chore(deps): bump the python-packages group across 1 directory with 7 updates

Updates the requirements on bs4, [pypdfium2](https://github.com/pypdfium2-team/pypdfium2), [pyyaml](https://github.com/yaml/pyyaml), [unstructured](https://github.com/Unstructured-IO/unstructured), [pypandoc](https://github.com/JessicaTegner/pypandoc), [httpx-sse](https://github.com/florimondmanca/httpx-sse) and [nltk](https://github.com/nltk/nltk) to permit the latest version.

Updates `bs4` to 0.0.2

Updates `pypdfium2` from 5.6.0 to 5.7.0
- [Release notes](https://github.com/pypdfium2-team/pypdfium2/releases)
- [Commits](https://github.com/pypdfium2-team/pypdfium2/compare/5.6.0...5.7.0)

Updates `pyyaml` to 6.0.3
- [Release notes](https://github.com/yaml/pyyaml/releases)
- [Changelog](https://github.com/yaml/pyyaml/blob/6.0.3/CHANGES)
- [Commits](https://github.com/yaml/pyyaml/compare/6.0.1...6.0.3)

Updates `unstructured` to 0.22.18
- [Release notes](https://github.com/Unstructured-IO/unstructured/releases)
- [Changelog](https://github.com/Unstructured-IO/unstructured/blob/main/CHANGELOG.md)
- [Commits](https://github.com/Unstructured-IO/unstructured/compare/0.21.5...0.22.18)

Updates `pypandoc` to 1.17
- [Release notes](https://github.com/JessicaTegner/pypandoc/releases)
- [Changelog](https://github.com/JessicaTegner/pypandoc/blob/master/release.md)
- [Commits](https://github.com/JessicaTegner/pypandoc/compare/v1.13...v1.17)

Updates `httpx-sse` to 0.4.3
- [Release notes](https://github.com/florimondmanca/httpx-sse/releases)
- [Changelog](https://github.com/florimondmanca/httpx-sse/blob/master/CHANGELOG.md)
- [Commits](https://github.com/florimondmanca/httpx-sse/compare/0.4.0...0.4.3)

Updates `nltk` to 3.9.4
- [Changelog](https://github.com/nltk/nltk/blob/develop/ChangeLog)
- [Commits](https://github.com/nltk/nltk/compare/3.9.1...3.9.4)

---
updated-dependencies:
- dependency-name: bs4
  dependency-version: 0.0.2
  dependency-type: direct:production
  dependency-group: python-packages
- dependency-name: pypdfium2
  dependency-version: 5.7.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: python-packages
- dependency-name: pyyaml
  dependency-version: 6.0.3
  dependency-type: direct:production
  dependency-group: python-packages
- dependency-name: unstructured
  dependency-version: 0.22.18
  dependency-type: direct:production
  dependency-group: python-packages
- dependency-name: pypandoc
  dependency-version: '1.17'
  dependency-type: direct:production
  dependency-group: python-packages
- dependency-name: httpx-sse
  dependency-version: 0.4.3
  dependency-type: direct:production
  dependency-group: python-packages
- dependency-name: nltk
  dependency-version: 3.9.4
  dependency-type: direct:development
  dependency-group: python-packages
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/workflows/api-tests.yml

@@ -54,7 +54,7 @@ jobs:
         run: uv run --project api bash dev/pytest/pytest_unit_tests.sh
 
       - name: Upload unit coverage data
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: api-coverage-unit
           path: coverage-unit
@@ -129,7 +129,7 @@ jobs:
             api/tests/test_containers_integration_tests
 
       - name: Upload integration coverage data
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: api-coverage-integration
           path: coverage-integration

.github/workflows/build-push.yml

@@ -81,7 +81,7 @@ jobs:
 
       - name: Build Docker image
         id: build
-        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v7.0.0
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
         with:
           context: ${{ matrix.build_context }}
           file: ${{ matrix.file }}
@@ -101,7 +101,7 @@ jobs:
           touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: digests-${{ matrix.artifact_context }}-${{ env.PLATFORM_PAIR }}
           path: /tmp/digests/*

.github/workflows/docker-build.yml

@@ -50,7 +50,7 @@ jobs:
         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: ${{ matrix.context }}

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

@@ -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: |

.github/workflows/pyrefly-diff.yml

@@ -66,7 +66,7 @@ jobs:
           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: |
@@ -75,7 +75,7 @@ jobs:
 
       - name: Comment PR with pyrefly diff
         if: ${{ github.event.pull_request.head.repo.full_name == github.repository && steps.line_count_check.outputs.same == 'false' }}
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |

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

@@ -32,7 +32,7 @@ jobs:
         run: uv sync --project api --dev
 
       - name: Download type coverage artifact
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -73,7 +73,7 @@ jobs:
           } > /tmp/type_coverage_comment.md
 
       - 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: |

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

@@ -71,7 +71,7 @@ jobs:
           echo ${{ github.event.pull_request.number }} > pr_number.txt
 
       - name: Upload type coverage artifact
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: pyrefly_type_coverage
           path: |
@@ -81,7 +81,7 @@ jobs:
 
       - name: Comment PR with type coverage
         if: ${{ github.event.pull_request.head.repo.full_name == github.repository }}
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |

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

@@ -158,7 +158,7 @@ jobs:
 
       - name: Run Claude Code for Translation Sync
         if: steps.context.outputs.CHANGED_FILES != ''
-        uses: anthropics/claude-code-action@6e2bd52842c65e914eba5c8badd17560bd26b5de # v1.0.89
+        uses: anthropics/claude-code-action@b47fd721da662d48c5680e154ad16a73ed74d2e0 # v1.0.93
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}

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

@@ -56,7 +56,7 @@ jobs:
 
       - name: Trigger i18n sync workflow
         if: steps.detect.outputs.has_changes == 'true'
-        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           BASE_SHA: ${{ steps.detect.outputs.base_sha }}
           HEAD_SHA: ${{ steps.detect.outputs.head_sha }}

.github/workflows/web-e2e.yml

@@ -53,7 +53,7 @@ jobs:
 
       - name: Upload Cucumber report
         if: ${{ !cancelled() }}
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: cucumber-report
           path: e2e/cucumber-report
@@ -61,7 +61,7 @@ jobs:
 
       - name: Upload E2E logs
         if: ${{ !cancelled() }}
-        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
           name: e2e-logs
           path: e2e/.logs

.github/workflows/web-tests.yml

@@ -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/*

api/models/dataset.py

@@ -353,13 +353,17 @@ class Dataset(Base):
         if self.provider != "external":
             return None
         external_knowledge_binding = db.session.scalar(
-            select(ExternalKnowledgeBindings).where(ExternalKnowledgeBindings.dataset_id == self.id)
+            select(ExternalKnowledgeBindings).where(
+                ExternalKnowledgeBindings.dataset_id == self.id,
+                ExternalKnowledgeBindings.tenant_id == self.tenant_id,
+            )
         )
         if not external_knowledge_binding:
             return None
         external_knowledge_api = db.session.scalar(
             select(ExternalKnowledgeApis).where(
-                ExternalKnowledgeApis.id == external_knowledge_binding.external_knowledge_api_id
+                ExternalKnowledgeApis.id == external_knowledge_binding.external_knowledge_api_id,
+                ExternalKnowledgeApis.tenant_id == self.tenant_id,
             )
         )
         if external_knowledge_api is None or external_knowledge_api.settings is None:

api/pyproject.toml

@@ -4,42 +4,42 @@ version = "1.13.3"
 requires-python = "~=3.12.0"
 
 dependencies = [
-    "aliyun-log-python-sdk~=0.9.37",
+    "aliyun-log-python-sdk~=0.9.44",
     "arize-phoenix-otel~=0.15.0",
     "azure-identity==1.25.3",
     "beautifulsoup4==4.14.3",
-    "boto3==1.42.83",
-    "bs4~=0.0.1",
-    "cachetools~=5.3.0",
-    "celery~=5.6.2",
-    "charset-normalizer>=3.4.4",
-    "flask~=3.1.2",
-    "flask-compress>=1.17,<1.25",
-    "flask-cors~=6.0.0",
+    "boto3==1.42.88",
+    "bs4~=0.0.2",
+    "cachetools~=7.0.5",
+    "celery~=5.6.3",
+    "charset-normalizer>=3.4.7",
+    "flask~=3.1.3",
+    "flask-compress>=1.24,<1.25",
+    "flask-cors~=6.0.2",
     "flask-login~=0.6.3",
     "flask-migrate~=4.1.0",
     "flask-orjson~=2.0.0",
     "flask-sqlalchemy~=3.1.1",
-    "gevent~=25.9.1",
+    "gevent~=26.4.0",
     "gmpy2~=2.3.0",
-    "google-api-core>=2.19.1",
-    "google-api-python-client==2.193.0",
-    "google-auth>=2.47.0",
+    "google-api-core>=2.30.3",
+    "google-api-python-client==2.194.0",
+    "google-auth>=2.49.2",
     "google-auth-httplib2==0.3.1",
-    "google-cloud-aiplatform>=1.123.0",
-    "googleapis-common-protos>=1.65.0",
+    "google-cloud-aiplatform>=1.147.0",
+    "googleapis-common-protos>=1.74.0",
     "graphon>=0.1.2",
     "gunicorn~=25.3.0",
-    "httpx[socks]~=0.28.0",
+    "httpx[socks]~=0.28.1",
     "jieba==0.42.1",
-    "json-repair>=0.55.1",
-    "langfuse>=3.0.0,<5.0.0",
-    "langsmith~=0.7.16",
+    "json-repair>=0.59.2",
+    "langfuse>=4.2.0,<5.0.0",
+    "langsmith~=0.7.30",
     "markdown~=3.10.2",
-    "mlflow-skinny>=3.0.0",
-    "numpy~=1.26.4",
+    "mlflow-skinny>=3.11.1",
+    "numpy~=2.4.4",
     "openpyxl~=3.1.5",
-    "opik~=1.10.37",
+    "opik~=1.11.2",
     "litellm==1.83.0",                                    # Pinned to avoid madoka dependency issue
     "opentelemetry-api==1.40.0",
     "opentelemetry-distro==0.61b0",
@@ -53,41 +53,41 @@ dependencies = [
     "opentelemetry-instrumentation-httpx==0.61b0",
     "opentelemetry-instrumentation-redis==0.61b0",
     "opentelemetry-instrumentation-sqlalchemy==0.61b0",
-    "opentelemetry-propagator-b3==1.40.0",
+    "opentelemetry-propagator-b3==1.41.0",
     "opentelemetry-proto==1.40.0",
     "opentelemetry-sdk==1.40.0",
     "opentelemetry-semantic-conventions==0.61b0",
     "opentelemetry-util-http==0.61b0",
-    "pandas[excel,output-formatting,performance]~=3.0.1",
+    "pandas[excel,output-formatting,performance]~=3.0.2",
     "psycogreen~=1.0.2",
-    "psycopg2-binary~=2.9.6",
+    "psycopg2-binary~=2.9.11",
     "pycryptodome==3.23.0",
     "pydantic~=2.12.5",
     "pydantic-settings~=2.13.1",
-    "pyjwt~=2.12.0",
-    "pypdfium2==5.6.0",
+    "pyjwt~=2.12.1",
+    "pypdfium2==5.7.0",
     "python-docx~=1.2.0",
     "python-dotenv==1.2.2",
-    "pyyaml~=6.0.1",
+    "pyyaml~=6.0.3",
     "readabilipy~=0.3.0",
     "redis[hiredis]~=7.4.0",
-    "resend~=2.26.0",
-    "sentry-sdk[flask]~=2.55.0",
-    "sqlalchemy~=2.0.29",
+    "resend~=2.27.0",
+    "sentry-sdk[flask]~=2.57.0",
+    "sqlalchemy~=2.0.49",
     "starlette==1.0.0",
     "tiktoken~=0.12.0",
     "transformers~=5.3.0",
-    "unstructured[docx,epub,md,ppt,pptx]~=0.21.5",
-    "pypandoc~=1.13",
+    "unstructured[docx,epub,md,ppt,pptx]~=0.22.18",
+    "pypandoc~=1.17",
     "yarl~=1.23.0",
     "sseclient-py~=1.9.0",
-    "httpx-sse~=0.4.0",
-    "sendgrid~=6.12.3",
+    "httpx-sse~=0.4.3",
+    "sendgrid~=6.12.5",
     "flask-restx~=1.3.2",
-    "packaging~=23.2",
-    "croniter>=6.0.0",
-    "weaviate-client==4.20.4",
-    "apscheduler>=3.11.0",
+    "packaging~=26.0",
+    "croniter>=6.2.2",
+    "weaviate-client==4.20.5",
+    "apscheduler>=3.11.2",
     "weave>=0.52.16",
     "fastopenapi[flask]>=0.7.0",
     "bleach~=6.3.0",
@@ -111,16 +111,16 @@ package = false
 dev = [
     "coverage~=7.13.4",
     "dotenv-linter~=0.7.0",
-    "faker~=40.12.0",
+    "faker~=40.13.0",
     "lxml-stubs~=0.5.1",
     "basedpyright~=1.39.0",
-    "ruff~=0.15.5",
-    "pytest~=9.0.2",
+    "ruff~=0.15.10",
+    "pytest~=9.0.3",
     "pytest-benchmark~=5.2.3",
     "pytest-cov~=7.1.0",
     "pytest-env~=1.6.0",
     "pytest-mock~=3.15.1",
-    "testcontainers~=4.14.1",
+    "testcontainers~=4.14.2",
     "types-aiofiles~=25.1.0",
     "types-beautifulsoup4~=4.12.0",
     "types-cachetools~=6.2.0",
@@ -130,8 +130,8 @@ dev = [
     "types-docutils~=0.22.3",
     "types-flask-cors~=6.0.0",
     "types-flask-migrate~=4.1.0",
-    "types-gevent~=25.9.0",
-    "types-greenlet~=3.3.0",
+    "types-gevent~=26.4.0",
+    "types-greenlet~=3.4.0",
     "types-html5lib~=1.1.11",
     "types-markdown~=3.10.2",
     "types-oauthlib~=3.3.0",
@@ -149,20 +149,20 @@ dev = [
     "types-pyyaml~=6.0.12",
     "types-regex~=2026.4.4",
     "types-shapely~=2.1.0",
-    "types-simplejson>=3.20.0",
-    "types-six>=1.17.0",
-    "types-tensorflow>=2.18.0",
-    "types-tqdm>=4.67.0",
+    "types-simplejson>=3.20.0.20260408",
+    "types-six>=1.17.0.20260408",
+    "types-tensorflow>=2.18.0.20260408",
+    "types-tqdm>=4.67.3.20260408",
     "types-ujson>=5.10.0",
-    "boto3-stubs>=1.38.20",
-    "types-jmespath>=1.0.2.20240106",
-    "hypothesis>=6.131.15",
+    "boto3-stubs>=1.42.88",
+    "types-jmespath>=1.1.0.20260408",
+    "hypothesis>=6.151.12",
     "types_pyOpenSSL>=24.1.0",
-    "types_cffi>=1.17.0",
-    "types_setuptools>=80.9.0",
+    "types_cffi>=2.0.0.20260408",
+    "types_setuptools>=82.0.0.20260408",
     "pandas-stubs~=3.0.0",
     "scipy-stubs>=1.15.3.0",
-    "types-python-http-client>=3.3.7.20240910",
+    "types-python-http-client>=3.3.7.20260408",
     "import-linter>=2.3",
     "types-redis>=4.6.0.20241004",
     "celery-types>=0.23.0",
@@ -180,10 +180,10 @@ dev = [
 ############################################################
 storage = [
     "azure-storage-blob==12.28.0",
-    "bce-python-sdk~=0.9.23",
+    "bce-python-sdk~=0.9.69",
     "cos-python-sdk-v5==1.9.41",
     "esdk-obs-python==3.26.2",
-    "google-cloud-storage>=3.0.0",
+    "google-cloud-storage>=3.10.1",
     "opendal~=0.46.0",
     "oss2==2.19.1",
     "supabase~=2.18.1",
@@ -193,7 +193,7 @@ storage = [
 ############################################################
 # [ Tools ] dependency group
 ############################################################
-tools = ["cloudscraper~=1.2.71", "nltk~=3.9.1"]
+tools = ["cloudscraper~=1.2.71", "nltk~=3.9.4"]
 
 ############################################################
 # [ VDB ] dependency group
@@ -209,23 +209,23 @@ vdb = [
     "elasticsearch==8.14.0",
     "opensearch-py==3.1.0",
     "oracledb==3.4.2",
-    "pgvecto-rs[sqlalchemy]~=0.2.1",
+    "pgvecto-rs[sqlalchemy]~=0.2.2",
     "pgvector==0.4.2",
-    "pymilvus~=2.6.10",
+    "pymilvus~=2.6.12",
     "pymochow==2.4.0",
     "pyobvector~=0.2.17",
     "qdrant-client==1.9.0",
     "intersystems-irispython>=5.1.0",
-    "tablestore==6.4.3",
+    "tablestore==6.4.4",
     "tcvectordb~=2.1.0",
     "tidb-vector==0.0.15",
     "upstash-vector==0.8.0",
     "volcengine-compat~=1.0.0",
-    "weaviate-client==4.20.4",
+    "weaviate-client==4.20.5",
     "xinference-client~=2.4.0",
     "mo-vector~=0.1.13",
     "mysql-connector-python>=9.3.0",
-    "holo-search-sdk>=0.4.1",
+    "holo-search-sdk>=0.4.2",
 ]
 
 [tool.pyrefly]

api/services/dataset_service.py

@@ -528,6 +528,8 @@ class DatasetService:
             raise ValueError("External knowledge id is required.")
         if not external_knowledge_api_id:
             raise ValueError("External knowledge api id is required.")
+        # Ensure the referenced external API template exists and belongs to the dataset tenant.
+        ExternalDatasetService.get_external_knowledge_api(external_knowledge_api_id, dataset.tenant_id)
         # Update metadata fields
         dataset.updated_by = user.id if user else None
         dataset.updated_at = naive_utc_now()

api/services/external_knowledge_service.py

@@ -317,7 +317,10 @@ class ExternalDatasetService:
 
         external_knowledge_api = db.session.scalar(
             select(ExternalKnowledgeApis)
-            .where(ExternalKnowledgeApis.id == external_knowledge_binding.external_knowledge_api_id)
+            .where(
+                ExternalKnowledgeApis.id == external_knowledge_binding.external_knowledge_api_id,
+                ExternalKnowledgeApis.tenant_id == tenant_id,
+            )
             .limit(1)
         )
         if external_knowledge_api is None or external_knowledge_api.settings is None:

api/tests/test_containers_integration_tests/services/test_dataset_service_update_dataset.py

@@ -1,3 +1,4 @@
+import json
 from unittest.mock import Mock, patch
 from uuid import uuid4
 
@@ -7,7 +8,7 @@ from sqlalchemy.orm import Session
 
 from core.rag.index_processor.constant.index_type import IndexTechniqueType
 from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
-from models.dataset import Dataset, ExternalKnowledgeBindings
+from models.dataset import Dataset, ExternalKnowledgeApis, ExternalKnowledgeBindings
 from models.enums import DataSourceType
 from services.dataset_service import DatasetService
 from services.errors.account import NoPermissionError
@@ -103,6 +104,34 @@ class DatasetUpdateTestDataFactory:
         db_session_with_containers.commit()
         return binding
 
+    @staticmethod
+    def create_external_knowledge_api(
+        db_session_with_containers: Session,
+        tenant_id: str,
+        created_by: str,
+        api_id: str | None = None,
+        name: str = "test-api",
+    ) -> ExternalKnowledgeApis:
+        """Create a real external knowledge API template for tenant-scoped update validation."""
+        external_api = ExternalKnowledgeApis(
+            tenant_id=tenant_id,
+            created_by=created_by,
+            updated_by=created_by,
+            name=name,
+            description="test description",
+            settings=json.dumps(
+                {
+                    "endpoint": "https://example.com",
+                    "api_key": "test-api-key",
+                }
+            ),
+        )
+        if api_id is not None:
+            external_api.id = api_id
+        db_session_with_containers.add(external_api)
+        db_session_with_containers.commit()
+        return external_api
+
 
 class TestDatasetServiceUpdateDataset:
     """
@@ -138,6 +167,11 @@ class TestDatasetServiceUpdateDataset:
         )
         binding_id = binding.id
         db_session_with_containers.expunge(binding)
+        external_api = DatasetUpdateTestDataFactory.create_external_knowledge_api(
+            db_session_with_containers,
+            tenant_id=tenant.id,
+            created_by=user.id,
+        )
 
         update_data = {
             "name": "new_name",
@@ -145,7 +179,7 @@ class TestDatasetServiceUpdateDataset:
             "external_retrieval_model": "new_model",
             "permission": "only_me",
             "external_knowledge_id": "new_knowledge_id",
-            "external_knowledge_api_id": str(uuid4()),
+            "external_knowledge_api_id": external_api.id,
         }
 
         result = DatasetService.update_dataset(dataset.id, update_data, user)
@@ -218,11 +252,16 @@ class TestDatasetServiceUpdateDataset:
             created_by=user.id,
             provider="external",
         )
+        external_api = DatasetUpdateTestDataFactory.create_external_knowledge_api(
+            db_session_with_containers,
+            tenant_id=tenant.id,
+            created_by=user.id,
+        )
 
         update_data = {
             "name": "new_name",
             "external_knowledge_id": "knowledge_id",
-            "external_knowledge_api_id": str(uuid4()),
+            "external_knowledge_api_id": external_api.id,
         }
 
         with pytest.raises(ValueError) as context:

api/tests/unit_tests/models/test_dataset_models.py

@@ -12,7 +12,7 @@ This test suite covers:
 import json
 import pickle
 from datetime import UTC, datetime
-from unittest.mock import patch
+from unittest.mock import Mock, patch
 from uuid import uuid4
 
 from core.rag.index_processor.constant.index_type import IndexTechniqueType
@@ -25,6 +25,7 @@ from models.dataset import (
     Document,
     DocumentSegment,
     Embedding,
+    ExternalKnowledgeBindings,
 )
 from models.enums import (
     DataSourceType,
@@ -180,6 +181,24 @@ class TestDatasetModelValidation:
         assert result["top_k"] == 2
         assert result["score_threshold"] == 0.0
 
+    def test_dataset_external_knowledge_info_returns_none_for_cross_tenant_template(self):
+        """Test external datasets fail closed when the bound template is outside the tenant."""
+        dataset = Dataset(
+            tenant_id=str(uuid4()),
+            name="External Dataset",
+            data_source_type=DataSourceType.UPLOAD_FILE,
+            created_by=str(uuid4()),
+            provider="external",
+        )
+        binding = Mock(spec=ExternalKnowledgeBindings)
+        binding.external_knowledge_id = "knowledge-1"
+        binding.external_knowledge_api_id = str(uuid4())
+
+        with patch("models.dataset.db") as mock_db:
+            mock_db.session.scalar.side_effect = [binding, None]
+
+            assert dataset.external_knowledge_info is None
+
     def test_dataset_retrieval_model_dict_property(self):
         """Test retrieval_model_dict property with default values."""
         # Arrange

api/tests/unit_tests/services/test_dataset_service_dataset.py

@@ -532,6 +532,9 @@ class TestDatasetServiceCreationAndUpdate:
 
         with (
             patch.object(DatasetService, "_update_external_knowledge_binding") as update_binding,
+            patch(
+                "services.dataset_service.ExternalDatasetService.get_external_knowledge_api", return_value=object()
+            ) as get_external_knowledge_api,
             patch("services.dataset_service.naive_utc_now", return_value=now),
             patch("services.dataset_service.db") as mock_db,
         ):
@@ -557,6 +560,7 @@ class TestDatasetServiceCreationAndUpdate:
         assert dataset.permission == DatasetPermissionEnum.PARTIAL_TEAM
         assert dataset.updated_by == "user-1"
         assert dataset.updated_at is now
+        get_external_knowledge_api.assert_called_once_with("api-1", dataset.tenant_id)
         update_binding.assert_called_once_with("dataset-1", "knowledge-1", "api-1")
         mock_db.session.add.assert_called_once_with(dataset)
         mock_db.session.commit.assert_called_once()
@@ -574,6 +578,31 @@ class TestDatasetServiceCreationAndUpdate:
         with pytest.raises(ValueError, match=message):
             DatasetService._update_external_dataset(dataset, payload, SimpleNamespace(id="user-1"))
 
+    def test_update_external_dataset_rejects_cross_tenant_external_api_id(self):
+        dataset = DatasetServiceUnitDataFactory.create_dataset_mock(dataset_id="dataset-1")
+
+        with (
+            patch(
+                "services.dataset_service.ExternalDatasetService.get_external_knowledge_api",
+                side_effect=ValueError("api template not found"),
+            ) as get_external_knowledge_api,
+            patch.object(DatasetService, "_update_external_knowledge_binding") as update_binding,
+            patch("services.dataset_service.db") as mock_db,
+        ):
+            with pytest.raises(ValueError, match="api template not found"):
+                DatasetService._update_external_dataset(
+                    dataset,
+                    {
+                        "external_knowledge_id": "knowledge-1",
+                        "external_knowledge_api_id": "foreign-api",
+                    },
+                    SimpleNamespace(id="user-1"),
+                )
+
+        get_external_knowledge_api.assert_called_once_with("foreign-api", dataset.tenant_id)
+        update_binding.assert_not_called()
+        mock_db.session.commit.assert_not_called()
+
     def test_update_external_knowledge_binding_updates_changed_binding_values(self):
         binding = SimpleNamespace(external_knowledge_id="old-knowledge", external_knowledge_api_id="old-api")
         session = MagicMock()

api/tests/unit_tests/services/test_external_dataset_service.py

@@ -1560,6 +1560,17 @@ class TestExternalDatasetServiceFetchRetrieval:
         with pytest.raises(ValueError, match="external knowledge binding not found"):
             ExternalDatasetService.fetch_external_knowledge_retrieval("tenant-123", "dataset-123", "query", {})
 
+    @patch("services.external_knowledge_service.db")
+    def test_fetch_external_knowledge_retrieval_cross_tenant_api_template_error(self, mock_db, factory):
+        """Test error when a binding points to an API template outside the dataset tenant."""
+        # Arrange
+        binding = factory.create_external_knowledge_binding_mock()
+        mock_db.session.scalar.side_effect = [binding, None]
+
+        # Act & Assert
+        with pytest.raises(ValueError, match="external api template not found"):
+            ExternalDatasetService.fetch_external_knowledge_retrieval("tenant-123", "dataset-123", "query", {})
+
     @patch("services.external_knowledge_service.ExternalDatasetService.process_external_api")
     @patch("services.external_knowledge_service.db")
     def test_fetch_external_knowledge_retrieval_empty_results(self, mock_db, mock_process, factory):