiKeyAuthBindingPayload(BaseModel):
     category: str = Field(...)
@@ -16,7 +17,10 @@ class ApiKeyAuthBindingPayload(BaseModel):
     credentials: dict = Field(...)
 
 
-register_schema_models(console_ns, ApiKeyAuthBindingPayload)
+console_ns.schema_model(
+    ApiKeyAuthBindingPayload.__name__,
+    ApiKeyAuthBindingPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 @console_ns.route("/api-key-auth/data-source")

api/controllers/console/auth/email_register.py

@@ -4,7 +4,6 @@ from pydantic import BaseModel, Field, field_validator
 
 from configs import dify_config
 from constants.languages import languages
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.auth.error import (
     EmailAlreadyInUseError,
@@ -24,6 +23,8 @@ from services.errors.account import AccountNotFoundError, AccountRegisterError
 from ..error import AccountInFreezeError, EmailSendIpLimitError
 from ..wraps import email_password_login_enabled, email_register_enabled, setup_required
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class EmailRegisterSendPayload(BaseModel):
     email: EmailStr = Field(..., description="Email address")
@@ -47,7 +48,8 @@ class EmailRegisterResetPayload(BaseModel):
         return valid_password(value)
 
 
-register_schema_models(console_ns, EmailRegisterSendPayload, EmailRegisterValidityPayload, EmailRegisterResetPayload)
+for model in (EmailRegisterSendPayload, EmailRegisterValidityPayload, EmailRegisterResetPayload):
+    console_ns.schema_model(model.__name__, model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
 
 
 @console_ns.route("/email-register/send-email")

api/controllers/console/auth/forgot_password.py

@@ -28,6 +28,8 @@ from services.entities.auth_entities import (
 )
 from services.feature_service import FeatureService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class ForgotPasswordEmailResponse(BaseModel):
     result: str = Field(description="Operation result")

api/controllers/console/auth/login.py

@@ -9,7 +9,6 @@ from werkzeug.exceptions import Unauthorized
 import services
 from configs import dify_config
 from constants.languages import get_valid_language
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.auth.error import (
     AuthenticationFailedError,
@@ -51,6 +50,7 @@ from services.errors.account import AccountRegisterError
 from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
 from services.feature_service import FeatureService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 logger = logging.getLogger(__name__)
 
 
@@ -71,7 +71,13 @@ class EmailCodeLoginPayload(BaseModel):
     language: str | None = Field(default=None)
 
 
-register_schema_models(console_ns, LoginPayload, EmailPayload, EmailCodeLoginPayload)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(LoginPayload)
+reg(EmailPayload)
+reg(EmailCodeLoginPayload)
 
 
 @console_ns.route("/login")

api/controllers/console/datasets/datasets.py

@@ -606,63 +606,63 @@ class DatasetIndexingEstimateApi(Resource):
         # validate args
         DocumentService.estimate_args_validate(args)
         extract_settings = []
-        match args["info_list"]["data_source_type"]:
-            case "upload_file":
-                file_ids = args["info_list"]["file_info_list"]["file_ids"]
-                file_details = db.session.scalars(
-                    select(UploadFile).where(UploadFile.tenant_id == current_tenant_id, UploadFile.id.in_(file_ids))
-                ).all()
-                if file_details is None:
-                    raise NotFound("File not found.")
+        if args["info_list"]["data_source_type"] == "upload_file":
+            file_ids = args["info_list"]["file_info_list"]["file_ids"]
+            file_details = db.session.scalars(
+                select(UploadFile).where(UploadFile.tenant_id == current_tenant_id, UploadFile.id.in_(file_ids))
+            ).all()
 
-                if file_details:
-                    for file_detail in file_details:
-                        extract_setting = ExtractSetting(
-                            datasource_type=DatasourceType.FILE,
-                            upload_file=file_detail,
-                            document_model=args["doc_form"],
-                        )
-                        extract_settings.append(extract_setting)
-            case "notion_import":
-                notion_info_list = args["info_list"]["notion_info_list"]
-                for notion_info in notion_info_list:
-                    workspace_id = notion_info["workspace_id"]
-                    credential_id = notion_info.get("credential_id")
-                    for page in notion_info["pages"]:
-                        extract_setting = ExtractSetting(
-                            datasource_type=DatasourceType.NOTION,
-                            notion_info=NotionInfo.model_validate(
-                                {
-                                    "credential_id": credential_id,
-                                    "notion_workspace_id": workspace_id,
-                                    "notion_obj_id": page["page_id"],
-                                    "notion_page_type": page["type"],
-                                    "tenant_id": current_tenant_id,
-                                }
-                            ),
-                            document_model=args["doc_form"],
-                        )
-                        extract_settings.append(extract_setting)
-            case "website_crawl":
-                website_info_list = args["info_list"]["website_info_list"]
-                for url in website_info_list["urls"]:
+            if file_details is None:
+                raise NotFound("File not found.")
+
+            if file_details:
+                for file_detail in file_details:
                     extract_setting = ExtractSetting(
-                        datasource_type=DatasourceType.WEBSITE,
-                        website_info=WebsiteInfo.model_validate(
+                        datasource_type=DatasourceType.FILE,
+                        upload_file=file_detail,
+                        document_model=args["doc_form"],
+                    )
+                    extract_settings.append(extract_setting)
+        elif args["info_list"]["data_source_type"] == "notion_import":
+            notion_info_list = args["info_list"]["notion_info_list"]
+            for notion_info in notion_info_list:
+                workspace_id = notion_info["workspace_id"]
+                credential_id = notion_info.get("credential_id")
+                for page in notion_info["pages"]:
+                    extract_setting = ExtractSetting(
+                        datasource_type=DatasourceType.NOTION,
+                        notion_info=NotionInfo.model_validate(
                             {
-                                "provider": website_info_list["provider"],
-                                "job_id": website_info_list["job_id"],
-                                "url": url,
+                                "credential_id": credential_id,
+                                "notion_workspace_id": workspace_id,
+                                "notion_obj_id": page["page_id"],
+                                "notion_page_type": page["type"],
                                 "tenant_id": current_tenant_id,
-                                "mode": "crawl",
-                                "only_main_content": website_info_list["only_main_content"],
                             }
                         ),
                         document_model=args["doc_form"],
                     )
                     extract_settings.append(extract_setting)
-            case _:
-                raise ValueError("Data source type not support")
+        elif args["info_list"]["data_source_type"] == "website_crawl":
+            website_info_list = args["info_list"]["website_info_list"]
+            for url in website_info_list["urls"]:
+                extract_setting = ExtractSetting(
+                    datasource_type=DatasourceType.WEBSITE,
+                    website_info=WebsiteInfo.model_validate(
+                        {
+                            "provider": website_info_list["provider"],
+                            "job_id": website_info_list["job_id"],
+                            "url": url,
+                            "tenant_id": current_tenant_id,
+                            "mode": "crawl",
+                            "only_main_content": website_info_list["only_main_content"],
+                        }
+                    ),
+                    document_model=args["doc_form"],
+                )
+                extract_settings.append(extract_setting)
+        else:
+            raise ValueError("Data source type not support")
         indexing_runner = IndexingRunner()
         try:
             response = indexing_runner.indexing_estimate(

api/controllers/console/datasets/datasets_document.py

@@ -369,31 +369,28 @@ class DatasetDocumentListApi(Resource):
         else:
             sort_logic = asc
 
-        match sort:
-            case "hit_count":
-                sub_query = (
-                    sa.select(
-                        DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count")
-                    )
-                    .where(DocumentSegment.dataset_id == str(dataset_id))
-                    .group_by(DocumentSegment.document_id)
-                    .subquery()
-                )
+        if sort == "hit_count":
+            sub_query = (
+                sa.select(DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count"))
+                .where(DocumentSegment.dataset_id == str(dataset_id))
+                .group_by(DocumentSegment.document_id)
+                .subquery()
+            )
 
-                query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by(
-                    sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)),
-                    sort_logic(Document.position),
-                )
-            case "created_at":
-                query = query.order_by(
-                    sort_logic(Document.created_at),
-                    sort_logic(Document.position),
-                )
-            case _:
-                query = query.order_by(
-                    desc(Document.created_at),
-                    desc(Document.position),
-                )
+            query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by(
+                sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)),
+                sort_logic(Document.position),
+            )
+        elif sort == "created_at":
+            query = query.order_by(
+                sort_logic(Document.created_at),
+                sort_logic(Document.position),
+            )
+        else:
+            query = query.order_by(
+                desc(Document.created_at),
+                desc(Document.position),
+            )
 
         paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
         documents = paginated_documents.items

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

@@ -4,7 +4,6 @@ from flask_restx import (  # type: ignore
 from pydantic import BaseModel
 from werkzeug.exceptions import Forbidden
 
-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 account_initialization_required, setup_required
@@ -13,6 +12,8 @@ from models import Account
 from models.dataset import Pipeline
 from services.rag_pipeline.rag_pipeline import RagPipelineService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class Parser(BaseModel):
     inputs: dict
@@ -20,7 +21,7 @@ class Parser(BaseModel):
     credential_id: str | None = None
 
 
-register_schema_models(console_ns, Parser)
+console_ns.schema_model(Parser.__name__, Parser.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
 
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/published/datasource/nodes/<string:node_id>/preview")

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

@@ -10,7 +10,7 @@ from werkzeug.exceptions import BadRequest, Forbidden, InternalServerError, NotF
 
 import services
 from controllers.common.controller_schemas import DefaultBlockConfigQuery, WorkflowListQuery, WorkflowUpdatePayload
-from controllers.common.schema import register_response_schema_models, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.app.error import (
     ConversationCompletedError,
@@ -22,6 +22,12 @@ 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,
@@ -34,12 +40,6 @@ from core.app.apps.pipeline.pipeline_generator import PipelineGenerator
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
 from factories import variable_factory
-from fields.workflow_run_fields import (
-    WorkflowRunDetailResponse,
-    WorkflowRunNodeExecutionListResponse,
-    WorkflowRunNodeExecutionResponse,
-    WorkflowRunPaginationResponse,
-)
 from graphon.model_runtime.utils.encoders import jsonable_encoder
 from libs import helper
 from libs.helper import TimestampField, UUIDStrOrEmpty
@@ -131,13 +131,6 @@ register_schema_models(
     DatasourceVariablesPayload,
     RagPipelineRecommendedPluginQuery,
 )
-register_response_schema_models(
-    console_ns,
-    WorkflowRunDetailResponse,
-    WorkflowRunNodeExecutionListResponse,
-    WorkflowRunNodeExecutionResponse,
-    WorkflowRunPaginationResponse,
-)
 
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft")
@@ -422,16 +415,12 @@ class RagPipelineDraftDatasourceNodeRunApi(Resource):
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/nodes/<string:node_id>/run")
 class RagPipelineDraftNodeRunApi(Resource):
     @console_ns.expect(console_ns.models[NodeRunRequiredPayload.__name__])
-    @console_ns.response(
-        200,
-        "Node run started successfully",
-        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-    )
     @setup_required
     @login_required
     @edit_permission_required
     @account_initialization_required
     @get_rag_pipeline
+    @marshal_with(workflow_run_node_execution_model)
     def post(self, pipeline: Pipeline, node_id: str):
         """
         Run draft workflow node
@@ -450,9 +439,7 @@ class RagPipelineDraftNodeRunApi(Resource):
         if workflow_node_execution is None:
             raise ValueError("Workflow node execution not found")
 
-        return WorkflowRunNodeExecutionResponse.model_validate(
-            workflow_node_execution, from_attributes=True
-        ).model_dump(mode="json")
+        return workflow_node_execution
 
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflow-runs/tasks/<string:task_id>/stop")
@@ -791,15 +778,11 @@ class DraftRagPipelineSecondStepApi(Resource):
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflow-runs")
 class RagPipelineWorkflowRunListApi(Resource):
-    @console_ns.response(
-        200,
-        "Workflow runs retrieved successfully",
-        console_ns.models[WorkflowRunPaginationResponse.__name__],
-    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_rag_pipeline
+    @marshal_with(workflow_run_pagination_model)
     def get(self, pipeline: Pipeline):
         """
         Get workflow run list
@@ -818,20 +801,16 @@ class RagPipelineWorkflowRunListApi(Resource):
         rag_pipeline_service = RagPipelineService()
         result = rag_pipeline_service.get_rag_pipeline_paginate_workflow_runs(pipeline=pipeline, args=args)
 
-        return WorkflowRunPaginationResponse.model_validate(result, from_attributes=True).model_dump(mode="json")
+        return result
 
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflow-runs/<uuid:run_id>")
 class RagPipelineWorkflowRunDetailApi(Resource):
-    @console_ns.response(
-        200,
-        "Workflow run detail retrieved successfully",
-        console_ns.models[WorkflowRunDetailResponse.__name__],
-    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_rag_pipeline
+    @marshal_with(workflow_run_detail_model)
     def get(self, pipeline: Pipeline, run_id):
         """
         Get workflow run detail
@@ -840,23 +819,17 @@ class RagPipelineWorkflowRunDetailApi(Resource):
 
         rag_pipeline_service = RagPipelineService()
         workflow_run = rag_pipeline_service.get_rag_pipeline_workflow_run(pipeline=pipeline, run_id=run_id)
-        if workflow_run is None:
-            raise NotFound("Workflow run not found")
 
-        return WorkflowRunDetailResponse.model_validate(workflow_run, from_attributes=True).model_dump(mode="json")
+        return workflow_run
 
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflow-runs/<uuid:run_id>/node-executions")
 class RagPipelineWorkflowRunNodeExecutionListApi(Resource):
-    @console_ns.response(
-        200,
-        "Node executions retrieved successfully",
-        console_ns.models[WorkflowRunNodeExecutionListResponse.__name__],
-    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_rag_pipeline
+    @marshal_with(workflow_run_node_execution_list_model)
     def get(self, pipeline: Pipeline, run_id: str):
         """
         Get workflow run node execution list
@@ -871,9 +844,7 @@ class RagPipelineWorkflowRunNodeExecutionListApi(Resource):
             user=user,
         )
 
-        return WorkflowRunNodeExecutionListResponse.model_validate(
-            {"data": node_executions}, from_attributes=True
-        ).model_dump(mode="json")
+        return {"data": node_executions}
 
 
 @console_ns.route("/rag/pipelines/datasource-plugins")
@@ -888,15 +859,11 @@ class DatasourceListApi(Resource):
 
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/nodes/<string:node_id>/last-run")
 class RagPipelineWorkflowLastRunApi(Resource):
-    @console_ns.response(
-        200,
-        "Node last run retrieved successfully",
-        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_rag_pipeline
+    @marshal_with(workflow_run_node_execution_model)
     def get(self, pipeline: Pipeline, node_id: str):
         rag_pipeline_service = RagPipelineService()
         workflow = rag_pipeline_service.get_draft_workflow(pipeline=pipeline)
@@ -909,7 +876,7 @@ class RagPipelineWorkflowLastRunApi(Resource):
         )
         if node_exec is None:
             raise NotFound("last run not found")
-        return WorkflowRunNodeExecutionResponse.model_validate(node_exec, from_attributes=True).model_dump(mode="json")
+        return node_exec
 
 
 @console_ns.route("/rag/pipelines/transform/datasets/<uuid:dataset_id>")
@@ -932,16 +899,12 @@ class RagPipelineTransformApi(Resource):
 @console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/datasource/variables-inspect")
 class RagPipelineDatasourceVariableApi(Resource):
     @console_ns.expect(console_ns.models[DatasourceVariablesPayload.__name__])
-    @console_ns.response(
-        200,
-        "Datasource variables set successfully",
-        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
-    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_rag_pipeline
     @edit_permission_required
+    @marshal_with(workflow_run_node_execution_model)
     def post(self, pipeline: Pipeline):
         """
         Set datasource variables
@@ -955,9 +918,7 @@ class RagPipelineDatasourceVariableApi(Resource):
             args=args,
             current_user=current_user,
         )
-        return WorkflowRunNodeExecutionResponse.model_validate(
-            workflow_node_execution, from_attributes=True
-        ).model_dump(mode="json")
+        return workflow_node_execution
 
 
 @console_ns.route("/rag/pipelines/recommended-plugins")

api/controllers/console/explore/recommended_app.py

@@ -1,12 +1,11 @@
 from typing import Any
-from uuid import UUID
 
 from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, computed_field, field_validator
 
 from constants.languages import languages
-from controllers.common.schema import query_params_from_model, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required
 from fields.base import ResponseModel
@@ -16,7 +15,7 @@ from services.recommended_app_service import RecommendedAppService
 
 
 class RecommendedAppsQuery(BaseModel):
-    language: str | None = Field(default=None, description="Language code for recommended app localization")
+    language: str | None = Field(default=None)
 
 
 class RecommendedAppInfoResponse(ResponseModel):
@@ -75,13 +74,13 @@ register_schema_models(
 
 @console_ns.route("/explore/apps")
 class RecommendedAppListApi(Resource):
-    @console_ns.doc(params=query_params_from_model(RecommendedAppsQuery))
+    @console_ns.expect(console_ns.models[RecommendedAppsQuery.__name__])
     @console_ns.response(200, "Success", console_ns.models[RecommendedAppListResponse.__name__])
     @login_required
     @account_initialization_required
     def get(self):
         # language args
-        args = RecommendedAppsQuery.model_validate(request.args.to_dict(flat=True))
+        args = RecommendedAppsQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         language = args.language
         if language and language in languages:
             language_prefix = language
@@ -100,5 +99,6 @@ class RecommendedAppListApi(Resource):
 class RecommendedAppApi(Resource):
     @login_required
     @account_initialization_required
-    def get(self, app_id: UUID):
-        return RecommendedAppService.get_recommend_app_detail(str(app_id))
+    def get(self, app_id):
+        app_id = str(app_id)
+        return RecommendedAppService.get_recommend_app_detail(app_id)

api/controllers/console/explore/trial.py

@@ -10,7 +10,7 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.common.fields import Parameters as ParametersResponse
 from controllers.common.fields import Site as SiteResponse
-from controllers.common.schema import get_or_create_model, register_schema_models
+from controllers.common.schema import get_or_create_model
 from controllers.console import console_ns
 from controllers.console.app.error import (
     AppUnavailableError,
@@ -106,7 +106,7 @@ app_detail_fields_with_site_copy["tags"] = fields.List(fields.Nested(tag_model))
 app_detail_fields_with_site_copy["site"] = fields.Nested(site_model)
 app_detail_with_site_model = get_or_create_model("TrialAppDetailWithSite", app_detail_fields_with_site_copy)
 
-simple_account_model = get_or_create_model("TrialSimpleAccount", simple_account_fields)
+simple_account_model = get_or_create_model("SimpleAccount", simple_account_fields)
 conversation_variable_model = get_or_create_model("TrialConversationVariable", conversation_variable_fields)
 pipeline_variable_model = get_or_create_model("TrialPipelineVariable", pipeline_variable_fields)
 
@@ -120,6 +120,10 @@ workflow_fields_copy["rag_pipeline_variables"] = fields.List(fields.Nested(pipel
 workflow_model = get_or_create_model("TrialWorkflow", workflow_fields_copy)
 
 
+# Pydantic models for request validation
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
 class WorkflowRunRequest(BaseModel):
     inputs: dict
     files: list | None = None
@@ -149,7 +153,19 @@ class CompletionRequest(BaseModel):
     retriever_from: str = "explore_app"
 
 
-register_schema_models(console_ns, WorkflowRunRequest, ChatRequest, TextToSpeechRequest, CompletionRequest)
+# Register schemas for Swagger documentation
+console_ns.schema_model(
+    WorkflowRunRequest.__name__, WorkflowRunRequest.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    ChatRequest.__name__, ChatRequest.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    TextToSpeechRequest.__name__, TextToSpeechRequest.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    CompletionRequest.__name__, CompletionRequest.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 class TrialAppWorkflowRunApi(TrialAppResource):

api/controllers/console/extension.py

@@ -89,7 +89,7 @@ class CodeBasedExtensionAPI(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        query = CodeBasedExtensionQuery.model_validate(request.args.to_dict(flat=True))
+        query = CodeBasedExtensionQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         return CodeBasedExtensionResponse(
             module=query.module,

api/controllers/console/files.py

@@ -82,7 +82,7 @@ class FileApi(Resource):
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=current_user,
                 source=source,

api/controllers/console/workspace/account.py

@@ -52,6 +52,8 @@ from services.account_service import AccountService
 from services.billing_service import BillingService
 from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class AccountInitPayload(BaseModel):
     interface_language: str
@@ -159,26 +161,27 @@ class CheckEmailUniquePayload(BaseModel):
     email: EmailStr
 
 
-register_schema_models(
-    console_ns,
-    AccountResponse,
-    AccountInitPayload,
-    AccountNamePayload,
-    AccountAvatarPayload,
-    AccountAvatarQuery,
-    AccountInterfaceLanguagePayload,
-    AccountInterfaceThemePayload,
-    AccountTimezonePayload,
-    AccountPasswordPayload,
-    AccountDeletePayload,
-    AccountDeletionFeedbackPayload,
-    EducationActivatePayload,
-    EducationAutocompleteQuery,
-    ChangeEmailSendPayload,
-    ChangeEmailValidityPayload,
-    ChangeEmailResetPayload,
-    CheckEmailUniquePayload,
-)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(AccountInitPayload)
+reg(AccountNamePayload)
+reg(AccountAvatarPayload)
+reg(AccountAvatarQuery)
+reg(AccountInterfaceLanguagePayload)
+reg(AccountInterfaceThemePayload)
+reg(AccountTimezonePayload)
+reg(AccountPasswordPayload)
+reg(AccountDeletePayload)
+reg(AccountDeletionFeedbackPayload)
+reg(EducationActivatePayload)
+reg(EducationAutocompleteQuery)
+reg(ChangeEmailSendPayload)
+reg(ChangeEmailValidityPayload)
+reg(ChangeEmailResetPayload)
+reg(CheckEmailUniquePayload)
+register_schema_models(console_ns, AccountResponse)
 
 
 def _serialize_account(account) -> dict[str, Any]:
@@ -323,7 +326,7 @@ class AccountAvatarApi(Resource):
     @account_initialization_required
     def get(self):
         current_user, current_tenant_id = current_account_with_tenant()
-        args = AccountAvatarQuery.model_validate(request.args.to_dict(flat=True))
+        args = AccountAvatarQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         avatar = args.avatar
 
         if avatar.startswith(("http://", "https://")):

api/controllers/console/workspace/endpoint.py

@@ -20,6 +20,8 @@ from graphon.model_runtime.utils.encoders import jsonable_encoder
 from libs.login import current_account_with_tenant, login_required
 from services.plugin.endpoint_service import EndpointService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class EndpointCreatePayload(BaseModel):
     plugin_unique_identifier: str
@@ -78,6 +80,10 @@ class EndpointDisableResponse(BaseModel):
     success: bool = Field(description="Operation success")
 
 
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
 register_schema_models(
     console_ns,
     EndpointCreatePayload,
@@ -209,7 +215,7 @@ class EndpointListApi(Resource):
     def get(self):
         user, tenant_id = current_account_with_tenant()
 
-        args = EndpointListQuery.model_validate(request.args.to_dict(flat=True))
+        args = EndpointListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         page = args.page
         page_size = args.page_size
@@ -242,7 +248,7 @@ class EndpointListForSinglePluginApi(Resource):
     def get(self):
         user, tenant_id = current_account_with_tenant()
 
-        args = EndpointListForPluginQuery.model_validate(request.args.to_dict(flat=True))
+        args = EndpointListForPluginQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         page = args.page
         page_size = args.page_size

api/controllers/console/workspace/members.py

@@ -33,6 +33,8 @@ from services.account_service import AccountService, RegisterService, TenantServ
 from services.errors.account import AccountAlreadyInTenantError
 from services.feature_service import FeatureService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class MemberInvitePayload(BaseModel):
     emails: list[str] = Field(default_factory=list)
@@ -57,17 +59,17 @@ class OwnerTransferPayload(BaseModel):
     token: str
 
 
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(MemberInvitePayload)
+reg(MemberRoleUpdatePayload)
+reg(OwnerTransferEmailPayload)
+reg(OwnerTransferCheckPayload)
+reg(OwnerTransferPayload)
 register_enum_models(console_ns, TenantAccountRole)
-register_schema_models(
-    console_ns,
-    AccountWithRole,
-    AccountWithRoleList,
-    MemberInvitePayload,
-    MemberRoleUpdatePayload,
-    OwnerTransferEmailPayload,
-    OwnerTransferCheckPayload,
-    OwnerTransferPayload,
-)
+register_schema_models(console_ns, AccountWithRole, AccountWithRoleList)
 
 
 @console_ns.route("/workspaces/current/members")

api/controllers/console/workspace/model_providers.py

@@ -5,7 +5,6 @@ from flask import request, send_file
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
 
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
 from graphon.model_runtime.entities.model_entities import ModelType
@@ -16,6 +15,8 @@ from libs.login import current_account_with_tenant, login_required
 from services.billing_service import BillingService
 from services.model_provider_service import ModelProviderService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class ParserModelList(BaseModel):
     model_type: ModelType | None = None
@@ -74,17 +75,18 @@ class ParserPreferredProviderType(BaseModel):
     preferred_provider_type: Literal["system", "custom"]
 
 
-register_schema_models(
-    console_ns,
-    ParserModelList,
-    ParserCredentialId,
-    ParserCredentialCreate,
-    ParserCredentialUpdate,
-    ParserCredentialDelete,
-    ParserCredentialSwitch,
-    ParserCredentialValidate,
-    ParserPreferredProviderType,
-)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(ParserModelList)
+reg(ParserCredentialId)
+reg(ParserCredentialCreate)
+reg(ParserCredentialUpdate)
+reg(ParserCredentialDelete)
+reg(ParserCredentialSwitch)
+reg(ParserCredentialValidate)
+reg(ParserPreferredProviderType)
 
 
 @console_ns.route("/workspaces/current/model-providers")

api/controllers/console/workspace/models.py

@@ -17,6 +17,7 @@ from services.model_load_balancing_service import ModelLoadBalancingService
 from services.model_provider_service import ModelProviderService
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
 class ParserGetDefault(BaseModel):
@@ -106,12 +107,6 @@ class ParserParameter(BaseModel):
     model: str
 
 
-class ParserSwitch(BaseModel):
-    model: str
-    model_type: ModelType
-    credential_id: str
-
-
 register_schema_models(
     console_ns,
     ParserGetDefault,
@@ -124,7 +119,6 @@ register_schema_models(
     ParserDeleteCredential,
     ParserParameter,
     Inner,
-    ParserSwitch,
 )
 
 register_enum_models(console_ns, ModelType)
@@ -139,7 +133,7 @@ class DefaultModelApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserGetDefault.model_validate(request.args.to_dict(flat=True))
+        args = ParserGetDefault.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         model_provider_service = ModelProviderService()
         default_model_entity = model_provider_service.get_default_model_of_model_type(
@@ -267,7 +261,7 @@ class ModelProviderModelCredentialApi(Resource):
     def get(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserGetCredentials.model_validate(request.args.to_dict(flat=True))
+        args = ParserGetCredentials.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         model_provider_service = ModelProviderService()
         current_credential = model_provider_service.get_model_credential(
@@ -393,6 +387,17 @@ class ModelProviderModelCredentialApi(Resource):
         return {"result": "success"}, 204
 
 
+class ParserSwitch(BaseModel):
+    model: str
+    model_type: ModelType
+    credential_id: str
+
+
+console_ns.schema_model(
+    ParserSwitch.__name__, ParserSwitch.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/credentials/switch")
 class ModelProviderModelCredentialSwitchApi(Resource):
     @console_ns.expect(console_ns.models[ParserSwitch.__name__])
@@ -463,7 +468,9 @@ class ParserValidate(BaseModel):
     credentials: dict[str, Any]
 
 
-register_schema_models(console_ns, ParserSwitch, ParserValidate)
+console_ns.schema_model(
+    ParserValidate.__name__, ParserValidate.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/credentials/validate")
@@ -508,7 +515,7 @@ class ModelProviderModelParameterRuleApi(Resource):
     @login_required
     @account_initialization_required
     def get(self, provider: str):
-        args = ParserParameter.model_validate(request.args.to_dict(flat=True))
+        args = ParserParameter.model_validate(request.args.to_dict(flat=True))  # type: ignore
         _, tenant_id = current_account_with_tenant()
 
         model_provider_service = ModelProviderService()

api/controllers/console/workspace/plugin.py

@@ -177,7 +177,7 @@ def _read_upload_content(file: FileStorage, max_size: int) -> bytes:
     FileStorage.content_length is not reliable for multipart test uploads and may be zero even when
     content exists, so the controllers validate against the loaded bytes instead.
     """
-    content = file.stream.read()
+    content = file.read()
     if len(content) > max_size:
         raise ValueError("File size exceeds the maximum allowed size")
 
@@ -211,7 +211,7 @@ class PluginListApi(Resource):
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserList.model_validate(request.args.to_dict(flat=True))
+        args = ParserList.model_validate(request.args.to_dict(flat=True))  # type: ignore
         try:
             plugins_with_total = PluginService.list_with_total(tenant_id, args.page, args.page_size)
         except PluginDaemonClientSideError as e:
@@ -261,7 +261,7 @@ class PluginIconApi(Resource):
     @console_ns.expect(console_ns.models[ParserIcon.__name__])
     @setup_required
     def get(self):
-        args = ParserIcon.model_validate(request.args.to_dict(flat=True))
+        args = ParserIcon.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             icon_bytes, mimetype = PluginService.get_asset(args.tenant_id, args.filename)
@@ -279,7 +279,7 @@ class PluginAssetApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        args = ParserAsset.model_validate(request.args.to_dict(flat=True))
+        args = ParserAsset.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         _, tenant_id = current_account_with_tenant()
         try:
@@ -421,7 +421,7 @@ class PluginFetchMarketplacePkgApi(Resource):
     @plugin_permission_required(install_required=True)
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             return jsonable_encoder(
@@ -446,7 +446,7 @@ class PluginFetchManifestApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             return jsonable_encoder(
@@ -466,7 +466,7 @@ class PluginFetchInstallTasksApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = ParserTasks.model_validate(request.args.to_dict(flat=True))
+        args = ParserTasks.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             return jsonable_encoder({"tasks": PluginService.fetch_install_tasks(tenant_id, args.page, args.page_size)})
@@ -660,7 +660,7 @@ class PluginFetchDynamicSelectOptionsApi(Resource):
         current_user, tenant_id = current_account_with_tenant()
         user_id = current_user.id
 
-        args = ParserDynamicOptions.model_validate(request.args.to_dict(flat=True))
+        args = ParserDynamicOptions.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             options = PluginParameterService.get_dynamic_select_options(
@@ -822,7 +822,7 @@ class PluginReadmeApi(Resource):
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = ParserReadme.model_validate(request.args.to_dict(flat=True))
+        args = ParserReadme.model_validate(request.args.to_dict(flat=True))  # type: ignore
         return jsonable_encoder(
             {"readme": PluginService.fetch_plugin_readme(tenant_id, args.plugin_unique_identifier, args.language)}
         )

api/controllers/console/workspace/workspace.py

@@ -16,7 +16,6 @@ from controllers.common.errors import (
     TooManyFilesError,
     UnsupportedFileTypeError,
 )
-from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
 from controllers.console.admin import admin_required
 from controllers.console.error import AccountNotLinkTenantError
@@ -40,6 +39,7 @@ from services.file_service import FileService
 from services.workspace_service import WorkspaceService
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
 class WorkspaceListQuery(BaseModel):
@@ -91,14 +91,15 @@ class TenantInfoResponse(ResponseModel):
         return value
 
 
-register_schema_models(
-    console_ns,
-    WorkspaceListQuery,
-    SwitchWorkspacePayload,
-    WorkspaceCustomConfigPayload,
-    WorkspaceInfoPayload,
-    TenantInfoResponse,
-)
+def reg(cls: type[BaseModel]):
+    console_ns.schema_model(cls.__name__, cls.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+
+reg(WorkspaceListQuery)
+reg(SwitchWorkspacePayload)
+reg(WorkspaceCustomConfigPayload)
+reg(WorkspaceInfoPayload)
+reg(TenantInfoResponse)
 
 provider_fields = {
     "provider_name": fields.String,
@@ -321,7 +322,7 @@ class WebappLogoWorkspaceApi(Resource):
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=current_user,
             )

api/controllers/files/image_preview.py

@@ -8,12 +8,13 @@ from werkzeug.exceptions import NotFound
 import services
 from controllers.common.errors import UnsupportedFileTypeError
 from controllers.common.file_response import enforce_download_for_html
-from controllers.common.schema import register_schema_models
 from controllers.files import files_ns
 from extensions.ext_database import db
 from services.account_service import TenantService
 from services.file_service import FileService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class FileSignatureQuery(BaseModel):
     timestamp: str = Field(..., description="Unix timestamp used in the signature")
@@ -25,7 +26,12 @@ class FilePreviewQuery(FileSignatureQuery):
     as_attachment: bool = Field(default=False, description="Whether to download as attachment")
 
 
-register_schema_models(files_ns, FileSignatureQuery, FilePreviewQuery)
+files_ns.schema_model(
+    FileSignatureQuery.__name__, FileSignatureQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+files_ns.schema_model(
+    FilePreviewQuery.__name__, FilePreviewQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @files_ns.route("/<uuid:file_id>/image-preview")
@@ -52,7 +58,7 @@ class ImagePreviewApi(Resource):
     def get(self, file_id):
         file_id = str(file_id)
 
-        args = FileSignatureQuery.model_validate(request.args.to_dict(flat=True))
+        args = FileSignatureQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
         timestamp = args.timestamp
         nonce = args.nonce
         sign = args.sign
@@ -94,7 +100,7 @@ class FilePreviewApi(Resource):
     def get(self, file_id):
         file_id = str(file_id)
 
-        args = FilePreviewQuery.model_validate(request.args.to_dict(flat=True))
+        args = FilePreviewQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             generator, upload_file = FileService(db.engine).get_file_generator_by_file_id(

api/controllers/files/tool_files.py

@@ -7,11 +7,12 @@ from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.common.errors import UnsupportedFileTypeError
 from controllers.common.file_response import enforce_download_for_html
-from controllers.common.schema import register_schema_models
 from controllers.files import files_ns
 from core.tools.signature import verify_tool_file_signature
 from core.tools.tool_file_manager import ToolFileManager
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class ToolFileQuery(BaseModel):
     timestamp: str = Field(..., description="Unix timestamp")
@@ -20,7 +21,9 @@ class ToolFileQuery(BaseModel):
     as_attachment: bool = Field(default=False, description="Download as attachment")
 
 
-register_schema_models(files_ns, ToolFileQuery)
+files_ns.schema_model(
+    ToolFileQuery.__name__, ToolFileQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @files_ns.route("/tools/<uuid:file_id>.<string:extension>")

api/controllers/files/upload.py

@@ -20,6 +20,8 @@ from ..console.wraps import setup_required
 from ..files import files_ns
 from ..inner_api.plugin.wraps import get_user
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 class PluginUploadQuery(BaseModel):
     timestamp: str = Field(..., description="Unix timestamp for signature verification")
@@ -29,8 +31,9 @@ class PluginUploadQuery(BaseModel):
     user_id: str | None = Field(default=None, description="User identifier")
 
 
-register_schema_models(files_ns, PluginUploadQuery)
-
+files_ns.schema_model(
+    PluginUploadQuery.__name__, PluginUploadQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 register_schema_models(files_ns, FileResponse)
 
@@ -66,7 +69,7 @@ class PluginUploadFileApi(Resource):
             FileTooLargeError: File exceeds size limit
             UnsupportedFileTypeError: File type not supported
         """
-        args = PluginUploadQuery.model_validate(request.args.to_dict(flat=True))
+        args = PluginUploadQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         file = request.files.get("file")
         if file is None:
@@ -100,7 +103,7 @@ class PluginUploadFileApi(Resource):
             tool_file = ToolFileManager().create_file_by_raw(
                 user_id=user.id,
                 tenant_id=tenant_id,
-                file_binary=file.stream.read(),
+                file_binary=file.read(),
                 mimetype=mimetype,
                 filename=filename,
                 conversation_id=None,

api/controllers/service_api/app/file.py

@@ -58,7 +58,7 @@ class FileApi(Resource):
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=end_user,
             )

api/controllers/service_api/dataset/dataset.py

@@ -6,7 +6,7 @@ from pydantic import BaseModel, Field, TypeAdapter, field_validator, model_valid
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
-from controllers.common.schema import register_enum_models, register_schema_models
+from controllers.common.schema import register_schema_models
 from controllers.console.wraps import edit_permission_required
 from controllers.service_api import service_api_ns
 from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError, InvalidActionError
@@ -34,7 +34,13 @@ from services.tag_service import (
     UpdateTagPayload,
 )
 
-register_enum_models(service_api_ns, DatasetPermissionEnum)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
+service_api_ns.schema_model(
+    DatasetPermissionEnum.__name__,
+    TypeAdapter(DatasetPermissionEnum).json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 class DatasetCreatePayload(BaseModel):

api/controllers/service_api/dataset/document.py

@@ -77,6 +77,9 @@ class DocumentTextCreatePayload(BaseModel):
         return value
 
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
 class DocumentTextUpdate(BaseModel):
     name: str | None = None
     text: str | None = None
@@ -136,7 +139,7 @@ def _create_document_by_text(tenant_id: str, dataset_id: UUID) -> tuple[Mapping[
     if not dataset:
         raise ValueError("Dataset does not exist.")
 
-    if not dataset.indexing_technique and not args.get("indexing_technique"):
+    if not dataset.indexing_technique and not args["indexing_technique"]:
         raise ValueError("indexing_technique is required.")
 
     embedding_model_provider = payload.embedding_model_provider
@@ -432,7 +435,7 @@ class DocumentAddByFileApi(DatasetApiResource):
             raise ValueError("current_user is required")
         upload_file = FileService(db.engine).upload_file(
             filename=file.filename,
-            content=file.stream.read(),
+            content=file.read(),
             mimetype=file.mimetype,
             user=current_user,
             source="datasets",
@@ -506,7 +509,7 @@ def _update_document_by_file(tenant_id: str, dataset_id: UUID, document_id: UUID
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=current_user,
                 source="datasets",

api/controllers/service_api/dataset/rag_pipeline/rag_pipeline_workflow.py

@@ -241,7 +241,7 @@ class KnowledgebasePipelineFileUploadApi(DatasetApiResource):
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=current_user,
             )

api/controllers/web/files.py

@@ -73,7 +73,7 @@ class FileApi(WebApiResource):
         try:
             upload_file = FileService(db.engine).upload_file(
                 filename=file.filename,
-                content=file.stream.read(),
+                content=file.read(),
                 mimetype=file.mimetype,
                 user=end_user,
                 source="datasets" if source == "datasets" else None,

api/core/agent/base_agent_runner.py

@@ -532,6 +532,7 @@ class BaseAgentRunner(AppRunner):
         file_objs = file_factory.build_from_message_files(
             message_files=files,
             tenant_id=self.tenant_id,
+            config=file_extra_config,
             access_controller=_file_access_controller,
         )
         if not file_objs:

api/core/app/app_config/easy_ui_based_app/prompt_template/manager.py

@@ -75,7 +75,7 @@ class PromptTemplateConfigManager:
         if not config.get("prompt_type"):
             config["prompt_type"] = PromptTemplateEntity.PromptType.SIMPLE
 
-        prompt_type_vals = list(PromptTemplateEntity.PromptType)
+        prompt_type_vals = [typ.value for typ in PromptTemplateEntity.PromptType]
         if config["prompt_type"] not in prompt_type_vals:
             raise ValueError(f"prompt_type must be in {prompt_type_vals}")
 

api/core/app/apps/common/workflow_response_converter.py

@@ -842,24 +842,24 @@ class WorkflowResponseConverter:
             return []
 
         files: list[Mapping[str, Any]] = []
-        match value:
-            case FileSegment():
-                files.append(value.value.to_dict())
-            case ArrayFileSegment():
-                files.extend([i.to_dict() for i in value.value])
-            case File():
-                files.append(value.to_dict())
-            case list():
-                for item in value:
-                    file = cls._get_file_var_from_value(item)
-                    if file:
-                        files.append(file)
-            case dict():
-                file = cls._get_file_var_from_value(value)
+        if isinstance(value, FileSegment):
+            files.append(value.value.to_dict())
+        elif isinstance(value, ArrayFileSegment):
+            files.extend([i.to_dict() for i in value.value])
+        elif isinstance(value, File):
+            files.append(value.to_dict())
+        elif isinstance(value, list):
+            for item in value:
+                file = cls._get_file_var_from_value(item)
                 if file:
                     files.append(file)
-            case _:
-                pass
+        elif isinstance(
+            value,
+            dict,
+        ):
+            file = cls._get_file_var_from_value(value)
+            if file:
+                files.append(file)
 
         return files
 

api/core/app/apps/workflow/app_generator.py

@@ -32,7 +32,7 @@ from core.app.entities.task_entities import (
 )
 from core.app.layers.pause_state_persist_layer import PauseStateLayerConfig, PauseStatePersistenceLayer
 from core.db.session_factory import session_factory
-from core.helper.trace_id_helper import extract_external_trace_id_from_args, extract_parent_trace_context_from_args
+from core.helper.trace_id_helper import extract_external_trace_id_from_args
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.repositories import DifyCoreRepositoryFactory
 from core.repositories.factory import WorkflowExecutionRepository, WorkflowNodeExecutionRepository
@@ -166,7 +166,6 @@ class WorkflowAppGenerator(BaseAppGenerator):
 
             extras = {
                 **extract_external_trace_id_from_args(args),
-                **extract_parent_trace_context_from_args(args),
             }
             workflow_run_id = str(workflow_run_id or uuid.uuid4())
             # FIXME (Yeuoly): we need to remove the SKIP_PREPARE_USER_INPUTS_KEY from the args

api/core/app/llm/__init__.py

@@ -1,15 +1,5 @@
 """LLM-related application services."""
 
-from .quota import (
-    deduct_llm_quota,
-    deduct_llm_quota_for_model,
-    ensure_llm_quota_available,
-    ensure_llm_quota_available_for_model,
-)
+from .quota import deduct_llm_quota, ensure_llm_quota_available
 
-__all__ = [
-    "deduct_llm_quota",
-    "deduct_llm_quota_for_model",
-    "ensure_llm_quota_available",
-    "ensure_llm_quota_available_for_model",
-]
+__all__ = ["deduct_llm_quota", "ensure_llm_quota_available"]

api/core/app/llm/quota.py

@@ -1,14 +1,4 @@
-"""Tenant-scoped helpers for checking and deducting LLM provider quota.
-
-System-hosted quota accounting is currently defined only for LLM models. Keep
-the public helpers LLM-specific so callers do not carry unused model-type
-plumbing, and fail loudly if the deprecated ``ModelInstance`` wrappers are used
-with a non-LLM model.
-"""
-
-import warnings
-
-from sqlalchemy import select
+from sqlalchemy import update
 from sqlalchemy.orm import sessionmaker
 
 from configs import dify_config
@@ -16,47 +6,44 @@ from core.entities.model_entities import ModelStatus
 from core.entities.provider_entities import ProviderQuotaType, QuotaUnit
 from core.errors.error import QuotaExceededError
 from core.model_manager import ModelInstance
-from core.plugin.impl.model_runtime_factory import create_plugin_provider_manager
 from extensions.ext_database import db
 from graphon.model_runtime.entities.llm_entities import LLMUsage
-from graphon.model_runtime.entities.model_entities import ModelType
 from libs.datetime_utils import naive_utc_now
 from models.provider import Provider, ProviderType
 from models.provider_ids import ModelProviderID
 
 
-def _get_provider_configuration(*, tenant_id: str, provider: str):
-    """Resolve the tenant-bound provider configuration for quota decisions."""
-    provider_manager = create_plugin_provider_manager(tenant_id=tenant_id)
-    provider_configuration = provider_manager.get_configurations(tenant_id).get(provider)
-    if provider_configuration is None:
-        raise ValueError(f"Provider {provider} does not exist.")
-    return provider_configuration
+def ensure_llm_quota_available(*, model_instance: ModelInstance) -> None:
+    provider_model_bundle = model_instance.provider_model_bundle
+    provider_configuration = provider_model_bundle.configuration
 
-
-def ensure_llm_quota_available_for_model(*, tenant_id: str, provider: str, model: str) -> None:
-    """Raise when a tenant-bound LLM model is already out of quota."""
-    provider_configuration = _get_provider_configuration(tenant_id=tenant_id, provider=provider)
     if provider_configuration.using_provider_type != ProviderType.SYSTEM:
         return
 
     provider_model = provider_configuration.get_provider_model(
-        model_type=ModelType.LLM,
-        model=model,
+        model_type=model_instance.model_type_instance.model_type,
+        model=model_instance.model_name,
     )
     if provider_model and provider_model.status == ModelStatus.QUOTA_EXCEEDED:
-        raise QuotaExceededError(f"Model provider {provider} quota exceeded.")
+        raise QuotaExceededError(f"Model provider {model_instance.provider} quota exceeded.")
 
 
-def _resolve_llm_used_quota(*, system_configuration, model: str, usage: LLMUsage) -> int | None:
-    """Compute the quota impact for an LLM invocation under the current quota mode."""
+def deduct_llm_quota(*, tenant_id: str, model_instance: ModelInstance, usage: LLMUsage) -> None:
+    provider_model_bundle = model_instance.provider_model_bundle
+    provider_configuration = provider_model_bundle.configuration
+
+    if provider_configuration.using_provider_type != ProviderType.SYSTEM:
+        return
+
+    system_configuration = provider_configuration.system_configuration
+
     quota_unit = None
     for quota_configuration in system_configuration.quota_configurations:
         if quota_configuration.quota_type == system_configuration.current_quota_type:
             quota_unit = quota_configuration.quota_unit
 
             if quota_configuration.quota_limit == -1:
-                return None
+                return
 
             break
 
@@ -65,136 +52,42 @@ def _resolve_llm_used_quota(*, system_configuration, model: str, usage: LLMUsage
         if quota_unit == QuotaUnit.TOKENS:
             used_quota = usage.total_tokens
         elif quota_unit == QuotaUnit.CREDITS:
-            used_quota = dify_config.get_model_credits(model)
+            used_quota = dify_config.get_model_credits(model_instance.model_name)
         else:
             used_quota = 1
 
-    return used_quota
-
-
-def _deduct_free_llm_quota(
-    *,
-    tenant_id: str,
-    provider: str,
-    quota_type: ProviderQuotaType,
-    used_quota: int,
-) -> None:
-    """Deduct FREE provider quota, capping at the limit before reporting exhaustion."""
-    quota_exceeded = False
-    with sessionmaker(bind=db.engine).begin() as session:
-        provider_record = session.scalar(
-            select(Provider)
-            .where(
-                Provider.tenant_id == tenant_id,
-                # TODO: Use provider name with prefix after the data migration.
-                Provider.provider_name == ModelProviderID(provider).provider_name,
-                Provider.provider_type == ProviderType.SYSTEM.value,
-                Provider.quota_type == quota_type,
-            )
-            .with_for_update()
-        )
-        if (
-            provider_record is None
-            or provider_record.quota_limit is None
-            or provider_record.quota_used is None
-            or provider_record.quota_limit <= provider_record.quota_used
-        ):
-            quota_exceeded = True
-        else:
-            available_quota = provider_record.quota_limit - provider_record.quota_used
-            deducted_quota = min(used_quota, available_quota)
-            provider_record.quota_used += deducted_quota
-            provider_record.last_used = naive_utc_now()
-            quota_exceeded = deducted_quota < used_quota
-
-    if quota_exceeded:
-        raise QuotaExceededError(f"Model provider {provider} quota exceeded.")
-
-
-def _deduct_used_llm_quota(*, tenant_id: str, provider: str, provider_configuration, used_quota: int | None) -> None:
-    """Apply a resolved LLM quota charge against the current provider quota bucket."""
-    if provider_configuration.using_provider_type != ProviderType.SYSTEM:
-        return
-
-    system_configuration = provider_configuration.system_configuration
     if used_quota is not None and system_configuration.current_quota_type is not None:
         match system_configuration.current_quota_type:
             case ProviderQuotaType.TRIAL:
                 from services.credit_pool_service import CreditPoolService
 
-                CreditPoolService.deduct_credits_capped(
+                CreditPoolService.check_and_deduct_credits(
                     tenant_id=tenant_id,
                     credits_required=used_quota,
                 )
             case ProviderQuotaType.PAID:
                 from services.credit_pool_service import CreditPoolService
 
-                CreditPoolService.deduct_credits_capped(
+                CreditPoolService.check_and_deduct_credits(
                     tenant_id=tenant_id,
                     credits_required=used_quota,
                     pool_type="paid",
                 )
             case ProviderQuotaType.FREE:
-                _deduct_free_llm_quota(
-                    tenant_id=tenant_id,
-                    provider=provider,
-                    quota_type=system_configuration.current_quota_type,
-                    used_quota=used_quota,
-                )
-            case _:
-                return
-
-
-def deduct_llm_quota_for_model(*, tenant_id: str, provider: str, model: str, usage: LLMUsage) -> None:
-    """Deduct tenant-bound quota for the resolved LLM model identity."""
-    provider_configuration = _get_provider_configuration(tenant_id=tenant_id, provider=provider)
-    used_quota = _resolve_llm_used_quota(
-        system_configuration=provider_configuration.system_configuration,
-        model=model,
-        usage=usage,
-    )
-    _deduct_used_llm_quota(
-        tenant_id=tenant_id,
-        provider=provider,
-        provider_configuration=provider_configuration,
-        used_quota=used_quota,
-    )
-
-
-def _require_llm_model_instance(model_instance: ModelInstance) -> None:
-    """Reject deprecated wrapper calls that pass a non-LLM model instance."""
-    if model_instance.model_type_instance.model_type != ModelType.LLM:
-        raise ValueError("LLM quota helpers only support LLM model instances.")
-
-
-def ensure_llm_quota_available(*, model_instance: ModelInstance) -> None:
-    """Deprecated compatibility wrapper for callers that still pass ModelInstance."""
-    warnings.warn(
-        "ensure_llm_quota_available(model_instance=...) is deprecated; "
-        "use ensure_llm_quota_available_for_model(...) instead.",
-        DeprecationWarning,
-        stacklevel=2,
-    )
-    _require_llm_model_instance(model_instance)
-    ensure_llm_quota_available_for_model(
-        tenant_id=model_instance.provider_model_bundle.configuration.tenant_id,
-        provider=model_instance.provider,
-        model=model_instance.model_name,
-    )
-
-
-def deduct_llm_quota(*, tenant_id: str, model_instance: ModelInstance, usage: LLMUsage) -> None:
-    """Deprecated compatibility wrapper for callers that still pass ModelInstance."""
-    warnings.warn(
-        "deduct_llm_quota(tenant_id=..., model_instance=..., usage=...) is deprecated; "
-        "use deduct_llm_quota_for_model(...) instead.",
-        DeprecationWarning,
-        stacklevel=2,
-    )
-    _require_llm_model_instance(model_instance)
-    deduct_llm_quota_for_model(
-        tenant_id=tenant_id,
-        provider=model_instance.provider,
-        model=model_instance.model_name,
-        usage=usage,
-    )
+                with sessionmaker(bind=db.engine).begin() as session:
+                    stmt = (
+                        update(Provider)
+                        .where(
+                            Provider.tenant_id == tenant_id,
+                            # TODO: Use provider name with prefix after the data migration.
+                            Provider.provider_name == ModelProviderID(model_instance.provider).provider_name,
+                            Provider.provider_type == ProviderType.SYSTEM.value,
+                            Provider.quota_type == system_configuration.current_quota_type,
+                            Provider.quota_limit > Provider.quota_used,
+                        )
+                        .values(
+                            quota_used=Provider.quota_used + used_quota,
+                            last_used=naive_utc_now(),
+                        )
+                    )
+                    session.execute(stmt)

api/core/app/workflow/file_runtime.py

@@ -128,7 +128,7 @@ class DifyWorkflowFileRuntime(WorkflowFileRuntimeProtocol):
 
     @staticmethod
     def _secret_key() -> bytes:
-        return dify_config.SECRET_KEY.encode()
+        return dify_config.SECRET_KEY.encode() if dify_config.SECRET_KEY else b""
 
     def _sign_query(self, *, payload: str) -> dict[str, str]:
         timestamp = str(int(time.time()))

api/core/app/workflow/layers/llm_quota.py

@@ -1,48 +1,36 @@
 """
 LLM quota deduction layer for GraphEngine.
 
-This layer centralizes model-quota handling outside node implementations.
-
-Graphon LLM-backed nodes expose provider/model identity through public node
-configuration and, after execution, through ``node_run_result.inputs``. Resolve
-quota billing from that public identity instead of depending on
-``ModelInstance`` reconstruction inside the workflow layer. Missing identity on
-quota-tracked nodes is treated as a workflow bug and aborts execution so quota
-handling is never silently skipped.
+This layer centralizes model-quota deduction outside node implementations.
 """
 
 import logging
-from typing import final, override
+from typing import TYPE_CHECKING, cast, final, override
 
-from core.app.llm import deduct_llm_quota_for_model, ensure_llm_quota_available_for_model
+from core.app.entities.app_invoke_entities import DIFY_RUN_CONTEXT_KEY, DifyRunContext
+from core.app.llm import deduct_llm_quota, ensure_llm_quota_available
 from core.errors.error import QuotaExceededError
-from graphon.enums import BuiltinNodeTypes, WorkflowNodeExecutionStatus
+from core.model_manager import ModelInstance
+from graphon.enums import BuiltinNodeTypes
 from graphon.graph_engine.entities.commands import AbortCommand, CommandType
 from graphon.graph_engine.layers import GraphEngineLayer
 from graphon.graph_events import GraphEngineEvent, GraphNodeEventBase, NodeRunSucceededEvent
-from graphon.node_events import NodeRunResult
 from graphon.nodes.base.node import Node
 
+if TYPE_CHECKING:
+    from graphon.nodes.llm.node import LLMNode
+    from graphon.nodes.parameter_extractor.parameter_extractor_node import ParameterExtractorNode
+    from graphon.nodes.question_classifier.question_classifier_node import QuestionClassifierNode
+
 logger = logging.getLogger(__name__)
-_QUOTA_NODE_TYPES = frozenset(
-    [
-        BuiltinNodeTypes.LLM,
-        BuiltinNodeTypes.PARAMETER_EXTRACTOR,
-        BuiltinNodeTypes.QUESTION_CLASSIFIER,
-    ]
-)
 
 
 @final
 class LLMQuotaLayer(GraphEngineLayer):
-    """Graph layer that applies tenant-scoped quota checks to LLM-backed nodes."""
+    """Graph layer that applies LLM quota deduction after node execution."""
 
-    tenant_id: str
-    _abort_sent: bool
-
-    def __init__(self, tenant_id: str) -> None:
+    def __init__(self) -> None:
         super().__init__()
-        self.tenant_id = tenant_id
         self._abort_sent = False
 
     @override
@@ -62,49 +50,33 @@ class LLMQuotaLayer(GraphEngineLayer):
         if self._abort_sent:
             return
 
-        if not self._supports_quota(node):
+        model_instance = self._extract_model_instance(node)
+        if model_instance is None:
             return
 
-        model_identity = self._extract_model_identity_from_node(node)
-        if model_identity is None:
-            reason = "LLM quota check requires public node model identity before execution."
-            self._abort_before_node_run(node=node, reason=reason, error_type="LLMQuotaIdentityError")
-            logger.error("LLM quota handling aborted, node_id=%s, reason=%s", node.id, reason)
-            return
-
-        provider, model_name = model_identity
         try:
-            ensure_llm_quota_available_for_model(
-                tenant_id=self.tenant_id,
-                provider=provider,
-                model=model_name,
-            )
+            ensure_llm_quota_available(model_instance=model_instance)
         except QuotaExceededError as exc:
-            self._abort_before_node_run(node=node, reason=str(exc), error_type=QuotaExceededError.__name__)
+            self._set_stop_event(node)
+            self._send_abort_command(reason=str(exc))
             logger.warning("LLM quota check failed, node_id=%s, error=%s", node.id, exc)
 
     @override
     def on_node_run_end(
         self, node: Node, error: Exception | None, result_event: GraphNodeEventBase | None = None
     ) -> None:
-        if error is not None or not isinstance(result_event, NodeRunSucceededEvent) or not self._supports_quota(node):
+        if error is not None or not isinstance(result_event, NodeRunSucceededEvent):
             return
 
-        model_identity = self._extract_model_identity_from_result_event(result_event)
-        if model_identity is None:
-            self._abort_for_missing_model_identity(
-                node=node,
-                reason="LLM quota deduction requires model identity in the node result event.",
-            )
+        model_instance = self._extract_model_instance(node)
+        if model_instance is None:
             return
 
-        provider, model_name = model_identity
-
         try:
-            deduct_llm_quota_for_model(
-                tenant_id=self.tenant_id,
-                provider=provider,
-                model=model_name,
+            dify_ctx = DifyRunContext.model_validate(node.require_run_context_value(DIFY_RUN_CONTEXT_KEY))
+            deduct_llm_quota(
+                tenant_id=dify_ctx.tenant_id,
+                model_instance=model_instance,
                 usage=result_event.node_run_result.llm_usage,
             )
         except QuotaExceededError as exc:
@@ -120,27 +92,6 @@ class LLMQuotaLayer(GraphEngineLayer):
         if stop_event is not None:
             stop_event.set()
 
-    def _abort_before_node_run(self, *, node: Node, reason: str, error_type: str) -> None:
-        self._set_stop_event(node)
-        node.node_data.error_strategy = None
-        node.node_data.retry_config.retry_enabled = False
-
-        def quota_aborted_run() -> NodeRunResult:
-            return NodeRunResult(
-                status=WorkflowNodeExecutionStatus.FAILED,
-                error=reason,
-                error_type=error_type,
-            )
-
-        # TODO: Push Graphon to expose a public pre-run failure/skip hook, then replace this private _run override.
-        node._run = quota_aborted_run  # type: ignore[method-assign]
-        self._send_abort_command(reason=reason)
-
-    def _abort_for_missing_model_identity(self, *, node: Node, reason: str) -> None:
-        self._set_stop_event(node)
-        self._send_abort_command(reason=reason)
-        logger.error("LLM quota handling aborted, node_id=%s, reason=%s", node.id, reason)
-
     def _send_abort_command(self, *, reason: str) -> None:
         if not self.command_channel or self._abort_sent:
             return
@@ -157,38 +108,29 @@ class LLMQuotaLayer(GraphEngineLayer):
             logger.exception("Failed to send quota abort command")
 
     @staticmethod
-    def _supports_quota(node: Node) -> bool:
-        return node.node_type in _QUOTA_NODE_TYPES
-
-    @staticmethod
-    def _extract_model_identity_from_result_event(result_event: NodeRunSucceededEvent) -> tuple[str, str] | None:
-        provider = result_event.node_run_result.inputs.get("model_provider")
-        model_name = result_event.node_run_result.inputs.get("model_name")
-        if isinstance(provider, str) and provider and isinstance(model_name, str) and model_name:
-            return provider, model_name
-        return None
-
-    @staticmethod
-    def _extract_model_identity_from_node(node: Node) -> tuple[str, str] | None:
-        node_data = getattr(node, "node_data", None)
-        if node_data is None:
-            node_data = getattr(node, "data", None)
-
-        model_config = getattr(node_data, "model", None)
-        if model_config is None:
+    def _extract_model_instance(node: Node) -> ModelInstance | None:
+        try:
+            match node.node_type:
+                case BuiltinNodeTypes.LLM:
+                    model_instance = cast("LLMNode", node).model_instance
+                case BuiltinNodeTypes.PARAMETER_EXTRACTOR:
+                    model_instance = cast("ParameterExtractorNode", node).model_instance
+                case BuiltinNodeTypes.QUESTION_CLASSIFIER:
+                    model_instance = cast("QuestionClassifierNode", node).model_instance
+                case _:
+                    return None
+        except AttributeError:
             logger.warning(
-                "LLMQuotaLayer skipped quota handling because node model config is missing, node_id=%s",
+                "LLMQuotaLayer skipped quota deduction because node does not expose a model instance, node_id=%s",
                 node.id,
             )
             return None
 
-        provider = getattr(model_config, "provider", None)
-        model_name = getattr(model_config, "name", None)
-        if isinstance(provider, str) and provider and isinstance(model_name, str) and model_name:
-            return provider, model_name
+        if isinstance(model_instance, ModelInstance):
+            return model_instance
+
+        raw_model_instance = getattr(model_instance, "_model_instance", None)
+        if isinstance(raw_model_instance, ModelInstance):
+            return raw_model_instance
 
-        logger.warning(
-            "LLMQuotaLayer skipped quota handling because node model identity is invalid, node_id=%s",
-            node.id,
-        )
         return None

api/core/app/workflow/layers/persistence.py

@@ -15,7 +15,6 @@ from datetime import datetime
 from typing import Any, Union
 
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity
-from core.helper.trace_id_helper import ParentTraceContext
 from core.ops.entities.trace_entity import TraceTaskName
 from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.repositories.factory import WorkflowExecutionRepository, WorkflowNodeExecutionRepository
@@ -404,13 +403,8 @@ class WorkflowPersistenceLayer(GraphEngineLayer):
 
         conversation_id = self._system_variables().get(SystemVariableKey.CONVERSATION_ID.value)
         external_trace_id = None
-        parent_trace_context = None
         if isinstance(self._application_generate_entity, (WorkflowAppGenerateEntity, AdvancedChatAppGenerateEntity)):
-            extras = self._application_generate_entity.extras
-            external_trace_id = extras.get("external_trace_id")
-            parent_trace_context = extras.get("parent_trace_context")
-            if isinstance(parent_trace_context, ParentTraceContext):
-                parent_trace_context = parent_trace_context.model_dump(exclude_none=True)
+            external_trace_id = self._application_generate_entity.extras.get("external_trace_id")
 
         trace_task = TraceTask(
             TraceTaskName.WORKFLOW_TRACE,
@@ -418,7 +412,6 @@ class WorkflowPersistenceLayer(GraphEngineLayer):
             conversation_id=conversation_id,
             user_id=self._trace_manager.user_id,
             external_trace_id=external_trace_id,
-            parent_trace_context=parent_trace_context,
         )
         self._trace_manager.add_trace_task(trace_task)
 

api/core/datasource/datasource_file_manager.py

@@ -35,11 +35,8 @@ class DatasourceFileManager:
         timestamp = str(int(time.time()))
         nonce = os.urandom(16).hex()
         data_to_sign = f"file-preview|{datasource_file_id}|{timestamp}|{nonce}"
-        sign = hmac.new(
-            dify_config.SECRET_KEY.encode(),
-            data_to_sign.encode(),
-            hashlib.sha256,
-        ).digest()
+        secret_key = dify_config.SECRET_KEY.encode() if dify_config.SECRET_KEY else b""
+        sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
         encoded_sign = base64.urlsafe_b64encode(sign).decode()
 
         return f"{file_preview_url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}"
@@ -50,11 +47,8 @@ class DatasourceFileManager:
         verify signature
         """
         data_to_sign = f"file-preview|{datasource_file_id}|{timestamp}|{nonce}"
-        recalculated_sign = hmac.new(
-            dify_config.SECRET_KEY.encode(),
-            data_to_sign.encode(),
-            hashlib.sha256,
-        ).digest()
+        secret_key = dify_config.SECRET_KEY.encode() if dify_config.SECRET_KEY else b""
+        recalculated_sign = hmac.new(secret_key, data_to_sign.encode(), hashlib.sha256).digest()
         recalculated_encoded_sign = base64.urlsafe_b64encode(recalculated_sign).decode()
 
         # verify signature

api/core/entities/provider_configuration.py

@@ -23,7 +23,7 @@ from core.entities.provider_entities import (
 )
 from core.helper import encrypter
 from core.helper.model_provider_cache import ProviderCredentialsCache, ProviderCredentialsCacheType
-from core.plugin.impl.model_runtime_factory import create_model_type_instance, create_plugin_model_assembly
+from core.plugin.impl.model_runtime_factory import create_plugin_model_provider_factory
 from graphon.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType
 from graphon.model_runtime.entities.provider_entities import (
     ConfigurateMethod,
@@ -33,7 +33,7 @@ from graphon.model_runtime.entities.provider_entities import (
 )
 from graphon.model_runtime.model_providers.base.ai_model import AIModel
 from graphon.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
-from graphon.model_runtime.protocols.runtime import ModelRuntime
+from graphon.model_runtime.runtime import ModelRuntime
 from libs.datetime_utils import naive_utc_now
 from models.engine import db
 from models.enums import CredentialSourceType
@@ -106,18 +106,11 @@ class ProviderConfiguration(BaseModel):
         """Attach the already-composed runtime for request-bound call chains."""
         self._bound_model_runtime = model_runtime
 
-    def _get_runtime_and_provider_factory(self) -> tuple[ModelRuntime, ModelProviderFactory]:
-        """Resolve a provider factory that stays aligned with the runtime used by the caller."""
-        if self._bound_model_runtime is not None:
-            return self._bound_model_runtime, ModelProviderFactory(runtime=self._bound_model_runtime)
-
-        model_assembly = create_plugin_model_assembly(tenant_id=self.tenant_id)
-        return model_assembly.model_runtime, model_assembly.model_provider_factory
-
     def get_model_provider_factory(self) -> ModelProviderFactory:
         """Return a provider factory that preserves any request-bound runtime."""
-        _, model_provider_factory = self._get_runtime_and_provider_factory()
-        return model_provider_factory
+        if self._bound_model_runtime is not None:
+            return ModelProviderFactory(model_runtime=self._bound_model_runtime)
+        return create_plugin_model_provider_factory(tenant_id=self.tenant_id)
 
     def get_current_credentials(self, model_type: ModelType, model: str) -> dict[str, Any] | None:
         """
@@ -1399,13 +1392,10 @@ class ProviderConfiguration(BaseModel):
         :param model_type: model type
         :return:
         """
-        model_runtime, model_provider_factory = self._get_runtime_and_provider_factory()
-        provider_schema = model_provider_factory.get_provider_schema(provider=self.provider.provider)
-        return create_model_type_instance(
-            runtime=model_runtime,
-            provider_schema=provider_schema,
-            model_type=model_type,
-        )
+        model_provider_factory = self.get_model_provider_factory()
+
+        # Get model instance of LLM
+        return model_provider_factory.get_model_type_instance(provider=self.provider.provider, model_type=model_type)
 
     def get_model_schema(
         self, model_type: ModelType, model: str, credentials: dict[str, Any] | None

api/core/helper/moderation.py

@@ -4,7 +4,7 @@ from typing import cast
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.entities import DEFAULT_PLUGIN_ID
-from core.plugin.impl.model_runtime_factory import create_plugin_model_assembly
+from core.plugin.impl.model_runtime_factory import create_plugin_model_provider_factory
 from extensions.ext_hosting_provider import hosting_configuration
 from graphon.model_runtime.entities.model_entities import ModelType
 from graphon.model_runtime.errors.invoke import InvokeBadRequestError
@@ -41,8 +41,10 @@ def check_moderation(tenant_id: str, model_config: ModelConfigWithCredentialsEnt
             text_chunk = secrets.choice(text_chunks)
 
             try:
-                model_assembly = create_plugin_model_assembly(tenant_id=tenant_id)
-                model_type_instance = model_assembly.create_model_type_instance(
+                model_provider_factory = create_plugin_model_provider_factory(tenant_id=tenant_id)
+
+                # Get model instance of LLM
+                model_type_instance = model_provider_factory.get_model_type_instance(
                     provider=openai_provider_name, model_type=ModelType.MODERATION
                 )
                 model_type_instance = cast(ModerationModel, model_type_instance)

api/core/helper/trace_id_helper.py

@@ -3,17 +3,6 @@ import re
 from collections.abc import Mapping
 from typing import Any
 
-from pydantic import BaseModel, ConfigDict, StrictStr, ValidationError
-
-
-class ParentTraceContext(BaseModel):
-    """Typed parent trace context propagated from an outer workflow tool node."""
-
-    parent_workflow_run_id: StrictStr
-    parent_node_execution_id: StrictStr | None = None
-
-    model_config = ConfigDict(extra="forbid")
-
 
 def is_valid_trace_id(trace_id: str) -> bool:
     """
@@ -72,30 +61,6 @@ def extract_external_trace_id_from_args(args: Mapping[str, Any]):
     return {}
 
 
-def extract_parent_trace_context_from_args(args: Mapping[str, Any]) -> dict[str, ParentTraceContext]:
-    """
-    Extract 'parent_trace_context' from args.
-
-    Returns a dict suitable for use in extras when both parent identifiers exist.
-    Returns an empty dict if the context is missing or incomplete.
-    """
-    parent_trace_context = args.get("parent_trace_context")
-    if isinstance(parent_trace_context, ParentTraceContext):
-        context = parent_trace_context
-    elif isinstance(parent_trace_context, Mapping):
-        try:
-            context = ParentTraceContext.model_validate(parent_trace_context)
-        except ValidationError:
-            return {}
-    else:
-        return {}
-
-    if context.parent_node_execution_id is None:
-        return {}
-
-    return {"parent_trace_context": context}
-
-
 def get_trace_id_from_otel_context() -> str | None:
     """
     Retrieve the current trace ID from the active OpenTelemetry trace context.

api/core/indexing_runner.py

@@ -324,10 +324,9 @@ class IndexingRunner:
         # one extract_setting is one source document
         for extract_setting in extract_settings:
             # extract
-            processing_rule = {
-                "mode": tmp_processing_rule["mode"],
-                "rules": tmp_processing_rule.get("rules"),
-            }
+            processing_rule = DatasetProcessRule(
+                mode=tmp_processing_rule["mode"], rules=json.dumps(tmp_processing_rule["rules"])
+            )
             # Extract document content
             text_docs = index_processor.extract(extract_setting, process_rule_mode=tmp_processing_rule["mode"])
             # Cleaning and segmentation
@@ -335,7 +334,7 @@ class IndexingRunner:
                 text_docs,
                 current_user=None,
                 embedding_model_instance=embedding_model_instance,
-                process_rule=processing_rule,
+                process_rule=processing_rule.to_dict(),
                 tenant_id=tenant_id,
                 doc_language=doc_language,
                 preview=True,

api/core/memory/token_buffer_memory.py

@@ -86,10 +86,12 @@ class TokenBufferMemory:
 
         detail = ImagePromptMessageContent.DETAIL.HIGH
         if file_extra_config and app_record:
+            # Build files directly without filtering by belongs_to
             file_objs = [
                 file_factory.build_from_message_file(
                     message_file=message_file,
                     tenant_id=app_record.tenant_id,
+                    config=file_extra_config,
                     access_controller=_file_access_controller,
                 )
                 for message_file in message_files

api/core/ops/entities/trace_entity.py

@@ -5,8 +5,6 @@ from typing import Any, Union
 
 from pydantic import BaseModel, ConfigDict, field_serializer, field_validator
 
-from core.helper.trace_id_helper import ParentTraceContext
-
 
 class BaseTraceInfo(BaseModel):
     message_id: str | None = None
@@ -53,8 +51,8 @@ class BaseTraceInfo(BaseModel):
     def resolved_parent_context(self) -> tuple[str | None, str | None]:
         """Resolve cross-workflow parent linking from metadata.
 
-        Extracts typed parent IDs from the ``parent_trace_context`` metadata
-        payload (set by tool_node when invoking nested workflows).
+        Extracts typed parent IDs from the untyped ``parent_trace_context``
+        metadata dict (set by tool_node when invoking nested workflows).
 
         Returns:
             (trace_correlation_override, parent_span_id_source) where
@@ -62,18 +60,13 @@ class BaseTraceInfo(BaseModel):
             parent_span_id_source is the outer node_execution_id.
         """
         parent_ctx = self.metadata.get("parent_trace_context")
-        if isinstance(parent_ctx, ParentTraceContext):
-            context = parent_ctx
-        elif isinstance(parent_ctx, Mapping):
-            try:
-                context = ParentTraceContext.model_validate(parent_ctx)
-            except ValueError:
-                return None, None
-        else:
+        if not isinstance(parent_ctx, dict):
             return None, None
+        trace_override = parent_ctx.get("parent_workflow_run_id")
+        parent_span = parent_ctx.get("parent_node_execution_id")
         return (
-            context.parent_workflow_run_id,
-            context.parent_node_execution_id,
+            trace_override if isinstance(trace_override, str) else None,
+            parent_span if isinstance(parent_span, str) else None,
         )
 
     @field_serializer("start_time", "end_time")

api/core/ops/exceptions.py

@@ -1,22 +0,0 @@
-"""Core exceptions shared by ops trace dispatchers and trace providers.
-
-Provider packages may raise these types to request generic task behavior, but
-generic Celery tasks should not import provider-specific exception classes.
-"""
-
-
-class RetryableTraceDispatchError(RuntimeError):
-    """Base class for transient trace dispatch failures that Celery may retry."""
-
-
-class PendingTraceParentContextError(RetryableTraceDispatchError):
-    """Raised when a nested trace arrives before its parent span context is available."""
-
-    parent_node_execution_id: str
-
-    def __init__(self, parent_node_execution_id: str) -> None:
-        self.parent_node_execution_id = parent_node_execution_id
-        super().__init__(
-            "Pending trace parent context for parent_node_execution_id="
-            f"{parent_node_execution_id}. Retry after the parent span context is published."
-        )