chore: DocumentSegment to Typebase (#35635)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

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

@@ -63,7 +63,7 @@ pnpm analyze-component <path> --json
 
 ```typescript
 // ❌ Before: Complex state logic in component
-const Configuration: FC = () => {
+function Configuration() {
   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
-const Configuration: FC = () => {
+function Configuration() {
   const { modelConfig, setModelConfig } = useModelConfig(appId)
   return <div>...</div>
 }
@@ -189,8 +189,6 @@ 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.
 
@@ -367,7 +365,7 @@ For each extraction:
   ┌────────────────────────────────────────┐
   │ 1. Extract code                        │
   │ 2. Run: pnpm lint:fix                  │
-  │ 3. Run: pnpm type-check:tsgo           │
+  │ 3. Run: pnpm type-check                │
   │ 4. Run: pnpm test                      │
   │ 5. Test functionality manually         │
   │ 6. PASS? → Next extraction             │

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

@@ -60,8 +60,10 @@ const Template = useMemo(() => {
 **After** (complexity: ~3):
 
 ```typescript
+import type { ComponentType } from 'react'
+
 // Define lookup table outside component
-const TEMPLATE_MAP: Record<AppModeEnum, Record<string, FC<TemplateProps>>> = {
+const TEMPLATE_MAP: Record<AppModeEnum, Record<string, ComponentType<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
 }
 
-const ConfigurationHeader: FC<ConfigurationHeaderProps> = ({
+function ConfigurationHeader({
   isAdvancedMode,
   onPublish,
-}) => {
+}: ConfigurationHeaderProps) {
   const { t } = useTranslation()
   
   return (
@@ -136,7 +136,7 @@ const AppInfo = () => {
 }
 
 // ✅ After: Separate view components
-const AppInfoExpanded: FC<AppInfoViewProps> = ({ appDetail, onAction }) => {
+function AppInfoExpanded({ appDetail, onAction }: AppInfoViewProps) {
   return (
     <div className="expanded">
       {/* Clean, focused expanded view */}
@@ -144,7 +144,7 @@ const AppInfoExpanded: FC<AppInfoViewProps> = ({ appDetail, onAction }) => {
   )
 }
 
-const AppInfoCollapsed: FC<AppInfoViewProps> = ({ appDetail, onAction }) => {
+function AppInfoCollapsed({ appDetail, onAction }: AppInfoViewProps) {
   return (
     <div className="collapsed">
       {/* Clean, focused collapsed view */}
@@ -203,12 +203,12 @@ interface AppInfoModalsProps {
   onSuccess: () => void
 }
 
-const AppInfoModals: FC<AppInfoModalsProps> = ({
+function AppInfoModals({
   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
 }
 
-const OperationItem: FC<OperationItemProps> = ({ operation, onAction }) => {
+function OperationItem({ operation, onAction }: OperationItemProps) {
   return (
     <div className="operation-item">
       <span className="icon">{operation.icon}</span>
@@ -435,7 +435,7 @@ interface ChildProps {
   onSubmit: () => void
 }
 
-const Child: FC<ChildProps> = ({ value, onChange, onSubmit }) => {
+function Child({ value, onChange, onSubmit }: ChildProps) {
   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
-const Configuration: FC = () => {
+function Configuration() {
   const [modelConfig, setModelConfig] = useState<ModelConfig>(...)
   // ... lots of related state and effects
 }
 
 // After: Clean component
-const Configuration: FC = () => {
+function Configuration() {
   const {
     modelConfig,
     setModelConfig,
@@ -159,8 +159,6 @@ const Configuration: FC = () => {
 
 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

@@ -0,0 +1,79 @@
+---
+name: e2e-cucumber-playwright
+description: Write, update, or review Dify end-to-end tests under `e2e/` that use Cucumber, Gherkin, and Playwright. Use when the task involves `.feature` files, `features/step-definitions/`, `features/support/`, `DifyWorld`, scenario tags, locator/assertion choices, or E2E testing best practices for this repository.
+---
+
+# Dify E2E Cucumber + Playwright
+
+Use this skill for Dify's repository-level E2E suite in `e2e/`. Use [`e2e/AGENTS.md`](../../../e2e/AGENTS.md) as the canonical guide for local architecture and conventions, then apply Playwright/Cucumber best practices only where they fit the current suite.
+
+## Scope
+
+- Use this skill for `.feature` files, Cucumber step definitions, `DifyWorld`, hooks, tags, and E2E review work under `e2e/`.
+- Do not use this skill for Vitest or React Testing Library work under `web/`; use `frontend-testing` instead.
+- Do not use this skill for backend test or API review tasks under `api/`.
+
+## Read Order
+
+1. Read [`e2e/AGENTS.md`](../../../e2e/AGENTS.md) first.
+2. Read only the files directly involved in the task:
+   - target `.feature` files under `e2e/features/`
+   - related step files under `e2e/features/step-definitions/`
+   - `e2e/features/support/hooks.ts` and `e2e/features/support/world.ts` when session lifecycle or shared state matters
+   - `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.
+
+## Local Rules
+
+- `e2e/` uses Cucumber for scenarios and Playwright as the browser layer.
+- `DifyWorld` is the per-scenario context object. Type `this` as `DifyWorld` and use `async function`, not arrow functions.
+- Keep glue organized by capability under `e2e/features/step-definitions/`; use `common/` only for broadly reusable steps.
+- Browser session behavior comes from `features/support/hooks.ts`:
+  - default: authenticated session with shared storage state
+  - `@unauthenticated`: clean browser context
+  - `@authenticated`: readability/selective-run tag only unless implementation changes
+  - `@fresh`: only for `e2e:full*` flows
+- Do not import Playwright Test runner patterns that bypass the current Cucumber + `DifyWorld` architecture unless the task is explicitly about changing that architecture.
+
+## Workflow
+
+1. Rebuild local context.
+   - Inspect the target feature area.
+   - Reuse an existing step when wording and behavior already match.
+   - Add a new step only for a genuinely new user action or assertion.
+   - Keep edits close to the current capability folder unless the step is broadly reusable.
+2. Write behavior-first scenarios.
+   - Describe user-observable behavior, not DOM mechanics.
+   - Keep each scenario focused on one workflow or outcome.
+   - Keep scenarios independent and re-runnable.
+3. Write step definitions in the local style.
+   - Keep one step to one user-visible action or one assertion.
+   - Prefer Cucumber Expressions such as `{string}` and `{int}`.
+   - Scope locators to stable containers when the page has repeated elements.
+   - Avoid page-object layers or extra helper abstractions unless repeated complexity clearly justifies them.
+4. Use Playwright in the local style.
+   - Prefer user-facing locators: `getByRole`, `getByLabel`, `getByPlaceholder`, `getByText`, then `getByTestId` for explicit contracts.
+   - Use web-first `expect(...)` assertions.
+   - Do not use `waitForTimeout`, manual polling, or raw visibility checks when a locator action or retrying assertion already expresses the behavior.
+5. Validate narrowly.
+   - Run the narrowest tagged scenario or flow that exercises the change.
+   - Run `pnpm -C e2e check`.
+   - Broaden verification only when the change affects hooks, tags, setup, or shared step semantics.
+
+## Review Checklist
+
+- Does the scenario describe behavior rather than implementation?
+- Does it fit the current session model, tags, and `DifyWorld` usage?
+- Should an existing step be reused instead of adding a new one?
+- Are locators user-facing and assertions web-first?
+- Does the change introduce hidden coupling across scenarios, tags, or instance state?
+- Does it document or implement behavior that differs from the real hooks or configuration?
+
+Lead findings with correctness, flake risk, and architecture drift.
+
+## References
+
+- [`references/playwright-best-practices.md`](references/playwright-best-practices.md)
+- [`references/cucumber-best-practices.md`](references/cucumber-best-practices.md)

.agents/skills/e2e-cucumber-playwright/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "E2E Cucumber + Playwright"
+  short_description: "Write and review Dify E2E scenarios."
+  default_prompt: "Use $e2e-cucumber-playwright to write or review a Dify E2E scenario under e2e/."

.agents/skills/e2e-cucumber-playwright/references/cucumber-best-practices.md

@@ -0,0 +1,93 @@
+# Cucumber Best Practices For Dify E2E
+
+Use this reference when writing or reviewing Gherkin scenarios, step definitions, parameter expressions, and step reuse in Dify's `e2e/` suite.
+
+Official sources:
+
+- https://cucumber.io/docs/guides/10-minute-tutorial/
+- https://cucumber.io/docs/cucumber/step-definitions/
+- https://cucumber.io/docs/cucumber/cucumber-expressions/
+
+## What Matters Most
+
+### 1. Treat scenarios as executable specifications
+
+Cucumber scenarios should describe examples of behavior, not test implementation recipes.
+
+Apply it like this:
+
+- write what the user does and what should happen
+- avoid UI-internal wording such as selector details, DOM structure, or component names
+- keep language concrete enough that the scenario reads like living documentation
+
+### 2. Keep scenarios focused
+
+A scenario should usually prove one workflow or business outcome. If a scenario wanders across several unrelated behaviors, split it.
+
+In Dify's suite, this means:
+
+- one capability-focused scenario per feature path
+- no long setup chains when existing bootstrap or reusable steps already cover them
+- no hidden dependency on another scenario's side effects
+
+### 3. Reuse steps, but only when behavior really matches
+
+Good reuse reduces duplication. Bad reuse hides meaning.
+
+Prefer reuse when:
+
+- the user action is genuinely the same
+- the expected outcome is genuinely the same
+- the wording stays natural across features
+
+Write a new step when:
+
+- the behavior is materially different
+- reusing the old wording would make the scenario misleading
+- a supposedly generic step would become an implementation-detail wrapper
+
+### 4. Prefer Cucumber Expressions
+
+Use Cucumber Expressions for parameters unless regex is clearly necessary.
+
+Common examples:
+
+- `{string}` for labels, names, and visible text
+- `{int}` for counts
+- `{float}` for decimal values
+- `{word}` only when the value is truly a single token
+
+Keep expressions readable. If a step needs complicated parsing logic, first ask whether the scenario wording should be simpler.
+
+### 5. Keep step definitions thin and meaningful
+
+Step definitions are glue between Gherkin and automation, not a second abstraction language.
+
+For Dify:
+
+- type `this` as `DifyWorld`
+- use `async function`
+- keep each step to one user-visible action or assertion
+- rely on `DifyWorld` and existing support code for shared context
+- avoid leaking cross-scenario state
+
+### 6. Use tags intentionally
+
+Tags should communicate run scope or session semantics, not become ad hoc metadata.
+
+In Dify's current suite:
+
+- capability tags group related scenarios
+- `@unauthenticated` changes session behavior
+- `@authenticated` is descriptive/selective, not a behavior switch by itself
+- `@fresh` belongs to reset/full-install flows only
+
+If a proposed tag implies behavior, verify that hooks or runner configuration actually implement it.
+
+## Review Questions
+
+- Does the scenario read like a real example of product behavior?
+- Are the steps behavior-oriented instead of implementation-oriented?
+- Is a reused step still truthful in this feature?
+- Is a new tag documenting real behavior, or inventing semantics that the suite does not implement?
+- Would a new reader understand the outcome without opening the step-definition file?

.agents/skills/e2e-cucumber-playwright/references/playwright-best-practices.md

@@ -0,0 +1,96 @@
+# Playwright Best Practices For Dify E2E
+
+Use this reference when writing or reviewing locator, assertion, isolation, or synchronization logic for Dify's Cucumber-based E2E suite.
+
+Official sources:
+
+- https://playwright.dev/docs/best-practices
+- https://playwright.dev/docs/locators
+- https://playwright.dev/docs/test-assertions
+- https://playwright.dev/docs/browser-contexts
+
+## What Matters Most
+
+### 1. Keep scenarios isolated
+
+Playwright's model is built around clean browser contexts so one test does not leak into another. In Dify's suite, that principle maps to per-scenario session setup in `features/support/hooks.ts` and `DifyWorld`.
+
+Apply it like this:
+
+- do not depend on another scenario having run first
+- do not persist ad hoc scenario state outside `DifyWorld`
+- do not couple ordinary scenarios to `@fresh` behavior
+- when a flow needs special auth/session semantics, express that through the existing tag model or explicit hook changes
+
+### 2. Prefer user-facing locators
+
+Playwright recommends built-in locators that reflect what users perceive on the page.
+
+Preferred order in this repository:
+
+1. `getByRole`
+2. `getByLabel`
+3. `getByPlaceholder`
+4. `getByText`
+5. `getByTestId` when an explicit test contract is the most stable option
+
+Avoid raw CSS/XPath selectors unless no stable user-facing contract exists and adding one is not practical.
+
+Also remember:
+
+- repeated content usually needs scoping to a stable container
+- exact text matching is often too brittle when role/name or label already exists
+- `getByTestId` is acceptable when semantics are weak but the contract is intentional
+
+### 3. Use web-first assertions
+
+Playwright assertions auto-wait and retry. Prefer them over manual state inspection.
+
+Prefer:
+
+- `await expect(page).toHaveURL(...)`
+- `await expect(locator).toBeVisible()`
+- `await expect(locator).toBeHidden()`
+- `await expect(locator).toBeEnabled()`
+- `await expect(locator).toHaveText(...)`
+
+Avoid:
+
+- `expect(await locator.isVisible()).toBe(true)`
+- custom polling loops for DOM state
+- `waitForTimeout` as synchronization
+
+If a condition genuinely needs custom retry logic, use Playwright's polling/assertion tools deliberately and keep that choice local and explicit.
+
+### 4. Let actions wait for actionability
+
+Locator actions already wait for the element to be actionable. Do not preface every click/fill with extra timing logic unless the action needs a specific visible/ready assertion for clarity.
+
+Good pattern:
+
+- assert a meaningful visible state when that is part of the behavior
+- then click/fill/select via locator APIs
+
+Bad pattern:
+
+- stack arbitrary waits before every action
+- wait on unstable implementation details instead of the visible state the user cares about
+
+### 5. Match debugging to the current suite
+
+Playwright's wider ecosystem supports traces and rich debugging tools. Dify's current suite already captures:
+
+- full-page screenshots
+- page HTML
+- console errors
+- page errors
+
+Use the existing artifact flow by default. If a task is specifically about improving diagnostics, confirm the change fits the current Cucumber architecture before importing broader Playwright tooling.
+
+## Review Questions
+
+- Would this locator survive DOM refactors that do not change user-visible behavior?
+- Is this assertion using Playwright's retrying semantics?
+- Is any explicit wait masking a real readiness problem?
+- Does this code preserve per-scenario isolation?
+- Is a new abstraction really needed, or does it bypass the existing `DifyWorld` + step-definition model?

.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 memoization
+## Complex prop stability
 
-IsUrgent: True
+IsUrgent: False
 Category: Performance
 
 ### Description
 
-Wrap complex prop values (objects, arrays, maps) in `useMemo` prior to passing them into child components to guarantee stable references and prevent unnecessary renders.
+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.
 
 Update this file when adding, editing, or removing Performance rules so the catalog remains accurate.
 
-Wrong:
+Risky:
 
 ```tsx
 <HeavyComp
@@ -31,7 +31,7 @@ Wrong:
 />
 ```
 
-Right:
+Better when stable identity matters:
 
 ```tsx
 const config = useMemo(() => ({

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

@@ -1,44 +0,0 @@
----
-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() directly or extract a helper or use-* hook, handling conditional queries, cache 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 invalidation and mutation flow knowledge in the service layer.
-- 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, 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 `web/service/use-{domain}.ts` only for orchestration or shared domain behavior.
-3. Preserve Dify conventions.
-   - Keep contract inputs in `{ params, query?, body? }` shape.
-   - Bind invalidation in the service-layer mutation definition.
-   - 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`
-- `web/service/use-*.ts`
-- 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

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

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

@@ -1,98 +0,0 @@
-# Contract Patterns
-
-## Table of Contents
-
-- Intent
-- Minimal structure
-- Core workflow
-- Query usage decision rule
-- Mutation usage 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 `web/service/use-{domain}.ts` only for orchestration.
-   - Combine multiple queries or mutations.
-   - Share domain-level derived state or invalidation helpers.
-
-```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.
-
-## 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.
-- 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

@@ -1,130 +0,0 @@
-# Runtime Rules
-
-## Table of Contents
-
-- Conditional queries
-- 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,
-  }))
-}
-```
-
-## Cache Invalidation
-
-Bind invalidation in the service-layer mutation definition.
-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
-// Service layer owns cache invalidation.
-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 layer | `queryClient.invalidateQueries(...)` inside mutation `onSuccess` |
-| component-triggered invalidation after mutation | move invalidation into the service-layer mutation definition |
-| 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 Claude to generate high-quality, comprehensive frontend tests for the Dify project following established conventions and best practices.
+This skill enables Codex 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.*`).
 
@@ -24,35 +24,27 @@ 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 (Playwright/Cypress)
+- User is asking about E2E tests (Cucumber + Playwright under `e2e/`)
 - User is only asking conceptual questions without code context
 
 ## Quick Reference
 
-### Tech Stack
-
-| 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
 
+Run these commands from `web/`. From the repository root, prefix them with `pnpm -C web`.
+
 ```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>
@@ -200,7 +192,7 @@ When assigned to test a directory/path, test **ALL content** within that path:
 
 - ✅ **Import real project components** directly (including base components and siblings)
 - ✅ **Only mock**: API services (`@/service/*`), `next/navigation`, complex context providers
-- ❌ **DO NOT mock** base components (`@/app/components/base/*`)
+- ❌ **DO NOT mock** base components (`@/app/components/base/*`) or dify-ui primitives (`@langgenius/dify-ui/*`)
 - ❌ **DO NOT mock** sibling/child components in the same directory
 
 > See [Test Structure Template](#test-structure-template) for correct import/mock patterns.
@@ -228,7 +220,10 @@ Every test should clearly separate:
 ### 2. Black-Box Testing
 
 - Test observable behavior, not implementation details
-- Use semantic queries (getByRole, getByLabelText)
+- 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`.
 - Avoid testing internal state directly
 - **Prefer pattern matching over hardcoded strings** in assertions:
 
@@ -325,12 +320,12 @@ For more detailed information, refer to:
 ### Reference Examples in Codebase
 
 - `web/utils/classnames.spec.ts` - Utility function tests
-- `web/app/components/base/button/index.spec.tsx` - Component tests
+- `web/app/components/base/radio/__tests__/index.spec.tsx` - Component tests
 - `web/__mocks__/provider-context.ts` - Mock factory example
 
 ### Project Configuration
 
-- `web/vitest.config.ts` - Vitest configuration
+- `web/vite.config.ts` - Vite/Vitest configuration
 - `web/vitest.setup.ts` - Test environment setup
 - `web/scripts/analyze-component.js` - Component analysis tool
 - Modules are not mocked automatically. Global mocks live in `web/vitest.setup.ts` (for example `react-i18next`, `next/image`); mock other modules like `ky` or `mime` locally in test files.

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

@@ -36,7 +36,7 @@ Use this checklist when generating or reviewing tests for Dify frontend componen
 
 ### Integration vs Mocking
 
-- [ ] **DO NOT mock base components** (`Loading`, `Button`, `Tooltip`, etc.)
+- [ ] **DO NOT mock base components or dify-ui primitives** (base `Loading`, `Input`, `Badge`; dify-ui `Button`, `Tooltip`, `Dialog`, etc.)
 - [ ] Import real project components instead of mocking
 - [ ] Only mock: API calls, complex context providers, third-party libs with side effects
 - [ ] Prefer integration testing when using single spec file
@@ -73,7 +73,7 @@ Use this checklist when generating or reviewing tests for Dify frontend componen
 
 ### Mocks
 
-- [ ] **DO NOT mock base components** (`@/app/components/base/*`)
+- [ ] **DO NOT mock base components or dify-ui primitives** (`@/app/components/base/*` or `@langgenius/dify-ui/*`)
 - [ ] `vi.clearAllMocks()` in `beforeEach` (not `afterEach`)
 - [ ] Shared mock state reset in `beforeEach`
 - [ ] i18n uses global mock (auto-loaded in `web/vitest.setup.ts`); only override locally for custom translations
@@ -127,7 +127,7 @@ For the current file being tested:
 - [ ] Run full directory test: `pnpm test path/to/directory/`
 - [ ] Check coverage report: `pnpm test:coverage`
 - [ ] Run `pnpm lint:fix` on all test files
-- [ ] Run `pnpm type-check:tsgo`
+- [ ] Run `pnpm type-check`
 
 ## Common Issues to Watch
 

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

@@ -2,29 +2,27 @@
 
 ## ⚠️ Important: What NOT to Mock
 
-### DO NOT Mock Base Components
+### DO NOT Mock Base Components or dify-ui Primitives
 
-**Never mock components from `@/app/components/base/`** such as:
+**Never mock components from `@/app/components/base/` or from `@langgenius/dify-ui/*`** such as:
 
-- `Loading`, `Spinner`
-- `Button`, `Input`, `Select`
-- `Tooltip`, `Modal`, `Dropdown`
-- `Icon`, `Badge`, `Tag`
+- Legacy base (`@/app/components/base/*`): `Loading`, `Spinner`, `Input`, `Badge`, `Tag`
+- dify-ui primitives (`@langgenius/dify-ui/*`): `Button`, `Tooltip`, `Dialog`, `Popover`, `DropdownMenu`, `ContextMenu`, `Select`, `AlertDialog`, `Toast`
 
 **Why?**
 
-- Base components will have their own dedicated tests
+- These components have their own dedicated tests
 - Mocking them creates false positives (tests pass but real integration fails)
 - Using real components tests actual integration behavior
 
 ```typescript
-// ❌ WRONG: Don't mock base components
+// ❌ WRONG: Don't mock base components or dify-ui primitives
 vi.mock('@/app/components/base/loading', () => () => <div>Loading</div>)
-vi.mock('@/app/components/base/button', () => ({ children }: any) => <button>{children}</button>)
+vi.mock('@langgenius/dify-ui/button', () => ({ Button: ({ children }: any) => <button>{children}</button> }))
 
-// ✅ CORRECT: Import and use real base components
+// ✅ CORRECT: Import and use the real components
 import Loading from '@/app/components/base/loading'
-import Button from '@/app/components/base/button'
+import { Button } from '@langgenius/dify-ui/button'
 // They will render normally in tests
 ```
 
@@ -58,7 +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`, `next/image`, `zustand`) |
+| `web/vitest.setup.ts` | Global mocks shared by all tests (`react-i18next`, `zustand`, clipboard, FloatingPortal, Monaco, localStorage`) |
 | `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()` |
@@ -218,28 +216,21 @@ describe('Component', () => {
 })
 ```
 
-### 5. HTTP Mocking with Nock
+### 5. HTTP and `fetch` Mocking
 
 ```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', () => {
-  afterEach(() => {
-    nock.cleanAll()
+  beforeEach(() => {
+    vi.clearAllMocks()
   })
 
   it('should display repo info', async () => {
-    mockGithubApi(200, { name: 'dify', stars: 1000 })
+    vi.mocked(globalThis.fetch).mockResolvedValueOnce(
+      new Response(JSON.stringify({ name: 'dify', stars: 1000 }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    )
     
     render(<GithubComponent />)
     
@@ -249,7 +240,12 @@ describe('GithubComponent', () => {
   })
 
   it('should handle API error', async () => {
-    mockGithubApi(500, { message: 'Server error' })
+    vi.mocked(globalThis.fetch).mockResolvedValueOnce(
+      new Response(JSON.stringify({ message: 'Server error' }), {
+        status: 500,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    )
     
     render(<GithubComponent />)
     
@@ -260,6 +256,8 @@ 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
@@ -319,7 +317,7 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
 
 ### ✅ DO
 
-1. **Use real base components** - Import from `@/app/components/base/` directly
+1. **Use real base components and dify-ui primitives** - Import from `@/app/components/base/` or `@langgenius/dify-ui/*` directly
 1. **Use real project components** - Prefer importing over mocking
 1. **Use real Zustand stores** - Set test state via `store.setState()`
 1. **Reset mocks in `beforeEach`**, not `afterEach`
@@ -330,11 +328,11 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
 
 ### ❌ DON'T
 
-1. **Don't mock base components** (`Loading`, `Button`, `Tooltip`, etc.)
+1. **Don't mock base components or dify-ui primitives** (`Loading`, `Input`, `Button`, `Tooltip`, `Dialog`, etc.)
 1. **Don't mock Zustand store modules** - Use real stores with `setState()`
 1. Don't mock components you can import directly
 1. Don't create overly simplified mocks that miss conditional logic
-1. Don't forget to clean up nock after each test
+1. Don't leave HTTP mocks or service mock state leaking between tests
 1. Don't use `any` types in mocks without necessity
 
 ### Mock Decision Tree
@@ -342,7 +340,7 @@ const renderWithQueryClient = (ui: React.ReactElement) => {
 ```
 Need to use a component in test?
 │
-├─ Is it from @/app/components/base/*?
+├─ Is it from @/app/components/base/* or @langgenius/dify-ui/*?
 │  └─ YES → Import real component, DO NOT mock
 │
 ├─ Is it a project component?

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

@@ -227,12 +227,12 @@ Failing tests compound:
 
 **Fix failures immediately before proceeding.**
 
-## Integration with Claude's Todo Feature
+## Integration with Codex's Todo Feature
 
-When using Claude for multi-file testing:
+When using Codex for multi-file testing:
 
-1. **Ask Claude to create a todo list** before starting
-1. **Request one file at a time** or ensure Claude processes incrementally
+1. **Create a todo list** before starting
+1. **Process one file at a time**
 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

@@ -0,0 +1,71 @@
+---
+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

@@ -0,0 +1,367 @@
+---
+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]`)

.claude/skills/e2e-cucumber-playwright

@@ -0,0 +1 @@
+../../.agents/skills/e2e-cucumber-playwright

.devcontainer/post_create_command.sh

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

.github/CODEOWNERS

@@ -6,6 +6,9 @@
 
 * @crazywoola @laipz8200 @Yeuoly
 
+# ESLint suppression file is maintained by autofix.ci pruning.
+/eslint-suppressions.json
+
 # CODEOWNERS file
 /.github/CODEOWNERS @laipz8200 @crazywoola
 

.github/actions/setup-web/action.yml

@@ -4,7 +4,7 @@ runs:
   using: composite
   steps:
     - name: Setup Vite+
-      uses: voidzero-dev/setup-vp@20553a7a7429c429a74894104a2835d7fed28a72 # v1.3.0
+      uses: voidzero-dev/setup-vp@4f5aa3e38c781f1b01e78fb9255527cee8a6efa6 # v1.8.0
       with:
         node-version-file: .nvmrc
         cache: true

.github/labeler.yml

@@ -6,5 +6,4 @@ web:
           - 'package.json'
           - 'pnpm-lock.yaml'
           - 'pnpm-workspace.yaml'
-          - '.npmrc'
           - '.nvmrc'

.github/workflows/anti-slop.yml

@@ -1,19 +0,0 @@
-name: Anti-Slop PR Check
-
-on:
-  pull_request_target:
-    types: [opened, edited, synchronize]
-
-permissions:
-  pull-requests: write
-  contents: read
-
-jobs:
-  anti-slop:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: peakoss/anti-slop@85daca1880e9e1af197fc06ea03349daf08f4202 # v0.2.1
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          close-pr: false
-          failure-add-pr-labels: "needs-revision"

.github/workflows/api-tests.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   api-unit:
     name: API Unit Tests
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     env:
       COVERAGE_FILE: coverage-unit
     defaults:
@@ -35,7 +35,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -62,7 +62,7 @@ jobs:
 
   api-integration:
     name: API Integration Tests
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     env:
       COVERAGE_FILE: coverage-integration
       STORAGE_TYPE: opendal
@@ -84,7 +84,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -99,13 +99,13 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
+          cp docker/envs/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
       - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -137,7 +137,7 @@ jobs:
 
   api-coverage:
     name: API Coverage
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     needs:
       - api-unit
       - api-integration
@@ -156,7 +156,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"

.github/workflows/autofix.yml

@@ -13,7 +13,7 @@ permissions:
 jobs:
   autofix:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Complete merge group check
         if: github.event_name == 'merge_group'
@@ -25,7 +25,7 @@ jobs:
       - name: Check Docker Compose inputs
         if: github.event_name != 'merge_group'
         id: docker-compose-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             docker/generate_docker_compose
@@ -35,7 +35,7 @@ jobs:
       - name: Check web inputs
         if: github.event_name != 'merge_group'
         id: web-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             web/**
@@ -43,12 +43,11 @@ jobs:
             package.json
             pnpm-lock.yaml
             pnpm-workspace.yaml
-            .npmrc
             .nvmrc
       - name: Check api inputs
         if: github.event_name != 'merge_group'
         id: api-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             api/**
@@ -58,7 +57,7 @@ jobs:
           python-version: "3.11"
 
       - if: github.event_name != 'merge_group'
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
 
       - name: Generate Docker Compose
         if: github.event_name != 'merge_group' && steps.docker-compose-changes.outputs.any_changed == 'true'
@@ -114,14 +113,19 @@ jobs:
           find . -name "*.py.bak" -type f -delete
 
       - name: Setup web environment
-        if: github.event_name != 'merge_group' && steps.web-changes.outputs.any_changed == 'true'
+        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: |
-          cd web
           vp exec eslint --concurrency=2 --prune-suppressions --quiet || true
 
       - if: github.event_name != 'merge_group'
-        uses: autofix-ci/action@7a166d7532b277f34e16238930461bf77f9d7ed8 # v1.3.3
+        uses: autofix-ci/action@c5b2d67aa2274e7b5a18224e8171550871fc7e4a # v1.3.4

.github/workflows/build-push.yml

@@ -26,6 +26,9 @@ jobs:
   build:
     runs-on: ${{ matrix.runs_on }}
     if: github.repository == 'langgenius/dify'
+    permissions:
+      contents: read
+      id-token: write
     strategy:
       matrix:
         include:
@@ -35,28 +38,28 @@ jobs:
             build_context: "{{defaultContext}}:api"
             file: "Dockerfile"
             platform: linux/amd64
-            runs_on: ubuntu-latest
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-api-arm64"
             image_name_env: "DIFY_API_IMAGE_NAME"
             artifact_context: "api"
             build_context: "{{defaultContext}}:api"
             file: "Dockerfile"
             platform: linux/arm64
-            runs_on: ubuntu-24.04-arm
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-web-amd64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
             artifact_context: "web"
             build_context: "{{defaultContext}}"
             file: "web/Dockerfile"
             platform: linux/amd64
-            runs_on: ubuntu-latest
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-web-arm64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
             artifact_context: "web"
             build_context: "{{defaultContext}}"
             file: "web/Dockerfile"
             platform: linux/arm64
-            runs_on: ubuntu-24.04-arm
+            runs_on: depot-ubuntu-24.04-4
 
     steps:
       - name: Prepare
@@ -70,8 +73,8 @@ jobs:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
+      - name: Set up Depot CLI
+        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
 
       - name: Extract metadata for Docker
         id: meta
@@ -81,16 +84,15 @@ jobs:
 
       - name: Build Docker image
         id: build
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
         with:
+          project: ${{ vars.DEPOT_PROJECT_ID }}
           context: ${{ matrix.build_context }}
           file: ${{ matrix.file }}
           platforms: ${{ matrix.platform }}
           build-args: COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
           labels: ${{ steps.meta.outputs.labels }}
           outputs: type=image,name=${{ env[matrix.image_name_env] }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: type=gha,scope=${{ matrix.service_name }}
-          cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}
 
       - name: Export digest
         env:
@@ -108,9 +110,33 @@ jobs:
           if-no-files-found: error
           retention-days: 1
 
+  fork-build-validate:
+    if: github.repository != 'langgenius/dify'
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        include:
+          - service_name: "validate-api-amd64"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
+          - service_name: "validate-web-amd64"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
+
+      - name: Validate Docker image
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        with:
+          push: false
+          context: ${{ matrix.build_context }}
+          file: ${{ matrix.file }}
+          platforms: linux/amd64
+
   create-manifest:
     needs: build
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: github.repository == 'langgenius/dify'
     strategy:
       matrix:

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

@@ -9,7 +9,7 @@ concurrency:
 
 jobs:
   db-migration-test-postgres:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -19,7 +19,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -37,10 +37,10 @@ jobs:
       - name: Prepare middleware env
         run: |
           cd docker
-          cp middleware.env.example middleware.env
+          cp envs/middleware.env.example middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -59,7 +59,7 @@ jobs:
         run: uv run --directory api flask upgrade-db
 
   db-migration-test-mysql:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -69,7 +69,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -87,14 +87,14 @@ jobs:
       - name: Prepare middleware env for MySQL
         run: |
           cd docker
-          cp middleware.env.example middleware.env
+          cp envs/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
           sed -i 's/DB_USERNAME=postgres/DB_USERNAME=mysql/' middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -110,6 +110,28 @@ jobs:
           sed -i 's/DB_PORT=5432/DB_PORT=3306/' .env
           sed -i 's/DB_USERNAME=postgres/DB_USERNAME=root/' .env
 
+      # hoverkraft-tech/compose-action@v2.6.0 only waits for `docker compose up -d`
+      # to return (container processes started); it does not wait on healthcheck
+      # status. mysql:8.0's first-time init takes 15-30s, so without an explicit
+      # wait the migration runs while InnoDB is still initialising and gets
+      # killed with "Lost connection during query". Poll a real SELECT until it
+      # succeeds.
+      - name: Wait for MySQL to accept queries
+        run: |
+          set +e
+          for i in $(seq 1 60); do
+            if docker run --rm --network host mysql:8.0 \
+                mysql -h 127.0.0.1 -P 3306 -uroot -pdifyai123456 \
+                -e 'SELECT 1' >/dev/null 2>&1; then
+              echo "MySQL ready after ${i}s"
+              exit 0
+            fi
+            sleep 1
+          done
+          echo "MySQL not ready after 60s; dumping container logs:"
+          docker compose -f docker/docker-compose.middleware.yaml --profile mysql logs --tail=200 db_mysql
+          exit 1
+
       - name: Run DB Migration
         env:
           DEBUG: true

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

@@ -13,7 +13,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: |
       github.event.workflow_run.conclusion == 'success' &&
       github.event.workflow_run.head_branch == 'deploy/agent-dev'

.github/workflows/deploy-dev.yml

@@ -10,7 +10,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: |
       github.event.workflow_run.conclusion == 'success' &&
       github.event.workflow_run.head_branch == 'deploy/dev'

.github/workflows/deploy-enterprise.yml

@@ -13,7 +13,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: |
       github.event.workflow_run.conclusion == 'success' &&
       github.event.workflow_run.head_branch == 'deploy/enterprise'

.github/workflows/deploy-hitl.yml

@@ -10,7 +10,7 @@ on:
 
 jobs:
   deploy:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: |
       github.event.workflow_run.conclusion == 'success' &&
       github.event.workflow_run.head_branch == 'build/feat/hitl'

.github/workflows/docker-build.yml

@@ -6,14 +6,7 @@ on:
       - "main"
     paths:
       - api/Dockerfile
-      - web/docker/**
       - web/Dockerfile
-      - packages/**
-      - package.json
-      - pnpm-lock.yaml
-      - pnpm-workspace.yaml
-      - .npmrc
-      - .nvmrc
 
 concurrency:
   group: docker-build-${{ github.head_ref || github.run_id }}
@@ -21,28 +14,59 @@ concurrency:
 
 jobs:
   build-docker:
+    if: github.event.pull_request.head.repo.full_name == github.repository
     runs-on: ${{ matrix.runs_on }}
+    permissions:
+      contents: read
+      id-token: write
     strategy:
       matrix:
         include:
           - service_name: "api-amd64"
             platform: linux/amd64
-            runs_on: ubuntu-latest
+            runs_on: depot-ubuntu-24.04-4
             context: "{{defaultContext}}:api"
             file: "Dockerfile"
           - service_name: "api-arm64"
             platform: linux/arm64
-            runs_on: ubuntu-24.04-arm
+            runs_on: depot-ubuntu-24.04-4
             context: "{{defaultContext}}:api"
             file: "Dockerfile"
           - service_name: "web-amd64"
             platform: linux/amd64
-            runs_on: ubuntu-latest
+            runs_on: depot-ubuntu-24.04-4
             context: "{{defaultContext}}"
             file: "web/Dockerfile"
           - service_name: "web-arm64"
             platform: linux/arm64
-            runs_on: ubuntu-24.04-arm
+            runs_on: depot-ubuntu-24.04-4
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
+    steps:
+      - name: Set up Depot CLI
+        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
+
+      - name: Build Docker Image
+        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
+        with:
+          project: ${{ vars.DEPOT_PROJECT_ID }}
+          push: false
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
+          platforms: ${{ matrix.platform }}
+
+  build-docker-fork:
+    if: github.event.pull_request.head.repo.full_name != github.repository
+    runs-on: ubuntu-24.04
+    permissions:
+      contents: read
+    strategy:
+      matrix:
+        include:
+          - service_name: "api-amd64"
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
+          - service_name: "web-amd64"
             context: "{{defaultContext}}"
             file: "web/Dockerfile"
     steps:
@@ -55,6 +79,4 @@ jobs:
           push: false
           context: ${{ matrix.context }}
           file: ${{ matrix.file }}
-          platforms: ${{ matrix.platform }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          platforms: linux/amd64

.github/workflows/labeler.yml

@@ -7,8 +7,8 @@ jobs:
     permissions:
       contents: read
       pull-requests: write
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
-      - uses: actions/labeler@634933edcd8ababfe52f92936142cc22ac488b1b # v6.0.1
+      - uses: actions/labeler@f27b608878404679385c85cfa523b85ccb86e213 # v6.1.0
         with:
           sync-labels: true

.github/workflows/main-ci.yml

@@ -23,7 +23,7 @@ concurrency:
 jobs:
   pre_job:
     name: Skip Duplicate Checks
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     outputs:
       should_skip: ${{ steps.skip_check.outputs.should_skip || 'false' }}
     steps:
@@ -39,7 +39,7 @@ jobs:
     name: Check Changed Files
     needs: pre_job
     if: needs.pre_job.outputs.should_skip != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     outputs:
       api-changed: ${{ steps.changes.outputs.api }}
       e2e-changed: ${{ steps.changes.outputs.e2e }}
@@ -57,7 +57,7 @@ jobs:
               - '.github/workflows/api-tests.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/middleware.env.example'
+              - 'docker/envs/middleware.env.example'
               - 'docker/docker-compose.middleware.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'
@@ -69,7 +69,6 @@ jobs:
               - 'package.json'
               - 'pnpm-lock.yaml'
               - 'pnpm-workspace.yaml'
-              - '.npmrc'
               - '.nvmrc'
               - '.github/workflows/web-tests.yml'
               - '.github/actions/setup-web/**'
@@ -83,19 +82,19 @@ jobs:
               - 'package.json'
               - 'pnpm-lock.yaml'
               - 'pnpm-workspace.yaml'
-              - '.npmrc'
               - '.nvmrc'
               - 'docker/docker-compose.middleware.yaml'
-              - 'docker/middleware.env.example'
+              - 'docker/envs/middleware.env.example'
               - '.github/workflows/web-e2e.yml'
               - '.github/actions/setup-web/**'
             vdb:
               - 'api/core/rag/datasource/**'
               - 'api/tests/integration_tests/vdb/**'
+              - 'api/providers/vdb/*/tests/**'
               - '.github/workflows/vdb-tests.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/middleware.env.example'
+              - 'docker/envs/middleware.env.example'
               - 'docker/docker-compose.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'
@@ -117,7 +116,7 @@ jobs:
               - '.github/workflows/db-migration-test.yml'
               - '.github/workflows/expose_service_ports.sh'
               - 'docker/.env.example'
-              - 'docker/middleware.env.example'
+              - 'docker/envs/middleware.env.example'
               - 'docker/docker-compose.middleware.yaml'
               - 'docker/docker-compose-template.yaml'
               - 'docker/generate_docker_compose'
@@ -140,7 +139,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.api-changed != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Report skipped API tests
         run: echo "No API-related changes detected; skipping API tests."
@@ -153,7 +152,7 @@ jobs:
       - check-changes
       - api-tests-run
       - api-tests-skip
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Finalize API Tests status
         env:
@@ -200,7 +199,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.web-changed != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Report skipped web tests
         run: echo "No web-related changes detected; skipping web tests."
@@ -213,7 +212,7 @@ jobs:
       - check-changes
       - web-tests-run
       - web-tests-skip
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Finalize Web Tests status
         env:
@@ -259,7 +258,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Report skipped web full-stack e2e
         run: echo "No E2E-related changes detected; skipping web full-stack E2E."
@@ -272,7 +271,7 @@ jobs:
       - check-changes
       - web-e2e-run
       - web-e2e-skip
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Finalize Web Full-Stack E2E status
         env:
@@ -324,7 +323,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.vdb-changed != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Report skipped VDB tests
         run: echo "No VDB-related changes detected; skipping VDB tests."
@@ -337,7 +336,7 @@ jobs:
       - check-changes
       - vdb-tests-run
       - vdb-tests-skip
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Finalize VDB Tests status
         env:
@@ -383,7 +382,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.migration-changed != 'true'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Report skipped DB migration tests
         run: echo "No migration-related changes detected; skipping DB migration tests."
@@ -396,7 +395,7 @@ jobs:
       - check-changes
       - db-migration-test-run
       - db-migration-test-skip
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Finalize DB Migration Test status
         env:

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

@@ -12,7 +12,7 @@ permissions: {}
 jobs:
   comment:
     name: Comment PR with pyrefly diff
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       actions: read
       contents: read
@@ -76,13 +76,29 @@ jobs:
               diff += '\\n\\n... (truncated) ...';
             }
 
-            const body = diff.trim()
-              ? '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>'
-              : '### Pyrefly Diff\nNo changes detected.';
+            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({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+              });
+              const existing = comments.find((comment) => comment.body.startsWith(marker));
 
-            await github.rest.issues.createComment({
-              issue_number: prNumber,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body,
-            });
+              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

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   pyrefly-diff:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       contents: read
       issues: write
@@ -22,7 +22,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup Python & UV
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
 
@@ -103,9 +103,26 @@ jobs:
                 ].join('\n')
               : '### Pyrefly Diff\nNo changes detected.';
 
-            await github.rest.issues.createComment({
+            const marker = '### Pyrefly Diff';
+            const { data: comments } = await github.rest.issues.listComments({
               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/pyrefly-type-coverage-comment.yml

@@ -12,7 +12,7 @@ permissions: {}
 jobs:
   comment:
     name: Comment PR with type coverage
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       actions: read
       contents: read
@@ -24,7 +24,7 @@ jobs:
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Setup Python & UV
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
 
@@ -62,7 +62,7 @@ jobs:
       - name: Render coverage markdown from structured data
         id: render
         run: |
-          comment_body="$(uv run --directory api python api/libs/pyrefly_type_coverage.py \
+          comment_body="$(uv run --directory api python libs/pyrefly_type_coverage.py \
             --base base_report.json \
             < pr_report.json)"
 

.github/workflows/pyrefly-type-coverage.yml

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   pyrefly-type-coverage:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       contents: read
       issues: write
@@ -22,7 +22,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup Python & UV
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
 

.github/workflows/semantic-pull-request.yml

@@ -16,7 +16,7 @@ jobs:
     name: Validate PR title
     permissions:
       pull-requests: read
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
       - name: Complete merge group check
         if: github.event_name == 'merge_group'

.github/workflows/stale.yml

@@ -12,7 +12,7 @@ on:
 jobs:
   stale:
 
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       issues: write
       pull-requests: write

.github/workflows/style.yml

@@ -15,7 +15,7 @@ permissions:
 jobs:
   python-style:
     name: Python Style
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -25,7 +25,7 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             api/**
@@ -33,7 +33,7 @@ jobs:
 
       - name: Setup UV and Python
         if: steps.changed-files.outputs.any_changed == 'true'
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: false
           python-version: "3.12"
@@ -57,7 +57,7 @@ jobs:
 
   web-style:
     name: Web Style
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     defaults:
       run:
         working-directory: ./web
@@ -73,15 +73,16 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             web/**
+            e2e/**
+            sdks/nodejs-client/**
             packages/**
             package.json
             pnpm-lock.yaml
             pnpm-workspace.yaml
-            .npmrc
             .nvmrc
             .github/workflows/style.yml
             .github/actions/setup-web/**
@@ -93,26 +94,28 @@ jobs:
       - name: Restore ESLint cache
         if: steps.changed-files.outputs.any_changed == 'true'
         id: eslint-cache-restore
-        uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          path: web/.eslintcache
-          key: ${{ runner.os }}-web-eslint-${{ hashFiles('web/package.json', 'pnpm-lock.yaml', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-${{ github.sha }}
+          path: .eslintcache
+          key: ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-${{ github.sha }}
           restore-keys: |
-            ${{ runner.os }}-web-eslint-${{ hashFiles('web/package.json', 'pnpm-lock.yaml', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-
+            ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
+        working-directory: .
         run: vp run lint:ci
 
       - name: Web tsslint
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
+        env:
+          NODE_OPTIONS: --max-old-space-size=4096
         run: vp run lint:tss
 
       - name: Web type check
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
+        working-directory: .
         run: vp run type-check
 
       - name: Web dead code check
@@ -122,14 +125,14 @@ jobs:
 
       - name: Save ESLint cache
         if: steps.changed-files.outputs.any_changed == 'true' && success() && steps.eslint-cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          path: web/.eslintcache
+          path: .eslintcache
           key: ${{ steps.eslint-cache-restore.outputs.cache-primary-key }}
 
   superlinter:
     name: SuperLinter
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -140,7 +143,7 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             **.sh

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

@@ -9,7 +9,6 @@ on:
       - package.json
       - pnpm-lock.yaml
       - pnpm-workspace.yaml
-      - .npmrc
 
 concurrency:
   group: sdk-tests-${{ github.head_ref || github.run_id }}
@@ -18,7 +17,7 @@ concurrency:
 jobs:
   build:
     name: unit test for Node.js SDK
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     defaults:
       run:
@@ -30,7 +29,7 @@ jobs:
           persist-credentials: false
 
       - name: Use Node.js
-        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: 22
           cache: ''

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

@@ -35,7 +35,7 @@ concurrency:
 jobs:
   translate:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     timeout-minutes: 120
 
     steps:
@@ -158,7 +158,7 @@ jobs:
 
       - name: Run Claude Code for Translation Sync
         if: steps.context.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@b47fd721da662d48c5680e154ad16a73ed74d2e0 # v1.0.93
+        uses: anthropics/claude-code-action@476e359e6203e73dad705c8b322e333fabbd7416 # v1.0.119
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}

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

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   trigger:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     timeout-minutes: 5
 
     steps:

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

@@ -16,7 +16,7 @@ jobs:
   test:
     name: Full VDB Tests
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     strategy:
       matrix:
         python-version:
@@ -36,7 +36,7 @@ jobs:
           remove_tool_cache: true
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -51,7 +51,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
+          cp docker/envs/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
@@ -65,7 +65,7 @@ jobs:
 #            tiflash
 
       - name: Set up Full Vector Store Matrix
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.yaml
@@ -89,7 +89,7 @@ jobs:
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
 #      - name: Check VDB Ready (TiDB)
-#        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
 
       - name: Test Vector Stores
         run: uv run --project api bash dev/pytest/pytest_vdb.sh

.github/workflows/vdb-tests.yml

@@ -13,7 +13,7 @@ concurrency:
 jobs:
   test:
     name: VDB Smoke Tests
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     strategy:
       matrix:
         python-version:
@@ -33,7 +33,7 @@ jobs:
           remove_tool_cache: true
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -48,7 +48,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
+          cp docker/envs/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
@@ -62,7 +62,7 @@ jobs:
 #            tiflash
 
       - name: Set up Vector Stores for Smoke Coverage
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.yaml
@@ -81,12 +81,12 @@ jobs:
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
 #      - name: Check VDB Ready (TiDB)
-#        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
 
       - name: Test Vector Stores
         run: |
           uv run --project api pytest --timeout "${PYTEST_TIMEOUT:-180}" \
-            api/tests/integration_tests/vdb/chroma \
-            api/tests/integration_tests/vdb/pgvector \
-            api/tests/integration_tests/vdb/qdrant \
-            api/tests/integration_tests/vdb/weaviate
+            api/providers/vdb/vdb-chroma/tests/integration_tests \
+            api/providers/vdb/vdb-pgvector/tests/integration_tests \
+            api/providers/vdb/vdb-qdrant/tests/integration_tests \
+            api/providers/vdb/vdb-weaviate/tests/integration_tests

.github/workflows/web-e2e.yml

@@ -13,7 +13,7 @@ concurrency:
 jobs:
   test:
     name: Web Full-Stack E2E
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04-4
     defaults:
       run:
         shell: bash
@@ -28,7 +28,7 @@ jobs:
         uses: ./.github/actions/setup-web
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@cec208311dfd045dd5311c1add060b2062131d57 # v8.0.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"

.github/workflows/web-tests.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   test:
     name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04-4
     env:
       VITEST_COVERAGE_SCOPE: app-components
     strategy:
@@ -54,7 +54,7 @@ jobs:
     name: Merge Test Reports
     if: ${{ !cancelled() }}
     needs: [test]
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04-4
     env:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:
@@ -89,3 +89,37 @@ jobs:
           flags: web
         env:
           CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}
+
+  dify-ui-test:
+    name: dify-ui Tests
+    runs-on: depot-ubuntu-24.04-4
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+    defaults:
+      run:
+        shell: bash
+        working-directory: ./packages/dify-ui
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Setup web environment
+        uses: ./.github/actions/setup-web
+
+      - name: Install Chromium for Browser Mode
+        run: vp exec playwright install --with-deps chromium
+
+      - name: Run dify-ui tests
+        run: vp test run --coverage --silent=passed-only
+
+      - name: Report coverage
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
+        with:
+          directory: packages/dify-ui/coverage
+          flags: dify-ui
+        env:
+          CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}

.gitignore

@@ -203,6 +203,7 @@ sdks/python-client/dify_client.egg-info
 
 .vscode/*
 !.vscode/launch.json.template
+!.vscode/settings.example.json
 !.vscode/README.md
 api/.vscode
 # vscode Code History Extension
@@ -218,6 +219,9 @@ node_modules
 # plugin migrate
 plugins.jsonl
 
+# generated API OpenAPI specs
+packages/contracts/openapi/
+
 # mise
 mise.toml
 
@@ -236,9 +240,15 @@ scripts/stress-test/reports/
 .playwright-mcp/
 .serena/
 
+# vitest browser mode attachments (failure screenshots, traces, etc.)
+.vitest-attachments/
+**/__screenshots__/
+
 # settings
 *.local.json
 *.local.md
 
 # Code Agent Folder
 .qoder/*
+
+.eslintcache

.npmrc

@@ -1 +0,0 @@
-save-exact=true

.vite-hooks/pre-commit

@@ -56,44 +56,9 @@ if $api_modified; then
     fi
 fi
 
-if $web_modified; then
-    if $skip_web_checks; then
-        echo "Git operation in progress, skipping web checks"
-        exit 0
-    fi
-
-    echo "Running ESLint on web module"
-
-    if git diff --cached --quiet -- 'web/**/*.ts' 'web/**/*.tsx'; then
-        web_ts_modified=false
-    else
-        ts_diff_status=$?
-        if [ $ts_diff_status -eq 1 ]; then
-            web_ts_modified=true
-        else
-            echo "Unable to determine staged TypeScript changes (git exit code: $ts_diff_status)."
-            exit $ts_diff_status
-        fi
-    fi
-
-    cd ./web || exit 1
-    vp staged
-
-    if $web_ts_modified; then
-        echo "Running TypeScript type-check:tsgo"
-        if ! npm run type-check:tsgo; then
-            echo "Type check failed. Please run 'npm run type-check:tsgo' to fix the errors."
-            exit 1
-        fi
-    else
-        echo "No staged TypeScript changes detected, skipping type-check:tsgo"
-    fi
-
-    echo "Running knip"
-    if ! npm run knip; then
-        echo "Knip check failed. Please run 'npm run knip' to fix the errors."
-        exit 1
-    fi
-
-    cd ../
+if $skip_web_checks; then
+    echo "Git operation in progress, skipping web checks"
+    exit 0
 fi
+
+vp staged

.vscode/launch.json.template

@@ -2,21 +2,10 @@
     "version": "0.2.0",
     "configurations": [
         {
-            "name": "Python: Flask API",
+            "name": "Python: API (gevent)",
             "type": "debugpy",
             "request": "launch",
-            "module": "flask",
-            "env": {
-                "FLASK_APP": "app.py",
-                "FLASK_ENV": "development"
-            },
-            "args": [
-                "run",
-                "--host=0.0.0.0",
-                "--port=5001",
-                "--no-debugger",
-                "--no-reload"
-            ],
+            "program": "${workspaceFolder}/api/app.py",
             "jinja": true,
             "justMyCode": true,
             "cwd": "${workspaceFolder}/api",

.vscode/settings.example.json

@@ -1,12 +1,16 @@
 {
-  // Disable the default formatter, use eslint instead
-  "prettier.enable": false,
-  "editor.formatOnSave": false,
+  "cucumber.features": [
+    "e2e/features/**/*.feature",
+  ],
+  "cucumber.glue": [
+    "e2e/features/**/*.ts",
+  ],
+
+  "tailwindCSS.experimental.configFile": "web/app/styles/globals.css",
 
   // Auto fix
   "editor.codeActionsOnSave": {
     "source.fixAll.eslint": "explicit",
-    "source.organizeImports": "never"
   },
 
   // Silent the stylistic rules in your IDE, but still auto fix them

AGENTS.md

@@ -30,7 +30,7 @@ The codebase is split into:
 ## Language Style
 
 - **Python**: Keep type hints on functions and attributes, and implement relevant special methods (e.g., `__repr__`, `__str__`). Prefer `TypedDict` over `dict` or `Mapping` for type safety and better code documentation.
-- **TypeScript**: Use the strict config, rely on ESLint (`pnpm lint:fix` preferred) plus `pnpm type-check:tsgo`, and avoid `any` types.
+- **TypeScript**: Use the strict config, rely on ESLint (`pnpm lint:fix` preferred) plus `pnpm type-check`, and avoid `any` types.
 
 ## General Practices
 

Makefile

@@ -3,6 +3,10 @@ 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
@@ -17,8 +21,13 @@ dev-setup: prepare-docker prepare-web prepare-api
 # Step 1: Prepare Docker middleware
 prepare-docker:
 	@echo "🐳 Setting up Docker middleware..."
-	@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
+	@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
 	@echo "✅ Docker middleware started"
 
 # Step 2: Prepare web environment
@@ -39,12 +48,18 @@ prepare-api:
 # Clean dev environment
 dev-clean:
 	@echo "⚠️  Stopping Docker containers..."
-	@cd docker && docker compose -f docker-compose.middleware.yaml --env-file middleware.env -p dify-middlewares-dev down
+	@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
 	@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"
 
@@ -71,13 +86,13 @@ 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/' --check-untyped-defs --disable-error-code=import-untyped .
+	@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 .
 	@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/' --check-untyped-defs --disable-error-code=import-untyped .
+	@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 .
 	@echo "✅ Core type checks complete"
 
 test:
@@ -132,7 +147,7 @@ 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"
+	@echo "  make dev-clean      - Stop Docker middleware containers and remove dev data"
 	@echo ""
 	@echo "Backend Code Quality:"
 	@echo "  make format         - Format code with ruff"

README.md

@@ -137,20 +137,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ### Custom configurations
 
-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).
-
-#### Customizing Suggested Questions
-
-You can now customize the "Suggested Questions After Answer" feature to better fit your use case. For example, to generate longer, more technical questions:
-
-```bash
-# In your .env file
-SUGGESTED_QUESTIONS_PROMPT='Please help me predict the five most likely technical follow-up questions a developer would ask. Focus on implementation details, best practices, and architecture considerations. Keep each question between 40-60 characters. Output must be JSON array: ["question1","question2","question3","question4","question5"]'
-SUGGESTED_QUESTIONS_MAX_TOKENS=512
-SUGGESTED_QUESTIONS_TEMPERATURE=0.3
-```
-
-See the [Suggested Questions Configuration Guide](docs/suggested-questions-configuration.md) for detailed examples and usage instructions.
+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).
 
 ### Metrics Monitoring with Grafana
 
@@ -160,7 +147,7 @@ Import the dashboard to Grafana, using Dify's PostgreSQL database as data source
 
 ### Deployment with Kubernetes
 
-If you'd like to configure a highly-available setup, there are community-contributed [Helm Charts](https://helm.sh/) and YAML files which allow Dify to be deployed on Kubernetes.
+If you'd like to configure a highly available setup, there are community-contributed [Helm Charts](https://helm.sh/) and YAML files which allow Dify to be deployed on Kubernetes.
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)

api/.env.example

@@ -33,6 +33,9 @@ TRIGGER_URL=http://localhost:5001
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
+# Collaboration mode toggle
+ENABLE_COLLABORATION_MODE=true
+
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
 
@@ -57,6 +60,9 @@ REDIS_SSL_CERTFILE=
 REDIS_SSL_KEYFILE=
 # Path to client private key file for SSL authentication
 REDIS_DB=0
+# Optional global prefix for Redis keys, topics, streams, and Celery Redis transport artifacts.
+# Leave empty to preserve current unprefixed behavior.
+REDIS_KEY_PREFIX=
 
 # redis Sentinel configuration.
 REDIS_USE_SENTINEL=false
@@ -82,6 +88,10 @@ 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
@@ -92,6 +102,8 @@ 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...
@@ -375,7 +387,7 @@ VIKINGDB_ACCESS_KEY=your-ak
 VIKINGDB_SECRET_KEY=your-sk
 VIKINGDB_REGION=cn-shanghai
 VIKINGDB_HOST=api-vikingdb.xxx.volces.com
-VIKINGDB_SCHEMA=http
+VIKINGDB_SCHEME=http
 VIKINGDB_CONNECTION_TIMEOUT=30
 VIKINGDB_SOCKET_TIMEOUT=30
 
@@ -426,8 +438,6 @@ 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
@@ -653,6 +663,11 @@ INNER_API_KEY_FOR_PLUGIN=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y
 MARKETPLACE_ENABLED=true
 MARKETPLACE_API_URL=https://marketplace.dify.ai
 
+# Creators Platform configuration
+CREATORS_PLATFORM_FEATURES_ENABLED=true
+CREATORS_PLATFORM_API_URL=https://creators.dify.ai
+CREATORS_PLATFORM_OAUTH_CLIENT_ID=
+
 # Endpoint configuration
 ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}
 
@@ -703,22 +718,6 @@ SWAGGER_UI_PATH=/swagger-ui.html
 # Set to false to export dataset IDs as plain text for easier cross-environment import
 DSL_EXPORT_ENCRYPT_DATASET_ID=true
 
-# Suggested Questions After Answer Configuration
-# These environment variables allow customization of the suggested questions feature
-#
-# Custom prompt for generating suggested questions (optional)
-# If not set, uses the default prompt that generates 3 questions under 20 characters each
-# Example: "Please help me predict the five most likely technical follow-up questions a developer would ask. Focus on implementation details, best practices, and architecture considerations. Keep each question between 40-60 characters. Output must be JSON array: [\"question1\",\"question2\",\"question3\",\"question4\",\"question5\"]"
-# SUGGESTED_QUESTIONS_PROMPT=
-
-# Maximum number of tokens for suggested questions generation (default: 256)
-# Adjust this value for longer questions or more questions
-# SUGGESTED_QUESTIONS_MAX_TOKENS=256
-
-# Temperature for suggested questions generation (default: 0.0)
-# Higher values (0.5-1.0) produce more creative questions, lower values (0.0-0.3) produce more focused questions
-# SUGGESTED_QUESTIONS_TEMPERATURE=0
-
 # Tenant isolated task queue configuration
 TENANT_ISOLATED_TASK_CONCURRENCY=1
 

api/.ruff.toml

@@ -69,8 +69,6 @@ ignore = [
     "FURB152", # math-constant
     "UP007",   # non-pep604-annotation
     "UP032",   # f-string
-    "UP045",   # non-pep604-annotation-optional
-    "B005",    # strip-with-multi-characters
     "B006",    # mutable-argument-default
     "B007",    # unused-loop-control-variable
     "B026",    # star-arg-unpacking-after-keyword-arg
@@ -84,7 +82,6 @@ ignore = [
     "SIM102",  # collapsible-if
     "SIM103",  # needless-bool
     "SIM105",  # suppressible-exception
-    "SIM107",  # return-in-try-except-finally
     "SIM108",  # if-else-block-instead-of-if-exp
     "SIM113",  # enumerate-for-loop
     "SIM117",  # multiple-with-statements
@@ -93,32 +90,22 @@ ignore = [
 ]
 
 [lint.per-file-ignores]
-"__init__.py" = [
-    "F401", # unused-import
-    "F811", # redefined-while-unused
-]
 "configs/*" = [
     "N802", # invalid-function-name
 ]
-"graphon/model_runtime/callbacks/base_callback.py" = ["T201"]
-"core/workflow/callbacks/workflow_logging_callback.py" = ["T201"]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
     "N803", # invalid-argument-name
 ]
 "tests/*" = [
-    "F811", # redefined-while-unused
     "T201", # allow print in tests,
     "S110", # allow ignoring exceptions in tests code (currently)
-
 ]
-"controllers/console/explore/trial.py" = ["TID251"]
-"controllers/console/human_input_form.py" = ["TID251"]
-"controllers/web/human_input_form.py" = ["TID251"]
-
-[lint.flake8-tidy-imports]
 
 [lint.flake8-tidy-imports.banned-api."flask_restx.reqparse"]
 msg = "Use Pydantic payload/query models instead of reqparse."
 
 [lint.flake8-tidy-imports.banned-api."flask_restx.reqparse.RequestParser"]
 msg = "Use Pydantic payload/query models instead of reqparse."
+
+[lint.isort]
+known-first-party = ["graphon"]

api/.vscode/launch.json.example

@@ -3,29 +3,21 @@
     "compounds": [
         {
             "name": "Launch Flask and Celery",
-            "configurations": ["Python: Flask", "Python: Celery"]
+            "configurations": ["Python: API (gevent)", "Python: Celery"]
         }
     ],
     "configurations": [
         {
-            "name": "Python: Flask",
-            "consoleName": "Flask",
+            "name": "Python: API (gevent)",
+            "consoleName": "API",
             "type": "debugpy",
             "request": "launch",
             "python": "${workspaceFolder}/.venv/bin/python",
             "cwd": "${workspaceFolder}",
             "envFile": ".env",
-            "module": "flask",
+            "program": "${workspaceFolder}/app.py",
             "justMyCode": true,
-            "jinja": true,
-            "env": {
-                "FLASK_APP": "app.py",
-                "GEVENT_SUPPORT": "True"
-            },
-            "args": [
-                "run",
-                "--port=5001"
-            ]
+            "jinja": true
         },
         {
             "name": "Python: Celery",

api/AGENTS.md

@@ -193,6 +193,10 @@ 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/Dockerfile

@@ -21,8 +21,9 @@ RUN apt-get update \
           # for building gmpy2
           libmpfr-dev libmpc-dev
 
-# Install Python dependencies
+# Install Python dependencies (workspace members under providers/vdb/)
 COPY pyproject.toml uv.lock ./
+COPY providers ./providers
 RUN uv sync --locked --no-dev
 
 # production stage

api/README.md

@@ -101,3 +101,11 @@ The scripts resolve paths relative to their location, so you can run them from a
    uv run ruff format ./        # Format code
    uv run basedpyright .        # Type checking
    ```
+
+## Generate TS stub
+
+```
+uv run dev/generate_swagger_specs.py --output-dir openapi
+```
+
+use https://jsontotable.org/openapi-to-typescript to convert to typescript

api/app.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import logging
 import sys
 from typing import TYPE_CHECKING, cast
 
@@ -9,17 +10,35 @@ if TYPE_CHECKING:
     celery: Celery
 
 
+HOST = "0.0.0.0"
+PORT = 5001
+logger = logging.getLogger(__name__)
+
+
 def is_db_command() -> bool:
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
 
 
+def log_startup_banner(host: str, port: int) -> None:
+    debugger_attached = sys.gettrace() is not None
+    logger.info("Serving Dify API via gevent WebSocket server")
+    logger.info("Bound to http://%s:%s", host, port)
+    logger.info("Debugger attached: %s", "on" if debugger_attached else "off")
+    logger.info("Press CTRL+C to quit")
+
+
 # create app
+flask_app = None
+socketio_app = None
+
 if is_db_command():
     from app_factory import create_migrations_app
 
     app = create_migrations_app()
+    socketio_app = app
+    flask_app = app
 else:
     # Gunicorn and Celery handle monkey patching automatically in production by
     # specifying the `gevent` worker class. Manual monkey patching is not required here.
@@ -30,8 +49,14 @@ else:
 
     from app_factory import create_app
 
-    app = create_app()
+    socketio_app, flask_app = create_app()
+    app = flask_app
     celery = cast("Celery", app.extensions["celery"])
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5001)
+    from gevent import pywsgi
+    from geventwebsocket.handler import WebSocketHandler  # type: ignore[reportMissingTypeStubs]
+
+    log_startup_banner(HOST, PORT)
+    server = pywsgi.WSGIServer((HOST, PORT), socketio_app, handler_class=WebSocketHandler)
+    server.serve_forever()

api/app_factory.py

@@ -1,6 +1,7 @@
 import logging
 import time
 
+import socketio  # type: ignore[reportMissingTypeStubs]
 from flask import request
 from opentelemetry.trace import get_current_span
 from opentelemetry.trace.span import INVALID_SPAN_ID, INVALID_TRACE_ID
@@ -10,6 +11,7 @@ from contexts.wrapper import RecyclableContextVar
 from controllers.console.error import UnauthorizedAndForceLogout
 from core.logging.context import init_request_context
 from dify_app import DifyApp
+from extensions.ext_socketio import sio
 from services.enterprise.enterprise_service import EnterpriseService
 from services.feature_service import LicenseStatus
 
@@ -122,14 +124,18 @@ def create_flask_app_with_configs() -> DifyApp:
     return dify_app
 
 
-def create_app() -> DifyApp:
+def create_app() -> tuple[socketio.WSGIApp, DifyApp]:
     start_time = time.perf_counter()
     app = create_flask_app_with_configs()
     initialize_extensions(app)
+
+    sio.app = app
+    socketio_app = socketio.WSGIApp(sio, app)
+
     end_time = time.perf_counter()
     if dify_config.DEBUG:
         logger.info("Finished create_app (%s ms)", round((end_time - start_time) * 1000, 2))
-    return app
+    return socketio_app, app
 
 
 def initialize_extensions(app: DifyApp):
@@ -175,7 +181,6 @@ def initialize_extensions(app: DifyApp):
         ext_import_modules,
         ext_orjson,
         ext_forward_refs,
-        ext_set_secretkey,
         ext_compress,
         ext_code_based_extension,
         ext_database,
@@ -183,6 +188,7 @@ 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/commands/account.py

@@ -2,6 +2,7 @@ import base64
 import secrets
 
 import click
+from sqlalchemy.orm import Session
 
 from constants.languages import languages
 from extensions.ext_database import db
@@ -43,10 +44,11 @@ def reset_password(email, new_password, password_confirm):
     # encrypt password with salt
     password_hashed = hash_password(new_password, salt)
     base64_password_hashed = base64.b64encode(password_hashed).decode()
-    account = db.session.merge(account)
-    account.password = base64_password_hashed
-    account.password_salt = base64_salt
-    db.session.commit()
+    with Session(db.engine) as session:
+        account = session.merge(account)
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        session.commit()
     AccountService.reset_login_error_rate_limit(normalized_email)
     click.echo(click.style("Password reset successfully.", fg="green"))
 
@@ -77,9 +79,10 @@ def reset_email(email, new_email, email_confirm):
         click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
         return
 
-    account = db.session.merge(account)
-    account.email = normalized_new_email
-    db.session.commit()
+    with Session(db.engine) as session:
+        account = session.merge(account)
+        account.email = normalized_new_email
+        session.commit()
     click.echo(click.style("Email updated successfully.", fg="green"))
 
 
@@ -110,8 +113,18 @@ def create_tenant(email: str, language: str | None = None, name: str | None = No
     # Validates name encoding for non-Latin characters.
     name = name.strip().encode("utf-8").decode("utf-8") if name else None
 
-    # generate random password
-    new_password = secrets.token_urlsafe(16)
+    # Generate a random password that satisfies the password policy.
+    # The iteration limit guards against infinite loops caused by unexpected bugs in valid_password.
+    for _ in range(100):
+        new_password = secrets.token_urlsafe(16)
+        try:
+            valid_password(new_password)
+            break
+        except Exception:
+            continue
+    else:
+        click.echo(click.style("Failed to generate a valid password. Please try again.", fg="red"))
+        return
 
     # register account
     account = RegisterService.register(

api/commands/plugin.py

@@ -11,7 +11,7 @@ from configs import dify_config
 from core.helper import encrypter
 from core.plugin.entities.plugin_daemon import CredentialType
 from core.plugin.impl.plugin import PluginInstaller
-from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_params
+from core.tools.utils.system_encryption import encrypt_system_params
 from extensions.ext_database import db
 from models import Tenant
 from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
@@ -44,7 +44,7 @@ def setup_system_tool_oauth_client(provider, client_params):
 
         click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
         click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
-        oauth_client_params = encrypt_system_oauth_params(client_params_dict)
+        oauth_client_params = encrypt_system_params(client_params_dict)
         click.echo(click.style("Client params encrypted successfully.", fg="green"))
     except Exception as e:
         click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
@@ -94,7 +94,7 @@ def setup_system_trigger_oauth_client(provider, client_params):
 
         click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
         click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
-        oauth_client_params = encrypt_system_oauth_params(client_params_dict)
+        oauth_client_params = encrypt_system_params(client_params_dict)
         click.echo(click.style("Client params encrypted successfully.", fg="green"))
     except Exception as e:
         click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))

api/commands/vector.py

@@ -341,11 +341,10 @@ def add_qdrant_index(field: str):
             click.echo(click.style("No dataset collection bindings found.", fg="red"))
             return
         import qdrant_client
+        from dify_vdb_qdrant.qdrant_vector import PathQdrantParams, QdrantConfig
         from qdrant_client.http.exceptions import UnexpectedResponse
         from qdrant_client.http.models import PayloadSchemaType
 
-        from core.rag.datasource.vdb.qdrant.qdrant_vector import PathQdrantParams, QdrantConfig
-
         for binding in bindings:
             if dify_config.QDRANT_URL is None:
                 raise ValueError("Qdrant URL is required.")

api/configs/feature/__init__.py

@@ -23,9 +23,9 @@ class SecurityConfig(BaseSettings):
     """
 
     SECRET_KEY: str = Field(
-        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.",
+        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.",
         default="",
     )
 
@@ -289,11 +289,11 @@ class MarketplaceConfig(BaseSettings):
 
 class CreatorsPlatformConfig(BaseSettings):
     """
-    Configuration for creators platform
+    Configuration for Creators Platform integration
     """
 
     CREATORS_PLATFORM_FEATURES_ENABLED: bool = Field(
-        description="Enable or disable creators platform features",
+        description="Enable or disable Creators Platform features",
         default=True,
     )
 
@@ -303,7 +303,7 @@ class CreatorsPlatformConfig(BaseSettings):
     )
 
     CREATORS_PLATFORM_OAUTH_CLIENT_ID: str = Field(
-        description="OAuth client_id for the Creators Platform app registered in Dify",
+        description="OAuth client ID for Creators Platform integration",
         default="",
     )
 
@@ -362,15 +362,6 @@ class FileAccessConfig(BaseSettings):
         default="",
     )
 
-    FILES_API_URL: str = Field(
-        description="Base URL for storage file ticket API endpoints."
-        " Used by sandbox containers (internal or external like e2b) that need"
-        " an absolute, routable address to upload/download files via the API."
-        " For all-in-one Docker deployments, set to http://localhost."
-        " For public sandbox environments, set to a public domain or IP.",
-        default="",
-    )
-
     FILES_ACCESS_TIMEOUT: int = Field(
         description="Expiration time in seconds for file access URLs",
         default=300,
@@ -1146,6 +1137,18 @@ 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",
@@ -1307,46 +1310,7 @@ class PositionConfig(BaseSettings):
 class CollaborationConfig(BaseSettings):
     ENABLE_COLLABORATION_MODE: bool = Field(
         description="Whether to enable collaboration mode features across the workspace",
-        default=False,
-    )
-
-
-class SandboxExpiredRecordsCleanConfig(BaseSettings):
-    SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD: NonNegativeInt = Field(
-        description="Graceful period in days for sandbox records clean after subscription expiration",
-        default=21,
-    )
-    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE: PositiveInt = Field(
-        description="Maximum number of records to process in each batch",
-        default=1000,
-    )
-    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_MAX_INTERVAL: PositiveInt = Field(
-        description="Maximum interval in milliseconds between batches",
-        default=200,
-    )
-    SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS: PositiveInt = Field(
-        description="Retention days for sandbox expired workflow_run records and message records",
-        default=30,
-    )
-    SANDBOX_EXPIRED_RECORDS_CLEAN_TASK_LOCK_TTL: PositiveInt = Field(
-        description="Lock TTL for sandbox expired records clean task in seconds",
-        default=90000,
-    )
-
-
-class AgentV2UpgradeConfig(BaseSettings):
-    """Feature flags for transparent Agent V2 upgrade."""
-
-    AGENT_V2_TRANSPARENT_UPGRADE: bool = Field(
-        description="Transparently run old apps (chat/completion/agent-chat) through the Agent V2 workflow engine. "
-        "When enabled, old apps synthesize a virtual workflow at runtime instead of using legacy runners.",
-        default=False,
-    )
-
-    AGENT_V2_REPLACES_LLM: bool = Field(
-        description="Transparently replace LLM nodes in workflows with Agent V2 nodes at runtime. "
-        "LLMNodeData is remapped to AgentV2NodeData with tools=[] (identical behavior).",
-        default=False,
+        default=True,
     )
 
 
@@ -1419,17 +1383,40 @@ class TenantIsolatedTaskQueueConfig(BaseSettings):
     )
 
 
+class SandboxExpiredRecordsCleanConfig(BaseSettings):
+    SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD: NonNegativeInt = Field(
+        description="Graceful period in days for sandbox records clean after subscription expiration",
+        default=21,
+    )
+    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE: PositiveInt = Field(
+        description="Maximum number of records to process in each batch",
+        default=1000,
+    )
+    SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_MAX_INTERVAL: PositiveInt = Field(
+        description="Maximum interval in milliseconds between batches",
+        default=200,
+    )
+    SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS: PositiveInt = Field(
+        description="Retention days for sandbox expired workflow_run records and message records",
+        default=30,
+    )
+    SANDBOX_EXPIRED_RECORDS_CLEAN_TASK_LOCK_TTL: PositiveInt = Field(
+        description="Lock TTL for sandbox expired records clean task in seconds",
+        default=90000,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
+    CreatorsPlatformConfig,
     TriggerConfig,
     AsyncWorkflowConfig,
     PluginConfig,
     MarketplaceConfig,
-    CreatorsPlatformConfig,
     DataSetConfig,
     EndpointConfig,
     FileAccessConfig,
@@ -1442,9 +1429,11 @@ class FeatureConfig(
     ModelLoadBalanceConfig,
     ModerationConfig,
     MultiModalTransferConfig,
+    OpsTraceConfig,
     PositionConfig,
     RagEtlConfig,
     RepositoryConfig,
+    SandboxExpiredRecordsCleanConfig,
     SecurityConfig,
     TenantIsolatedTaskQueueConfig,
     ToolConfig,
@@ -1453,8 +1442,6 @@ class FeatureConfig(
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     CollaborationConfig,
-    AgentV2UpgradeConfig,
-    SandboxExpiredRecordsCleanConfig,
     LoginConfig,
     AccountConfig,
     SwaggerUIConfig,

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: None
+    pool_reset_on_return: Literal["commit", "rollback", None]
     pool_timeout: int
 
 
@@ -160,6 +160,16 @@ class DatabaseConfig(BaseSettings):
         default="",
     )
 
+    DB_SESSION_TIMEZONE_OVERRIDE: str = Field(
+        description=(
+            "PostgreSQL session timezone override injected via startup options."
+            " Default is 'UTC' for out-of-the-box consistency."
+            " Set to empty string to disable app-level timezone injection, for example when using RDS Proxy"
+            " together with a database-side default timezone."
+        ),
+        default="UTC",
+    )
+
     @computed_field  # type: ignore[prop-decorator]
     @property
     def SQLALCHEMY_DATABASE_URI_SCHEME(self) -> str:
@@ -213,6 +223,11 @@ 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,
@@ -227,12 +242,13 @@ class DatabaseConfig(BaseSettings):
         connect_args: dict[str, str] = {}
         # Use the dynamic SQLALCHEMY_DATABASE_URI_SCHEME property
         if self.SQLALCHEMY_DATABASE_URI_SCHEME.startswith("postgresql"):
-            timezone_opt = "-c timezone=UTC"
-            if options:
-                merged_options = f"{options} {timezone_opt}"
-            else:
-                merged_options = timezone_opt
-            connect_args = {"options": merged_options}
+            merged_options = options.strip()
+            session_timezone_override = self.DB_SESSION_TIMEZONE_OVERRIDE.strip()
+            if session_timezone_override:
+                timezone_opt = f"-c timezone={session_timezone_override}"
+                merged_options = f"{merged_options} {timezone_opt}".strip() if merged_options else timezone_opt
+            if merged_options:
+                connect_args = {"options": merged_options}
 
         result: SQLAlchemyEngineOptionsDict = {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -241,7 +257,7 @@ 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": None,
+            "pool_reset_on_return": self.SQLALCHEMY_POOL_RESET_ON_RETURN,
             "pool_timeout": self.SQLALCHEMY_POOL_TIMEOUT,
         }
         return result

api/configs/middleware/cache/redis_config.py

@@ -32,6 +32,11 @@ class RedisConfig(BaseSettings):
         default=0,
     )
 
+    REDIS_KEY_PREFIX: str = Field(
+        description="Optional global prefix for Redis keys, topics, and transport artifacts",
+        default="",
+    )
+
     REDIS_USE_SSL: bool = Field(
         description="Enable SSL/TLS for the Redis connection",
         default=False,

api/configs/middleware/vdb/hologres_config.py

@@ -1,4 +1,3 @@
-from holo_search_sdk.types import BaseQuantizationType, DistanceType, TokenizerType
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -42,17 +41,17 @@ class HologresConfig(BaseSettings):
         default="public",
     )
 
-    HOLOGRES_TOKENIZER: TokenizerType = Field(
+    HOLOGRES_TOKENIZER: str = Field(
         description="Tokenizer for full-text search index (e.g., 'jieba', 'ik', 'standard', 'simple').",
         default="jieba",
     )
 
-    HOLOGRES_DISTANCE_METHOD: DistanceType = Field(
+    HOLOGRES_DISTANCE_METHOD: str = Field(
         description="Distance method for vector index (e.g., 'Cosine', 'Euclidean', 'InnerProduct').",
         default="Cosine",
     )
 
-    HOLOGRES_BASE_QUANTIZATION_TYPE: BaseQuantizationType = Field(
+    HOLOGRES_BASE_QUANTIZATION_TYPE: str = Field(
         description="Base quantization type for vector index (e.g., 'rabitq', 'sq8', 'fp16', 'fp32').",
         default="rabitq",
     )

api/configs/middleware/vdb/iris_config.py

@@ -1,5 +1,7 @@
 """Configuration for InterSystems IRIS vector database."""
 
+from typing import Any
+
 from pydantic import Field, PositiveInt, model_validator
 from pydantic_settings import BaseSettings
 
@@ -64,7 +66,7 @@ class IrisVectorConfig(BaseSettings):
 
     @model_validator(mode="before")
     @classmethod
-    def validate_config(cls, values: dict) -> dict:
+    def validate_config(cls, values: dict[str, Any]) -> dict[str, Any]:
         """Validate IRIS configuration values.
 
         Args:

api/configs/secret_key.py

@@ -0,0 +1,38 @@
+"""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/constants/dsl_version.py

@@ -0,0 +1 @@
+CURRENT_APP_DSL_VERSION = "0.6.0"

api/constants/model_template.py

@@ -81,20 +81,4 @@ default_app_templates: Mapping[AppMode, Mapping] = {
             },
         },
     },
-    # agent default mode (new agent backed by single-node workflow)
-    AppMode.AGENT: {
-        "app": {
-            "mode": AppMode.AGENT,
-            "enable_site": True,
-            "enable_api": True,
-        },
-        "model_config": {
-            "model": {
-                "provider": "openai",
-                "name": "gpt-4o",
-                "mode": "chat",
-                "completion_params": {},
-            },
-        },
-    },
 }

api/constants/recommended_apps.json

@@ -19,7 +19,7 @@
                         "name": "Website Generator"
                     },
                     "app_id": "b53545b1-79ea-4da3-b31a-c39391c6f041",
-                    "category": "Programming",
+                    "categories": ["Programming"],
                     "copyright": null,
                     "description": null,
                     "is_listed": true,
@@ -35,7 +35,7 @@
                         "name": "Investment Analysis Report Copilot"
                     },
                     "app_id": "a23b57fa-85da-49c0-a571-3aff375976c1",
-                    "category": "Agent",
+                    "categories": ["Agent"],
                     "copyright": "Dify.AI",
                     "description": "Welcome to your personalized Investment Analysis Copilot service, where we delve into the depths of stock analysis to provide you with comprehensive insights. \n",
                     "is_listed": true,
@@ -51,7 +51,7 @@
                         "name": "Workflow Planning Assistant "
                     },
                     "app_id": "f3303a7d-a81c-404e-b401-1f8711c998c1",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "An assistant that helps you plan and select the right node for a workflow (V0.6.0).  ",
                     "is_listed": true,
@@ -67,7 +67,7 @@
                         "name": "Automated Email Reply  "
                     },
                     "app_id": "e9d92058-7d20-4904-892f-75d90bef7587",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Reply emails using Gmail API. It will automatically retrieve email in your inbox and create a response in Gmail. \nConfigure your Gmail API in Google Cloud Console. ",
                     "is_listed": true,
@@ -83,7 +83,7 @@
                         "name": "Book Translation "
                     },
                     "app_id": "98b87f88-bd22-4d86-8b74-86beba5e0ed4",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "A workflow designed to translate a full book up to 15000 tokens per run. Uses Code node to separate text into chunks and Iteration to translate each chunk. ",
                     "is_listed": true,
@@ -99,7 +99,7 @@
                         "name": "Python bug fixer"
                     },
                     "app_id": "cae337e6-aec5-4c7b-beca-d6f1a808bd5e",
-                    "category": "Programming",
+                    "categories": ["Programming"],
                     "copyright": null,
                     "description": null,
                     "is_listed": true,
@@ -115,7 +115,7 @@
                         "name": "Code Interpreter"
                     },
                     "app_id": "d077d587-b072-4f2c-b631-69ed1e7cdc0f",
-                    "category": "Programming",
+                    "categories": ["Programming"],
                     "copyright": "Copyright 2023 Dify",
                     "description": "Code interpreter, clarifying the syntax and semantics of the code.",
                     "is_listed": true,
@@ -131,7 +131,7 @@
                         "name": "SVG Logo Design "
                     },
                     "app_id": "73fbb5f1-c15d-4d74-9cc8-46d9db9b2cca",
-                    "category": "Agent",
+                    "categories": ["Agent"],
                     "copyright": "Dify.AI",
                     "description": "Hello, I am your creative partner in bringing ideas to vivid life! I can assist you in creating stunning designs by leveraging abilities of DALL·E 3.  ",
                     "is_listed": true,
@@ -147,7 +147,7 @@
                         "name": "Long Story Generator (Iteration) "
                     },
                     "app_id": "5efb98d7-176b-419c-b6ef-50767391ab62",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "A workflow demonstrating how to use Iteration node to generate long article that is longer than the context length of LLMs. ",
                     "is_listed": true,
@@ -163,7 +163,7 @@
                         "name": "Text Summarization Workflow"
                     },
                     "app_id": "f00c4531-6551-45ee-808f-1d7903099515",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Based on users' choice, retrieve external knowledge to more accurately summarize articles.",
                     "is_listed": true,
@@ -179,7 +179,7 @@
                         "name": "YouTube Channel Data Analysis"
                     },
                     "app_id": "be591209-2ca8-410f-8f3b-ca0e530dd638",
-                    "category": "Agent",
+                    "categories": ["Agent"],
                     "copyright": "Dify.AI",
                     "description": "I am a YouTube Channel Data Analysis Copilot, I am here to provide expert data analysis tailored to your needs. ",
                     "is_listed": true,
@@ -195,7 +195,7 @@
                         "name": "Article Grading Bot"
                     },
                     "app_id": "a747f7b4-c48b-40d6-b313-5e628232c05f",
-                    "category": "Writing",
+                    "categories": ["Writing"],
                     "copyright": null,
                     "description": "Assess the quality of articles and text based on user defined criteria. ",
                     "is_listed": true,
@@ -211,7 +211,7 @@
                         "name": "SEO Blog Generator"
                     },
                     "app_id": "18f3bd03-524d-4d7a-8374-b30dbe7c69d5",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Workflow for retrieving information from the internet, followed by segmented generation of SEO blogs.",
                     "is_listed": true,
@@ -227,7 +227,7 @@
                         "name": "SQL Creator"
                     },
                     "app_id": "050ef42e-3e0c-40c1-a6b6-a64f2c49d744",
-                    "category": "Programming",
+                    "categories": ["Programming"],
                     "copyright": "Copyright 2023 Dify",
                     "description": "Write SQL from natural language by pasting in your schema with the request.Please describe your query requirements in natural language and select the target database type.",
                     "is_listed": true,
@@ -243,7 +243,7 @@
                         "name": "Sentiment Analysis "
                     },
                     "app_id": "f06bf86b-d50c-4895-a942-35112dbe4189",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Batch sentiment analysis of text, followed by JSON output of sentiment classification along with scores.",
                     "is_listed": true,
@@ -259,7 +259,7 @@
                         "name": "Strategic Consulting Expert"
                     },
                     "app_id": "7e8ca1ae-02f2-4b5f-979e-62d19133bee2",
-                    "category": "Assistant",
+                    "categories": ["Assistant"],
                     "copyright": "Copyright 2023 Dify",
                     "description": "I can answer your questions related to strategic marketing.",
                     "is_listed": true,
@@ -275,7 +275,7 @@
                         "name": "Code Converter"
                     },
                     "app_id": "4006c4b2-0735-4f37-8dbb-fb1a8c5bd87a",
-                    "category": "Programming",
+                    "categories": ["Programming"],
                     "copyright": "Copyright 2023 Dify",
                     "description": "This is an application that provides the ability to convert code snippets in multiple programming languages. You can input the code you wish to convert, select the target programming language, and get the desired output.",
                     "is_listed": true,
@@ -291,7 +291,7 @@
                         "name": "Question Classifier + Knowledge + Chatbot "
                     },
                     "app_id": "d9f6b733-e35d-4a40-9f38-ca7bbfa009f7",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Basic Workflow Template, a chatbot capable of identifying intents alongside with a knowledge base.",
                     "is_listed": true,
@@ -307,7 +307,7 @@
                         "name": "AI Front-end interviewer"
                     },
                     "app_id": "127efead-8944-4e20-ba9d-12402eb345e0",
-                    "category": "HR",
+                    "categories": ["HR"],
                     "copyright": "Copyright 2023 Dify",
                     "description": "A simulated front-end interviewer that tests the skill level of front-end development through questioning.",
                     "is_listed": true,
@@ -323,7 +323,7 @@
                         "name": "Knowledge Retrieval + Chatbot "
                     },
                     "app_id": "e9870913-dd01-4710-9f06-15d4180ca1ce",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Basic Workflow Template, A chatbot with a knowledge base. ",
                     "is_listed": true,
@@ -339,7 +339,7 @@
                         "name": "Email Assistant Workflow "
                     },
                     "app_id": "dd5b6353-ae9b-4bce-be6a-a681a12cf709",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "A multifunctional email assistant capable of summarizing, replying, composing, proofreading, and checking grammar.",
                     "is_listed": true,
@@ -355,7 +355,7 @@
                         "name": "Customer Review Analysis Workflow "
                     },
                     "app_id": "9c0cd31f-4b62-4005-adf5-e3888d08654a",
-                    "category": "Workflow",
+                    "categories": ["Workflow"],
                     "copyright": null,
                     "description": "Utilize LLM (Large Language Models) to classify customer reviews and forward them to the internal system.",
                     "is_listed": true,

api/controllers/API_SCHEMA_GUIDE.md

@@ -0,0 +1,193 @@
+# 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/fields.py

@@ -2,9 +2,9 @@ from __future__ import annotations
 
 from typing import Any
 
-from graphon.file import helpers as file_helpers
 from pydantic import BaseModel, ConfigDict, computed_field
 
+from graphon.file import helpers as file_helpers
 from models.model import IconType
 
 type JSONValue = str | int | float | bool | None | dict[str, Any] | list[Any]

api/controllers/common/helpers.py

@@ -41,7 +41,8 @@ def guess_file_info_from_response(response: httpx.Response):
     # Try to extract filename from URL
     parsed_url = urllib.parse.urlparse(url)
     url_path = parsed_url.path
-    filename = os.path.basename(url_path)
+    # Decode percent-encoded characters in the path segment
+    filename = urllib.parse.unquote(os.path.basename(url_path))
 
     # If filename couldn't be extracted, use Content-Disposition header
     if not filename:

api/controllers/common/human_input.py

@@ -0,0 +1,6 @@
+from pydantic import BaseModel, JsonValue
+
+
+class HumanInputFormSubmitPayload(BaseModel):
+    inputs: dict[str, JsonValue]
+    action: str

api/controllers/common/schema.py

@@ -1,6 +1,14 @@
-"""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
@@ -8,10 +16,59 @@ from pydantic import BaseModel, TypeAdapter
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
-def register_schema_model(namespace: Namespace, model: type[BaseModel]) -> None:
-    """Register a single BaseModel with a namespace for Swagger documentation."""
+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],
+    },
+)
 
-    namespace.schema_model(model.__name__, model.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+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_schema_model(namespace, model, mode="validation")
 
 
 def register_schema_models(namespace: Namespace, *models: type[BaseModel]) -> None:
@@ -21,6 +78,19 @@ 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
@@ -34,15 +104,114 @@ 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:
-        namespace.schema_model(
-            model.__name__, TypeAdapter(model).json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+        _register_json_schema(
+            namespace,
+            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/__init__.py

@@ -65,6 +65,7 @@ from .app import (
     statistic,
     workflow,
     workflow_app_log,
+    workflow_comment,
     workflow_draft_variable,
     workflow_run,
     workflow_statistic,
@@ -116,6 +117,7 @@ from .explore import (
     saved_message,
     trial,
 )
+from .socketio import workflow as socketio_workflow  # pyright: ignore[reportUnusedImport]
 
 # Import tag controllers
 from .tag import tags
@@ -201,6 +203,7 @@ __all__ = [
     "saved_message",
     "setup",
     "site",
+    "socketio_workflow",
     "spec",
     "statistic",
     "tags",
@@ -211,6 +214,7 @@ __all__ = [
     "website",
     "workflow",
     "workflow_app_log",
+    "workflow_comment",
     "workflow_draft_variable",
     "workflow_run",
     "workflow_statistic",

api/controllers/console/admin.py

@@ -3,6 +3,7 @@ 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
@@ -12,6 +13,7 @@ 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
@@ -20,8 +22,6 @@ 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(...)
@@ -58,15 +58,7 @@ class InsertExploreBannerPayload(BaseModel):
     model_config = {"populate_by_name": True}
 
 
-console_ns.schema_model(
-    InsertExploreAppPayload.__name__,
-    InsertExploreAppPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
-)
-
-console_ns.schema_model(
-    InsertExploreBannerPayload.__name__,
-    InsertExploreBannerPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
-)
+register_schema_models(console_ns, InsertExploreAppPayload, InsertExploreBannerPayload)
 
 
 def admin_required[**P, R](view: Callable[P, R]) -> Callable[P, R]:
@@ -190,7 +182,7 @@ class InsertExploreAppApi(Resource):
     @console_ns.response(204, "App removed successfully")
     @only_edition_cloud
     @admin_required
-    def delete(self, app_id):
+    def delete(self, app_id: UUID):
         with session_factory.create_session() as session:
             recommended_app = session.execute(
                 select(RecommendedApp).where(RecommendedApp.app_id == str(app_id))
@@ -301,15 +293,7 @@ class BatchAddNotificationAccountsPayload(BaseModel):
     user_email: list[str] = Field(..., description="List of account email addresses")
 
 
-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),
-)
+register_schema_models(console_ns, UpsertNotificationPayload, BatchAddNotificationAccountsPayload)
 
 
 @console_ns.route("/admin/upsert_notification")
@@ -411,11 +395,11 @@ class BatchAddNotificationAccountsApi(Resource):
             raise BadRequest("Invalid file type. Only CSV (.csv) and TXT (.txt) files are allowed.")
 
         try:
-            content = file.read().decode("utf-8")
+            content = file.stream.read().decode("utf-8")
         except UnicodeDecodeError:
             try:
-                file.seek(0)
-                content = file.read().decode("gbk")
+                file.stream.seek(0)
+                content = file.stream.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

@@ -5,7 +5,7 @@ from pydantic import BaseModel, Field
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
-from services.advanced_prompt_template_service import AdvancedPromptTemplateService
+from services.advanced_prompt_template_service import AdvancedPromptTemplateArgs, AdvancedPromptTemplateService
 
 
 class AdvancedPromptTemplateQuery(BaseModel):
@@ -34,6 +34,11 @@ class AdvancedPromptTemplateList(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
-
-        return AdvancedPromptTemplateService.get_prompt(args.model_dump())
+        args = AdvancedPromptTemplateQuery.model_validate(request.args.to_dict(flat=True))
+        prompt_args: AdvancedPromptTemplateArgs = {
+            "app_mode": args.app_mode,
+            "model_mode": args.model_mode,
+            "model_name": args.model_name,
+            "has_context": args.has_context,
+        }
+        return AdvancedPromptTemplateService.get_prompt(prompt_args)

api/controllers/console/app/agent.py

@@ -2,6 +2,7 @@ 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
@@ -10,8 +11,6 @@ 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")
@@ -23,9 +22,7 @@ class AgentLogQuery(BaseModel):
         return uuid_value(value)
 
 
-console_ns.schema_model(
-    AgentLogQuery.__name__, AgentLogQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
-)
+register_schema_models(console_ns, AgentLogQuery)
 
 
 @console_ns.route("/apps/<uuid:app_id>/agent/logs")
@@ -44,6 +41,6 @@ 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))  # type: ignore
+        args = AgentLogQuery.model_validate(request.args.to_dict(flat=True))
 
         return AgentService.get_agent_logs(app_model, args.conversation_id, args.message_id)

api/controllers/console/app/annotation.py

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

api/controllers/console/app/app.py

@@ -1,15 +1,16 @@
 import logging
+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
-from graphon.enums import WorkflowExecutionStatus
-from graphon.file import helpers as file_helpers
 from pydantic import AliasChoices, BaseModel, Field, computed_field, field_validator
 from sqlalchemy import select
-from sqlalchemy.orm import sessionmaker
+from sqlalchemy.orm import Session
+from werkzeug.datastructures import MultiDict
 from werkzeug.exceptions import BadRequest
 
 from controllers.common.helpers import FileInfo
@@ -25,19 +26,22 @@ 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
 from core.trigger.constants import TRIGGER_NODE_TYPES
 from extensions.ext_database import db
 from fields.base import ResponseModel
+from graphon.enums import WorkflowExecutionStatus
+from libs.helper import build_icon_url
 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 AppService
+from services.app_service import AppListParams, AppService, CreateAppParams
 from services.enterprise.enterprise_service import EnterpriseService
-from services.entities.dsl_entities import ImportMode
+from services.entities.dsl_entities import ImportMode, ImportStatus
 from services.entities.knowledge_entities.knowledge_entities import (
     DataSource,
     InfoList,
@@ -52,36 +56,34 @@ from services.entities.knowledge_entities.knowledge_entities import (
 )
 from services.feature_service import FeatureService
 
-ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion", "agent"]
+ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
 register_enum_models(console_ns, IconType)
 
 _logger = logging.getLogger(__name__)
+_TAG_IDS_BRACKET_PATTERN = re.compile(r"^tag_ids\[(\d+)\]$")
 
 
 class AppListQuery(BaseModel):
     page: int = Field(default=1, ge=1, le=99999, description="Page number (1-99999)")
     limit: int = Field(default=20, ge=1, le=100, description="Page size (1-100)")
-    mode: Literal["completion", "chat", "advanced-chat", "workflow", "agent-chat", "agent", "channel", "all"] = Field(
+    mode: Literal["completion", "chat", "advanced-chat", "workflow", "agent-chat", "channel", "all"] = Field(
         default="all", description="App mode filter"
     )
     name: str | None = Field(default=None, description="Filter by app name")
-    tag_ids: list[str] | None = Field(default=None, description="Comma-separated tag IDs")
+    tag_ids: list[str] | None = Field(default=None, description="Filter by tag IDs")
     is_created_by_me: bool | None = Field(default=None, description="Filter by creator")
 
     @field_validator("tag_ids", mode="before")
     @classmethod
-    def validate_tag_ids(cls, value: str | list[str] | None) -> list[str] | None:
+    def validate_tag_ids(cls, value: list[str] | None) -> list[str] | None:
         if not value:
             return None
 
-        if isinstance(value, str):
-            items = [item.strip() for item in value.split(",") if item.strip()]
-        elif isinstance(value, list):
-            items = [str(item).strip() for item in value if item and str(item).strip()]
-        else:
-            raise TypeError("Unsupported tag_ids type.")
+        if not isinstance(value, list):
+            raise ValueError("Unsupported tag_ids type.")
 
+        items = [str(item).strip() for item in value if item and str(item).strip()]
         if not items:
             return None
 
@@ -91,12 +93,30 @@ class AppListQuery(BaseModel):
             raise ValueError("Invalid UUID format in tag_ids.") from exc
 
 
+def _normalize_app_list_query_args(query_args: MultiDict[str, str]) -> dict[str, str | list[str]]:
+    normalized: dict[str, str | list[str]] = {}
+    indexed_tag_ids: list[tuple[int, str]] = []
+
+    for key in query_args:
+        match = _TAG_IDS_BRACKET_PATTERN.fullmatch(key)
+        if match:
+            indexed_tag_ids.extend((int(match.group(1)), value) for value in query_args.getlist(key))
+            continue
+
+        value = query_args.get(key)
+        if value is not None:
+            normalized[key] = value
+
+    if indexed_tag_ids:
+        normalized["tag_ids"] = [value for _, value in sorted(indexed_tag_ids)]
+
+    return normalized
+
+
 class CreateAppPayload(BaseModel):
     name: str = Field(..., min_length=1, description="App name")
     description: str | None = Field(default=None, description="App description (max 400 chars)", max_length=400)
-    mode: Literal["chat", "agent-chat", "advanced-chat", "workflow", "completion", "agent"] = Field(
-        ..., description="App mode"
-    )
+    mode: Literal["chat", "agent-chat", "advanced-chat", "workflow", "completion"] = Field(..., description="App mode")
     icon_type: IconType | None = Field(default=None, description="Icon type")
     icon: str | None = Field(default=None, description="Icon")
     icon_background: str | None = Field(default=None, description="Icon background color")
@@ -131,6 +151,7 @@ class AppNamePayload(BaseModel):
 
 class AppIconPayload(BaseModel):
     icon: str | None = Field(default=None, description="Icon data")
+    icon_type: IconType | None = Field(default=None, description="Icon type")
     icon_background: str | None = Field(default=None, description="Icon background color")
 
 
@@ -163,15 +184,6 @@ def _to_timestamp(value: datetime | int | None) -> int | None:
     return value
 
 
-def _build_icon_url(icon_type: str | IconType | None, icon: str | None) -> str | None:
-    if icon is None or icon_type is None:
-        return None
-    icon_type_value = icon_type.value if isinstance(icon_type, IconType) else str(icon_type)
-    if icon_type_value.lower() != IconType.IMAGE:
-        return None
-    return file_helpers.get_signed_file_url(icon)
-
-
 class Tag(ResponseModel):
     id: str
     name: str
@@ -294,7 +306,7 @@ class Site(ResponseModel):
     @computed_field(return_type=str | None)  # type: ignore
     @property
     def icon_url(self) -> str | None:
-        return _build_icon_url(self.icon_type, self.icon)
+        return build_icon_url(self.icon_type, self.icon)
 
     @field_validator("icon_type", mode="before")
     @classmethod
@@ -344,7 +356,7 @@ class AppPartial(ResponseModel):
     @computed_field(return_type=str | None)  # type: ignore
     @property
     def icon_url(self) -> str | None:
-        return _build_icon_url(self.icon_type, self.icon)
+        return build_icon_url(self.icon_type, self.icon)
 
     @field_validator("created_at", "updated_at", mode="before")
     @classmethod
@@ -392,7 +404,7 @@ class AppDetailWithSite(AppDetail):
     @computed_field(return_type=str | None)  # type: ignore
     @property
     def icon_url(self) -> str | None:
-        return _build_icon_url(self.icon_type, self.icon)
+        return build_icon_url(self.icon_type, self.icon)
 
 
 class AppPagination(ResponseModel):
@@ -465,12 +477,19 @@ class AppListApi(Resource):
         """Get app list"""
         current_user, current_tenant_id = current_account_with_tenant()
 
-        args = AppListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
-        args_dict = args.model_dump()
+        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,
+        )
 
         # get app list
         app_service = AppService()
-        app_pagination = app_service.get_paginate_apps(current_user.id, current_tenant_id, args_dict)
+        app_pagination = app_service.get_paginate_apps(current_user.id, current_tenant_id, params)
         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
@@ -534,9 +553,17 @@ 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, args.model_dump(), current_user)
+        app = app_service.create_app(current_tenant_id, params, current_user)
         app_detail = AppDetail.model_validate(app, from_attributes=True)
         return app_detail.model_dump(mode="json"), 201
 
@@ -634,7 +661,7 @@ class AppCopyApi(Resource):
 
         args = CopyAppPayload.model_validate(console_ns.payload or {})
 
-        with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        with Session(db.engine, expire_on_commit=False) as session:
             import_service = AppDslService(session)
             yaml_content = import_service.export_dsl(app_model=app_model, include_secret=True)
             result = import_service.import_app(
@@ -647,6 +674,13 @@ class AppCopyApi(Resource):
                 icon=args.icon,
                 icon_background=args.icon_background,
             )
+            if result.status == ImportStatus.FAILED:
+                session.rollback()
+                return result.model_dump(mode="json"), 400
+            if result.status == ImportStatus.PENDING:
+                session.rollback()
+                return result.model_dump(mode="json"), 202
+            session.commit()
 
             # Inherit web app permission from original app
             if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
@@ -683,7 +717,7 @@ class AppExportApi(Resource):
     @edit_permission_required
     def get(self, app_model):
         """Export app"""
-        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = AppExportQuery.model_validate(request.args.to_dict(flat=True))
 
         payload = AppExportResponse(
             data=AppDslService.export_dsl(
@@ -695,6 +729,32 @@ class AppExportApi(Resource):
         return payload.model_dump(mode="json")
 
 
+@console_ns.route("/apps/<uuid:app_id>/publish-to-creators-platform")
+class AppPublishToCreatorsPlatformApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=None)
+    @edit_permission_required
+    def post(self, app_model):
+        """Publish app to Creators Platform"""
+        from configs import dify_config
+        from core.helper.creators import get_redirect_url, upload_dsl
+
+        if not dify_config.CREATORS_PLATFORM_FEATURES_ENABLED:
+            return {"error": "Creators Platform features are not enabled"}, 403
+
+        current_user, _ = current_account_with_tenant()
+
+        dsl_content = AppDslService.export_dsl(app_model=app_model, include_secret=False)
+        dsl_bytes = dsl_content.encode("utf-8")
+
+        claim_code = upload_dsl(dsl_bytes)
+        redirect_url = get_redirect_url(str(current_user.id), claim_code)
+
+        return {"redirect_url": redirect_url}
+
+
 @console_ns.route("/apps/<uuid:app_id>/name")
 class AppNameApi(Resource):
     @console_ns.doc("check_app_name")
@@ -733,7 +793,12 @@ class AppIconApi(Resource):
         args = AppIconPayload.model_validate(console_ns.payload or {})
 
         app_service = AppService()
-        app_model = app_service.update_app_icon(app_model, args.icon or "", args.icon_background or "")
+        app_model = app_service.update_app_icon(
+            app_model,
+            args.icon or "",
+            args.icon_background or "",
+            args.icon_type,
+        )
         response_model = AppDetail.model_validate(app_model, from_attributes=True)
         return response_model.model_dump(mode="json")
 
@@ -791,9 +856,10 @@ class AppTraceApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id):
+    def get(self, app_id: UUID):
         """Get app trace"""
-        app_trace_config = OpsTraceManager.get_app_tracing_config(app_id=app_id)
+        with session_factory.create_session() as session:
+            app_trace_config = OpsTraceManager.get_app_tracing_config(str(app_id), session)
 
         return app_trace_config
 
@@ -807,12 +873,12 @@ class AppTraceApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def post(self, app_id):
+    def post(self, app_id: UUID):
         # add app trace
         args = AppTracePayload.model_validate(console_ns.payload)
 
         OpsTraceManager.update_app_tracing_config(
-            app_id=app_id,
+            app_id=str(app_id),
             enabled=args.enabled,
             tracing_provider=args.tracing_provider,
         )

api/controllers/console/app/app_import.py

@@ -1,8 +1,8 @@
 from flask_restx import Resource
 from pydantic import BaseModel, Field
-from sqlalchemy.orm import sessionmaker
+from sqlalchemy.orm import Session
 
-from controllers.common.schema import register_schema_models
+from controllers.common.schema import register_enum_models, register_schema_models
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import (
     account_initialization_required,
@@ -33,6 +33,7 @@ class AppImportPayload(BaseModel):
     app_id: str | None = Field(None)
 
 
+register_enum_models(console_ns, ImportStatus)
 register_schema_models(console_ns, AppImportPayload, Import, CheckDependenciesResult)
 
 
@@ -52,8 +53,9 @@ class AppImportApi(Resource):
         current_user, _ = current_account_with_tenant()
         args = AppImportPayload.model_validate(console_ns.payload)
 
-        # Create service with session
-        with sessionmaker(db.engine).begin() as session:
+        # AppDslService performs internal commits for some creation paths, so use a plain
+        # Session here instead of nesting it inside sessionmaker(...).begin().
+        with Session(db.engine, expire_on_commit=False) as session:
             import_service = AppDslService(session)
             # Import app
             account = current_user
@@ -69,6 +71,10 @@ class AppImportApi(Resource):
                 icon_background=args.icon_background,
                 app_id=args.app_id,
             )
+            if result.status == ImportStatus.FAILED:
+                session.rollback()
+            else:
+                session.commit()
         if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
             # update web app setting as private
             EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, "private")
@@ -95,12 +101,15 @@ class AppImportConfirmApi(Resource):
         # Check user role first
         current_user, _ = current_account_with_tenant()
 
-        # Create service with session
-        with sessionmaker(db.engine).begin() as session:
+        with Session(db.engine, expire_on_commit=False) as session:
             import_service = AppDslService(session)
             # Confirm import
             account = current_user
             result = import_service.confirm_import(import_id=import_id, account=account)
+            if result.status == ImportStatus.FAILED:
+                session.rollback()
+            else:
+                session.commit()
 
         # Return appropriate status code based on result
         if result.status == ImportStatus.FAILED:
@@ -117,7 +126,7 @@ class AppImportCheckDependenciesApi(Resource):
     @account_initialization_required
     @edit_permission_required
     def get(self, app_model: App):
-        with sessionmaker(db.engine).begin() as session:
+        with Session(db.engine, expire_on_commit=False) as session:
             import_service = AppDslService(session)
             result = import_service.check_dependencies(app_model=app_model)
 

api/controllers/console/app/audio.py

@@ -2,7 +2,6 @@ import logging
 
 from flask import request
 from flask_restx import Resource, fields
-from graphon.model_runtime.errors.invoke import InvokeError
 from pydantic import BaseModel, Field
 from werkzeug.exceptions import InternalServerError
 
@@ -23,6 +22,7 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from graphon.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
 from models import App, AppMode
 from services.audio_service import AudioService
@@ -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))  # type: ignore
+            args = TextToSpeechVoiceQuery.model_validate(request.args.to_dict(flat=True))
 
             response = AudioService.transcript_tts_voices(
                 tenant_id=app_model.tenant_id,

api/controllers/console/app/completion.py

@@ -3,11 +3,11 @@ from typing import Any, Literal
 
 from flask import request
 from flask_restx import Resource
-from graphon.model_runtime.errors.invoke import InvokeError
 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,
@@ -27,6 +27,7 @@ from core.errors.error import (
     QuotaExceededError,
 )
 from core.helper.trace_id_helper import get_external_trace_id
+from graphon.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import uuid_value
 from libs.login import current_user, login_required
@@ -37,7 +38,6 @@ 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):
@@ -65,13 +65,7 @@ class ChatMessagePayload(BaseMessagePayload):
         return uuid_value(value)
 
 
-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)
-)
+register_schema_models(console_ns, CompletionMessagePayload, ChatMessagePayload)
 
 
 # define completion message api for user
@@ -161,7 +155,7 @@ class ChatMessageApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT])
     @edit_permission_required
     def post(self, app_model):
         args_model = ChatMessagePayload.model_validate(console_ns.payload)
@@ -215,7 +209,7 @@ class ChatMessageStopApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
     def post(self, app_model, task_id):
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")

api/controllers/console/app/conversation.py

@@ -2,28 +2,43 @@ from typing import Literal
 
 import sqlalchemy as sa
 from flask import abort, request
-from flask_restx import Resource, fields, marshal_with
+from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import func, or_
 from sqlalchemy.orm import selectinload
 from werkzeug.exceptions import NotFound
 
+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, edit_permission_required, setup_required
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
-from fields.raws import FilesContainedField
+from fields.conversation_fields import (
+    Conversation as ConversationResponse,
+)
+from fields.conversation_fields import (
+    ConversationDetail as ConversationDetailResponse,
+)
+from fields.conversation_fields import (
+    ConversationMessageDetail as ConversationMessageDetailResponse,
+)
+from fields.conversation_fields import (
+    ConversationPagination as ConversationPaginationResponse,
+)
+from fields.conversation_fields import (
+    ConversationWithSummaryPagination as ConversationWithSummaryPaginationResponse,
+)
+from fields.conversation_fields import (
+    ResultResponse,
+)
 from libs.datetime_utils import naive_utc_now, parse_time_range
-from libs.helper import TimestampField
 from libs.login import current_account_with_tenant, login_required
 from models import Conversation, EndUser, Message, MessageAnnotation
 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")
@@ -53,276 +68,18 @@ 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 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",
-    {
-        "id": fields.String,
-        "name": fields.String,
-        "email": fields.String,
-    },
-)
-
-feedback_stat_model = console_ns.model(
-    "FeedbackStat",
-    {
-        "like": fields.Integer,
-        "dislike": fields.Integer,
-    },
-)
-
-status_count_model = console_ns.model(
-    "StatusCount",
-    {
-        "success": fields.Integer,
-        "failed": fields.Integer,
-        "partial_success": fields.Integer,
-        "paused": fields.Integer,
-    },
-)
-
-message_file_model = console_ns.model(
-    "MessageFile",
-    {
-        "id": fields.String,
-        "filename": fields.String,
-        "type": fields.String,
-        "url": fields.String,
-        "mime_type": fields.String,
-        "size": fields.Integer,
-        "transfer_method": fields.String,
-        "belongs_to": fields.String(default="user"),
-        "upload_file_id": fields.String(default=None),
-    },
-)
-
-agent_thought_model = console_ns.model(
-    "AgentThought",
-    {
-        "id": fields.String,
-        "chain_id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "thought": fields.String,
-        "tool": fields.String,
-        "tool_labels": fields.Raw,
-        "tool_input": fields.String,
-        "created_at": TimestampField,
-        "observation": fields.String,
-        "files": fields.List(fields.String),
-    },
-)
-
-simple_model_config_model = console_ns.model(
-    "SimpleModelConfig",
-    {
-        "model": fields.Raw(attribute="model_dict"),
-        "pre_prompt": fields.String,
-    },
-)
-
-model_config_model = console_ns.model(
-    "ModelConfig",
-    {
-        "opening_statement": fields.String,
-        "suggested_questions": fields.Raw,
-        "model": fields.Raw,
-        "user_input_form": fields.Raw,
-        "pre_prompt": fields.String,
-        "agent_mode": fields.Raw,
-    },
-)
-
-# Models that depend on simple_account_model
-feedback_model = console_ns.model(
-    "Feedback",
-    {
-        "rating": fields.String,
-        "content": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account": fields.Nested(simple_account_model, allow_null=True),
-    },
-)
-
-annotation_model = console_ns.model(
-    "Annotation",
-    {
-        "id": fields.String,
-        "question": fields.String,
-        "content": fields.String,
-        "account": fields.Nested(simple_account_model, allow_null=True),
-        "created_at": TimestampField,
-    },
-)
-
-annotation_hit_history_model = console_ns.model(
-    "AnnotationHitHistory",
-    {
-        "annotation_id": fields.String(attribute="id"),
-        "annotation_create_account": fields.Nested(simple_account_model, allow_null=True),
-        "created_at": TimestampField,
-    },
-)
-
-
-class MessageTextField(fields.Raw):
-    def format(self, value):
-        return value[0]["text"] if value else ""
-
-
-# Simple message detail model
-simple_message_detail_model = console_ns.model(
-    "SimpleMessageDetail",
-    {
-        "inputs": FilesContainedField,
-        "query": fields.String,
-        "message": MessageTextField,
-        "answer": fields.String,
-    },
-)
-
-# Message detail model that depends on multiple models
-message_detail_model = console_ns.model(
-    "MessageDetail",
-    {
-        "id": fields.String,
-        "conversation_id": fields.String,
-        "inputs": FilesContainedField,
-        "query": fields.String,
-        "message": fields.Raw,
-        "message_tokens": fields.Integer,
-        "answer": fields.String(attribute="re_sign_file_url_answer"),
-        "answer_tokens": fields.Integer,
-        "provider_response_latency": fields.Float,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account_id": fields.String,
-        "feedbacks": fields.List(fields.Nested(feedback_model)),
-        "workflow_run_id": fields.String,
-        "annotation": fields.Nested(annotation_model, allow_null=True),
-        "annotation_hit_history": fields.Nested(annotation_hit_history_model, allow_null=True),
-        "created_at": TimestampField,
-        "agent_thoughts": fields.List(fields.Nested(agent_thought_model)),
-        "message_files": fields.List(fields.Nested(message_file_model)),
-        "metadata": fields.Raw(attribute="message_metadata_dict"),
-        "status": fields.String,
-        "error": fields.String,
-        "parent_message_id": fields.String,
-    },
-)
-
-# Conversation models
-conversation_fields_model = console_ns.model(
-    "Conversation",
-    {
-        "id": fields.String,
-        "status": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_end_user_session_id": fields.String(),
-        "from_account_id": fields.String,
-        "from_account_name": fields.String,
-        "read_at": TimestampField,
-        "created_at": TimestampField,
-        "updated_at": TimestampField,
-        "annotation": fields.Nested(annotation_model, allow_null=True),
-        "model_config": fields.Nested(simple_model_config_model),
-        "user_feedback_stats": fields.Nested(feedback_stat_model),
-        "admin_feedback_stats": fields.Nested(feedback_stat_model),
-        "message": fields.Nested(simple_message_detail_model, attribute="first_message"),
-    },
-)
-
-conversation_pagination_model = console_ns.model(
-    "ConversationPagination",
-    {
-        "page": fields.Integer,
-        "limit": fields.Integer(attribute="per_page"),
-        "total": fields.Integer,
-        "has_more": fields.Boolean(attribute="has_next"),
-        "data": fields.List(fields.Nested(conversation_fields_model), attribute="items"),
-    },
-)
-
-conversation_message_detail_model = console_ns.model(
-    "ConversationMessageDetail",
-    {
-        "id": fields.String,
-        "status": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account_id": fields.String,
-        "created_at": TimestampField,
-        "model_config": fields.Nested(model_config_model),
-        "message": fields.Nested(message_detail_model, attribute="first_message"),
-    },
-)
-
-conversation_with_summary_model = console_ns.model(
-    "ConversationWithSummary",
-    {
-        "id": fields.String,
-        "status": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_end_user_session_id": fields.String,
-        "from_account_id": fields.String,
-        "from_account_name": fields.String,
-        "name": fields.String,
-        "summary": fields.String(attribute="summary_or_query"),
-        "read_at": TimestampField,
-        "created_at": TimestampField,
-        "updated_at": TimestampField,
-        "annotated": fields.Boolean,
-        "model_config": fields.Nested(simple_model_config_model),
-        "message_count": fields.Integer,
-        "user_feedback_stats": fields.Nested(feedback_stat_model),
-        "admin_feedback_stats": fields.Nested(feedback_stat_model),
-        "status_count": fields.Nested(status_count_model),
-    },
-)
-
-conversation_with_summary_pagination_model = console_ns.model(
-    "ConversationWithSummaryPagination",
-    {
-        "page": fields.Integer,
-        "limit": fields.Integer(attribute="per_page"),
-        "total": fields.Integer,
-        "has_more": fields.Boolean(attribute="has_next"),
-        "data": fields.List(fields.Nested(conversation_with_summary_model), attribute="items"),
-    },
-)
-
-conversation_detail_model = console_ns.model(
-    "ConversationDetail",
-    {
-        "id": fields.String,
-        "status": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account_id": fields.String,
-        "created_at": TimestampField,
-        "updated_at": TimestampField,
-        "annotated": fields.Boolean,
-        "introduction": fields.String,
-        "model_config": fields.Nested(model_config_model),
-        "message_count": fields.Integer,
-        "user_feedback_stats": fields.Nested(feedback_stat_model),
-        "admin_feedback_stats": fields.Nested(feedback_stat_model),
-    },
+register_schema_models(
+    console_ns,
+    CompletionConversationQuery,
+    ChatConversationQuery,
+    ConversationResponse,
+    ConversationPaginationResponse,
+    ConversationMessageDetailResponse,
+    ConversationWithSummaryPaginationResponse,
+    ConversationDetailResponse,
+    ResultResponse,
+    CompletionConversationQuery,
+    ChatConversationQuery,
 )
 
 
@@ -332,17 +89,16 @@ class CompletionConversationApi(Resource):
     @console_ns.doc(description="Get completion conversations with pagination and filtering")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[CompletionConversationQuery.__name__])
-    @console_ns.response(200, "Success", conversation_pagination_model)
+    @console_ns.response(200, "Success", console_ns.models[ConversationPaginationResponse.__name__])
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.COMPLETION)
-    @marshal_with(conversation_pagination_model)
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = CompletionConversationQuery.model_validate(request.args.to_dict(flat=True))
 
         query = sa.select(Conversation).where(
             Conversation.app_id == app_model.id, Conversation.mode == "completion", Conversation.is_deleted.is_(False)
@@ -394,7 +150,9 @@ class CompletionConversationApi(Resource):
 
         conversations = db.paginate(query, page=args.page, per_page=args.limit, error_out=False)
 
-        return conversations
+        return ConversationPaginationResponse.model_validate(conversations, from_attributes=True).model_dump(
+            mode="json"
+        )
 
 
 @console_ns.route("/apps/<uuid:app_id>/completion-conversations/<uuid:conversation_id>")
@@ -402,19 +160,19 @@ class CompletionConversationDetailApi(Resource):
     @console_ns.doc("get_completion_conversation")
     @console_ns.doc(description="Get completion conversation details with messages")
     @console_ns.doc(params={"app_id": "Application ID", "conversation_id": "Conversation ID"})
-    @console_ns.response(200, "Success", conversation_message_detail_model)
+    @console_ns.response(200, "Success", console_ns.models[ConversationMessageDetailResponse.__name__])
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Conversation not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.COMPLETION)
-    @marshal_with(conversation_message_detail_model)
     @edit_permission_required
     def get(self, app_model, conversation_id):
         conversation_id = str(conversation_id)
-
-        return _get_conversation(app_model, conversation_id)
+        return ConversationMessageDetailResponse.model_validate(
+            _get_conversation(app_model, conversation_id), from_attributes=True
+        ).model_dump(mode="json")
 
     @console_ns.doc("delete_completion_conversation")
     @console_ns.doc(description="Delete a completion conversation")
@@ -436,7 +194,7 @@ class CompletionConversationDetailApi(Resource):
         except ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 
-        return {"result": "success"}, 204
+        return ResultResponse(result="success").model_dump(mode="json"), 204
 
 
 @console_ns.route("/apps/<uuid:app_id>/chat-conversations")
@@ -445,17 +203,16 @@ class ChatConversationApi(Resource):
     @console_ns.doc(description="Get chat conversations with pagination, filtering and summary")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[ChatConversationQuery.__name__])
-    @console_ns.response(200, "Success", conversation_with_summary_pagination_model)
+    @console_ns.response(200, "Success", console_ns.models[ConversationWithSummaryPaginationResponse.__name__])
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
-    @marshal_with(conversation_with_summary_pagination_model)
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
-        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ChatConversationQuery.model_validate(request.args.to_dict(flat=True))
 
         subquery = (
             sa.select(Conversation.id.label("conversation_id"), EndUser.session_id.label("from_end_user_session_id"))
@@ -546,7 +303,9 @@ class ChatConversationApi(Resource):
 
         conversations = db.paginate(query, page=args.page, per_page=args.limit, error_out=False)
 
-        return conversations
+        return ConversationWithSummaryPaginationResponse.model_validate(conversations, from_attributes=True).model_dump(
+            mode="json"
+        )
 
 
 @console_ns.route("/apps/<uuid:app_id>/chat-conversations/<uuid:conversation_id>")
@@ -554,19 +313,19 @@ class ChatConversationDetailApi(Resource):
     @console_ns.doc("get_chat_conversation")
     @console_ns.doc(description="Get chat conversation details")
     @console_ns.doc(params={"app_id": "Application ID", "conversation_id": "Conversation ID"})
-    @console_ns.response(200, "Success", conversation_detail_model)
+    @console_ns.response(200, "Success", console_ns.models[ConversationDetailResponse.__name__])
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Conversation not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
-    @marshal_with(conversation_detail_model)
     @edit_permission_required
     def get(self, app_model, conversation_id):
         conversation_id = str(conversation_id)
-
-        return _get_conversation(app_model, conversation_id)
+        return ConversationDetailResponse.model_validate(
+            _get_conversation(app_model, conversation_id), from_attributes=True
+        ).model_dump(mode="json")
 
     @console_ns.doc("delete_chat_conversation")
     @console_ns.doc(description="Delete a chat conversation")
@@ -588,7 +347,7 @@ class ChatConversationDetailApi(Resource):
         except ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 
-        return {"result": "success"}, 204
+        return ResultResponse(result="success").model_dump(mode="json"), 204
 
 
 def _get_conversation(app_model, conversation_id):

api/controllers/console/app/conversation_variables.py

@@ -1,44 +1,86 @@
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Any
+
 from flask import request
-from flask_restx import Resource, fields, marshal_with
-from pydantic import BaseModel, Field
+from flask_restx import Resource
+from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import select
 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
 from extensions.ext_database import db
-from fields.conversation_variable_fields import (
-    conversation_variable_fields,
-    paginated_conversation_variable_fields,
-)
+from fields._value_type_serializer import serialize_value_type
+from fields.base import ResponseModel
 from libs.login import login_required
 from models import ConversationVariable
 from models.model import AppMode
 
-DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
-
 
 class ConversationVariablesQuery(BaseModel):
     conversation_id: str = Field(..., description="Conversation ID to filter variables")
 
 
-console_ns.schema_model(
-    ConversationVariablesQuery.__name__,
-    ConversationVariablesQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
-)
+def _to_timestamp(value: datetime | int | None) -> int | None:
+    if isinstance(value, datetime):
+        return int(value.timestamp())
+    return value
 
-# Register models for flask_restx to avoid dict type issues in Swagger
-# Register base model first
-conversation_variable_model = console_ns.model("ConversationVariable", conversation_variable_fields)
 
-# For nested models, need to replace nested dict with registered model
-paginated_conversation_variable_fields_copy = paginated_conversation_variable_fields.copy()
-paginated_conversation_variable_fields_copy["data"] = fields.List(
-    fields.Nested(conversation_variable_model), attribute="data"
-)
-paginated_conversation_variable_model = console_ns.model(
-    "PaginatedConversationVariable", paginated_conversation_variable_fields_copy
+class ConversationVariableResponse(ResponseModel):
+    id: str
+    name: str
+    value_type: str
+    value: str | None = None
+    description: str | None = None
+    created_at: int | None = None
+    updated_at: int | None = None
+
+    @field_validator("value_type", mode="before")
+    @classmethod
+    def _normalize_value_type(cls, value: Any) -> str:
+        exposed_type = getattr(value, "exposed_type", None)
+        if callable(exposed_type):
+            return str(exposed_type())
+        if isinstance(value, str):
+            return value
+        try:
+            return serialize_value_type(value)
+        except Exception:
+            return serialize_value_type({"value_type": value})
+
+    @field_validator("value", mode="before")
+    @classmethod
+    def _normalize_value(cls, value: Any | None) -> str | None:
+        if value is None:
+            return None
+        if isinstance(value, str):
+            return value
+        return str(value)
+
+    @field_validator("created_at", "updated_at", mode="before")
+    @classmethod
+    def _normalize_timestamp(cls, value: datetime | int | None) -> int | None:
+        return _to_timestamp(value)
+
+
+class PaginatedConversationVariableResponse(ResponseModel):
+    page: int
+    limit: int
+    total: int
+    has_more: bool
+    data: list[ConversationVariableResponse]
+
+
+register_schema_models(
+    console_ns,
+    ConversationVariablesQuery,
+    ConversationVariableResponse,
+    PaginatedConversationVariableResponse,
 )
 
 
@@ -48,14 +90,17 @@ class ConversationVariablesApi(Resource):
     @console_ns.doc(description="Get conversation variables for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[ConversationVariablesQuery.__name__])
-    @console_ns.response(200, "Conversation variables retrieved successfully", paginated_conversation_variable_model)
+    @console_ns.response(
+        200,
+        "Conversation variables retrieved successfully",
+        console_ns.models[PaginatedConversationVariableResponse.__name__],
+    )
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.ADVANCED_CHAT)
-    @marshal_with(paginated_conversation_variable_model)
     def get(self, app_model):
-        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = ConversationVariablesQuery.model_validate(request.args.to_dict(flat=True))
 
         stmt = (
             select(ConversationVariable)
@@ -72,17 +117,22 @@ class ConversationVariablesApi(Resource):
         with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
             rows = session.scalars(stmt).all()
 
-        return {
-            "page": page,
-            "limit": page_size,
-            "total": len(rows),
-            "has_more": False,
-            "data": [
-                {
-                    "created_at": row.created_at,
-                    "updated_at": row.updated_at,
-                    **row.to_variable().model_dump(),
-                }
-                for row in rows
-            ],
-        }
+        response = PaginatedConversationVariableResponse.model_validate(
+            {
+                "page": page,
+                "limit": page_size,
+                "total": len(rows),
+                "has_more": False,
+                "data": [
+                    ConversationVariableResponse.model_validate(
+                        {
+                            "created_at": row.created_at,
+                            "updated_at": row.updated_at,
+                            **row.to_variable().model_dump(),
+                        }
+                    )
+                    for row in rows
+                ],
+            }
+        )
+        return response.model_dump(mode="json")

api/controllers/console/app/generator.py

@@ -1,9 +1,9 @@
 from collections.abc import Sequence
 
 from flask_restx import Resource
-from graphon.model_runtime.errors.invoke import InvokeError
 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 +20,12 @@ 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")
 
 
-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)
+register_enum_models(console_ns, LLMMode)
+register_schema_models(
+    console_ns,
+    RuleGeneratePayload,
+    RuleCodeGeneratePayload,
+    RuleStructuredOutputPayload,
+    InstructionGeneratePayload,
+    InstructionTemplatePayload,
+    ModelConfig,
+)
 
 
 @console_ns.route("/rule-generate")

api/controllers/console/app/mcp_server.py

@@ -18,37 +18,37 @@ from models.enums import AppMCPServerStatus
 from models.model import AppMCPServer
 
 
-def _to_timestamp(value: datetime | int | None) -> int | None:
-    if isinstance(value, datetime):
-        return int(value.timestamp())
-    return value
-
-
 class MCPServerCreatePayload(BaseModel):
     description: str | None = Field(default=None, description="Server description")
-    parameters: dict = Field(..., description="Server parameters configuration")
+    parameters: dict[str, Any] = Field(..., description="Server parameters configuration")
 
 
 class MCPServerUpdatePayload(BaseModel):
     id: str = Field(..., description="Server ID")
     description: str | None = Field(default=None, description="Server description")
-    parameters: dict = Field(..., description="Server parameters configuration")
+    parameters: dict[str, Any] = Field(..., description="Server parameters configuration")
     status: str | None = Field(default=None, description="Server status")
 
 
+def _to_timestamp(value: datetime | int | None) -> int | None:
+    if isinstance(value, datetime):
+        return int(value.timestamp())
+    return value
+
+
 class AppMCPServerResponse(ResponseModel):
     id: str
     name: str
     server_code: str
     description: str
-    status: str
+    status: AppMCPServerStatus
     parameters: dict[str, Any] | list[Any] | str
     created_at: int | None = None
     updated_at: int | None = None
 
     @field_validator("parameters", mode="before")
     @classmethod
-    def _parse_json_string(cls, value: Any) -> Any:
+    def _normalize_parameters(cls, value: Any) -> Any:
         if isinstance(value, str):
             try:
                 return json.loads(value)
@@ -70,7 +70,9 @@ class AppMCPServerController(Resource):
     @console_ns.doc("get_app_mcp_server")
     @console_ns.doc(description="Get MCP server configuration for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Server configuration", console_ns.models[AppMCPServerResponse.__name__])
+    @console_ns.response(
+        200, "MCP server configuration retrieved successfully", console_ns.models[AppMCPServerResponse.__name__]
+    )
     @login_required
     @account_initialization_required
     @setup_required
@@ -85,7 +87,9 @@ class AppMCPServerController(Resource):
     @console_ns.doc(description="Create MCP server configuration for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[MCPServerCreatePayload.__name__])
-    @console_ns.response(200, "Server created", console_ns.models[AppMCPServerResponse.__name__])
+    @console_ns.response(
+        201, "MCP server configuration created successfully", console_ns.models[AppMCPServerResponse.__name__]
+    )
     @console_ns.response(403, "Insufficient permissions")
     @account_initialization_required
     @get_app_model
@@ -111,13 +115,15 @@ class AppMCPServerController(Resource):
         )
         db.session.add(server)
         db.session.commit()
-        return AppMCPServerResponse.model_validate(server, from_attributes=True).model_dump(mode="json")
+        return AppMCPServerResponse.model_validate(server, from_attributes=True).model_dump(mode="json"), 201
 
     @console_ns.doc("update_app_mcp_server")
     @console_ns.doc(description="Update MCP server configuration for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[MCPServerUpdatePayload.__name__])
-    @console_ns.response(200, "Server updated", console_ns.models[AppMCPServerResponse.__name__])
+    @console_ns.response(
+        200, "MCP server configuration updated successfully", console_ns.models[AppMCPServerResponse.__name__]
+    )
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Server not found")
     @get_app_model
@@ -154,7 +160,7 @@ class AppMCPServerRefreshController(Resource):
     @console_ns.doc("refresh_app_mcp_server")
     @console_ns.doc(description="Refresh MCP server configuration and regenerate server code")
     @console_ns.doc(params={"server_id": "Server ID"})
-    @console_ns.response(200, "Server refreshed", console_ns.models[AppMCPServerResponse.__name__])
+    @console_ns.response(200, "MCP server refreshed successfully", console_ns.models[AppMCPServerResponse.__name__])
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Server not found")
     @setup_required

api/controllers/console/app/message.py

@@ -1,9 +1,9 @@
 import logging
+from datetime import datetime
 from typing import Literal
 
 from flask import request
-from flask_restx import Resource, fields, marshal_with
-from graphon.model_runtime.errors.invoke import InvokeError
+from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
 from sqlalchemy import exists, func, select
 from werkzeug.exceptions import InternalServerError, NotFound
@@ -25,10 +25,22 @@ from controllers.console.wraps import (
     setup_required,
 )
 from core.app.entities.app_invoke_entities import InvokeFrom
+from core.entities.execution_extra_content import ExecutionExtraContentDomainModel
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from extensions.ext_database import db
-from fields.raws import FilesContainedField
-from libs.helper import TimestampField, uuid_value
+from fields.base import ResponseModel
+from fields.conversation_fields import (
+    AgentThought,
+    ConversationAnnotation,
+    ConversationAnnotationHitHistory,
+    Feedback,
+    JSONValue,
+    MessageFile,
+    format_files_contained,
+    to_timestamp,
+)
+from graphon.model_runtime.errors.invoke import InvokeError
+from libs.helper import uuid_value
 from libs.infinite_scroll_pagination import InfiniteScrollPagination
 from libs.login import current_account_with_tenant, login_required
 from models.enums import FeedbackFromSource, FeedbackRating
@@ -98,6 +110,51 @@ class SuggestedQuestionsResponse(BaseModel):
     data: list[str] = Field(description="Suggested question")
 
 
+class MessageDetailResponse(ResponseModel):
+    id: str
+    conversation_id: str
+    inputs: dict[str, JSONValue]
+    query: str
+    message: JSONValue | None = None
+    message_tokens: int | None = None
+    answer: str = Field(validation_alias="re_sign_file_url_answer")
+    answer_tokens: int | None = None
+    provider_response_latency: float | None = None
+    from_source: str
+    from_end_user_id: str | None = None
+    from_account_id: str | None = None
+    feedbacks: list[Feedback] = Field(default_factory=list)
+    workflow_run_id: str | None = None
+    annotation: ConversationAnnotation | None = None
+    annotation_hit_history: ConversationAnnotationHitHistory | None = None
+    created_at: int | None = None
+    agent_thoughts: list[AgentThought] = Field(default_factory=list)
+    message_files: list[MessageFile] = Field(default_factory=list)
+    extra_contents: list[ExecutionExtraContentDomainModel] = Field(default_factory=list)
+    metadata: JSONValue | None = Field(default=None, validation_alias="message_metadata_dict")
+    status: str
+    error: str | None = None
+    parent_message_id: str | None = None
+
+    @field_validator("inputs", mode="before")
+    @classmethod
+    def _normalize_inputs(cls, value: JSONValue) -> JSONValue:
+        return format_files_contained(value)
+
+    @field_validator("created_at", mode="before")
+    @classmethod
+    def _normalize_created_at(cls, value: datetime | int | None) -> int | None:
+        if isinstance(value, datetime):
+            return to_timestamp(value)
+        return value
+
+
+class MessageInfiniteScrollPaginationResponse(ResponseModel):
+    limit: int
+    has_more: bool
+    data: list[MessageDetailResponse]
+
+
 register_schema_models(
     console_ns,
     ChatMessagesQuery,
@@ -105,124 +162,8 @@ register_schema_models(
     FeedbackExportQuery,
     AnnotationCountResponse,
     SuggestedQuestionsResponse,
-)
-
-# 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",
-    {
-        "id": fields.String,
-        "name": fields.String,
-        "email": fields.String,
-    },
-)
-
-message_file_model = console_ns.model(
-    "MessageFile",
-    {
-        "id": fields.String,
-        "filename": fields.String,
-        "type": fields.String,
-        "url": fields.String,
-        "mime_type": fields.String,
-        "size": fields.Integer,
-        "transfer_method": fields.String,
-        "belongs_to": fields.String(default="user"),
-        "upload_file_id": fields.String(default=None),
-    },
-)
-
-agent_thought_model = console_ns.model(
-    "AgentThought",
-    {
-        "id": fields.String,
-        "chain_id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "thought": fields.String,
-        "tool": fields.String,
-        "tool_labels": fields.Raw,
-        "tool_input": fields.String,
-        "created_at": TimestampField,
-        "observation": fields.String,
-        "files": fields.List(fields.String),
-    },
-)
-
-# Models that depend on simple_account_model
-feedback_model = console_ns.model(
-    "Feedback",
-    {
-        "rating": fields.String,
-        "content": fields.String,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account": fields.Nested(simple_account_model, allow_null=True),
-    },
-)
-
-annotation_model = console_ns.model(
-    "Annotation",
-    {
-        "id": fields.String,
-        "question": fields.String,
-        "content": fields.String,
-        "account": fields.Nested(simple_account_model, allow_null=True),
-        "created_at": TimestampField,
-    },
-)
-
-annotation_hit_history_model = console_ns.model(
-    "AnnotationHitHistory",
-    {
-        "annotation_id": fields.String(attribute="id"),
-        "annotation_create_account": fields.Nested(simple_account_model, allow_null=True),
-        "created_at": TimestampField,
-    },
-)
-
-# Message detail model that depends on multiple models
-message_detail_model = console_ns.model(
-    "MessageDetail",
-    {
-        "id": fields.String,
-        "conversation_id": fields.String,
-        "inputs": FilesContainedField,
-        "query": fields.String,
-        "message": fields.Raw,
-        "message_tokens": fields.Integer,
-        "answer": fields.String(attribute="re_sign_file_url_answer"),
-        "answer_tokens": fields.Integer,
-        "provider_response_latency": fields.Float,
-        "from_source": fields.String,
-        "from_end_user_id": fields.String,
-        "from_account_id": fields.String,
-        "feedbacks": fields.List(fields.Nested(feedback_model)),
-        "workflow_run_id": fields.String,
-        "annotation": fields.Nested(annotation_model, allow_null=True),
-        "annotation_hit_history": fields.Nested(annotation_hit_history_model, allow_null=True),
-        "created_at": TimestampField,
-        "agent_thoughts": fields.List(fields.Nested(agent_thought_model)),
-        "message_files": fields.List(fields.Nested(message_file_model)),
-        "extra_contents": fields.List(fields.Raw),
-        "metadata": fields.Raw(attribute="message_metadata_dict"),
-        "status": fields.String,
-        "error": fields.String,
-        "parent_message_id": fields.String,
-    },
-)
-
-# Message infinite scroll pagination model
-message_infinite_scroll_pagination_model = console_ns.model(
-    "MessageInfiniteScrollPagination",
-    {
-        "limit": fields.Integer,
-        "has_more": fields.Boolean,
-        "data": fields.List(fields.Nested(message_detail_model)),
-    },
+    MessageDetailResponse,
+    MessageInfiniteScrollPaginationResponse,
 )
 
 
@@ -232,13 +173,12 @@ class ChatMessageListApi(Resource):
     @console_ns.doc(description="Get chat messages for a conversation with pagination")
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.expect(console_ns.models[ChatMessagesQuery.__name__])
-    @console_ns.response(200, "Success", message_infinite_scroll_pagination_model)
+    @console_ns.response(200, "Success", console_ns.models[MessageInfiniteScrollPaginationResponse.__name__])
     @console_ns.response(404, "Conversation not found")
     @login_required
     @account_initialization_required
     @setup_required
-    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT, AppMode.AGENT])
-    @marshal_with(message_infinite_scroll_pagination_model)
+    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def get(self, app_model):
         args = ChatMessagesQuery.model_validate(request.args.to_dict())
@@ -298,7 +238,10 @@ class ChatMessageListApi(Resource):
         history_messages = list(reversed(history_messages))
         attach_message_extra_contents(history_messages)
 
-        return InfiniteScrollPagination(data=history_messages, limit=args.limit, has_more=has_more)
+        return MessageInfiniteScrollPaginationResponse.model_validate(
+            InfiniteScrollPagination(data=history_messages, limit=args.limit, has_more=has_more),
+            from_attributes=True,
+        ).model_dump(mode="json")
 
 
 @console_ns.route("/apps/<uuid:app_id>/feedbacks")
@@ -393,7 +336,7 @@ class MessageSuggestedQuestionApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
     def get(self, app_model, message_id):
         current_user, _ = current_account_with_tenant()
         message_id = str(message_id)
@@ -468,13 +411,12 @@ class MessageApi(Resource):
     @console_ns.doc("get_message")
     @console_ns.doc(description="Get message details by ID")
     @console_ns.doc(params={"app_id": "Application ID", "message_id": "Message ID"})
-    @console_ns.response(200, "Message retrieved successfully", message_detail_model)
+    @console_ns.response(200, "Message retrieved successfully", console_ns.models[MessageDetailResponse.__name__])
     @console_ns.response(404, "Message not found")
     @get_app_model
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(message_detail_model)
     def get(self, app_model, message_id: str):
         message_id = str(message_id)
 
@@ -486,4 +428,4 @@ class MessageApi(Resource):
             raise NotFound("Message Not Exists.")
 
         attach_message_extra_contents([message])
-        return message
+        return MessageDetailResponse.model_validate(message, from_attributes=True).model_dump(mode="json")

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")
@@ -23,13 +23,7 @@ class TraceConfigPayload(BaseModel):
     tracing_config: dict[str, Any] = Field(..., description="Tracing configuration data")
 
 
-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)
-)
+register_schema_models(console_ns, TraceProviderQuery, TraceConfigPayload)
 
 
 @console_ns.route("/apps/<uuid:app_id>/trace-config")
@@ -49,11 +43,11 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id):
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+    def get(self, app_id: UUID):
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))
 
         try:
-            trace_config = OpsService.get_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
+            trace_config = OpsService.get_tracing_app_config(app_id=str(app_id), tracing_provider=args.tracing_provider)
             if not trace_config:
                 return {"has_not_configured": True}
             return trace_config
@@ -71,13 +65,13 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def post(self, app_id):
+    def post(self, app_id: UUID):
         """Create a new trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.create_tracing_app_config(
-                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=str(app_id), tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigIsExist()
@@ -96,13 +90,13 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def patch(self, app_id):
+    def patch(self, app_id: UUID):
         """Update an existing trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.update_tracing_app_config(
-                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=str(app_id), tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigNotExist()
@@ -119,12 +113,12 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def delete(self, app_id):
+    def delete(self, app_id: UUID):
         """Delete an existing trace app configuration"""
-        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))
 
         try:
-            result = OpsService.delete_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
+            result = OpsService.delete_tracing_app_config(app_id=str(app_id), tracing_provider=args.tracing_provider)
             if not result:
                 raise TracingConfigNotExist()
             return {"result": "success"}, 204

api/controllers/console/app/statistic.py

@@ -5,6 +5,7 @@ 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
@@ -15,8 +16,6 @@ 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)")
@@ -30,10 +29,7 @@ class StatisticTimeRangeQuery(BaseModel):
         return value
 
 
-console_ns.schema_model(
-    StatisticTimeRangeQuery.__name__,
-    StatisticTimeRangeQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
-)
+register_schema_models(console_ns, StatisticTimeRangeQuery)
 
 
 @console_ns.route("/apps/<uuid:app_id>/statistics/daily-messages")
@@ -54,7 +50,7 @@ class DailyMessageStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -111,7 +107,7 @@ class DailyConversationStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -167,7 +163,7 @@ class DailyTerminalsStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -224,7 +220,7 @@ class DailyTokenCostStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -284,7 +280,7 @@ class AverageSessionInteractionStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("c.created_at")
         sql_query = f"""SELECT
@@ -360,7 +356,7 @@ class UserSatisfactionRateStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("m.created_at")
         sql_query = f"""SELECT
@@ -426,7 +422,7 @@ class AverageResponseTimeStatistic(Resource):
     def get(self, app_model):
         account, _ = current_account_with_tenant()
 
-        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT
@@ -482,7 +478,7 @@ 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))  # type: ignore
+        args = StatisticTimeRangeQuery.model_validate(request.args.to_dict(flat=True))
 
         converted_created_at = convert_datetime_to_date("created_at")
         sql_query = f"""SELECT

api/controllers/console/app/workflow.py

@@ -4,20 +4,16 @@ from collections.abc import Sequence
 from typing import Any
 
 from flask import abort, request
-from flask_restx import Resource, fields, marshal_with
-from graphon.enums import NodeType
-from graphon.file import File
-from graphon.graph_engine.manager import GraphEngineManager
-from graphon.model_runtime.utils.encoders import jsonable_encoder
+from flask_restx import Resource, fields, marshal, marshal_with
 from pydantic import BaseModel, Field, ValidationError, field_validator
 from sqlalchemy.orm import sessionmaker
 from werkzeug.exceptions import BadRequest, Forbidden, InternalServerError, NotFound
 
 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
@@ -39,7 +35,14 @@ from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 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
+from graphon.graph_engine.manager import GraphEngineManager
+from graphon.model_runtime.utils.encoders import jsonable_encoder
 from libs import helper
 from libs.datetime_utils import naive_utc_now
 from libs.helper import TimestampField, uuid_value
@@ -47,16 +50,20 @@ from libs.login import current_account_with_tenant, login_required
 from models import App
 from models.model import AppMode
 from models.workflow import Workflow
+from repositories.workflow_collaboration_repository import WORKFLOW_ONLINE_USERS_PREFIX
 from services.app_generate_service import AppGenerateService
 from services.errors.app import IsDraftWorkflowError, WorkflowHashNotEqualError, WorkflowNotFoundError
 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
 
 # Register models for flask_restx to avoid dict type issues in Swagger
 # Register in dependency order: base models first, then dependent models
@@ -150,6 +157,19 @@ class ConvertToWorkflowPayload(BaseModel):
     icon_background: str | None = None
 
 
+class WorkflowFeaturesPayload(BaseModel):
+    features: dict[str, Any] = Field(..., description="Workflow feature configuration")
+
+
+class WorkflowOnlineUsersPayload(BaseModel):
+    app_ids: list[str] = Field(default_factory=list, description="App IDs")
+
+    @field_validator("app_ids")
+    @classmethod
+    def normalize_app_ids(cls, app_ids: list[str]) -> list[str]:
+        return list(dict.fromkeys(app_id.strip() for app_id in app_ids if app_id.strip()))
+
+
 class DraftWorkflowTriggerRunPayload(BaseModel):
     node_id: str
 
@@ -158,23 +178,25 @@ class DraftWorkflowTriggerRunAllPayload(BaseModel):
     node_ids: list[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(SyncDraftWorkflowPayload)
-reg(AdvancedChatWorkflowRunPayload)
-reg(IterationNodeRunPayload)
-reg(LoopNodeRunPayload)
-reg(DraftWorkflowRunPayload)
-reg(DraftWorkflowNodeRunPayload)
-reg(PublishWorkflowPayload)
-reg(DefaultBlockConfigQuery)
-reg(ConvertToWorkflowPayload)
-reg(WorkflowListQuery)
-reg(WorkflowUpdatePayload)
-reg(DraftWorkflowTriggerRunPayload)
-reg(DraftWorkflowTriggerRunAllPayload)
+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)
 
 
 # TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
@@ -206,7 +228,7 @@ class DraftWorkflowApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @marshal_with(workflow_model)
     @edit_permission_required
     def get(self, app_model: App):
@@ -226,7 +248,7 @@ class DraftWorkflowApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @console_ns.doc("sync_draft_workflow")
     @console_ns.doc(description="Sync draft workflow configuration")
     @console_ns.expect(console_ns.models[SyncDraftWorkflowPayload.__name__])
@@ -310,7 +332,7 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def post(self, app_model: App):
         """
@@ -356,7 +378,7 @@ class AdvancedChatDraftRunIterationNodeApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -432,7 +454,7 @@ class AdvancedChatDraftRunLoopNodeApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -520,9 +542,12 @@ class HumanInputDeliveryTestPayload(BaseModel):
     )
 
 
-reg(HumanInputFormPreviewPayload)
-reg(HumanInputFormSubmitPayload)
-reg(HumanInputDeliveryTestPayload)
+register_schema_models(
+    console_ns,
+    HumanInputFormPreviewPayload,
+    HumanInputFormSubmitPayload,
+    HumanInputDeliveryTestPayload,
+)
 
 
 @console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/human-input/nodes/<string:node_id>/form/preview")
@@ -534,7 +559,7 @@ class AdvancedChatDraftHumanInputFormPreviewApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -563,7 +588,7 @@ class AdvancedChatDraftHumanInputFormRunApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT])
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -718,7 +743,7 @@ class WorkflowTaskStopApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def post(self, app_model: App, task_id: str):
         """
@@ -740,14 +765,17 @@ 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", workflow_run_node_execution_model)
+    @console_ns.response(
+        200,
+        "Node run started successfully",
+        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
+    )
     @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, AppMode.AGENT])
-    @marshal_with(workflow_run_node_execution_model)
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -779,7 +807,9 @@ class DraftWorkflowNodeRunApi(Resource):
             files=files,
         )
 
-        return workflow_node_execution
+        return WorkflowRunNodeExecutionResponse.model_validate(
+            workflow_node_execution, from_attributes=True
+        ).model_dump(mode="json")
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflows/publish")
@@ -792,7 +822,7 @@ class PublishedWorkflowApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @marshal_with(workflow_model)
     @edit_permission_required
     def get(self, app_model: App):
@@ -810,7 +840,7 @@ class PublishedWorkflowApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def post(self, app_model: App):
         """
@@ -854,7 +884,7 @@ class DefaultBlockConfigsApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def get(self, app_model: App):
         """
@@ -876,13 +906,13 @@ class DefaultBlockConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def get(self, app_model: App, block_type: str):
         """
         Get default block config
         """
-        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = DefaultBlockConfigQuery.model_validate(request.args.to_dict(flat=True))
 
         filters = None
         if args.q:
@@ -931,6 +961,32 @@ class ConvertToWorkflowApi(Resource):
         }
 
 
+@console_ns.route("/apps/<uuid:app_id>/workflows/draft/features")
+class WorkflowFeaturesApi(Resource):
+    """Update draft workflow features."""
+
+    @console_ns.expect(console_ns.models[WorkflowFeaturesPayload.__name__])
+    @console_ns.doc("update_workflow_features")
+    @console_ns.doc(description="Update draft workflow features")
+    @console_ns.doc(params={"app_id": "Application ID"})
+    @console_ns.response(200, "Workflow features updated successfully")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @edit_permission_required
+    def post(self, app_model: App):
+        current_user, _ = current_account_with_tenant()
+
+        args = WorkflowFeaturesPayload.model_validate(console_ns.payload or {})
+        features = args.features
+
+        workflow_service = WorkflowService()
+        workflow_service.update_draft_workflow_features(app_model=app_model, features=features, account=current_user)
+
+        return {"result": "success"}
+
+
 @console_ns.route("/apps/<uuid:app_id>/workflows")
 class PublishedAllWorkflowApi(Resource):
     @console_ns.expect(console_ns.models[WorkflowListQuery.__name__])
@@ -941,8 +997,7 @@ class PublishedAllWorkflowApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
-    @marshal_with(workflow_pagination_model)
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def get(self, app_model: App):
         """
@@ -950,7 +1005,7 @@ class PublishedAllWorkflowApi(Resource):
         """
         current_user, _ = current_account_with_tenant()
 
-        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
+        args = WorkflowListQuery.model_validate(request.args.to_dict(flat=True))
         page = args.page
         limit = args.limit
         user_id = args.user_id
@@ -970,9 +1025,10 @@ class PublishedAllWorkflowApi(Resource):
                 user_id=user_id,
                 named_only=named_only,
             )
+            serialized_workflows = marshal(workflows, workflow_fields_copy)
 
             return {
-                "items": workflows,
+                "items": serialized_workflows,
                 "page": page,
                 "limit": limit,
                 "has_more": has_more,
@@ -990,7 +1046,7 @@ class DraftWorkflowRestoreApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def post(self, app_model: App, workflow_id: str):
         current_user, _ = current_account_with_tenant()
@@ -1028,7 +1084,7 @@ class WorkflowByIdApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @marshal_with(workflow_model)
     @edit_permission_required
     def patch(self, app_model: App, workflow_id: str):
@@ -1068,7 +1124,7 @@ class WorkflowByIdApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW, AppMode.AGENT])
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     @edit_permission_required
     def delete(self, app_model: App, workflow_id: str):
         """
@@ -1097,14 +1153,17 @@ 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", workflow_run_node_execution_model)
+    @console_ns.response(
+        200,
+        "Node last run retrieved successfully",
+        console_ns.models[WorkflowRunNodeExecutionResponse.__name__],
+    )
     @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, AppMode.AGENT])
-    @marshal_with(workflow_run_node_execution_model)
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
     def get(self, app_model: App, node_id: str):
         srv = WorkflowService()
         workflow = srv.get_draft_workflow(app_model)
@@ -1117,7 +1176,7 @@ class DraftWorkflowNodeLastRunApi(Resource):
         )
         if node_exec is None:
             raise NotFound("last run not found")
-        return node_exec
+        return WorkflowRunNodeExecutionResponse.model_validate(node_exec, from_attributes=True).model_dump(mode="json")
 
 
 @console_ns.route("/apps/<uuid:app_id>/workflows/draft/trigger/run")
@@ -1340,3 +1399,73 @@ class DraftWorkflowTriggerRunAllApi(Resource):
                     "status": "error",
                 }
             ), 400
+
+
+@console_ns.route("/apps/workflows/online-users")
+class WorkflowOnlineUsersApi(Resource):
+    @console_ns.expect(console_ns.models[WorkflowOnlineUsersPayload.__name__])
+    @console_ns.doc("get_workflow_online_users")
+    @console_ns.doc(description="Get workflow online users")
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(online_user_list_fields)
+    def post(self):
+        args = WorkflowOnlineUsersPayload.model_validate(console_ns.payload or {})
+
+        app_ids = args.app_ids
+        if len(app_ids) > MAX_WORKFLOW_ONLINE_USERS_REQUEST_IDS:
+            raise BadRequest(f"Maximum {MAX_WORKFLOW_ONLINE_USERS_REQUEST_IDS} app_ids are allowed per request.")
+
+        if not app_ids:
+            return {"data": []}
+
+        _, current_tenant_id = current_account_with_tenant()
+        workflow_service = WorkflowService()
+        accessible_app_ids = workflow_service.get_accessible_app_ids(app_ids, current_tenant_id)
+        ordered_accessible_app_ids = [app_id for app_id in app_ids if app_id in accessible_app_ids]
+
+        users_json_by_app_id: dict[str, Any] = {}
+        for start_index in range(0, len(ordered_accessible_app_ids), WORKFLOW_ONLINE_USERS_REDIS_BATCH_SIZE):
+            app_id_batch = ordered_accessible_app_ids[
+                start_index : start_index + WORKFLOW_ONLINE_USERS_REDIS_BATCH_SIZE
+            ]
+            pipe = redis_client.pipeline(transaction=False)
+            for app_id in app_id_batch:
+                pipe.hgetall(f"{WORKFLOW_ONLINE_USERS_PREFIX}{app_id}")
+
+            users_json_batch = pipe.execute()
+            for app_id, users_json in zip(app_id_batch, users_json_batch):
+                users_json_by_app_id[app_id] = users_json
+
+        results = []
+        for app_id in ordered_accessible_app_ids:
+            users_json = users_json_by_app_id.get(app_id, {})
+
+            users = []
+            for _, user_info_json in users_json.items():
+                try:
+                    user_info = json.loads(user_info_json)
+                except Exception:
+                    continue
+
+                if not isinstance(user_info, dict):
+                    continue
+
+                avatar = user_info.get("avatar")
+                if isinstance(avatar, str) and avatar and not avatar.startswith(("http://", "https://")):
+                    try:
+                        user_info["avatar"] = file_helpers.get_signed_file_url(avatar)
+                    except Exception as exc:
+                        logger.warning(
+                            "Failed to sign workflow online user avatar; using original value. "
+                            "app_id=%s avatar=%s error=%s",
+                            app_id,
+                            avatar,
+                            exc,
+                        )
+
+                users.append(user_info)
+            results.append({"app_id": app_id, "users": users})
+
+        return {"data": results}