fix(chat): enhance pointer event handling in chat components (#38385)

(cherry picked from commit 5b4ceacbe7)

.ee-base-commit

@@ -0,0 +1 @@
+cc72e56cd0cfd60581d98a2a5e2d4d4a41c9436d

.github/workflows/anti-slop.yml

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

.github/workflows/api-tests.yml

@@ -14,11 +14,11 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  test:
-    name: API Tests
-    runs-on: ubuntu-latest
+  api-unit:
+    name: API Unit Tests
+    runs-on: depot-ubuntu-24.04
     env:
-      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+      COVERAGE_FILE: coverage-unit
     defaults:
       run:
         shell: bash
@@ -35,7 +35,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -50,16 +50,62 @@ jobs:
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
 
+      - name: Run Unit Tests
+        run: uv run --project api bash dev/pytest/pytest_unit_tests.sh
+
+      - name: Upload unit coverage data
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: api-coverage-unit
+          path: coverage-unit
+          retention-days: 1
+
+  api-integration:
+    name: API Integration Tests
+    runs-on: depot-ubuntu-24.04
+    env:
+      COVERAGE_FILE: coverage-integration
+      STORAGE_TYPE: opendal
+      OPENDAL_SCHEME: fs
+      OPENDAL_FS_ROOT: /tmp/dify-storage
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        python-version:
+          - "3.12"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+          cache-dependency-glob: api/uv.lock
+
+      - name: Check UV lockfile
+        run: uv lock --project api --check
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
+          cp docker/envs/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
       - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -73,23 +119,91 @@ jobs:
         run: |
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
-      - name: Run API Tests
-        env:
-          STORAGE_TYPE: opendal
-          OPENDAL_SCHEME: fs
-          OPENDAL_FS_ROOT: /tmp/dify-storage
+      - name: Run Integration Tests
         run: |
           uv run --project api pytest \
             -n auto \
             --timeout "${PYTEST_TIMEOUT:-180}" \
             api/tests/integration_tests/workflow \
             api/tests/integration_tests/tools \
-            api/tests/test_containers_integration_tests \
-            api/tests/unit_tests
+            api/tests/test_containers_integration_tests
+
+      - name: Upload integration coverage data
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: api-coverage-integration
+          path: coverage-integration
+          retention-days: 1
+
+  api-coverage:
+    name: API Coverage
+    runs-on: depot-ubuntu-24.04
+    needs:
+      - api-unit
+      - api-integration
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+      COVERAGE_FILE: .coverage
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+          python-version: "3.12"
+          cache-dependency-glob: api/uv.lock
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Download coverage data
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          path: coverage-data
+          pattern: api-coverage-*
+          merge-multiple: true
+
+      - name: Combine coverage
+        run: |
+          set -euo pipefail
+
+          echo "### API Coverage" >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+          echo "Merged backend coverage report generated for Codecov project status." >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+
+          unit_coverage="$(find coverage-data -type f -name coverage-unit -print -quit)"
+          integration_coverage="$(find coverage-data -type f -name coverage-integration -print -quit)"
+          : "${unit_coverage:?coverage-unit artifact not found}"
+          : "${integration_coverage:?coverage-integration artifact not found}"
+
+          report_file="$(mktemp)"
+          uv run --project api coverage combine "$unit_coverage" "$integration_coverage"
+          uv run --project api coverage report --show-missing | tee "$report_file"
+          echo "Summary: \`$(tail -n 1 "$report_file")\`" >> "$GITHUB_STEP_SUMMARY"
+          {
+            echo ""
+            echo "<details><summary>Coverage report</summary>"
+            echo ""
+            echo '```'
+            cat "$report_file"
+            echo '```'
+            echo "</details>"
+          } >> "$GITHUB_STEP_SUMMARY"
+          uv run --project api coverage xml -o coverage.xml
 
       - name: Report coverage
-        if: ${{ env.CODECOV_TOKEN != '' && matrix.python-version == '3.12' }}
-        uses: codecov/codecov-action@1af58845a975a7985b0beb0cbe6fbbb71a41dbad # v5.5.3
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
         with:
           files: ./coverage.xml
           disable_search: true

.github/workflows/autofix.yml

@@ -2,6 +2,9 @@ name: autofix.ci
 on:
   pull_request:
     branches: ["main"]
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
   push:
     branches: ["main"]
 permissions:
@@ -10,13 +13,19 @@ permissions:
 jobs:
   autofix:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - name: Complete merge group check
+        if: github.event_name == 'merge_group'
+        run: echo "autofix.ci updates pull request branches, not merge group refs."
+
+      - if: github.event_name != 'merge_group'
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Check Docker Compose inputs
+        if: github.event_name != 'merge_group'
         id: docker-compose-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             docker/generate_docker_compose
@@ -24,30 +33,39 @@ jobs:
             docker/docker-compose-template.yaml
             docker/docker-compose.yaml
       - name: Check web inputs
+        if: github.event_name != 'merge_group'
         id: web-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             web/**
+            packages/**
+            package.json
+            pnpm-lock.yaml
+            pnpm-workspace.yaml
+            .nvmrc
       - name: Check api inputs
+        if: github.event_name != 'merge_group'
         id: api-changes
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             api/**
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      - if: github.event_name != 'merge_group'
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: "3.11"
 
-      - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      - if: github.event_name != 'merge_group'
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
 
       - name: Generate Docker Compose
-        if: steps.docker-compose-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group' && steps.docker-compose-changes.outputs.any_changed == 'true'
         run: |
           cd docker
           ./generate_docker_compose
 
-      - if: steps.api-changes.outputs.any_changed == 'true'
+      - if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
         run: |
           cd api
           uv sync --dev
@@ -59,13 +77,13 @@ jobs:
           uv run ruff format ..
 
       - name: count migration progress
-        if: steps.api-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
         run: |
           cd api
           ./cnt_base.sh
 
       - name: ast-grep
-        if: steps.api-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
         run: |
           # ast-grep exits 1 if no matches are found; allow idempotent runs.
           uvx --from ast-grep-cli ast-grep --pattern 'db.session.query($WHATEVER).filter($HERE)' --rewrite 'db.session.query($WHATEVER).where($HERE)' -l py --update-all || true
@@ -95,13 +113,23 @@ jobs:
           find . -name "*.py.bak" -type f -delete
 
       - name: Setup web environment
-        if: steps.web-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group'
         uses: ./.github/actions/setup-web
 
+      - name: Generate API docs
+        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
+        run: |
+          cd api
+          uv run dev/generate_swagger_markdown_docs.py --swagger-dir ../packages/contracts/openapi --markdown-dir openapi/markdown --keep-swagger-json
+
+      - name: Generate frontend contracts
+        if: github.event_name != 'merge_group' && steps.api-changes.outputs.any_changed == 'true'
+        run: pnpm --dir packages/contracts gen-api-contract-from-openapi
+
       - name: ESLint autofix
-        if: steps.web-changes.outputs.any_changed == 'true'
+        if: github.event_name != 'merge_group' && steps.web-changes.outputs.any_changed == 'true'
         run: |
-          cd web
           vp exec eslint --concurrency=2 --prune-suppressions --quiet || true
 
-      - uses: autofix-ci/action@7a166d7532b277f34e16238930461bf77f9d7ed8 # v1.3.3
+      - if: github.event_name != 'merge_group'
+        uses: autofix-ci/action@c5b2d67aa2274e7b5a18224e8171550871fc7e4a # v1.3.4

.github/workflows/build-push.yml

@@ -24,27 +24,42 @@ env:
 
 jobs:
   build:
-    runs-on: ${{ matrix.platform == 'linux/arm64' && 'arm64_runner' || 'ubuntu-latest' }}
+    runs-on: ${{ matrix.runs_on }}
     if: github.repository == 'langgenius/dify'
+    permissions:
+      contents: read
+      id-token: write
     strategy:
       matrix:
         include:
           - service_name: "build-api-amd64"
             image_name_env: "DIFY_API_IMAGE_NAME"
-            context: "api"
+            artifact_context: "api"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
             platform: linux/amd64
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-api-arm64"
             image_name_env: "DIFY_API_IMAGE_NAME"
-            context: "api"
+            artifact_context: "api"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
             platform: linux/arm64
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-web-amd64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
-            context: "web"
+            artifact_context: "web"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
             platform: linux/amd64
+            runs_on: depot-ubuntu-24.04-4
           - service_name: "build-web-arm64"
             image_name_env: "DIFY_WEB_IMAGE_NAME"
-            context: "web"
+            artifact_context: "web"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
             platform: linux/arm64
+            runs_on: depot-ubuntu-24.04-4
 
     steps:
       - name: Prepare
@@ -53,16 +68,13 @@ jobs:
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
       - name: Login to Docker Hub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
+      - name: Set up Depot CLI
+        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
 
       - name: Extract metadata for Docker
         id: meta
@@ -72,15 +84,15 @@ jobs:
 
       - name: Build Docker image
         id: build
-        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
+        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
         with:
-          context: "{{defaultContext}}:${{ matrix.context }}"
+          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:
@@ -91,16 +103,40 @@ jobs:
           touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: digests-${{ matrix.context }}-${{ env.PLATFORM_PAIR }}
+          name: digests-${{ matrix.artifact_context }}-${{ env.PLATFORM_PAIR }}
           path: /tmp/digests/*
           if-no-files-found: error
           retention-days: 1
 
+  fork-build-validate:
+    if: github.repository != 'langgenius/dify'
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        include:
+          - service_name: "validate-api-amd64"
+            build_context: "{{defaultContext}}:api"
+            file: "Dockerfile"
+          - service_name: "validate-web-amd64"
+            build_context: "{{defaultContext}}"
+            file: "web/Dockerfile"
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
+
+      - name: Validate Docker image
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        with:
+          push: false
+          context: ${{ matrix.build_context }}
+          file: ${{ matrix.file }}
+          platforms: linux/amd64
+
   create-manifest:
     needs: build
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     if: github.repository == 'langgenius/dify'
     strategy:
       matrix:
@@ -120,7 +156,7 @@ jobs:
           merge-multiple: true
 
       - name: Login to Docker Hub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v4.0.0
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}

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

@@ -9,7 +9,7 @@ concurrency:
 
 jobs:
   db-migration-test-postgres:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -19,7 +19,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -37,10 +37,10 @@ jobs:
       - name: Prepare middleware env
         run: |
           cd docker
-          cp middleware.env.example middleware.env
+          cp envs/middleware.env.example middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -59,7 +59,7 @@ jobs:
         run: uv run --directory api flask upgrade-db
 
   db-migration-test-mysql:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -69,7 +69,7 @@ jobs:
           persist-credentials: false
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: "3.12"
@@ -87,14 +87,14 @@ jobs:
       - name: Prepare middleware env for MySQL
         run: |
           cd docker
-          cp middleware.env.example middleware.env
+          cp envs/middleware.env.example middleware.env
           sed -i 's/DB_TYPE=postgresql/DB_TYPE=mysql/' middleware.env
           sed -i 's/DB_HOST=db_postgres/DB_HOST=db_mysql/' middleware.env
           sed -i 's/DB_PORT=5432/DB_PORT=3306/' middleware.env
           sed -i 's/DB_USERNAME=postgres/DB_USERNAME=mysql/' middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -110,6 +110,28 @@ jobs:
           sed -i 's/DB_PORT=5432/DB_PORT=3306/' .env
           sed -i 's/DB_USERNAME=postgres/DB_USERNAME=root/' .env
 
+      # hoverkraft-tech/compose-action@v2.6.0 only waits for `docker compose up -d`
+      # to return (container processes started); it does not wait on healthcheck
+      # status. mysql:8.0's first-time init takes 15-30s, so without an explicit
+      # wait the migration runs while InnoDB is still initialising and gets
+      # killed with "Lost connection during query". Poll a real SELECT until it
+      # succeeds.
+      - name: Wait for MySQL to accept queries
+        run: |
+          set +e
+          for i in $(seq 1 60); do
+            if docker run --rm --network host mysql:8.0 \
+                mysql -h 127.0.0.1 -P 3306 -uroot -pdifyai123456 \
+                -e 'SELECT 1' >/dev/null 2>&1; then
+              echo "MySQL ready after ${i}s"
+              exit 0
+            fi
+            sleep 1
+          done
+          echo "MySQL not ready after 60s; dumping container logs:"
+          docker compose -f docker/docker-compose.middleware.yaml --profile mysql logs --tail=200 db_mysql
+          exit 1
+
       - name: Run DB Migration
         env:
           DEBUG: true

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

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

.github/workflows/deploy-dev.yml

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

.github/workflows/deploy-enterprise.yml

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

.github/workflows/deploy-hitl.yml

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

.github/workflows/docker-build.yml

@@ -14,35 +14,69 @@ concurrency:
 
 jobs:
   build-docker:
-    runs-on: ubuntu-latest
+    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
-            context: "api"
+            runs_on: depot-ubuntu-24.04-4
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
           - service_name: "api-arm64"
             platform: linux/arm64
-            context: "api"
+            runs_on: depot-ubuntu-24.04-4
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
           - service_name: "web-amd64"
             platform: linux/amd64
-            context: "web"
+            runs_on: depot-ubuntu-24.04-4
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
           - service_name: "web-arm64"
             platform: linux/arm64
-            context: "web"
+            runs_on: depot-ubuntu-24.04-4
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
     steps:
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v4.0.0
+      - name: Set up Depot CLI
+        uses: depot/setup-action@15c09a5f77a0840ad4bce955686522a257853461 # v1.7.1
 
+      - name: Build Docker Image
+        uses: depot/build-push-action@5f3b3c2e5a00f0093de47f657aeaefcedff27d18 # v1.17.0
+        with:
+          project: ${{ vars.DEPOT_PROJECT_ID }}
+          push: false
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
+          platforms: ${{ matrix.platform }}
+
+  build-docker-fork:
+    if: github.event.pull_request.head.repo.full_name != github.repository
+    runs-on: ubuntu-24.04
+    permissions:
+      contents: read
+    strategy:
+      matrix:
+        include:
+          - service_name: "api-amd64"
+            context: "{{defaultContext}}:api"
+            file: "Dockerfile"
+          - service_name: "web-amd64"
+            context: "{{defaultContext}}"
+            file: "web/Dockerfile"
+    steps:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0
 
       - name: Build Docker Image
-        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
         with:
           push: false
-          context: "{{defaultContext}}:${{ matrix.context }}"
-          file: "${{ matrix.file }}"
-          platforms: ${{ matrix.platform }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          context: ${{ matrix.context }}
+          file: ${{ matrix.file }}
+          platforms: linux/amd64

.github/workflows/hotfix-cherry-pick.yml

@@ -0,0 +1,49 @@
+name: Hotfix Cherry-Pick Provenance
+
+on:
+  pull_request:
+    branches:
+      - 'hotfix/**'
+      - 'lts/**'
+    types:
+      - opened
+      - edited
+      - reopened
+      - ready_for_review
+      - synchronize
+
+permissions:
+  contents: read
+
+concurrency:
+  group: hotfix-cherry-pick-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  check-cherry-pick-provenance:
+    name: Require cherry-pick provenance
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Fetch PR base, PR head, and main
+        env:
+          BASE_REF: ${{ github.base_ref }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        run: |
+          git fetch --no-tags --prune origin \
+            "+refs/heads/main:refs/remotes/origin/main" \
+            "+refs/heads/${BASE_REF}:refs/remotes/origin/${BASE_REF}" \
+            "+refs/pull/${PR_NUMBER}/head:refs/remotes/pull/${PR_NUMBER}/head"
+
+      - name: Load checker from main
+        run: git show origin/main:.github/scripts/check-hotfix-cherry-picks.sh > "$RUNNER_TEMP/check-hotfix-cherry-picks.sh"
+
+      - name: Check PR commits
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+          MAIN_REF: origin/main
+        run: bash "$RUNNER_TEMP/check-hotfix-cherry-picks.sh"

.github/workflows/labeler.yml

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

.github/workflows/main-ci.yml

@@ -3,10 +3,14 @@ name: Main CI Pipeline
 on:
   pull_request:
     branches: ["main"]
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
   push:
     branches: ["main"]
 
 permissions:
+  actions: write
   contents: write
   pull-requests: write
   checks: write
@@ -17,12 +21,28 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  pre_job:
+    name: Skip Duplicate Checks
+    runs-on: depot-ubuntu-24.04
+    outputs:
+      should_skip: ${{ steps.skip_check.outputs.should_skip || 'false' }}
+    steps:
+      - id: skip_check
+        continue-on-error: true
+        uses: fkirc/skip-duplicate-actions@f75f66ce1886f00957d99748a42c724f4330bdcf # v5.3.1
+        with:
+          cancel_others: 'true'
+          concurrent_skipping: same_content_newer
+
   # Check which paths were changed to determine which tests to run
   check-changes:
     name: Check Changed Files
-    runs-on: ubuntu-latest
+    needs: pre_job
+    if: needs.pre_job.outputs.should_skip != 'true'
+    runs-on: depot-ubuntu-24.04
     outputs:
       api-changed: ${{ steps.changes.outputs.api }}
+      e2e-changed: ${{ steps.changes.outputs.e2e }}
       web-changed: ${{ steps.changes.outputs.web }}
       vdb-changed: ${{ steps.changes.outputs.vdb }}
       migration-changed: ${{ steps.changes.outputs.migration }}
@@ -34,49 +54,375 @@ jobs:
           filters: |
             api:
               - 'api/**'
-              - 'docker/**'
               - '.github/workflows/api-tests.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/envs/middleware.env.example'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/volumes/sandbox/conf/**'
             web:
               - 'web/**'
+              - 'packages/**'
+              - 'package.json'
+              - 'pnpm-lock.yaml'
+              - 'pnpm-workspace.yaml'
+              - '.nvmrc'
               - '.github/workflows/web-tests.yml'
               - '.github/actions/setup-web/**'
+            e2e:
+              - 'api/**'
+              - 'api/pyproject.toml'
+              - 'api/uv.lock'
+              - 'e2e/**'
+              - 'web/**'
+              - 'packages/**'
+              - 'package.json'
+              - 'pnpm-lock.yaml'
+              - 'pnpm-workspace.yaml'
+              - '.nvmrc'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/envs/middleware.env.example'
+              - '.github/workflows/web-e2e.yml'
+              - '.github/actions/setup-web/**'
             vdb:
               - 'api/core/rag/datasource/**'
-              - 'docker/**'
+              - 'api/tests/integration_tests/vdb/**'
+              - 'api/providers/vdb/*/tests/**'
               - '.github/workflows/vdb-tests.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/envs/middleware.env.example'
+              - 'docker/docker-compose.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/certbot/**'
+              - 'docker/couchbase-server/**'
+              - 'docker/elasticsearch/**'
+              - 'docker/iris/**'
+              - 'docker/nginx/**'
+              - 'docker/pgvector/**'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/startupscripts/**'
+              - 'docker/tidb/**'
+              - 'docker/volumes/**'
               - 'api/uv.lock'
               - 'api/pyproject.toml'
             migration:
               - 'api/migrations/**'
+              - 'api/.env.example'
               - '.github/workflows/db-migration-test.yml'
+              - '.github/workflows/expose_service_ports.sh'
+              - 'docker/.env.example'
+              - 'docker/envs/middleware.env.example'
+              - 'docker/docker-compose.middleware.yaml'
+              - 'docker/docker-compose-template.yaml'
+              - 'docker/generate_docker_compose'
+              - 'docker/ssrf_proxy/**'
+              - 'docker/volumes/sandbox/conf/**'
 
-  # Run tests in parallel
-  api-tests:
-    name: API Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.api-changed == 'true'
+  # Run tests in parallel while always emitting stable required checks.
+  api-tests-run:
+    name: Run API Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.api-changed == 'true'
     uses: ./.github/workflows/api-tests.yml
     secrets: inherit
 
-  web-tests:
-    name: Web Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.web-changed == 'true'
+  api-tests-skip:
+    name: Skip API Tests
+    needs:
+      - 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
+    steps:
+      - name: Report skipped API tests
+        run: echo "No API-related changes detected; skipping API tests."
+
+  api-tests:
+    name: API Tests
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - api-tests-run
+      - api-tests-skip
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - name: Finalize API Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.api-changed }}
+          RUN_RESULT: ${{ needs.api-tests-run.result }}
+          SKIP_RESULT: ${{ needs.api-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "API tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "API tests ran successfully."
+              exit 0
+            fi
+
+            echo "API tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "API tests were skipped because no API-related files changed."
+            exit 0
+          fi
+
+          echo "API tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  web-tests-run:
+    name: Run Web Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.web-changed == 'true'
     uses: ./.github/workflows/web-tests.yml
     secrets: inherit
 
+  web-tests-skip:
+    name: Skip Web Tests
+    needs:
+      - 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
+    steps:
+      - name: Report skipped web tests
+        run: echo "No web-related changes detected; skipping web tests."
+
+  web-tests:
+    name: Web Tests
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - web-tests-run
+      - web-tests-skip
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - name: Finalize Web Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.web-changed }}
+          RUN_RESULT: ${{ needs.web-tests-run.result }}
+          SKIP_RESULT: ${{ needs.web-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "Web tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "Web tests ran successfully."
+              exit 0
+            fi
+
+            echo "Web tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "Web tests were skipped because no web-related files changed."
+            exit 0
+          fi
+
+          echo "Web tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  web-e2e-run:
+    name: Run Web Full-Stack E2E
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed == 'true'
+    uses: ./.github/workflows/web-e2e.yml
+
+  web-e2e-skip:
+    name: Skip Web Full-Stack E2E
+    needs:
+      - 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
+    steps:
+      - name: Report skipped web full-stack e2e
+        run: echo "No E2E-related changes detected; skipping web full-stack E2E."
+
+  web-e2e:
+    name: Web Full-Stack E2E
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - web-e2e-run
+      - web-e2e-skip
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - name: Finalize Web Full-Stack E2E status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.e2e-changed }}
+          RUN_RESULT: ${{ needs.web-e2e-run.result }}
+          SKIP_RESULT: ${{ needs.web-e2e-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "Web full-stack E2E was skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "Web full-stack E2E ran successfully."
+              exit 0
+            fi
+
+            echo "Web full-stack E2E was required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "Web full-stack E2E was skipped because no E2E-related files changed."
+            exit 0
+          fi
+
+          echo "Web full-stack E2E was not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
   style-check:
     name: Style Check
+    needs: pre_job
+    if: needs.pre_job.outputs.should_skip != 'true'
     uses: ./.github/workflows/style.yml
 
+  vdb-tests-run:
+    name: Run VDB Tests
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.vdb-changed == 'true'
+    uses: ./.github/workflows/vdb-tests.yml
+
+  vdb-tests-skip:
+    name: Skip VDB Tests
+    needs:
+      - 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
+    steps:
+      - name: Report skipped VDB tests
+        run: echo "No VDB-related changes detected; skipping VDB tests."
+
   vdb-tests:
     name: VDB Tests
-    needs: check-changes
-    if: needs.check-changes.outputs.vdb-changed == 'true'
-    uses: ./.github/workflows/vdb-tests.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - vdb-tests-run
+      - vdb-tests-skip
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - name: Finalize VDB Tests status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.vdb-changed }}
+          RUN_RESULT: ${{ needs.vdb-tests-run.result }}
+          SKIP_RESULT: ${{ needs.vdb-tests-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "VDB tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "VDB tests ran successfully."
+              exit 0
+            fi
+
+            echo "VDB tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "VDB tests were skipped because no VDB-related files changed."
+            exit 0
+          fi
+
+          echo "VDB tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1
+
+  db-migration-test-run:
+    name: Run DB Migration Test
+    needs:
+      - pre_job
+      - check-changes
+    if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.migration-changed == 'true'
+    uses: ./.github/workflows/db-migration-test.yml
+
+  db-migration-test-skip:
+    name: Skip DB Migration Test
+    needs:
+      - 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
+    steps:
+      - name: Report skipped DB migration tests
+        run: echo "No migration-related changes detected; skipping DB migration tests."
 
   db-migration-test:
     name: DB Migration Test
-    needs: check-changes
-    if: needs.check-changes.outputs.migration-changed == 'true'
-    uses: ./.github/workflows/db-migration-test.yml
+    if: ${{ always() }}
+    needs:
+      - pre_job
+      - check-changes
+      - db-migration-test-run
+      - db-migration-test-skip
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - name: Finalize DB Migration Test status
+        env:
+          SHOULD_SKIP_WORKFLOW: ${{ needs.pre_job.outputs.should_skip }}
+          TESTS_CHANGED: ${{ needs.check-changes.outputs.migration-changed }}
+          RUN_RESULT: ${{ needs.db-migration-test-run.result }}
+          SKIP_RESULT: ${{ needs.db-migration-test-skip.result }}
+        run: |
+          if [[ "$SHOULD_SKIP_WORKFLOW" == 'true' ]]; then
+            echo "DB migration tests were skipped because this workflow run duplicated a successful or newer run."
+            exit 0
+          fi
+
+          if [[ "$TESTS_CHANGED" == 'true' ]]; then
+            if [[ "$RUN_RESULT" == 'success' ]]; then
+              echo "DB migration tests ran successfully."
+              exit 0
+            fi
+
+            echo "DB migration tests were required but finished with result: $RUN_RESULT" >&2
+            exit 1
+          fi
+
+          if [[ "$SKIP_RESULT" == 'success' ]]; then
+            echo "DB migration tests were skipped because no migration-related files changed."
+            exit 0
+          fi
+
+          echo "DB migration tests were not required, but the skip job finished with result: $SKIP_RESULT" >&2
+          exit 1

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

@@ -12,7 +12,7 @@ permissions: {}
 jobs:
   comment:
     name: Comment PR with pyrefly diff
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       actions: read
       contents: read
@@ -21,7 +21,7 @@ jobs:
     if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.pull_requests[0].head.repo.full_name != github.repository }}
     steps:
       - name: Download pyrefly diff artifact
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -49,7 +49,7 @@ jobs:
         run: unzip -o pyrefly_diff.zip
 
       - name: Post comment
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -76,13 +76,29 @@ jobs:
               diff += '\\n\\n... (truncated) ...';
             }
 
-            const body = diff.trim()
-              ? '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>'
-              : '### Pyrefly Diff\nNo changes detected.';
+            if (diff.trim()) {
+              const body = '### Pyrefly Diff\n<details>\n<summary>base → PR</summary>\n\n```diff\n' + diff + '\n```\n</details>';
+              const marker = '### Pyrefly Diff';
+              const { data: comments } = await github.rest.issues.listComments({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+              });
+              const existing = comments.find((comment) => comment.body.startsWith(marker));
 
-            await github.rest.issues.createComment({
-              issue_number: prNumber,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body,
-            });
+              if (existing) {
+                await github.rest.issues.updateComment({
+                  comment_id: existing.id,
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  body,
+                });
+              } else {
+                await github.rest.issues.createComment({
+                  issue_number: prNumber,
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  body,
+                });
+              }
+            }

.github/workflows/pyrefly-diff.yml

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   pyrefly-diff:
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       contents: read
       issues: write
@@ -22,7 +22,7 @@ jobs:
           fetch-depth: 0
 
       - name: Setup Python & UV
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
 
@@ -50,12 +50,23 @@ jobs:
         run: |
           diff -u /tmp/pyrefly_base.txt /tmp/pyrefly_pr.txt > pyrefly_diff.txt || true
 
+      - name: Check if line counts match
+        id: line_count_check
+        run: |
+          base_lines=$(wc -l < /tmp/pyrefly_base.txt)
+          pr_lines=$(wc -l < /tmp/pyrefly_pr.txt)
+          if [ "$base_lines" -eq "$pr_lines" ]; then
+            echo "same=true" >> $GITHUB_OUTPUT
+          else
+            echo "same=false" >> $GITHUB_OUTPUT
+          fi
+
       - name: Save PR number
         run: |
           echo ${{ github.event.pull_request.number }} > pr_number.txt
 
       - name: Upload pyrefly diff
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: pyrefly_diff
           path: |
@@ -63,8 +74,8 @@ jobs:
             pr_number.txt
 
       - name: Comment PR with pyrefly diff
-        if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        if: ${{ github.event.pull_request.head.repo.full_name == github.repository && steps.line_count_check.outputs.same == 'false' }}
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -92,9 +103,26 @@ jobs:
                 ].join('\n')
               : '### Pyrefly Diff\nNo changes detected.';
 
-            await github.rest.issues.createComment({
+            const marker = '### Pyrefly Diff';
+            const { data: comments } = await github.rest.issues.listComments({
               issue_number: prNumber,
               owner: context.repo.owner,
               repo: context.repo.repo,
-              body,
             });
+            const existing = comments.find((comment) => comment.body.startsWith(marker));
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            }

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

@@ -0,0 +1,118 @@
+name: Comment with Pyrefly Type Coverage
+
+on:
+  workflow_run:
+    workflows:
+      - Pyrefly Type Coverage
+    types:
+      - completed
+
+permissions: {}
+
+jobs:
+  comment:
+    name: Comment PR with type coverage
+    runs-on: depot-ubuntu-24.04
+    permissions:
+      actions: read
+      contents: read
+      issues: write
+      pull-requests: write
+    if: ${{ github.event.workflow_run.conclusion == 'success' && github.event.workflow_run.pull_requests[0].head.repo.full_name != github.repository }}
+    steps:
+      - name: Checkout default branch (trusted code)
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Setup Python & UV
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Download type coverage artifact
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const artifacts = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: ${{ github.event.workflow_run.id }},
+            });
+            const match = artifacts.data.artifacts.find((artifact) =>
+              artifact.name === 'pyrefly_type_coverage'
+            );
+            if (!match) {
+              throw new Error('pyrefly_type_coverage artifact not found');
+            }
+            const download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: match.id,
+              archive_format: 'zip',
+            });
+            fs.writeFileSync('pyrefly_type_coverage.zip', Buffer.from(download.data));
+
+      - name: Unzip artifact
+        run: unzip -o pyrefly_type_coverage.zip
+
+      - name: Render coverage markdown from structured data
+        id: render
+        run: |
+          comment_body="$(uv run --directory api python libs/pyrefly_type_coverage.py \
+            --base base_report.json \
+            < pr_report.json)"
+
+          {
+            echo "### Pyrefly Type Coverage"
+            echo ""
+            echo "$comment_body"
+          } > /tmp/type_coverage_comment.md
+
+      - name: Post comment
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const body = fs.readFileSync('/tmp/type_coverage_comment.md', { encoding: 'utf8' });
+            let prNumber = null;
+            try {
+              prNumber = parseInt(fs.readFileSync('pr_number.txt', { encoding: 'utf8' }), 10);
+            } catch (err) {
+              const prs = context.payload.workflow_run.pull_requests || [];
+              if (prs.length > 0 && prs[0].number) {
+                prNumber = prs[0].number;
+              }
+            }
+            if (!prNumber) {
+              throw new Error('PR number not found in artifact or workflow_run payload');
+            }
+
+            // Update existing comment if one exists, otherwise create new
+            const { data: comments } = await github.rest.issues.listComments({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+            });
+            const marker = '### Pyrefly Type Coverage';
+            const existing = comments.find(c => c.body.startsWith(marker));
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            }

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

@@ -0,0 +1,120 @@
+name: Pyrefly Type Coverage
+
+on:
+  pull_request:
+    paths:
+      - 'api/**/*.py'
+
+permissions:
+  contents: read
+
+jobs:
+  pyrefly-type-coverage:
+    runs-on: depot-ubuntu-24.04
+    permissions:
+      contents: read
+      issues: write
+      pull-requests: write
+    steps:
+      - name: Checkout PR branch
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python & UV
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Run pyrefly report on PR branch
+        run: |
+          uv run --directory api --dev pyrefly report 2>/dev/null > /tmp/pyrefly_report_pr.tmp && \
+            mv /tmp/pyrefly_report_pr.tmp /tmp/pyrefly_report_pr.json || \
+            echo '{}' > /tmp/pyrefly_report_pr.json
+
+      - name: Save helper script from base branch
+        run: |
+          git show ${{ github.event.pull_request.base.sha }}:api/libs/pyrefly_type_coverage.py > /tmp/pyrefly_type_coverage.py 2>/dev/null \
+            || cp api/libs/pyrefly_type_coverage.py /tmp/pyrefly_type_coverage.py
+
+      - name: Checkout base branch
+        run: git checkout ${{ github.base_ref }}
+
+      - name: Run pyrefly report on base branch
+        run: |
+          uv run --directory api --dev pyrefly report 2>/dev/null > /tmp/pyrefly_report_base.tmp && \
+            mv /tmp/pyrefly_report_base.tmp /tmp/pyrefly_report_base.json || \
+            echo '{}' > /tmp/pyrefly_report_base.json
+
+      - name: Generate coverage comparison
+        id: coverage
+        run: |
+          comment_body="$(uv run --directory api python /tmp/pyrefly_type_coverage.py \
+            --base /tmp/pyrefly_report_base.json \
+            < /tmp/pyrefly_report_pr.json)"
+
+          {
+            echo "### Pyrefly Type Coverage"
+            echo ""
+            echo "$comment_body"
+          } | tee -a "$GITHUB_STEP_SUMMARY" > /tmp/type_coverage_comment.md
+
+          # Save structured data for the fork-PR comment workflow
+          cp /tmp/pyrefly_report_pr.json pr_report.json
+          cp /tmp/pyrefly_report_base.json base_report.json
+
+      - name: Save PR number
+        run: |
+          echo ${{ github.event.pull_request.number }} > pr_number.txt
+
+      - name: Upload type coverage artifact
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: pyrefly_type_coverage
+          path: |
+            pr_report.json
+            base_report.json
+            pr_number.txt
+
+      - name: Comment PR with type coverage
+        if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const marker = '### Pyrefly Type Coverage';
+            let body;
+            try {
+              body = fs.readFileSync('/tmp/type_coverage_comment.md', { encoding: 'utf8' });
+            } catch {
+              body = `${marker}\n\n_Coverage report unavailable._`;
+            }
+            const prNumber = context.payload.pull_request.number;
+
+            // Update existing comment if one exists, otherwise create new
+            const { data: comments } = await github.rest.issues.listComments({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+            });
+            const existing = comments.find(c => c.body.startsWith(marker));
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body,
+              });
+            }

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

@@ -7,15 +7,22 @@ on:
       - edited
       - reopened
       - synchronize
+  merge_group:
+    branches: ["main"]
+    types: [checks_requested]
 
 jobs:
   lint:
     name: Validate PR title
     permissions:
       pull-requests: read
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     steps:
+      - name: Complete merge group check
+        if: github.event_name == 'merge_group'
+        run: echo "Semantic PR title validation is handled on pull requests."
       - name: Check title
+        if: github.event_name == 'pull_request'
         uses: amannn/action-semantic-pull-request@48f256284bd46cdaab1048c3721360e808335d50 # v6.1.1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/stale.yml

@@ -12,7 +12,7 @@ on:
 jobs:
   stale:
 
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     permissions:
       issues: write
       pull-requests: write
@@ -23,8 +23,8 @@ jobs:
           days-before-issue-stale: 15
           days-before-issue-close: 3
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          stale-issue-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
-          stale-pr-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
+          stale-issue-message: "Closed due to inactivity. If you have any questions, you can reopen it."
+          stale-pr-message: "Closed due to inactivity. If you have any questions, you can reopen it."
           stale-issue-label: 'no-issue-activity'
           stale-pr-label: 'no-pr-activity'
-          any-of-labels: 'duplicate,question,invalid,wontfix,no-issue-activity,no-pr-activity,enhancement,cant-reproduce,help-wanted'
+          any-of-labels: '🌚 invalid,🙋‍♂️ question,wont-fix,no-issue-activity,no-pr-activity,💪 enhancement,🤔 cant-reproduce,🙏 help wanted'

.github/workflows/style.yml

@@ -15,7 +15,7 @@ permissions:
 jobs:
   python-style:
     name: Python Style
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -25,7 +25,7 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             api/**
@@ -33,7 +33,7 @@ jobs:
 
       - name: Setup UV and Python
         if: steps.changed-files.outputs.any_changed == 'true'
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: false
           python-version: "3.12"
@@ -49,7 +49,7 @@ jobs:
 
       - name: Run Type Checks
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: make type-check
+        run: make type-check-core
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
@@ -57,7 +57,7 @@ jobs:
 
   web-style:
     name: Web Style
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     defaults:
       run:
         working-directory: ./web
@@ -73,10 +73,17 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             web/**
+            e2e/**
+            sdks/nodejs-client/**
+            packages/**
+            package.json
+            pnpm-lock.yaml
+            pnpm-workspace.yaml
+            .nvmrc
             .github/workflows/style.yml
             .github/actions/setup-web/**
 
@@ -87,26 +94,28 @@ jobs:
       - name: Restore ESLint cache
         if: steps.changed-files.outputs.any_changed == 'true'
         id: eslint-cache-restore
-        uses: actions/cache/restore@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          path: web/.eslintcache
-          key: ${{ runner.os }}-web-eslint-${{ hashFiles('web/package.json', 'web/pnpm-lock.yaml', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-${{ github.sha }}
+          path: .eslintcache
+          key: ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-${{ github.sha }}
           restore-keys: |
-            ${{ runner.os }}-web-eslint-${{ hashFiles('web/package.json', 'web/pnpm-lock.yaml', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-
+            ${{ runner.os }}-eslint-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'web/eslint.config.mjs', 'web/eslint.constants.mjs', 'web/plugins/eslint/**') }}-
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
+        working-directory: .
         run: vp run lint:ci
 
       - name: Web tsslint
         if: steps.changed-files.outputs.any_changed == 'true'
         working-directory: ./web
+        env:
+          NODE_OPTIONS: --max-old-space-size=4096
         run: vp run lint:tss
 
       - name: Web type check
         if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
+        working-directory: .
         run: vp run type-check
 
       - name: Web dead code check
@@ -116,14 +125,14 @@ jobs:
 
       - name: Save ESLint cache
         if: steps.changed-files.outputs.any_changed == 'true' && success() && steps.eslint-cache-restore.outputs.cache-hit != 'true'
-        uses: actions/cache/save@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
-          path: web/.eslintcache
+          path: .eslintcache
           key: ${{ steps.eslint-cache-restore.outputs.cache-primary-key }}
 
   superlinter:
     name: SuperLinter
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     steps:
       - name: Checkout code
@@ -134,7 +143,7 @@ jobs:
 
       - name: Check changed files
         id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
+        uses: tj-actions/changed-files@9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 # v47.0.6
         with:
           files: |
             **.sh
@@ -145,7 +154,7 @@ jobs:
             .editorconfig
 
       - name: Super-linter
-        uses: super-linter/super-linter/slim@61abc07d755095a68f4987d1c2c3d1d64408f1f9 # v8.5.0
+        uses: super-linter/super-linter/slim@9e863354e3ff62e0727d37183162c4a88873df41 # v8.6.0
         if: steps.changed-files.outputs.any_changed == 'true'
         env:
           BASH_SEVERITY: warning

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

@@ -6,6 +6,9 @@ on:
       - main
     paths:
       - sdks/**
+      - package.json
+      - pnpm-lock.yaml
+      - pnpm-workspace.yaml
 
 concurrency:
   group: sdk-tests-${{ github.head_ref || github.run_id }}
@@ -14,7 +17,7 @@ concurrency:
 jobs:
   build:
     name: unit test for Node.js SDK
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
 
     defaults:
       run:
@@ -26,7 +29,7 @@ jobs:
           persist-credentials: false
 
       - name: Use Node.js
-        uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
         with:
           node-version: 22
           cache: ''

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

@@ -1,26 +1,24 @@
 name: Translate i18n Files with Claude Code
 
 # Note: claude-code-action doesn't support push events directly.
-# Push events are handled by trigger-i18n-sync.yml which sends repository_dispatch.
-# See: https://github.com/langgenius/dify/issues/30743
-
+# Push events are bridged by trigger-i18n-sync.yml via repository_dispatch.
 on:
   repository_dispatch:
     types: [i18n-sync]
   workflow_dispatch:
     inputs:
       files:
-        description: 'Specific files to translate (space-separated, e.g., "app common"). Leave empty for all files.'
+        description: 'Specific files to translate (space-separated, e.g., "app common"). Required for full mode; leave empty in incremental mode to use en-US files changed since HEAD~1.'
         required: false
         type: string
       languages:
-        description: 'Specific languages to translate (space-separated, e.g., "zh-Hans ja-JP"). Leave empty for all supported languages.'
+        description: 'Specific languages to translate (space-separated, e.g., "zh-Hans ja-JP"). Leave empty for all supported target languages except en-US.'
         required: false
         type: string
       mode:
-        description: 'Sync mode: incremental (only changes) or full (re-check all keys)'
+        description: 'Sync mode: incremental (compare with previous en-US revision) or full (sync all keys in scope)'
         required: false
-        default: 'incremental'
+        default: incremental
         type: choice
         options:
           - incremental
@@ -30,11 +28,15 @@ permissions:
   contents: write
   pull-requests: write
 
+concurrency:
+  group: translate-i18n-${{ github.event_name }}-${{ github.ref }}
+  cancel-in-progress: false
+
 jobs:
   translate:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
-    timeout-minutes: 60
+    runs-on: depot-ubuntu-24.04
+    timeout-minutes: 120
 
     steps:
       - name: Checkout repository
@@ -51,380 +53,293 @@ jobs:
       - name: Setup web environment
         uses: ./.github/actions/setup-web
 
-      - name: Detect changed files and generate diff
-        id: detect_changes
+      - name: Prepare sync context
+        id: context
+        shell: bash
         run: |
-          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
-            # Manual trigger
-            if [ -n "${{ github.event.inputs.files }}" ]; then
-              echo "CHANGED_FILES=${{ github.event.inputs.files }}" >> $GITHUB_OUTPUT
-            else
-              # Get all JSON files in en-US directory
-              files=$(ls web/i18n/en-US/*.json 2>/dev/null | xargs -n1 basename | sed 's/.json$//' | tr '\n' ' ')
-              echo "CHANGED_FILES=$files" >> $GITHUB_OUTPUT
-            fi
-            echo "TARGET_LANGS=${{ github.event.inputs.languages }}" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.inputs.mode || 'incremental' }}" >> $GITHUB_OUTPUT
+          DEFAULT_TARGET_LANGS=$(awk "
+            /value: '/ {
+              value=\$2
+              gsub(/[',]/, \"\", value)
+            }
+            /supported: true/ && value != \"en-US\" {
+              printf \"%s \", value
+            }
+          " web/i18n-config/languages.ts | sed 's/[[:space:]]*$//')
 
-            # For manual trigger with incremental mode, get diff from last commit
-            # For full mode, we'll do a complete check anyway
-            if [ "${{ github.event.inputs.mode }}" == "full" ]; then
-              echo "Full mode: will check all keys" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-            else
-              git diff HEAD~1..HEAD -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-              if [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
-            fi
-          elif [ "${{ github.event_name }}" == "repository_dispatch" ]; then
-            # Triggered by push via trigger-i18n-sync.yml workflow
-            # Validate required payload fields
-            if [ -z "${{ github.event.client_payload.changed_files }}" ]; then
-              echo "Error: repository_dispatch payload missing required 'changed_files' field" >&2
-              exit 1
-            fi
-            echo "CHANGED_FILES=${{ github.event.client_payload.changed_files }}" >> $GITHUB_OUTPUT
-            echo "TARGET_LANGS=" >> $GITHUB_OUTPUT
-            echo "SYNC_MODE=${{ github.event.client_payload.sync_mode || 'incremental' }}" >> $GITHUB_OUTPUT
+          generate_changes_json() {
+            node .github/scripts/generate-i18n-changes.mjs
+          }
 
-            # Decode the base64-encoded diff from the trigger workflow
-            if [ -n "${{ github.event.client_payload.diff_base64 }}" ]; then
-              if ! echo "${{ github.event.client_payload.diff_base64 }}" | base64 -d > /tmp/i18n-diff.txt 2>&1; then
-                echo "Warning: Failed to decode base64 diff payload" >&2
-                echo "" > /tmp/i18n-diff.txt
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              elif [ -s /tmp/i18n-diff.txt ]; then
-                echo "DIFF_AVAILABLE=true" >> $GITHUB_OUTPUT
-              else
-                echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
-              fi
+          if [ "${{ github.event_name }}" = "repository_dispatch" ]; then
+            BASE_SHA="${{ github.event.client_payload.base_sha }}"
+            HEAD_SHA="${{ github.event.client_payload.head_sha }}"
+            CHANGED_FILES="${{ github.event.client_payload.changed_files }}"
+            TARGET_LANGS="$DEFAULT_TARGET_LANGS"
+            SYNC_MODE="${{ github.event.client_payload.sync_mode || 'incremental' }}"
+
+            if [ -n "${{ github.event.client_payload.changes_base64 }}" ]; then
+              printf '%s' '${{ github.event.client_payload.changes_base64 }}' | base64 -d > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="embedded"
+            elif [ -n "$BASE_SHA" ] && [ -n "$CHANGED_FILES" ]; then
+              export BASE_SHA HEAD_SHA CHANGED_FILES
+              generate_changes_json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="recomputed"
             else
-              echo "" > /tmp/i18n-diff.txt
-              echo "DIFF_AVAILABLE=false" >> $GITHUB_OUTPUT
+              printf '%s' '{"baseSha":"","headSha":"","files":[],"changes":{}}' > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="false"
+              CHANGES_SOURCE="unavailable"
             fi
           else
-            echo "Unsupported event type: ${{ github.event_name }}"
-            exit 1
+            BASE_SHA=""
+            HEAD_SHA=$(git rev-parse HEAD)
+            if [ -n "${{ github.event.inputs.languages }}" ]; then
+              TARGET_LANGS="${{ github.event.inputs.languages }}"
+            else
+              TARGET_LANGS="$DEFAULT_TARGET_LANGS"
+            fi
+            SYNC_MODE="${{ github.event.inputs.mode || 'incremental' }}"
+            if [ -n "${{ github.event.inputs.files }}" ]; then
+              CHANGED_FILES="${{ github.event.inputs.files }}"
+            elif [ "$SYNC_MODE" = "incremental" ]; then
+              BASE_SHA=$(git rev-parse HEAD~1 2>/dev/null || true)
+              if [ -n "$BASE_SHA" ]; then
+                CHANGED_FILES=$(git diff --name-only "$BASE_SHA" "$HEAD_SHA" -- 'web/i18n/en-US/*.json' 2>/dev/null | sed -n 's@^.*/@@p' | sed 's/\.json$//' | tr '\n' ' ' | sed 's/[[:space:]]*$//')
+              else
+                CHANGED_FILES=$(find web/i18n/en-US -maxdepth 1 -type f -name '*.json' -print | sed -n 's@^.*/@@p' | sed 's/\.json$//' | sort | tr '\n' ' ' | sed 's/[[:space:]]*$//')
+              fi
+            elif [ "$SYNC_MODE" = "full" ]; then
+              echo "workflow_dispatch full mode requires the files input to stay within CI limits." >&2
+              exit 1
+            else
+              CHANGED_FILES=""
+            fi
+
+            if [ "$SYNC_MODE" = "incremental" ] && [ -n "$CHANGED_FILES" ]; then
+              export BASE_SHA HEAD_SHA CHANGED_FILES
+              generate_changes_json
+              CHANGES_AVAILABLE="true"
+              CHANGES_SOURCE="local"
+            else
+              printf '%s' '{"baseSha":"","headSha":"","files":[],"changes":{}}' > /tmp/i18n-changes.json
+              CHANGES_AVAILABLE="false"
+              CHANGES_SOURCE="unavailable"
+            fi
           fi
 
-          # Truncate diff if too large (keep first 50KB)
-          if [ -f /tmp/i18n-diff.txt ]; then
-            head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-            mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
+          FILE_ARGS=""
+          if [ -n "$CHANGED_FILES" ]; then
+            FILE_ARGS="--file $CHANGED_FILES"
           fi
 
-          echo "Detected files: $(cat $GITHUB_OUTPUT | grep CHANGED_FILES || echo 'none')"
+          LANG_ARGS=""
+          if [ -n "$TARGET_LANGS" ]; then
+            LANG_ARGS="--lang $TARGET_LANGS"
+          fi
+
+          {
+            echo "DEFAULT_TARGET_LANGS=$DEFAULT_TARGET_LANGS"
+            echo "BASE_SHA=$BASE_SHA"
+            echo "HEAD_SHA=$HEAD_SHA"
+            echo "CHANGED_FILES=$CHANGED_FILES"
+            echo "TARGET_LANGS=$TARGET_LANGS"
+            echo "SYNC_MODE=$SYNC_MODE"
+            echo "CHANGES_AVAILABLE=$CHANGES_AVAILABLE"
+            echo "CHANGES_SOURCE=$CHANGES_SOURCE"
+            echo "FILE_ARGS=$FILE_ARGS"
+            echo "LANG_ARGS=$LANG_ARGS"
+          } >> "$GITHUB_OUTPUT"
+
+          echo "Files: ${CHANGED_FILES:-<none>}"
+          echo "Languages: ${TARGET_LANGS:-<none>}"
+          echo "Mode: $SYNC_MODE"
 
       - name: Run Claude Code for Translation Sync
-        if: steps.detect_changes.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@ff9acae5886d41a99ed4ec14b7dc147d55834722 # v1.0.77
+        if: steps.context.outputs.CHANGED_FILES != ''
+        uses: anthropics/claude-code-action@476e359e6203e73dad705c8b322e333fabbd7416 # v1.0.119
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}
-          # Allow github-actions bot to trigger this workflow via repository_dispatch
-          # See: https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           allowed_bots: 'github-actions[bot]'
+          show_full_output: ${{ github.event_name == 'workflow_dispatch' }}
           prompt: |
-            You are a professional i18n synchronization engineer for the Dify project.
-            Your task is to keep all language translations in sync with the English source (en-US).
+            You are the i18n sync agent for the Dify repository.
+            Your job is to keep translations synchronized with the English source files under `${{ github.workspace }}/web/i18n/en-US/`.
 
-            ## CRITICAL TOOL RESTRICTIONS
-            - Use **Read** tool to read files (NOT cat or bash)
-            - Use **Edit** tool to modify JSON files (NOT node, jq, or bash scripts)
-            - Use **Bash** ONLY for: git commands, gh commands, pnpm commands
-            - Run bash commands ONE BY ONE, never combine with && or ||
-            - NEVER use `$()` command substitution - it's not supported. Split into separate commands instead.
+            Use absolute paths at all times:
+            - Repo root: `${{ github.workspace }}`
+            - Web directory: `${{ github.workspace }}/web`
+            - Language config: `${{ github.workspace }}/web/i18n-config/languages.ts`
 
-            ## WORKING DIRECTORY & ABSOLUTE PATHS
-            Claude Code sandbox working directory may vary. Always use absolute paths:
-            - For pnpm: `pnpm --dir ${{ github.workspace }}/web <command>`
-            - For git: `git -C ${{ github.workspace }} <command>`
-            - For gh: `gh --repo ${{ github.repository }} <command>`
-            - For file paths: `${{ github.workspace }}/web/i18n/`
+            Inputs:
+            - Files in scope: `${{ steps.context.outputs.CHANGED_FILES }}`
+            - Target languages: `${{ steps.context.outputs.TARGET_LANGS }}`
+            - Sync mode: `${{ steps.context.outputs.SYNC_MODE }}`
+            - Base SHA: `${{ steps.context.outputs.BASE_SHA }}`
+            - Head SHA: `${{ steps.context.outputs.HEAD_SHA }}`
+            - Scoped file args: `${{ steps.context.outputs.FILE_ARGS }}`
+            - Scoped language args: `${{ steps.context.outputs.LANG_ARGS }}`
+            - Structured change set available: `${{ steps.context.outputs.CHANGES_AVAILABLE }}`
+            - Structured change set source: `${{ steps.context.outputs.CHANGES_SOURCE }}`
+            - Structured change set file: `/tmp/i18n-changes.json`
 
-            ## EFFICIENCY RULES
-            - **ONE Edit per language file** - batch all key additions into a single Edit
-            - Insert new keys at the beginning of JSON (after `{`), lint:fix will sort them
-            - Translate ALL keys for a language mentally first, then do ONE Edit
-
-            ## Context
-            - Changed/target files: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-            - Target languages (empty means all supported): ${{ steps.detect_changes.outputs.TARGET_LANGS }}
-            - Sync mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Translation files are located in: ${{ github.workspace }}/web/i18n/{locale}/{filename}.json
-            - Language configuration is in: ${{ github.workspace }}/web/i18n-config/languages.ts
-            - Git diff is available: ${{ steps.detect_changes.outputs.DIFF_AVAILABLE }}
-
-            ## CRITICAL DESIGN: Verify First, Then Sync
-
-            You MUST follow this three-phase approach:
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 1: VERIFY - Analyze and Generate Change Report       ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 1.1: Analyze Git Diff (for incremental mode)
-            Use the Read tool to read `/tmp/i18n-diff.txt` to see the git diff.
-
-            Parse the diff to categorize changes:
-            - Lines with `+` (not `+++`): Added or modified values
-            - Lines with `-` (not `---`): Removed or old values
-            - Identify specific keys for each category:
-              * ADD: Keys that appear only in `+` lines (new keys)
-              * UPDATE: Keys that appear in both `-` and `+` lines (value changed)
-              * DELETE: Keys that appear only in `-` lines (removed keys)
-
-            ### Step 1.2: Read Language Configuration
-            Use the Read tool to read `${{ github.workspace }}/web/i18n-config/languages.ts`.
-            Extract all languages with `supported: true`.
-
-            ### Step 1.3: Run i18n:check for Each Language
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web install --frozen-lockfile
-            ```
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            This will report:
-            - Missing keys (need to ADD)
-            - Extra keys (need to DELETE)
-
-            ### Step 1.4: Generate Change Report
-
-            Create a structured report identifying:
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    I18N SYNC CHANGE REPORT                   ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Files to process: [list]                                     ║
-            ║ Languages to sync: [list]                                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ ADD (New Keys):                                              ║
-            ║   - [filename].[key]: "English value"                        ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ UPDATE (Modified Keys - MUST re-translate):                  ║
-            ║   - [filename].[key]: "Old value" → "New value"              ║
-            ║   ...                                                        ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ DELETE (Extra Keys):                                         ║
-            ║   - [language]/[filename].[key]                              ║
-            ║   ...                                                        ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            **IMPORTANT**: For UPDATE detection, compare git diff to find keys where
-            the English value changed. These MUST be re-translated even if target
-            language already has a translation (it's now stale!).
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 2: SYNC - Execute Changes Based on Report            ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 2.1: Process ADD Operations (BATCH per language file)
-
-            **CRITICAL WORKFLOW for efficiency:**
-            1. First, translate ALL new keys for ALL languages mentally
-            2. Then, for EACH language file, do ONE Edit operation:
-               - Read the file once
-               - Insert ALL new keys at the beginning (right after the opening `{`)
-               - Don't worry about alphabetical order - lint:fix will sort them later
-
-            Example Edit (adding 3 keys to zh-Hans/app.json):
-            ```
-            old_string: '{\n  "accessControl"'
-            new_string: '{\n  "newKey1": "translation1",\n  "newKey2": "translation2",\n  "newKey3": "translation3",\n  "accessControl"'
-            ```
-
-            **IMPORTANT**:
-            - ONE Edit per language file (not one Edit per key!)
-            - Always use the Edit tool. NEVER use bash scripts, node, or jq.
-
-            ### Step 2.2: Process UPDATE Operations
-
-            **IMPORTANT: Special handling for zh-Hans and ja-JP**
-            If zh-Hans or ja-JP files were ALSO modified in the same push:
-            - Run: `git -C ${{ github.workspace }} diff HEAD~1 --name-only` and check for zh-Hans or ja-JP files
-            - If found, it means someone manually translated them. Apply these rules:
-
-            1. **Missing keys**: Still ADD them (completeness required)
-            2. **Existing translations**: Compare with the NEW English value:
-               - If translation is **completely wrong** or **unrelated** → Update it
-               - If translation is **roughly correct** (captures the meaning) → Keep it, respect manual work
-               - When in doubt, **keep the manual translation**
-
-            Example:
-            - English changed: "Save" → "Save Changes"
-            - Manual translation: "保存更改" → Keep it (correct meaning)
-            - Manual translation: "删除" → Update it (completely wrong)
-
-            For other languages:
-            Use Edit tool to replace the old value with the new translation.
-            You can batch multiple updates in one Edit if they are adjacent.
-
-            ### Step 2.3: Process DELETE Operations
-            For extra keys reported by i18n:check:
-            - Run: `pnpm --dir ${{ github.workspace }}/web run i18n:check --auto-remove`
-            - Or manually remove from target language JSON files
-
-            ## Translation Guidelines
-
-            - PRESERVE all placeholders exactly as-is:
-              - `{{variable}}` - Mustache interpolation
-              - `${variable}` - Template literal
-              - `<tag>content</tag>` - HTML tags
-              - `_one`, `_other` - Pluralization suffixes (these are KEY suffixes, not values)
-
-              **CRITICAL: Variable names and tag names MUST stay in English - NEVER translate them**
-
-              ✅ CORRECT examples:
-              - English: "{{count}} items" → Japanese: "{{count}} 個のアイテム"
-              - English: "{{name}} updated" → Korean: "{{name}} 업데이트됨"
-              - English: "<email>{{email}}</email>" → Chinese: "<email>{{email}}</email>"
-              - English: "<CustomLink>Marketplace</CustomLink>" → Japanese: "<CustomLink>マーケットプレイス</CustomLink>"
-
-              ❌ WRONG examples (NEVER do this - will break the application):
-              - "{{count}}" → "{{カウント}}" ❌ (variable name translated to Japanese)
-              - "{{name}}" → "{{이름}}" ❌ (variable name translated to Korean)
-              - "{{email}}" → "{{邮箱}}" ❌ (variable name translated to Chinese)
-              - "<email>" → "<メール>" ❌ (tag name translated)
-              - "<CustomLink>" → "<自定义链接>" ❌ (component name translated)
-
-            - Use appropriate language register (formal/informal) based on existing translations
-            - Match existing translation style in each language
-            - Technical terms: check existing conventions per language
-            - For CJK languages: no spaces between characters unless necessary
-            - For RTL languages (ar-TN, fa-IR): ensure proper text handling
-
-            ## Output Format Requirements
-            - Alphabetical key ordering (if original file uses it)
-            - 2-space indentation
-            - Trailing newline at end of file
-            - Valid JSON (use proper escaping for special characters)
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 3: RE-VERIFY - Confirm All Issues Resolved           ║
-            ═══════════════════════════════════════════════════════════════
-
-            ### Step 3.1: Run Lint Fix (IMPORTANT!)
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web lint:fix --quiet -- 'i18n/**/*.json'
-            ```
-            This ensures:
-            - JSON keys are sorted alphabetically (jsonc/sort-keys rule)
-            - Valid i18n keys (dify-i18n/valid-i18n-keys rule)
-            - No extra keys (dify-i18n/no-extra-keys rule)
-
-            ### Step 3.2: Run Final i18n Check
-            ```bash
-            pnpm --dir ${{ github.workspace }}/web run i18n:check
-            ```
-
-            ### Step 3.3: Fix Any Remaining Issues
-            If check reports issues:
-            - Go back to PHASE 2 for unresolved items
-            - Repeat until check passes
-
-            ### Step 3.4: Generate Final Summary
-            ```
-            ╔══════════════════════════════════════════════════════════════╗
-            ║                    SYNC COMPLETED SUMMARY                    ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ Language      │ Added │ Updated │ Deleted │ Status          ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ zh-Hans       │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ja-JP         │  5    │   2     │    1    │ ✓ Complete      ║
-            ║ ...           │ ...   │  ...    │   ...   │ ...             ║
-            ╠══════════════════════════════════════════════════════════════╣
-            ║ i18n:check    │ PASSED - All keys in sync                   ║
-            ╚══════════════════════════════════════════════════════════════╝
-            ```
-
-            ## Mode-Specific Behavior
-
-            **SYNC_MODE = "incremental"** (default):
-            - Focus on keys identified from git diff
-            - Also check i18n:check output for any missing/extra keys
-            - Efficient for small changes
-
-            **SYNC_MODE = "full"**:
-            - Compare ALL keys between en-US and each language
-            - Run i18n:check to identify all discrepancies
-            - Use for first-time sync or fixing historical issues
-
-            ## Important Notes
-
-            1. Always run i18n:check BEFORE and AFTER making changes
-            2. The check script is the source of truth for missing/extra keys
-            3. For UPDATE scenario: git diff is the source of truth for changed values
-            4. Create a single commit with all translation changes
-            5. If any translation fails, continue with others and report failures
-
-            ═══════════════════════════════════════════════════════════════
-            ║  PHASE 4: COMMIT AND CREATE PR                              ║
-            ═══════════════════════════════════════════════════════════════
-
-            After all translations are complete and verified:
-
-            ### Step 4.1: Check for changes
-            ```bash
-            git -C ${{ github.workspace }} status --porcelain
-            ```
-
-            If there are changes:
-
-            ### Step 4.2: Create a new branch and commit
-            Run these git commands ONE BY ONE (not combined with &&).
-            **IMPORTANT**: Do NOT use `$()` command substitution. Use two separate commands:
-
-            1. First, get the timestamp:
-            ```bash
-            date +%Y%m%d-%H%M%S
-            ```
-            (Note the output, e.g., "20260115-143052")
-
-            2. Then create branch using the timestamp value:
-            ```bash
-            git -C ${{ github.workspace }} checkout -b chore/i18n-sync-20260115-143052
-            ```
-            (Replace "20260115-143052" with the actual timestamp from step 1)
-
-            3. Stage changes:
-            ```bash
-            git -C ${{ github.workspace }} add web/i18n/
-            ```
-
-            4. Commit:
-            ```bash
-            git -C ${{ github.workspace }} commit -m "chore(i18n): sync translations with en-US - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}"
-            ```
-
-            5. Push:
-            ```bash
-            git -C ${{ github.workspace }} push origin HEAD
-            ```
-
-            ### Step 4.3: Create Pull Request
-            ```bash
-            gh pr create --repo ${{ github.repository }} --title "chore(i18n): sync translations with en-US" --body "## Summary
-
-            This PR was automatically generated to sync i18n translation files.
-
-            ### Changes
-            - Mode: ${{ steps.detect_changes.outputs.SYNC_MODE }}
-            - Files processed: ${{ steps.detect_changes.outputs.CHANGED_FILES }}
-
-            ### Verification
-            - [x] \`i18n:check\` passed
-            - [x] \`lint:fix\` applied
-
-            🤖 Generated with Claude Code GitHub Action" --base main
-            ```
+            Tool rules:
+            - Use Read for repository files.
+            - Use Edit for JSON updates.
+            - Use Bash only for `vp`.
+            - Do not use Bash for `git`, `gh`, or branch management.
 
+            Required execution plan:
+            1. Resolve target languages.
+               - Use the provided `Target languages` value as the source of truth.
+               - If it is unexpectedly empty, read `${{ github.workspace }}/web/i18n-config/languages.ts` and use every language with `supported: true` except `en-US`.
+            2. Stay strictly in scope.
+               - Only process the files listed in `Files in scope`.
+               - Only process the resolved target languages, never `en-US`.
+               - Do not touch unrelated i18n files.
+               - Do not modify `${{ github.workspace }}/web/i18n/en-US/`.
+            3. Resolve source changes.
+               - If `Structured change set available` is `true`, read `/tmp/i18n-changes.json` and use it as the source of truth for file-level and key-level changes.
+               - For each file entry:
+                 - `added` contains new English keys that need translations.
+                 - `updated` contains stale keys whose English source changed; re-translate using the `after` value.
+                 - `deleted` contains keys that should be removed from locale files.
+                 - `fileDeleted: true` means the English file no longer exists; remove the matching locale file if present.
+               - Read the current English JSON file for any file that still exists so wording, placeholders, and surrounding terminology stay accurate.
+               - If `Structured change set available` is `false`, treat this as a scoped full sync and use the current English files plus scoped checks as the source of truth.
+            4. Run a scoped pre-check before editing:
+               - `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }}`
+               - Use this command as the source of truth for missing and extra keys inside the current scope.
+            5. Apply translations.
+               - For every target language and scoped file:
+                 - If `fileDeleted` is `true`, remove the locale file if it exists and skip the rest of that file.
+                 - If the locale file does not exist yet, create it with `Write` and then continue with `Edit` as needed.
+                 - ADD missing keys.
+                 - UPDATE stale translations when the English value changed.
+                 - DELETE removed keys. Prefer `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }} --auto-remove` for extra keys so deletions stay in scope.
+               - Preserve placeholders exactly: `{{variable}}`, `${variable}`, HTML tags, component tags, and variable names.
+               - Match the existing terminology and register used by each locale.
+               - Prefer one Edit per file when stable, but prioritize correctness over batching.
+            6. Verify only the edited files.
+               - Run `vp run dify-web#lint:fix --quiet -- <relative edited i18n file paths under web/>`
+               - Run `vp run dify-web#i18n:check ${{ steps.context.outputs.FILE_ARGS }} ${{ steps.context.outputs.LANG_ARGS }}`
+               - If verification fails, fix the remaining problems before continuing.
+            7. Stop after the scoped locale files are updated and verification passes.
+               - Do not create branches, commits, or pull requests.
           claude_args: |
-            --max-turns 150
-            --allowedTools "Read,Write,Edit,Bash(git *),Bash(git:*),Bash(gh *),Bash(gh:*),Bash(pnpm *),Bash(pnpm:*),Bash(date *),Bash(date:*),Glob,Grep"
+            --max-turns 120
+            --allowedTools "Read,Write,Edit,Bash(vp *),Bash(vp:*),Glob,Grep"
+
+      - name: Prepare branch metadata
+        id: pr_meta
+        if: steps.context.outputs.CHANGED_FILES != ''
+        shell: bash
+        run: |
+          if [ -z "$(git -C "${{ github.workspace }}" status --porcelain -- web/i18n/)" ]; then
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          SCOPE_HASH=$(printf '%s|%s|%s' "${{ steps.context.outputs.CHANGED_FILES }}" "${{ steps.context.outputs.TARGET_LANGS }}" "${{ steps.context.outputs.SYNC_MODE }}" | sha256sum | cut -c1-8)
+          HEAD_SHORT=$(printf '%s' "${{ steps.context.outputs.HEAD_SHA }}" | cut -c1-12)
+          BRANCH_NAME="chore/i18n-sync-${HEAD_SHORT}-${SCOPE_HASH}"
+
+          {
+            echo "has_changes=true"
+            echo "branch_name=$BRANCH_NAME"
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Commit translation changes
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        shell: bash
+        run: |
+          git -C "${{ github.workspace }}" checkout -B "${{ steps.pr_meta.outputs.branch_name }}"
+          git -C "${{ github.workspace }}" add web/i18n/
+          git -C "${{ github.workspace }}" commit -m "chore(i18n): sync translations with en-US"
+
+      - name: Push translation branch
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        shell: bash
+        run: |
+          if git -C "${{ github.workspace }}" ls-remote --exit-code --heads origin "${{ steps.pr_meta.outputs.branch_name }}" >/dev/null 2>&1; then
+            git -C "${{ github.workspace }}" push --force-with-lease origin "${{ steps.pr_meta.outputs.branch_name }}"
+          else
+            git -C "${{ github.workspace }}" push --set-upstream origin "${{ steps.pr_meta.outputs.branch_name }}"
+          fi
+
+      - name: Create or update translation PR
+        if: steps.pr_meta.outputs.has_changes == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          BRANCH_NAME: ${{ steps.pr_meta.outputs.branch_name }}
+          FILES_IN_SCOPE: ${{ steps.context.outputs.CHANGED_FILES }}
+          TARGET_LANGS: ${{ steps.context.outputs.TARGET_LANGS }}
+          SYNC_MODE: ${{ steps.context.outputs.SYNC_MODE }}
+          CHANGES_SOURCE: ${{ steps.context.outputs.CHANGES_SOURCE }}
+          BASE_SHA: ${{ steps.context.outputs.BASE_SHA }}
+          HEAD_SHA: ${{ steps.context.outputs.HEAD_SHA }}
+          REPO_NAME: ${{ github.repository }}
+        shell: bash
+        run: |
+          PR_BODY_FILE=/tmp/i18n-pr-body.md
+          LANG_COUNT=$(printf '%s\n' "$TARGET_LANGS" | wc -w | tr -d ' ')
+          if [ "$LANG_COUNT" = "0" ]; then
+            LANG_COUNT="0"
+          fi
+          export LANG_COUNT
+
+          node <<'NODE' > "$PR_BODY_FILE"
+          const fs = require('node:fs')
+
+          const changesPath = '/tmp/i18n-changes.json'
+          const changes = fs.existsSync(changesPath)
+            ? JSON.parse(fs.readFileSync(changesPath, 'utf8'))
+            : { changes: {} }
+
+          const filesInScope = (process.env.FILES_IN_SCOPE || '').split(/\s+/).filter(Boolean)
+          const lines = [
+            '## Summary',
+            '',
+            `- **Files synced**: \`${process.env.FILES_IN_SCOPE || '<none>'}\``,
+            `- **Languages updated**: ${process.env.TARGET_LANGS || '<none>'} (${process.env.LANG_COUNT} languages)`,
+            `- **Sync mode**: ${process.env.SYNC_MODE}${process.env.BASE_SHA ? ` (base: \`${process.env.BASE_SHA.slice(0, 10)}\`, head: \`${process.env.HEAD_SHA.slice(0, 10)}\`)` : ` (head: \`${process.env.HEAD_SHA.slice(0, 10)}\`)`}`,
+            '',
+            '### Key changes',
+          ]
+
+          for (const fileName of filesInScope) {
+            const fileChange = changes.changes?.[fileName] || { added: {}, updated: {}, deleted: [], fileDeleted: false }
+            const addedKeys = Object.keys(fileChange.added || {})
+            const updatedKeys = Object.keys(fileChange.updated || {})
+            const deletedKeys = fileChange.deleted || []
+            lines.push(`- \`${fileName}\`: +${addedKeys.length} / ~${updatedKeys.length} / -${deletedKeys.length}${fileChange.fileDeleted ? ' (file deleted in en-US)' : ''}`)
+          }
+
+          lines.push(
+            '',
+            '## Verification',
+            '',
+            `- \`vp run dify-web#i18n:check --file ${process.env.FILES_IN_SCOPE} --lang ${process.env.TARGET_LANGS}\``,
+            `- \`vp run dify-web#lint:fix --quiet -- <edited i18n files under web/>\``,
+            '',
+            '## Notes',
+            '',
+            '- This PR was generated from structured en-US key changes produced by `trigger-i18n-sync.yml`.',
+            `- Structured change source: ${process.env.CHANGES_SOURCE || 'unknown'}.`,
+            '- Branch name is deterministic for the head SHA and scope, so reruns update the same PR instead of opening duplicates.',
+            '',
+            '🤖 Generated with [Claude Code](https://claude.com/claude-code)'
+          )
+
+          process.stdout.write(lines.join('\n'))
+          NODE
+
+          EXISTING_PR_NUMBER=$(gh pr list --repo "$REPO_NAME" --head "$BRANCH_NAME" --state open --json number --jq '.[0].number')
+
+          if [ -n "$EXISTING_PR_NUMBER" ] && [ "$EXISTING_PR_NUMBER" != "null" ]; then
+            gh pr edit "$EXISTING_PR_NUMBER" --repo "$REPO_NAME" --title "chore(i18n): sync translations with en-US" --body-file "$PR_BODY_FILE"
+          else
+            gh pr create --repo "$REPO_NAME" --head "$BRANCH_NAME" --base main --title "chore(i18n): sync translations with en-US" --body-file "$PR_BODY_FILE"
+          fi

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

@@ -1,9 +1,5 @@
 name: Trigger i18n Sync on Push
 
-# This workflow bridges the push event to repository_dispatch
-# because claude-code-action doesn't support push events directly.
-# See: https://github.com/langgenius/dify/issues/30743
-
 on:
   push:
     branches: [main]
@@ -13,10 +9,14 @@ on:
 permissions:
   contents: write
 
+concurrency:
+  group: trigger-i18n-sync-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   trigger:
     if: github.repository == 'langgenius/dify'
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04
     timeout-minutes: 5
 
     steps:
@@ -25,42 +25,66 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Detect changed files and generate diff
+      - name: Detect changed files and build structured change set
         id: detect
+        shell: bash
         run: |
-          BEFORE_SHA="${{ github.event.before }}"
-          # Handle edge case: force push may have null/zero SHA
-          if [ -z "$BEFORE_SHA" ] || [ "$BEFORE_SHA" = "0000000000000000000000000000000000000000" ]; then
-            BEFORE_SHA="HEAD~1"
+          BASE_SHA="${{ github.event.before }}"
+          if [ -z "$BASE_SHA" ] || [ "$BASE_SHA" = "0000000000000000000000000000000000000000" ]; then
+            BASE_SHA=$(git rev-parse HEAD~1 2>/dev/null || true)
           fi
+          HEAD_SHA="${{ github.sha }}"
 
-          # Detect changed i18n files
-          changed=$(git diff --name-only "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' 2>/dev/null | xargs -n1 basename 2>/dev/null | sed 's/.json$//' | tr '\n' ' ' || echo "")
-          echo "changed_files=$changed" >> $GITHUB_OUTPUT
-
-          # Generate diff for context
-          git diff "$BEFORE_SHA" "${{ github.sha }}" -- 'web/i18n/en-US/*.json' > /tmp/i18n-diff.txt 2>/dev/null || echo "" > /tmp/i18n-diff.txt
-
-          # Truncate if too large (keep first 50KB to match receiving workflow)
-          head -c 50000 /tmp/i18n-diff.txt > /tmp/i18n-diff-truncated.txt
-          mv /tmp/i18n-diff-truncated.txt /tmp/i18n-diff.txt
-
-          # Base64 encode the diff for safe JSON transport (portable, single-line)
-          diff_base64=$(base64 < /tmp/i18n-diff.txt | tr -d '\n')
-          echo "diff_base64=$diff_base64" >> $GITHUB_OUTPUT
-
-          if [ -n "$changed" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            echo "Detected changed files: $changed"
+          if [ -n "$BASE_SHA" ]; then
+            CHANGED_FILES=$(git diff --name-only "$BASE_SHA" "$HEAD_SHA" -- 'web/i18n/en-US/*.json' 2>/dev/null | sed -n 's@^.*/@@p' | sed 's/\.json$//' | tr '\n' ' ' | sed 's/[[:space:]]*$//')
           else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-            echo "No i18n changes detected"
+            CHANGED_FILES=$(find web/i18n/en-US -maxdepth 1 -type f -name '*.json' -print | sed -n 's@^.*/@@p' | sed 's/\.json$//' | sort | tr '\n' ' ' | sed 's/[[:space:]]*$//')
           fi
 
+          export BASE_SHA HEAD_SHA CHANGED_FILES
+          node .github/scripts/generate-i18n-changes.mjs
+
+          if [ -n "$CHANGED_FILES" ]; then
+            echo "has_changes=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+          fi
+
+          echo "base_sha=$BASE_SHA" >> "$GITHUB_OUTPUT"
+          echo "head_sha=$HEAD_SHA" >> "$GITHUB_OUTPUT"
+          echo "changed_files=$CHANGED_FILES" >> "$GITHUB_OUTPUT"
+
       - name: Trigger i18n sync workflow
         if: steps.detect.outputs.has_changes == 'true'
-        uses: peter-evans/repository-dispatch@28959ce8df70de7be546dd1250a005dd32156697 # v4.0.1
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
+        env:
+          BASE_SHA: ${{ steps.detect.outputs.base_sha }}
+          HEAD_SHA: ${{ steps.detect.outputs.head_sha }}
+          CHANGED_FILES: ${{ steps.detect.outputs.changed_files }}
         with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          event-type: i18n-sync
-          client-payload: '{"changed_files": "${{ steps.detect.outputs.changed_files }}", "diff_base64": "${{ steps.detect.outputs.diff_base64 }}", "sync_mode": "incremental", "trigger_sha": "${{ github.sha }}"}'
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs')
+
+            const changesJson = fs.readFileSync('/tmp/i18n-changes.json', 'utf8')
+            const changesBase64 = Buffer.from(changesJson).toString('base64')
+            const maxEmbeddedChangesChars = 48000
+            const changesEmbedded = changesBase64.length <= maxEmbeddedChangesChars
+
+            if (!changesEmbedded) {
+              console.log(`Structured change set too large to embed safely (${changesBase64.length} chars). Downstream workflow will regenerate it from git history.`)
+            }
+
+            await github.rest.repos.createDispatchEvent({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              event_type: 'i18n-sync',
+              client_payload: {
+                changed_files: process.env.CHANGED_FILES,
+                changes_base64: changesEmbedded ? changesBase64 : '',
+                changes_embedded: changesEmbedded,
+                sync_mode: 'incremental',
+                base_sha: process.env.BASE_SHA,
+                head_sha: process.env.HEAD_SHA,
+              },
+            })

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

@@ -0,0 +1,95 @@
+name: Run Full VDB Tests
+
+on:
+  schedule:
+    - cron: '0 3 * * 1'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: vdb-tests-full-${{ github.ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Full VDB Tests
+    if: github.repository == 'langgenius/dify'
+    runs-on: depot-ubuntu-24.04
+    strategy:
+      matrix:
+        python-version:
+          - "3.12"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Free Disk Space
+        uses: endersonmenezes/free-disk-space@7901478139cff6e9d44df5972fd8ab8fcade4db1 # v3.2.2
+        with:
+          remove_dotnet: true
+          remove_haskell: true
+          remove_tool_cache: true
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+          cache-dependency-glob: api/uv.lock
+
+      - name: Check UV lockfile
+        run: uv lock --project api --check
+
+      - name: Install dependencies
+        run: uv sync --project api --dev
+
+      - name: Set up dotenvs
+        run: |
+          cp docker/.env.example docker/.env
+          cp docker/envs/middleware.env.example docker/middleware.env
+
+      - name: Expose Service Ports
+        run: sh .github/workflows/expose_service_ports.sh
+
+#      - name: Set up Vector Store (TiDB)
+#        uses: hoverkraft-tech/compose-action@v2.0.2
+#        with:
+#          compose-file: docker/tidb/docker-compose.yaml
+#          services: |
+#            tidb
+#            tiflash
+
+      - name: Set up Full Vector Store Matrix
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
+        with:
+          compose-file: |
+            docker/docker-compose.yaml
+          services: |
+            weaviate
+            qdrant
+            couchbase-server
+            etcd
+            minio
+            milvus-standalone
+            pgvecto-rs
+            pgvector
+            chroma
+            elasticsearch
+            oceanbase
+
+      - name: setup test config
+        run: |
+          echo $(pwd)
+          ls -lah .
+          cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
+
+#      - name: Check VDB Ready (TiDB)
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
+
+      - name: Test Vector Stores
+        run: uv run --project api bash dev/pytest/pytest_vdb.sh

.github/workflows/vdb-tests.yml

@@ -1,20 +1,22 @@
-name: Run VDB Tests
+name: Run VDB Smoke Tests
 
 on:
   workflow_call:
 
+permissions:
+  contents: read
+
 concurrency:
   group: vdb-tests-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 
 jobs:
   test:
-    name: VDB Tests
-    runs-on: ubuntu-latest
+    name: VDB Smoke Tests
+    runs-on: depot-ubuntu-24.04
     strategy:
       matrix:
         python-version:
-          - "3.11"
           - "3.12"
 
     steps:
@@ -31,7 +33,7 @@ jobs:
           remove_tool_cache: true
 
       - name: Setup UV and Python
-        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           enable-cache: true
           python-version: ${{ matrix.python-version }}
@@ -46,7 +48,7 @@ jobs:
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
+          cp docker/envs/middleware.env.example docker/middleware.env
 
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
@@ -59,23 +61,18 @@ jobs:
 #            tidb
 #            tiflash
 
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
-        uses: hoverkraft-tech/compose-action@4894d2492015c1774ee5a13a95b1072093087ec3 # v2.5.0
+      - name: Set up Vector Stores for Smoke Coverage
+        uses: hoverkraft-tech/compose-action@d2bee4f07e8ca410d6b196d00f90c12e7d48c33a # v2.6.0
         with:
           compose-file: |
             docker/docker-compose.yaml
           services: |
+            db_postgres
+            redis
             weaviate
             qdrant
-            couchbase-server
-            etcd
-            minio
-            milvus-standalone
-            pgvecto-rs
             pgvector
             chroma
-            elasticsearch
-            oceanbase
 
       - name: setup test config
         run: |
@@ -84,7 +81,12 @@ jobs:
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
 #      - name: Check VDB Ready (TiDB)
-#        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+#        run: uv run --project api python api/providers/vdb/tidb-vector/tests/integration_tests/check_tiflash_ready.py
 
       - name: Test Vector Stores
-        run: uv run --project api bash dev/pytest/pytest_vdb.sh
+        run: |
+          uv run --project api pytest --timeout "${PYTEST_TIMEOUT:-180}" \
+            api/providers/vdb/vdb-chroma/tests/integration_tests \
+            api/providers/vdb/vdb-pgvector/tests/integration_tests \
+            api/providers/vdb/vdb-qdrant/tests/integration_tests \
+            api/providers/vdb/vdb-weaviate/tests/integration_tests

.github/workflows/web-e2e.yml

@@ -0,0 +1,68 @@
+name: Web Full-Stack E2E
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: web-e2e-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Web Full-Stack E2E
+    runs-on: depot-ubuntu-24.04-4
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Setup web dependencies
+        uses: ./.github/actions/setup-web
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
+        with:
+          enable-cache: true
+          python-version: "3.12"
+          cache-dependency-glob: api/uv.lock
+
+      - name: Install API dependencies
+        run: uv sync --project api --dev
+
+      - name: Install Playwright browser
+        working-directory: ./e2e
+        run: vp run e2e:install
+
+      - name: Run isolated source-api and built-web Cucumber E2E tests
+        working-directory: ./e2e
+        env:
+          E2E_ADMIN_EMAIL: e2e-admin@example.com
+          E2E_ADMIN_NAME: E2E Admin
+          E2E_ADMIN_PASSWORD: E2eAdmin12345
+          E2E_FORCE_WEB_BUILD: "1"
+          E2E_INIT_PASSWORD: E2eInit12345
+        run: vp run e2e:full
+
+      - name: Upload Cucumber report
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: cucumber-report
+          path: e2e/cucumber-report
+          retention-days: 7
+
+      - name: Upload E2E logs
+        if: ${{ !cancelled() }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: e2e-logs
+          path: e2e/.logs
+          retention-days: 7

.github/workflows/web-tests.yml

@@ -16,14 +16,14 @@ concurrency:
 jobs:
   test:
     name: Web Tests (${{ matrix.shardIndex }}/${{ matrix.shardTotal }})
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04-4
     env:
       VITEST_COVERAGE_SCOPE: app-components
     strategy:
       fail-fast: false
       matrix:
-        shardIndex: [1, 2, 3, 4, 5, 6]
-        shardTotal: [6]
+        shardIndex: [1, 2, 3, 4]
+        shardTotal: [4]
     defaults:
       run:
         shell: bash
@@ -43,7 +43,7 @@ jobs:
 
       - name: Upload blob report
         if: ${{ !cancelled() }}
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: blob-report-${{ matrix.shardIndex }}
           path: web/.vitest-reports/*
@@ -54,7 +54,7 @@ jobs:
     name: Merge Test Reports
     if: ${{ !cancelled() }}
     needs: [test]
-    runs-on: ubuntu-latest
+    runs-on: depot-ubuntu-24.04-4
     env:
       CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:
@@ -66,7 +66,6 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
-          fetch-depth: 0
           persist-credentials: false
 
       - name: Setup web environment
@@ -84,19 +83,22 @@ jobs:
 
       - name: Report coverage
         if: ${{ env.CODECOV_TOKEN != '' }}
-        uses: codecov/codecov-action@1af58845a975a7985b0beb0cbe6fbbb71a41dbad # v5.5.3
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
         with:
           directory: web/coverage
           flags: web
         env:
           CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}
 
-  web-build:
-    name: Web Build
-    runs-on: ubuntu-latest
+  dify-ui-test:
+    name: dify-ui Tests
+    runs-on: depot-ubuntu-24.04-4
+    env:
+      CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
     defaults:
       run:
-        working-directory: ./web
+        shell: bash
+        working-directory: ./packages/dify-ui
 
     steps:
       - name: Checkout code
@@ -104,20 +106,20 @@ jobs:
         with:
           persist-credentials: false
 
-      - name: Check changed files
-        id: changed-files
-        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
-        with:
-          files: |
-            web/**
-            .github/workflows/web-tests.yml
-            .github/actions/setup-web/**
-
       - name: Setup web environment
-        if: steps.changed-files.outputs.any_changed == 'true'
         uses: ./.github/actions/setup-web
 
-      - name: Web build check
-        if: steps.changed-files.outputs.any_changed == 'true'
-        working-directory: ./web
-        run: vp run build
+      - name: Install Chromium for Browser Mode
+        run: vp exec playwright install --with-deps chromium
+
+      - name: Run dify-ui tests
+        run: vp test run --coverage --silent=passed-only
+
+      - name: Report coverage
+        if: ${{ env.CODECOV_TOKEN != '' }}
+        uses: codecov/codecov-action@57e3a136b779b570ffcdbf80b3bdc90e7fab3de2 # v6.0.0
+        with:
+          directory: packages/dify-ui/coverage
+          flags: dify-ui
+        env:
+          CODECOV_TOKEN: ${{ env.CODECOV_TOKEN }}

AGENTS.md

@@ -38,6 +38,13 @@ The codebase is split into:
 - Inject dependencies through constructors and preserve clean architecture boundaries.
 - Handle errors with domain-specific exceptions at the correct layer.
 
+## Cherry-Picking to LTS Branches
+
+- Always use `git cherry-pick -x` when backporting commits from `main` to any `lts/*` branch.
+- The `-x` flag appends `(cherry picked from commit <sha>)` to the commit message. CI validates this provenance line; commits without it will fail.
+- When cherry-picking multiple commits, each must carry its own `(cherry picked from ...)` annotation.
+- Run `git cherry-pick --continue` with `HUSKY=0` to skip pre-existing lint errors that are unrelated to the fix.
+
 ## Project Conventions
 
 - Backend architecture adheres to DDD and Clean Architecture principles.

README.md

@@ -133,7 +133,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ### Custom configurations
 
-If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+If you need to customize the configuration, edit `docker/.env`. The essential startup defaults live in [`docker/.env.example`](docker/.env.example), and optional advanced variables are split under `docker/envs/` by theme. After making any changes, re-run `docker compose up -d` from the `docker` directory. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 #### Customizing Suggested Questions
 

api/.env.example

@@ -71,6 +71,13 @@ REDIS_USE_CLUSTERS=false
 REDIS_CLUSTERS=
 REDIS_CLUSTERS_PASSWORD=
 
+REDIS_RETRY_RETRIES=3
+REDIS_RETRY_BACKOFF_BASE=1.0
+REDIS_RETRY_BACKOFF_CAP=10.0
+REDIS_SOCKET_TIMEOUT=5.0
+REDIS_SOCKET_CONNECT_TIMEOUT=5.0
+REDIS_HEALTH_CHECK_INTERVAL=30
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:${REDIS_PORT}/1
 CELERY_BACKEND=redis
@@ -759,6 +766,7 @@ EVENT_BUS_REDIS_CHANNEL_TYPE=pubsub
 # Whether to use Redis cluster mode while use redis as event bus.
 #  It's highly recommended to enable this for large deployments.
 EVENT_BUS_REDIS_USE_CLUSTERS=false
+EVENT_BUS_LISTENER_JOIN_TIMEOUT_MS=2000
 
 # Whether to Enable human input timeout check task
 ENABLE_HUMAN_INPUT_TIMEOUT_TASK=true

api/commands/account.py

@@ -2,7 +2,6 @@ import base64
 import secrets
 
 import click
-from sqlalchemy.orm import sessionmaker
 
 from constants.languages import languages
 from extensions.ext_database import db
@@ -25,30 +24,31 @@ def reset_password(email, new_password, password_confirm):
         return
     normalized_email = email.strip().lower()
 
-    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
-        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+    account = AccountService.get_account_by_email_with_case_fallback(email.strip())
 
-        if not account:
-            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-            return
+    if not account:
+        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+        return
 
-        try:
-            valid_password(new_password)
-        except:
-            click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
-            return
+    try:
+        valid_password(new_password)
+    except:
+        click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
+        return
 
-        # generate password salt
-        salt = secrets.token_bytes(16)
-        base64_salt = base64.b64encode(salt).decode()
+    # generate password salt
+    salt = secrets.token_bytes(16)
+    base64_salt = base64.b64encode(salt).decode()
 
-        # encrypt password with salt
-        password_hashed = hash_password(new_password, salt)
-        base64_password_hashed = base64.b64encode(password_hashed).decode()
-        account.password = base64_password_hashed
-        account.password_salt = base64_salt
-        AccountService.reset_login_error_rate_limit(normalized_email)
-        click.echo(click.style("Password reset successfully.", fg="green"))
+    # encrypt password with salt
+    password_hashed = hash_password(new_password, salt)
+    base64_password_hashed = base64.b64encode(password_hashed).decode()
+    account = db.session.merge(account)
+    account.password = base64_password_hashed
+    account.password_salt = base64_salt
+    db.session.commit()
+    AccountService.reset_login_error_rate_limit(normalized_email)
+    click.echo(click.style("Password reset successfully.", fg="green"))
 
 
 @click.command("reset-email", help="Reset the account email.")
@@ -65,21 +65,22 @@ def reset_email(email, new_email, email_confirm):
         return
     normalized_new_email = new_email.strip().lower()
 
-    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
-        account = AccountService.get_account_by_email_with_case_fallback(email.strip(), session=session)
+    account = AccountService.get_account_by_email_with_case_fallback(email.strip())
 
-        if not account:
-            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-            return
+    if not account:
+        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+        return
 
-        try:
-            email_validate(normalized_new_email)
-        except:
-            click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
-            return
+    try:
+        email_validate(normalized_new_email)
+    except:
+        click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
+        return
 
-        account.email = normalized_new_email
-        click.echo(click.style("Email updated successfully.", fg="green"))
+    account = db.session.merge(account)
+    account.email = normalized_new_email
+    db.session.commit()
+    click.echo(click.style("Email updated successfully.", fg="green"))
 
 
 @click.command("create-tenant", help="Create account and tenant.")

api/configs/enterprise/__init__.py

@@ -23,6 +23,12 @@ class EnterpriseFeatureConfig(BaseSettings):
         ge=1, description="Maximum timeout in seconds for enterprise requests", default=5
     )
 
+    ENTERPRISE_DISABLE_RUNTIME_CREDENTIAL_CHECK: bool = Field(
+        default=False,
+        description="When disabled, credential policy check is disabled at workflow run time."
+        "You can disable to gain performance by trading off consistency",
+    )
+
 
 class EnterpriseTelemetryConfig(BaseSettings):
     """

api/configs/middleware/cache/redis_config.py

@@ -117,6 +117,37 @@ class RedisConfig(BaseSettings):
         default=None,
     )
 
+    REDIS_RETRY_RETRIES: NonNegativeInt = Field(
+        description="Maximum number of retries per Redis command on "
+        "transient failures (ConnectionError, TimeoutError, socket.timeout)",
+        default=3,
+    )
+
+    REDIS_RETRY_BACKOFF_BASE: PositiveFloat = Field(
+        description="Base delay in seconds for exponential backoff between retries",
+        default=1.0,
+    )
+
+    REDIS_RETRY_BACKOFF_CAP: PositiveFloat = Field(
+        description="Maximum backoff delay in seconds between retries",
+        default=10.0,
+    )
+
+    REDIS_SOCKET_TIMEOUT: PositiveFloat | None = Field(
+        description="Socket timeout in seconds for Redis read/write operations",
+        default=5.0,
+    )
+
+    REDIS_SOCKET_CONNECT_TIMEOUT: PositiveFloat | None = Field(
+        description="Socket timeout in seconds for Redis connection establishment",
+        default=5.0,
+    )
+
+    REDIS_HEALTH_CHECK_INTERVAL: NonNegativeInt = Field(
+        description="Interval in seconds between Redis connection health checks (0 to disable)",
+        default=30,
+    )
+
     @field_validator("REDIS_MAX_CONNECTIONS", mode="before")
     @classmethod
     def _empty_string_to_none_for_max_conns(cls, v):

api/configs/middleware/cache/redis_pubsub_config.py

@@ -2,6 +2,7 @@ from typing import Literal, Protocol, cast
 from urllib.parse import quote_plus, urlunparse
 
 from pydantic import AliasChoices, Field
+from pydantic.types import NonNegativeInt
 from pydantic_settings import BaseSettings
 
 
@@ -70,6 +71,24 @@ class RedisPubSubConfig(BaseSettings):
         default=600,
     )
 
+    PUBSUB_LISTENER_JOIN_TIMEOUT_MS: NonNegativeInt = Field(
+        validation_alias=AliasChoices("EVENT_BUS_LISTENER_JOIN_TIMEOUT_MS", "PUBSUB_LISTENER_JOIN_TIMEOUT_MS"),
+        description=(
+            "Maximum time (milliseconds) that ``Subscription.close()`` waits for its listener thread to "
+            "finish before returning. Bounds the tail latency between a terminal event being delivered to "
+            "an SSE client and the response stream actually closing.\n\n"
+            "The listener thread blocks on a polling read (XREAD BLOCK for streams, get_message timeout "
+            "for pubsub/sharded) with a fixed 1s window, so close() naturally has to wait up to ~1s for "
+            "the thread to notice the subscription was closed. Setting this lower (e.g. 100) lets close() "
+            "return promptly while the daemon listener thread cleans itself up on the next poll "
+            "boundary - safe because the listener holds no critical state and exits within one poll "
+            "window. Setting it higher (e.g. 5000) gives the listener more grace before close() gives up "
+            "and logs a warning. Default 2000ms preserves the pre-change behaviour.\n\n"
+            "Also accepts ENV: EVENT_BUS_LISTENER_JOIN_TIMEOUT_MS."
+        ),
+        default=2000,
+    )
+
     def _build_default_pubsub_url(self) -> str:
         defaults = _redis_defaults(self)
         if not defaults.REDIS_HOST or not defaults.REDIS_PORT:

api/controllers/console/app/app.py

@@ -800,9 +800,10 @@ class AppTraceApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id):
+    @get_app_model
+    def get(self, app_model):
         """Get app trace"""
-        app_trace_config = OpsTraceManager.get_app_tracing_config(app_id=app_id)
+        app_trace_config = OpsTraceManager.get_app_tracing_config(app_id=app_model.id)
 
         return app_trace_config
 
@@ -816,12 +817,13 @@ class AppTraceApi(Resource):
     @login_required
     @account_initialization_required
     @edit_permission_required
-    def post(self, app_id):
+    @get_app_model
+    def post(self, app_model):
         # add app trace
         args = AppTracePayload.model_validate(console_ns.payload)
 
         OpsTraceManager.update_app_tracing_config(
-            app_id=app_id,
+            app_id=app_model.id,
             enabled=args.enabled,
             tracing_provider=args.tracing_provider,
         )

api/controllers/console/app/ops_trace.py

@@ -7,8 +7,10 @@ from werkzeug.exceptions import BadRequest
 
 from controllers.console import console_ns
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
+from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
+from models import App
 from services.ops_service import OpsService
 
 DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
@@ -49,11 +51,14 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id):
+    @get_app_model
+    def get(self, app_model: App):
         args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            trace_config = OpsService.get_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
+            trace_config = OpsService.get_tracing_app_config(
+                app_id=app_model.id, tracing_provider=args.tracing_provider
+            )
             if not trace_config:
                 return {"has_not_configured": True}
             return trace_config
@@ -71,13 +76,14 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def post(self, app_id):
+    @get_app_model
+    def post(self, app_model: App):
         """Create a new trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.create_tracing_app_config(
-                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=app_model.id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigIsExist()
@@ -96,13 +102,14 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def patch(self, app_id):
+    @get_app_model
+    def patch(self, app_model: App):
         """Update an existing trace app configuration"""
         args = TraceConfigPayload.model_validate(console_ns.payload)
 
         try:
             result = OpsService.update_tracing_app_config(
-                app_id=app_id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
+                app_id=app_model.id, tracing_provider=args.tracing_provider, tracing_config=args.tracing_config
             )
             if not result:
                 raise TracingConfigNotExist()
@@ -119,12 +126,13 @@ class TraceAppConfigApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def delete(self, app_id):
+    @get_app_model
+    def delete(self, app_model: App):
         """Delete an existing trace app configuration"""
         args = TraceProviderQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            result = OpsService.delete_tracing_app_config(app_id=app_id, tracing_provider=args.tracing_provider)
+            result = OpsService.delete_tracing_app_config(app_id=app_model.id, tracing_provider=args.tracing_provider)
             if not result:
                 raise TracingConfigNotExist()
             return {"result": "success"}, 204

api/controllers/console/auth/email_register.py

@@ -1,7 +1,6 @@
 from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
-from sqlalchemy.orm import sessionmaker
 
 from configs import dify_config
 from constants.languages import languages
@@ -14,7 +13,6 @@ from controllers.console.auth.error import (
     InvalidTokenError,
     PasswordMismatchError,
 )
-from extensions.ext_database import db
 from libs.helper import EmailStr, extract_remote_ip
 from libs.password import valid_password
 from models import Account
@@ -73,8 +71,7 @@ class EmailRegisterSendEmailApi(Resource):
         if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(normalized_email):
             raise AccountInFreezeError()
 
-        with sessionmaker(db.engine).begin() as session:
-            account = AccountService.get_account_by_email_with_case_fallback(args.email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(args.email)
         token = AccountService.send_email_register_email(email=normalized_email, account=account, language=language)
         return {"result": "success", "data": token}
 
@@ -145,17 +142,16 @@ class EmailRegisterResetApi(Resource):
         email = register_data.get("email", "")
         normalized_email = email.lower()
 
-        with sessionmaker(db.engine).begin() as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(email)
 
-            if account:
-                raise EmailAlreadyInUseError()
-            else:
-                account = self._create_new_account(normalized_email, args.password_confirm)
-                if not account:
-                    raise AccountNotFoundError()
-                token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
-                AccountService.reset_login_error_rate_limit(normalized_email)
+        if account:
+            raise EmailAlreadyInUseError()
+        else:
+            account = self._create_new_account(normalized_email, args.password_confirm)
+            if not account:
+                raise AccountNotFoundError()
+            token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
+            AccountService.reset_login_error_rate_limit(normalized_email)
 
         return {"result": "success", "data": token_pair.model_dump()}
 

api/controllers/console/auth/forgot_password.py

@@ -4,7 +4,6 @@ import secrets
 from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
-from sqlalchemy.orm import sessionmaker
 
 from controllers.common.schema import register_schema_models
 from controllers.console import console_ns
@@ -102,8 +101,7 @@ class ForgotPasswordSendEmailApi(Resource):
         else:
             language = "en-US"
 
-        with sessionmaker(db.engine).begin() as session:
-            account = AccountService.get_account_by_email_with_case_fallback(args.email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(args.email)
 
         token = AccountService.send_reset_password_email(
             account=account,
@@ -201,17 +199,18 @@ class ForgotPasswordResetApi(Resource):
         password_hashed = hash_password(args.new_password, salt)
 
         email = reset_data.get("email", "")
-        with sessionmaker(db.engine).begin() as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(email)
 
-            if account:
-                self._update_existing_account(account, password_hashed, salt, session)
-            else:
-                raise AccountNotFound()
+        if account:
+            account = db.session.merge(account)
+            self._update_existing_account(account, password_hashed, salt)
+            db.session.commit()
+        else:
+            raise AccountNotFound()
 
         return {"result": "success"}
 
-    def _update_existing_account(self, account, password_hashed, salt, session):
+    def _update_existing_account(self, account, password_hashed, salt):
         # Update existing account credentials
         account.password = base64.b64encode(password_hashed).decode()
         account.password_salt = base64.b64encode(salt).decode()

api/controllers/console/auth/oauth.py

@@ -4,7 +4,6 @@ import urllib.parse
 import httpx
 from flask import current_app, redirect, request
 from flask_restx import Resource
-from sqlalchemy.orm import sessionmaker
 from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
@@ -180,8 +179,7 @@ def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) ->
     account: Account | None = Account.get_by_openid(provider, user_info.id)
 
     if not account:
-        with sessionmaker(db.engine).begin() as session:
-            account = AccountService.get_account_by_email_with_case_fallback(user_info.email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(user_info.email)
 
     return account
 

api/controllers/console/files.py

@@ -105,7 +105,8 @@ class FilePreviewApi(Resource):
     @account_initialization_required
     def get(self, file_id):
         file_id = str(file_id)
-        text = FileService(db.engine).get_file_preview(file_id)
+        _, tenant_id = current_account_with_tenant()
+        text = FileService(db.engine).get_file_preview(file_id, tenant_id)
         return {"content": text}
 
 

api/controllers/console/workspace/account.py

@@ -8,7 +8,6 @@ from flask import request
 from flask_restx import Resource, fields, marshal_with
 from pydantic import BaseModel, Field, field_validator, model_validator
 from sqlalchemy import select
-from sqlalchemy.orm import Session
 
 from configs import dify_config
 from constants.languages import supported_language
@@ -562,8 +561,7 @@ class ChangeEmailSendEmailApi(Resource):
 
             user_email = current_user.email
         else:
-            with Session(db.engine) as session:
-                account = AccountService.get_account_by_email_with_case_fallback(args.email, session=session)
+            account = AccountService.get_account_by_email_with_case_fallback(args.email)
             if account is None:
                 raise AccountNotFound()
             email_for_sending = account.email

api/controllers/console/workspace/tool_providers.py

@@ -875,10 +875,10 @@ class ToolBuiltinProviderSetDefaultApi(Resource):
     @login_required
     @account_initialization_required
     def post(self, provider):
-        current_user, current_tenant_id = current_account_with_tenant()
+        _, current_tenant_id = current_account_with_tenant()
         payload = BuiltinProviderDefaultCredentialPayload.model_validate(console_ns.payload or {})
         return BuiltinToolManageService.set_default_provider(
-            tenant_id=current_tenant_id, user_id=current_user.id, provider=provider, id=payload.id
+            tenant_id=current_tenant_id, provider=provider, id=payload.id
         )
 
 

api/controllers/web/forgot_password.py

@@ -4,7 +4,6 @@ import secrets
 from flask import request
 from flask_restx import Resource
 from pydantic import BaseModel, Field, field_validator
-from sqlalchemy.orm import Session
 
 from controllers.common.schema import register_schema_models
 from controllers.console.auth.error import (
@@ -81,9 +80,7 @@ class ForgotPasswordSendEmailApi(Resource):
         else:
             language = "en-US"
 
-        with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(request_email, session=session)
-        token = None
+        account = AccountService.get_account_by_email_with_case_fallback(request_email)
         if account is None:
             raise AuthenticationFailedError()
         else:
@@ -180,18 +177,18 @@ class ForgotPasswordResetApi(Resource):
 
         email = reset_data.get("email", "")
 
-        with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(email)
 
-            if account:
-                self._update_existing_account(account, password_hashed, salt, session)
-            else:
-                raise AuthenticationFailedError()
+        if account:
+            account = db.session.merge(account)
+            self._update_existing_account(account, password_hashed, salt)
+            db.session.commit()
+        else:
+            raise AuthenticationFailedError()
 
         return {"result": "success"}
 
-    def _update_existing_account(self, account: Account, password_hashed, salt, session):
+    def _update_existing_account(self, account: Account, password_hashed, salt):
         # Update existing account credentials
         account.password = base64.b64encode(password_hashed).decode()
         account.password_salt = base64.b64encode(salt).decode()
-        session.commit()

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

@@ -50,6 +50,7 @@ from models import Account, App, Conversation, EndUser, Message, Workflow, Workf
 from models.base import Base
 from models.enums import WorkflowRunTriggeredFrom
 from services.conversation_service import ConversationService
+from services.errors.conversation import ConversationNotExistsError
 from services.workflow_draft_variable_service import (
     DraftVarLoader,
     WorkflowDraftVariableService,
@@ -140,9 +141,15 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         conversation = None
         conversation_id = args.get("conversation_id")
         if conversation_id:
-            conversation = ConversationService.get_conversation(
-                app_model=app_model, conversation_id=conversation_id, user=user
-            )
+            try:
+                conversation = ConversationService.get_conversation(
+                    app_model=app_model, conversation_id=conversation_id, user=user
+                )
+            except ConversationNotExistsError:
+                if invoke_from == InvokeFrom.SERVICE_API:
+                    conversation = None
+                else:
+                    raise
 
         # parse files
         # TODO(QuantumGhost): Move file parsing logic to the API controller layer

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

@@ -1,13 +1,12 @@
 import json
 import logging
-import re
 import time
 from collections.abc import Callable, Generator, Mapping
 from contextlib import contextmanager
 from threading import Thread
 from typing import Any, Union
 
-from sqlalchemy import select
+from sqlalchemy import select, update
 from sqlalchemy.orm import Session
 
 from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
@@ -311,11 +310,9 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         self._workflow_run_id = run_id
 
         with self._database_session() as session:
-            message = self._get_message(session=session)
-            if not message:
-                raise ValueError(f"Message not found: {self._message_id}")
-
-            message.workflow_run_id = run_id
+            session.execute(
+                update(Message).where(Message.id == self._message_id).values(workflow_run_id=run_id)
+            )
 
         workflow_start_resp = self._workflow_response_converter.workflow_start_to_stream_response(
             task_id=self._application_generate_entity.task_id,
@@ -897,11 +894,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         if message.status == MessageStatus.PAUSED:
             message.status = MessageStatus.NORMAL
 
-        # If there are assistant files, remove markdown image links from answer
         answer_text = self._task_state.answer
-        if self._recorded_files:
-            # Remove markdown image links since we're storing files separately
-            answer_text = re.sub(r"!\[.*?\]\(.*?\)", "", answer_text).strip()
 
         message.answer = answer_text
         message.updated_at = naive_utc_now()

api/core/app/llm/model_access.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from copy import deepcopy
 from typing import Any
 
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
@@ -15,12 +16,17 @@ from dify_graph.nodes.llm.protocols import CredentialsProvider, ModelFactory
 class DifyCredentialsProvider:
     tenant_id: str
     provider_manager: ProviderManager
+    credentials_cache: dict[tuple[str, str], dict[str, Any]]
 
     def __init__(self, tenant_id: str, provider_manager: ProviderManager | None = None) -> None:
         self.tenant_id = tenant_id
         self.provider_manager = provider_manager or ProviderManager()
+        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:
@@ -35,6 +41,7 @@ class DifyCredentialsProvider:
         if credentials is None:
             raise ProviderTokenNotInitError(f"Model {model_name} credentials is not initialized.")
 
+        self.credentials_cache[(provider_name, model_name)] = deepcopy(credentials)
         return credentials
 
 
@@ -44,7 +51,7 @@ class DifyModelFactory:
 
     def __init__(self, tenant_id: str, model_manager: ModelManager | None = None) -> None:
         self.tenant_id = tenant_id
-        self.model_manager = model_manager or ModelManager()
+        self.model_manager = model_manager or ModelManager(enable_credentials_cache=True)
 
     def init_model_instance(self, provider_name: str, model_name: str) -> ModelInstance:
         return self.model_manager.get_model_instance(
@@ -56,9 +63,13 @@ class DifyModelFactory:
 
 
 def build_dify_model_access(tenant_id: str) -> tuple[CredentialsProvider, ModelFactory]:
+    provider_manager = ProviderManager()
     return (
-        DifyCredentialsProvider(tenant_id=tenant_id),
-        DifyModelFactory(tenant_id=tenant_id),
+        DifyCredentialsProvider(tenant_id=tenant_id, provider_manager=provider_manager),
+        DifyModelFactory(
+            tenant_id=tenant_id,
+            model_manager=ModelManager(enable_credentials_cache=True, provider_manager=provider_manager),
+        ),
     )
 
 

api/core/entities/provider_configuration.py

@@ -9,6 +9,7 @@ from pydantic import BaseModel, ConfigDict, Field, model_validator
 from sqlalchemy import func, select
 from sqlalchemy.orm import Session
 
+from configs import dify_config
 from constants import HIDDEN_VALUE
 from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
 from core.entities.provider_entities import (
@@ -144,9 +145,9 @@ class ProviderConfiguration(BaseModel):
                 current_credential_id = self.custom_configuration.provider.current_credential_id
 
             if current_credential_id:
-                from core.helper.credential_utils import check_credential_policy_compliance
+                from core.helper.credential_utils import runtime_check_credential_policy_compliance
 
-                check_credential_policy_compliance(
+                runtime_check_credential_policy_compliance(
                     credential_id=current_credential_id,
                     provider=self.provider.provider,
                     credential_type=PluginCredentialType.MODEL,
@@ -155,9 +156,9 @@ class ProviderConfiguration(BaseModel):
                 # no current credential id, check all available credentials
                 if self.custom_configuration.provider:
                     for credential_configuration in self.custom_configuration.provider.available_credentials:
-                        from core.helper.credential_utils import check_credential_policy_compliance
+                        from core.helper.credential_utils import runtime_check_credential_policy_compliance
 
-                        check_credential_policy_compliance(
+                        runtime_check_credential_policy_compliance(
                             credential_id=credential_configuration.credential_id,
                             provider=self.provider.provider,
                             credential_type=PluginCredentialType.MODEL,

api/core/helper/credential_utils.py

@@ -2,6 +2,7 @@
 Credential utility functions for checking credential existence and policy compliance.
 """
 
+from configs import dify_config
 from services.enterprise.plugin_manager_service import PluginCredentialType
 
 
@@ -39,6 +40,14 @@ def is_credential_exists(credential_id: str, credential_type: "PluginCredentialT
         return False
 
 
+def runtime_check_credential_policy_compliance(
+    *args, **kwargs
+) -> None:
+    if dify_config.ENTERPRISE_DISABLE_RUNTIME_CREDENTIAL_CHECK:
+        return
+    check_credential_policy_compliance(*args, **kwargs)
+
+
 def check_credential_policy_compliance(
     credential_id: str, provider: str, credential_type: "PluginCredentialType", check_existence: bool = True
 ) -> None:

api/core/helper/ssrf_proxy.py

@@ -42,13 +42,16 @@ request_error = httpx.RequestError
 max_retries_exceeded_error = MaxRetriesExceededError
 
 
-def _create_proxy_mounts() -> dict[str, httpx.HTTPTransport]:
+def _create_proxy_mounts(verify: bool) -> dict[str, httpx.HTTPTransport]:
+    """Build per-scheme proxy transports with the same TLS policy as the SSRF client."""
     return {
         "http://": httpx.HTTPTransport(
             proxy=dify_config.SSRF_PROXY_HTTP_URL,
+            verify=verify,
         ),
         "https://": httpx.HTTPTransport(
             proxy=dify_config.SSRF_PROXY_HTTPS_URL,
+            verify=verify,
         ),
     }
 
@@ -63,7 +66,7 @@ def _build_ssrf_client(verify: bool) -> httpx.Client:
 
     if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
         return httpx.Client(
-            mounts=_create_proxy_mounts(),
+            mounts=_create_proxy_mounts(verify=verify),
             verify=verify,
             limits=_SSRF_CLIENT_LIMITS,
         )

api/core/model_manager.py

@@ -1,5 +1,6 @@
 import logging
 from collections.abc import Callable, Generator, Iterable, Mapping, Sequence
+from copy import deepcopy
 from typing import IO, Any, Literal, Optional, Union, cast, overload
 
 from configs import dify_config
@@ -33,11 +34,13 @@ class ModelInstance:
     Model instance class
     """
 
-    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str):
+    def __init__(self, provider_model_bundle: ProviderModelBundle, model: str, credentials: dict | None = None):
         self.provider_model_bundle = provider_model_bundle
         self.model_name = model
         self.provider = provider_model_bundle.configuration.provider.provider
-        self.credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
+        if credentials is None:
+            credentials = self._fetch_credentials_from_bundle(provider_model_bundle, model)
+        self.credentials = credentials
         # Runtime LLM invocation fields.
         self.parameters: Mapping[str, Any] = {}
         self.stop: Sequence[str] = ()
@@ -430,10 +433,10 @@ class ModelInstance:
 
             # Additional policy compliance check as fallback (in case fetch_next didn't catch it)
             try:
-                from core.helper.credential_utils import check_credential_policy_compliance
+                from core.helper.credential_utils import runtime_check_credential_policy_compliance
 
                 if lb_config.credential_id:
-                    check_credential_policy_compliance(
+                    runtime_check_credential_policy_compliance(
                         credential_id=lb_config.credential_id,
                         provider=self.provider,
                         credential_type=PluginCredentialType.MODEL,
@@ -477,8 +480,10 @@ class ModelInstance:
 
 
 class ModelManager:
-    def __init__(self):
-        self._provider_manager = ProviderManager()
+    def __init__(self, enable_credentials_cache: bool = False, provider_manager: ProviderManager | None = None):
+        self._provider_manager = provider_manager or ProviderManager()
+        self._credentials_cache: dict[tuple[str, str, str, str], Any] = {}
+        self._enable_credentials_cache = enable_credentials_cache
 
     def get_model_instance(self, tenant_id: str, provider: str, model_type: ModelType, model: str) -> ModelInstance:
         """
@@ -496,7 +501,19 @@ class ModelManager:
             tenant_id=tenant_id, provider=provider, model_type=model_type
         )
 
-        return ModelInstance(provider_model_bundle, model)
+        cred_cache_key = (tenant_id, provider, model_type.value, model)
+
+        if cred_cache_key in self._credentials_cache:
+            return ModelInstance(
+                provider_model_bundle, 
+                model, 
+                deepcopy(self._credentials_cache[cred_cache_key]),
+            )
+
+        ret = ModelInstance(provider_model_bundle, model)
+        if self._enable_credentials_cache:
+            self._credentials_cache[cred_cache_key] = deepcopy(ret.credentials)
+        return ret
 
     def get_default_provider_model_name(self, tenant_id: str, model_type: ModelType) -> tuple[str | None, str | None]:
         """
@@ -626,10 +643,10 @@ class LBModelManager:
 
             # Check policy compliance for the selected configuration
             try:
-                from core.helper.credential_utils import check_credential_policy_compliance
+                from core.helper.credential_utils import runtime_check_credential_policy_compliance
 
                 if config.credential_id:
-                    check_credential_policy_compliance(
+                    runtime_check_credential_policy_compliance(
                         credential_id=config.credential_id,
                         provider=self._provider,
                         credential_type=PluginCredentialType.MODEL,

api/core/plugin/impl/base.py

@@ -3,6 +3,7 @@ import json
 import logging
 from collections.abc import Callable, Generator
 from typing import Any, TypeVar, cast
+from urllib.parse import unquote
 
 import httpx
 from pydantic import BaseModel
@@ -51,6 +52,9 @@ else:
 
 T = TypeVar("T", bound=(BaseModel | dict[str, Any] | list[Any] | bool | str))
 
+PLUGIN_DAEMON_MAX_PATH_LENGTH = 4096
+PLUGIN_DAEMON_MAX_PATH_DECODE_DEPTH = 8
+
 logger = logging.getLogger(__name__)
 
 
@@ -98,6 +102,20 @@ class BasePluginClient:
         params: dict[str, Any] | None,
         files: dict[str, Any] | None,
     ) -> tuple[str, dict[str, str], bytes | dict[str, Any] | str | None, dict[str, Any] | None, dict[str, Any] | None]:
+        if len(path) > PLUGIN_DAEMON_MAX_PATH_LENGTH:
+            raise ValueError(f"Invalid plugin daemon path: path length exceeds {PLUGIN_DAEMON_MAX_PATH_LENGTH}")
+
+        decoded_path = path
+        for _ in range(PLUGIN_DAEMON_MAX_PATH_DECODE_DEPTH):
+            next_decoded_path = unquote(decoded_path)
+            if next_decoded_path == decoded_path:
+                break
+            decoded_path = next_decoded_path
+        else:
+            raise ValueError("Invalid plugin daemon path: path is too deeply encoded")
+
+        if any(seg == ".." for seg in decoded_path.split("/")):
+            raise ValueError(f"Invalid plugin daemon path: traversal sequence detected in {path!r}")
         url = plugin_daemon_inner_api_baseurl / path
         prepared_headers = dict(headers or {})
         prepared_headers["X-Api-Key"] = dify_config.PLUGIN_DAEMON_KEY

api/core/plugin/impl/plugin.py

@@ -209,7 +209,10 @@ class PluginInstaller(BasePluginClient):
             "GET",
             f"plugin/{tenant_id}/management/decode/from_identifier",
             PluginDecodeResponse,
-            params={"plugin_unique_identifier": plugin_unique_identifier},
+            params={
+                "plugin_unique_identifier": plugin_unique_identifier,
+                "PluginUniqueIdentifier": plugin_unique_identifier,  # compat with daemon <= 0.5.4
+            },
         )
 
     def fetch_plugin_installation_by_ids(

api/core/rag/datasource/retrieval_service.py

@@ -1,9 +1,12 @@
 import concurrent.futures
+import functools
 import logging
+from collections.abc import Callable, Sequence
 from concurrent.futures import ThreadPoolExecutor
 from typing import Any, NotRequired
 
 from flask import Flask, current_app
+from opentelemetry import context as otel_context
 from sqlalchemy import select
 from sqlalchemy.orm import Session, load_only
 from typing_extensions import TypedDict
@@ -22,9 +25,10 @@ from core.rag.index_processor.constant.query_type import QueryType
 from core.rag.models.document import Document
 from core.rag.rerank.rerank_type import RerankMode
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
-from core.tools.signature import sign_upload_file
+from core.tools.signature import sign_upload_file_preview_url
 from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
+from extensions.otel import trace_span
 from models.dataset import (
     ChildChunk,
     Dataset,
@@ -89,9 +93,24 @@ default_retrieval_model: DefaultRetrievalModelDict = {
 logger = logging.getLogger(__name__)
 
 
+def _propagate_otel_context[**P, R](func: Callable[P, R]) -> Callable[P, R]:
+    captured_context = otel_context.get_current()
+
+    @functools.wraps(func)
+    def wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
+        token = otel_context.attach(captured_context)
+        try:
+            return func(*args, **kwargs)
+        finally:
+            otel_context.detach(token)
+
+    return wrapper
+
+
 class RetrievalService:
     # Cache precompiled regular expressions to avoid repeated compilation
     @classmethod
+    @trace_span()
     def retrieve(
         cls,
         retrieval_method: RetrievalMethod,
@@ -121,7 +140,7 @@ class RetrievalService:
             if query:
                 futures.append(
                     executor.submit(
-                        retrieval_service._retrieve,
+                        _propagate_otel_context(retrieval_service._retrieve),
                         flask_app=current_app._get_current_object(),  # type: ignore
                         retrieval_method=retrieval_method,
                         dataset=dataset,
@@ -141,7 +160,7 @@ class RetrievalService:
                 for attachment_id in attachment_ids:
                     futures.append(
                         executor.submit(
-                            retrieval_service._retrieve,
+                            _propagate_otel_context(retrieval_service._retrieve),
                             flask_app=current_app._get_current_object(),  # type: ignore
                             retrieval_method=retrieval_method,
                             dataset=dataset,
@@ -244,6 +263,7 @@ class RetrievalService:
             return session.query(Dataset).where(Dataset.id == dataset_id).first()
 
     @classmethod
+    @trace_span()
     def keyword_search(
         cls,
         flask_app: Flask,
@@ -271,6 +291,7 @@ class RetrievalService:
                 exceptions.append(str(e))
 
     @classmethod
+    @trace_span()
     def embedding_search(
         cls,
         flask_app: Flask,
@@ -365,6 +386,7 @@ class RetrievalService:
                 exceptions.append(str(e))
 
     @classmethod
+    @trace_span()
     def full_text_index_search(
         cls,
         flask_app: Flask,
@@ -726,6 +748,7 @@ class RetrievalService:
             db.session.rollback()
             raise e
 
+    @trace_span()
     def _retrieve(
         self,
         flask_app: Flask,
@@ -752,7 +775,7 @@ class RetrievalService:
                 if retrieval_method == RetrievalMethod.KEYWORD_SEARCH and query:
                     futures.append(
                         executor.submit(
-                            self.keyword_search,
+                            _propagate_otel_context(self.keyword_search),
                             flask_app=current_app._get_current_object(),  # type: ignore
                             dataset_id=dataset.id,
                             query=query,
@@ -766,7 +789,7 @@ class RetrievalService:
                     if query:
                         futures.append(
                             executor.submit(
-                                self.embedding_search,
+                                _propagate_otel_context(self.embedding_search),
                                 flask_app=current_app._get_current_object(),  # type: ignore
                                 dataset_id=dataset.id,
                                 query=query,
@@ -783,7 +806,7 @@ class RetrievalService:
                     if attachment_id:
                         futures.append(
                             executor.submit(
-                                self.embedding_search,
+                                _propagate_otel_context(self.embedding_search),
                                 flask_app=current_app._get_current_object(),  # type: ignore
                                 dataset_id=dataset.id,
                                 query=attachment_id,
@@ -800,7 +823,7 @@ class RetrievalService:
                 if RetrievalMethod.is_support_fulltext_search(retrieval_method) and query:
                     futures.append(
                         executor.submit(
-                            self.full_text_index_search,
+                            _propagate_otel_context(self.full_text_index_search),
                             flask_app=current_app._get_current_object(),  # type: ignore
                             dataset_id=dataset.id,
                             query=query,
@@ -864,7 +887,7 @@ class RetrievalService:
                     "name": upload_file.name,
                     "extension": "." + upload_file.extension,
                     "mime_type": upload_file.mime_type,
-                    "source_url": sign_upload_file(upload_file.id, upload_file.extension),
+                    "source_url": sign_upload_file_preview_url(upload_file.id, upload_file.extension),
                     "size": upload_file.size,
                 }
                 return {"attachment_info": attachment_info, "segment_id": attachment_binding.segment_id}
@@ -893,7 +916,7 @@ class RetrievalService:
                         "name": upload_file.name,
                         "extension": "." + upload_file.extension,
                         "mime_type": upload_file.mime_type,
-                        "source_url": sign_upload_file(upload_file.id, upload_file.extension),
+                        "source_url": sign_upload_file_preview_url(upload_file.id, upload_file.extension),
                         "size": upload_file.size,
                     }
                     if attachment_binding:

api/core/rag/datasource/vdb/myscale/myscale_vector.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import re
 import uuid
 from enum import StrEnum
 from typing import Any
@@ -17,6 +18,8 @@ from models.dataset import Dataset
 
 logger = logging.getLogger(__name__)
 
+METADATA_KEY_PATTERN = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
+
 
 class MyScaleConfig(BaseModel):
     host: str
@@ -98,47 +101,63 @@ class MyScaleVector(BaseVector):
         return "".join(" " if c in {"\\", "'"} else c for c in str(value))
 
     def text_exists(self, id: str) -> bool:
-        results = self._client.query(f"SELECT id FROM {self._config.database}.{self._collection_name} WHERE id='{id}'")
+        results = self._client.query(
+            f"SELECT id FROM {self._config.database}.{self._collection_name} WHERE id={{id:String}}",
+            parameters={"id": id},
+        )
         return results.row_count > 0
 
     def delete_by_ids(self, ids: list[str]):
         if not ids:
             return
         self._client.command(
-            f"DELETE FROM {self._config.database}.{self._collection_name} WHERE id IN {str(tuple(ids))}"
+            f"DELETE FROM {self._config.database}.{self._collection_name} WHERE id IN {{ids:Array(String)}}",
+            parameters={"ids": ids},
         )
 
     def get_ids_by_metadata_field(self, key: str, value: str):
+        self._validate_metadata_key(key)
         rows = self._client.query(
-            f"SELECT DISTINCT id FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'"
+            f"SELECT DISTINCT id FROM {self._config.database}.{self._collection_name} "
+            f"WHERE metadata.{key}={{value:String}}",
+            parameters={"value": value},
         ).result_rows
         return [row[0] for row in rows]
 
     def delete_by_metadata_field(self, key: str, value: str):
+        self._validate_metadata_key(key)
         self._client.command(
-            f"DELETE FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'"
+            f"DELETE FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}={{value:String}}",
+            parameters={"value": value},
         )
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
         return self._search(f"distance(vector, {str(query_vector)})", self._vec_order, **kwargs)
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
-        return self._search(f"TextSearch('enable_nlq=false')(text, '{query}')", SortOrder.DESC, **kwargs)
+        return self._search(
+            "TextSearch('enable_nlq=false')(text, {query:String})",
+            SortOrder.DESC,
+            parameters={"query": query},
+            **kwargs,
+        )
 
-    def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]:
+    def _search(
+        self, dist: str, order: SortOrder, parameters: dict[str, Any] | None = None, **kwargs: Any
+    ) -> list[Document]:
         top_k = kwargs.get("top_k", 4)
         if not isinstance(top_k, int) or top_k <= 0:
             raise ValueError("top_k must be a positive integer")
         score_threshold = float(kwargs.get("score_threshold") or 0.0)
-        where_str = (
-            f"WHERE dist < {1 - score_threshold}"
-            if self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0
-            else ""
-        )
+        where_conditions = []
+        query_parameters = dict(parameters or {})
+        if self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0:
+            where_conditions.append(f"dist < {1 - score_threshold}")
         document_ids_filter = kwargs.get("document_ids_filter")
         if document_ids_filter:
-            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
-            where_str = f"{where_str} AND metadata['document_id'] in ({document_ids})"
+            where_conditions.append("metadata['document_id'] IN {document_ids_filter:Array(String)}")
+            query_parameters["document_ids_filter"] = document_ids_filter
+        where_str = f"WHERE {' AND '.join(where_conditions)}" if where_conditions else ""
         sql = f"""
             SELECT text, vector, metadata, {dist} as dist FROM {self._config.database}.{self._collection_name}
             {where_str} ORDER BY dist {order.value} LIMIT {top_k}
@@ -150,12 +169,17 @@ class MyScaleVector(BaseVector):
                     vector=r["vector"],
                     metadata=r["metadata"],
                 )
-                for r in self._client.query(sql).named_results()
+                for r in self._client.query(sql, parameters=query_parameters).named_results()
             ]
         except Exception:
             logger.exception("Vector search operation failed")
             return []
 
+    @staticmethod
+    def _validate_metadata_key(key: str) -> None:
+        if not METADATA_KEY_PATTERN.match(key):
+            raise ValueError("metadata key must be a valid identifier")
+
     def delete(self):
         self._client.command(f"DROP TABLE IF EXISTS {self._config.database}.{self._collection_name}")
 

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

@@ -18,6 +18,7 @@ from dify_graph.model_runtime.entities.model_entities import ModelType
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
+from extensions.otel import trace_span
 from models.dataset import Dataset, Whitelist
 from models.model import UploadFile
 
@@ -274,6 +275,10 @@ class Vector:
 
     def search_by_vector(self, query: str, **kwargs: Any) -> list[Document]:
         query_vector = self._embeddings.embed_query(query)
+        return self._search_by_vector_traced(query_vector, **kwargs)
+
+    @trace_span()
+    def _search_by_vector_traced(self, query_vector: list[float], **kwargs) -> list[Document]:
         return self._vector_processor.search_by_vector(query_vector, **kwargs)
 
     def search_by_file(self, file_id: str, **kwargs: Any) -> list[Document]:
@@ -290,7 +295,7 @@ class Vector:
                 "file_id": file_id,
             }
         )
-        return self._vector_processor.search_by_vector(multimodal_vector, **kwargs)
+        return self._search_by_vector_traced(multimodal_vector, **kwargs)
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         return self._vector_processor.search_by_full_text(query, **kwargs)

api/core/rag/extractor/pdf_extractor.py

@@ -115,7 +115,7 @@ class PdfExtractor(BaseExtractor):
         """
         image_content = []
         upload_files = []
-        base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL
+        base_url = dify_config.FILES_URL
 
         try:
             image_objects = page.get_objects(filter=(pdfium_c.FPDF_PAGEOBJ_IMAGE,))

api/core/rag/extractor/word_extractor.py

@@ -88,7 +88,7 @@ class WordExtractor(BaseExtractor):
     def _extract_images_from_docx(self, doc):
         image_count = 0
         image_map = {}
-        base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL
+        base_url = dify_config.FILES_URL
 
         for r_id, rel in doc.part.rels.items():
             if "image" in rel.target_ref:

api/core/rag/retrieval/dataset_retrieval.py

@@ -54,7 +54,7 @@ from core.rag.retrieval.template_prompts import (
     METADATA_FILTER_USER_PROMPT_2,
     METADATA_FILTER_USER_PROMPT_3,
 )
-from core.tools.signature import sign_upload_file
+from core.tools.signature import sign_upload_file_preview_url
 from core.tools.utils.dataset_retriever.dataset_retriever_base_tool import DatasetRetrieverBaseTool
 from core.workflow.nodes.knowledge_retrieval import exc
 from core.workflow.nodes.knowledge_retrieval.retrieval import (
@@ -524,7 +524,7 @@ class DatasetRetrieval:
                                     related_id=upload_file.id,
                                     size=upload_file.size,
                                     storage_key=upload_file.key,
-                                    url=sign_upload_file(upload_file.id, upload_file.extension),
+                                    url=sign_upload_file_preview_url(upload_file.id, upload_file.extension),
                                 )
                                 context_files.append(attachment_info)
                 if show_retrieve_source:

api/core/tools/signature.py

@@ -25,12 +25,14 @@ def sign_tool_file(tool_file_id: str, extension: str, for_external: bool = True)
     return f"{file_preview_url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}"
 
 
-def sign_upload_file(upload_file_id: str, extension: str) -> str:
+def sign_upload_file_preview_url(upload_file_id: str, extension: str) -> str:
     """
-    sign file to get a temporary url for plugin access
+    Sign an upload file to get a temporary image preview URL.
+
+    The URL generated by this function is only for external preview and download,
+    not for internal communication.
     """
-    # Use internal URL for plugin/tool file access in Docker environments
-    base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL
+    base_url = dify_config.FILES_URL
     file_preview_url = f"{base_url}/files/{upload_file_id}/image-preview"
 
     timestamp = str(int(time.time()))

api/core/tools/tool_manager.py

@@ -246,9 +246,9 @@ class ToolManager:
                     raise ToolProviderNotFoundError(f"builtin provider {provider_id} not found")
 
             # check if the credential is allowed to be used
-            from core.helper.credential_utils import check_credential_policy_compliance
+            from core.helper.credential_utils import runtime_check_credential_policy_compliance
 
-            check_credential_policy_compliance(
+            runtime_check_credential_policy_compliance(
                 credential_id=builtin_provider.id,
                 provider=provider_id,
                 credential_type=PluginCredentialType.TOOL,

api/dify_graph/graph/graph.py

@@ -10,7 +10,6 @@ from pydantic import TypeAdapter
 from dify_graph.entities.graph_config import NodeConfigDict
 from dify_graph.enums import ErrorStrategy, NodeExecutionType, NodeState
 from dify_graph.nodes.base.node import Node
-from libs.typing import is_str
 
 from .edge import Edge
 from .validation import get_graph_validator
@@ -102,7 +101,7 @@ class Graph:
             source = edge_config.get("source")
             target = edge_config.get("target")
 
-            if not is_str(source) or not is_str(target):
+            if not isinstance(source, str) or not isinstance(target, str):
                 continue
 
             # Create edge
@@ -110,7 +109,7 @@ class Graph:
             edge_counter += 1
 
             source_handle = edge_config.get("sourceHandle", "source")
-            if not is_str(source_handle):
+            if not isinstance(source_handle, str):
                 continue
 
             edge = Edge(

api/dify_graph/nodes/llm/node.py

@@ -16,7 +16,7 @@ from core.llm_generator.output_parser.structured_output import invoke_llm_with_s
 from core.model_manager import ModelInstance
 from core.prompt.entities.advanced_prompt_entities import CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
-from core.tools.signature import sign_upload_file
+from core.tools.signature import sign_upload_file_preview_url
 from dify_graph.constants import SYSTEM_VARIABLE_NODE_ID
 from dify_graph.entities import GraphInitParams
 from dify_graph.entities.graph_config import NodeConfigDict
@@ -712,7 +712,7 @@ class LLMNode(Node[LLMNodeData]):
                                         related_id=upload_file.id,
                                         size=upload_file.size,
                                         storage_key=upload_file.key,
-                                        url=sign_upload_file(upload_file.id, upload_file.extension),
+                                        url=sign_upload_file_preview_url(upload_file.id, upload_file.extension),
                                     )
                                     context_files.append(attachment_info)
                 yield RunRetrieverResourceEvent(

api/extensions/ext_redis.py

@@ -7,10 +7,12 @@ from typing import TYPE_CHECKING, Any, ParamSpec, TypeVar, Union
 
 import redis
 from redis import RedisError
+from redis.backoff import ExponentialWithJitterBackoff  # type: ignore
 from redis.cache import CacheConfig
 from redis.client import PubSub
 from redis.cluster import ClusterNode, RedisCluster
 from redis.connection import Connection, SSLConnection
+from redis.retry import Retry
 from redis.sentinel import Sentinel
 
 from configs import dify_config
@@ -158,8 +160,41 @@ def _get_cache_configuration() -> CacheConfig | None:
     return CacheConfig()
 
 
+def _get_retry_policy() -> Retry:
+    """Build the shared retry policy for Redis connections."""
+    return Retry(
+        backoff=ExponentialWithJitterBackoff(
+            base=dify_config.REDIS_RETRY_BACKOFF_BASE,
+            cap=dify_config.REDIS_RETRY_BACKOFF_CAP,
+        ),
+        retries=dify_config.REDIS_RETRY_RETRIES,
+    )
+
+
+def _get_connection_health_params() -> dict[str, Any]:
+    """Get connection health and retry parameters for standalone and Sentinel Redis clients."""
+    return {
+        "retry": _get_retry_policy(),
+        "socket_timeout": dify_config.REDIS_SOCKET_TIMEOUT,
+        "socket_connect_timeout": dify_config.REDIS_SOCKET_CONNECT_TIMEOUT,
+        "health_check_interval": dify_config.REDIS_HEALTH_CHECK_INTERVAL,
+    }
+
+
+def _get_cluster_connection_health_params() -> dict[str, Any]:
+    """Get retry and timeout parameters for Redis Cluster clients.
+
+    RedisCluster does not support ``health_check_interval`` as a constructor
+    keyword (it is silently stripped by ``cleanup_kwargs``), so it is excluded
+    here. Only ``retry``, ``socket_timeout``, and ``socket_connect_timeout``
+    are passed through.
+    """
+    params = _get_connection_health_params()
+    return {k: v for k, v in params.items() if k != "health_check_interval"}
+
+
 def _get_base_redis_params() -> dict[str, Any]:
-    """Get base Redis connection parameters."""
+    """Get base Redis connection parameters including retry and health policy."""
     return {
         "username": dify_config.REDIS_USERNAME,
         "password": dify_config.REDIS_PASSWORD or None,
@@ -169,6 +204,7 @@ def _get_base_redis_params() -> dict[str, Any]:
         "decode_responses": False,
         "protocol": dify_config.REDIS_SERIALIZATION_PROTOCOL,
         "cache_config": _get_cache_configuration(),
+        **_get_connection_health_params(),
     }
 
 
@@ -215,6 +251,7 @@ def _create_cluster_client() -> Union[redis.Redis, RedisCluster]:
         "password": dify_config.REDIS_CLUSTERS_PASSWORD,
         "protocol": dify_config.REDIS_SERIALIZATION_PROTOCOL,
         "cache_config": _get_cache_configuration(),
+        **_get_cluster_connection_health_params(),
     }
     if dify_config.REDIS_MAX_CONNECTIONS:
         cluster_kwargs["max_connections"] = dify_config.REDIS_MAX_CONNECTIONS
@@ -226,7 +263,8 @@ def _create_standalone_client(redis_params: dict[str, Any]) -> Union[redis.Redis
     """Create standalone Redis client."""
     connection_class, ssl_kwargs = _get_ssl_configuration()
 
-    redis_params.update(
+    params = {**redis_params}
+    params.update(
         {
             "host": dify_config.REDIS_HOST,
             "port": dify_config.REDIS_PORT,
@@ -235,28 +273,31 @@ def _create_standalone_client(redis_params: dict[str, Any]) -> Union[redis.Redis
     )
 
     if dify_config.REDIS_MAX_CONNECTIONS:
-        redis_params["max_connections"] = dify_config.REDIS_MAX_CONNECTIONS
+        params["max_connections"] = dify_config.REDIS_MAX_CONNECTIONS
 
     if ssl_kwargs:
-        redis_params.update(ssl_kwargs)
+        params.update(ssl_kwargs)
 
-    pool = redis.ConnectionPool(**redis_params)
+    pool = redis.ConnectionPool(**params)
     client: redis.Redis = redis.Redis(connection_pool=pool)
     return client
 
 
 def _create_pubsub_client(pubsub_url: str, use_clusters: bool) -> redis.Redis | RedisCluster:
     max_conns = dify_config.REDIS_MAX_CONNECTIONS
-    if use_clusters:
-        if max_conns:
-            return RedisCluster.from_url(pubsub_url, max_connections=max_conns)
-        else:
-            return RedisCluster.from_url(pubsub_url)
 
+    if use_clusters:
+        health_params = _get_cluster_connection_health_params()
+        kwargs: dict[str, Any] = {**health_params}
+        if max_conns:
+            kwargs["max_connections"] = max_conns
+        return RedisCluster.from_url(pubsub_url, **kwargs)
+
+    health_params = _get_connection_health_params()
+    kwargs = {**health_params}
     if max_conns:
-        return redis.Redis.from_url(pubsub_url, max_connections=max_conns)
-    else:
-        return redis.Redis.from_url(pubsub_url)
+        kwargs["max_connections"] = max_conns
+    return redis.Redis.from_url(pubsub_url, **kwargs)
 
 
 def init_app(app: DifyApp):
@@ -287,14 +328,16 @@ def init_app(app: DifyApp):
 
 def get_pubsub_broadcast_channel() -> BroadcastChannelProtocol:
     assert _pubsub_redis_client is not None, "PubSub redis Client should be initialized here."
+    join_timeout_ms = dify_config.PUBSUB_LISTENER_JOIN_TIMEOUT_MS
     if dify_config.PUBSUB_REDIS_CHANNEL_TYPE == "sharded":
-        return ShardedRedisBroadcastChannel(_pubsub_redis_client)
+        return ShardedRedisBroadcastChannel(_pubsub_redis_client, join_timeout_ms=join_timeout_ms)
     if dify_config.PUBSUB_REDIS_CHANNEL_TYPE == "streams":
         return StreamsBroadcastChannel(
             _pubsub_redis_client,
             retention_seconds=dify_config.PUBSUB_STREAMS_RETENTION_SECONDS,
+            join_timeout_ms=join_timeout_ms,
         )
-    return RedisBroadcastChannel(_pubsub_redis_client)
+    return RedisBroadcastChannel(_pubsub_redis_client, join_timeout_ms=join_timeout_ms)
 
 
 P = ParamSpec("P")

api/libs/broadcast_channel/redis/_subscription.py

@@ -26,6 +26,8 @@ class RedisSubscriptionBase(Subscription):
         client: Redis | RedisCluster,
         pubsub: PubSub,
         topic: str,
+        *,
+        join_timeout_ms: int = 2000,
     ):
         # The _pubsub is None only if the subscription is closed.
         self._client = client
@@ -37,6 +39,11 @@ class RedisSubscriptionBase(Subscription):
         self._listener_thread: threading.Thread | None = None
         self._start_lock = threading.Lock()
         self._started = False
+        # Max time close() will wait for the listener thread to finish before
+        # returning. Bounds SSE close tail latency. The listener is a daemon
+        # and exits on its own within one poll window (~1s), so a low value
+        # here just means close() returns sooner without breaking anything.
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def _start_if_needed(self) -> None:
         """Start the subscription if not already started."""
@@ -205,7 +212,7 @@ class RedisSubscriptionBase(Subscription):
         # Due to the restriction above, the PubSub cleanup logic happens inside the consumer thread.
         listener = self._listener_thread
         if listener is not None:
-            listener.join(timeout=1.0)
+            listener.join(timeout=self._join_timeout_ms / 1000.0)
             self._listener_thread = None
 
     # Abstract methods to be implemented by subclasses

api/libs/broadcast_channel/redis/channel.py

@@ -19,17 +19,29 @@ class BroadcastChannel:
     def __init__(
         self,
         redis_client: Redis | RedisCluster,
+        *,
+        join_timeout_ms: int = 2000,
     ):
         self._client = redis_client
+        # See `RedisSubscriptionBase._join_timeout_ms`: how long close()
+        # waits for the listener thread before returning.
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def topic(self, topic: str) -> Topic:
-        return Topic(self._client, topic)
+        return Topic(self._client, topic, join_timeout_ms=self._join_timeout_ms)
 
 
 class Topic:
-    def __init__(self, redis_client: Redis | RedisCluster, topic: str):
+    def __init__(
+        self,
+        redis_client: Redis | RedisCluster,
+        topic: str,
+        *,
+        join_timeout_ms: int = 2000,
+    ):
         self._client = redis_client
         self._topic = topic
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def as_producer(self) -> Producer:
         return self
@@ -45,6 +57,7 @@ class Topic:
             client=self._client,
             pubsub=self._client.pubsub(),
             topic=self._topic,
+            join_timeout_ms=self._join_timeout_ms,
         )
 
 

api/libs/broadcast_channel/redis/sharded_channel.py

@@ -17,17 +17,27 @@ class ShardedRedisBroadcastChannel:
     def __init__(
         self,
         redis_client: Redis | RedisCluster,
+        *,
+        join_timeout_ms: int = 2000,
     ):
         self._client = redis_client
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def topic(self, topic: str) -> ShardedTopic:
-        return ShardedTopic(self._client, topic)
+        return ShardedTopic(self._client, topic, join_timeout_ms=self._join_timeout_ms)
 
 
 class ShardedTopic:
-    def __init__(self, redis_client: Redis | RedisCluster, topic: str):
+    def __init__(
+        self,
+        redis_client: Redis | RedisCluster,
+        topic: str,
+        *,
+        join_timeout_ms: int = 2000,
+    ):
         self._client = redis_client
         self._topic = topic
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def as_producer(self) -> Producer:
         return self
@@ -43,6 +53,7 @@ class ShardedTopic:
             client=self._client,
             pubsub=self._client.pubsub(),
             topic=self._topic,
+            join_timeout_ms=self._join_timeout_ms,
         )
 
 

api/libs/broadcast_channel/redis/streams_channel.py

@@ -23,20 +23,42 @@ class StreamsBroadcastChannel:
     - The stream key expires `retention_seconds` after the last event is published (to bound storage).
     """
 
-    def __init__(self, redis_client: Redis | RedisCluster, *, retention_seconds: int = 600):
+    def __init__(
+        self,
+        redis_client: Redis | RedisCluster,
+        *,
+        retention_seconds: int = 600,
+        join_timeout_ms: int = 2000,
+    ):
         self._client = redis_client
         self._retention_seconds = max(int(retention_seconds or 0), 0)
+        # Max time close() will wait for the listener thread to finish.
+        # See `_StreamsSubscription._join_timeout_ms` for the rationale.
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
     def topic(self, topic: str) -> StreamsTopic:
-        return StreamsTopic(self._client, topic, retention_seconds=self._retention_seconds)
+        return StreamsTopic(
+            self._client,
+            topic,
+            retention_seconds=self._retention_seconds,
+            join_timeout_ms=self._join_timeout_ms,
+        )
 
 
 class StreamsTopic:
-    def __init__(self, redis_client: Redis | RedisCluster, topic: str, *, retention_seconds: int = 600):
+    def __init__(
+        self,
+        redis_client: Redis | RedisCluster,
+        topic: str,
+        *,
+        retention_seconds: int = 600,
+        join_timeout_ms: int = 2000,
+    ):
         self._client = redis_client
         self._topic = topic
         self._key = f"stream:{topic}"
         self._retention_seconds = retention_seconds
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
         self.max_length = 5000
 
     def as_producer(self) -> Producer:
@@ -54,15 +76,23 @@ class StreamsTopic:
         return self
 
     def subscribe(self) -> Subscription:
-        return _StreamsSubscription(self._client, self._key)
+        return _StreamsSubscription(self._client, self._key, join_timeout_ms=self._join_timeout_ms)
 
 
 class _StreamsSubscription(Subscription):
     _SENTINEL = object()
 
-    def __init__(self, client: Redis | RedisCluster, key: str):
+    def __init__(self, client: Redis | RedisCluster, key: str, *, join_timeout_ms: int = 2000):
         self._client = client
         self._key = key
+        # Max time close() will wait for the listener thread to finish before
+        # returning. Bounds SSE close tail latency: the listener blocks on
+        # XREAD with BLOCK=1000ms, so close() naturally waits up to ~1s for
+        # the thread to notice _closed. Setting this lower lets close()
+        # return promptly while the daemon listener exits on its own within
+        # one BLOCK window - safe because the listener holds no critical
+        # state. ``0`` means close() does not wait at all.
+        self._join_timeout_ms = max(int(join_timeout_ms or 0), 0)
 
         self._queue: queue.Queue[object] = queue.Queue()
 
@@ -180,11 +210,13 @@ class _StreamsSubscription(Subscription):
         # We close the listener outside of the with block to avoid holding the
         # lock for a long time.
         if listener is not None and listener.is_alive():
-            listener.join(timeout=2.0)
+            listener.join(timeout=self._join_timeout_ms / 1000.0)
             if listener.is_alive():
-                logger.warning(
-                    "Streams subscription listener for key %s did not stop within timeout; keeping reference.",
+                logger.debug(
+                    "Streams subscription listener for key %s did not stop within %dms; "
+                    "daemon thread will exit on its own within one poll window.",
                     self._key,
+                    self._join_timeout_ms,
                 )
 
     # Context manager helpers

api/libs/pyrefly_type_coverage.py

@@ -0,0 +1,145 @@
+"""Helpers for generating type-coverage summaries from pyrefly report output."""
+
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+from typing import TypedDict
+
+
+class CoverageSummary(TypedDict):
+    n_modules: int
+    n_typable: int
+    n_typed: int
+    n_any: int
+    n_untyped: int
+    coverage: float
+    strict_coverage: float
+
+
+_REQUIRED_KEYS = frozenset(CoverageSummary.__annotations__)
+
+_EMPTY_SUMMARY: CoverageSummary = {
+    "n_modules": 0,
+    "n_typable": 0,
+    "n_typed": 0,
+    "n_any": 0,
+    "n_untyped": 0,
+    "coverage": 0.0,
+    "strict_coverage": 0.0,
+}
+
+
+def parse_summary(report_json: str) -> CoverageSummary:
+    """Extract the summary section from ``pyrefly report`` JSON output.
+
+    Returns an empty summary when *report_json* is empty or malformed so that
+    the CI workflow can degrade gracefully instead of crashing.
+    """
+    if not report_json or not report_json.strip():
+        return _EMPTY_SUMMARY.copy()
+
+    try:
+        data = json.loads(report_json)
+    except json.JSONDecodeError:
+        return _EMPTY_SUMMARY.copy()
+
+    summary = data.get("summary")
+    if not isinstance(summary, dict) or not _REQUIRED_KEYS.issubset(summary):
+        return _EMPTY_SUMMARY.copy()
+
+    return {
+        "n_modules": summary["n_modules"],
+        "n_typable": summary["n_typable"],
+        "n_typed": summary["n_typed"],
+        "n_any": summary["n_any"],
+        "n_untyped": summary["n_untyped"],
+        "coverage": summary["coverage"],
+        "strict_coverage": summary["strict_coverage"],
+    }
+
+
+def format_summary_markdown(summary: CoverageSummary) -> str:
+    """Format a single coverage summary as a Markdown table."""
+
+    return (
+        "| Metric | Value |\n"
+        "| --- | ---: |\n"
+        f"| Modules | {summary['n_modules']} |\n"
+        f"| Typable symbols | {summary['n_typable']:,} |\n"
+        f"| Typed symbols | {summary['n_typed']:,} |\n"
+        f"| Untyped symbols | {summary['n_untyped']:,} |\n"
+        f"| Any symbols | {summary['n_any']:,} |\n"
+        f"| **Type coverage** | **{summary['coverage']:.2f}%** |\n"
+        f"| Strict coverage | {summary['strict_coverage']:.2f}% |"
+    )
+
+
+def format_comparison_markdown(
+    base: CoverageSummary,
+    pr: CoverageSummary,
+) -> str:
+    """Format a comparison between base and PR coverage as Markdown."""
+
+    coverage_delta = pr["coverage"] - base["coverage"]
+    strict_delta = pr["strict_coverage"] - base["strict_coverage"]
+    typed_delta = pr["n_typed"] - base["n_typed"]
+    untyped_delta = pr["n_untyped"] - base["n_untyped"]
+
+    def _fmt_delta(value: float, fmt: str = ".2f") -> str:
+        sign = "+" if value > 0 else ""
+        return f"{sign}{value:{fmt}}"
+
+    lines = [
+        "| Metric | Base | PR | Delta |",
+        "| --- | ---: | ---: | ---: |",
+        (f"| **Type coverage** | {base['coverage']:.2f}% | {pr['coverage']:.2f}% | {_fmt_delta(coverage_delta)}% |"),
+        (
+            f"| Strict coverage | {base['strict_coverage']:.2f}% "
+            f"| {pr['strict_coverage']:.2f}% "
+            f"| {_fmt_delta(strict_delta)}% |"
+        ),
+        (f"| Typed symbols | {base['n_typed']:,} | {pr['n_typed']:,} | {_fmt_delta(typed_delta, ',')} |"),
+        (f"| Untyped symbols | {base['n_untyped']:,} | {pr['n_untyped']:,} | {_fmt_delta(untyped_delta, ',')} |"),
+        (
+            f"| Modules | {base['n_modules']} "
+            f"| {pr['n_modules']} "
+            f"| {_fmt_delta(pr['n_modules'] - base['n_modules'], ',')} |"
+        ),
+    ]
+    return "\n".join(lines)
+
+
+def main() -> int:
+    """Read pyrefly report JSON from stdin and print a Markdown summary.
+
+    Accepts an optional ``--base <file>`` argument. When provided, the output
+    includes a base-vs-PR comparison table.
+    """
+
+    args = sys.argv[1:]
+
+    base_file: str | None = None
+    if "--base" in args:
+        idx = args.index("--base")
+        if idx + 1 >= len(args):
+            sys.stderr.write("error: --base requires a file path\n")
+            return 1
+        base_file = args[idx + 1]
+
+    pr_report = sys.stdin.read()
+    pr_summary = parse_summary(pr_report)
+
+    if base_file is not None:
+        base_text = Path(base_file).read_text() if Path(base_file).exists() else ""
+        base_summary = parse_summary(base_text)
+        sys.stdout.write(format_comparison_markdown(base_summary, pr_summary) + "\n")
+    else:
+        sys.stdout.write(format_summary_markdown(pr_summary) + "\n")
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

api/libs/typing.py

@@ -1,9 +0,0 @@
-from typing import TypeGuard
-
-
-def is_str_dict(v: object) -> TypeGuard[dict[str, object]]:
-    return isinstance(v, dict)
-
-
-def is_str(v: object) -> TypeGuard[str]:
-    return isinstance(v, str)

api/models/dataset.py

@@ -23,7 +23,7 @@ from core.rag.index_processor.constant.built_in_field import BuiltInField, Metad
 from core.rag.index_processor.constant.index_type import IndexStructureType, IndexTechniqueType
 from core.rag.index_processor.constant.query_type import QueryType
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
-from core.tools.signature import sign_upload_file
+from core.tools.signature import sign_upload_file_preview_url
 from extensions.ext_storage import storage
 from libs.uuid_utils import uuidv7
 from services.entities.knowledge_entities.knowledge_entities import ParentMode, Rule
@@ -965,7 +965,7 @@ class DocumentSegment(Base):
             encoded_sign = base64.urlsafe_b64encode(sign).decode()
 
             params = f"timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}"
-            reference_url = dify_config.CONSOLE_API_URL or ""
+            reference_url = dify_config.FILES_URL or dify_config.CONSOLE_API_URL or ""
             base_url = f"{reference_url}/files/{upload_file_id}/image-preview"
             source_url = f"{base_url}?{params}"
             attachment_list.append(
@@ -1094,7 +1094,7 @@ class DatasetQuery(TypeBase):
                                 "size": file_info.size,
                                 "extension": file_info.extension,
                                 "mime_type": file_info.mime_type,
-                                "source_url": sign_upload_file(file_info.id, file_info.extension),
+                                "source_url": sign_upload_file_preview_url(file_info.id, file_info.extension),
                             }
                     else:
                         query["file_info"] = None

api/pyproject.toml

@@ -34,13 +34,13 @@ dependencies = [
     "json-repair>=0.55.1",
     "jsonschema>=4.25.1",
     "langfuse~=2.51.3",
-    "langsmith~=0.7.16",
+    "langsmith>=0.8.18",
     "markdown~=3.10.2",
     "mlflow-skinny>=3.0.0",
     "numpy~=1.26.4",
     "openpyxl~=3.1.5",
     "opik~=1.10.37",
-    "litellm==1.83.0", # Pinned to avoid madoka dependency issue
+    "litellm>=1.83.10",
     "opentelemetry-api==1.28.0",
     "opentelemetry-distro==0.49b0",
     "opentelemetry-exporter-otlp==1.28.0",
@@ -64,8 +64,8 @@ dependencies = [
     "pycryptodome==3.23.0",
     "pydantic~=2.12.5",
     "pydantic-extra-types~=2.11.0",
-    "pydantic-settings~=2.13.1",
-    "pyjwt~=2.12.0",
+    "pydantic-settings>=2.14.2,<3.0.0",
+    "pyjwt~=2.13.0",
     "pypdfium2==5.6.0",
     "python-docx~=1.2.0",
     "python-dotenv==1.2.2",
@@ -75,7 +75,7 @@ dependencies = [
     "resend~=2.26.0",
     "sentry-sdk[flask]~=2.55.0",
     "sqlalchemy~=2.0.29",
-    "starlette==1.0.0",
+    "starlette>=1.3.1,<2.0.0",
     "tiktoken~=0.12.0",
     "transformers~=5.3.0",
     "unstructured[docx,epub,md,ppt,pptx]~=0.21.5",
@@ -84,15 +84,15 @@ dependencies = [
     "webvtt-py~=0.5.1",
     "sseclient-py~=1.9.0",
     "httpx-sse~=0.4.0",
-    "sendgrid~=6.12.3",
+    "sendgrid~=6.12.5",
     "flask-restx~=1.3.2",
     "packaging~=23.2",
     "croniter>=6.0.0",
     "weaviate-client==4.20.5",
     "apscheduler>=3.11.0",
-    "weave>=0.52.25",
+    "weave>=0.52.16",
     "fastopenapi[flask]>=0.7.0",
-    "bleach~=6.3.0",
+    "bleach>=6.4.0,<7.0.0",
 ]
 # Before adding new dependency, consider place it in
 # alphabet order (a-z) and suitable group.
@@ -103,6 +103,14 @@ packages = []
 [tool.uv]
 default-groups = ["storage", "tools", "vdb"]
 package = false
+# litellm==1.83.7 pins jsonschema==4.23.0 and python-dotenv==1.0.1; overrides keep
+# resolution aligned with our direct deps (see dependency-groups / CI lock checks).
+override-dependencies = [
+    "jsonschema>=4.25.1",
+    "python-dotenv==1.2.2",
+    "pyarrow>=18.0.0",
+    "cryptography>=48.0.1,<50.0.0",
+ ]
 
 [dependency-groups]
 
@@ -196,10 +204,7 @@ storage = [
 ############################################################
 # [ Tools ] dependency group
 ############################################################
-tools = [
-    "cloudscraper~=1.2.71",
-    "nltk~=3.9.4",
-]
+tools = ["cloudscraper~=1.2.71", "nltk~=3.9.1"]
 
 ############################################################
 # [ VDB ] dependency group

api/services/account_service.py

@@ -5,11 +5,12 @@ import secrets
 import uuid
 from datetime import UTC, datetime, timedelta
 from hashlib import sha256
-from typing import Any, cast
+from typing import Any, TypedDict, cast
 
-from pydantic import BaseModel
-from sqlalchemy import func, select
-from sqlalchemy.orm import Session
+from pydantic import BaseModel, TypeAdapter
+from sqlalchemy import delete, func, select, update
+
+from core.db.session_factory import session_factory
 from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
@@ -74,6 +75,15 @@ from tasks.mail_reset_password_task import (
 logger = logging.getLogger(__name__)
 
 
+class InvitationData(TypedDict):
+    account_id: str
+    email: str
+    workspace_id: str
+
+
+_invitation_adapter: TypeAdapter[InvitationData] = TypeAdapter(InvitationData)
+
+
 def _try_join_enterprise_default_workspace(account_id: str) -> None:
     """Best-effort join to enterprise default workspace."""
     if not dify_config.ENTERPRISE_ENABLED:
@@ -777,19 +787,19 @@ class AccountService:
         return token
 
     @staticmethod
-    def get_account_by_email_with_case_fallback(email: str, session: Session | None = None) -> Account | None:
+    def get_account_by_email_with_case_fallback(email: str) -> Account | None:
         """
         Retrieve an account by email and fall back to the lowercase email if the original lookup fails.
 
         This keeps backward compatibility for older records that stored uppercase emails while the
         rest of the system gradually normalizes new inputs.
         """
-        query_session = session or db.session
-        account = query_session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
-        if account or email == email.lower():
-            return account
+        with session_factory.create_session() as session:
+            account = session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
+            if account or email == email.lower():
+                return account
 
-        return query_session.execute(select(Account).filter_by(email=email.lower())).scalar_one_or_none()
+            return session.execute(select(Account).filter_by(email=email.lower())).scalar_one_or_none()
 
     @classmethod
     def get_email_code_login_data(cls, token: str) -> dict[str, Any] | None:
@@ -1460,8 +1470,7 @@ class RegisterService:
 
         check_workspace_member_invite_permission(tenant.id)
 
-        with Session(db.engine) as session:
-            account = AccountService.get_account_by_email_with_case_fallback(email, session=session)
+        account = AccountService.get_account_by_email_with_case_fallback(email)
 
         if not account:
             TenantService.check_member_permission(tenant, inviter, None, "add")

api/services/enterprise/enterprise_service.py

@@ -5,6 +5,7 @@ import uuid
 from datetime import datetime
 from typing import TYPE_CHECKING
 
+from cachetools.func import ttl_cache
 from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 from configs import dify_config
@@ -98,7 +99,9 @@ def try_join_default_workspace(account_id: str) -> None:
 
 
 class EnterpriseService:
+
     @classmethod
+    @ttl_cache(ttl=5)
     def get_info(cls):
         return EnterpriseRequest.send_request("GET", "/info")
 

api/services/file_service.py

@@ -173,12 +173,14 @@ class FileService:
 
         return upload_file
 
-    def get_file_preview(self, file_id: str):
+    def get_file_preview(self, file_id: str, tenant_id: str):
         """
         Return a short text preview extracted from a document file.
         """
         with self._session_maker(expire_on_commit=False) as session:
-            upload_file = session.query(UploadFile).where(UploadFile.id == file_id).first()
+            upload_file = session.scalar(
+                select(UploadFile).where(UploadFile.id == file_id, UploadFile.tenant_id == tenant_id).limit(1)
+            )
 
         if not upload_file:
             raise NotFound("File not found")

api/services/tools/builtin_tools_manage_service.py

@@ -406,7 +406,7 @@ class BuiltinToolManageService:
         return {"result": "success"}
 
     @staticmethod
-    def set_default_provider(tenant_id: str, user_id: str, provider: str, id: str):
+    def set_default_provider(tenant_id: str, provider: str, id: str):
         """
         set default provider
         """
@@ -416,9 +416,9 @@ class BuiltinToolManageService:
             if target_provider is None:
                 raise ValueError("provider not found")
 
-            # clear default provider
+            # clear default provider (tenant-scoped: only one default per provider per workspace)
             session.query(BuiltinToolProvider).filter_by(
-                tenant_id=tenant_id, user_id=user_id, provider=provider, is_default=True
+                tenant_id=tenant_id, provider=provider, is_default=True
             ).update({"is_default": False})
 
             # set new default provider

api/tests/test_containers_integration_tests/controllers/console/auth/test_email_register.py

@@ -158,7 +158,10 @@ def test_get_account_by_email_with_case_fallback_falls_back_to_lowercase():
     second_result.scalar_one_or_none.return_value = expected_account
     mock_session.execute.side_effect = [first_result, second_result]
 
-    result = AccountService.get_account_by_email_with_case_fallback("Case@Test.com", session=mock_session)
+    with patch("services.account_service.session_factory") as mock_factory:
+        mock_factory.create_session.return_value.__enter__ = MagicMock(return_value=mock_session)
+        mock_factory.create_session.return_value.__exit__ = MagicMock(return_value=False)
+        result = AccountService.get_account_by_email_with_case_fallback("Case@Test.com")
 
     assert result is expected_account
     assert mock_session.execute.call_count == 2

api/tests/test_containers_integration_tests/controllers/console/auth/test_forgot_password.py

@@ -113,12 +113,14 @@ class TestForgotPasswordCheckApi:
 class TestForgotPasswordResetApi:
     @patch("controllers.console.auth.forgot_password.ForgotPasswordResetApi._update_existing_account")
     @patch("controllers.console.auth.forgot_password.AccountService.get_account_by_email_with_case_fallback")
+    @patch("controllers.console.auth.forgot_password.db")
     @patch("controllers.console.auth.forgot_password.AccountService.revoke_reset_password_token")
     @patch("controllers.console.auth.forgot_password.AccountService.get_reset_password_data")
     def test_reset_fetches_account_with_original_email(
         self,
         mock_get_reset_data,
         mock_revoke_token,
+        mock_db,
         mock_get_account,
         mock_update_account,
         app,
@@ -126,6 +128,7 @@ class TestForgotPasswordResetApi:
         mock_get_reset_data.return_value = {"phase": "reset", "email": "User@Example.com"}
         mock_account = MagicMock()
         mock_get_account.return_value = mock_account
+        mock_db.session.merge.return_value = mock_account
 
         wraps_features = SimpleNamespace(enable_email_password_login=True)
         with (
@@ -161,7 +164,10 @@ def test_get_account_by_email_with_case_fallback_falls_back_to_lowercase():
     second_result.scalar_one_or_none.return_value = expected_account
     mock_session.execute.side_effect = [first_result, second_result]
 
-    result = AccountService.get_account_by_email_with_case_fallback("Mixed@Test.com", session=mock_session)
+    with patch("services.account_service.session_factory") as mock_factory:
+        mock_factory.create_session.return_value.__enter__ = MagicMock(return_value=mock_session)
+        mock_factory.create_session.return_value.__exit__ = MagicMock(return_value=False)
+        result = AccountService.get_account_by_email_with_case_fallback("Mixed@Test.com")
 
     assert result is expected_account
     assert mock_session.execute.call_count == 2

api/tests/test_containers_integration_tests/controllers/console/auth/test_oauth.py

@@ -437,7 +437,10 @@ class TestAccountGeneration:
         second_result.scalar_one_or_none.return_value = expected_account
         mock_session.execute.side_effect = [first_result, second_result]
 
-        result = AccountService.get_account_by_email_with_case_fallback("Case@Test.com", session=mock_session)
+        with patch("services.account_service.session_factory") as mock_factory:
+            mock_factory.create_session.return_value.__enter__ = MagicMock(return_value=mock_session)
+            mock_factory.create_session.return_value.__exit__ = MagicMock(return_value=False)
+            result = AccountService.get_account_by_email_with_case_fallback("Case@Test.com")
 
         assert result is expected_account
         assert mock_session.execute.call_count == 2

api/tests/test_containers_integration_tests/controllers/console/auth/test_password_reset.py

@@ -335,10 +335,12 @@ class TestForgotPasswordResetApi:
     @patch("controllers.console.auth.forgot_password.AccountService.get_reset_password_data")
     @patch("controllers.console.auth.forgot_password.AccountService.revoke_reset_password_token")
     @patch("controllers.console.auth.forgot_password.AccountService.get_account_by_email_with_case_fallback")
+    @patch("controllers.console.auth.forgot_password.db")
     @patch("controllers.console.auth.forgot_password.TenantService.get_join_tenants")
     def test_reset_password_success(
         self,
         mock_get_tenants,
+        mock_db,
         mock_get_account,
         mock_revoke_token,
         mock_get_data,
@@ -356,6 +358,7 @@ class TestForgotPasswordResetApi:
         # Arrange
         mock_get_data.return_value = {"email": "test@example.com", "phase": "reset"}
         mock_get_account.return_value = mock_account
+        mock_db.session.merge.return_value = mock_account
         mock_get_tenants.return_value = [MagicMock()]
 
         # Act

api/tests/test_containers_integration_tests/services/test_file_service.py

@@ -514,7 +514,7 @@ class TestFileService:
 
         db_session_with_containers.commit()
 
-        result = FileService(engine).get_file_preview(file_id=upload_file.id)
+        result = FileService(engine).get_file_preview(file_id=upload_file.id, tenant_id=upload_file.tenant_id)
 
         assert result == "extracted text content"
         mock_external_service_dependencies["extract_processor"].load_from_upload_file.assert_called_once()
@@ -529,7 +529,7 @@ class TestFileService:
         non_existent_id = str(fake.uuid4())
 
         with pytest.raises(NotFound, match="File not found"):
-            FileService(engine).get_file_preview(file_id=non_existent_id)
+            FileService(engine).get_file_preview(file_id=non_existent_id, tenant_id=str(fake.uuid4()))
 
     def test_get_file_preview_unsupported_file_type(
         self, db_session_with_containers: Session, engine, mock_external_service_dependencies
@@ -549,7 +549,7 @@ class TestFileService:
         db_session_with_containers.commit()
 
         with pytest.raises(UnsupportedFileTypeError):
-            FileService(engine).get_file_preview(file_id=upload_file.id)
+            FileService(engine).get_file_preview(file_id=upload_file.id, tenant_id=upload_file.tenant_id)
 
     def test_get_file_preview_text_truncation(
         self, db_session_with_containers: Session, engine, mock_external_service_dependencies
@@ -572,7 +572,7 @@ class TestFileService:
         long_text = "x" * 5000  # Longer than PREVIEW_WORDS_LIMIT
         mock_external_service_dependencies["extract_processor"].load_from_upload_file.return_value = long_text
 
-        result = FileService(engine).get_file_preview(file_id=upload_file.id)
+        result = FileService(engine).get_file_preview(file_id=upload_file.id, tenant_id=upload_file.tenant_id)
 
         assert len(result) == 3000  # PREVIEW_WORDS_LIMIT
         assert result == "x" * 3000

api/tests/test_containers_integration_tests/services/test_webapp_auth_service.py

@@ -233,11 +233,10 @@ class TestWebAppAuthService:
         assert result.status == AccountStatus.ACTIVE
 
         # Verify database state
-
-        db_session_with_containers.refresh(result)
-        assert result.id is not None
-        assert result.password is not None
-        assert result.password_salt is not None
+        refreshed = db_session_with_containers.get(Account, result.id)
+        assert refreshed is not None
+        assert refreshed.password is not None
+        assert refreshed.password_salt is not None
 
     def test_authenticate_account_not_found(
         self, db_session_with_containers: Session, mock_external_service_dependencies
@@ -414,9 +413,8 @@ class TestWebAppAuthService:
         assert result.status == AccountStatus.ACTIVE
 
         # Verify database state
-
-        db_session_with_containers.refresh(result)
-        assert result.id is not None
+        refreshed = db_session_with_containers.get(Account, result.id)
+        assert refreshed is not None
 
     def test_get_user_through_email_not_found(
         self, db_session_with_containers: Session, mock_external_service_dependencies

api/tests/unit_tests/controllers/console/app/test_app_apis.py

@@ -274,7 +274,7 @@ class TestOpsTraceEndpoints:
         )
 
         with app.test_request_context("/?tracing_provider=langfuse"):
-            result = method(app_id="app-1")
+            result = method(app_model=MagicMock(id="app-1"))
 
         assert result == {"has_not_configured": True}
 
@@ -293,7 +293,7 @@ class TestOpsTraceEndpoints:
             json={"tracing_provider": "langfuse", "tracing_config": {"api_key": "k"}},
         ):
             with pytest.raises(BadRequest):
-                method(app_id="app-1")
+                method(app_model=MagicMock(id="app-1"))
 
     def test_trace_app_config_delete_not_found(self, app, monkeypatch):
         api = ops_trace_module.TraceAppConfigApi()
@@ -307,7 +307,7 @@ class TestOpsTraceEndpoints:
 
         with app.test_request_context("/?tracing_provider=langfuse"):
             with pytest.raises(BadRequest):
-                method(app_id="app-1")
+                method(app_model=MagicMock(id="app-1"))
 
 
 # ========== Site Tests ==========

api/tests/unit_tests/controllers/console/test_files.py

@@ -278,7 +278,7 @@ class TestFileApiPost:
 
 
 class TestFilePreviewApi:
-    def test_get_preview(self, app, mock_file_service):
+    def test_get_preview(self, app, mock_account_context, mock_file_service):
         api = FilePreviewApi()
         get_method = unwrap(api.get)
         mock_file_service.get_file_preview.return_value = "preview text"

api/tests/unit_tests/controllers/console/test_workspace_account.py

@@ -233,15 +233,20 @@ class TestCheckEmailUnique:
 
 
 def test_get_account_by_email_with_case_fallback_uses_lowercase_lookup():
-    session = MagicMock()
+    mock_session = MagicMock()
     first = MagicMock()
     first.scalar_one_or_none.return_value = None
     second = MagicMock()
     expected_account = MagicMock()
     second.scalar_one_or_none.return_value = expected_account
-    session.execute.side_effect = [first, second]
+    mock_session.execute.side_effect = [first, second]
 
-    result = AccountService.get_account_by_email_with_case_fallback("Mixed@Test.com", session=session)
+    mock_factory = MagicMock()
+    mock_factory.create_session.return_value.__enter__ = MagicMock(return_value=mock_session)
+    mock_factory.create_session.return_value.__exit__ = MagicMock(return_value=False)
+
+    with patch("services.account_service.session_factory", mock_factory):
+        result = AccountService.get_account_by_email_with_case_fallback("Mixed@Test.com")
 
     assert result is expected_account
-    assert session.execute.call_count == 2
+    assert mock_session.execute.call_count == 2

api/tests/unit_tests/controllers/web/test_web_forgot_password.py

@@ -37,10 +37,8 @@ class TestForgotPasswordSendEmailApi:
     @patch("controllers.web.forgot_password.AccountService.get_account_by_email_with_case_fallback")
     @patch("controllers.web.forgot_password.AccountService.is_email_send_ip_limit", return_value=False)
     @patch("controllers.web.forgot_password.extract_remote_ip", return_value="127.0.0.1")
-    @patch("controllers.web.forgot_password.Session")
     def test_should_normalize_email_before_sending(
         self,
-        mock_session_cls,
         mock_extract_ip,
         mock_rate_limit,
         mock_get_account,
@@ -50,19 +48,16 @@ class TestForgotPasswordSendEmailApi:
         mock_account = MagicMock()
         mock_get_account.return_value = mock_account
         mock_send_mail.return_value = "token-123"
-        mock_session = MagicMock()
-        mock_session_cls.return_value.__enter__.return_value = mock_session
 
-        with patch("controllers.web.forgot_password.db", SimpleNamespace(engine="engine")):
-            with app.test_request_context(
-                "/web/forgot-password",
-                method="POST",
-                json={"email": "User@Example.com", "language": "zh-Hans"},
-            ):
-                response = ForgotPasswordSendEmailApi().post()
+        with app.test_request_context(
+            "/web/forgot-password",
+            method="POST",
+            json={"email": "User@Example.com", "language": "zh-Hans"},
+        ):
+            response = ForgotPasswordSendEmailApi().post()
 
         assert response == {"result": "success", "data": "token-123"}
-        mock_get_account.assert_called_once_with("User@Example.com", session=mock_session)
+        mock_get_account.assert_called_once_with("User@Example.com")
         mock_send_mail.assert_called_once_with(account=mock_account, email="user@example.com", language="zh-Hans")
         mock_extract_ip.assert_called_once()
         mock_rate_limit.assert_called_once_with("127.0.0.1")
@@ -145,14 +140,14 @@ class TestForgotPasswordCheckApi:
 class TestForgotPasswordResetApi:
     @patch("controllers.web.forgot_password.ForgotPasswordResetApi._update_existing_account")
     @patch("controllers.web.forgot_password.AccountService.get_account_by_email_with_case_fallback")
-    @patch("controllers.web.forgot_password.Session")
+    @patch("controllers.web.forgot_password.db")
     @patch("controllers.web.forgot_password.AccountService.revoke_reset_password_token")
     @patch("controllers.web.forgot_password.AccountService.get_reset_password_data")
     def test_should_fetch_account_with_fallback(
         self,
         mock_get_reset_data,
         mock_revoke_token,
-        mock_session_cls,
+        mock_db,
         mock_get_account,
         mock_update_account,
         app,
@@ -160,29 +155,27 @@ class TestForgotPasswordResetApi:
         mock_get_reset_data.return_value = {"phase": "reset", "email": "User@Example.com", "code": "1234"}
         mock_account = MagicMock()
         mock_get_account.return_value = mock_account
-        mock_session = MagicMock()
-        mock_session_cls.return_value.__enter__.return_value = mock_session
+        mock_db.session.merge.return_value = mock_account
 
-        with patch("controllers.web.forgot_password.db", SimpleNamespace(engine="engine")):
-            with app.test_request_context(
-                "/web/forgot-password/resets",
-                method="POST",
-                json={
-                    "token": "token-123",
-                    "new_password": "ValidPass123!",
-                    "password_confirm": "ValidPass123!",
-                },
-            ):
-                response = ForgotPasswordResetApi().post()
+        with app.test_request_context(
+            "/web/forgot-password/resets",
+            method="POST",
+            json={
+                "token": "token-123",
+                "new_password": "ValidPass123!",
+                "password_confirm": "ValidPass123!",
+            },
+        ):
+            response = ForgotPasswordResetApi().post()
 
         assert response == {"result": "success"}
-        mock_get_account.assert_called_once_with("User@Example.com", session=mock_session)
+        mock_get_account.assert_called_once_with("User@Example.com")
         mock_update_account.assert_called_once()
         mock_revoke_token.assert_called_once_with("token-123")
 
     @patch("controllers.web.forgot_password.hash_password", return_value=b"hashed-value")
     @patch("controllers.web.forgot_password.secrets.token_bytes", return_value=b"0123456789abcdef")
-    @patch("controllers.web.forgot_password.Session")
+    @patch("controllers.web.forgot_password.db")
     @patch("controllers.web.forgot_password.AccountService.revoke_reset_password_token")
     @patch("controllers.web.forgot_password.AccountService.get_reset_password_data")
     @patch("controllers.web.forgot_password.AccountService.get_account_by_email_with_case_fallback")
@@ -191,7 +184,7 @@ class TestForgotPasswordResetApi:
         mock_get_account,
         mock_get_reset_data,
         mock_revoke_token,
-        mock_session_cls,
+        mock_db,
         mock_token_bytes,
         mock_hash_password,
         app,
@@ -199,20 +192,18 @@ class TestForgotPasswordResetApi:
         mock_get_reset_data.return_value = {"phase": "reset", "email": "user@example.com"}
         account = MagicMock()
         mock_get_account.return_value = account
-        mock_session = MagicMock()
-        mock_session_cls.return_value.__enter__.return_value = mock_session
+        mock_db.session.merge.return_value = account
 
-        with patch("controllers.web.forgot_password.db", SimpleNamespace(engine="engine")):
-            with app.test_request_context(
-                "/web/forgot-password/resets",
-                method="POST",
-                json={
-                    "token": "reset-token",
-                    "new_password": "StrongPass123!",
-                    "password_confirm": "StrongPass123!",
-                },
-            ):
-                response = ForgotPasswordResetApi().post()
+        with app.test_request_context(
+            "/web/forgot-password/resets",
+            method="POST",
+            json={
+                "token": "reset-token",
+                "new_password": "StrongPass123!",
+                "password_confirm": "StrongPass123!",
+            },
+        ):
+            response = ForgotPasswordResetApi().post()
 
         assert response == {"result": "success"}
         mock_get_reset_data.assert_called_once_with("reset-token")
@@ -223,4 +214,4 @@ class TestForgotPasswordResetApi:
         assert account.password == expected_password
         expected_salt = base64.b64encode(b"0123456789abcdef").decode()
         assert account.password_salt == expected_salt
-        mock_session.commit.assert_called_once()
+        mock_db.session.commit.assert_called_once()

api/tests/unit_tests/core/app/apps/advanced_chat/test_generate_task_pipeline_core.py

@@ -173,7 +173,7 @@ class TestAdvancedChatGenerateTaskPipeline:
 
         @contextmanager
         def _fake_session():
-            yield SimpleNamespace()
+            yield SimpleNamespace(execute=lambda *args, **kwargs: None)
 
         monkeypatch.setattr(pipeline, "_database_session", _fake_session)
         monkeypatch.setattr(pipeline, "_get_message", lambda **kwargs: SimpleNamespace())
@@ -479,7 +479,7 @@ class TestAdvancedChatGenerateTaskPipeline:
         assert list(pipeline._handle_human_input_form_timeout_event(timeout_event)) == ["timeout"]
         assert persisted == ["saved"]
 
-    def test_save_message_strips_markdown_and_sets_usage(self):
+    def test_save_message_preserves_full_answer_and_sets_usage(self):
         pipeline = _make_pipeline()
         pipeline._recorded_files = [
             {
@@ -489,7 +489,8 @@ class TestAdvancedChatGenerateTaskPipeline:
                 "related_id": "file-id",
             }
         ]
-        pipeline._task_state.answer = "![img](url) hello"
+        # The answer is stored verbatim; markdown image links are never stripped.
+        pipeline._task_state.answer = "![img](http://example.com/file.png) hello ![inline](http://llm.com/img.jpg)"
         pipeline._task_state.is_streaming_response = True
         pipeline._task_state.first_token_time = pipeline._base_task_pipeline.start_at + 0.1
         pipeline._task_state.last_token_time = pipeline._base_task_pipeline.start_at + 0.2
@@ -529,7 +530,7 @@ class TestAdvancedChatGenerateTaskPipeline:
         pipeline._save_message(session=_Session(), graph_runtime_state=graph_runtime_state)
 
         assert message.status == MessageStatus.NORMAL
-        assert message.answer == "hello"
+        assert message.answer == "![img](http://example.com/file.png) hello ![inline](http://llm.com/img.jpg)"
         assert message.message_metadata
 
     def test_handle_stop_event_saves_message_for_moderation(self, monkeypatch):

api/tests/unit_tests/core/app/apps/test_advanced_chat_app_generator.py

@@ -11,8 +11,10 @@ from core.app.apps.advanced_chat.app_generator import AdvancedChatAppGenerator
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
 from core.app.task_pipeline import message_cycle_manager
 from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
+from core.ops.ops_trace_manager import TraceQueueManager
 from models.enums import ConversationFromSource
 from models.model import AppMode, Conversation, Message
+from services.errors.conversation import ConversationNotExistsError
 
 
 def _make_app_config() -> WorkflowUIBasedAppConfig:
@@ -108,6 +110,75 @@ def test_init_generate_records_marks_existing_conversation():
     assert entity.is_new_conversation is False
 
 
+def test_generate_falls_back_to_new_conversation_when_conversation_missing(monkeypatch: pytest.MonkeyPatch):
+    app_config = _make_app_config()
+    workflow = SimpleNamespace(
+        features_dict={},
+        tenant_id="tenant-id",
+        app_id="app-id",
+        id="workflow-id",
+    )
+    app_model = SimpleNamespace(id="app-id", tenant_id="tenant-id")
+    user = SimpleNamespace(id="user-id", session_id="session-id")
+
+    def raise_conversation_not_exists(**_kwargs):
+        raise ConversationNotExistsError()
+
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.ConversationService.get_conversation",
+        raise_conversation_not_exists,
+    )
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.FileUploadConfigManager.convert",
+        lambda *_args, **_kwargs: None,
+    )
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.AdvancedChatAppConfigManager.get_app_config",
+        lambda **_kwargs: app_config,
+    )
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.db",
+        SimpleNamespace(engine=object()),
+    )
+    trace_manager = object.__new__(TraceQueueManager)
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.TraceQueueManager",
+        lambda **_kwargs: trace_manager,
+    )
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.DifyCoreRepositoryFactory.create_workflow_execution_repository",
+        lambda **_kwargs: SimpleNamespace(),
+    )
+    monkeypatch.setattr(
+        "core.app.apps.advanced_chat.app_generator.DifyCoreRepositoryFactory.create_workflow_node_execution_repository",
+        lambda **_kwargs: SimpleNamespace(),
+    )
+
+    captured: dict[str, object] = {}
+
+    def fake_generate(self, **kwargs):
+        captured.update(kwargs)
+        return {"status": "ok"}
+
+    monkeypatch.setattr(AdvancedChatAppGenerator, "_generate", fake_generate)
+
+    result = AdvancedChatAppGenerator().generate(
+        app_model=app_model,
+        workflow=workflow,
+        user=user,
+        args={"inputs": {}, "query": "hello", "conversation_id": "missing-conversation-id"},
+        invoke_from=InvokeFrom.SERVICE_API,
+        workflow_run_id="workflow-run-id",
+        streaming=False,
+    )
+
+    assert result == {"status": "ok"}
+    assert captured["conversation"] is None
+    application_generate_entity = captured["application_generate_entity"]
+    assert isinstance(application_generate_entity, AdvancedChatAppGenerateEntity)
+    assert application_generate_entity.conversation_id is None
+
+
 def test_message_cycle_manager_uses_new_conversation_flag(monkeypatch):
     app_config = _make_app_config()
     entity = _make_generate_entity(app_config)

api/tests/unit_tests/core/helper/test_ssrf_proxy.py

@@ -1,9 +1,11 @@
-from unittest.mock import MagicMock, patch
+from unittest.mock import ANY, MagicMock, call, patch
 
 import pytest
 
 from core.helper.ssrf_proxy import (
     SSRF_DEFAULT_MAX_RETRIES,
+    SSRFProxy,
+    _build_ssrf_client,
     _get_user_provided_host_header,
     make_request,
 )
@@ -35,6 +37,34 @@ def test_retry_exceed_max_retries(mock_get_client):
     assert str(e.value) == f"Reached maximum retries ({SSRF_DEFAULT_MAX_RETRIES - 1}) for URL http://example.com"
 
 
+def test_build_ssrf_client_passes_ssl_verify_to_proxy_mount_transports():
+    mock_client = MagicMock()
+    http_transport = MagicMock()
+    https_transport = MagicMock()
+
+    with (
+        patch("core.helper.ssrf_proxy.dify_config.SSRF_PROXY_ALL_URL", None),
+        patch("core.helper.ssrf_proxy.dify_config.SSRF_PROXY_HTTP_URL", "http://proxy.example.com:8080"),
+        patch("core.helper.ssrf_proxy.dify_config.SSRF_PROXY_HTTPS_URL", "http://proxy.example.com:8443"),
+        patch("core.helper.ssrf_proxy.httpx.HTTPTransport", side_effect=[http_transport, https_transport]) as transport,
+        patch("core.helper.ssrf_proxy.httpx.Client", return_value=mock_client) as client,
+    ):
+        ssrf_client = _build_ssrf_client(verify=False)
+
+    assert ssrf_client is mock_client
+    transport.assert_has_calls(
+        [
+            call(proxy="http://proxy.example.com:8080", verify=False),
+            call(proxy="http://proxy.example.com:8443", verify=False),
+        ],
+    )
+    client.assert_called_once_with(
+        mounts={"http://": http_transport, "https://": https_transport},
+        verify=False,
+        limits=ANY,
+    )
+
+
 class TestGetUserProvidedHostHeader:
     """Tests for _get_user_provided_host_header function."""
 

api/tests/unit_tests/core/plugin/impl/test_base_client_impl.py

@@ -1,10 +1,11 @@
 import json
+from urllib.parse import quote
 
 import pytest
 
 from core.plugin.endpoint.exc import EndpointSetupFailedError
 from core.plugin.entities.plugin_daemon import PluginDaemonInnerError
-from core.plugin.impl.base import BasePluginClient
+from core.plugin.impl.base import PLUGIN_DAEMON_MAX_PATH_LENGTH, BasePluginClient
 from core.trigger.errors import (
     EventIgnoreError,
     TriggerInvokeError,
@@ -66,6 +67,36 @@ class TestBasePluginClientImpl:
         assert result == ["hello", "world"]
         assert stream_mock.call_args.kwargs["data"] == {"k": "v"}
 
+    @pytest.mark.parametrize(
+        "path",
+        [
+            "plugin/tenant/%252e%252e%252ftarget",
+            "plugin/tenant/%2e%2e%252ftarget",
+        ],
+    )
+    def test_prepare_request_rejects_encoded_traversal_with_encoded_separator(self, path: str):
+        client = BasePluginClient()
+
+        with pytest.raises(ValueError, match="traversal sequence detected"):
+            client._prepare_request(path, None, None, None, None)
+
+    def test_prepare_request_rejects_path_exceeding_max_length(self):
+        client = BasePluginClient()
+        path = "a" * (PLUGIN_DAEMON_MAX_PATH_LENGTH + 1)
+
+        with pytest.raises(ValueError, match="path length exceeds"):
+            client._prepare_request(path, None, None, None, None)
+
+    def test_prepare_request_rejects_excessively_encoded_path(self):
+        client = BasePluginClient()
+        segment = "..%2Ftarget"
+        for _ in range(9):
+            segment = quote(segment, safe="")
+        path = f"plugin/tenant/{segment}"
+
+        with pytest.raises(ValueError, match="too deeply encoded"):
+            client._prepare_request(path, None, None, None, None)
+
     def test_request_with_plugin_daemon_response_handles_request_exception(self, mocker):
         client = BasePluginClient()
         mocker.patch.object(client, "_request", side_effect=RuntimeError("boom"))

api/tests/unit_tests/core/rag/datasource/test_datasource_retrieval.py

@@ -1034,7 +1034,7 @@ class TestRetrievalServiceInternals:
         assert any(doc.metadata["doc_id"] == "processed-doc" for doc in all_documents)
         processor_instance.invoke.assert_called_once()
 
-    @patch("core.rag.datasource.retrieval_service.sign_upload_file", return_value="signed://file")
+    @patch("core.rag.datasource.retrieval_service.sign_upload_file_preview_url", return_value="signed://file")
     def test_get_segment_attachment_info_success(self, mock_sign):
         upload_file = SimpleNamespace(
             id="upload-1",
@@ -1124,7 +1124,7 @@ class TestRetrievalServiceInternals:
 
         assert result == []
 
-    @patch("core.rag.datasource.retrieval_service.sign_upload_file", return_value="signed://file")
+    @patch("core.rag.datasource.retrieval_service.sign_upload_file_preview_url", return_value="signed://file")
     def test_get_segment_attachment_infos_success(self, mock_sign):
         upload_file_1 = SimpleNamespace(
             id="upload-1",

api/tests/unit_tests/core/rag/datasource/vdb/myscale/test_myscale_vector.py

@@ -181,14 +181,41 @@ def test_text_exists_and_metadata_operations(myscale_module):
     vector = myscale_module.MyScaleVector("collection_1", _config(myscale_module))
     vector._client.query.return_value = SimpleNamespace(row_count=1, result_rows=[("id-1",), ("id-2",)])
 
-    assert vector.text_exists("id-1") is True
-    assert vector.get_ids_by_metadata_field("document_id", "doc-1") == ["id-1", "id-2"]
+    assert vector.text_exists("id-1' OR '1'='1") is True
+    text_exists_call = vector._client.query.call_args
+    assert "id={id:String}" in text_exists_call.args[0]
+    assert "id-1' OR '1'='1" not in text_exists_call.args[0]
+    assert text_exists_call.kwargs["parameters"] == {"id": "id-1' OR '1'='1"}
+
+    assert vector.get_ids_by_metadata_field("document_id", "doc-1' OR '1'='1") == ["id-1", "id-2"]
+    metadata_query_call = vector._client.query.call_args
+    assert "metadata.document_id={value:String}" in metadata_query_call.args[0]
+    assert "doc-1' OR '1'='1" not in metadata_query_call.args[0]
+    assert metadata_query_call.kwargs["parameters"] == {"value": "doc-1' OR '1'='1"}
 
     vector.delete_by_ids(["id-1", "id-2"])
-    vector.delete_by_metadata_field("document_id", "doc-1")
+    delete_ids_call = vector._client.command.call_args
+    assert "id IN {ids:Array(String)}" in delete_ids_call.args[0]
+    assert delete_ids_call.kwargs["parameters"] == {"ids": ["id-1", "id-2"]}
+
+    vector.delete_by_metadata_field("document_id", "doc-1' OR '1'='1")
+    delete_metadata_call = vector._client.command.call_args
+    assert "metadata.document_id={value:String}" in delete_metadata_call.args[0]
+    assert "doc-1' OR '1'='1" not in delete_metadata_call.args[0]
+    assert delete_metadata_call.kwargs["parameters"] == {"value": "doc-1' OR '1'='1"}
     assert vector._client.command.call_count >= 2
 
 
+def test_metadata_operations_reject_invalid_key(myscale_module):
+    vector = myscale_module.MyScaleVector("collection_1", _config(myscale_module))
+
+    with pytest.raises(ValueError, match="metadata key must be a valid identifier"):
+        vector.get_ids_by_metadata_field("document_id) OR 1=1 --", "doc-1")
+
+    with pytest.raises(ValueError, match="metadata key must be a valid identifier"):
+        vector.delete_by_metadata_field("document_id) OR 1=1 --", "doc-1")
+
+
 def test_search_delegation_methods(myscale_module):
     vector = myscale_module.MyScaleVector("collection_1", _config(myscale_module))
     vector._search = MagicMock(return_value=["result"])
@@ -199,6 +226,28 @@ def test_search_delegation_methods(myscale_module):
     assert result_vector == ["result"]
     assert result_text == ["result"]
     assert vector._search.call_count == 2
+    vector._search.assert_any_call(
+        "TextSearch('enable_nlq=false')(text, {query:String})",
+        myscale_module.SortOrder.DESC,
+        parameters={"query": "hello"},
+        top_k=2,
+    )
+
+
+def test_search_by_full_text_uses_query_parameters(myscale_module):
+    vector = myscale_module.MyScaleVector("collection_1", _config(myscale_module))
+    vector._client.query.return_value = SimpleNamespace(
+        named_results=lambda: [{"text": "doc", "vector": [0.1], "metadata": {"doc_id": "1"}}]
+    )
+    payload = "x') AS dist FROM dify.collection_1 UNION ALL SELECT secret FROM users --"
+
+    docs = vector.search_by_full_text(payload, top_k=2)
+
+    assert len(docs) == 1
+    sql = vector._client.query.call_args.args[0]
+    assert payload not in sql
+    assert "TextSearch('enable_nlq=false')(text, {query:String})" in sql
+    assert vector._client.query.call_args.kwargs["parameters"] == {"query": payload}
 
 
 def test_search_with_document_filter_and_exception(myscale_module):
@@ -215,7 +264,8 @@ def test_search_with_document_filter_and_exception(myscale_module):
     )
     assert len(docs) == 1
     sql = vector._client.query.call_args.args[0]
-    assert "metadata['document_id'] in ('doc-1', 'doc-2')" in sql
+    assert "WHERE metadata['document_id'] IN {document_ids_filter:Array(String)}" in sql
+    assert vector._client.query.call_args.kwargs["parameters"] == {"document_ids_filter": ["doc-1", "doc-2"]}
 
     vector._client.query.side_effect = RuntimeError("boom")
     assert vector._search("distance(vector, [0.1])", myscale_module.SortOrder.ASC, top_k=1) == []

api/tests/unit_tests/core/rag/retrieval/test_dataset_retrieval.py

@@ -4410,7 +4410,7 @@ class TestRetrieveCoverage:
                 "core.rag.retrieval.dataset_retrieval.RetrievalService.format_retrieval_documents",
                 return_value=[record],
             ),
-            patch("core.rag.retrieval.dataset_retrieval.sign_upload_file", return_value="https://signed"),
+            patch("core.rag.retrieval.dataset_retrieval.sign_upload_file_preview_url", return_value="https://signed"),
             patch("core.rag.retrieval.dataset_retrieval.db.session.execute") as mock_execute,
         ):
             mock_model_manager.return_value.get_model_instance.return_value = Mock()

api/tests/unit_tests/core/tools/test_signature.py

@@ -6,7 +6,11 @@ from urllib.parse import parse_qs, urlparse
 
 import pytest
 
-from core.tools.signature import sign_tool_file, sign_upload_file, verify_tool_file_signature
+from core.tools.signature import (
+    sign_tool_file,
+    sign_upload_file_preview_url,
+    verify_tool_file_signature,
+)
 
 
 def test_sign_tool_file_and_verify_roundtrip(monkeypatch: pytest.MonkeyPatch) -> None:
@@ -83,32 +87,32 @@ def test_verify_tool_file_signature_rejects_expired_signature(monkeypatch: pytes
     assert verify_tool_file_signature("tool-file-id", timestamp, nonce, sign) is False
 
 
-def test_sign_upload_file_prefers_internal_url(monkeypatch: pytest.MonkeyPatch) -> None:
+def test_sign_upload_file_preview_url_uses_files_url(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setattr("core.tools.signature.time.time", lambda: 1700000000)
     monkeypatch.setattr("core.tools.signature.os.urandom", lambda _: b"\x03" * 16)
     monkeypatch.setattr("core.tools.signature.dify_config.SECRET_KEY", "unit-secret")
     monkeypatch.setattr("core.tools.signature.dify_config.FILES_URL", "https://files.example.com")
     monkeypatch.setattr("core.tools.signature.dify_config.INTERNAL_FILES_URL", "https://internal.example.com")
 
-    url = sign_upload_file("upload-id", ".png")
+    url = sign_upload_file_preview_url("upload-id", ".png")
     parsed = urlparse(url)
     query = parse_qs(parsed.query)
 
-    assert parsed.netloc == "internal.example.com"
+    assert parsed.netloc == "files.example.com"
     assert parsed.path == "/files/upload-id/image-preview"
     assert query["timestamp"][0]
     assert query["nonce"][0]
     assert query["sign"][0]
 
 
-def test_sign_upload_file_uses_files_url_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
+def test_sign_upload_file_preview_url_ignores_internal_files_url(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setattr("core.tools.signature.time.time", lambda: 1700000000)
     monkeypatch.setattr("core.tools.signature.os.urandom", lambda _: b"\x05" * 16)
     monkeypatch.setattr("core.tools.signature.dify_config.SECRET_KEY", "unit-secret")
     monkeypatch.setattr("core.tools.signature.dify_config.FILES_URL", "https://files.example.com")
-    monkeypatch.setattr("core.tools.signature.dify_config.INTERNAL_FILES_URL", "")
+    monkeypatch.setattr("core.tools.signature.dify_config.INTERNAL_FILES_URL", "https://internal.example.com")
 
-    url = sign_upload_file("upload-id", ".png")
+    url = sign_upload_file_preview_url("upload-id", ".png")
     parsed = urlparse(url)
     query = parse_qs(parsed.query)
 

api/tests/unit_tests/extensions/test_redis.py

@@ -1,53 +1,125 @@
+from unittest.mock import patch
+
 from redis import RedisError
+from redis.retry import Retry
 
-from extensions.ext_redis import redis_fallback
+from extensions.ext_redis import (
+    _get_base_redis_params,
+    _get_cluster_connection_health_params,
+    _get_connection_health_params,
+    redis_fallback,
+)
 
 
-def test_redis_fallback_success():
-    @redis_fallback(default_return=None)
-    def test_func():
-        return "success"
+class TestGetConnectionHealthParams:
+    @patch("extensions.ext_redis.dify_config")
+    def test_includes_all_health_params(self, mock_config):
+        mock_config.REDIS_RETRY_RETRIES = 3
+        mock_config.REDIS_RETRY_BACKOFF_BASE = 1.0
+        mock_config.REDIS_RETRY_BACKOFF_CAP = 10.0
+        mock_config.REDIS_SOCKET_TIMEOUT = 5.0
+        mock_config.REDIS_SOCKET_CONNECT_TIMEOUT = 5.0
+        mock_config.REDIS_HEALTH_CHECK_INTERVAL = 30
 
-    assert test_func() == "success"
+        params = _get_connection_health_params()
+
+        assert "retry" in params
+        assert "socket_timeout" in params
+        assert "socket_connect_timeout" in params
+        assert "health_check_interval" in params
+        assert isinstance(params["retry"], Retry)
+        assert params["retry"]._retries == 3
+        assert params["socket_timeout"] == 5.0
+        assert params["socket_connect_timeout"] == 5.0
+        assert params["health_check_interval"] == 30
 
 
-def test_redis_fallback_error():
-    @redis_fallback(default_return="fallback")
-    def test_func():
-        raise RedisError("Redis error")
+class TestGetClusterConnectionHealthParams:
+    @patch("extensions.ext_redis.dify_config")
+    def test_excludes_health_check_interval(self, mock_config):
+        mock_config.REDIS_RETRY_RETRIES = 3
+        mock_config.REDIS_RETRY_BACKOFF_BASE = 1.0
+        mock_config.REDIS_RETRY_BACKOFF_CAP = 10.0
+        mock_config.REDIS_SOCKET_TIMEOUT = 5.0
+        mock_config.REDIS_SOCKET_CONNECT_TIMEOUT = 5.0
+        mock_config.REDIS_HEALTH_CHECK_INTERVAL = 30
 
-    assert test_func() == "fallback"
+        params = _get_cluster_connection_health_params()
+
+        assert "retry" in params
+        assert "socket_timeout" in params
+        assert "socket_connect_timeout" in params
+        assert "health_check_interval" not in params
 
 
-def test_redis_fallback_none_default():
-    @redis_fallback()
-    def test_func():
-        raise RedisError("Redis error")
+class TestGetBaseRedisParams:
+    @patch("extensions.ext_redis.dify_config")
+    def test_includes_retry_and_health_params(self, mock_config):
+        mock_config.REDIS_USERNAME = None
+        mock_config.REDIS_PASSWORD = None
+        mock_config.REDIS_DB = 0
+        mock_config.REDIS_SERIALIZATION_PROTOCOL = 3
+        mock_config.REDIS_ENABLE_CLIENT_SIDE_CACHE = False
+        mock_config.REDIS_RETRY_RETRIES = 3
+        mock_config.REDIS_RETRY_BACKOFF_BASE = 1.0
+        mock_config.REDIS_RETRY_BACKOFF_CAP = 10.0
+        mock_config.REDIS_SOCKET_TIMEOUT = 5.0
+        mock_config.REDIS_SOCKET_CONNECT_TIMEOUT = 5.0
+        mock_config.REDIS_HEALTH_CHECK_INTERVAL = 30
 
-    assert test_func() is None
+        params = _get_base_redis_params()
+
+        assert "retry" in params
+        assert isinstance(params["retry"], Retry)
+        assert params["socket_timeout"] == 5.0
+        assert params["socket_connect_timeout"] == 5.0
+        assert params["health_check_interval"] == 30
+        # Existing params still present
+        assert params["db"] == 0
+        assert params["encoding"] == "utf-8"
 
 
-def test_redis_fallback_with_args():
-    @redis_fallback(default_return=0)
-    def test_func(x, y):
-        raise RedisError("Redis error")
+class TestRedisFallback:
+    def test_redis_fallback_success(self):
+        @redis_fallback(default_return=None)
+        def test_func():
+            return "success"
 
-    assert test_func(1, 2) == 0
+        assert test_func() == "success"
 
+    def test_redis_fallback_error(self):
+        @redis_fallback(default_return="fallback")
+        def test_func():
+            raise RedisError("Redis error")
 
-def test_redis_fallback_with_kwargs():
-    @redis_fallback(default_return={})
-    def test_func(x=None, y=None):
-        raise RedisError("Redis error")
+        assert test_func() == "fallback"
 
-    assert test_func(x=1, y=2) == {}
+    def test_redis_fallback_none_default(self):
+        @redis_fallback()
+        def test_func():
+            raise RedisError("Redis error")
 
+        assert test_func() is None
 
-def test_redis_fallback_preserves_function_metadata():
-    @redis_fallback(default_return=None)
-    def test_func():
-        """Test function docstring"""
-        pass
+    def test_redis_fallback_with_args(self):
+        @redis_fallback(default_return=0)
+        def test_func(x, y):
+            raise RedisError("Redis error")
 
-    assert test_func.__name__ == "test_func"
-    assert test_func.__doc__ == "Test function docstring"
+        assert test_func(1, 2) == 0
+
+    def test_redis_fallback_with_kwargs(self):
+        @redis_fallback(default_return={})
+        def test_func(x=None, y=None):
+            raise RedisError("Redis error")
+
+        assert test_func(x=1, y=2) == {}
+
+    def test_redis_fallback_preserves_function_metadata(self):
+        @redis_fallback(default_return=None)
+        def test_func():
+            """Test function docstring"""
+            pass
+
+        assert test_func.__name__ == "test_func"
+        assert test_func.__doc__ == "Test function docstring"

api/tests/unit_tests/libs/broadcast_channel/redis/test_streams_channel_unit_tests.py

@@ -156,6 +156,48 @@ class TestStreamsBroadcastChannel:
         assert topic.as_producer() is topic
         assert topic.as_subscriber() is topic
 
+    def test_join_timeout_ms_propagates_from_channel_to_subscription(self, fake_redis: FakeStreamsRedis):
+        channel = StreamsBroadcastChannel(fake_redis, retention_seconds=60, join_timeout_ms=150)
+        topic = channel.topic("join-timeout-prop")
+
+        assert topic._join_timeout_ms == 150
+
+        sub = topic.subscribe()
+        try:
+            assert sub._join_timeout_ms == 150
+        finally:
+            sub.close()
+
+    def test_join_timeout_ms_defaults_to_2000(self, fake_redis: FakeStreamsRedis):
+        channel = StreamsBroadcastChannel(fake_redis, retention_seconds=60)
+        topic = channel.topic("join-timeout-default")
+
+        assert topic._join_timeout_ms == 2000
+
+    def test_small_join_timeout_makes_close_return_promptly(self, fake_redis: FakeStreamsRedis):
+        """close() should respect the configured join timeout.
+
+        Regression test for SSE close tail latency: when an idle listener is
+        blocked on its poll cycle, close() with a small join_timeout_ms must
+        not wait for the full poll window. The orphaned daemon listener
+        cleans itself up later.
+        """
+        channel = StreamsBroadcastChannel(fake_redis, retention_seconds=60, join_timeout_ms=50)
+        topic = channel.topic("join-timeout-prompt-close")
+        sub = topic.subscribe()
+
+        # Drive listener startup so the thread is actually blocked in xread.
+        assert sub.receive(timeout=0.05) is None
+        time.sleep(0.05)
+
+        started = time.monotonic()
+        sub.close()
+        elapsed = time.monotonic() - started
+
+        # 50ms timeout + scheduling slack; pick a ceiling well under the
+        # default poll window (1000ms) to make the regression meaningful.
+        assert elapsed < 0.5, f"close() took {elapsed:.3f}s; expected prompt return"
+
     def test_publish_logs_warning_when_expire_fails(self, caplog: pytest.LogCaptureFixture):
         channel = StreamsBroadcastChannel(FailExpireRedis(), retention_seconds=60)
         topic = channel.topic("expire-warning")
@@ -322,10 +364,17 @@ class TestStreamsSubscription:
 
         assert next(iter(subscription)) == b"event"
 
-    def test_close_logs_warning_when_listener_does_not_stop_in_time(
+    def test_close_logs_debug_when_listener_does_not_stop_in_time(
         self,
         caplog: pytest.LogCaptureFixture,
     ):
+        """When a low join_timeout elapses with the listener still alive,
+        close() should log at DEBUG (not WARNING) - with a deliberately small
+        timeout this is expected, not anomalous; the orphaned daemon thread
+        cleans itself up on the next poll boundary.
+        """
+        import logging
+
         blocking_redis = BlockingRedis()
         subscription = _StreamsSubscription(blocking_redis, "stream:slow-close")
 
@@ -343,8 +392,10 @@ class TestStreamsSubscription:
         listener.is_alive = lambda: True  # type: ignore[method-assign]
 
         try:
-            subscription.close()
-            assert "did not stop within timeout" in caplog.text
+            with caplog.at_level(logging.DEBUG, logger="libs.broadcast_channel.redis.streams_channel"):
+                subscription.close()
+            assert "did not stop within" in caplog.text
+            assert "daemon thread will exit on its own" in caplog.text
         finally:
             listener.join = original_join  # type: ignore[method-assign]
             listener.is_alive = original_is_alive  # type: ignore[method-assign]

api/tests/unit_tests/libs/test_passport.py

@@ -149,11 +149,9 @@ class TestPassportService:
             mock_config.SECRET_KEY = ""
             service = PassportService()
 
-            # Empty secret key should still work but is insecure
             payload = {"test": "data"}
-            token = service.issue(payload)
-            decoded = service.verify(token)
-            assert decoded == payload
+            with pytest.raises(jwt.exceptions.InvalidKeyError):
+                service.issue(payload)
 
     def test_should_handle_none_secret_key(self):
         """Test behavior when SECRET_KEY is None"""

api/tests/unit_tests/libs/test_pyrefly_type_coverage.py

@@ -0,0 +1,138 @@
+import json
+
+from libs.pyrefly_type_coverage import (
+    CoverageSummary,
+    format_comparison_markdown,
+    format_summary_markdown,
+    parse_summary,
+)
+
+
+def _make_report(summary: dict) -> str:
+    return json.dumps({"module_reports": [], "summary": summary})
+
+
+_SAMPLE_SUMMARY: dict = {
+    "n_modules": 100,
+    "n_typable": 1000,
+    "n_typed": 400,
+    "n_any": 50,
+    "n_untyped": 550,
+    "coverage": 45.0,
+    "strict_coverage": 40.0,
+    "n_functions": 200,
+    "n_methods": 300,
+    "n_function_params": 150,
+    "n_method_params": 250,
+    "n_classes": 80,
+    "n_attrs": 40,
+    "n_properties": 20,
+    "n_type_ignores": 10,
+}
+
+
+def _make_summary(
+    *,
+    n_modules: int = 100,
+    n_typable: int = 1000,
+    n_typed: int = 400,
+    n_any: int = 50,
+    n_untyped: int = 550,
+    coverage: float = 45.0,
+    strict_coverage: float = 40.0,
+) -> CoverageSummary:
+    return {
+        "n_modules": n_modules,
+        "n_typable": n_typable,
+        "n_typed": n_typed,
+        "n_any": n_any,
+        "n_untyped": n_untyped,
+        "coverage": coverage,
+        "strict_coverage": strict_coverage,
+    }
+
+
+def test_parse_summary_extracts_fields() -> None:
+    report_json = _make_report(_SAMPLE_SUMMARY)
+
+    result = parse_summary(report_json)
+
+    assert result["n_modules"] == 100
+    assert result["n_typable"] == 1000
+    assert result["n_typed"] == 400
+    assert result["n_any"] == 50
+    assert result["n_untyped"] == 550
+    assert result["coverage"] == 45.0
+    assert result["strict_coverage"] == 40.0
+
+
+def test_parse_summary_handles_empty_input() -> None:
+    assert parse_summary("")["n_modules"] == 0
+    assert parse_summary("   ")["n_modules"] == 0
+
+
+def test_parse_summary_handles_invalid_json() -> None:
+    assert parse_summary("not json")["n_modules"] == 0
+
+
+def test_parse_summary_handles_missing_summary_key() -> None:
+    assert parse_summary(json.dumps({"other": 1}))["n_modules"] == 0
+
+
+def test_parse_summary_handles_incomplete_summary() -> None:
+    partial = json.dumps({"summary": {"n_modules": 5}})
+    assert parse_summary(partial)["n_modules"] == 0
+
+
+def test_format_summary_markdown_contains_key_metrics() -> None:
+    summary = _make_summary()
+
+    result = format_summary_markdown(summary)
+
+    assert "**Type coverage**" in result
+    assert "45.00%" in result
+    assert "40.00%" in result
+    assert "| Modules | 100 |" in result
+
+
+def test_format_comparison_markdown_shows_positive_delta() -> None:
+    base = _make_summary()
+    pr = _make_summary(
+        n_modules=101,
+        n_typable=1010,
+        n_typed=420,
+        n_untyped=540,
+        coverage=46.53,
+        strict_coverage=41.58,
+    )
+
+    result = format_comparison_markdown(base, pr)
+
+    assert "| Base | PR | Delta |" in result
+    assert "+1.53%" in result
+    assert "+1.58%" in result
+    assert "+20" in result
+
+
+def test_format_comparison_markdown_shows_negative_delta() -> None:
+    base = _make_summary()
+    pr = _make_summary(
+        n_typed=390,
+        n_any=60,
+        coverage=44.0,
+        strict_coverage=39.0,
+    )
+
+    result = format_comparison_markdown(base, pr)
+
+    assert "-1.00%" in result
+    assert "-10" in result
+
+
+def test_format_comparison_markdown_shows_zero_delta() -> None:
+    summary = _make_summary()
+
+    result = format_comparison_markdown(summary, summary)
+
+    assert "0.00%" in result
+    assert "| 0 |" in result

api/tests/unit_tests/models/test_dataset_models.py

@@ -12,7 +12,9 @@ This test suite covers:
 import json
 import pickle
 from datetime import UTC, datetime
-from unittest.mock import patch
+from types import SimpleNamespace
+from unittest.mock import Mock, patch
+from urllib.parse import parse_qs, urlparse
 from uuid import uuid4
 
 from core.rag.index_processor.constant.index_type import IndexTechniqueType
@@ -657,6 +659,51 @@ class TestDocumentSegmentIndexing:
         # Assert
         assert segment.hit_count == 5
 
+    def test_document_segment_attachments_prefers_files_url_for_source_url(self, monkeypatch):
+        """Test attachment source URLs use FILES_URL before falling back to CONSOLE_API_URL."""
+        # Arrange
+        segment = DocumentSegment(
+            tenant_id="tenant-1",
+            dataset_id="dataset-1",
+            document_id="document-1",
+            position=1,
+            content="Test",
+            word_count=1,
+            tokens=2,
+            created_by="user-1",
+        )
+        segment.id = "segment-1"
+        attachment = SimpleNamespace(
+            id="upload-1",
+            name="image.png",
+            size=128,
+            extension="png",
+            mime_type="image/png",
+        )
+
+        monkeypatch.setattr("models.dataset.time.time", lambda: 1700000000)
+        monkeypatch.setattr("models.dataset.os.urandom", lambda _: b"\x01" * 16)
+        monkeypatch.setattr("models.dataset.dify_config.SECRET_KEY", "unit-secret")
+        monkeypatch.setattr("models.dataset.dify_config.FILES_URL", "https://files.example.com")
+        monkeypatch.setattr("models.dataset.dify_config.CONSOLE_API_URL", "https://console.example.com")
+
+        with patch("models.dataset.db") as mock_db:
+            mock_db.session.execute.return_value.all.return_value = [(Mock(), attachment)]
+
+            # Act
+            attachments = segment.attachments
+
+        # Assert
+        assert len(attachments) == 1
+        source_url = attachments[0]["source_url"]
+        parsed = urlparse(source_url)
+        query = parse_qs(parsed.query)
+        assert parsed.netloc == "files.example.com"
+        assert parsed.path == "/files/upload-1/image-preview"
+        assert query["timestamp"] == ["1700000000"]
+        assert query["nonce"] == ["01010101010101010101010101010101"]
+        assert query["sign"][0]
+
     def test_document_segment_error_tracking(self):
         """Test document segment error tracking."""
         # Arrange

api/tests/unit_tests/services/test_account_service.py

@@ -1499,16 +1499,9 @@ class TestRegisterService:
         mock_tenant.name = "Test Workspace"
         mock_inviter = TestAccountAssociatedDataFactory.create_account_mock(account_id="inviter-123", name="Inviter")
 
-        # Mock database queries - need to mock the Session query
-        mock_session = MagicMock()
-        mock_session.query.return_value.filter_by.return_value.first.return_value = None  # No existing account
-
         with (
-            patch("services.account_service.Session") as mock_session_class,
             patch("services.account_service.AccountService.get_account_by_email_with_case_fallback") as mock_lookup,
         ):
-            mock_session_class.return_value.__enter__.return_value = mock_session
-            mock_session_class.return_value.__exit__.return_value = None
             mock_lookup.return_value = None
 
             # Mock RegisterService.register
@@ -1545,7 +1538,7 @@ class TestRegisterService:
                         status=AccountStatus.PENDING,
                         is_setup=True,
                     )
-                    mock_lookup.assert_called_once_with("newuser@example.com", session=mock_session)
+                    mock_lookup.assert_called_once_with("newuser@example.com")
 
     def test_invite_new_member_normalizes_new_account_email(
         self, mock_db_dependencies, mock_redis_dependencies, mock_task_dependencies
@@ -1556,13 +1549,9 @@ class TestRegisterService:
         mock_inviter = TestAccountAssociatedDataFactory.create_account_mock(account_id="inviter-123", name="Inviter")
         mixed_email = "Invitee@Example.com"
 
-        mock_session = MagicMock()
         with (
-            patch("services.account_service.Session") as mock_session_class,
             patch("services.account_service.AccountService.get_account_by_email_with_case_fallback") as mock_lookup,
         ):
-            mock_session_class.return_value.__enter__.return_value = mock_session
-            mock_session_class.return_value.__exit__.return_value = None
             mock_lookup.return_value = None
 
             mock_new_account = TestAccountAssociatedDataFactory.create_account_mock(
@@ -1593,7 +1582,7 @@ class TestRegisterService:
                         status=AccountStatus.PENDING,
                         is_setup=True,
                     )
-                    mock_lookup.assert_called_once_with(mixed_email, session=mock_session)
+                    mock_lookup.assert_called_once_with(mixed_email)
                     mock_check_permission.assert_called_once_with(mock_tenant, mock_inviter, None, "add")
                     mock_create_member.assert_called_once_with(mock_tenant, mock_new_account, "normal")
                     mock_switch_tenant.assert_called_once_with(mock_new_account, mock_tenant.id)
@@ -1613,16 +1602,9 @@ class TestRegisterService:
             account_id="existing-user-456", email="existing@example.com", status="pending"
         )
 
-        # Mock database queries - need to mock the Session query
-        mock_session = MagicMock()
-        mock_session.query.return_value.filter_by.return_value.first.return_value = mock_existing_account
-
         with (
-            patch("services.account_service.Session") as mock_session_class,
             patch("services.account_service.AccountService.get_account_by_email_with_case_fallback") as mock_lookup,
         ):
-            mock_session_class.return_value.__enter__.return_value = mock_session
-            mock_session_class.return_value.__exit__.return_value = None
             mock_lookup.return_value = mock_existing_account
 
             # Mock the db.session.query for TenantAccountJoin
@@ -1652,7 +1634,7 @@ class TestRegisterService:
                 mock_create_member.assert_called_once_with(mock_tenant, mock_existing_account, "normal")
                 mock_generate_token.assert_called_once_with(mock_tenant, mock_existing_account)
                 mock_task_dependencies.delay.assert_called_once()
-                mock_lookup.assert_called_once_with("existing@example.com", session=mock_session)
+                mock_lookup.assert_called_once_with("existing@example.com")
 
     def test_invite_new_member_already_in_tenant(self, mock_db_dependencies, mock_redis_dependencies):
         """Test inviting a member who is already in the tenant."""