feat: add service api of HITL

Co-authored-by: hjlarry <hjlarry@163.com>
Co-authored-by: QuantumGhost <QuantumGhost@users.noreply.github.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                │
+  │ 3. Run: pnpm type-check:tsgo           │
   │ 4. Run: pnpm test                      │
   │ 5. Test functionality manually         │
   │ 6. PASS? → Next extraction             │

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

@@ -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`
+- [ ] Run `pnpm type-check:tsgo`
 
 ## Common Issues to Watch
 

.github/CODEOWNERS

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

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

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

.github/labeler.yml

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

.github/workflows/api-tests.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   api-unit:
     name: API Unit Tests
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     env:
       COVERAGE_FILE: coverage-unit
     defaults:
@@ -62,7 +62,7 @@ jobs:
 
   api-integration:
     name: API Integration Tests
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     env:
       COVERAGE_FILE: coverage-integration
       STORAGE_TYPE: opendal
@@ -137,7 +137,7 @@ jobs:
 
   api-coverage:
     name: API Coverage
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     needs:
       - api-unit
       - api-integration

.github/workflows/autofix.yml

@@ -13,7 +13,7 @@ permissions:
 jobs:
   autofix:
     if: github.repository == 'langgenius/dify'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Complete merge group check
         if: github.event_name == 'merge_group'
@@ -43,6 +43,7 @@ jobs:
             package.json
             pnpm-lock.yaml
             pnpm-workspace.yaml
+            .npmrc
             .nvmrc
       - name: Check api inputs
         if: github.event_name != 'merge_group'

.github/workflows/build-push.yml

@@ -26,9 +26,6 @@ jobs:
   build:
     runs-on: ${{ matrix.runs_on }}
     if: github.repository == 'langgenius/dify'
-    permissions:
-      contents: read
-      id-token: write
     strategy:
       matrix:
         include:
@@ -38,28 +35,28 @@ jobs:
             build_context: "{{defaultContext}}:api"
             file: "Dockerfile"
             platform: linux/amd64
-            runs_on: depot-ubuntu-24.04-4
+            runs_on: ubuntu-latest
           - 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: depot-ubuntu-24.04-4
+            runs_on: ubuntu-24.04-arm
           - 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: depot-ubuntu-24.04-4
+            runs_on: ubuntu-latest
           - 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: depot-ubuntu-24.04-4
+            runs_on: ubuntu-24.04-arm
 
     steps:
       - name: Prepare
@@ -73,8 +70,8 @@ jobs:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
-      - name: Set up Depot CLI
-        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Extract metadata for Docker
         id: meta
@@ -84,15 +81,16 @@ jobs:
 
       - name: Build Docker image
         id: build
-        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
         with:
-          project: ${{ vars.DEPOT_PROJECT_ID }}
           context: ${{ matrix.build_context }}
           file: ${{ matrix.file }}
           platforms: ${{ matrix.platform }}
           build-args: COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
           labels: ${{ steps.meta.outputs.labels }}
           outputs: type=image,name=${{ env[matrix.image_name_env] }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha,scope=${{ matrix.service_name }}
+          cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}
 
       - name: Export digest
         env:
@@ -110,33 +108,9 @@ jobs:
           if-no-files-found: error
           retention-days: 1
 
-  fork-build-validate:
-    if: github.repository != 'langgenius/dify'
-    runs-on: ubuntu-24.04
-    strategy:
-      matrix:
-        include:
-          - service_name: "validate-api-amd64"
-            build_context: "{{defaultContext}}:api"
-            file: "Dockerfile"
-          - service_name: "validate-web-amd64"
-            build_context: "{{defaultContext}}"
-            file: "web/Dockerfile"
-    steps:
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
-
-      - name: Validate Docker image
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
-        with:
-          push: false
-          context: ${{ matrix.build_context }}
-          file: ${{ matrix.file }}
-          platforms: linux/amd64
-
   create-manifest:
     needs: build
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
 
     steps:
       - name: Checkout code
@@ -59,7 +59,7 @@ jobs:
         run: uv run --directory api flask upgrade-db
 
   db-migration-test-mysql:
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
 
     steps:
       - name: Checkout code
@@ -110,28 +110,6 @@ 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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     if: |
       github.event.workflow_run.conclusion == 'success' &&
       github.event.workflow_run.head_branch == 'build/feat/hitl'

.github/workflows/docker-build.yml

@@ -14,59 +14,28 @@ 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: depot-ubuntu-24.04-4
+            runs_on: ubuntu-latest
             context: "{{defaultContext}}:api"
             file: "Dockerfile"
           - service_name: "api-arm64"
             platform: linux/arm64
-            runs_on: depot-ubuntu-24.04-4
+            runs_on: ubuntu-24.04-arm
             context: "{{defaultContext}}:api"
             file: "Dockerfile"
           - service_name: "web-amd64"
             platform: linux/amd64
-            runs_on: depot-ubuntu-24.04-4
+            runs_on: ubuntu-latest
             context: "{{defaultContext}}"
             file: "web/Dockerfile"
           - service_name: "web-arm64"
             platform: linux/arm64
-            runs_on: depot-ubuntu-24.04-4
-            context: "{{defaultContext}}"
-            file: "web/Dockerfile"
-    steps:
-      - name: Set up Depot CLI
-        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
-
-      - name: Build Docker Image
-        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
-        with:
-          project: ${{ vars.DEPOT_PROJECT_ID }}
-          push: false
-          context: ${{ matrix.context }}
-          file: ${{ matrix.file }}
-          platforms: ${{ matrix.platform }}
-
-  build-docker-fork:
-    if: github.event.pull_request.head.repo.full_name != github.repository
-    runs-on: ubuntu-24.04
-    permissions:
-      contents: read
-    strategy:
-      matrix:
-        include:
-          - service_name: "api-amd64"
-            context: "{{defaultContext}}:api"
-            file: "Dockerfile"
-          - service_name: "web-amd64"
+            runs_on: ubuntu-24.04-arm
             context: "{{defaultContext}}"
             file: "web/Dockerfile"
     steps:
@@ -79,4 +48,6 @@ jobs:
           push: false
           context: ${{ matrix.context }}
           file: ${{ matrix.file }}
-          platforms: linux/amd64
+          platforms: ${{ matrix.platform }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/labeler.yml

@@ -7,7 +7,7 @@ jobs:
     permissions:
       contents: read
       pull-requests: write
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     outputs:
       api-changed: ${{ steps.changes.outputs.api }}
       e2e-changed: ${{ steps.changes.outputs.e2e }}
@@ -69,6 +69,7 @@ jobs:
               - 'package.json'
               - 'pnpm-lock.yaml'
               - 'pnpm-workspace.yaml'
+              - '.npmrc'
               - '.nvmrc'
               - '.github/workflows/web-tests.yml'
               - '.github/actions/setup-web/**'
@@ -82,6 +83,7 @@ jobs:
               - 'package.json'
               - 'pnpm-lock.yaml'
               - 'pnpm-workspace.yaml'
+              - '.npmrc'
               - '.nvmrc'
               - 'docker/docker-compose.middleware.yaml'
               - 'docker/middleware.env.example'
@@ -139,7 +141,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.api-changed != 'true'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Report skipped API tests
         run: echo "No API-related changes detected; skipping API tests."
@@ -152,7 +154,7 @@ jobs:
       - check-changes
       - api-tests-run
       - api-tests-skip
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Finalize API Tests status
         env:
@@ -199,7 +201,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.web-changed != 'true'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Report skipped web tests
         run: echo "No web-related changes detected; skipping web tests."
@@ -212,7 +214,7 @@ jobs:
       - check-changes
       - web-tests-run
       - web-tests-skip
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Finalize Web Tests status
         env:
@@ -258,7 +260,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed != 'true'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Report skipped web full-stack e2e
         run: echo "No E2E-related changes detected; skipping web full-stack E2E."
@@ -271,7 +273,7 @@ jobs:
       - check-changes
       - web-e2e-run
       - web-e2e-skip
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Finalize Web Full-Stack E2E status
         env:
@@ -323,7 +325,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.vdb-changed != 'true'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Report skipped VDB tests
         run: echo "No VDB-related changes detected; skipping VDB tests."
@@ -336,7 +338,7 @@ jobs:
       - check-changes
       - vdb-tests-run
       - vdb-tests-skip
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Finalize VDB Tests status
         env:
@@ -382,7 +384,7 @@ jobs:
       - pre_job
       - check-changes
     if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.migration-changed != 'true'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     steps:
       - name: Report skipped DB migration tests
         run: echo "No migration-related changes detected; skipping DB migration tests."
@@ -395,7 +397,7 @@ jobs:
       - check-changes
       - db-migration-test-run
       - db-migration-test-skip
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     permissions:
       actions: read
       contents: read

.github/workflows/pyrefly-diff.yml

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   pyrefly-diff:
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     permissions:
       contents: read
       issues: write

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

@@ -12,7 +12,7 @@ permissions: {}
 jobs:
   comment:
     name: Comment PR with type coverage
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     permissions:
       actions: read
       contents: read

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

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   pyrefly-type-coverage:
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     permissions:
       contents: read
       issues: write

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

@@ -16,7 +16,7 @@ jobs:
     name: Validate PR title
     permissions:
       pull-requests: read
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     permissions:
       issues: write
       pull-requests: write

.github/workflows/style.yml

@@ -15,7 +15,7 @@ permissions:
 jobs:
   python-style:
     name: Python Style
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
 
     steps:
       - name: Checkout code
@@ -57,7 +57,7 @@ jobs:
 
   web-style:
     name: Web Style
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     defaults:
       run:
         working-directory: ./web
@@ -83,6 +83,7 @@ jobs:
             package.json
             pnpm-lock.yaml
             pnpm-workspace.yaml
+            .npmrc
             .nvmrc
             .github/workflows/style.yml
             .github/actions/setup-web/**
@@ -130,7 +131,7 @@ jobs:
 
   superlinter:
     name: SuperLinter
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
 
     steps:
       - name: Checkout code

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

@@ -9,6 +9,7 @@ on:
       - package.json
       - pnpm-lock.yaml
       - pnpm-workspace.yaml
+      - .npmrc
 
 concurrency:
   group: sdk-tests-${{ github.head_ref || github.run_id }}
@@ -17,7 +18,7 @@ concurrency:
 jobs:
   build:
     name: unit test for Node.js SDK
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
 
     defaults:
       run:

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

@@ -35,7 +35,7 @@ concurrency:
 jobs:
   translate:
     if: github.repository == 'langgenius/dify'
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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@ef50f123a3a9be95b60040d042717517407c7256 # v1.0.110
+        uses: anthropics/claude-code-action@38ec876110f9fbf8b950c79f534430740c3ac009 # v1.0.101
         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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     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: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version:

.github/workflows/vdb-tests.yml

@@ -13,7 +13,7 @@ concurrency:
 jobs:
   test:
     name: VDB Smoke Tests
-    runs-on: depot-ubuntu-24.04
+    runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version:

.github/workflows/web-e2e.yml

@@ -13,7 +13,7 @@ concurrency:
 jobs:
   test:
     name: Web Full-Stack E2E
-    runs-on: depot-ubuntu-24.04-4
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash

.github/workflows/web-tests.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   test:
     name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
-    runs-on: depot-ubuntu-24.04-4
+    runs-on: ubuntu-latest
     env:
       VITEST_COVERAGE_SCOPE: app-components
     strategy:
@@ -54,7 +54,7 @@ jobs:
     name: Merge Test Reports
     if: ${{ !cancelled() }}
     needs: [test]
-    runs-on: depot-ubuntu-24.04-4
+    runs-on: ubuntu-latest
     env:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:
@@ -92,7 +92,7 @@ jobs:
 
   dify-ui-test:
     name: dify-ui Tests
-    runs-on: depot-ubuntu-24.04-4
+    runs-on: ubuntu-latest
     env:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:

.gitignore

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

.npmrc

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

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`, and avoid `any` types.
+- **TypeScript**: Use the strict config, rely on ESLint (`pnpm lint:fix` preferred) plus `pnpm type-check:tsgo`, and avoid `any` types.
 
 ## General Practices
 

README.md

@@ -139,6 +139,19 @@ 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.
@@ -147,7 +160,7 @@ 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

@@ -659,11 +659,6 @@ 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}
 
@@ -714,6 +709,22 @@ 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

@@ -101,11 +101,3 @@ 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

@@ -113,18 +113,8 @@ def create_tenant(email: str, language: str | None = None, name: str | None = No
     # Validates name encoding for non-Latin characters.
     name = name.strip().encode("utf-8").decode("utf-8") if name else None
 
-    # Generate a random password that satisfies the password policy.
-    # The iteration limit guards against infinite loops caused by unexpected bugs in valid_password.
-    for _ in range(100):
-        new_password = secrets.token_urlsafe(16)
-        try:
-            valid_password(new_password)
-            break
-        except Exception:
-            continue
-    else:
-        click.echo(click.style("Failed to generate a valid password. Please try again.", fg="red"))
-        return
+    # generate random password
+    new_password = secrets.token_urlsafe(16)
 
     # register account
     account = RegisterService.register(

api/commands/plugin.py

@@ -11,7 +11,7 @@ from configs import dify_config
 from core.helper import encrypter
 from core.plugin.entities.plugin_daemon import CredentialType
 from core.plugin.impl.plugin import PluginInstaller
-from core.tools.utils.system_encryption import encrypt_system_params
+from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_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_params(client_params_dict)
+        oauth_client_params = encrypt_system_oauth_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_params(client_params_dict)
+        oauth_client_params = encrypt_system_oauth_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

@@ -287,27 +287,6 @@ 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
@@ -1400,7 +1379,6 @@ class FeatureConfig(
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
-    CreatorsPlatformConfig,
     TriggerConfig,
     AsyncWorkflowConfig,
     PluginConfig,

api/controllers/common/human_input.py

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

api/controllers/console/app/app.py

@@ -692,32 +692,6 @@ 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")

api/controllers/console/datasets/hit_testing_base.py

@@ -38,48 +38,6 @@ 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)
@@ -117,12 +75,7 @@ class DatasetsHitTestingBase:
                 attachment_ids=args.get("attachment_ids"),
                 limit=10,
             )
-            return {
-                "query": DatasetsHitTestingBase._normalize_hit_testing_query(response.get("query")),
-                "records": DatasetsHitTestingBase._normalize_hit_testing_records(
-                    marshal(response.get("records", []), hit_testing_record_fields)
-                ),
-            }
+            return {"query": response["query"], "records": marshal(response["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
@@ -34,6 +34,11 @@ 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())

api/controllers/console/tag/tags.py

@@ -37,11 +37,6 @@ 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")
@@ -75,7 +70,6 @@ register_schema_models(
     TagBasePayload,
     TagBindingPayload,
     TagBindingRemovePayload,
-    TagBindingItemDeletePayload,
     TagListQueryParam,
     TagResponse,
 )
@@ -158,107 +152,41 @@ class TagUpdateDeleteApi(Resource):
         return "", 204
 
 
-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.route("/tag-bindings/create")
+class TagBindingCreateApi(Resource):
     @console_ns.expect(console_ns.models[TagBindingPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        return _create_tag_bindings()
+        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()
 
-
-@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,
-            )
+        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
 
 
-@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 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.")
+class TagBindingDeleteApi(Resource):
     @console_ns.expect(console_ns.models[TagBindingRemovePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        return _remove_tag_binding()
+        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

api/controllers/console/workspace/endpoint.py

@@ -1,11 +1,3 @@
-"""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
@@ -33,12 +25,7 @@ class EndpointIdPayload(BaseModel):
     endpoint_id: str
 
 
-class EndpointUpdatePayload(BaseModel):
-    settings: dict[str, Any]
-    name: str = Field(min_length=1)
-
-
-class LegacyEndpointUpdatePayload(EndpointIdPayload):
+class EndpointUpdatePayload(EndpointIdPayload):
     settings: dict[str, Any]
     name: str = Field(min_length=1)
 
@@ -89,7 +76,6 @@ register_schema_models(
     EndpointCreatePayload,
     EndpointIdPayload,
     EndpointUpdatePayload,
-    LegacyEndpointUpdatePayload,
     EndpointListQuery,
     EndpointListForPluginQuery,
     EndpointCreateResponse,
@@ -102,60 +88,8 @@ register_schema_models(
 )
 
 
-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.route("/workspaces/current/endpoints/create")
+class EndpointCreateApi(Resource):
     @console_ns.doc("create_endpoint")
     @console_ns.doc(description="Create a new plugin endpoint")
     @console_ns.expect(console_ns.models[EndpointCreatePayload.__name__])
@@ -170,33 +104,22 @@ class EndpointCollectionApi(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self):
-        return _create_endpoint()
+        user, tenant_id = current_account_with_tenant()
 
+        args = EndpointCreatePayload.model_validate(console_ns.payload)
 
-@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()
+        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/list")
@@ -267,56 +190,10 @@ class EndpointListForSinglePluginApi(Resource):
         )
 
 
-@console_ns.route("/workspaces/current/endpoints/<string:id>")
-class EndpointItemApi(Resource):
-    """Canonical item resource for endpoint updates and deletion."""
-
+@console_ns.route("/workspaces/current/endpoints/delete")
+class EndpointDeleteApi(Resource):
     @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,
@@ -329,23 +206,22 @@ class DeprecatedEndpointDeleteApi(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 _delete_endpoint(endpoint_id=args.endpoint_id)
+
+        return {
+            "success": EndpointService.delete_endpoint(
+                tenant_id=tenant_id, user_id=user.id, endpoint_id=args.endpoint_id
+            )
+        }
 
 
 @console_ns.route("/workspaces/current/endpoints/update")
-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__])
+class EndpointUpdateApi(Resource):
+    @console_ns.doc("update_endpoint")
+    @console_ns.doc(description="Update a plugin endpoint")
+    @console_ns.expect(console_ns.models[EndpointUpdatePayload.__name__])
     @console_ns.response(
         200,
         "Endpoint updated successfully",
@@ -357,8 +233,19 @@ class DeprecatedEndpointUpdateApi(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self):
-        args = LegacyEndpointUpdatePayload.model_validate(console_ns.payload)
-        return _update_endpoint(endpoint_id=args.endpoint_id)
+        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,
+            )
+        }
 
 
 @console_ns.route("/workspaces/current/endpoints/enable")

api/controllers/service_api/app/human_input_form.py

@@ -8,12 +8,13 @@ paused human input forms in workflow/chatflow runs.
 import json
 import logging
 from datetime import datetime
+from typing import Any
 
 from flask import Response
 from flask_restx import Resource
-from werkzeug.exceptions import BadRequest, NotFound
+from pydantic import BaseModel
+from werkzeug.exceptions import InternalServerError, 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
@@ -25,6 +26,11 @@ from services.human_input_service import Form, FormNotFoundError, HumanInputServ
 logger = logging.getLogger(__name__)
 
 
+class HumanInputFormSubmitPayload(BaseModel):
+    inputs: dict[str, Any]
+    action: str
+
+
 register_schema_models(service_api_ns, HumanInputFormSubmitPayload)
 
 
@@ -121,7 +127,7 @@ class WorkflowHumanInputFormApi(Resource):
         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")
+            raise InternalServerError("Form recipient type is invalid")
 
         try:
             service.submit_form_by_token(

api/controllers/service_api/app/workflow_events.py

@@ -18,8 +18,6 @@ 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
@@ -37,14 +35,8 @@ class WorkflowEventsApi(Resource):
         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.'
-            ),
+            "include_state_snapshot": "Whether to replay from persisted state snapshot",
+            "continue_on_pause": "Whether to keep the stream open across workflow_paused events",
         }
     )
     @service_api_ns.doc(
@@ -107,7 +99,7 @@ class WorkflowEventsApi(Resource):
 
             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
+            terminal_events = ["workflow_finished"] if continue_on_pause else None
 
             def _generate_stream_events():
                 if include_state_snapshot:
@@ -118,7 +110,6 @@ class WorkflowEventsApi(Resource):
                             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,
                         )
                     )

api/controllers/service_api/dataset/document.py

@@ -1,12 +1,4 @@
-"""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
@@ -125,137 +117,12 @@ register_schema_models(
 )
 
 
-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")
+@service_api_ns.route(
+    "/datasets/<uuid:dataset_id>/document/create_by_text",
+    "/datasets/<uuid:dataset_id>/document/create-by-text",
+)
 class DocumentAddByTextApi(DatasetApiResource):
-    """Resource for the canonical text document creation route."""
+    """Resource for documents."""
 
     @service_api_ns.expect(service_api_ns.models[DocumentTextCreatePayload.__name__])
     @service_api_ns.doc("create_document_by_text")
@@ -271,43 +138,81 @@ 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: str, dataset_id: UUID):
+    def post(self, tenant_id, dataset_id):
         """Create document by text."""
-        return _create_document_by_text(tenant_id=tenant_id, dataset_id=dataset_id)
+        payload = DocumentTextCreatePayload.model_validate(service_api_ns.payload or {})
+        args = payload.model_dump(exclude_none=True)
 
-
-@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."
+        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.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",
+
+        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]}},
         }
-    )
-    @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)
+        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
 
 
-@service_api_ns.route("/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",
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
+)
 class DocumentUpdateByTextApi(DatasetApiResource):
-    """Resource for the canonical text document update route."""
+    """Resource for update documents."""
 
     @service_api_ns.expect(service_api_ns.models[DocumentTextUpdate.__name__])
     @service_api_ns.doc("update_document_by_text")
@@ -324,35 +229,62 @@ 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."""
-        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."
+        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)
         )
-    )
-    @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)
+        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.route(
@@ -468,98 +400,15 @@ 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 DeprecatedDocumentUpdateByFileApi(DatasetApiResource):
-    """Deprecated resource aliases for file document updates."""
+class DocumentUpdateByFileApi(DatasetApiResource):
+    """Resource for update documents."""
 
-    @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("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={
@@ -570,9 +419,82 @@ class DeprecatedDocumentUpdateByFileApi(DatasetApiResource):
     )
     @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 file through the deprecated file-update aliases."""
-        return _update_document_by_file(tenant_id=tenant_id, dataset_id=dataset_id, document_id=document_id)
+    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
 
 
 @service_api_ns.route("/datasets/<uuid:dataset_id>/documents")
@@ -886,22 +808,6 @@ 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
@@ -26,6 +26,11 @@ 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/app/app_config/features/suggested_questions_after_answer/manager.py

@@ -1,7 +1,5 @@
 from typing import Any
 
-CUSTOM_FOLLOW_UP_PROMPT_MAX_LENGTH = 1000
-
 
 class SuggestedQuestionsAfterAnswerConfigManager:
     @classmethod
@@ -22,11 +20,7 @@ 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.
-
-        Optional fields:
-        - prompt: custom instruction prompt.
-        - model: provider/model configuration for suggested question generation.
+        Validate and set defaults for suggested questions feature
 
         :param config: app model config args
         """
@@ -45,27 +39,4 @@ 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

@@ -35,8 +35,8 @@ 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 (
-    AdvancedChatPausedBlockingResponse,
     ChatbotAppBlockingResponse,
+    ChatbotAppPausedBlockingResponse,
     ChatbotAppStreamResponse,
 )
 from core.app.layers.pause_state_persist_layer import PauseStateLayerConfig, PauseStatePersistenceLayer
@@ -660,9 +660,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         draft_var_saver_factory: DraftVariableSaverFactory,
         stream: bool = False,
     ) -> (
-        ChatbotAppBlockingResponse
-        | AdvancedChatPausedBlockingResponse
-        | Generator[ChatbotAppStreamResponse, None, None]
+        ChatbotAppBlockingResponse | ChatbotAppPausedBlockingResponse | Generator[ChatbotAppStreamResponse, None, None]
     ):
         """
         Handle response.

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

@@ -175,7 +175,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
 
             # Create a variable pool.
             # init variable pool
-            variable_pool = VariablePool.from_bootstrap()
+            variable_pool = VariablePool()
             add_variables_to_pool(
                 variable_pool,
                 build_bootstrap_variables(

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

@@ -3,35 +3,34 @@ from typing import Any, cast
 
 from core.app.apps.base_app_generate_response_converter import AppGenerateResponseConverter
 from core.app.entities.task_entities import (
-    AdvancedChatPausedBlockingResponse,
     AppStreamResponse,
     ChatbotAppBlockingResponse,
+    ChatbotAppPausedBlockingResponse,
     ChatbotAppStreamResponse,
     ErrorStreamResponse,
     MessageEndStreamResponse,
     NodeFinishStreamResponse,
     NodeStartStreamResponse,
     PingStreamResponse,
-    StreamEvent,
 )
 
 
 class AdvancedChatAppGenerateResponseConverter(
-    AppGenerateResponseConverter[ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse]
+    AppGenerateResponseConverter[ChatbotAppBlockingResponse | ChatbotAppPausedBlockingResponse]
 ):
     @classmethod
     def convert_blocking_full_response(
-        cls, blocking_response: ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse
+        cls, blocking_response: ChatbotAppBlockingResponse | ChatbotAppPausedBlockingResponse
     ) -> dict[str, Any]:
         """
         Convert blocking full response.
         :param blocking_response: blocking response
         :return:
         """
-        if isinstance(blocking_response, AdvancedChatPausedBlockingResponse):
+        if isinstance(blocking_response, ChatbotAppPausedBlockingResponse):
             paused_data = blocking_response.data.model_dump(mode="json")
             return {
-                "event": StreamEvent.WORKFLOW_PAUSED.value,
+                "event": "workflow_paused",
                 "task_id": blocking_response.task_id,
                 "id": blocking_response.data.id,
                 "message_id": blocking_response.data.message_id,
@@ -45,7 +44,7 @@ class AdvancedChatAppGenerateResponseConverter(
             }
 
         response = {
-            "event": StreamEvent.MESSAGE.value,
+            "event": "message",
             "task_id": blocking_response.task_id,
             "id": blocking_response.data.id,
             "message_id": blocking_response.data.message_id,
@@ -60,7 +59,7 @@ class AdvancedChatAppGenerateResponseConverter(
 
     @classmethod
     def convert_blocking_simple_response(
-        cls, blocking_response: ChatbotAppBlockingResponse | AdvancedChatPausedBlockingResponse
+        cls, blocking_response: ChatbotAppBlockingResponse | ChatbotAppPausedBlockingResponse
     ) -> dict[str, Any]:
         """
         Convert blocking simple response.

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

@@ -53,11 +53,10 @@ from core.app.entities.queue_entities import (
     WorkflowQueueMessage,
 )
 from core.app.entities.task_entities import (
-    AdvancedChatPausedBlockingResponse,
     ChatbotAppBlockingResponse,
+    ChatbotAppPausedBlockingResponse,
     ChatbotAppStreamResponse,
     ErrorStreamResponse,
-    HumanInputRequiredPauseReasonPayload,
     HumanInputRequiredResponse,
     MessageAudioEndStreamResponse,
     MessageAudioStreamResponse,
@@ -75,7 +74,7 @@ from core.repositories.human_input_repository import HumanInputFormRepositoryImp
 from core.workflow.file_reference import resolve_file_record_id
 from core.workflow.system_variables import build_system_variables
 from extensions.ext_database import db
-from graphon.entities.pause_reason import HumanInputRequired
+from graphon.entities.pause_reason import HumanInputRequired, PauseReasonType
 from graphon.enums import WorkflowExecutionStatus
 from graphon.model_runtime.entities.llm_entities import LLMUsage
 from graphon.model_runtime.utils.encoders import jsonable_encoder
@@ -218,7 +217,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         self,
     ) -> Union[
         ChatbotAppBlockingResponse,
-        AdvancedChatPausedBlockingResponse,
+        ChatbotAppPausedBlockingResponse,
         Generator[ChatbotAppStreamResponse, None, None],
     ]:
         """
@@ -238,7 +237,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
     def _to_blocking_response(
         self, generator: Generator[StreamResponse, None, None]
-    ) -> Union[ChatbotAppBlockingResponse, AdvancedChatPausedBlockingResponse]:
+    ) -> Union[ChatbotAppBlockingResponse, ChatbotAppPausedBlockingResponse]:
         """
         Process blocking response.
         :return:
@@ -250,9 +249,9 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             elif isinstance(stream_response, HumanInputRequiredResponse):
                 human_input_responses.append(stream_response)
             elif isinstance(stream_response, WorkflowPauseStreamResponse):
-                return AdvancedChatPausedBlockingResponse(
+                return ChatbotAppPausedBlockingResponse(
                     task_id=stream_response.task_id,
-                    data=AdvancedChatPausedBlockingResponse.Data(
+                    data=ChatbotAppPausedBlockingResponse.Data(
                         id=self._message_id,
                         mode=self._conversation_mode,
                         conversation_id=self._conversation_id,
@@ -296,17 +295,18 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
     def _build_paused_blocking_response_from_human_input(
         self, human_input_responses: list[HumanInputRequiredResponse]
-    ) -> AdvancedChatPausedBlockingResponse:
+    ) -> ChatbotAppPausedBlockingResponse:
         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
-        ]
+        reasons = []
+        for response in human_input_responses:
+            reason = response.data.model_dump(mode="json")
+            reason["type"] = PauseReasonType.HUMAN_INPUT_REQUIRED
+            reasons.append(reason)
 
-        return AdvancedChatPausedBlockingResponse(
+        return ChatbotAppPausedBlockingResponse(
             task_id=self._application_generate_entity.task_id,
-            data=AdvancedChatPausedBlockingResponse.Data(
+            data=ChatbotAppPausedBlockingResponse.Data(
                 id=self._message_id,
                 mode=self._conversation_mode,
                 conversation_id=self._conversation_id,

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

@@ -1,8 +1,6 @@
 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,
@@ -70,7 +68,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter[Chatbot
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,
@@ -101,7 +99,7 @@ class AgentChatAppGenerateResponseConverter(AppGenerateResponseConverter[Chatbot
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "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

@@ -3,8 +3,6 @@ from abc import ABC, abstractmethod
 from collections.abc import Generator, Mapping
 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
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
@@ -110,13 +108,13 @@ class AppGenerateResponseConverter[TBlockingResponse: AppBlockingResponse](ABC):
         return metadata
 
     @classmethod
-    def _error_to_stream_response(cls, e: Exception) -> dict[str, JsonValue]:
+    def _error_to_stream_response(cls, e: Exception) -> dict[str, Any]:
         """
         Error to stream response.
         :param e: exception
         :return:
         """
-        error_responses: dict[type[Exception], dict[str, JsonValue]] = {
+        error_responses: dict[type[Exception], dict[str, Any]] = {
             ValueError: {"code": "invalid_param", "status": 400},
             ProviderTokenNotInitError: {"code": "provider_not_initialize", "status": 400},
             QuotaExceededError: {
@@ -130,7 +128,7 @@ class AppGenerateResponseConverter[TBlockingResponse: AppBlockingResponse](ABC):
         }
 
         # Determine the response based on the type of exception
-        data: dict[str, JsonValue] | None = None
+        data: dict[str, Any] | None = None
         for k, v in error_responses.items():
             if isinstance(e, k):
                 data = v

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

@@ -1,8 +1,6 @@
 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,
@@ -70,7 +68,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter[ChatbotAppBl
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,
@@ -101,7 +99,7 @@ class ChatAppGenerateResponseConverter(AppGenerateResponseConverter[ChatbotAppBl
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "event": sub_stream_response.event.value,
                 "conversation_id": chunk.conversation_id,
                 "message_id": chunk.message_id,

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

@@ -0,0 +1,17 @@
+from collections.abc import Mapping
+from typing import Any
+
+from graphon.entities.pause_reason import PauseReason
+
+
+def pause_reason_to_public_dict(reason: PauseReason | Mapping[str, Any]) -> dict[str, Any]:
+    if isinstance(reason, Mapping):
+        data = dict(reason)
+    else:
+        data = dict(reason.model_dump(mode="json"))
+
+    discriminator = data.pop("TYPE", None)
+    if discriminator is not None:
+        data["type"] = discriminator
+
+    return data

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

@@ -9,7 +9,9 @@ from typing import Any, NewType, TypedDict, Union
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
+from core.app.apps.common.pause_reason_serializer import pause_reason_to_public_dict
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom, WorkflowAppGenerateEntity
+from core.workflow.human_input_policy import enrich_human_input_pause_reasons
 from core.app.entities.queue_entities import (
     QueueAgentLogEvent,
     QueueHumanInputFormFilledEvent,
@@ -52,7 +54,6 @@ 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
@@ -318,7 +319,7 @@ class WorkflowResponseConverter:
         encoded_outputs = self._encode_outputs(event.outputs) or {}
         if self._application_generate_entity.invoke_from == InvokeFrom.SERVICE_API:
             encoded_outputs = {}
-        pause_reasons = [reason.model_dump(mode="json") for reason in event.reasons]
+        pause_reasons = [pause_reason_to_public_dict(reason) for reason in event.reasons]
         human_input_form_ids = [reason.form_id for reason in event.reasons if isinstance(reason, HumanInputRequired)]
         expiration_times_by_form_id: dict[str, datetime] = {}
         display_in_ui_by_form_id: dict[str, bool] = {}
@@ -337,15 +338,7 @@ 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,
-                    surface=(
-                        HumanInputSurface.SERVICE_API
-                        if self._application_generate_entity.invoke_from == InvokeFrom.SERVICE_API
-                        else None
-                    ),
-                )
+                form_token_by_form_id = load_form_tokens_by_form_id(human_input_form_ids, session=session)
 
         # Reconnect paths must preserve the same pause-reason contract as live streams;
         # otherwise clients see schema drift after resume.

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

@@ -1,8 +1,6 @@
 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,
@@ -22,7 +20,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter[Comple
         :param blocking_response: blocking response
         :return:
         """
-        response: dict[str, Any] = {
+        response = {
             "event": "message",
             "task_id": blocking_response.task_id,
             "id": blocking_response.data.id,
@@ -69,7 +67,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter[Comple
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "event": sub_stream_response.event.value,
                 "message_id": chunk.message_id,
                 "created_at": chunk.created_at,
@@ -99,7 +97,7 @@ class CompletionAppGenerateResponseConverter(AppGenerateResponseConverter[Comple
                 yield "ping"
                 continue
 
-            response_chunk: dict[str, JsonValue] = {
+            response_chunk = {
                 "event": sub_stream_response.event.value,
                 "message_id": chunk.message_id,
                 "created_at": chunk.created_at,

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

@@ -144,7 +144,7 @@ class PipelineRunner(WorkflowBasedAppRunner):
                             )
                         )
 
-            variable_pool = VariablePool.from_bootstrap()
+            variable_pool = VariablePool()
             add_variables_to_pool(
                 variable_pool,
                 build_bootstrap_variables(

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 terminal_events is None:
+    if not terminal_events:
         return {StreamEvent.WORKFLOW_FINISHED.value, StreamEvent.WORKFLOW_PAUSED.value}
     values: set[str] = set()
     for item in terminal_events:

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

@@ -106,7 +106,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
                 workflow_id=app_config.workflow_id,
                 workflow_execution_id=self.application_generate_entity.workflow_execution_id,
             )
-            variable_pool = VariablePool.from_bootstrap()
+            variable_pool = VariablePool()
             add_variables_to_pool(
                 variable_pool,
                 build_bootstrap_variables(

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

@@ -63,7 +63,7 @@ class WorkflowAppGenerateResponseConverter(
 
             if isinstance(sub_stream_response, ErrorStreamResponse):
                 data = cls._error_to_stream_response(sub_stream_response.err)
-                response_chunk.update(data)
+                response_chunk.update(cast(dict[str, object], data))
             else:
                 response_chunk.update(sub_stream_response.model_dump(mode="json"))
             yield response_chunk
@@ -92,9 +92,9 @@ class WorkflowAppGenerateResponseConverter(
 
             if isinstance(sub_stream_response, ErrorStreamResponse):
                 data = cls._error_to_stream_response(sub_stream_response.err)
-                response_chunk.update(data)
+                response_chunk.update(cast(dict[str, object], data))
             elif isinstance(sub_stream_response, NodeStartStreamResponse | NodeFinishStreamResponse):
-                response_chunk.update(sub_stream_response.to_ignore_detail_dict())
+                response_chunk.update(cast(dict[str, object], sub_stream_response.to_ignore_detail_dict()))
             else:
                 response_chunk.update(sub_stream_response.model_dump(mode="json"))
             yield response_chunk

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

@@ -42,7 +42,6 @@ from core.app.entities.queue_entities import (
 )
 from core.app.entities.task_entities import (
     ErrorStreamResponse,
-    HumanInputRequiredPauseReasonPayload,
     HumanInputRequiredResponse,
     MessageAudioEndStreamResponse,
     MessageAudioStreamResponse,
@@ -200,11 +199,14 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
     ) -> 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
-        ]
+        # Graph runtime `start_at` is a perf-counter value, not an epoch timestamp, so
+        # fallback API payloads need a wall-clock source for `created_at`.
+        created_at = int(time.time())
+        reasons = []
+        for response in human_input_responses:
+            reason = response.data.model_dump(mode="json")
+            reason["type"] = "human_input_required"
+            reasons.append(reason)
 
         return WorkflowAppPausedBlockingResponse(
             task_id=self._application_generate_entity.task_id,

api/core/app/apps/workflow_app_runner.py

@@ -188,7 +188,7 @@ class WorkflowBasedAppRunner:
             ValueError: If neither single_iteration_run nor single_loop_run is specified
         """
         # Create initial runtime state with variable pool containing environment variables
-        variable_pool = VariablePool.from_bootstrap()
+        variable_pool = VariablePool()
         add_variables_to_pool(
             variable_pool,
             build_bootstrap_variables(

api/core/app/entities/task_entities.py

@@ -1,13 +1,12 @@
 from collections.abc import Mapping, Sequence
 from enum import StrEnum
-from typing import Any, Literal
+from typing import Any
 
-from pydantic import BaseModel, ConfigDict, Field, JsonValue
+from pydantic import BaseModel, ConfigDict, Field
 
 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
@@ -296,40 +295,6 @@ 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):
         """
@@ -390,7 +355,7 @@ class NodeStartStreamResponse(StreamResponse):
     workflow_run_id: str
     data: Data
 
-    def to_ignore_detail_dict(self) -> dict[str, JsonValue]:
+    def to_ignore_detail_dict(self):
         return {
             "event": self.event.value,
             "task_id": self.task_id,
@@ -447,7 +412,7 @@ class NodeFinishStreamResponse(StreamResponse):
     workflow_run_id: str
     data: Data
 
-    def to_ignore_detail_dict(self) -> dict[str, JsonValue]:
+    def to_ignore_detail_dict(self):
         return {
             "event": self.event.value,
             "task_id": self.task_id,
@@ -809,7 +774,7 @@ class ChatbotAppBlockingResponse(AppBlockingResponse):
     data: Data
 
 
-class AdvancedChatPausedBlockingResponse(AppBlockingResponse):
+class ChatbotAppPausedBlockingResponse(AppBlockingResponse):
     """
     ChatbotAppPausedBlockingResponse entity
     """
@@ -828,7 +793,7 @@ class AdvancedChatPausedBlockingResponse(AppBlockingResponse):
         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]])
+        reasons: Sequence[Mapping[str, Any]] = Field(default_factory=list)
         status: WorkflowExecutionStatus
         elapsed_time: float
         total_tokens: int

api/core/app/file_access/scope.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from collections.abc import Generator  # Changed from Iterator
+from collections.abc import 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) -> Generator[None, None, None]:  # Changed from Iterator[None]
+def bind_file_access_scope(scope: FileAccessScope) -> Iterator[None]:
     token = _current_file_access_scope.set(scope)
     try:
         yield

api/core/app/llm/model_access.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from copy import deepcopy
 from typing import Any
 
 from core.app.entities.app_invoke_entities import DifyRunContext, ModelConfigWithCredentialsEntity
@@ -15,21 +14,8 @@ 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,
@@ -44,12 +30,8 @@ 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:
@@ -64,7 +46,6 @@ 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
 
 
@@ -84,8 +65,7 @@ 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
 
@@ -104,7 +84,7 @@ 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, enable_credentials_cache=True)
+    model_manager = ModelManager(provider_manager=provider_manager)
 
     return (
         DifyCredentialsProvider(run_context=run_context, provider_manager=provider_manager),

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

@@ -16,7 +16,6 @@ from graphon.graph_engine.entities.commands import AbortCommand, CommandType
 from graphon.graph_engine.layers import GraphEngineLayer
 from graphon.graph_events import GraphEngineEvent, GraphNodeEventBase, NodeRunSucceededEvent
 from graphon.nodes.base.node import Node
-from graphon.nodes.llm.runtime_protocols import PreparedLLMProtocol
 
 if TYPE_CHECKING:
     from graphon.nodes.llm.node import LLMNode
@@ -117,8 +116,7 @@ class LLMQuotaLayer(GraphEngineLayer):
                 case BuiltinNodeTypes.PARAMETER_EXTRACTOR:
                     model_instance = cast("ParameterExtractorNode", node).model_instance
                 case BuiltinNodeTypes.QUESTION_CLASSIFIER:
-                    typed_node: QuestionClassifierNode = cast("QuestionClassifierNode", node)
-                    model_instance = cast(PreparedLLMProtocol, typed_node._model_instance)
+                    model_instance = cast("QuestionClassifierNode", node).model_instance
                 case _:
                     return None
         except AttributeError:

api/core/entities/provider_configuration.py

@@ -24,7 +24,6 @@ from core.entities.provider_entities import (
 from core.helper import encrypter
 from core.helper.model_provider_cache import ProviderCredentialsCache, ProviderCredentialsCacheType
 from core.plugin.impl.model_runtime_factory import create_plugin_model_provider_factory
-from graphon.model_runtime import ModelRuntime
 from graphon.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType
 from graphon.model_runtime.entities.provider_entities import (
     ConfigurateMethod,
@@ -34,6 +33,7 @@ from graphon.model_runtime.entities.provider_entities import (
 )
 from graphon.model_runtime.model_providers.base.ai_model import AIModel
 from graphon.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from graphon.model_runtime.runtime import ModelRuntime
 from libs.datetime_utils import naive_utc_now
 from models.engine import db
 from models.enums import CredentialSourceType
@@ -109,7 +109,7 @@ class ProviderConfiguration(BaseModel):
     def get_model_provider_factory(self) -> ModelProviderFactory:
         """Return a provider factory that preserves any request-bound runtime."""
         if self._bound_model_runtime is not None:
-            return ModelProviderFactory(runtime=self._bound_model_runtime)
+            return ModelProviderFactory(model_runtime=self._bound_model_runtime)
         return create_plugin_model_provider_factory(tenant_id=self.tenant_id)
 
     def get_current_credentials(self, model_type: ModelType, model: str) -> dict[str, Any] | None:
@@ -1392,12 +1392,10 @@ class ProviderConfiguration(BaseModel):
         :param model_type: model type
         :return:
         """
-        from core.plugin.impl.model_runtime_factory import create_model_type_instance
-
         model_provider_factory = self.get_model_provider_factory()
-        return create_model_type_instance(
-            factory=model_provider_factory, provider=self.provider.provider, model_type=model_type
-        )
+
+        # Get model instance of LLM
+        return model_provider_factory.get_model_type_instance(provider=self.provider.provider, model_type=model_type)
 
     def get_model_schema(
         self, model_type: ModelType, model: str, credentials: dict[str, Any] | None

api/core/helper/creators.py

@@ -1,41 +0,0 @@
-"""
-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

@@ -4,7 +4,7 @@ from typing import cast
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.entities import DEFAULT_PLUGIN_ID
-from core.plugin.impl.model_runtime_factory import create_model_type_instance, create_plugin_model_provider_factory
+from core.plugin.impl.model_runtime_factory import create_plugin_model_provider_factory
 from extensions.ext_hosting_provider import hosting_configuration
 from graphon.model_runtime.entities.model_entities import ModelType
 from graphon.model_runtime.errors.invoke import InvokeBadRequestError
@@ -44,8 +44,8 @@ def check_moderation(tenant_id: str, model_config: ModelConfigWithCredentialsEnt
                 model_provider_factory = create_plugin_model_provider_factory(tenant_id=tenant_id)
 
                 # Get model instance of LLM
-                model_type_instance = create_model_type_instance(
-                    factory=model_provider_factory, provider=openai_provider_name, model_type=ModelType.MODERATION
+                model_type_instance = model_provider_factory.get_model_type_instance(
+                    provider=openai_provider_name, model_type=ModelType.MODERATION
                 )
                 model_type_instance = cast(ModerationModel, model_type_instance)
                 moderation_result = model_type_instance.invoke(

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, NotRequired, Protocol, TypedDict, cast
+from typing import Any, Protocol, TypedDict, cast
 
 import json_repair
 from sqlalchemy import select
@@ -18,6 +18,8 @@ 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,
 )
@@ -39,36 +41,6 @@ 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
@@ -151,15 +123,8 @@ class LLMGenerator:
         return name
 
     @classmethod
-    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)
+    def generate_suggested_questions_after_answer(cls, tenant_id: str, histories: str) -> Sequence[str]:
+        output_parser = SuggestedQuestionsAfterAnswerOutputParser()
         format_instructions = output_parser.get_format_instructions()
 
         prompt_template = PromptTemplateParser(template="{{histories}}\n{{format_instructions}}\nquestions:\n")
@@ -168,36 +133,10 @@ class LLMGenerator:
 
         try:
             model_manager = ModelManager.for_tenant(tenant_id=tenant_id)
-            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,
-                )
+            model_instance = model_manager.get_default_model_instance(
+                tenant_id=tenant_id,
+                model_type=ModelType.LLM,
+            )
         except InvokeAuthorizationError:
             return []
 
@@ -206,29 +145,19 @@ 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=model_parameters,
-                stop=stop,
+                model_parameters={
+                    "max_tokens": SUGGESTED_QUESTIONS_MAX_TOKENS,
+                    "temperature": SUGGESTED_QUESTIONS_TEMPERATURE,
+                },
                 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

@@ -3,28 +3,17 @@ import logging
 import re
 from collections.abc import Sequence
 
-from core.llm_generator.prompts import DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
+from core.llm_generator.prompts import 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 self._instruction_prompt
+        return SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
 
     def parse(self, text: str) -> Sequence[str]:
-        stripped_text = text.strip()
-        action_match = re.search(r"\[.*?\]", stripped_text, re.DOTALL)
+        action_match = re.search(r"\[.*?\]", text.strip(), re.DOTALL)
         questions: list[str] = []
         if action_match is not None:
             try:
@@ -34,6 +23,4 @@ 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

@@ -1,4 +1,5 @@
 # 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”.
 
@@ -95,8 +96,8 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 )
 
 
-# Default prompt and model parameters for suggested questions.
-DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
+# Default prompt for suggested questions (can be overridden by environment variable)
+_DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_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. "
@@ -104,6 +105,15 @@ DEFAULT_SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_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/model_manager.py

@@ -1,6 +1,5 @@
 import logging
 from collections.abc import Callable, Generator, Iterable, Mapping, Sequence
-from copy import deepcopy
 from typing import IO, Any, Literal, Optional, ParamSpec, TypeVar, Union, cast, overload
 
 from configs import dify_config
@@ -37,13 +36,11 @@ class ModelInstance:
     Model instance class.
     """
 
-    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str, credentials: dict | None = None) -> None:
+    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str):
         self.provider_model_bundle = provider_model_bundle
         self.model_name = model
         self.provider = provider_model_bundle.configuration.provider.provider
-        if credentials is None:
-            credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
-        self.credentials = credentials
+        self.credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
         # Runtime LLM invocation fields.
         self.parameters: Mapping[str, Any] = {}
         self.stop: Sequence[str] = ()
@@ -437,30 +434,8 @@ class ModelInstance:
 
 
 class ModelManager:
-    """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:
+    def __init__(self, provider_manager: ProviderManager):
         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":
@@ -488,19 +463,8 @@ class ModelManager:
             tenant_id=tenant_id, provider=provider, model_type=model_type
         )
 
-        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
+        model_instance = ModelInstance(provider_model_bundle, model)
+        return model_instance
 
     def get_default_provider_model_name(self, tenant_id: str, model_type: ModelType) -> tuple[str | None, str | None]:
         """

api/core/plugin/impl/model_runtime.py

@@ -4,7 +4,7 @@ import hashlib
 import logging
 from collections.abc import Generator, Iterable, Sequence
 from threading import Lock
-from typing import IO, Any, Literal, Union, overload
+from typing import IO, Any, Union
 
 from pydantic import ValidationError
 from redis import RedisError
@@ -14,18 +14,13 @@ from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
 from core.plugin.impl.asset import PluginAssetManager
 from core.plugin.impl.model import PluginModelClient
 from extensions.ext_redis import redis_client
-from graphon.model_runtime import ModelRuntime
-from graphon.model_runtime.entities.llm_entities import (
-    LLMResult,
-    LLMResultChunk,
-    LLMResultChunkWithStructuredOutput,
-    LLMResultWithStructuredOutput,
-)
+from graphon.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
 from graphon.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
 from graphon.model_runtime.entities.model_entities import AIModelEntity, ModelType
 from graphon.model_runtime.entities.provider_entities import ProviderEntity
 from graphon.model_runtime.entities.rerank_entities import MultimodalRerankInput, RerankResult
 from graphon.model_runtime.entities.text_embedding_entities import EmbeddingInputType, EmbeddingResult
+from graphon.model_runtime.runtime import ModelRuntime
 from models.provider_ids import ModelProviderID
 
 logger = logging.getLogger(__name__)
@@ -200,34 +195,6 @@ class PluginModelRuntime(ModelRuntime):
 
         return schema
 
-    @overload
-    def invoke_llm(
-        self,
-        *,
-        provider: str,
-        model: str,
-        credentials: dict[str, Any],
-        model_parameters: dict[str, Any],
-        prompt_messages: Sequence[PromptMessage],
-        tools: list[PromptMessageTool] | None,
-        stop: Sequence[str] | None,
-        stream: Literal[False],
-    ) -> LLMResult: ...
-
-    @overload
-    def invoke_llm(
-        self,
-        *,
-        provider: str,
-        model: str,
-        credentials: dict[str, Any],
-        model_parameters: dict[str, Any],
-        prompt_messages: Sequence[PromptMessage],
-        tools: list[PromptMessageTool] | None,
-        stop: Sequence[str] | None,
-        stream: Literal[True],
-    ) -> Generator[LLMResultChunk, None, None]: ...
-
     def invoke_llm(
         self,
         *,
@@ -255,50 +222,6 @@ class PluginModelRuntime(ModelRuntime):
             stream=stream,
         )
 
-    @overload
-    def invoke_llm_with_structured_output(
-        self,
-        *,
-        provider: str,
-        model: str,
-        credentials: dict[str, Any],
-        json_schema: dict[str, Any],
-        model_parameters: dict[str, Any],
-        prompt_messages: Sequence[PromptMessage],
-        stop: Sequence[str] | None,
-        stream: Literal[False],
-    ) -> LLMResultWithStructuredOutput: ...
-
-    @overload
-    def invoke_llm_with_structured_output(
-        self,
-        *,
-        provider: str,
-        model: str,
-        credentials: dict[str, Any],
-        json_schema: dict[str, Any],
-        model_parameters: dict[str, Any],
-        prompt_messages: Sequence[PromptMessage],
-        stop: Sequence[str] | None,
-        stream: Literal[True],
-    ) -> Generator[LLMResultChunkWithStructuredOutput, None, None]: ...
-
-    def invoke_llm_with_structured_output(
-        self,
-        *,
-        provider: str,
-        model: str,
-        credentials: dict[str, Any],
-        json_schema: dict[str, Any],
-        model_parameters: dict[str, Any],
-        prompt_messages: Sequence[PromptMessage],
-        stop: Sequence[str] | None,
-        stream: bool,
-    ) -> LLMResultWithStructuredOutput | Generator[LLMResultChunkWithStructuredOutput, None, None]:
-        # TODO: added to pass type check.
-        # it is a new method from upstream that is not invoked at all.
-        raise NotImplementedError
-
     def get_llm_num_tokens(
         self,
         *,

api/core/plugin/impl/model_runtime_factory.py

@@ -3,14 +3,6 @@ from __future__ import annotations
 from typing import TYPE_CHECKING
 
 from core.plugin.impl.model import PluginModelClient
-from graphon.model_runtime.entities.model_entities import ModelType
-from graphon.model_runtime.model_providers.base.ai_model import AIModel
-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.model_provider_factory import ModelProviderFactory
 
 if TYPE_CHECKING:
@@ -18,15 +10,6 @@ if TYPE_CHECKING:
     from core.plugin.impl.model_runtime import PluginModelRuntime
     from core.provider_manager import ProviderManager
 
-_MODEL_TYPE_CLASS_MAP: dict[ModelType, type[AIModel]] = {
-    ModelType.LLM: LargeLanguageModel,
-    ModelType.TEXT_EMBEDDING: TextEmbeddingModel,
-    ModelType.RERANK: RerankModel,
-    ModelType.SPEECH2TEXT: Speech2TextModel,
-    ModelType.MODERATION: ModerationModel,
-    ModelType.TTS: TTSModel,
-}
-
 
 class PluginModelAssembly:
     """Compose request-scoped model views on top of a single plugin runtime."""
@@ -55,7 +38,7 @@ class PluginModelAssembly:
     @property
     def model_provider_factory(self) -> ModelProviderFactory:
         if self._model_provider_factory is None:
-            self._model_provider_factory = ModelProviderFactory(runtime=self.model_runtime)
+            self._model_provider_factory = ModelProviderFactory(model_runtime=self.model_runtime)
         return self._model_provider_factory
 
     @property
@@ -104,30 +87,3 @@ def create_plugin_provider_manager(*, tenant_id: str, user_id: str | None = None
 def create_plugin_model_manager(*, tenant_id: str, user_id: str | None = None) -> ModelManager:
     """Create a tenant-bound model manager for service flows."""
     return create_plugin_model_assembly(tenant_id=tenant_id, user_id=user_id).model_manager
-
-
-def create_model_type_instance(
-    factory: ModelProviderFactory,
-    provider: str,
-    model_type: ModelType,
-) -> AIModel:
-    """Instantiate the AIModel subclass for *model_type* backed by *factory*'s runtime.
-
-    This replaces ``ModelProviderFactory.get_model_type_instance`` which was
-    removed in graphon 0.3.0.  The mapping from ModelType to concrete AIModel
-    subclass is maintained here so that callers do not need to know the
-    subclass constructors.
-
-    :param factory: factory whose ``runtime`` and provider resolution are used.
-    :param provider: provider identifier (canonical or short name).
-    :param model_type: the model type to instantiate.
-    :returns: an AIModel subclass instance wired to the factory's runtime.
-    :raises ValueError: if *model_type* is not supported.
-    """
-    model_class = _MODEL_TYPE_CLASS_MAP.get(model_type)
-    if model_class is None:
-        msg = f"Unsupported model type: {model_type}"
-        raise ValueError(msg)
-
-    provider_entity = factory.get_model_provider(provider)
-    return model_class(provider_schema=provider_entity, model_runtime=factory.runtime)

api/core/plugin/utils/http_parser.py

@@ -151,12 +151,6 @@ def deserialize_response(raw_data: bytes) -> Response:
 
     response = Response(response=body, status=status_code)
 
-    # Replace Flask's default headers (e.g. Content-Type, Content-Length) with the
-    # parsed ones so we faithfully reproduce the original response. Use Headers.add
-    # rather than dict-style assignment so that repeated headers such as Set-Cookie
-    # (and any other multi-valued header per RFC 9110) are preserved instead of
-    # being overwritten.
-    response.headers.clear()
     for line in lines[1:]:
         if not line:
             continue
@@ -164,6 +158,6 @@ def deserialize_response(raw_data: bytes) -> Response:
         if ":" not in line_str:
             continue
         name, value = line_str.split(":", 1)
-        response.headers.add(name, value.strip())
+        response.headers[name] = value.strip()
 
     return response

api/core/provider_manager.py

@@ -56,7 +56,7 @@ from models.provider_ids import ModelProviderID
 from services.feature_service import FeatureService
 
 if TYPE_CHECKING:
-    from graphon.model_runtime import ModelRuntime
+    from graphon.model_runtime.runtime import ModelRuntime
 
 _credentials_adapter: TypeAdapter[dict[str, Any]] = TypeAdapter(dict[str, Any])
 
@@ -70,32 +70,12 @@ 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:
         """
@@ -134,10 +114,6 @@ 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)
 
@@ -165,7 +141,7 @@ class ProviderManager:
                 )
 
         # Get all provider entities
-        model_provider_factory = ModelProviderFactory(runtime=self._model_runtime)
+        model_provider_factory = ModelProviderFactory(model_runtime=self._model_runtime)
         provider_entities = model_provider_factory.get_providers()
 
         # Get All preferred provider types of the workspace
@@ -297,8 +273,6 @@ class ProviderManager:
 
             provider_configurations[str(provider_id_entity)] = provider_configuration
 
-        self._configurations_cache[tenant_id] = provider_configurations
-
         # Return the encapsulated object
         return provider_configurations
 
@@ -362,7 +336,7 @@ class ProviderManager:
         if not default_model:
             return None
 
-        model_provider_factory = ModelProviderFactory(runtime=self._model_runtime)
+        model_provider_factory = ModelProviderFactory(model_runtime=self._model_runtime)
         provider_schema = model_provider_factory.get_provider_schema(provider=default_model.provider_name)
 
         return DefaultModelEntity(

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

@@ -139,10 +139,8 @@ 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 if dataset_keyword_table else "file"
+        keyword_data_source_type = dataset_keyword_table.data_source_type
         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:
@@ -156,8 +154,7 @@ class Jieba(BaseKeyword):
         if dataset_keyword_table:
             keyword_table_dict = dataset_keyword_table.keyword_table_dict
             if keyword_table_dict:
-                data: Any = keyword_table_dict["__data__"]
-                return dict(data["table"])
+                return dict(keyword_table_dict["__data__"]["table"])
         else:
             keyword_data_source_type = dify_config.KEYWORD_DATA_SOURCE_TYPE
             dataset_keyword_table = DatasetKeywordTable(

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

@@ -1,5 +1,4 @@
 import re
-from collections.abc import Callable
 from operator import itemgetter
 from typing import cast
 
@@ -81,14 +80,12 @@ class JiebaKeywordTableHandler:
 
             def extract_tags(self, sentence: str, top_k: int | None = 20, **kwargs):
                 # Basic frequency-based keyword extraction as a fallback when TF-IDF is unavailable.
-                top_k = cast(int | None, kwargs.pop("topK", top_k))
-                if top_k is None:
-                    top_k = 20
+                top_k = kwargs.pop("topK", top_k)
                 cut = getattr(jieba, "cut", None)
                 if self._lcut:
                     tokens = self._lcut(sentence)
                 elif callable(cut):
-                    tokens = list(cast(Callable[[str], list[str]], cut)(sentence))
+                    tokens = list(cut(sentence))
                 else:
                     tokens = re.findall(r"\w+", sentence)
 
@@ -109,9 +106,9 @@ class JiebaKeywordTableHandler:
         """Extract keywords with JIEBA tfidf."""
         keywords = self._tfidf.extract_tags(
             sentence=text,
-            topK=max_keywords_per_chunk or 10,
+            topK=max_keywords_per_chunk,
         )
-        # jieba.analyse.extract_tags returns an untyped list when withFlag is False by default.
+        # jieba.analyse.extract_tags returns list[Any] when withFlag is False by default.
         keywords = cast(list[str], keywords)
 
         return set(self._expand_tokens_with_subtokens(set(keywords)))

api/core/rag/datasource/retrieval_service.py

@@ -158,7 +158,7 @@ class RetrievalService:
                     )
 
             if futures:
-                for _ in concurrent.futures.as_completed(futures, timeout=3600):
+                for future in concurrent.futures.as_completed(futures, timeout=3600):
                     if exceptions:
                         for f in futures:
                             f.cancel()
@@ -551,7 +551,6 @@ class RetrievalService:
                 child_index_nodes = session.execute(child_chunk_stmt).scalars().all()
 
                 for i in child_index_nodes:
-                    assert i.index_node_id
                     segment_ids.append(i.segment_id)
                     if i.segment_id in child_chunk_map:
                         child_chunk_map[i.segment_id].append(i)

api/core/rag/datasource/vdb/vector_factory.py

@@ -39,58 +39,6 @@ class AbstractVectorFactory(ABC):
         return index_struct_dict
 
 
-class _LazyEmbeddings(Embeddings):
-    """Lazy proxy that defers materializing the real embedding model.
-
-    Constructing the real embeddings (via ``ModelManager.get_model_instance``)
-    transitively calls ``FeatureService.get_features`` → ``BillingService``
-    HTTP GETs (see ``provider_manager.py``). Cleanup paths
-    (``delete_by_ids`` / ``delete`` / ``text_exists``) do not need embeddings
-    at all, so deferring this until an ``embed_*`` method is actually invoked
-    keeps cleanup tasks resilient to transient billing-API failures and avoids
-    leaving stranded ``document_segments`` / ``child_chunks`` whenever billing
-    hiccups.
-
-    Existing callers that perform create / search operations are unaffected:
-    the first ``embed_*`` call materializes the underlying model and the
-    behavior is identical from that point on.
-    """
-
-    def __init__(self, dataset: Dataset):
-        self._dataset = dataset
-        self._real: Embeddings | None = None
-
-    def _ensure(self) -> Embeddings:
-        if self._real is None:
-            model_manager = ModelManager.for_tenant(tenant_id=self._dataset.tenant_id)
-            embedding_model = model_manager.get_model_instance(
-                tenant_id=self._dataset.tenant_id,
-                provider=self._dataset.embedding_model_provider,
-                model_type=ModelType.TEXT_EMBEDDING,
-                model=self._dataset.embedding_model,
-            )
-            self._real = CacheEmbedding(embedding_model)
-        return self._real
-
-    def embed_documents(self, texts: list[str]) -> list[list[float]]:
-        return self._ensure().embed_documents(texts)
-
-    def embed_multimodal_documents(self, multimodel_documents: list[dict[str, Any]]) -> list[list[float]]:
-        return self._ensure().embed_multimodal_documents(multimodel_documents)
-
-    def embed_query(self, text: str) -> list[float]:
-        return self._ensure().embed_query(text)
-
-    def embed_multimodal_query(self, multimodel_document: dict[str, Any]) -> list[float]:
-        return self._ensure().embed_multimodal_query(multimodel_document)
-
-    async def aembed_documents(self, texts: list[str]) -> list[list[float]]:
-        return await self._ensure().aembed_documents(texts)
-
-    async def aembed_query(self, text: str) -> list[float]:
-        return await self._ensure().aembed_query(text)
-
-
 class Vector:
     def __init__(self, dataset: Dataset, attributes: list | None = None):
         if attributes is None:
@@ -112,11 +60,7 @@ class Vector:
                 "original_chunk_id",
             ]
         self._dataset = dataset
-        # Use a lazy proxy so cleanup paths (delete_by_ids / delete / text_exists)
-        # never transitively trigger billing API calls during ``Vector(dataset)``
-        # construction. The real embedding model is materialized only when an
-        # ``embed_*`` method is actually invoked (i.e. create / search paths).
-        self._embeddings: Embeddings = _LazyEmbeddings(dataset)
+        self._embeddings = self._get_embeddings()
         self._attributes = attributes
         self._vector_processor = self._init_vector()
 

api/core/rag/docstore/dataset_docstore.py

@@ -11,7 +11,6 @@ from core.rag.models.document import AttachmentDocument, Document
 from extensions.ext_database import db
 from graphon.model_runtime.entities.model_entities import ModelType
 from models.dataset import ChildChunk, Dataset, DocumentSegment, SegmentAttachmentBinding
-from models.enums import SegmentType
 
 
 class DatasetDocumentStore:
@@ -128,7 +127,6 @@ class DatasetDocumentStore:
                 if save_child:
                     if doc.children:
                         for position, child in enumerate(doc.children, start=1):
-                            assert self._document_id
                             child_segment = ChildChunk(
                                 tenant_id=self._dataset.tenant_id,
                                 dataset_id=self._dataset.id,
@@ -139,7 +137,7 @@ class DatasetDocumentStore:
                                 index_node_hash=child.metadata.get("doc_hash"),
                                 content=child.page_content,
                                 word_count=len(child.page_content),
-                                type=SegmentType.AUTOMATIC,
+                                type="automatic",
                                 created_by=self._user_id,
                             )
                             db.session.add(child_segment)
@@ -165,7 +163,6 @@ class DatasetDocumentStore:
                     )
                     # add new child chunks
                     for position, child in enumerate(doc.children, start=1):
-                        assert self._document_id
                         child_segment = ChildChunk(
                             tenant_id=self._dataset.tenant_id,
                             dataset_id=self._dataset.id,
@@ -176,7 +173,7 @@ class DatasetDocumentStore:
                             index_node_hash=child.metadata.get("doc_hash"),
                             content=child.page_content,
                             word_count=len(child.page_content),
-                            type=SegmentType.AUTOMATIC,
+                            type="automatic",
                             created_by=self._user_id,
                         )
                         db.session.add(child_segment)

api/core/rag/extractor/extract_processor.py

@@ -94,7 +94,6 @@ class ExtractProcessor:
         cls, extract_setting: ExtractSetting, is_automatic: bool = False, file_path: str | None = None
     ) -> list[Document]:
         if extract_setting.datasource_type == DatasourceType.FILE:
-            upload_file = extract_setting.upload_file
             with tempfile.TemporaryDirectory() as temp_dir:
                 upload_file = extract_setting.upload_file
                 if not file_path:
@@ -105,7 +104,6 @@ class ExtractProcessor:
                     storage.download(upload_file.key, file_path)
                 input_file = Path(file_path)
                 file_extension = input_file.suffix.lower()
-                assert upload_file is not None, "upload_file is required"
                 etl_type = dify_config.ETL_TYPE
                 extractor: BaseExtractor | None = None
                 if etl_type == "Unstructured":

api/core/rag/retrieval/router/multi_dataset_function_call_router.py

@@ -28,10 +28,10 @@ class FunctionCallMultiDatasetRouter:
                 SystemPromptMessage(content="You are a helpful AI assistant."),
                 UserPromptMessage(content=query),
             ]
-            result: LLMResult = model_instance.invoke_llm(  # pyright: ignore[reportCallIssue, reportArgumentType]
+            result: LLMResult = model_instance.invoke_llm(
                 prompt_messages=prompt_messages,
                 tools=dataset_tools,
-                stream=False,  # pyright: ignore[reportArgumentType]
+                stream=False,
                 model_parameters={"temperature": 0.2, "top_p": 0.3, "max_tokens": 1500},
             )
             usage = result.usage or LLMUsage.empty_usage()

api/core/rag/splitter/fixed_text_splitter.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import codecs
 import re
-from collections.abc import Set as AbstractSet
+from collections.abc import Collection
 from typing import Any, Literal
 
 from core.model_manager import ModelInstance
@@ -21,8 +21,8 @@ class EnhanceRecursiveCharacterTextSplitter(RecursiveCharacterTextSplitter):
     def from_encoder[T: EnhanceRecursiveCharacterTextSplitter](
         cls: type[T],
         embedding_model_instance: ModelInstance | None,
-        allowed_special: Literal["all"] | AbstractSet[str] = frozenset(),
-        disallowed_special: Literal["all"] | AbstractSet[str] = "all",
+        allowed_special: Literal["all"] | set[str] = set(),
+        disallowed_special: Literal["all"] | Collection[str] = "all",
         **kwargs: Any,
     ) -> T:
         def _token_encoder(texts: list[str]) -> list[int]:
@@ -40,7 +40,6 @@ class EnhanceRecursiveCharacterTextSplitter(RecursiveCharacterTextSplitter):
 
             return [len(text) for text in texts]
 
-        _ = _token_encoder  # kept for future token-length wiring
         return cls(length_function=_character_encoder, **kwargs)
 
 

api/core/rag/splitter/text_splitter.py

@@ -4,8 +4,7 @@ import copy
 import logging
 import re
 from abc import ABC, abstractmethod
-from collections.abc import Callable, Iterable, Sequence
-from collections.abc import Set as AbstractSet
+from collections.abc import Callable, Collection, Iterable, Sequence, Set
 from dataclasses import dataclass
 from typing import Any, Literal
 
@@ -188,8 +187,8 @@ class TokenTextSplitter(TextSplitter):
         self,
         encoding_name: str = "gpt2",
         model_name: str | None = None,
-        allowed_special: Literal["all"] | AbstractSet[str] = frozenset(),
-        disallowed_special: Literal["all"] | AbstractSet[str] = "all",
+        allowed_special: Literal["all"] | Set[str] = set(),
+        disallowed_special: Literal["all"] | Collection[str] = "all",
         **kwargs: Any,
     ):
         """Create a new TextSplitter."""
@@ -208,8 +207,8 @@ class TokenTextSplitter(TextSplitter):
         else:
             enc = tiktoken.get_encoding(encoding_name)
         self._tokenizer = enc
-        self._allowed_special: Literal["all"] | AbstractSet[str] = allowed_special
-        self._disallowed_special: Literal["all"] | AbstractSet[str] = disallowed_special
+        self._allowed_special = allowed_special
+        self._disallowed_special = disallowed_special
 
     def split_text(self, text: str) -> list[str]:
         def _encode(_text: str) -> list[int]:

api/core/tools/utils/system_oauth_encryption.py

@@ -14,23 +14,23 @@ from configs import dify_config
 logger = logging.getLogger(__name__)
 
 
-class EncryptionError(Exception):
-    """Encryption/decryption specific error"""
+class OAuthEncryptionError(Exception):
+    """OAuth encryption/decryption specific error"""
 
     pass
 
 
-class SystemEncrypter:
+class SystemOAuthEncrypter:
     """
-    A simple parameters encrypter using AES-CBC encryption.
+    A simple OAuth parameters encrypter using AES-CBC encryption.
 
-    This class provides methods to encrypt and decrypt parameters
+    This class provides methods to encrypt and decrypt OAuth parameters
     using AES-CBC mode with a key derived from the application's SECRET_KEY.
     """
 
     def __init__(self, secret_key: str | None = None):
         """
-        Initialize the encrypter.
+        Initialize the OAuth encrypter.
 
         Args:
             secret_key: Optional secret key. If not provided, uses dify_config.SECRET_KEY
@@ -43,19 +43,19 @@ class SystemEncrypter:
         # Generate a fixed 256-bit key using SHA-256
         self.key = hashlib.sha256(secret_key.encode()).digest()
 
-    def encrypt_params(self, params: Mapping[str, Any]) -> str:
+    def encrypt_oauth_params(self, oauth_params: Mapping[str, Any]) -> str:
         """
-        Encrypt parameters.
+        Encrypt OAuth parameters.
 
         Args:
-            params: Parameters dictionary, e.g., {"client_id": "xxx", "client_secret": "xxx"}
+            oauth_params: OAuth parameters dictionary, e.g., {"client_id": "xxx", "client_secret": "xxx"}
 
         Returns:
             Base64-encoded encrypted string
 
         Raises:
-            EncryptionError: If encryption fails
-            ValueError: If params is invalid
+            OAuthEncryptionError: If encryption fails
+            ValueError: If oauth_params is invalid
         """
 
         try:
@@ -66,7 +66,7 @@ class SystemEncrypter:
             cipher = AES.new(self.key, AES.MODE_CBC, iv)
 
             # Encrypt data
-            padded_data = pad(TypeAdapter(dict).dump_json(dict(params)), AES.block_size)
+            padded_data = pad(TypeAdapter(dict).dump_json(dict(oauth_params)), AES.block_size)
             encrypted_data = cipher.encrypt(padded_data)
 
             # Combine IV and encrypted data
@@ -76,20 +76,20 @@ class SystemEncrypter:
             return base64.b64encode(combined).decode()
 
         except Exception as e:
-            raise EncryptionError(f"Encryption failed: {str(e)}") from e
+            raise OAuthEncryptionError(f"Encryption failed: {str(e)}") from e
 
-    def decrypt_params(self, encrypted_data: str) -> Mapping[str, Any]:
+    def decrypt_oauth_params(self, encrypted_data: str) -> Mapping[str, Any]:
         """
-        Decrypt parameters.
+        Decrypt OAuth parameters.
 
         Args:
             encrypted_data: Base64-encoded encrypted string
 
         Returns:
-            Decrypted parameters dictionary
+            Decrypted OAuth parameters dictionary
 
         Raises:
-            EncryptionError: If decryption fails
+            OAuthEncryptionError: If decryption fails
             ValueError: If encrypted_data is invalid
         """
         if not isinstance(encrypted_data, str):
@@ -118,70 +118,70 @@ class SystemEncrypter:
             unpadded_data = unpad(decrypted_data, AES.block_size)
 
             # Parse JSON
-            params: Mapping[str, Any] = TypeAdapter(Mapping[str, Any]).validate_json(unpadded_data)
+            oauth_params: Mapping[str, Any] = TypeAdapter(Mapping[str, Any]).validate_json(unpadded_data)
 
-            if not isinstance(params, dict):
+            if not isinstance(oauth_params, dict):
                 raise ValueError("Decrypted data is not a valid dictionary")
 
-            return params
+            return oauth_params
 
         except Exception as e:
-            raise EncryptionError(f"Decryption failed: {str(e)}") from e
+            raise OAuthEncryptionError(f"Decryption failed: {str(e)}") from e
 
 
 # Factory function for creating encrypter instances
-def create_system_encrypter(secret_key: str | None = None) -> SystemEncrypter:
+def create_system_oauth_encrypter(secret_key: str | None = None) -> SystemOAuthEncrypter:
     """
-    Create an encrypter instance.
+    Create an OAuth encrypter instance.
 
     Args:
         secret_key: Optional secret key. If not provided, uses dify_config.SECRET_KEY
 
     Returns:
-        SystemEncrypter instance
+        SystemOAuthEncrypter instance
     """
-    return SystemEncrypter(secret_key=secret_key)
+    return SystemOAuthEncrypter(secret_key=secret_key)
 
 
 # Global encrypter instance (for backward compatibility)
-_encrypter: SystemEncrypter | None = None
+_oauth_encrypter: SystemOAuthEncrypter | None = None
 
 
-def get_system_encrypter() -> SystemEncrypter:
+def get_system_oauth_encrypter() -> SystemOAuthEncrypter:
     """
-    Get the global encrypter instance.
+    Get the global OAuth encrypter instance.
 
     Returns:
-        SystemEncrypter instance
+        SystemOAuthEncrypter instance
     """
-    global _encrypter
-    if _encrypter is None:
-        _encrypter = SystemEncrypter()
-    return _encrypter
+    global _oauth_encrypter
+    if _oauth_encrypter is None:
+        _oauth_encrypter = SystemOAuthEncrypter()
+    return _oauth_encrypter
 
 
 # Convenience functions for backward compatibility
-def encrypt_system_params(params: Mapping[str, Any]) -> str:
+def encrypt_system_oauth_params(oauth_params: Mapping[str, Any]) -> str:
     """
-    Encrypt parameters using the global encrypter.
+    Encrypt OAuth parameters using the global encrypter.
 
     Args:
-        params: Parameters dictionary
+        oauth_params: OAuth parameters dictionary
 
     Returns:
         Base64-encoded encrypted string
     """
-    return get_system_encrypter().encrypt_params(params)
+    return get_system_oauth_encrypter().encrypt_oauth_params(oauth_params)
 
 
-def decrypt_system_params(encrypted_data: str) -> Mapping[str, Any]:
+def decrypt_system_oauth_params(encrypted_data: str) -> Mapping[str, Any]:
     """
-    Decrypt parameters using the global encrypter.
+    Decrypt OAuth parameters using the global encrypter.
 
     Args:
         encrypted_data: Base64-encoded encrypted string
 
     Returns:
-        Decrypted parameters dictionary
+        Decrypted OAuth parameters dictionary
     """
-    return get_system_encrypter().decrypt_params(encrypted_data)
+    return get_system_oauth_encrypter().decrypt_oauth_params(encrypted_data)

api/core/tools/utils/web_reader_tool.py

@@ -105,7 +105,7 @@ class Article:
 
 
 def extract_using_readabilipy(html: str):
-    json_article: dict[str, Any] = simple_json_from_html_string(html, use_readability=False)
+    json_article: dict[str, Any] = simple_json_from_html_string(html, use_readability=True)
     article = Article(
         title=json_article.get("title") or "",
         author=json_article.get("byline") or "",

api/core/workflow/human_input_forms.py

@@ -12,7 +12,7 @@ from collections.abc import Sequence
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
-from core.workflow.human_input_policy import HumanInputSurface, get_preferred_form_token
+from core.workflow.human_input_policy import get_preferred_form_token
 from extensions.ext_database import db
 from models.human_input import HumanInputFormRecipient, RecipientType
 
@@ -21,7 +21,6 @@ def load_form_tokens_by_form_id(
     form_ids: Sequence[str],
     *,
     session: Session | None = None,
-    surface: HumanInputSurface | None = None,
 ) -> dict[str, str]:
     """Load the preferred access token for each human input form."""
     unique_form_ids = list(dict.fromkeys(form_ids))
@@ -29,43 +28,23 @@ def load_form_tokens_by_form_id(
         return {}
 
     if session is not None:
-        return _load_form_tokens_by_form_id(session, unique_form_ids, surface=surface)
+        return _load_form_tokens_by_form_id(session, unique_form_ids)
 
     with Session(bind=db.engine, expire_on_commit=False) as new_session:
-        return _load_form_tokens_by_form_id(new_session, unique_form_ids, surface=surface)
+        return _load_form_tokens_by_form_id(new_session, unique_form_ids)
 
 
-def _load_form_tokens_by_form_id(
-    session: Session,
-    form_ids: Sequence[str],
-    *,
-    surface: HumanInputSurface | None = None,
-) -> dict[str, str]:
+def _load_form_tokens_by_form_id(session: Session, form_ids: Sequence[str]) -> dict[str, str]:
     recipients_by_form_id: dict[str, list[tuple[RecipientType, str]]] = {}
     stmt = select(HumanInputFormRecipient).where(HumanInputFormRecipient.form_id.in_(form_ids))
     for recipient in session.scalars(stmt):
         if not recipient.access_token:
             continue
-        recipients_by_form_id.setdefault(recipient.form_id, []).append(
-            (recipient.recipient_type, recipient.access_token)
-        )
+        recipients_by_form_id.setdefault(recipient.form_id, []).append((recipient.recipient_type, recipient.access_token))
 
     tokens_by_form_id: dict[str, str] = {}
     for form_id, recipients in recipients_by_form_id.items():
-        token = _get_surface_form_token(recipients, surface=surface)
+        token = get_preferred_form_token(recipients)
         if token is not None:
             tokens_by_form_id[form_id] = token
     return tokens_by_form_id
-
-
-def _get_surface_form_token(
-    recipients: Sequence[tuple[RecipientType, str]],
-    *,
-    surface: HumanInputSurface | None,
-) -> str | None:
-    if surface == HumanInputSurface.SERVICE_API:
-        for recipient_type, token in recipients:
-            if recipient_type == RecipientType.STANDALONE_WEB_APP and token:
-                return token
-
-    return get_preferred_form_token(recipients)

api/core/workflow/human_input_policy.py

@@ -4,7 +4,6 @@ from collections.abc import Mapping, Sequence
 from enum import StrEnum
 from typing import Any
 
-from graphon.entities.pause_reason import PauseReasonType
 from models.human_input import RecipientType
 
 
@@ -62,7 +61,7 @@ def enrich_human_input_pause_reasons(
     enriched: list[dict[str, Any]] = []
     for reason in reasons:
         updated = dict(reason)
-        if updated.get("TYPE") == PauseReasonType.HUMAN_INPUT_REQUIRED:
+        if updated.get("type") == "human_input_required":
             form_id = updated.get("form_id")
             if isinstance(form_id, str):
                 updated["form_token"] = form_tokens_by_form_id.get(form_id)

api/core/workflow/node_factory.py

@@ -365,8 +365,7 @@ class DifyNodeFactory(NodeFactory):
             (including pydantic ValidationError, which subclasses ValueError),
             if node type is unknown, or if no implementation exists for the resolved version
         """
-        adapted_node_config = adapt_node_config_for_graph(node_config)
-        typed_node_config = NodeConfigDictAdapter.validate_python(adapted_node_config)
+        typed_node_config = NodeConfigDictAdapter.validate_python(adapt_node_config_for_graph(node_config))
         node_id = typed_node_config["id"]
         node_data = typed_node_config["data"]
         node_class = self._resolve_node_class(node_type=node_data.type, node_version=str(node_data.version))
@@ -374,11 +373,6 @@ class DifyNodeFactory(NodeFactory):
         # Re-validate using the resolved node class so workflow-local node schemas
         # stay explicit and constructors receive the concrete typed payload.
         resolved_node_data = self._validate_resolved_node_data(node_class, node_data)
-        config_for_node_init: BaseNodeData | dict[str, Any]
-        if isinstance(resolved_node_data, BaseNodeData):
-            config_for_node_init = resolved_node_data.model_dump(mode="python", by_alias=True)
-        else:
-            config_for_node_init = resolved_node_data
         node_type = node_data.type
         node_init_kwargs_factories: Mapping[NodeType, Callable[[], dict[str, object]]] = {
             BuiltinNodeTypes.CODE: lambda: {
@@ -448,7 +442,7 @@ class DifyNodeFactory(NodeFactory):
         node_init_kwargs = node_init_kwargs_factories.get(node_type, lambda: {})()
         return node_class(
             node_id=node_id,
-            data=config_for_node_init,
+            config=resolved_node_data,
             graph_init_params=self.graph_init_params,
             graph_runtime_state=self.graph_runtime_state,
             **node_init_kwargs,
@@ -480,7 +474,10 @@ class DifyNodeFactory(NodeFactory):
         include_retriever_attachment_loader: bool,
         include_jinja2_template_renderer: bool,
     ) -> dict[str, object]:
-        validated_node_data = cast(LLMCompatibleNodeData, node_data)
+        validated_node_data = cast(
+            LLMCompatibleNodeData,
+            self._validate_resolved_node_data(node_class=node_class, node_data=node_data),
+        )
         model_instance = self._build_model_instance_for_llm_node(validated_node_data)
         node_init_kwargs: dict[str, object] = {
             "credentials_provider": self._llm_credentials_provider,

api/core/workflow/nodes/agent/agent_node.py

@@ -35,7 +35,7 @@ class AgentNode(Node[AgentNodeData]):
     def __init__(
         self,
         node_id: str,
-        data: AgentNodeData,
+        config: AgentNodeData,
         *,
         graph_init_params: GraphInitParams,
         graph_runtime_state: GraphRuntimeState,
@@ -46,7 +46,7 @@ class AgentNode(Node[AgentNodeData]):
     ) -> None:
         super().__init__(
             node_id=node_id,
-            data=data,
+            config=config,
             graph_init_params=graph_init_params,
             graph_runtime_state=graph_runtime_state,
         )

api/core/workflow/nodes/datasource/datasource_node.py

@@ -36,14 +36,14 @@ class DatasourceNode(Node[DatasourceNodeData]):
     def __init__(
         self,
         node_id: str,
-        data: DatasourceNodeData,
+        config: DatasourceNodeData,
         *,
         graph_init_params: "GraphInitParams",
         graph_runtime_state: "GraphRuntimeState",
     ) -> None:
         super().__init__(
             node_id=node_id,
-            data=data,
+            config=config,
             graph_init_params=graph_init_params,
             graph_runtime_state=graph_runtime_state,
         )

api/core/workflow/nodes/knowledge_index/knowledge_index_node.py

@@ -32,14 +32,14 @@ class KnowledgeIndexNode(Node[KnowledgeIndexNodeData]):
     def __init__(
         self,
         node_id: str,
-        data: KnowledgeIndexNodeData,
+        config: KnowledgeIndexNodeData,
         *,
         graph_init_params: "GraphInitParams",
         graph_runtime_state: "GraphRuntimeState",
     ) -> None:
         super().__init__(
             node_id=node_id,
-            data=data,
+            config=config,
             graph_init_params=graph_init_params,
             graph_runtime_state=graph_runtime_state,
         )

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -71,14 +71,14 @@ class KnowledgeRetrievalNode(LLMUsageTrackingMixin, Node[KnowledgeRetrievalNodeD
     def __init__(
         self,
         node_id: str,
-        data: KnowledgeRetrievalNodeData,
+        config: KnowledgeRetrievalNodeData,
         *,
         graph_init_params: "GraphInitParams",
         graph_runtime_state: "GraphRuntimeState",
     ) -> None:
         super().__init__(
             node_id=node_id,
-            data=data,
+            config=config,
             graph_init_params=graph_init_params,
             graph_runtime_state=graph_runtime_state,
         )

api/core/workflow/system_variables.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from collections import defaultdict
 from collections.abc import Mapping, Sequence
 from enum import StrEnum
-from typing import Any, Protocol
+from typing import Any, Protocol, cast
 from uuid import uuid4
 
 from graphon.enums import BuiltinNodeTypes
@@ -82,10 +82,13 @@ def build_system_variables(values: Mapping[str, Any] | None = None, /, **kwargs:
     normalized = _normalize_system_variable_values(values, **kwargs)
 
     return [
-        segment_to_variable(
-            segment=build_segment(value),
-            selector=system_variable_selector(key),
-            name=key,
+        cast(
+            Variable,
+            segment_to_variable(
+                segment=build_segment(value),
+                selector=system_variable_selector(key),
+                name=key,
+            ),
         )
         for key, value in normalized.items()
     ]
@@ -127,10 +130,13 @@ def build_bootstrap_variables(
 
     for node_id, value in rag_pipeline_variables_map.items():
         variables.append(
-            segment_to_variable(
-                segment=build_segment(value),
-                selector=(RAG_PIPELINE_VARIABLE_NODE_ID, node_id),
-                name=node_id,
+            cast(
+                Variable,
+                segment_to_variable(
+                    segment=build_segment(value),
+                    selector=(RAG_PIPELINE_VARIABLE_NODE_ID, node_id),
+                    name=node_id,
+                ),
             )
         )