Merge branch 'main' into copilot/fix-css-issue

Signed-off-by: kenwoodjw <blackxin55+@gmail.com>

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

@@ -367,7 +367,7 @@ 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/frontend-testing/SKILL.md

@@ -200,7 +200,7 @@ 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.
@@ -325,12 +325,12 @@ 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
 ```
 
@@ -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`
@@ -330,7 +328,7 @@ 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
@@ -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?

.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 }}
@@ -105,7 +105,7 @@ jobs:
         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/**
@@ -48,7 +48,7 @@ jobs:
       - 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 +58,7 @@ 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'
@@ -123,4 +123,4 @@ jobs:
           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@v1
 
       - 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@v1
         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@98e3b2c9eab4f4f98a95c0c0a3ea5e5e672fd2a8 # v3.10.0
+
+      - name: Validate Docker image
+        uses: docker/build-push-action@5cd29d66b4a8d8e6f4d5dfe2e9329f0b1d446289 # v6.18.0
+        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"
@@ -40,7 +40,7 @@ jobs:
           cp 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"
@@ -94,7 +94,7 @@ jobs:
           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

@@ -14,40 +14,69 @@ 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 Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
+      - name: Set up Depot CLI
+        uses: depot/setup-action@v1
 
       - name: Build Docker Image
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        uses: depot/build-push-action@v1
         with:
+          project: ${{ vars.DEPOT_PROJECT_ID }}
           push: false
           context: ${{ matrix.context }}
           file: ${{ matrix.file }}
           platforms: ${{ matrix.platform }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+
+  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:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@98e3b2c9eab4f4f98a95c0c0a3ea5e5e672fd2a8 # v3.10.0
+
+      - name: Build Docker Image
+        uses: docker/build-push-action@5cd29d66b4a8d8e6f4d5dfe2e9329f0b1d446289 # v6.18.0
+        with:
+          push: false
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
+          platforms: linux/amd64

.github/workflows/labeler.yml

@@ -7,7 +7,7 @@ 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
         with:

.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 }}
@@ -141,7 +141,7 @@ 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."
@@ -154,7 +154,7 @@ 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:
@@ -201,7 +201,7 @@ 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."
@@ -214,7 +214,7 @@ 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:
@@ -260,7 +260,7 @@ 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."
@@ -273,7 +273,7 @@ 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:
@@ -325,7 +325,7 @@ 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."
@@ -338,7 +338,7 @@ 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:
@@ -384,7 +384,7 @@ 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."
@@ -397,7 +397,7 @@ 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 +76,11 @@ 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.';
-
-            await github.rest.issues.createComment({
-              issue_number: prNumber,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body,
-            });
+            if (diff.trim()) {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>',
+              });
+            }

.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
 

.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
 

.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
@@ -73,7 +73,7 @@ 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: |
             web/**
@@ -95,7 +95,7 @@ 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: .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 }}
@@ -110,6 +110,8 @@ jobs:
       - 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
@@ -124,14 +126,14 @@ 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: .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
@@ -142,7 +144,7 @@ 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

@@ -18,7 +18,7 @@ concurrency:
 jobs:
   build:
     name: unit test for Node.js SDK
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     defaults:
       run:
@@ -30,7 +30,7 @@ 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@567fe954a4527e81f132d87d1bdbcc94f7737434 # v1.0.107
         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 }}
@@ -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

.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 }}
@@ -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

.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

@@ -237,6 +237,10 @@ scripts/stress-test/reports/
 .playwright-mcp/
 .serena/
 
+# vitest browser mode attachments (failure screenshots, traces, etc.)
+.vitest-attachments/
+**/__screenshots__/
+
 # settings
 *.local.json
 *.local.md

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
 

README.md

@@ -139,19 +139,6 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 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.
-
 ### Metrics Monitoring with Grafana
 
 Import the dashboard to Grafana, using Dify's PostgreSQL database as data source, to monitor metrics in granularity of apps, tenants, messages, and more.
@@ -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

@@ -659,6 +659,11 @@ 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}
 
@@ -709,22 +714,6 @@ 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/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/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"))
 
 

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/configs/feature/__init__.py

@@ -287,6 +287,27 @@ class MarketplaceConfig(BaseSettings):
     )
 
 
+class CreatorsPlatformConfig(BaseSettings):
+    """
+    Configuration for Creators Platform integration
+    """
+
+    CREATORS_PLATFORM_FEATURES_ENABLED: bool = Field(
+        description="Enable or disable Creators Platform features",
+        default=True,
+    )
+
+    CREATORS_PLATFORM_API_URL: HttpUrl = Field(
+        description="Creators Platform API URL",
+        default=HttpUrl("https://creators.dify.ai"),
+    )
+
+    CREATORS_PLATFORM_OAUTH_CLIENT_ID: str = Field(
+        description="OAuth client ID for Creators Platform integration",
+        default="",
+    )
+
+
 class EndpointConfig(BaseSettings):
     """
     Configuration for various application endpoints and URLs
@@ -1379,6 +1400,7 @@ class FeatureConfig(
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
+    CreatorsPlatformConfig,
     TriggerConfig,
     AsyncWorkflowConfig,
     PluginConfig,

api/constants/dsl_version.py

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

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/console/app/app.py

@@ -129,6 +129,7 @@ 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")
 
 
@@ -691,6 +692,32 @@ 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")
@@ -729,7 +756,12 @@ 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")
 

api/controllers/console/app/conversation_variables.py

@@ -45,7 +45,7 @@ class ConversationVariableResponse(ResponseModel):
     def _normalize_value_type(cls, value: Any) -> str:
         exposed_type = getattr(value, "exposed_type", None)
         if callable(exposed_type):
-            return str(exposed_type().value)
+            return str(exposed_type())
         if isinstance(value, str):
             return value
         try:

api/controllers/console/app/workflow_draft_variable.py

@@ -102,7 +102,7 @@ def _serialize_var_value(variable: WorkflowDraftVariable):
 
 def _serialize_variable_type(workflow_draft_var: WorkflowDraftVariable) -> str:
     value_type = workflow_draft_var.value_type
-    return value_type.exposed_type().value
+    return str(value_type.exposed_type())
 
 
 class FullContentDict(TypedDict):
@@ -122,7 +122,7 @@ def _serialize_full_content(variable: WorkflowDraftVariable) -> FullContentDict
 
     result: FullContentDict = {
         "size_bytes": variable_file.size,
-        "value_type": variable_file.value_type.exposed_type().value,
+        "value_type": str(variable_file.value_type.exposed_type()),
         "length": variable_file.length,
         "download_url": file_helpers.get_signed_file_url(variable_file.upload_file_id, as_attachment=True),
     }
@@ -598,7 +598,7 @@ class EnvironmentVariableCollectionApi(Resource):
                     "name": v.name,
                     "description": v.description,
                     "selector": v.selector,
-                    "value_type": v.value_type.exposed_type().value,
+                    "value_type": str(v.value_type.exposed_type()),
                     "value": v.value,
                     # Do not track edited for env vars.
                     "edited": False,

api/controllers/console/datasets/datasets.py

@@ -50,6 +50,7 @@ from fields.dataset_fields import (
 from fields.document_fields import document_status_fields
 from graphon.model_runtime.entities.model_entities import ModelType
 from libs.login import current_account_with_tenant, login_required
+from libs.url_utils import normalize_api_base_url
 from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
 from models.dataset import DatasetPermission, DatasetPermissionEnum
 from models.enums import ApiTokenType, SegmentStatus
@@ -889,7 +890,8 @@ class DatasetApiBaseUrlApi(Resource):
     @login_required
     @account_initialization_required
     def get(self):
-        return {"api_base_url": (dify_config.SERVICE_API_URL or request.host_url.rstrip("/")) + "/v1"}
+        base = dify_config.SERVICE_API_URL or request.host_url.rstrip("/")
+        return {"api_base_url": normalize_api_base_url(base)}
 
 
 @console_ns.route("/datasets/retrieval-setting")

api/controllers/console/datasets/hit_testing_base.py

@@ -38,6 +38,48 @@ class HitTestingPayload(BaseModel):
 
 
 class DatasetsHitTestingBase:
+    @staticmethod
+    def _normalize_hit_testing_query(query: Any) -> str:
+        """Return the user-visible query string from legacy and current response shapes."""
+        if isinstance(query, str):
+            return query
+
+        if isinstance(query, dict):
+            content = query.get("content")
+            if isinstance(content, str):
+                return content
+
+        raise ValueError("Invalid hit testing query response")
+
+    @staticmethod
+    def _normalize_hit_testing_records(records: Any) -> list[dict[str, Any]]:
+        """Coerce nullable collection fields into lists before response validation."""
+        if not isinstance(records, list):
+            return []
+
+        normalized_records: list[dict[str, Any]] = []
+        for record in records:
+            if not isinstance(record, dict):
+                continue
+
+            normalized_record = dict(record)
+            segment = normalized_record.get("segment")
+            if isinstance(segment, dict):
+                normalized_segment = dict(segment)
+                if normalized_segment.get("keywords") is None:
+                    normalized_segment["keywords"] = []
+                normalized_record["segment"] = normalized_segment
+
+            if normalized_record.get("child_chunks") is None:
+                normalized_record["child_chunks"] = []
+
+            if normalized_record.get("files") is None:
+                normalized_record["files"] = []
+
+            normalized_records.append(normalized_record)
+
+        return normalized_records
+
     @staticmethod
     def get_and_validate_dataset(dataset_id: str):
         assert isinstance(current_user, Account)
@@ -75,7 +117,12 @@ class DatasetsHitTestingBase:
                 attachment_ids=args.get("attachment_ids"),
                 limit=10,
             )
-            return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
+            return {
+                "query": DatasetsHitTestingBase._normalize_hit_testing_query(response.get("query")),
+                "records": DatasetsHitTestingBase._normalize_hit_testing_records(
+                    marshal(response.get("records", []), hit_testing_record_fields)
+                ),
+            }
         except services.errors.index.IndexNotInitializedError:
             raise DatasetNotInitializedError()
         except ProviderTokenNotInitError as ex:

api/controllers/console/human_input_form.py

@@ -8,10 +8,10 @@ from collections.abc import Generator
 
 from flask import Response, jsonify, request
 from flask_restx import Resource
-from pydantic import BaseModel
 from sqlalchemy import select
 from sqlalchemy.orm import Session, sessionmaker
 
+from controllers.common.human_input import HumanInputFormSubmitPayload
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
@@ -20,11 +20,11 @@ from core.app.apps.base_app_generator import BaseAppGenerator
 from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
 from core.app.apps.message_generator import MessageGenerator
 from core.app.apps.workflow.app_generator import WorkflowAppGenerator
+from core.workflow.human_input_policy import HumanInputSurface, is_recipient_type_allowed_for_surface
 from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
 from models import App
 from models.enums import CreatorUserRole
-from models.human_input import RecipientType
 from models.model import AppMode
 from models.workflow import WorkflowRun
 from repositories.factory import DifyAPIRepositoryFactory
@@ -34,11 +34,6 @@ from services.workflow_event_snapshot_service import build_workflow_event_stream
 logger = logging.getLogger(__name__)
 
 
-class HumanInputFormSubmitPayload(BaseModel):
-    inputs: dict
-    action: str
-
-
 def _jsonify_form_definition(form: Form) -> Response:
     payload = form.get_definition().model_dump()
     payload["expiration_time"] = int(form.expiration_time.timestamp())
@@ -56,6 +51,11 @@ class ConsoleHumanInputFormApi(Resource):
         if form.tenant_id != current_tenant_id:
             raise NotFoundError("App not found")
 
+    @staticmethod
+    def _ensure_console_recipient_type(form: Form) -> None:
+        if not is_recipient_type_allowed_for_surface(form.recipient_type, HumanInputSurface.CONSOLE):
+            raise NotFoundError("form not found")
+
     @setup_required
     @login_required
     @account_initialization_required
@@ -99,10 +99,8 @@ class ConsoleHumanInputFormApi(Resource):
             raise NotFoundError(f"form not found, token={form_token}")
 
         self._ensure_console_access(form)
-
+        self._ensure_console_recipient_type(form)
         recipient_type = form.recipient_type
-        if recipient_type not in {RecipientType.CONSOLE, RecipientType.BACKSTAGE}:
-            raise NotFoundError(f"form not found, token={form_token}")
         # The type checker is not smart enought to validate the following invariant.
         # So we need to assert it manually.
         assert recipient_type is not None, "recipient_type cannot be None here."

api/controllers/console/tag/tags.py

@@ -37,6 +37,11 @@ class TagBindingRemovePayload(BaseModel):
     type: TagType = Field(description="Tag type")
 
 
+class TagBindingItemDeletePayload(BaseModel):
+    target_id: str = Field(description="Target ID to unbind tag from")
+    type: TagType = Field(description="Tag type")
+
+
 class TagListQueryParam(BaseModel):
     type: Literal["knowledge", "app", ""] = Field("", description="Tag type filter")
     keyword: str | None = Field(None, description="Search keyword")
@@ -70,6 +75,7 @@ register_schema_models(
     TagBasePayload,
     TagBindingPayload,
     TagBindingRemovePayload,
+    TagBindingItemDeletePayload,
     TagListQueryParam,
     TagResponse,
 )
@@ -152,41 +158,107 @@ class TagUpdateDeleteApi(Resource):
         return "", 204
 
 
-@console_ns.route("/tag-bindings/create")
-class TagBindingCreateApi(Resource):
+def _require_tag_binding_edit_permission() -> None:
+    """
+    Ensure the current account can edit tag bindings.
+
+    Tag binding operations are allowed for users who can edit resources (app/dataset) within the current tenant.
+    """
+    current_user, _ = current_account_with_tenant()
+    # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+    if not (current_user.has_edit_permission or current_user.is_dataset_editor):
+        raise Forbidden()
+
+
+def _create_tag_bindings() -> tuple[dict[str, str], int]:
+    _require_tag_binding_edit_permission()
+
+    payload = TagBindingPayload.model_validate(console_ns.payload or {})
+    TagService.save_tag_binding(
+        TagBindingCreatePayload(
+            tag_ids=payload.tag_ids,
+            target_id=payload.target_id,
+            type=payload.type,
+        )
+    )
+    return {"result": "success"}, 200
+
+
+def _remove_tag_binding() -> tuple[dict[str, str], int]:
+    _require_tag_binding_edit_permission()
+
+    payload = TagBindingRemovePayload.model_validate(console_ns.payload or {})
+    TagService.delete_tag_binding(
+        TagBindingDeletePayload(
+            tag_id=payload.tag_id,
+            target_id=payload.target_id,
+            type=payload.type,
+        )
+    )
+    return {"result": "success"}, 200
+
+
+@console_ns.route("/tag-bindings")
+class TagBindingCollectionApi(Resource):
+    """Canonical collection resource for tag binding creation."""
+
+    @console_ns.doc("create_tag_binding")
     @console_ns.expect(console_ns.models[TagBindingPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        current_user, _ = current_account_with_tenant()
-        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
-        if not (current_user.has_edit_permission or current_user.is_dataset_editor):
-            raise Forbidden()
+        return _create_tag_bindings()
 
-        payload = TagBindingPayload.model_validate(console_ns.payload or {})
-        TagService.save_tag_binding(
-            TagBindingCreatePayload(tag_ids=payload.tag_ids, target_id=payload.target_id, type=payload.type)
+
+@console_ns.route("/tag-bindings/<uuid:id>")
+class TagBindingItemApi(Resource):
+    """Canonical item resource for tag binding deletion."""
+
+    @console_ns.doc("delete_tag_binding")
+    @console_ns.doc(params={"id": "Tag ID"})
+    @console_ns.expect(console_ns.models[TagBindingItemDeletePayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, id):
+        _require_tag_binding_edit_permission()
+        payload = TagBindingItemDeletePayload.model_validate(console_ns.payload or {})
+        TagService.delete_tag_binding(
+            TagBindingDeletePayload(
+                tag_id=str(id),
+                target_id=payload.target_id,
+                type=payload.type,
+            )
         )
-
         return {"result": "success"}, 200
 
 
+@console_ns.route("/tag-bindings/create")
+class DeprecatedTagBindingCreateApi(Resource):
+    """Deprecated verb-based alias for tag binding creation."""
+
+    @console_ns.doc("create_tag_binding_deprecated")
+    @console_ns.doc(deprecated=True)
+    @console_ns.doc(description="Deprecated legacy alias. Use POST /tag-bindings instead.")
+    @console_ns.expect(console_ns.models[TagBindingPayload.__name__])
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        return _create_tag_bindings()
+
+
 @console_ns.route("/tag-bindings/remove")
-class TagBindingDeleteApi(Resource):
+class DeprecatedTagBindingRemoveApi(Resource):
+    """Deprecated verb-based alias for tag binding deletion."""
+
+    @console_ns.doc("delete_tag_binding_deprecated")
+    @console_ns.doc(deprecated=True)
+    @console_ns.doc(description="Deprecated legacy alias. Use DELETE /tag-bindings/{id} instead.")
     @console_ns.expect(console_ns.models[TagBindingRemovePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        current_user, _ = current_account_with_tenant()
-        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
-        if not (current_user.has_edit_permission or current_user.is_dataset_editor):
-            raise Forbidden()
-
-        payload = TagBindingRemovePayload.model_validate(console_ns.payload or {})
-        TagService.delete_tag_binding(
-            TagBindingDeletePayload(tag_id=payload.tag_id, target_id=payload.target_id, type=payload.type)
-        )
-
-        return {"result": "success"}, 200
+        return _remove_tag_binding()

api/controllers/console/workspace/account.py

@@ -595,13 +595,25 @@ class ChangeEmailSendEmailApi(Resource):
         account = None
         user_email = None
         email_for_sending = args.email.lower()
-        if args.phase is not None and args.phase == "new_email":
+        # Default to the initial phase; any legacy/unexpected client input is
+        # coerced back to `old_email` so we never trust the caller to declare
+        # later phases without a verified predecessor token.
+        send_phase = AccountService.CHANGE_EMAIL_PHASE_OLD
+        if args.phase is not None and args.phase == AccountService.CHANGE_EMAIL_PHASE_NEW:
+            send_phase = AccountService.CHANGE_EMAIL_PHASE_NEW
             if args.token is None:
                 raise InvalidTokenError()
 
             reset_data = AccountService.get_change_email_data(args.token)
             if reset_data is None:
                 raise InvalidTokenError()
+
+            # The token used to request a new-email code must come from the
+            # old-email verification step. This prevents the bypass described
+            # in GHSA-4q3w-q5mc-45rq where the phase-1 token was reused here.
+            token_phase = reset_data.get(AccountService.CHANGE_EMAIL_TOKEN_PHASE_KEY)
+            if token_phase != AccountService.CHANGE_EMAIL_PHASE_OLD_VERIFIED:
+                raise InvalidTokenError()
             user_email = reset_data.get("email", "")
 
             if user_email.lower() != current_user.email.lower():
@@ -620,7 +632,7 @@ class ChangeEmailSendEmailApi(Resource):
             email=email_for_sending,
             old_email=user_email,
             language=language,
-            phase=args.phase,
+            phase=send_phase,
         )
         return {"result": "success", "data": token}
 
@@ -655,12 +667,31 @@ class ChangeEmailCheckApi(Resource):
             AccountService.add_change_email_error_rate_limit(user_email)
             raise EmailCodeError()
 
+        # Only advance tokens that were minted by the matching send-code step;
+        # refuse tokens that have already progressed or lack a phase marker so
+        # the chain `old_email -> old_email_verified -> new_email -> new_email_verified`
+        # is strictly enforced.
+        phase_transitions = {
+            AccountService.CHANGE_EMAIL_PHASE_OLD: AccountService.CHANGE_EMAIL_PHASE_OLD_VERIFIED,
+            AccountService.CHANGE_EMAIL_PHASE_NEW: AccountService.CHANGE_EMAIL_PHASE_NEW_VERIFIED,
+        }
+        token_phase = token_data.get(AccountService.CHANGE_EMAIL_TOKEN_PHASE_KEY)
+        if not isinstance(token_phase, str):
+            raise InvalidTokenError()
+        refreshed_phase = phase_transitions.get(token_phase)
+        if refreshed_phase is None:
+            raise InvalidTokenError()
+
         # Verified, revoke the first token
         AccountService.revoke_change_email_token(args.token)
 
-        # Refresh token data by generating a new token
+        # Refresh token data by generating a new token that carries the
+        # upgraded phase so later steps can check it.
         _, new_token = AccountService.generate_change_email_token(
-            user_email, code=args.code, old_email=token_data.get("old_email"), additional_data={}
+            user_email,
+            code=args.code,
+            old_email=token_data.get("old_email"),
+            additional_data={AccountService.CHANGE_EMAIL_TOKEN_PHASE_KEY: refreshed_phase},
         )
 
         AccountService.reset_change_email_error_rate_limit(user_email)
@@ -690,13 +721,29 @@ class ChangeEmailResetApi(Resource):
         if not reset_data:
             raise InvalidTokenError()
 
-        AccountService.revoke_change_email_token(args.token)
+        # Only tokens that completed both verification phases may be used to
+        # change the email. This closes GHSA-4q3w-q5mc-45rq where a token from
+        # the initial send-code step could be replayed directly here.
+        token_phase = reset_data.get(AccountService.CHANGE_EMAIL_TOKEN_PHASE_KEY)
+        if token_phase != AccountService.CHANGE_EMAIL_PHASE_NEW_VERIFIED:
+            raise InvalidTokenError()
+
+        # Bind the new email to the token that was mailed and verified, so a
+        # verified token cannot be reused with a different `new_email` value.
+        token_email = reset_data.get("email")
+        normalized_token_email = token_email.lower() if isinstance(token_email, str) else token_email
+        if normalized_token_email != normalized_new_email:
+            raise InvalidTokenError()
 
         old_email = reset_data.get("old_email", "")
         current_user, _ = current_account_with_tenant()
         if current_user.email.lower() != old_email.lower():
             raise AccountNotFound()
 
+        # Revoke only after all checks pass so failed attempts don't burn a
+        # legitimately verified token.
+        AccountService.revoke_change_email_token(args.token)
+
         updated_account = AccountService.update_account_email(current_user, email=normalized_new_email)
 
         AccountService.send_change_email_completed_notify_email(

api/controllers/console/workspace/endpoint.py

@@ -1,3 +1,11 @@
+"""Console workspace endpoint controllers.
+
+This module exposes workspace-scoped plugin endpoint management APIs. The
+canonical write routes follow resource-oriented paths, while the historical
+verb-based aliases stay available as deprecated resources so OpenAPI metadata
+marks only the legacy paths as deprecated.
+"""
+
 from typing import Any
 
 from flask import request
@@ -25,7 +33,12 @@ class EndpointIdPayload(BaseModel):
     endpoint_id: str
 
 
-class EndpointUpdatePayload(EndpointIdPayload):
+class EndpointUpdatePayload(BaseModel):
+    settings: dict[str, Any]
+    name: str = Field(min_length=1)
+
+
+class LegacyEndpointUpdatePayload(EndpointIdPayload):
     settings: dict[str, Any]
     name: str = Field(min_length=1)
 
@@ -76,6 +89,7 @@ register_schema_models(
     EndpointCreatePayload,
     EndpointIdPayload,
     EndpointUpdatePayload,
+    LegacyEndpointUpdatePayload,
     EndpointListQuery,
     EndpointListForPluginQuery,
     EndpointCreateResponse,
@@ -88,8 +102,60 @@ register_schema_models(
 )
 
 
-@console_ns.route("/workspaces/current/endpoints/create")
-class EndpointCreateApi(Resource):
+def _create_endpoint() -> dict[str, bool]:
+    """Create a plugin endpoint for the current workspace."""
+    user, tenant_id = current_account_with_tenant()
+
+    args = EndpointCreatePayload.model_validate(console_ns.payload)
+
+    try:
+        return {
+            "success": EndpointService.create_endpoint(
+                tenant_id=tenant_id,
+                user_id=user.id,
+                plugin_unique_identifier=args.plugin_unique_identifier,
+                name=args.name,
+                settings=args.settings,
+            )
+        }
+    except PluginPermissionDeniedError as e:
+        raise ValueError(e.description) from e
+
+
+def _update_endpoint(endpoint_id: str) -> dict[str, bool]:
+    """Update a plugin endpoint identified by the canonical path parameter."""
+    user, tenant_id = current_account_with_tenant()
+
+    args = EndpointUpdatePayload.model_validate(console_ns.payload)
+
+    return {
+        "success": EndpointService.update_endpoint(
+            tenant_id=tenant_id,
+            user_id=user.id,
+            endpoint_id=endpoint_id,
+            name=args.name,
+            settings=args.settings,
+        )
+    }
+
+
+def _delete_endpoint(endpoint_id: str) -> dict[str, bool]:
+    """Delete a plugin endpoint identified by the canonical path parameter."""
+    user, tenant_id = current_account_with_tenant()
+
+    return {
+        "success": EndpointService.delete_endpoint(
+            tenant_id=tenant_id,
+            user_id=user.id,
+            endpoint_id=endpoint_id,
+        )
+    }
+
+
+@console_ns.route("/workspaces/current/endpoints")
+class EndpointCollectionApi(Resource):
+    """Canonical collection resource for endpoint creation."""
+
     @console_ns.doc("create_endpoint")
     @console_ns.doc(description="Create a new plugin endpoint")
     @console_ns.expect(console_ns.models[EndpointCreatePayload.__name__])
@@ -104,22 +170,33 @@ class EndpointCreateApi(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self):
-        user, tenant_id = current_account_with_tenant()
+        return _create_endpoint()
 
-        args = EndpointCreatePayload.model_validate(console_ns.payload)
 
-        try:
-            return {
-                "success": EndpointService.create_endpoint(
-                    tenant_id=tenant_id,
-                    user_id=user.id,
-                    plugin_unique_identifier=args.plugin_unique_identifier,
-                    name=args.name,
-                    settings=args.settings,
-                )
-            }
-        except PluginPermissionDeniedError as e:
-            raise ValueError(e.description) from e
+@console_ns.route("/workspaces/current/endpoints/create")
+class DeprecatedEndpointCreateApi(Resource):
+    """Deprecated verb-based alias for endpoint creation."""
+
+    @console_ns.doc("create_endpoint_deprecated")
+    @console_ns.doc(deprecated=True)
+    @console_ns.doc(
+        description=(
+            "Deprecated legacy alias for creating a plugin endpoint. Use POST /workspaces/current/endpoints instead."
+        )
+    )
+    @console_ns.expect(console_ns.models[EndpointCreatePayload.__name__])
+    @console_ns.response(
+        200,
+        "Endpoint created successfully",
+        console_ns.models[EndpointCreateResponse.__name__],
+    )
+    @console_ns.response(403, "Admin privileges required")
+    @setup_required
+    @login_required
+    @is_admin_or_owner_required
+    @account_initialization_required
+    def post(self):
+        return _create_endpoint()
 
 
 @console_ns.route("/workspaces/current/endpoints/list")
@@ -190,10 +267,56 @@ class EndpointListForSinglePluginApi(Resource):
         )
 
 
-@console_ns.route("/workspaces/current/endpoints/delete")
-class EndpointDeleteApi(Resource):
+@console_ns.route("/workspaces/current/endpoints/<string:id>")
+class EndpointItemApi(Resource):
+    """Canonical item resource for endpoint updates and deletion."""
+
     @console_ns.doc("delete_endpoint")
     @console_ns.doc(description="Delete a plugin endpoint")
+    @console_ns.doc(params={"id": {"description": "Endpoint ID", "type": "string", "required": True}})
+    @console_ns.response(
+        200,
+        "Endpoint deleted successfully",
+        console_ns.models[EndpointDeleteResponse.__name__],
+    )
+    @console_ns.response(403, "Admin privileges required")
+    @setup_required
+    @login_required
+    @is_admin_or_owner_required
+    @account_initialization_required
+    def delete(self, id: str):
+        return _delete_endpoint(endpoint_id=id)
+
+    @console_ns.doc("update_endpoint")
+    @console_ns.doc(description="Update a plugin endpoint")
+    @console_ns.expect(console_ns.models[EndpointUpdatePayload.__name__])
+    @console_ns.doc(params={"id": {"description": "Endpoint ID", "type": "string", "required": True}})
+    @console_ns.response(
+        200,
+        "Endpoint updated successfully",
+        console_ns.models[EndpointUpdateResponse.__name__],
+    )
+    @console_ns.response(403, "Admin privileges required")
+    @setup_required
+    @login_required
+    @is_admin_or_owner_required
+    @account_initialization_required
+    def patch(self, id: str):
+        return _update_endpoint(endpoint_id=id)
+
+
+@console_ns.route("/workspaces/current/endpoints/delete")
+class DeprecatedEndpointDeleteApi(Resource):
+    """Deprecated verb-based alias for endpoint deletion."""
+
+    @console_ns.doc("delete_endpoint_deprecated")
+    @console_ns.doc(deprecated=True)
+    @console_ns.doc(
+        description=(
+            "Deprecated legacy alias for deleting a plugin endpoint. "
+            "Use DELETE /workspaces/current/endpoints/{id} instead."
+        )
+    )
     @console_ns.expect(console_ns.models[EndpointIdPayload.__name__])
     @console_ns.response(
         200,
@@ -206,22 +329,23 @@ class EndpointDeleteApi(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self):
-        user, tenant_id = current_account_with_tenant()
-
         args = EndpointIdPayload.model_validate(console_ns.payload)
-
-        return {
-            "success": EndpointService.delete_endpoint(
-                tenant_id=tenant_id, user_id=user.id, endpoint_id=args.endpoint_id
-            )
-        }
+        return _delete_endpoint(endpoint_id=args.endpoint_id)
 
 
 @console_ns.route("/workspaces/current/endpoints/update")
-class EndpointUpdateApi(Resource):
-    @console_ns.doc("update_endpoint")
-    @console_ns.doc(description="Update a plugin endpoint")
-    @console_ns.expect(console_ns.models[EndpointUpdatePayload.__name__])
+class DeprecatedEndpointUpdateApi(Resource):
+    """Deprecated verb-based alias for endpoint updates."""
+
+    @console_ns.doc("update_endpoint_deprecated")
+    @console_ns.doc(deprecated=True)
+    @console_ns.doc(
+        description=(
+            "Deprecated legacy alias for updating a plugin endpoint. "
+            "Use PATCH /workspaces/current/endpoints/{id} instead."
+        )
+    )
+    @console_ns.expect(console_ns.models[LegacyEndpointUpdatePayload.__name__])
     @console_ns.response(
         200,
         "Endpoint updated successfully",
@@ -233,19 +357,8 @@ class EndpointUpdateApi(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self):
-        user, tenant_id = current_account_with_tenant()
-
-        args = EndpointUpdatePayload.model_validate(console_ns.payload)
-
-        return {
-            "success": EndpointService.update_endpoint(
-                tenant_id=tenant_id,
-                user_id=user.id,
-                endpoint_id=args.endpoint_id,
-                name=args.name,
-                settings=args.settings,
-            )
-        }
+        args = LegacyEndpointUpdatePayload.model_validate(console_ns.payload)
+        return _update_endpoint(endpoint_id=args.endpoint_id)
 
 
 @console_ns.route("/workspaces/current/endpoints/enable")

api/controllers/console/workspace/tool_providers.py

@@ -1131,6 +1131,14 @@ class ToolMCPAuthApi(Resource):
             with sessionmaker(db.engine).begin() as session:
                 service = MCPToolManageService(session=session)
                 service.clear_provider_credentials(provider_id=provider_id, tenant_id=tenant_id)
+            parsed = urlparse(server_url)
+            sanitized_url = f"{parsed.scheme}://{parsed.hostname}{parsed.path}"
+            logger.warning(
+                "MCP authorization failed for provider %s (url=%s)",
+                provider_id,
+                sanitized_url,
+                exc_info=True,
+            )
             raise ValueError(f"Failed to connect to MCP server: {e}") from e
 
 

api/controllers/inner_api/plugin/wraps.py

@@ -20,10 +20,13 @@ class TenantUserPayload(BaseModel):
 
 def get_user(tenant_id: str, user_id: str | None) -> EndUser:
     """
-    Get current user
+    Get current user.
 
     NOTE: user_id is not trusted, it could be maliciously set to any value.
-    As a result, it could only be considered as an end user id.
+    As a result, it could only be considered as an end user id. Even when a
+    concrete end-user ID is supplied, lookups must stay tenant-scoped so one
+    tenant cannot bind another tenant's user record into the plugin request
+    context.
     """
     if not user_id:
         user_id = DefaultEndUserSessionID.DEFAULT_SESSION_ID
@@ -42,7 +45,14 @@ def get_user(tenant_id: str, user_id: str | None) -> EndUser:
                     .limit(1)
                 )
             else:
-                user_model = session.get(EndUser, user_id)
+                user_model = session.scalar(
+                    select(EndUser)
+                    .where(
+                        EndUser.id == user_id,
+                        EndUser.tenant_id == tenant_id,
+                    )
+                    .limit(1)
+                )
 
             if not user_model:
                 user_model = EndUser(

api/controllers/service_api/__init__.py

@@ -23,9 +23,11 @@ from .app import (
     conversation,
     file,
     file_preview,
+    human_input_form,
     message,
     site,
     workflow,
+    workflow_events,
 )
 from .dataset import (
     dataset,
@@ -50,6 +52,7 @@ __all__ = [
     "file",
     "file_preview",
     "hit_testing",
+    "human_input_form",
     "index",
     "message",
     "metadata",
@@ -58,6 +61,7 @@ __all__ = [
     "segment",
     "site",
     "workflow",
+    "workflow_events",
 ]
 
 api.add_namespace(service_api_ns)

api/controllers/service_api/app/conversation.py

@@ -84,10 +84,10 @@ class ConversationVariableResponse(ResponseModel):
     def normalize_value_type(cls, value: Any) -> str:
         exposed_type = getattr(value, "exposed_type", None)
         if callable(exposed_type):
-            return str(exposed_type().value)
+            return str(exposed_type())
         if isinstance(value, str):
             try:
-                return str(SegmentType(value).exposed_type().value)
+                return str(SegmentType(value).exposed_type())
             except ValueError:
                 return value
         try:

api/controllers/service_api/app/human_input_form.py

@@ -0,0 +1,137 @@
+"""
+Service API human input form endpoints.
+
+This module exposes app-token authenticated APIs for fetching and submitting
+paused human input forms in workflow/chatflow runs.
+"""
+
+import json
+import logging
+from datetime import datetime
+
+from flask import Response
+from flask_restx import Resource
+from werkzeug.exceptions import BadRequest, NotFound
+
+from controllers.common.human_input import HumanInputFormSubmitPayload
+from controllers.common.schema import register_schema_models
+from controllers.service_api import service_api_ns
+from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from core.workflow.human_input_policy import HumanInputSurface, is_recipient_type_allowed_for_surface
+from extensions.ext_database import db
+from models.model import App, EndUser
+from services.human_input_service import Form, FormNotFoundError, HumanInputService
+
+logger = logging.getLogger(__name__)
+
+
+register_schema_models(service_api_ns, HumanInputFormSubmitPayload)
+
+
+def _stringify_default_values(values: dict[str, object]) -> dict[str, str]:
+    result: dict[str, str] = {}
+    for key, value in values.items():
+        if value is None:
+            result[key] = ""
+        elif isinstance(value, (dict, list)):
+            result[key] = json.dumps(value, ensure_ascii=False)
+        else:
+            result[key] = str(value)
+    return result
+
+
+def _to_timestamp(value: datetime) -> int:
+    return int(value.timestamp())
+
+
+def _jsonify_form_definition(form: Form) -> Response:
+    definition_payload = form.get_definition().model_dump()
+    payload = {
+        "form_content": definition_payload["rendered_content"],
+        "inputs": definition_payload["inputs"],
+        "resolved_default_values": _stringify_default_values(definition_payload["default_values"]),
+        "user_actions": definition_payload["user_actions"],
+        "expiration_time": _to_timestamp(form.expiration_time),
+    }
+    return Response(json.dumps(payload, ensure_ascii=False), mimetype="application/json")
+
+
+def _ensure_form_belongs_to_app(form: Form, app_model: App) -> None:
+    if form.app_id != app_model.id or form.tenant_id != app_model.tenant_id:
+        raise NotFound("Form not found")
+
+
+def _ensure_form_is_allowed_for_service_api(form: Form) -> None:
+    # Keep app-token callers scoped to the public web-form surface; internal HITL
+    # routes must continue to flow through console-only authentication.
+    if not is_recipient_type_allowed_for_surface(form.recipient_type, HumanInputSurface.SERVICE_API):
+        raise NotFound("Form not found")
+
+
+@service_api_ns.route("/form/human_input/<string:form_token>")
+class WorkflowHumanInputFormApi(Resource):
+    @service_api_ns.doc("get_human_input_form")
+    @service_api_ns.doc(description="Get a paused human input form by token")
+    @service_api_ns.doc(params={"form_token": "Human input form token"})
+    @service_api_ns.doc(
+        responses={
+            200: "Form retrieved successfully",
+            401: "Unauthorized - invalid API token",
+            404: "Form not found",
+            412: "Form already submitted or expired",
+        }
+    )
+    @validate_app_token
+    def get(self, app_model: App, form_token: str):
+        service = HumanInputService(db.engine)
+        form = service.get_form_by_token(form_token)
+        if form is None:
+            raise NotFound("Form not found")
+
+        _ensure_form_belongs_to_app(form, app_model)
+        _ensure_form_is_allowed_for_service_api(form)
+        service.ensure_form_active(form)
+        return _jsonify_form_definition(form)
+
+    @service_api_ns.expect(service_api_ns.models[HumanInputFormSubmitPayload.__name__])
+    @service_api_ns.doc("submit_human_input_form")
+    @service_api_ns.doc(description="Submit a paused human input form by token")
+    @service_api_ns.doc(params={"form_token": "Human input form token"})
+    @service_api_ns.doc(
+        responses={
+            200: "Form submitted successfully",
+            400: "Bad request - invalid submission data",
+            401: "Unauthorized - invalid API token",
+            404: "Form not found",
+            412: "Form already submitted or expired",
+        }
+    )
+    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
+    def post(self, app_model: App, end_user: EndUser, form_token: str):
+        payload = HumanInputFormSubmitPayload.model_validate(service_api_ns.payload or {})
+
+        service = HumanInputService(db.engine)
+        form = service.get_form_by_token(form_token)
+        if form is None:
+            raise NotFound("Form not found")
+
+        _ensure_form_belongs_to_app(form, app_model)
+        _ensure_form_is_allowed_for_service_api(form)
+
+        recipient_type = form.recipient_type
+        if recipient_type is None:
+            logger.warning("Recipient type is None for form, form_id=%s", form.id)
+            raise BadRequest("Form recipient type is invalid")
+
+        try:
+            service.submit_form_by_token(
+                recipient_type=recipient_type,
+                form_token=form_token,
+                selected_action_id=payload.action,
+                form_data=payload.inputs,
+                submission_end_user_id=end_user.id,
+            )
+        except FormNotFoundError:
+            raise NotFound("Form not found")
+
+        return {}, 200

api/controllers/service_api/app/workflow_events.py

@@ -0,0 +1,142 @@
+"""
+Service API workflow resume event stream endpoints.
+"""
+
+import json
+from collections.abc import Generator
+
+from flask import Response, request
+from flask_restx import Resource
+from sqlalchemy.orm import sessionmaker
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import service_api_ns
+from controllers.service_api.app.error import NotWorkflowAppError
+from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from core.app.apps.advanced_chat.app_generator import AdvancedChatAppGenerator
+from core.app.apps.base_app_generator import BaseAppGenerator
+from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
+from core.app.apps.message_generator import MessageGenerator
+from core.app.apps.workflow.app_generator import WorkflowAppGenerator
+from core.app.entities.task_entities import StreamEvent
+from core.workflow.human_input_policy import HumanInputSurface
+from extensions.ext_database import db
+from models.enums import CreatorUserRole
+from models.model import App, AppMode, EndUser
+from repositories.factory import DifyAPIRepositoryFactory
+from services.workflow_event_snapshot_service import build_workflow_event_stream
+
+
+@service_api_ns.route("/workflow/<string:task_id>/events")
+class WorkflowEventsApi(Resource):
+    """Service API for getting workflow execution events after resume."""
+
+    @service_api_ns.doc("get_workflow_events")
+    @service_api_ns.doc(description="Get workflow execution events stream after resume")
+    @service_api_ns.doc(
+        params={
+            "task_id": "Workflow run ID",
+            "user": "End user identifier (query param)",
+            "include_state_snapshot": (
+                "Whether to replay from persisted state snapshot, "
+                'specify `"true"` to include a status snapshot of executed nodes'
+            ),
+            "continue_on_pause": (
+                "Whether to keep the stream open across workflow_paused events,"
+                'specify `"true"` to keep the stream open for `workflow_paused` events.'
+            ),
+        }
+    )
+    @service_api_ns.doc(
+        responses={
+            200: "SSE event stream",
+            401: "Unauthorized - invalid API token",
+            404: "Workflow run not found",
+        }
+    )
+    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY, required=True))
+    def get(self, app_model: App, end_user: EndUser, task_id: str):
+        app_mode = AppMode.value_of(app_model.mode)
+        if app_mode not in {AppMode.WORKFLOW, AppMode.ADVANCED_CHAT}:
+            raise NotWorkflowAppError()
+
+        session_maker = sessionmaker(db.engine)
+        repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker)
+        workflow_run = repo.get_workflow_run_by_id_and_tenant_id(
+            tenant_id=app_model.tenant_id,
+            run_id=task_id,
+        )
+
+        if workflow_run is None:
+            raise NotFound("Workflow run not found")
+
+        if workflow_run.app_id != app_model.id:
+            raise NotFound("Workflow run not found")
+
+        if workflow_run.created_by_role != CreatorUserRole.END_USER:
+            raise NotFound("Workflow run not found")
+
+        if workflow_run.created_by != end_user.id:
+            raise NotFound("Workflow run not found")
+
+        workflow_run_entity = workflow_run
+
+        if workflow_run_entity.finished_at is not None:
+            response = WorkflowResponseConverter.workflow_run_result_to_finish_response(
+                task_id=workflow_run_entity.id,
+                workflow_run=workflow_run_entity,
+                creator_user=end_user,
+            )
+
+            payload = response.model_dump(mode="json")
+            payload["event"] = response.event.value
+
+            def _generate_finished_events() -> Generator[str, None, None]:
+                yield f"data: {json.dumps(payload)}\n\n"
+
+            event_generator = _generate_finished_events
+        else:
+            msg_generator = MessageGenerator()
+            generator: BaseAppGenerator
+            if app_mode == AppMode.ADVANCED_CHAT:
+                generator = AdvancedChatAppGenerator()
+            elif app_mode == AppMode.WORKFLOW:
+                generator = WorkflowAppGenerator()
+            else:
+                raise NotWorkflowAppError()
+
+            include_state_snapshot = request.args.get("include_state_snapshot", "false").lower() == "true"
+            continue_on_pause = request.args.get("continue_on_pause", "false").lower() == "true"
+            terminal_events: list[StreamEvent] | None = [] if continue_on_pause else None
+
+            def _generate_stream_events():
+                if include_state_snapshot:
+                    return generator.convert_to_event_stream(
+                        build_workflow_event_stream(
+                            app_mode=app_mode,
+                            workflow_run=workflow_run_entity,
+                            tenant_id=app_model.tenant_id,
+                            app_id=app_model.id,
+                            session_maker=session_maker,
+                            human_input_surface=HumanInputSurface.SERVICE_API,
+                            close_on_pause=not continue_on_pause,
+                        )
+                    )
+                return generator.convert_to_event_stream(
+                    msg_generator.retrieve_events(
+                        app_mode,
+                        workflow_run_entity.id,
+                        terminal_events=terminal_events,
+                    ),
+                )
+
+            event_generator = _generate_stream_events
+
+        return Response(
+            event_generator(),
+            mimetype="text/event-stream",
+            headers={
+                "Cache-Control": "no-cache",
+                "Connection": "keep-alive",
+            },
+        )

api/controllers/service_api/dataset/document.py

@@ -1,4 +1,12 @@
+"""Service API endpoints for dataset document management.
+
+The canonical Service API paths use hyphenated route segments. Legacy underscore
+aliases remain registered for backward compatibility, but they must stay marked
+deprecated in generated API docs so clients migrate toward the canonical paths.
+"""
+
 import json
+from collections.abc import Mapping
 from contextlib import ExitStack
 from typing import Self
 from uuid import UUID
@@ -117,12 +125,137 @@ register_schema_models(
 )
 
 
-@service_api_ns.route(
-    "/datasets/<uuid:dataset_id>/document/create_by_text",
-    "/datasets/<uuid:dataset_id>/document/create-by-text",
-)
+def _create_document_by_text(tenant_id: str, dataset_id: UUID) -> tuple[Mapping[str, object], int]:
+    """Create a document from text for both canonical and legacy routes."""
+    payload = DocumentTextCreatePayload.model_validate(service_api_ns.payload or {})
+    args = payload.model_dump(exclude_none=True)
+
+    dataset_id_str = str(dataset_id)
+    tenant_id_str = str(tenant_id)
+    dataset = db.session.scalar(
+        select(Dataset).where(Dataset.tenant_id == tenant_id_str, Dataset.id == dataset_id_str).limit(1)
+    )
+
+    if not dataset:
+        raise ValueError("Dataset does not exist.")
+
+    if not dataset.indexing_technique and not args["indexing_technique"]:
+        raise ValueError("indexing_technique is required.")
+
+    embedding_model_provider = payload.embedding_model_provider
+    embedding_model = payload.embedding_model
+    if embedding_model_provider and embedding_model:
+        DatasetService.check_embedding_model_setting(tenant_id_str, embedding_model_provider, embedding_model)
+
+    retrieval_model = payload.retrieval_model
+    if (
+        retrieval_model
+        and retrieval_model.reranking_model
+        and retrieval_model.reranking_model.reranking_provider_name
+        and retrieval_model.reranking_model.reranking_model_name
+    ):
+        DatasetService.check_reranking_model_setting(
+            tenant_id_str,
+            retrieval_model.reranking_model.reranking_provider_name,
+            retrieval_model.reranking_model.reranking_model_name,
+        )
+
+    if not current_user:
+        raise ValueError("current_user is required")
+
+    upload_file = FileService(db.engine).upload_text(
+        text=payload.text, text_name=payload.name, user_id=current_user.id, tenant_id=tenant_id_str
+    )
+    data_source = {
+        "type": "upload_file",
+        "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+    }
+    args["data_source"] = data_source
+    knowledge_config = KnowledgeConfig.model_validate(args)
+    DocumentService.document_create_args_validate(knowledge_config)
+
+    if not current_user:
+        raise ValueError("current_user is required")
+
+    try:
+        documents, batch = DocumentService.save_document_with_dataset_id(
+            dataset=dataset,
+            knowledge_config=knowledge_config,
+            account=current_user,
+            dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
+            created_from="api",
+        )
+    except ProviderTokenNotInitError as ex:
+        raise ProviderNotInitializeError(ex.description)
+    document = documents[0]
+
+    documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
+    return documents_and_batch_fields, 200
+
+
+def _update_document_by_text(tenant_id: str, dataset_id: UUID, document_id: UUID) -> tuple[Mapping[str, object], int]:
+    """Update a document from text for both canonical and legacy routes."""
+    payload = DocumentTextUpdate.model_validate(service_api_ns.payload or {})
+    dataset = db.session.scalar(
+        select(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == str(dataset_id)).limit(1)
+    )
+    args = payload.model_dump(exclude_none=True)
+    if not dataset:
+        raise ValueError("Dataset does not exist.")
+
+    retrieval_model = payload.retrieval_model
+    if (
+        retrieval_model
+        and retrieval_model.reranking_model
+        and retrieval_model.reranking_model.reranking_provider_name
+        and retrieval_model.reranking_model.reranking_model_name
+    ):
+        DatasetService.check_reranking_model_setting(
+            tenant_id,
+            retrieval_model.reranking_model.reranking_provider_name,
+            retrieval_model.reranking_model.reranking_model_name,
+        )
+
+    # indexing_technique is already set in dataset since this is an update
+    args["indexing_technique"] = dataset.indexing_technique
+
+    if args.get("text"):
+        text = args.get("text")
+        name = args.get("name")
+        if not current_user:
+            raise ValueError("current_user is required")
+        upload_file = FileService(db.engine).upload_text(
+            text=str(text), text_name=str(name), user_id=current_user.id, tenant_id=tenant_id
+        )
+        data_source = {
+            "type": "upload_file",
+            "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+        }
+        args["data_source"] = data_source
+
+    args["original_document_id"] = str(document_id)
+    knowledge_config = KnowledgeConfig.model_validate(args)
+    DocumentService.document_create_args_validate(knowledge_config)
+
+    try:
+        documents, batch = DocumentService.save_document_with_dataset_id(
+            dataset=dataset,
+            knowledge_config=knowledge_config,
+            account=current_user,
+            dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
+            created_from="api",
+        )
+    except ProviderTokenNotInitError as ex:
+        raise ProviderNotInitializeError(ex.description)
+    document = documents[0]
+
+    documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
+    return documents_and_batch_fields, 200
+
+
+@service_api_ns.route("/datasets/<uuid:dataset_id>/document/create-by-text")
 class DocumentAddByTextApi(DatasetApiResource):
-    """Resource for documents."""
+    """Resource for the canonical text document creation route."""
 
     @service_api_ns.expect(service_api_ns.models[DocumentTextCreatePayload.__name__])
     @service_api_ns.doc("create_document_by_text")
@@ -138,81 +271,43 @@ class DocumentAddByTextApi(DatasetApiResource):
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_resource_check("documents", "dataset")
     @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
-    def post(self, tenant_id, dataset_id):
+    def post(self, tenant_id: str, dataset_id: UUID):
         """Create document by text."""
-        payload = DocumentTextCreatePayload.model_validate(service_api_ns.payload or {})
-        args = payload.model_dump(exclude_none=True)
+        return _create_document_by_text(tenant_id=tenant_id, dataset_id=dataset_id)
 
-        dataset_id = str(dataset_id)
-        tenant_id = str(tenant_id)
-        dataset = db.session.scalar(
-            select(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).limit(1)
+
+@service_api_ns.route("/datasets/<uuid:dataset_id>/document/create_by_text")
+class DeprecatedDocumentAddByTextApi(DatasetApiResource):
+    """Deprecated resource alias for text document creation."""
+
+    @service_api_ns.expect(service_api_ns.models[DocumentTextCreatePayload.__name__])
+    @service_api_ns.doc("create_document_by_text_deprecated")
+    @service_api_ns.doc(deprecated=True)
+    @service_api_ns.doc(
+        description=(
+            "Deprecated legacy alias for creating a new document by providing text content. "
+            "Use /datasets/{dataset_id}/document/create-by-text instead."
         )
-
-        if not dataset:
-            raise ValueError("Dataset does not exist.")
-
-        if not dataset.indexing_technique and not args["indexing_technique"]:
-            raise ValueError("indexing_technique is required.")
-
-        embedding_model_provider = payload.embedding_model_provider
-        embedding_model = payload.embedding_model
-        if embedding_model_provider and embedding_model:
-            DatasetService.check_embedding_model_setting(tenant_id, embedding_model_provider, embedding_model)
-
-        retrieval_model = payload.retrieval_model
-        if (
-            retrieval_model
-            and retrieval_model.reranking_model
-            and retrieval_model.reranking_model.reranking_provider_name
-            and retrieval_model.reranking_model.reranking_model_name
-        ):
-            DatasetService.check_reranking_model_setting(
-                tenant_id,
-                retrieval_model.reranking_model.reranking_provider_name,
-                retrieval_model.reranking_model.reranking_model_name,
-            )
-
-        if not current_user:
-            raise ValueError("current_user is required")
-
-        upload_file = FileService(db.engine).upload_text(
-            text=payload.text, text_name=payload.name, user_id=current_user.id, tenant_id=tenant_id
-        )
-        data_source = {
-            "type": "upload_file",
-            "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+    )
+    @service_api_ns.doc(params={"dataset_id": "Dataset ID"})
+    @service_api_ns.doc(
+        responses={
+            200: "Document created successfully",
+            401: "Unauthorized - invalid API token",
+            400: "Bad request - invalid parameters",
         }
-        args["data_source"] = data_source
-        knowledge_config = KnowledgeConfig.model_validate(args)
-        # validate args
-        DocumentService.document_create_args_validate(knowledge_config)
-
-        if not current_user:
-            raise ValueError("current_user is required")
-
-        try:
-            documents, batch = DocumentService.save_document_with_dataset_id(
-                dataset=dataset,
-                knowledge_config=knowledge_config,
-                account=current_user,
-                dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
-                created_from="api",
-            )
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        document = documents[0]
-
-        documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
-        return documents_and_batch_fields, 200
+    )
+    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_resource_check("documents", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
+    def post(self, tenant_id: str, dataset_id: UUID):
+        """Create document by text through the deprecated underscore alias."""
+        return _create_document_by_text(tenant_id=tenant_id, dataset_id=dataset_id)
 
 
-@service_api_ns.route(
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text",
-    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
-)
+@service_api_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text")
 class DocumentUpdateByTextApi(DatasetApiResource):
-    """Resource for update documents."""
+    """Resource for the canonical text document update route."""
 
     @service_api_ns.expect(service_api_ns.models[DocumentTextUpdate.__name__])
     @service_api_ns.doc("update_document_by_text")
@@ -229,62 +324,35 @@ class DocumentUpdateByTextApi(DatasetApiResource):
     @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id: str, dataset_id: UUID, document_id: UUID):
         """Update document by text."""
-        payload = DocumentTextUpdate.model_validate(service_api_ns.payload or {})
-        dataset = db.session.scalar(
-            select(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == str(dataset_id)).limit(1)
+        return _update_document_by_text(tenant_id=tenant_id, dataset_id=dataset_id, document_id=document_id)
+
+
+@service_api_ns.route("/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text")
+class DeprecatedDocumentUpdateByTextApi(DatasetApiResource):
+    """Deprecated resource alias for text document updates."""
+
+    @service_api_ns.expect(service_api_ns.models[DocumentTextUpdate.__name__])
+    @service_api_ns.doc("update_document_by_text_deprecated")
+    @service_api_ns.doc(deprecated=True)
+    @service_api_ns.doc(
+        description=(
+            "Deprecated legacy alias for updating an existing document by providing text content. "
+            "Use /datasets/{dataset_id}/documents/{document_id}/update-by-text instead."
         )
-        args = payload.model_dump(exclude_none=True)
-        if not dataset:
-            raise ValueError("Dataset does not exist.")
-
-        retrieval_model = payload.retrieval_model
-        if (
-            retrieval_model
-            and retrieval_model.reranking_model
-            and retrieval_model.reranking_model.reranking_provider_name
-            and retrieval_model.reranking_model.reranking_model_name
-        ):
-            DatasetService.check_reranking_model_setting(
-                tenant_id,
-                retrieval_model.reranking_model.reranking_provider_name,
-                retrieval_model.reranking_model.reranking_model_name,
-            )
-
-        # indexing_technique is already set in dataset since this is an update
-        args["indexing_technique"] = dataset.indexing_technique
-
-        if args.get("text"):
-            text = args.get("text")
-            name = args.get("name")
-            if not current_user:
-                raise ValueError("current_user is required")
-            upload_file = FileService(db.engine).upload_text(
-                text=str(text), text_name=str(name), user_id=current_user.id, tenant_id=tenant_id
-            )
-            data_source = {
-                "type": "upload_file",
-                "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
-            }
-            args["data_source"] = data_source
-        # validate args
-        args["original_document_id"] = str(document_id)
-        knowledge_config = KnowledgeConfig.model_validate(args)
-        DocumentService.document_create_args_validate(knowledge_config)
-
-        try:
-            documents, batch = DocumentService.save_document_with_dataset_id(
-                dataset=dataset,
-                knowledge_config=knowledge_config,
-                account=current_user,
-                dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
-                created_from="api",
-            )
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        document = documents[0]
-
-        documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
-        return documents_and_batch_fields, 200
+    )
+    @service_api_ns.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @service_api_ns.doc(
+        responses={
+            200: "Document updated successfully",
+            401: "Unauthorized - invalid API token",
+            404: "Document not found",
+        }
+    )
+    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
+    def post(self, tenant_id: str, dataset_id: UUID, document_id: UUID):
+        """Update document by text through the deprecated underscore alias."""
+        return _update_document_by_text(tenant_id=tenant_id, dataset_id=dataset_id, document_id=document_id)
 
 
 @service_api_ns.route(
@@ -400,15 +468,98 @@ class DocumentAddByFileApi(DatasetApiResource):
         return documents_and_batch_fields, 200
 
 
+def _update_document_by_file(tenant_id: str, dataset_id: UUID, document_id: UUID) -> tuple[Mapping[str, object], int]:
+    """Update a document from an uploaded file for canonical and deprecated routes."""
+    dataset_id_str = str(dataset_id)
+    tenant_id_str = str(tenant_id)
+    dataset = db.session.scalar(
+        select(Dataset).where(Dataset.tenant_id == tenant_id_str, Dataset.id == dataset_id_str).limit(1)
+    )
+
+    if not dataset:
+        raise ValueError("Dataset does not exist.")
+
+    if dataset.provider == "external":
+        raise ValueError("External datasets are not supported.")
+
+    args: dict[str, object] = {}
+    if "data" in request.form:
+        args = json.loads(request.form["data"])
+    if "doc_form" not in args:
+        args["doc_form"] = dataset.chunk_structure or "text_model"
+    if "doc_language" not in args:
+        args["doc_language"] = "English"
+
+    # indexing_technique is already set in dataset since this is an update
+    args["indexing_technique"] = dataset.indexing_technique
+
+    if "file" in request.files:
+        # save file info
+        file = request.files["file"]
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if not current_user:
+            raise ValueError("current_user is required")
+
+        try:
+            upload_file = FileService(db.engine).upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source="datasets",
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+        data_source = {
+            "type": "upload_file",
+            "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
+        }
+        args["data_source"] = data_source
+
+    # validate args
+    args["original_document_id"] = str(document_id)
+
+    knowledge_config = KnowledgeConfig.model_validate(args)
+    DocumentService.document_create_args_validate(knowledge_config)
+
+    try:
+        documents, _ = DocumentService.save_document_with_dataset_id(
+            dataset=dataset,
+            knowledge_config=knowledge_config,
+            account=dataset.created_by_account,
+            dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
+            created_from="api",
+        )
+    except ProviderTokenNotInitError as ex:
+        raise ProviderNotInitializeError(ex.description)
+    document = documents[0]
+    documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": document.batch}
+    return documents_and_batch_fields, 200
+
+
 @service_api_ns.route(
     "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file",
     "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-file",
 )
-class DocumentUpdateByFileApi(DatasetApiResource):
-    """Resource for update documents."""
+class DeprecatedDocumentUpdateByFileApi(DatasetApiResource):
+    """Deprecated resource aliases for file document updates."""
 
-    @service_api_ns.doc("update_document_by_file")
-    @service_api_ns.doc(description="Update an existing document by uploading a file")
+    @service_api_ns.doc("update_document_by_file_deprecated")
+    @service_api_ns.doc(deprecated=True)
+    @service_api_ns.doc(
+        description=(
+            "Deprecated legacy alias for updating an existing document by uploading a file. "
+            "Use PATCH /datasets/{dataset_id}/documents/{document_id} instead."
+        )
+    )
     @service_api_ns.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
     @service_api_ns.doc(
         responses={
@@ -419,82 +570,9 @@ class DocumentUpdateByFileApi(DatasetApiResource):
     )
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
-    def post(self, tenant_id, dataset_id, document_id):
-        """Update document by upload file."""
-        dataset = db.session.scalar(
-            select(Dataset).where(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).limit(1)
-        )
-
-        if not dataset:
-            raise ValueError("Dataset does not exist.")
-
-        if dataset.provider == "external":
-            raise ValueError("External datasets are not supported.")
-
-        args = {}
-        if "data" in request.form:
-            args = json.loads(request.form["data"])
-        if "doc_form" not in args:
-            args["doc_form"] = dataset.chunk_structure or "text_model"
-        if "doc_language" not in args:
-            args["doc_language"] = "English"
-
-        # get dataset info
-        dataset_id = str(dataset_id)
-        tenant_id = str(tenant_id)
-
-        # indexing_technique is already set in dataset since this is an update
-        args["indexing_technique"] = dataset.indexing_technique
-
-        if "file" in request.files:
-            # save file info
-            file = request.files["file"]
-
-            if len(request.files) > 1:
-                raise TooManyFilesError()
-
-            if not file.filename:
-                raise FilenameNotExistsError
-
-            if not current_user:
-                raise ValueError("current_user is required")
-
-            try:
-                upload_file = FileService(db.engine).upload_file(
-                    filename=file.filename,
-                    content=file.read(),
-                    mimetype=file.mimetype,
-                    user=current_user,
-                    source="datasets",
-                )
-            except services.errors.file.FileTooLargeError as file_too_large_error:
-                raise FileTooLargeError(file_too_large_error.description)
-            except services.errors.file.UnsupportedFileTypeError:
-                raise UnsupportedFileTypeError()
-            data_source = {
-                "type": "upload_file",
-                "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
-            }
-            args["data_source"] = data_source
-        # validate args
-        args["original_document_id"] = str(document_id)
-
-        knowledge_config = KnowledgeConfig.model_validate(args)
-        DocumentService.document_create_args_validate(knowledge_config)
-
-        try:
-            documents, _ = DocumentService.save_document_with_dataset_id(
-                dataset=dataset,
-                knowledge_config=knowledge_config,
-                account=dataset.created_by_account,
-                dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
-                created_from="api",
-            )
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        document = documents[0]
-        documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": document.batch}
-        return documents_and_batch_fields, 200
+    def post(self, tenant_id: str, dataset_id: UUID, document_id: UUID):
+        """Update document by file through the deprecated file-update aliases."""
+        return _update_document_by_file(tenant_id=tenant_id, dataset_id=dataset_id, document_id=document_id)
 
 
 @service_api_ns.route("/datasets/<uuid:dataset_id>/documents")
@@ -808,6 +886,22 @@ class DocumentApi(DatasetApiResource):
 
         return response
 
+    @service_api_ns.doc("update_document_by_file")
+    @service_api_ns.doc(description="Update an existing document by uploading a file")
+    @service_api_ns.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})
+    @service_api_ns.doc(
+        responses={
+            200: "Document updated successfully",
+            401: "Unauthorized - invalid API token",
+            404: "Document not found",
+        }
+    )
+    @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
+    def patch(self, tenant_id: str, dataset_id: UUID, document_id: UUID):
+        """Update document by file on the canonical document resource."""
+        return _update_document_by_file(tenant_id=tenant_id, dataset_id=dataset_id, document_id=document_id)
+
     @service_api_ns.doc("delete_document")
     @service_api_ns.doc(description="Delete a document")
     @service_api_ns.doc(params={"dataset_id": "Dataset ID", "document_id": "Document ID"})

api/controllers/web/human_input_form.py

@@ -9,11 +9,11 @@ from typing import Any, NotRequired, TypedDict
 
 from flask import Response, request
 from flask_restx import Resource
-from pydantic import BaseModel
 from sqlalchemy import select
 from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
+from controllers.common.human_input import HumanInputFormSubmitPayload
 from controllers.web import web_ns
 from controllers.web.error import NotFoundError, WebFormRateLimitExceededError
 from controllers.web.site import serialize_app_site_payload
@@ -26,11 +26,6 @@ from services.human_input_service import Form, FormNotFoundError, HumanInputServ
 logger = logging.getLogger(__name__)
 
 
-class HumanInputFormSubmitPayload(BaseModel):
-    inputs: dict
-    action: str
-
-
 _FORM_SUBMIT_RATE_LIMITER = RateLimiter(
     prefix="web_form_submit_rate_limit",
     max_attempts=dify_config.WEB_FORM_SUBMIT_RATE_LIMIT_MAX_ATTEMPTS,

api/core/agent/base_agent_runner.py

@@ -42,7 +42,7 @@ from graphon.model_runtime.entities import (
 )
 from graphon.model_runtime.entities.message_entities import ImagePromptMessageContent, PromptMessageContentUnionTypes
 from graphon.model_runtime.entities.model_entities import ModelFeature
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 from models.enums import CreatorUserRole
 from models.model import Conversation, Message, MessageAgentThought, MessageFile
 

api/core/agent/fc_agent_runner.py

@@ -299,7 +299,9 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
             # update prompt tool
             for prompt_tool in prompt_messages_tools:
-                self.update_prompt_message_tool(tool_instances[prompt_tool.name], prompt_tool)
+                tool_instance = tool_instances.get(prompt_tool.name)
+                if tool_instance:
+                    self.update_prompt_message_tool(tool_instance, prompt_tool)
 
             iteration_step += 1
 

api/core/app/app_config/easy_ui_based_app/model_config/converter.py

@@ -7,7 +7,7 @@ from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotIni
 from core.plugin.impl.model_runtime_factory import create_plugin_provider_manager
 from graphon.model_runtime.entities.llm_entities import LLMMode
 from graphon.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 
 
 class ModelConfigConverter:

api/core/app/app_config/features/suggested_questions_after_answer/manager.py

@@ -1,5 +1,7 @@
 from typing import Any
 
+CUSTOM_FOLLOW_UP_PROMPT_MAX_LENGTH = 1000
+
 
 class SuggestedQuestionsAfterAnswerConfigManager:
     @classmethod
@@ -20,7 +22,11 @@ class SuggestedQuestionsAfterAnswerConfigManager:
     @classmethod
     def validate_and_set_defaults(cls, config: dict[str, Any]) -> tuple[dict[str, Any], list[str]]:
         """
-        Validate and set defaults for suggested questions feature
+        Validate and set defaults for suggested questions feature.
+
+        Optional fields:
+        - prompt: custom instruction prompt.
+        - model: provider/model configuration for suggested question generation.
 
         :param config: app model config args
         """
@@ -39,4 +45,27 @@ class SuggestedQuestionsAfterAnswerConfigManager:
         if not isinstance(config["suggested_questions_after_answer"]["enabled"], bool):
             raise ValueError("enabled in suggested_questions_after_answer must be of boolean type")
 
+        prompt = config["suggested_questions_after_answer"].get("prompt")
+        if prompt is not None and not isinstance(prompt, str):
+            raise ValueError("prompt in suggested_questions_after_answer must be of string type")
+        if isinstance(prompt, str) and len(prompt) > CUSTOM_FOLLOW_UP_PROMPT_MAX_LENGTH:
+            raise ValueError(
+                f"prompt in suggested_questions_after_answer must be less than or equal to "
+                f"{CUSTOM_FOLLOW_UP_PROMPT_MAX_LENGTH} characters"
+            )
+
+        if "model" in config["suggested_questions_after_answer"]:
+            model_config = config["suggested_questions_after_answer"]["model"]
+            if not isinstance(model_config, dict):
+                raise ValueError("model in suggested_questions_after_answer must be of object type")
+
+            if "provider" not in model_config or not isinstance(model_config["provider"], str):
+                raise ValueError("provider in suggested_questions_after_answer.model must be of string type")
+
+            if "name" not in model_config or not isinstance(model_config["name"], str):
+                raise ValueError("name in suggested_questions_after_answer.model must be of string type")
+
+            if "completion_params" in model_config and not isinstance(model_config["completion_params"], dict):
+                raise ValueError("completion_params in suggested_questions_after_answer.model must be of object type")
+
         return config, ["suggested_questions_after_answer"]

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

@@ -34,7 +34,11 @@ from core.app.apps.exc import GenerateTaskStoppedError
 from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
 from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
-from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
+from core.app.entities.task_entities import (
+    AdvancedChatPausedBlockingResponse,
+    ChatbotAppBlockingResponse,
+    ChatbotAppStreamResponse,
+)
 from core.app.layers.pause_state_persist_layer import PauseStateLayerConfig, PauseStatePersistenceLayer
 from core.helper.trace_id_helper import extract_external_trace_id_from_args
 from core.ops.ops_trace_manager import TraceQueueManager
@@ -655,7 +659,11 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         user: Account | EndUser,
         draft_var_saver_factory: DraftVariableSaverFactory,
         stream: bool = False,
-    ) -> ChatbotAppBlockingResponse | Generator[ChatbotAppStreamResponse, None, None]:
+    ) -> (
+        ChatbotAppBlockingResponse
+        | AdvancedChatPausedBlockingResponse
+        | Generator[ChatbotAppStreamResponse, None, None]
+    ):
         """
         Handle response.
         :param application_generate_entity: application generate entity

api/core/app/apps/advanced_chat/generate_response_converter.py

@@ -3,7 +3,7 @@ from typing import Any, cast
 
 from core.app.apps.base_app_generate_response_converter import AppGenerateResponseConverter
 from core.app.entities.task_entities import (
-    AppBlockingResponse,
+    AdvancedChatPausedBlockingResponse,
     AppStreamResponse,
     ChatbotAppBlockingResponse,
     ChatbotAppStreamResponse,
@@ -12,22 +12,40 @@ from core.app.entities.task_entities import (
     NodeFinishStreamResponse,
     NodeStartStreamResponse,
     PingStreamResponse,
+    StreamEvent,
 )
 
 
-class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = ChatbotAppBlockingResponse
-
+class AdvancedChatAppGenerateResponseConverter(
+    AppGenerateResponseConverter[ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse]
+):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: AppBlockingResponse) -> dict[str, Any]:
+    def convert_blocking_full_response(
+        cls, blocking_response: ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse
+    ) -> dict[str, Any]:
         """
         Convert blocking full response.
         :param blocking_response: blocking response
         :return:
         """
-        blocking_response = cast(ChatbotAppBlockingResponse, blocking_response)
+        if isinstance(blocking_response, AdvancedChatPausedBlockingResponse):
+            paused_data = blocking_response.data.model_dump(mode="json")
+            return {
+                "event": StreamEvent.WORKFLOW_PAUSED.value,
+                "task_id": blocking_response.task_id,
+                "id": blocking_response.data.id,
+                "message_id": blocking_response.data.message_id,
+                "conversation_id": blocking_response.data.conversation_id,
+                "mode": blocking_response.data.mode,
+                "answer": blocking_response.data.answer,
+                "metadata": blocking_response.data.metadata,
+                "created_at": blocking_response.data.created_at,
+                "workflow_run_id": blocking_response.data.workflow_run_id,
+                "data": paused_data,
+            }
+
         response = {
-            "event": "message",
+            "event": StreamEvent.MESSAGE.value,
             "task_id": blocking_response.task_id,
             "id": blocking_response.data.id,
             "message_id": blocking_response.data.message_id,
@@ -41,7 +59,9 @@ class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
         return response
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: AppBlockingResponse) -> dict[str, Any]:
+    def convert_blocking_simple_response(
+        cls, blocking_response: ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse
+    ) -> dict[str, Any]:
         """
         Convert blocking simple response.
         :param blocking_response: blocking response
@@ -50,7 +70,8 @@ class AdvancedChatAppGenerateResponseConverter(AppGenerateResponseConverter):
         response = cls.convert_blocking_full_response(blocking_response)
 
         metadata = response.get("metadata", {})
-        response["metadata"] = cls._get_simple_metadata(metadata)
+        if isinstance(metadata, dict):
+            response["metadata"] = cls._get_simple_metadata(metadata)
 
         return response
 

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -53,14 +53,18 @@ from core.app.entities.queue_entities import (
     WorkflowQueueMessage,
 )
 from core.app.entities.task_entities import (
+    AdvancedChatPausedBlockingResponse,
     ChatbotAppBlockingResponse,
     ChatbotAppStreamResponse,
     ErrorStreamResponse,
+    HumanInputRequiredPauseReasonPayload,
+    HumanInputRequiredResponse,
     MessageAudioEndStreamResponse,
     MessageAudioStreamResponse,
     MessageEndStreamResponse,
     PingStreamResponse,
     StreamResponse,
+    WorkflowPauseStreamResponse,
     WorkflowTaskState,
 )
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
@@ -210,7 +214,13 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         if message.status == MessageStatus.PAUSED and message.answer:
             self._task_state.answer = message.answer
 
-    def process(self) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
+    def process(
+        self,
+    ) -> Union[
+        ChatbotAppBlockingResponse,
+        AdvancedChatPausedBlockingResponse,
+        Generator[ChatbotAppStreamResponse, None, None],
+    ]:
         """
         Process generate task pipeline.
         :return:
@@ -226,14 +236,39 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         else:
             return self._to_blocking_response(generator)
 
-    def _to_blocking_response(self, generator: Generator[StreamResponse, None, None]) -> ChatbotAppBlockingResponse:
+    def _to_blocking_response(
+        self, generator: Generator[StreamResponse, None, None]
+    ) -> Union[ChatbotAppBlockingResponse, AdvancedChatPausedBlockingResponse]:
         """
         Process blocking response.
         :return:
         """
+        human_input_responses: list[HumanInputRequiredResponse] = []
         for stream_response in generator:
             if isinstance(stream_response, ErrorStreamResponse):
                 raise stream_response.err
+            elif isinstance(stream_response, HumanInputRequiredResponse):
+                human_input_responses.append(stream_response)
+            elif isinstance(stream_response, WorkflowPauseStreamResponse):
+                return AdvancedChatPausedBlockingResponse(
+                    task_id=stream_response.task_id,
+                    data=AdvancedChatPausedBlockingResponse.Data(
+                        id=self._message_id,
+                        mode=self._conversation_mode,
+                        conversation_id=self._conversation_id,
+                        message_id=self._message_id,
+                        workflow_run_id=stream_response.data.workflow_run_id,
+                        answer=self._task_state.answer,
+                        metadata=self._message_end_to_stream_response().metadata,
+                        created_at=self._message_created_at,
+                        paused_nodes=stream_response.data.paused_nodes,
+                        reasons=stream_response.data.reasons,
+                        status=stream_response.data.status,
+                        elapsed_time=stream_response.data.elapsed_time,
+                        total_tokens=stream_response.data.total_tokens,
+                        total_steps=stream_response.data.total_steps,
+                    ),
+                )
             elif isinstance(stream_response, MessageEndStreamResponse):
                 extras = {}
                 if stream_response.metadata:
@@ -254,8 +289,41 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             else:
                 continue
 
+        if human_input_responses:
+            return self._build_paused_blocking_response_from_human_input(human_input_responses)
+
         raise ValueError("queue listening stopped unexpectedly.")
 
+    def _build_paused_blocking_response_from_human_input(
+        self, human_input_responses: list[HumanInputRequiredResponse]
+    ) -> AdvancedChatPausedBlockingResponse:
+        runtime_state = self._resolve_graph_runtime_state()
+        paused_nodes = list(dict.fromkeys(response.data.node_id for response in human_input_responses))
+        reasons = [
+            HumanInputRequiredPauseReasonPayload.from_response_data(response.data).model_dump(mode="json")
+            for response in human_input_responses
+        ]
+
+        return AdvancedChatPausedBlockingResponse(
+            task_id=self._application_generate_entity.task_id,
+            data=AdvancedChatPausedBlockingResponse.Data(
+                id=self._message_id,
+                mode=self._conversation_mode,
+                conversation_id=self._conversation_id,
+                message_id=self._message_id,
+                workflow_run_id=human_input_responses[-1].workflow_run_id,
+                answer=self._task_state.answer,
+                metadata=self._message_end_to_stream_response().metadata,
+                created_at=self._message_created_at,
+                paused_nodes=paused_nodes,
+                reasons=reasons,
+                status=WorkflowExecutionStatus.PAUSED,
+                elapsed_time=time.perf_counter() - self._base_task_pipeline.start_at,
+                total_tokens=runtime_state.total_tokens,
+                total_steps=runtime_state.node_run_steps,
+            ),
+        )
+
     def _to_stream_response(
         self, generator: Generator[StreamResponse, None, None]
     ) -> Generator[ChatbotAppStreamResponse, Any, None]:

api/core/app/apps/agent_chat/app_runner.py

@@ -18,7 +18,7 @@ from core.moderation.base import ModerationError
 from extensions.ext_database import db
 from graphon.model_runtime.entities.llm_entities import LLMMode
 from graphon.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 from models.model import App, Conversation, Message
 
 logger = logging.getLogger(__name__)

api/core/app/apps/agent_chat/generate_response_converter.py

@@ -1,6 +1,8 @@
 from collections.abc import Generator
 from typing import Any, cast
 
+from pydantic import JsonValue
+
 from core.app.apps.base_app_generate_response_converter import AppGenerateResponseConverter
 from core.app.entities.task_entities import (
     AppStreamResponse,
@@ -12,11 +14,9 @@ from core.app.entities.task_entities import (
 )
 
 
-class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = ChatbotAppBlockingResponse
-
+class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter[ChatbotAppBlockingResponse]):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: ChatbotAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_full_response(cls, blocking_response: ChatbotAppBlockingResponse):
         """
         Convert blocking full response.
         :param blocking_response: blocking response
@@ -37,7 +37,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
         return response
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: ChatbotAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_simple_response(cls, blocking_response: ChatbotAppBlockingResponse):
         """
         Convert blocking simple response.
         :param blocking_response: blocking response
@@ -70,7 +70,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,
@@ -101,7 +101,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,

api/core/app/apps/base_app_generate_response_converter.py

@@ -1,7 +1,9 @@
 import logging
 from abc import ABC, abstractmethod
 from collections.abc import Generator, Mapping
-from typing import Any, Union
+from typing import Any, Union, cast
+
+from pydantic import JsonValue
 
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.app.entities.task_entities import AppBlockingResponse, AppStreamResponse
@@ -11,8 +13,10 @@ from graphon.model_runtime.errors.invoke import InvokeError
 logger = logging.getLogger(__name__)
 
 
-class AppGenerateResponseConverter(ABC):
-    _blocking_response_type: type[AppBlockingResponse]
+class AppGenerateResponseConverter[TBlockingResponse: AppBlockingResponse](ABC):
+    @classmethod
+    def _cast_blocking_response(cls, response: AppBlockingResponse) -> TBlockingResponse:
+        return cast(TBlockingResponse, response)
 
     @classmethod
     def convert(
@@ -20,7 +24,7 @@ class AppGenerateResponseConverter(ABC):
     ) -> Mapping[str, Any] | Generator[str | Mapping[str, Any], Any, None]:
         if invoke_from in {InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API}:
             if isinstance(response, AppBlockingResponse):
-                return cls.convert_blocking_full_response(response)
+                return cls.convert_blocking_full_response(cls._cast_blocking_response(response))
             else:
 
                 def _generate_full_response() -> Generator[dict[str, Any] | str, Any, None]:
@@ -29,7 +33,7 @@ class AppGenerateResponseConverter(ABC):
                 return _generate_full_response()
         else:
             if isinstance(response, AppBlockingResponse):
-                return cls.convert_blocking_simple_response(response)
+                return cls.convert_blocking_simple_response(cls._cast_blocking_response(response))
             else:
 
                 def _generate_simple_response() -> Generator[dict[str, Any] | str, Any, None]:
@@ -39,12 +43,12 @@ class AppGenerateResponseConverter(ABC):
 
     @classmethod
     @abstractmethod
-    def convert_blocking_full_response(cls, blocking_response: AppBlockingResponse) -> dict[str, Any]:
+    def convert_blocking_full_response(cls, blocking_response: TBlockingResponse) -> dict[str, Any]:
         raise NotImplementedError
 
     @classmethod
     @abstractmethod
-    def convert_blocking_simple_response(cls, blocking_response: AppBlockingResponse) -> dict[str, Any]:
+    def convert_blocking_simple_response(cls, blocking_response: TBlockingResponse) -> dict[str, Any]:
         raise NotImplementedError
 
     @classmethod
@@ -106,13 +110,13 @@ class AppGenerateResponseConverter(ABC):
         return metadata
 
     @classmethod
-    def _error_to_stream_response(cls, e: Exception) -> dict[str, Any]:
+    def _error_to_stream_response(cls, e: Exception) -> dict[str, JsonValue]:
         """
         Error to stream response.
         :param e: exception
         :return:
         """
-        error_responses: dict[type[Exception], dict[str, Any]] = {
+        error_responses: dict[type[Exception], dict[str, JsonValue]] = {
             ValueError: {"code": "invalid_param", "status": 400},
             ProviderTokenNotInitError: {"code": "provider_not_initialize", "status": 400},
             QuotaExceededError: {
@@ -126,7 +130,7 @@ class AppGenerateResponseConverter(ABC):
         }
 
         # Determine the response based on the type of exception
-        data: dict[str, Any] | None = None
+        data: dict[str, JsonValue] | None = None
         for k, v in error_responses.items():
             if isinstance(e, k):
                 data = v

api/core/app/apps/chat/generate_response_converter.py

@@ -1,6 +1,8 @@
 from collections.abc import Generator
 from typing import Any, cast
 
+from pydantic import JsonValue
+
 from core.app.apps.base_app_generate_response_converter import AppGenerateResponseConverter
 from core.app.entities.task_entities import (
     AppStreamResponse,
@@ -12,11 +14,9 @@ from core.app.entities.task_entities import (
 )
 
 
-class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = ChatbotAppBlockingResponse
-
+class ChatAppGenerateResponseConverter(AppGenerateResponseConverter[ChatbotAppBlockingResponse]):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: ChatbotAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_full_response(cls, blocking_response: ChatbotAppBlockingResponse):
         """
         Convert blocking full response.
         :param blocking_response: blocking response
@@ -37,7 +37,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
         return response
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: ChatbotAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_simple_response(cls, blocking_response: ChatbotAppBlockingResponse):
         """
         Convert blocking simple response.
         :param blocking_response: blocking response
@@ -70,7 +70,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,
@@ -101,7 +101,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,

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

@@ -52,6 +52,7 @@ from core.tools.tool_manager import ToolManager
 from core.trigger.constants import TRIGGER_PLUGIN_NODE_TYPE
 from core.trigger.trigger_manager import TriggerManager
 from core.workflow.human_input_forms import load_form_tokens_by_form_id
+from core.workflow.human_input_policy import HumanInputSurface, enrich_human_input_pause_reasons
 from core.workflow.system_variables import SystemVariableKey, system_variables_to_mapping
 from core.workflow.workflow_entry import WorkflowEntry
 from extensions.ext_database import db
@@ -336,7 +337,26 @@ class WorkflowResponseConverter:
                     except (TypeError, json.JSONDecodeError):
                         definition_payload = {}
                     display_in_ui_by_form_id[str(form_id)] = bool(definition_payload.get("display_in_ui"))
-                form_token_by_form_id = load_form_tokens_by_form_id(human_input_form_ids, session=session)
+                form_token_by_form_id = load_form_tokens_by_form_id(
+                    human_input_form_ids,
+                    session=session,
+                    surface=(
+                        HumanInputSurface.SERVICE_API
+                        if self._application_generate_entity.invoke_from == InvokeFrom.SERVICE_API
+                        else None
+                    ),
+                )
+
+        # Reconnect paths must preserve the same pause-reason contract as live streams;
+        # otherwise clients see schema drift after resume.
+        pause_reasons = enrich_human_input_pause_reasons(
+            pause_reasons,
+            form_tokens_by_form_id=form_token_by_form_id,
+            expiration_times_by_form_id={
+                form_id: int(expiration_time.timestamp())
+                for form_id, expiration_time in expiration_times_by_form_id.items()
+            },
+        )
 
         responses: list[StreamResponse] = []
 

api/core/app/apps/completion/generate_response_converter.py

@@ -1,6 +1,8 @@
 from collections.abc import Generator
 from typing import Any, cast
 
+from pydantic import JsonValue
+
 from core.app.apps.base_app_generate_response_converter import AppGenerateResponseConverter
 from core.app.entities.task_entities import (
     AppStreamResponse,
@@ -12,17 +14,15 @@ from core.app.entities.task_entities import (
 )
 
 
-class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = CompletionAppBlockingResponse
-
+class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter[CompletionAppBlockingResponse]):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: CompletionAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_full_response(cls, blocking_response: CompletionAppBlockingResponse):
         """
         Convert blocking full response.
         :param blocking_response: blocking response
         :return:
         """
-        response = {
+        response: dict[str, Any] = {
             "event": "message",
             "task_id": blocking_response.task_id,
             "id": blocking_response.data.id,
@@ -36,7 +36,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
         return response
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: CompletionAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_simple_response(cls, blocking_response: CompletionAppBlockingResponse):
         """
         Convert blocking simple response.
         :param blocking_response: blocking response
@@ -69,7 +69,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "message_id": chunk.message_id,
                 "created_at": chunk.created_at,
@@ -99,7 +99,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter):
                 yield "ping"
                 continue
 
-            response_chunk = {
+            response_chunk: dict[str, JsonValue] = {
                 "event": sub_stream_response.event.value,
                 "message_id": chunk.message_id,
                 "created_at": chunk.created_at,

api/core/app/apps/message_generator.py

@@ -1,6 +1,7 @@
-from collections.abc import Callable, Generator, Mapping
+from collections.abc import Callable, Generator, Iterable, Mapping
 
 from core.app.apps.streaming_utils import stream_topic_events
+from core.app.entities.task_entities import StreamEvent
 from extensions.ext_redis import get_pubsub_broadcast_channel
 from libs.broadcast_channel.channel import Topic
 from models.model import AppMode
@@ -26,6 +27,7 @@ class MessageGenerator:
         idle_timeout=300,
         ping_interval: float = 10.0,
         on_subscribe: Callable[[], None] | None = None,
+        terminal_events: Iterable[str | StreamEvent] | None = None,
     ) -> Generator[Mapping | str, None, None]:
         topic = cls.get_response_topic(app_mode, workflow_run_id)
         return stream_topic_events(
@@ -33,4 +35,5 @@ class MessageGenerator:
             idle_timeout=idle_timeout,
             ping_interval=ping_interval,
             on_subscribe=on_subscribe,
+            terminal_events=terminal_events,
         )

api/core/app/apps/pipeline/generate_response_converter.py

@@ -13,11 +13,9 @@ from core.app.entities.task_entities import (
 )
 
 
-class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = WorkflowAppBlockingResponse
-
+class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter[WorkflowAppBlockingResponse]):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: WorkflowAppBlockingResponse) -> dict[str, Any]:  # type: ignore[override]
+    def convert_blocking_full_response(cls, blocking_response: WorkflowAppBlockingResponse) -> dict[str, object]:
         """
         Convert blocking full response.
         :param blocking_response: blocking response
@@ -26,7 +24,7 @@ class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
         return dict(blocking_response.model_dump())
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: WorkflowAppBlockingResponse) -> dict[str, Any]:  # type: ignore[override]
+    def convert_blocking_simple_response(cls, blocking_response: WorkflowAppBlockingResponse) -> dict[str, object]:
         """
         Convert blocking simple response.
         :param blocking_response: blocking response

api/core/app/apps/pipeline/pipeline_generator.py

@@ -27,7 +27,11 @@ from core.app.apps.workflow.generate_response_converter import WorkflowAppGenera
 from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
 from core.app.entities.app_invoke_entities import InvokeFrom, RagPipelineGenerateEntity
 from core.app.entities.rag_pipeline_invoke_entities import RagPipelineInvokeEntity
-from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
+from core.app.entities.task_entities import (
+    WorkflowAppBlockingResponse,
+    WorkflowAppPausedBlockingResponse,
+    WorkflowAppStreamResponse,
+)
 from core.datasource.entities.datasource_entities import (
     DatasourceProviderType,
     OnlineDriveBrowseFilesRequest,
@@ -627,7 +631,11 @@ class PipelineGenerator(BaseAppGenerator):
         user: Account | EndUser,
         draft_var_saver_factory: DraftVariableSaverFactory,
         stream: bool = False,
-    ) -> WorkflowAppBlockingResponse | Generator[WorkflowAppStreamResponse, None, None]:
+    ) -> (
+        WorkflowAppBlockingResponse
+        | WorkflowAppPausedBlockingResponse
+        | Generator[WorkflowAppStreamResponse, None, None]
+    ):
         """
         Handle response.
         :param application_generate_entity: application generate entity

api/core/app/apps/streaming_utils.py

@@ -59,7 +59,7 @@ def stream_topic_events(
 
 
 def _normalize_terminal_events(terminal_events: Iterable[str | StreamEvent] | None) -> set[str]:
-    if not terminal_events:
+    if terminal_events is None:
         return {StreamEvent.WORKFLOW_FINISHED.value, StreamEvent.WORKFLOW_PAUSED.value}
     values: set[str] = set()
     for item in terminal_events:

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

@@ -25,7 +25,11 @@ from core.app.apps.workflow.app_runner import WorkflowAppRunner
 from core.app.apps.workflow.generate_response_converter import WorkflowAppGenerateResponseConverter
 from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
 from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerateEntity
-from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
+from core.app.entities.task_entities import (
+    WorkflowAppBlockingResponse,
+    WorkflowAppPausedBlockingResponse,
+    WorkflowAppStreamResponse,
+)
 from core.app.layers.pause_state_persist_layer import PauseStateLayerConfig, PauseStatePersistenceLayer
 from core.db.session_factory import session_factory
 from core.helper.trace_id_helper import extract_external_trace_id_from_args
@@ -612,7 +616,11 @@ class WorkflowAppGenerator(BaseAppGenerator):
         user: Account | EndUser,
         draft_var_saver_factory: DraftVariableSaverFactory,
         stream: bool = False,
-    ) -> WorkflowAppBlockingResponse | Generator[WorkflowAppStreamResponse, None, None]:
+    ) -> (
+        WorkflowAppBlockingResponse
+        | WorkflowAppPausedBlockingResponse
+        | Generator[WorkflowAppStreamResponse, None, None]
+    ):
         """
         Handle response.
         :param application_generate_entity: application generate entity

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

@@ -9,24 +9,29 @@ from core.app.entities.task_entities import (
     NodeStartStreamResponse,
     PingStreamResponse,
     WorkflowAppBlockingResponse,
+    WorkflowAppPausedBlockingResponse,
     WorkflowAppStreamResponse,
 )
 
 
-class WorkflowAppGenerateResponseConverter(AppGenerateResponseConverter):
-    _blocking_response_type = WorkflowAppBlockingResponse
-
+class WorkflowAppGenerateResponseConverter(
+    AppGenerateResponseConverter[WorkflowAppBlockingResponse | WorkflowAppPausedBlockingResponse]
+):
     @classmethod
-    def convert_blocking_full_response(cls, blocking_response: WorkflowAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_full_response(
+        cls, blocking_response: WorkflowAppBlockingResponse | WorkflowAppPausedBlockingResponse
+    ) -> dict[str, Any]:
         """
         Convert blocking full response.
         :param blocking_response: blocking response
         :return:
         """
-        return blocking_response.model_dump()
+        return dict(blocking_response.model_dump())
 
     @classmethod
-    def convert_blocking_simple_response(cls, blocking_response: WorkflowAppBlockingResponse):  # type: ignore[override]
+    def convert_blocking_simple_response(
+        cls, blocking_response: WorkflowAppBlockingResponse | WorkflowAppPausedBlockingResponse
+    ) -> dict[str, Any]:
         """
         Convert blocking simple response.
         :param blocking_response: blocking response

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

@@ -42,12 +42,15 @@ from core.app.entities.queue_entities import (
 )
 from core.app.entities.task_entities import (
     ErrorStreamResponse,
+    HumanInputRequiredPauseReasonPayload,
+    HumanInputRequiredResponse,
     MessageAudioEndStreamResponse,
     MessageAudioStreamResponse,
     PingStreamResponse,
     StreamResponse,
     TextChunkStreamResponse,
     WorkflowAppBlockingResponse,
+    WorkflowAppPausedBlockingResponse,
     WorkflowAppStreamResponse,
     WorkflowFinishStreamResponse,
     WorkflowPauseStreamResponse,
@@ -118,7 +121,11 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         )
         self._graph_runtime_state: GraphRuntimeState | None = self._base_task_pipeline.queue_manager.graph_runtime_state
 
-    def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
+    def process(
+        self,
+    ) -> Union[
+        WorkflowAppBlockingResponse, WorkflowAppPausedBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]
+    ]:
         """
         Process generate task pipeline.
         :return:
@@ -129,19 +136,24 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         else:
             return self._to_blocking_response(generator)
 
-    def _to_blocking_response(self, generator: Generator[StreamResponse, None, None]) -> WorkflowAppBlockingResponse:
+    def _to_blocking_response(
+        self, generator: Generator[StreamResponse, None, None]
+    ) -> Union[WorkflowAppBlockingResponse, WorkflowAppPausedBlockingResponse]:
         """
         To blocking response.
         :return:
         """
+        human_input_responses: list[HumanInputRequiredResponse] = []
         for stream_response in generator:
             if isinstance(stream_response, ErrorStreamResponse):
                 raise stream_response.err
+            elif isinstance(stream_response, HumanInputRequiredResponse):
+                human_input_responses.append(stream_response)
             elif isinstance(stream_response, WorkflowPauseStreamResponse):
-                response = WorkflowAppBlockingResponse(
+                return WorkflowAppPausedBlockingResponse(
                     task_id=self._application_generate_entity.task_id,
                     workflow_run_id=stream_response.data.workflow_run_id,
-                    data=WorkflowAppBlockingResponse.Data(
+                    data=WorkflowAppPausedBlockingResponse.Data(
                         id=stream_response.data.workflow_run_id,
                         workflow_id=self._workflow.id,
                         status=stream_response.data.status,
@@ -152,12 +164,13 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
                         total_steps=stream_response.data.total_steps,
                         created_at=stream_response.data.created_at,
                         finished_at=None,
+                        paused_nodes=stream_response.data.paused_nodes,
+                        reasons=stream_response.data.reasons,
                     ),
                 )
 
-                return response
             elif isinstance(stream_response, WorkflowFinishStreamResponse):
-                response = WorkflowAppBlockingResponse(
+                return WorkflowAppBlockingResponse(
                     task_id=self._application_generate_entity.task_id,
                     workflow_run_id=stream_response.data.id,
                     data=WorkflowAppBlockingResponse.Data(
@@ -174,12 +187,44 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
                     ),
                 )
 
-                return response
             else:
                 continue
 
+        if human_input_responses:
+            return self._build_paused_blocking_response_from_human_input(human_input_responses)
+
         raise ValueError("queue listening stopped unexpectedly.")
 
+    def _build_paused_blocking_response_from_human_input(
+        self, human_input_responses: list[HumanInputRequiredResponse]
+    ) -> WorkflowAppPausedBlockingResponse:
+        runtime_state = self._resolve_graph_runtime_state()
+        paused_nodes = list(dict.fromkeys(response.data.node_id for response in human_input_responses))
+        created_at = int(runtime_state.start_at)
+        reasons = [
+            HumanInputRequiredPauseReasonPayload.from_response_data(response.data).model_dump(mode="json")
+            for response in human_input_responses
+        ]
+
+        return WorkflowAppPausedBlockingResponse(
+            task_id=self._application_generate_entity.task_id,
+            workflow_run_id=human_input_responses[-1].workflow_run_id,
+            data=WorkflowAppPausedBlockingResponse.Data(
+                id=human_input_responses[-1].workflow_run_id,
+                workflow_id=self._workflow.id,
+                status=WorkflowExecutionStatus.PAUSED,
+                outputs={},
+                error=None,
+                elapsed_time=time.perf_counter() - self._base_task_pipeline.start_at,
+                total_tokens=runtime_state.total_tokens,
+                total_steps=runtime_state.node_run_steps,
+                created_at=created_at,
+                finished_at=None,
+                paused_nodes=paused_nodes,
+                reasons=reasons,
+            ),
+        )
+
     def _to_stream_response(
         self, generator: Generator[StreamResponse, None, None]
     ) -> Generator[WorkflowAppStreamResponse, None, None]:

api/core/app/entities/task_entities.py

@@ -1,12 +1,13 @@
 from collections.abc import Mapping, Sequence
 from enum import StrEnum
-from typing import Any
+from typing import Any, Literal
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, ConfigDict, Field, JsonValue
 
 from core.app.entities.agent_strategy import AgentStrategyInfo
 from core.rag.entities import RetrievalSourceMetadata
 from graphon.entities import WorkflowStartReason
+from graphon.entities.pause_reason import PauseReasonType
 from graphon.enums import WorkflowExecutionStatus, WorkflowNodeExecutionMetadataKey, WorkflowNodeExecutionStatus
 from graphon.model_runtime.entities.llm_entities import LLMResult, LLMUsage
 from graphon.nodes.human_input.entities import FormInput, UserAction
@@ -295,6 +296,40 @@ class HumanInputRequiredResponse(StreamResponse):
     data: Data
 
 
+class HumanInputRequiredPauseReasonPayload(BaseModel):
+    """
+    Public pause-reason payload used by blocking responses when only
+    ``human_input_required`` events are available.
+    """
+
+    TYPE: Literal[PauseReasonType.HUMAN_INPUT_REQUIRED] = PauseReasonType.HUMAN_INPUT_REQUIRED
+    form_id: str
+    node_id: str
+    node_title: str
+    form_content: str
+    inputs: Sequence[FormInput] = Field(default_factory=list)
+    actions: Sequence[UserAction] = Field(default_factory=list)
+    display_in_ui: bool = False
+    form_token: str | None = None
+    resolved_default_values: Mapping[str, Any] = Field(default_factory=dict)
+    expiration_time: int
+
+    @classmethod
+    def from_response_data(cls, data: HumanInputRequiredResponse.Data) -> "HumanInputRequiredPauseReasonPayload":
+        return cls(
+            form_id=data.form_id,
+            node_id=data.node_id,
+            node_title=data.node_title,
+            form_content=data.form_content,
+            inputs=data.inputs,
+            actions=data.actions,
+            display_in_ui=data.display_in_ui,
+            form_token=data.form_token,
+            resolved_default_values=data.resolved_default_values,
+            expiration_time=data.expiration_time,
+        )
+
+
 class HumanInputFormFilledResponse(StreamResponse):
     class Data(BaseModel):
         """
@@ -355,7 +390,7 @@ class NodeStartStreamResponse(StreamResponse):
     workflow_run_id: str
     data: Data
 
-    def to_ignore_detail_dict(self):
+    def to_ignore_detail_dict(self) -> dict[str, JsonValue]:
         return {
             "event": self.event.value,
             "task_id": self.task_id,
@@ -412,7 +447,7 @@ class NodeFinishStreamResponse(StreamResponse):
     workflow_run_id: str
     data: Data
 
-    def to_ignore_detail_dict(self):
+    def to_ignore_detail_dict(self) -> dict[str, JsonValue]:
         return {
             "event": self.event.value,
             "task_id": self.task_id,
@@ -774,6 +809,34 @@ class ChatbotAppBlockingResponse(AppBlockingResponse):
     data: Data
 
 
+class AdvancedChatPausedBlockingResponse(AppBlockingResponse):
+    """
+    ChatbotAppPausedBlockingResponse entity
+    """
+
+    class Data(BaseModel):
+        """
+        Data entity
+        """
+
+        id: str
+        mode: str
+        conversation_id: str
+        message_id: str
+        workflow_run_id: str
+        answer: str
+        metadata: Mapping[str, object] = Field(default_factory=dict)
+        created_at: int
+        paused_nodes: Sequence[str] = Field(default_factory=list)
+        reasons: Sequence[Mapping[str, Any]] = Field(default_factory=list[Mapping[str, Any]])
+        status: WorkflowExecutionStatus
+        elapsed_time: float
+        total_tokens: int
+        total_steps: int
+
+    data: Data
+
+
 class CompletionAppBlockingResponse(AppBlockingResponse):
     """
     CompletionAppBlockingResponse entity
@@ -819,6 +882,33 @@ class WorkflowAppBlockingResponse(AppBlockingResponse):
     data: Data
 
 
+class WorkflowAppPausedBlockingResponse(AppBlockingResponse):
+    """
+    WorkflowAppPausedBlockingResponse entity
+    """
+
+    class Data(BaseModel):
+        """
+        Data entity
+        """
+
+        id: str
+        workflow_id: str
+        status: WorkflowExecutionStatus
+        outputs: Mapping[str, Any] | None = None
+        error: str | None = None
+        elapsed_time: float
+        total_tokens: int
+        total_steps: int
+        created_at: int
+        finished_at: int | None
+        paused_nodes: Sequence[str] = Field(default_factory=list)
+        reasons: Sequence[Mapping[str, Any]] = Field(default_factory=list)
+
+    workflow_run_id: str
+    data: Data
+
+
 class AgentLogStreamResponse(StreamResponse):
     """
     AgentLogStreamResponse entity

api/core/app/file_access/scope.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from collections.abc import Iterator
+from collections.abc import Generator  # Changed from Iterator
 from contextlib import contextmanager
 from contextvars import ContextVar
 from dataclasses import dataclass
@@ -32,7 +32,7 @@ def get_current_file_access_scope() -> FileAccessScope | None:
 
 
 @contextmanager
-def bind_file_access_scope(scope: FileAccessScope) -> Iterator[None]:
+def bind_file_access_scope(scope: FileAccessScope) -> Generator[None, None, None]:  # Changed from Iterator[None]
     token = _current_file_access_scope.set(scope)
     try:
         yield

api/core/app/llm/model_access.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from copy import deepcopy
 from typing import Any
 
 from core.app.entities.app_invoke_entities import DifyRunContext, ModelConfigWithCredentialsEntity
@@ -14,8 +15,21 @@ from graphon.nodes.llm.protocols import CredentialsProvider
 
 
 class DifyCredentialsProvider:
+    """Resolves and returns LLM credentials for a given provider and model.
+
+    Fetched credentials are stored in :attr:`credentials_cache` and reused for
+    subsequent ``fetch`` calls for the same ``(provider_name, model_name)``.
+    Because of that cache, a single instance can return stale credentials after
+    the tenant or provider configuration changes (e.g. API key rotation).
+
+    Do **not** keep one instance for the lifetime of a process or across
+    unrelated invocations. Create a new provider per request, workflow run, or
+    other bounded scope where up-to-date credentials matter.
+    """
+
     tenant_id: str
     provider_manager: ProviderManager
+    credentials_cache: dict[tuple[str, str], dict[str, Any]]
 
     def __init__(
         self,
@@ -30,8 +44,12 @@ class DifyCredentialsProvider:
                 user_id=run_context.user_id,
             )
         self.provider_manager = provider_manager
+        self.credentials_cache = {}
 
     def fetch(self, provider_name: str, model_name: str) -> dict[str, Any]:
+        if (provider_name, model_name) in self.credentials_cache:
+            return deepcopy(self.credentials_cache[(provider_name, model_name)])
+
         provider_configurations = self.provider_manager.get_configurations(self.tenant_id)
         provider_configuration = provider_configurations.get(provider_name)
         if not provider_configuration:
@@ -46,6 +64,7 @@ class DifyCredentialsProvider:
         if credentials is None:
             raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
 
+        self.credentials_cache[(provider_name, model_name)] = deepcopy(credentials)
         return credentials
 
 
@@ -65,7 +84,8 @@ class DifyModelFactory:
                 provider_manager=create_plugin_provider_manager(
                     tenant_id=run_context.tenant_id,
                     user_id=run_context.user_id,
-                )
+                ),
+                enable_credentials_cache=True,
             )
         self.model_manager = model_manager
 
@@ -84,7 +104,7 @@ def build_dify_model_access(run_context: DifyRunContext) -> tuple[CredentialsPro
         tenant_id=run_context.tenant_id,
         user_id=run_context.user_id,
     )
-    model_manager = ModelManager(provider_manager=provider_manager)
+    model_manager = ModelManager(provider_manager=provider_manager, enable_credentials_cache=True)
 
     return (
         DifyCredentialsProvider(run_context=run_context, provider_manager=provider_manager),

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -59,7 +59,7 @@ from graphon.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     TextPromptMessageContent,
 )
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 from libs.datetime_utils import naive_utc_now
 from models.model import AppMode, Conversation, Message, MessageAgentThought, MessageFile, UploadFile
 

api/core/app/workflow/file_runtime.py

@@ -12,13 +12,14 @@ from typing import TYPE_CHECKING, Literal
 from configs import dify_config
 from core.app.file_access import DatabaseFileAccessController, FileAccessControllerProtocol
 from core.db.session_factory import session_factory
-from core.helper.ssrf_proxy import ssrf_proxy
+from core.helper.ssrf_proxy import graphon_ssrf_proxy
 from core.tools.signature import sign_tool_file
 from core.workflow.file_reference import parse_file_reference
 from extensions.ext_storage import storage
 from graphon.file import FileTransferMethod
-from graphon.file.protocols import HttpResponseProtocol, WorkflowFileRuntimeProtocol
+from graphon.file.protocols import WorkflowFileRuntimeProtocol
 from graphon.file.runtime import set_workflow_file_runtime
+from graphon.http.protocols import HttpResponseProtocol
 
 if TYPE_CHECKING:
     from graphon.file import File
@@ -43,7 +44,7 @@ class DifyWorkflowFileRuntime(WorkflowFileRuntimeProtocol):
         return dify_config.MULTIMODAL_SEND_FORMAT
 
     def http_get(self, url: str, *, follow_redirects: bool = True) -> HttpResponseProtocol:
-        return ssrf_proxy.get(url, follow_redirects=follow_redirects)
+        return graphon_ssrf_proxy.get(url, follow_redirects=follow_redirects)
 
     def storage_load(self, path: str, *, stream: bool = False) -> bytes | Generator:
         return storage.load(path, stream=stream)

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

@@ -349,7 +349,7 @@ class WorkflowPersistenceLayer(GraphEngineLayer):
         execution.total_tokens = runtime_state.total_tokens
         execution.total_steps = runtime_state.node_run_steps
         execution.outputs = execution.outputs or runtime_state.outputs
-        execution.exceptions_count = runtime_state.exceptions_count
+        execution.exceptions_count = max(execution.exceptions_count, runtime_state.exceptions_count)
 
     def _update_node_execution(
         self,

api/core/datasource/datasource_manager.py

@@ -352,11 +352,11 @@ class DatasourceManager:
                 raise ValueError(f"UploadFile not found for file_id={file_id}, tenant_id={tenant_id}")
 
         file_info = File(
-            id=upload_file.id,
+            file_id=upload_file.id,
             filename=upload_file.name,
             extension="." + upload_file.extension,
             mime_type=upload_file.mime_type,
-            type=FileType.CUSTOM,
+            file_type=FileType.CUSTOM,
             transfer_method=FileTransferMethod.LOCAL_FILE,
             remote_url=upload_file.source_url,
             reference=build_file_reference(record_id=str(upload_file.id)),

api/core/entities/provider_configuration.py

@@ -31,7 +31,7 @@ from graphon.model_runtime.entities.provider_entities import (
     FormType,
     ProviderEntity,
 )
-from graphon.model_runtime.model_providers.__base.ai_model import AIModel
+from graphon.model_runtime.model_providers.base.ai_model import AIModel
 from graphon.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
 from graphon.model_runtime.runtime import ModelRuntime
 from libs.datetime_utils import naive_utc_now
@@ -318,34 +318,28 @@ class ProviderConfiguration(BaseModel):
             else [],
         )
 
-    def validate_provider_credentials(
-        self, credentials: dict[str, Any], credential_id: str = "", session: Session | None = None
-    ):
+    def validate_provider_credentials(self, credentials: dict[str, Any], credential_id: str = ""):
         """
         Validate custom credentials.
         :param credentials: provider credentials
         :param credential_id: (Optional)If provided, can use existing credential's hidden api key to validate
-        :param session: optional database session
         :return:
         """
+        provider_credential_secret_variables = self.extract_secret_variables(
+            self.provider.provider_credential_schema.credential_form_schemas
+            if self.provider.provider_credential_schema
+            else []
+        )
 
-        def _validate(s: Session):
-            # Get provider credential secret variables
-            provider_credential_secret_variables = self.extract_secret_variables(
-                self.provider.provider_credential_schema.credential_form_schemas
-                if self.provider.provider_credential_schema
-                else []
-            )
-
-            if credential_id:
+        if credential_id:
+            with Session(db.engine) as session:
                 try:
                     stmt = select(ProviderCredential).where(
                         ProviderCredential.tenant_id == self.tenant_id,
                         ProviderCredential.provider_name.in_(self._get_provider_names()),
                         ProviderCredential.id == credential_id,
                     )
-                    credential_record = s.execute(stmt).scalar_one_or_none()
-                    # fix origin data
+                    credential_record = session.execute(stmt).scalar_one_or_none()
                     if credential_record and credential_record.encrypted_config:
                         if not credential_record.encrypted_config.startswith("{"):
                             original_credentials = {"openai_api_key": credential_record.encrypted_config}
@@ -356,31 +350,23 @@ class ProviderConfiguration(BaseModel):
                 except JSONDecodeError:
                     original_credentials = {}
 
-                # encrypt credentials
-                for key, value in credentials.items():
-                    if key in provider_credential_secret_variables:
-                        # if send [__HIDDEN__] in secret input, it will be same as original value
-                        if value == HIDDEN_VALUE and key in original_credentials:
-                            credentials[key] = encrypter.decrypt_token(
-                                tenant_id=self.tenant_id, token=original_credentials[key]
-                            )
-
-            model_provider_factory = self.get_model_provider_factory()
-            validated_credentials = model_provider_factory.provider_credentials_validate(
-                provider=self.provider.provider, credentials=credentials
-            )
-
-            for key, value in validated_credentials.items():
+            for key, value in credentials.items():
                 if key in provider_credential_secret_variables:
-                    validated_credentials[key] = encrypter.encrypt_token(self.tenant_id, value)
+                    if value == HIDDEN_VALUE and key in original_credentials:
+                        credentials[key] = encrypter.decrypt_token(
+                            tenant_id=self.tenant_id, token=original_credentials[key]
+                        )
 
-            return validated_credentials
+        model_provider_factory = self.get_model_provider_factory()
+        validated_credentials = model_provider_factory.provider_credentials_validate(
+            provider=self.provider.provider, credentials=credentials
+        )
 
-        if session:
-            return _validate(session)
-        else:
-            with Session(db.engine) as new_session:
-                return _validate(new_session)
+        for key, value in validated_credentials.items():
+            if key in provider_credential_secret_variables and isinstance(value, str):
+                validated_credentials[key] = encrypter.encrypt_token(self.tenant_id, value)
+
+        return validated_credentials
 
     def _generate_provider_credential_name(self, session) -> str:
         """
@@ -457,14 +443,16 @@ class ProviderConfiguration(BaseModel):
         :param credential_name: credential name
         :return:
         """
-        with Session(db.engine) as session:
+        with Session(db.engine) as pre_session:
             if credential_name:
-                if self._check_provider_credential_name_exists(credential_name=credential_name, session=session):
+                if self._check_provider_credential_name_exists(credential_name=credential_name, session=pre_session):
                     raise ValueError(f"Credential with name '{credential_name}' already exists.")
             else:
-                credential_name = self._generate_provider_credential_name(session)
+                credential_name = self._generate_provider_credential_name(pre_session)
 
-            credentials = self.validate_provider_credentials(credentials=credentials, session=session)
+        credentials = self.validate_provider_credentials(credentials=credentials)
+
+        with Session(db.engine) as session:
             provider_record = self._get_provider_record(session)
             try:
                 new_record = ProviderCredential(
@@ -477,7 +465,6 @@ class ProviderConfiguration(BaseModel):
                 session.flush()
 
                 if not provider_record:
-                    # If provider record does not exist, create it
                     provider_record = Provider(
                         tenant_id=self.tenant_id,
                         provider_name=self.provider.provider,
@@ -530,15 +517,15 @@ class ProviderConfiguration(BaseModel):
         :param credential_name: credential name
         :return:
         """
-        with Session(db.engine) as session:
+        with Session(db.engine) as pre_session:
             if credential_name and self._check_provider_credential_name_exists(
-                credential_name=credential_name, session=session, exclude_id=credential_id
+                credential_name=credential_name, session=pre_session, exclude_id=credential_id
             ):
                 raise ValueError(f"Credential with name '{credential_name}' already exists.")
 
-            credentials = self.validate_provider_credentials(
-                credentials=credentials, credential_id=credential_id, session=session
-            )
+        credentials = self.validate_provider_credentials(credentials=credentials, credential_id=credential_id)
+
+        with Session(db.engine) as session:
             provider_record = self._get_provider_record(session)
             stmt = select(ProviderCredential).where(
                 ProviderCredential.id == credential_id,
@@ -546,12 +533,10 @@ class ProviderConfiguration(BaseModel):
                 ProviderCredential.provider_name.in_(self._get_provider_names()),
             )
 
-            # Get the credential record to update
             credential_record = session.execute(stmt).scalar_one_or_none()
             if not credential_record:
                 raise ValueError("Credential record not found.")
             try:
-                # Update credential
                 credential_record.encrypted_config = json.dumps(credentials)
                 credential_record.updated_at = naive_utc_now()
                 if credential_name:
@@ -879,7 +864,6 @@ class ProviderConfiguration(BaseModel):
         model: str,
         credentials: dict[str, Any],
         credential_id: str = "",
-        session: Session | None = None,
     ):
         """
         Validate custom model credentials.
@@ -890,16 +874,14 @@ class ProviderConfiguration(BaseModel):
         :param credential_id: (Optional)If provided, can use existing credential's hidden api key to validate
         :return:
         """
+        provider_credential_secret_variables = self.extract_secret_variables(
+            self.provider.model_credential_schema.credential_form_schemas
+            if self.provider.model_credential_schema
+            else []
+        )
 
-        def _validate(s: Session):
-            # Get provider credential secret variables
-            provider_credential_secret_variables = self.extract_secret_variables(
-                self.provider.model_credential_schema.credential_form_schemas
-                if self.provider.model_credential_schema
-                else []
-            )
-
-            if credential_id:
+        if credential_id:
+            with Session(db.engine) as session:
                 try:
                     stmt = select(ProviderModelCredential).where(
                         ProviderModelCredential.id == credential_id,
@@ -908,7 +890,7 @@ class ProviderConfiguration(BaseModel):
                         ProviderModelCredential.model_name == model,
                         ProviderModelCredential.model_type == model_type,
                     )
-                    credential_record = s.execute(stmt).scalar_one_or_none()
+                    credential_record = session.execute(stmt).scalar_one_or_none()
                     original_credentials = (
                         json.loads(credential_record.encrypted_config)
                         if credential_record and credential_record.encrypted_config
@@ -917,31 +899,23 @@ class ProviderConfiguration(BaseModel):
                 except JSONDecodeError:
                     original_credentials = {}
 
-                # decrypt credentials
-                for key, value in credentials.items():
-                    if key in provider_credential_secret_variables:
-                        # if send [__HIDDEN__] in secret input, it will be same as original value
-                        if value == HIDDEN_VALUE and key in original_credentials:
-                            credentials[key] = encrypter.decrypt_token(
-                                tenant_id=self.tenant_id, token=original_credentials[key]
-                            )
-
-            model_provider_factory = self.get_model_provider_factory()
-            validated_credentials = model_provider_factory.model_credentials_validate(
-                provider=self.provider.provider, model_type=model_type, model=model, credentials=credentials
-            )
-
-            for key, value in validated_credentials.items():
+            for key, value in credentials.items():
                 if key in provider_credential_secret_variables:
-                    validated_credentials[key] = encrypter.encrypt_token(self.tenant_id, value)
+                    if value == HIDDEN_VALUE and key in original_credentials:
+                        credentials[key] = encrypter.decrypt_token(
+                            tenant_id=self.tenant_id, token=original_credentials[key]
+                        )
 
-            return validated_credentials
+        model_provider_factory = self.get_model_provider_factory()
+        validated_credentials = model_provider_factory.model_credentials_validate(
+            provider=self.provider.provider, model_type=model_type, model=model, credentials=credentials
+        )
 
-        if session:
-            return _validate(session)
-        else:
-            with Session(db.engine) as new_session:
-                return _validate(new_session)
+        for key, value in validated_credentials.items():
+            if key in provider_credential_secret_variables and isinstance(value, str):
+                validated_credentials[key] = encrypter.encrypt_token(self.tenant_id, value)
+
+        return validated_credentials
 
     def create_custom_model_credential(
         self, model_type: ModelType, model: str, credentials: dict[str, Any], credential_name: str | None
@@ -954,20 +928,22 @@ class ProviderConfiguration(BaseModel):
         :param credentials: model credentials dict
         :return:
         """
-        with Session(db.engine) as session:
+        with Session(db.engine) as pre_session:
             if credential_name:
                 if self._check_custom_model_credential_name_exists(
-                    model=model, model_type=model_type, credential_name=credential_name, session=session
+                    model=model, model_type=model_type, credential_name=credential_name, session=pre_session
                 ):
                     raise ValueError(f"Model credential with name '{credential_name}' already exists for {model}.")
             else:
                 credential_name = self._generate_custom_model_credential_name(
-                    model=model, model_type=model_type, session=session
+                    model=model, model_type=model_type, session=pre_session
                 )
-            # validate custom model config
-            credentials = self.validate_custom_model_credentials(
-                model_type=model_type, model=model, credentials=credentials, session=session
-            )
+
+        credentials = self.validate_custom_model_credentials(
+            model_type=model_type, model=model, credentials=credentials
+        )
+
+        with Session(db.engine) as session:
             provider_model_record = self._get_custom_model_record(model_type=model_type, model=model, session=session)
 
             try:
@@ -982,7 +958,6 @@ class ProviderConfiguration(BaseModel):
                 session.add(credential)
                 session.flush()
 
-                # save provider model
                 if not provider_model_record:
                     provider_model_record = ProviderModel(
                         tenant_id=self.tenant_id,
@@ -1024,23 +999,24 @@ class ProviderConfiguration(BaseModel):
         :param credential_id: credential id
         :return:
         """
-        with Session(db.engine) as session:
+        with Session(db.engine) as pre_session:
             if credential_name and self._check_custom_model_credential_name_exists(
                 model=model,
                 model_type=model_type,
                 credential_name=credential_name,
-                session=session,
+                session=pre_session,
                 exclude_id=credential_id,
             ):
                 raise ValueError(f"Model credential with name '{credential_name}' already exists for {model}.")
-            # validate custom model config
-            credentials = self.validate_custom_model_credentials(
-                model_type=model_type,
-                model=model,
-                credentials=credentials,
-                credential_id=credential_id,
-                session=session,
-            )
+
+        credentials = self.validate_custom_model_credentials(
+            model_type=model_type,
+            model=model,
+            credentials=credentials,
+            credential_id=credential_id,
+        )
+
+        with Session(db.engine) as session:
             provider_model_record = self._get_custom_model_record(model_type=model_type, model=model, session=session)
 
             stmt = select(ProviderModelCredential).where(
@@ -1055,7 +1031,6 @@ class ProviderConfiguration(BaseModel):
                 raise ValueError("Credential record not found.")
 
             try:
-                # Update credential
                 credential_record.encrypted_config = json.dumps(credentials)
                 credential_record.updated_at = naive_utc_now()
                 if credential_name:

api/core/helper/code_executor/template_transformer.py

@@ -102,7 +102,7 @@ class TemplateTransformer(ABC):
 
     @classmethod
     def serialize_inputs(cls, inputs: Mapping[str, Any]) -> str:
-        inputs_json_str = dumps_with_segments(inputs, ensure_ascii=False).encode()
+        inputs_json_str = dumps_with_segments(inputs).encode()
         input_base64_encoded = b64encode(inputs_json_str).decode("utf-8")
         return input_base64_encoded
 

api/core/helper/creators.py

@@ -0,0 +1,41 @@
+"""
+Helper module for Creators Platform integration.
+
+Provides functionality to upload DSL files to the Creators Platform
+and generate redirect URLs with OAuth authorization codes.
+"""
+
+import logging
+from urllib.parse import urlencode
+
+import httpx
+from yarl import URL
+
+from configs import dify_config
+
+logger = logging.getLogger(__name__)
+
+creators_platform_api_url = URL(str(dify_config.CREATORS_PLATFORM_API_URL))
+
+
+def upload_dsl(dsl_file_bytes: bytes, filename: str = "template.yaml") -> str:
+    url = str(creators_platform_api_url / "api/v1/templates/anonymous-upload")
+    response = httpx.post(url, files={"file": (filename, dsl_file_bytes)}, timeout=30)
+    response.raise_for_status()
+    data = response.json()
+    claim_code = data.get("data", {}).get("claim_code")
+    if not claim_code:
+        raise ValueError("Creators Platform did not return a valid claim_code")
+    return claim_code
+
+
+def get_redirect_url(user_account_id: str, claim_code: str) -> str:
+    base_url = str(dify_config.CREATORS_PLATFORM_API_URL).rstrip("/")
+    params: dict[str, str] = {"dsl_claim_code": claim_code}
+    client_id = str(dify_config.CREATORS_PLATFORM_OAUTH_CLIENT_ID or "")
+    if client_id:
+        from services.oauth_server import OAuthServerService
+
+        oauth_code = OAuthServerService.sign_oauth_authorization_code(client_id, user_account_id)
+        params["oauth_code"] = oauth_code
+    return f"{base_url}?{urlencode(params)}"

api/core/helper/moderation.py

@@ -8,7 +8,7 @@ from core.plugin.impl.model_runtime_factory import create_plugin_model_provider_
 from extensions.ext_hosting_provider import hosting_configuration
 from graphon.model_runtime.entities.model_entities import ModelType
 from graphon.model_runtime.errors.invoke import InvokeBadRequestError
-from graphon.model_runtime.model_providers.__base.moderation_model import ModerationModel
+from graphon.model_runtime.model_providers.base.moderation_model import ModerationModel
 from models.provider import ProviderType
 
 logger = logging.getLogger(__name__)

api/core/helper/ssrf_proxy.py

@@ -12,6 +12,7 @@ from pydantic import TypeAdapter, ValidationError
 from configs import dify_config
 from core.helper.http_client_pooling import get_pooled_http_client
 from core.tools.errors import ToolSSRFError
+from graphon.http.response import HttpResponse
 
 logger = logging.getLogger(__name__)
 
@@ -267,4 +268,47 @@ class SSRFProxy:
         return patch(url=url, max_retries=max_retries, **kwargs)
 
 
+def _to_graphon_http_response(response: httpx.Response) -> HttpResponse:
+    """Convert an ``httpx`` response into Graphon's transport-agnostic wrapper."""
+    return HttpResponse(
+        status_code=response.status_code,
+        headers=dict(response.headers),
+        content=response.content,
+        url=str(response.url) if response.url else None,
+        reason_phrase=response.reason_phrase,
+        fallback_text=response.text,
+    )
+
+
+class GraphonSSRFProxy:
+    """Adapter exposing SSRF helpers behind Graphon's ``HttpClientProtocol``."""
+
+    @property
+    def max_retries_exceeded_error(self) -> type[Exception]:
+        return max_retries_exceeded_error
+
+    @property
+    def request_error(self) -> type[Exception]:
+        return request_error
+
+    def get(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(get(url=url, max_retries=max_retries, **kwargs))
+
+    def head(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(head(url=url, max_retries=max_retries, **kwargs))
+
+    def post(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(post(url=url, max_retries=max_retries, **kwargs))
+
+    def put(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(put(url=url, max_retries=max_retries, **kwargs))
+
+    def delete(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(delete(url=url, max_retries=max_retries, **kwargs))
+
+    def patch(self, url: str, max_retries: int = SSRF_DEFAULT_MAX_RETRIES, **kwargs: Any) -> HttpResponse:
+        return _to_graphon_http_response(patch(url=url, max_retries=max_retries, **kwargs))
+
+
 ssrf_proxy = SSRFProxy()
+graphon_ssrf_proxy = GraphonSSRFProxy()

api/core/llm_generator/llm_generator.py

@@ -2,7 +2,7 @@ import json
 import logging
 import re
 from collections.abc import Sequence
-from typing import Any, Protocol, TypedDict, cast
+from typing import Any, NotRequired, Protocol, TypedDict, cast
 
 import json_repair
 from sqlalchemy import select
@@ -18,8 +18,6 @@ from core.llm_generator.prompts import (
     LLM_MODIFY_CODE_SYSTEM,
     LLM_MODIFY_PROMPT_SYSTEM,
     PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE,
-    SUGGESTED_QUESTIONS_MAX_TOKENS,
-    SUGGESTED_QUESTIONS_TEMPERATURE,
     SYSTEM_STRUCTURED_OUTPUT_GENERATE,
     WORKFLOW_RULE_CONFIG_PROMPT_GENERATE_TEMPLATE,
 )
@@ -41,6 +39,36 @@ from models.workflow import Workflow
 logger = logging.getLogger(__name__)
 
 
+class SuggestedQuestionsModelConfig(TypedDict):
+    provider: str
+    name: str
+    completion_params: NotRequired[dict[str, object]]
+
+
+def _normalize_completion_params(completion_params: dict[str, object]) -> tuple[dict[str, object], list[str]]:
+    """
+    Normalize raw completion params into invocation parameters and stop sequences.
+
+    This mirrors the app-model access path by separating ``stop`` from provider
+    parameters before invocation, then drops non-positive token limits because
+    some plugin-backed models reject ``0`` after mapping ``max_tokens`` to their
+    provider-specific output-token field.
+    """
+    normalized_parameters = dict(completion_params)
+    stop_value = normalized_parameters.pop("stop", [])
+    if isinstance(stop_value, list) and all(isinstance(item, str) for item in stop_value):
+        stop = stop_value
+    else:
+        stop = []
+
+    for token_limit_key in ("max_tokens", "max_output_tokens"):
+        token_limit = normalized_parameters.get(token_limit_key)
+        if isinstance(token_limit, int | float) and token_limit <= 0:
+            normalized_parameters.pop(token_limit_key, None)
+
+    return normalized_parameters, stop
+
+
 class WorkflowServiceInterface(Protocol):
     def get_draft_workflow(self, app_model: App, workflow_id: str | None = None) -> Workflow | None:
         pass
@@ -123,8 +151,15 @@ class LLMGenerator:
         return name
 
     @classmethod
-    def generate_suggested_questions_after_answer(cls, tenant_id: str, histories: str) -> Sequence[str]:
-        output_parser = SuggestedQuestionsAfterAnswerOutputParser()
+    def generate_suggested_questions_after_answer(
+        cls,
+        tenant_id: str,
+        histories: str,
+        *,
+        instruction_prompt: str | None = None,
+        model_config: object | None = None,
+    ) -> Sequence[str]:
+        output_parser = SuggestedQuestionsAfterAnswerOutputParser(instruction_prompt=instruction_prompt)
         format_instructions = output_parser.get_format_instructions()
 
         prompt_template = PromptTemplateParser(template="{{histories}}\n{{format_instructions}}\nquestions:\n")
@@ -133,10 +168,36 @@ class LLMGenerator:
 
         try:
             model_manager = ModelManager.for_tenant(tenant_id=tenant_id)
-            model_instance = model_manager.get_default_model_instance(
-                tenant_id=tenant_id,
-                model_type=ModelType.LLM,
-            )
+            configured_model = cast(dict[str, object], model_config) if isinstance(model_config, dict) else {}
+            provider = configured_model.get("provider")
+            model_name = configured_model.get("name")
+            use_configured_model = False
+
+            if isinstance(provider, str) and provider and isinstance(model_name, str) and model_name:
+                try:
+                    model_instance = model_manager.get_model_instance(
+                        tenant_id=tenant_id,
+                        model_type=ModelType.LLM,
+                        provider=provider,
+                        model=model_name,
+                    )
+                    use_configured_model = True
+                except Exception:
+                    logger.warning(
+                        "Failed to use configured suggested-questions model %s/%s, fallback to default model",
+                        provider,
+                        model_name,
+                        exc_info=True,
+                    )
+                    model_instance = model_manager.get_default_model_instance(
+                        tenant_id=tenant_id,
+                        model_type=ModelType.LLM,
+                    )
+            else:
+                model_instance = model_manager.get_default_model_instance(
+                    tenant_id=tenant_id,
+                    model_type=ModelType.LLM,
+                )
         except InvokeAuthorizationError:
             return []
 
@@ -145,19 +206,29 @@ class LLMGenerator:
         questions: Sequence[str] = []
 
         try:
+            configured_completion_params = configured_model.get("completion_params")
+            if use_configured_model and isinstance(configured_completion_params, dict):
+                model_parameters, stop = _normalize_completion_params(configured_completion_params)
+            elif use_configured_model:
+                model_parameters = {}
+                stop = []
+            else:
+                # Default-model generation keeps the built-in suggested-questions tuning.
+                model_parameters = {
+                    "max_tokens": 2560,
+                    "temperature": 0.0,
+                }
+                stop = []
+
             response: LLMResult = model_instance.invoke_llm(
                 prompt_messages=list(prompt_messages),
-                model_parameters={
-                    "max_tokens": SUGGESTED_QUESTIONS_MAX_TOKENS,
-                    "temperature": SUGGESTED_QUESTIONS_TEMPERATURE,
-                },
+                model_parameters=model_parameters,
+                stop=stop,
                 stream=False,
             )
 
             text_content = response.message.get_text_content()
             questions = output_parser.parse(text_content) if text_content else []
-        except InvokeError:
-            questions = []
         except Exception:
             logger.exception("Failed to generate suggested questions after answer")
             questions = []

api/core/llm_generator/output_parser/suggested_questions_after_answer.py

@@ -3,17 +3,28 @@ import logging
 import re
 from collections.abc import Sequence
 
-from core.llm_generator.prompts import SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
+from core.llm_generator.prompts import DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
 
 logger = logging.getLogger(__name__)
 
 
 class SuggestedQuestionsAfterAnswerOutputParser:
+    def __init__(self, instruction_prompt: str | None = None) -> None:
+        self._instruction_prompt = self._build_instruction_prompt(instruction_prompt)
+
+    @staticmethod
+    def _build_instruction_prompt(instruction_prompt: str | None) -> str:
+        if not instruction_prompt or not instruction_prompt.strip():
+            return DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
+
+        return f'{instruction_prompt}\nYou must output a JSON array like ["question1", "question2", "question3"].'
+
     def get_format_instructions(self) -> str:
-        return SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
+        return self._instruction_prompt
 
     def parse(self, text: str) -> Sequence[str]:
-        action_match = re.search(r"\[.*?\]", text.strip(), re.DOTALL)
+        stripped_text = text.strip()
+        action_match = re.search(r"\[.*?\]", stripped_text, re.DOTALL)
         questions: list[str] = []
         if action_match is not None:
             try:
@@ -23,4 +34,6 @@ class SuggestedQuestionsAfterAnswerOutputParser:
             else:
                 if isinstance(json_obj, list):
                     questions = [question for question in json_obj if isinstance(question, str)]
+        elif stripped_text:
+            logger.warning("Failed to find suggested questions payload array in text: %r", stripped_text[:200])
         return questions

api/core/llm_generator/prompts.py

@@ -1,5 +1,4 @@
 # Written by YORKI MINAKO🤡, Edited by Xiaoyi, Edited by yasu-oh
-import os
 
 CONVERSATION_TITLE_PROMPT = """You are asked to generate a concise chat title by decomposing the user’s input into two parts: “Intention” and “Subject”.
 
@@ -96,8 +95,8 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 )
 
 
-# Default prompt for suggested questions (can be overridden by environment variable)
-_DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_PROMPT = (
+# Default prompt and model parameters for suggested questions.
+DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
     "Please help me predict the three most likely questions that human would ask, "
     "and keep each question under 20 characters.\n"
     "MAKE SURE your output is the SAME language as the Assistant's latest response. "
@@ -105,15 +104,6 @@ _DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_PROMPT = (
     '["question1","question2","question3"]\n'
 )
 
-# Environment variable override for suggested questions prompt
-SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = os.getenv(
-    "SUGGESTED_QUESTIONS_PROMPT", _DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_PROMPT
-)
-
-# Configurable LLM parameters for suggested questions (can be overridden by environment variables)
-SUGGESTED_QUESTIONS_MAX_TOKENS = int(os.getenv("SUGGESTED_QUESTIONS_MAX_TOKENS", "256"))
-SUGGESTED_QUESTIONS_TEMPERATURE = float(os.getenv("SUGGESTED_QUESTIONS_TEMPERATURE", "0"))
-
 GENERATOR_QA_PROMPT = (
     "<Task> The user will send a long text. Generate a Question and Answer pairs only using the knowledge"
     " in the long text. Please think step by step."

api/core/mcp/client/streamable_client.py

@@ -303,9 +303,16 @@ class StreamableHTTPTransport:
 
             if response.status_code == 404:
                 if isinstance(message.root, JSONRPCRequest):
+                    error_msg = (
+                        f"MCP server URL returned 404 Not Found: {self.url} "
+                        "— verify the server URL is correct and the server is running"
+                        if is_initialization
+                        else "Session terminated by server"
+                    )
                     self._send_session_terminated_error(
                         ctx.server_to_client_queue,
                         message.root.id,
+                        message=error_msg,
                     )
                 return
 
@@ -381,12 +388,13 @@ class StreamableHTTPTransport:
         self,
         server_to_client_queue: ServerToClientQueue,
         request_id: RequestId,
+        message: str = "Session terminated by server",
     ):
         """Send a session terminated error response."""
         jsonrpc_error = JSONRPCError(
             jsonrpc="2.0",
             id=request_id,
-            error=ErrorData(code=32600, message="Session terminated by server"),
+            error=ErrorData(code=32600, message=message),
         )
         session_message = SessionMessage(JSONRPCMessage(jsonrpc_error))
         server_to_client_queue.put(session_message)

api/core/model_manager.py

@@ -1,6 +1,7 @@
 import logging
 from collections.abc import Callable, Generator, Iterable, Mapping, Sequence
-from typing import IO, Any, Literal, Optional, Union, cast, overload
+from copy import deepcopy
+from typing import IO, Any, Literal, Optional, ParamSpec, TypeVar, Union, cast, overload
 
 from configs import dify_config
 from core.entities import PluginCredentialType
@@ -18,15 +19,17 @@ from graphon.model_runtime.entities.model_entities import AIModelEntity, ModelFe
 from graphon.model_runtime.entities.rerank_entities import MultimodalRerankInput, RerankResult
 from graphon.model_runtime.entities.text_embedding_entities import EmbeddingResult
 from graphon.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeConnectionError, InvokeRateLimitError
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
-from graphon.model_runtime.model_providers.__base.moderation_model import ModerationModel
-from graphon.model_runtime.model_providers.__base.rerank_model import RerankModel
-from graphon.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
-from graphon.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
-from graphon.model_runtime.model_providers.__base.tts_model import TTSModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.moderation_model import ModerationModel
+from graphon.model_runtime.model_providers.base.rerank_model import RerankModel
+from graphon.model_runtime.model_providers.base.speech2text_model import Speech2TextModel
+from graphon.model_runtime.model_providers.base.text_embedding_model import TextEmbeddingModel
+from graphon.model_runtime.model_providers.base.tts_model import TTSModel
 from models.provider import ProviderType
 
 logger = logging.getLogger(__name__)
+P = ParamSpec("P")
+R = TypeVar("R")
 
 
 class ModelInstance:
@@ -34,11 +37,13 @@ class ModelInstance:
     Model instance class.
     """
 
-    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str):
+    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str, credentials: dict | None = None) -> None:
         self.provider_model_bundle = provider_model_bundle
         self.model_name = model
         self.provider = provider_model_bundle.configuration.provider.provider
-        self.credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
+        if credentials is None:
+            credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
+        self.credentials = credentials
         # Runtime LLM invocation fields.
         self.parameters: Mapping[str, Any] = {}
         self.stop: Sequence[str] = ()
@@ -168,7 +173,7 @@ class ModelInstance:
         return cast(
             Union[LLMResult, Generator],
             self._round_robin_invoke(
-                function=self.model_type_instance.invoke,
+                self.model_type_instance.invoke,
                 model=self.model_name,
                 credentials=self.credentials,
                 prompt_messages=list(prompt_messages),
@@ -193,7 +198,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, LargeLanguageModel):
             raise Exception("Model type instance is not LargeLanguageModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.get_num_tokens,
+            self.model_type_instance.get_num_tokens,
             model=self.model_name,
             credentials=self.credentials,
             prompt_messages=list(prompt_messages),
@@ -213,7 +218,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, TextEmbeddingModel):
             raise Exception("Model type instance is not TextEmbeddingModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             texts=texts,
@@ -235,7 +240,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, TextEmbeddingModel):
             raise Exception("Model type instance is not TextEmbeddingModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             multimodel_documents=multimodel_documents,
@@ -252,7 +257,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, TextEmbeddingModel):
             raise Exception("Model type instance is not TextEmbeddingModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.get_num_tokens,
+            self.model_type_instance.get_num_tokens,
             model=self.model_name,
             credentials=self.credentials,
             texts=texts,
@@ -277,7 +282,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, RerankModel):
             raise Exception("Model type instance is not RerankModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             query=query,
@@ -305,7 +310,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, RerankModel):
             raise Exception("Model type instance is not RerankModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke_multimodal_rerank,
+            self.model_type_instance.invoke_multimodal_rerank,
             model=self.model_name,
             credentials=self.credentials,
             query=query,
@@ -324,7 +329,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, ModerationModel):
             raise Exception("Model type instance is not ModerationModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             text=text,
@@ -340,7 +345,7 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, Speech2TextModel):
             raise Exception("Model type instance is not Speech2TextModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             file=file,
@@ -357,14 +362,14 @@ class ModelInstance:
         if not isinstance(self.model_type_instance, TTSModel):
             raise Exception("Model type instance is not TTSModel")
         return self._round_robin_invoke(
-            function=self.model_type_instance.invoke,
+            self.model_type_instance.invoke,
             model=self.model_name,
             credentials=self.credentials,
             content_text=content_text,
             voice=voice,
         )
 
-    def _round_robin_invoke[**P, R](self, function: Callable[P, R], *args: P.args, **kwargs: P.kwargs) -> R:
+    def _round_robin_invoke(self, function: Callable[P, R], *args: P.args, **kwargs: P.kwargs) -> R:
         """
         Round-robin invoke
         :param function: function to invoke
@@ -432,8 +437,30 @@ class ModelInstance:
 
 
 class ModelManager:
-    def __init__(self, provider_manager: ProviderManager):
+    """Resolves :class:`ModelInstance` objects for a tenant and provider.
+
+    When ``enable_credentials_cache`` is ``True``, resolved credentials for each
+    ``(tenant_id, provider, model_type, model)`` are stored in
+    ``_credentials_cache`` and reused. That can return **stale** credentials after
+    API keys or provider settings change, so a manager constructed with
+    ``enable_credentials_cache=True`` should not be kept for the lifetime of a
+    process or shared across unrelated work. Prefer a new manager per request,
+    workflow run, or similar bounded scope.
+
+    The default is ``enable_credentials_cache=False``; in that mode the internal
+    credential cache is not populated, and each ``get_model_instance`` call
+    loads credentials from the current provider configuration.
+    """
+
+    def __init__(
+        self,
+        provider_manager: ProviderManager,
+        *,
+        enable_credentials_cache: bool = False,
+    ) -> None:
         self._provider_manager = provider_manager
+        self._credentials_cache: dict[tuple[str, str, str, str], Any] = {}
+        self._enable_credentials_cache = enable_credentials_cache
 
     @classmethod
     def for_tenant(cls, tenant_id: str, user_id: str | None = None) -> "ModelManager":
@@ -461,8 +488,19 @@ class ModelManager:
             tenant_id=tenant_id, provider=provider, model_type=model_type
         )
 
-        model_instance = ModelInstance(provider_model_bundle, model)
-        return model_instance
+        cred_cache_key = (tenant_id, provider, model_type.value, model)
+
+        if cred_cache_key in self._credentials_cache:
+            return ModelInstance(
+                provider_model_bundle,
+                model,
+                deepcopy(self._credentials_cache[cred_cache_key]),
+            )
+
+        ret = ModelInstance(provider_model_bundle, model)
+        if self._enable_credentials_cache:
+            self._credentials_cache[cred_cache_key] = deepcopy(ret.credentials)
+        return ret
 
     def get_default_provider_model_name(self, tenant_id: str, model_type: ModelType) -> tuple[str | None, str | None]:
         """

api/core/ops/entities/config_entity.py

@@ -1,8 +1,8 @@
 from enum import StrEnum
 
-from pydantic import BaseModel, ValidationInfo, field_validator
+from pydantic import BaseModel
 
-from core.ops.utils import validate_integer_id, validate_project_name, validate_url, validate_url_with_path
+from core.ops.utils import validate_project_name, validate_url
 
 
 class TracingProviderEnum(StrEnum):
@@ -52,220 +52,5 @@ class BaseTracingConfig(BaseModel):
         return validate_project_name(v, default_name)
 
 
-class ArizeConfig(BaseTracingConfig):
-    """
-    Model class for Arize tracing config.
-    """
-
-    api_key: str | None = None
-    space_id: str | None = None
-    project: str | None = None
-    endpoint: str = "https://otlp.arize.com"
-
-    @field_validator("project")
-    @classmethod
-    def project_validator(cls, v, info: ValidationInfo):
-        return cls.validate_project_field(v, "default")
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        return cls.validate_endpoint_url(v, "https://otlp.arize.com")
-
-
-class PhoenixConfig(BaseTracingConfig):
-    """
-    Model class for Phoenix tracing config.
-    """
-
-    api_key: str | None = None
-    project: str | None = None
-    endpoint: str = "https://app.phoenix.arize.com"
-
-    @field_validator("project")
-    @classmethod
-    def project_validator(cls, v, info: ValidationInfo):
-        return cls.validate_project_field(v, "default")
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        return validate_url_with_path(v, "https://app.phoenix.arize.com")
-
-
-class LangfuseConfig(BaseTracingConfig):
-    """
-    Model class for Langfuse tracing config.
-    """
-
-    public_key: str
-    secret_key: str
-    host: str = "https://api.langfuse.com"
-
-    @field_validator("host")
-    @classmethod
-    def host_validator(cls, v, info: ValidationInfo):
-        return validate_url_with_path(v, "https://api.langfuse.com")
-
-
-class LangSmithConfig(BaseTracingConfig):
-    """
-    Model class for Langsmith tracing config.
-    """
-
-    api_key: str
-    project: str
-    endpoint: str = "https://api.smith.langchain.com"
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        # LangSmith only allows HTTPS
-        return validate_url(v, "https://api.smith.langchain.com", allowed_schemes=("https",))
-
-
-class OpikConfig(BaseTracingConfig):
-    """
-    Model class for Opik tracing config.
-    """
-
-    api_key: str | None = None
-    project: str | None = None
-    workspace: str | None = None
-    url: str = "https://www.comet.com/opik/api/"
-
-    @field_validator("project")
-    @classmethod
-    def project_validator(cls, v, info: ValidationInfo):
-        return cls.validate_project_field(v, "Default Project")
-
-    @field_validator("url")
-    @classmethod
-    def url_validator(cls, v, info: ValidationInfo):
-        return validate_url_with_path(v, "https://www.comet.com/opik/api/", required_suffix="/api/")
-
-
-class WeaveConfig(BaseTracingConfig):
-    """
-    Model class for Weave tracing config.
-    """
-
-    api_key: str
-    entity: str | None = None
-    project: str
-    endpoint: str = "https://trace.wandb.ai"
-    host: str | None = None
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        # Weave only allows HTTPS for endpoint
-        return validate_url(v, "https://trace.wandb.ai", allowed_schemes=("https",))
-
-    @field_validator("host")
-    @classmethod
-    def host_validator(cls, v, info: ValidationInfo):
-        if v is not None and v.strip() != "":
-            return validate_url(v, v, allowed_schemes=("https", "http"))
-        return v
-
-
-class AliyunConfig(BaseTracingConfig):
-    """
-    Model class for Aliyun tracing config.
-    """
-
-    app_name: str = "dify_app"
-    license_key: str
-    endpoint: str
-
-    @field_validator("app_name")
-    @classmethod
-    def app_name_validator(cls, v, info: ValidationInfo):
-        return cls.validate_project_field(v, "dify_app")
-
-    @field_validator("license_key")
-    @classmethod
-    def license_key_validator(cls, v, info: ValidationInfo):
-        if not v or v.strip() == "":
-            raise ValueError("License key cannot be empty")
-        return v
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        # aliyun uses two URL formats, which may include a URL path
-        return validate_url_with_path(v, "https://tracing-analysis-dc-hz.aliyuncs.com")
-
-
-class TencentConfig(BaseTracingConfig):
-    """
-    Tencent APM tracing config
-    """
-
-    token: str
-    endpoint: str
-    service_name: str
-
-    @field_validator("token")
-    @classmethod
-    def token_validator(cls, v, info: ValidationInfo):
-        if not v or v.strip() == "":
-            raise ValueError("Token cannot be empty")
-        return v
-
-    @field_validator("endpoint")
-    @classmethod
-    def endpoint_validator(cls, v, info: ValidationInfo):
-        return cls.validate_endpoint_url(v, "https://apm.tencentcloudapi.com")
-
-    @field_validator("service_name")
-    @classmethod
-    def service_name_validator(cls, v, info: ValidationInfo):
-        return cls.validate_project_field(v, "dify_app")
-
-
-class MLflowConfig(BaseTracingConfig):
-    """
-    Model class for MLflow tracing config.
-    """
-
-    tracking_uri: str = "http://localhost:5000"
-    experiment_id: str = "0"  # Default experiment id in MLflow is 0
-    username: str | None = None
-    password: str | None = None
-
-    @field_validator("tracking_uri")
-    @classmethod
-    def tracking_uri_validator(cls, v, info: ValidationInfo):
-        if isinstance(v, str) and v.startswith("databricks"):
-            raise ValueError(
-                "Please use Databricks tracing config below to record traces to Databricks-managed MLflow instances."
-            )
-        return validate_url_with_path(v, "http://localhost:5000")
-
-    @field_validator("experiment_id")
-    @classmethod
-    def experiment_id_validator(cls, v, info: ValidationInfo):
-        return validate_integer_id(v)
-
-
-class DatabricksConfig(BaseTracingConfig):
-    """
-    Model class for Databricks (Databricks-managed MLflow) tracing config.
-    """
-
-    experiment_id: str
-    host: str
-    client_id: str | None = None
-    client_secret: str | None = None
-    personal_access_token: str | None = None
-
-    @field_validator("experiment_id")
-    @classmethod
-    def experiment_id_validator(cls, v, info: ValidationInfo):
-        return validate_integer_id(v)
-
-
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"

api/core/ops/ops_trace_manager.py

@@ -204,114 +204,117 @@ class TracingProviderConfigEntry(TypedDict):
 
 class OpsTraceProviderConfigMap(collections.UserDict[str, TracingProviderConfigEntry]):
     def __getitem__(self, provider: str) -> TracingProviderConfigEntry:
-        match provider:
-            case TracingProviderEnum.LANGFUSE:
-                from core.ops.entities.config_entity import LangfuseConfig
-                from core.ops.langfuse_trace.langfuse_trace import LangFuseDataTrace
+        try:
+            match provider:
+                case TracingProviderEnum.LANGFUSE:
+                    from dify_trace_langfuse.config import LangfuseConfig
+                    from dify_trace_langfuse.langfuse_trace import LangFuseDataTrace
 
-                return {
-                    "config_class": LangfuseConfig,
-                    "secret_keys": ["public_key", "secret_key"],
-                    "other_keys": ["host", "project_key"],
-                    "trace_instance": LangFuseDataTrace,
-                }
+                    return {
+                        "config_class": LangfuseConfig,
+                        "secret_keys": ["public_key", "secret_key"],
+                        "other_keys": ["host", "project_key"],
+                        "trace_instance": LangFuseDataTrace,
+                    }
 
-            case TracingProviderEnum.LANGSMITH:
-                from core.ops.entities.config_entity import LangSmithConfig
-                from core.ops.langsmith_trace.langsmith_trace import LangSmithDataTrace
+                case TracingProviderEnum.LANGSMITH:
+                    from dify_trace_langsmith.config import LangSmithConfig
+                    from dify_trace_langsmith.langsmith_trace import LangSmithDataTrace
 
-                return {
-                    "config_class": LangSmithConfig,
-                    "secret_keys": ["api_key"],
-                    "other_keys": ["project", "endpoint"],
-                    "trace_instance": LangSmithDataTrace,
-                }
+                    return {
+                        "config_class": LangSmithConfig,
+                        "secret_keys": ["api_key"],
+                        "other_keys": ["project", "endpoint"],
+                        "trace_instance": LangSmithDataTrace,
+                    }
 
-            case TracingProviderEnum.OPIK:
-                from core.ops.entities.config_entity import OpikConfig
-                from core.ops.opik_trace.opik_trace import OpikDataTrace
+                case TracingProviderEnum.OPIK:
+                    from dify_trace_opik.config import OpikConfig
+                    from dify_trace_opik.opik_trace import OpikDataTrace
 
-                return {
-                    "config_class": OpikConfig,
-                    "secret_keys": ["api_key"],
-                    "other_keys": ["project", "url", "workspace"],
-                    "trace_instance": OpikDataTrace,
-                }
+                    return {
+                        "config_class": OpikConfig,
+                        "secret_keys": ["api_key"],
+                        "other_keys": ["project", "url", "workspace"],
+                        "trace_instance": OpikDataTrace,
+                    }
 
-            case TracingProviderEnum.WEAVE:
-                from core.ops.entities.config_entity import WeaveConfig
-                from core.ops.weave_trace.weave_trace import WeaveDataTrace
+                case TracingProviderEnum.WEAVE:
+                    from dify_trace_weave.config import WeaveConfig
+                    from dify_trace_weave.weave_trace import WeaveDataTrace
 
-                return {
-                    "config_class": WeaveConfig,
-                    "secret_keys": ["api_key"],
-                    "other_keys": ["project", "entity", "endpoint", "host"],
-                    "trace_instance": WeaveDataTrace,
-                }
-            case TracingProviderEnum.ARIZE:
-                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
-                from core.ops.entities.config_entity import ArizeConfig
+                    return {
+                        "config_class": WeaveConfig,
+                        "secret_keys": ["api_key"],
+                        "other_keys": ["project", "entity", "endpoint", "host"],
+                        "trace_instance": WeaveDataTrace,
+                    }
+                case TracingProviderEnum.ARIZE:
+                    from dify_trace_arize_phoenix.arize_phoenix_trace import ArizePhoenixDataTrace
+                    from dify_trace_arize_phoenix.config import ArizeConfig
 
-                return {
-                    "config_class": ArizeConfig,
-                    "secret_keys": ["api_key", "space_id"],
-                    "other_keys": ["project", "endpoint"],
-                    "trace_instance": ArizePhoenixDataTrace,
-                }
-            case TracingProviderEnum.PHOENIX:
-                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
-                from core.ops.entities.config_entity import PhoenixConfig
+                    return {
+                        "config_class": ArizeConfig,
+                        "secret_keys": ["api_key", "space_id"],
+                        "other_keys": ["project", "endpoint"],
+                        "trace_instance": ArizePhoenixDataTrace,
+                    }
+                case TracingProviderEnum.PHOENIX:
+                    from dify_trace_arize_phoenix.arize_phoenix_trace import ArizePhoenixDataTrace
+                    from dify_trace_arize_phoenix.config import PhoenixConfig
 
-                return {
-                    "config_class": PhoenixConfig,
-                    "secret_keys": ["api_key"],
-                    "other_keys": ["project", "endpoint"],
-                    "trace_instance": ArizePhoenixDataTrace,
-                }
-            case TracingProviderEnum.ALIYUN:
-                from core.ops.aliyun_trace.aliyun_trace import AliyunDataTrace
-                from core.ops.entities.config_entity import AliyunConfig
+                    return {
+                        "config_class": PhoenixConfig,
+                        "secret_keys": ["api_key"],
+                        "other_keys": ["project", "endpoint"],
+                        "trace_instance": ArizePhoenixDataTrace,
+                    }
+                case TracingProviderEnum.ALIYUN:
+                    from dify_trace_aliyun.aliyun_trace import AliyunDataTrace
+                    from dify_trace_aliyun.config import AliyunConfig
 
-                return {
-                    "config_class": AliyunConfig,
-                    "secret_keys": ["license_key"],
-                    "other_keys": ["endpoint", "app_name"],
-                    "trace_instance": AliyunDataTrace,
-                }
-            case TracingProviderEnum.MLFLOW:
-                from core.ops.entities.config_entity import MLflowConfig
-                from core.ops.mlflow_trace.mlflow_trace import MLflowDataTrace
+                    return {
+                        "config_class": AliyunConfig,
+                        "secret_keys": ["license_key"],
+                        "other_keys": ["endpoint", "app_name"],
+                        "trace_instance": AliyunDataTrace,
+                    }
+                case TracingProviderEnum.MLFLOW:
+                    from dify_trace_mlflow.config import MLflowConfig
+                    from dify_trace_mlflow.mlflow_trace import MLflowDataTrace
 
-                return {
-                    "config_class": MLflowConfig,
-                    "secret_keys": ["password"],
-                    "other_keys": ["tracking_uri", "experiment_id", "username"],
-                    "trace_instance": MLflowDataTrace,
-                }
-            case TracingProviderEnum.DATABRICKS:
-                from core.ops.entities.config_entity import DatabricksConfig
-                from core.ops.mlflow_trace.mlflow_trace import MLflowDataTrace
+                    return {
+                        "config_class": MLflowConfig,
+                        "secret_keys": ["password"],
+                        "other_keys": ["tracking_uri", "experiment_id", "username"],
+                        "trace_instance": MLflowDataTrace,
+                    }
+                case TracingProviderEnum.DATABRICKS:
+                    from dify_trace_mlflow.config import DatabricksConfig
+                    from dify_trace_mlflow.mlflow_trace import MLflowDataTrace
 
-                return {
-                    "config_class": DatabricksConfig,
-                    "secret_keys": ["personal_access_token", "client_secret"],
-                    "other_keys": ["host", "client_id", "experiment_id"],
-                    "trace_instance": MLflowDataTrace,
-                }
+                    return {
+                        "config_class": DatabricksConfig,
+                        "secret_keys": ["personal_access_token", "client_secret"],
+                        "other_keys": ["host", "client_id", "experiment_id"],
+                        "trace_instance": MLflowDataTrace,
+                    }
 
-            case TracingProviderEnum.TENCENT:
-                from core.ops.entities.config_entity import TencentConfig
-                from core.ops.tencent_trace.tencent_trace import TencentDataTrace
+                case TracingProviderEnum.TENCENT:
+                    from dify_trace_tencent.config import TencentConfig
+                    from dify_trace_tencent.tencent_trace import TencentDataTrace
 
-                return {
-                    "config_class": TencentConfig,
-                    "secret_keys": ["token"],
-                    "other_keys": ["endpoint", "service_name"],
-                    "trace_instance": TencentDataTrace,
-                }
+                    return {
+                        "config_class": TencentConfig,
+                        "secret_keys": ["token"],
+                        "other_keys": ["endpoint", "service_name"],
+                        "trace_instance": TencentDataTrace,
+                    }
 
-            case _:
-                raise KeyError(f"Unsupported tracing provider: {provider}")
+                case _:
+                    raise KeyError(f"Unsupported tracing provider: {provider}")
+        except ImportError:
+            raise ImportError(f"Provider {provider} is not installed.")
 
 
 provider_config_map = OpsTraceProviderConfigMap()

api/core/plugin/impl/model_runtime.py

@@ -66,15 +66,15 @@ class PluginModelRuntime(ModelRuntime):
             if not provider_schema.icon_small:
                 raise ValueError(f"Provider {provider} does not have small icon.")
             file_name = (
-                provider_schema.icon_small.zh_Hans if lang.lower() == "zh_hans" else provider_schema.icon_small.en_US
+                provider_schema.icon_small.zh_hans if lang.lower() == "zh_hans" else provider_schema.icon_small.en_us
             )
         elif icon_type.lower() == "icon_small_dark":
             if not provider_schema.icon_small_dark:
                 raise ValueError(f"Provider {provider} does not have small dark icon.")
             file_name = (
-                provider_schema.icon_small_dark.zh_Hans
+                provider_schema.icon_small_dark.zh_hans
                 if lang.lower() == "zh_hans"
-                else provider_schema.icon_small_dark.en_US
+                else provider_schema.icon_small_dark.en_us
             )
         else:
             raise ValueError(f"Unsupported icon type: {icon_type}.")

api/core/prompt/agent_history_prompt_transform.py

@@ -10,7 +10,7 @@ from graphon.model_runtime.entities.message_entities import (
     SystemPromptMessage,
     UserPromptMessage,
 )
-from graphon.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from graphon.model_runtime.model_providers.base.large_language_model import LargeLanguageModel
 
 
 class AgentHistoryPromptTransform(PromptTransform):

api/core/provider_manager.py

@@ -70,12 +70,32 @@ class ProviderManager:
     Request-bound managers may carry caller identity in that runtime, and the
     resulting ``ProviderConfiguration`` objects must reuse it for downstream
     model-type and schema lookups.
+
+    Configuration assembly is cached per manager instance so call chains that
+    share one request-scoped manager can reuse the same provider graph instead
+    of rebuilding it for every lookup. Call ``clear_configurations_cache()``
+    when a long-lived manager needs to observe writes performed within the same
+    instance scope.
     """
 
+    decoding_rsa_key: Any | None
+    decoding_cipher_rsa: Any | None
+    _model_runtime: ModelRuntime
+    _configurations_cache: dict[str, ProviderConfigurations]
+
     def __init__(self, model_runtime: ModelRuntime):
         self.decoding_rsa_key = None
         self.decoding_cipher_rsa = None
         self._model_runtime = model_runtime
+        self._configurations_cache = {}
+
+    def clear_configurations_cache(self, tenant_id: str | None = None) -> None:
+        """Drop assembled provider configurations cached on this manager instance."""
+        if tenant_id is None:
+            self._configurations_cache.clear()
+            return
+
+        self._configurations_cache.pop(tenant_id, None)
 
     def get_configurations(self, tenant_id: str) -> ProviderConfigurations:
         """
@@ -114,6 +134,10 @@ class ProviderManager:
         :param tenant_id:
         :return:
         """
+        cached_configurations = self._configurations_cache.get(tenant_id)
+        if cached_configurations is not None:
+            return cached_configurations
+
         # Get all provider records of the workspace
         provider_name_to_provider_records_dict = self._get_all_providers(tenant_id)
 
@@ -273,6 +297,8 @@ class ProviderManager:
 
             provider_configurations[str(provider_id_entity)] = provider_configuration
 
+        self._configurations_cache[tenant_id] = provider_configurations
+
         # Return the encapsulated object
         return provider_configurations
 

api/core/rag/datasource/keyword/jieba/jieba.py

@@ -139,8 +139,10 @@ class Jieba(BaseKeyword):
             "__data__": {"index_id": self.dataset.id, "summary": None, "table": keyword_table},
         }
         dataset_keyword_table = self.dataset.dataset_keyword_table
-        keyword_data_source_type = dataset_keyword_table.data_source_type
+        keyword_data_source_type = dataset_keyword_table.data_source_type if dataset_keyword_table else "file"
         if keyword_data_source_type == "database":
+            if dataset_keyword_table is None:
+                return
             dataset_keyword_table.keyword_table = dumps_with_sets(keyword_table_dict)
             db.session.commit()
         else:
@@ -154,7 +156,8 @@ class Jieba(BaseKeyword):
         if dataset_keyword_table:
             keyword_table_dict = dataset_keyword_table.keyword_table_dict
             if keyword_table_dict:
-                return dict(keyword_table_dict["__data__"]["table"])
+                data: Any = keyword_table_dict["__data__"]
+                return dict(data["table"])
         else:
             keyword_data_source_type = dify_config.KEYWORD_DATA_SOURCE_TYPE
             dataset_keyword_table = DatasetKeywordTable(