Merge branch 'develop' into feature/served-pipelines

Author: schustmi

.coderabbit.yaml

@@ -3,7 +3,7 @@ early_access: false
 reviews:
   high_level_summary: true
   poem: true
-  review_status: true
+  review_status: false
   collapse_walkthrough: true
   path_filters:
   - "!**/.xml"

docs/book/getting-started/zenml-pro/projects.md

@@ -45,6 +45,12 @@ This command sets the "default" project as your active project. All subsequent Z
 Best practice is to set your active project right after running `zenml init`, just like you would set an active stack. This ensures all your resources are properly organized within the project.
 {% endhint %}
 
+You can also set the project to be used by your client via an environment variable:
+
+```bash
+export ZENML_ACTIVE_PROJECT_ID=<PROJECT_ID>
+```
+
 ### Setting a default project
 
 The default project is something that each user can configure. This project will be automatically set as the active project when you connect your local Python client to a ZenML Pro workspace.

docs/book/reference/environment-variables.md

@@ -135,11 +135,12 @@ For more information on server configuration, see the [ZenML Server documentatio
 
 ## Client configuration
 
-Setting the `ZENML_STORE_URL` and `ZENML_STORE_API_KEY` environment variables automatically connects your ZenML Client to the specified server. This method is particularly useful when you are using the ZenML client in an automated CI/CD workload environment like GitHub Actions or GitLab CI or in a containerized environment like Docker or Kubernetes:
+Setting the `ZENML_STORE_URL`, `ZENML_STORE_API_KEY` and `ZENML_ACTIVE_PROJECT_ID` environment variables automatically connects your ZenML Client to the specified server for a specific project. This method is particularly useful when you are using the ZenML client in an automated CI/CD workload environment like GitHub Actions or GitLab CI or in a containerized environment like Docker or Kubernetes:
 
 ```bash
 export ZENML_STORE_URL=https://...
 export ZENML_STORE_API_KEY=<API_KEY>
+export ZENML_ACTIVE_PROJECT_ID=<PROJECT_ID>
 ```
 
 <figure><img src="https://static.scarf.sh/a.png?x-pxid=f0b4f458-0a54-4fcd-aa95-d5ee424815bc" alt="ZenML Scarf"><figcaption></figcaption></figure>

docs/link_checker.py

@@ -79,6 +79,32 @@
 except ImportError:
     HAS_REQUESTS = False
 
+# ------------------------------------------------------------------------------
+# Centralized exceptions for HTTP status codes we consider acceptable for
+# specific URLs or domains during link validation.
+#
+# How to extend:
+#   - To allow particular statuses for a *single* URL, add an entry to
+#     EXEMPT_URL_STATUS with the normalized URL (no trailing slash) and a set
+#     of allowed status codes.
+#   - To allow particular statuses for an entire *domain*, add an entry to
+#     EXEMPT_DOMAIN_STATUS with the domain suffix (e.g. "example.com") and a
+#     set of allowed status codes. Matching uses host.endswith(domain).
+# ------------------------------------------------------------------------------
+
+EXEMPT_URL_STATUS: Dict[str, set] = {
+    # Requires authentication; often returns 403 to unauthenticated HEAD/GET.
+    "https://huggingface.co/settings/tokens": {403},
+}
+
+EXEMPT_DOMAIN_STATUS: Dict[str, set] = {
+    # Some HashiCorp properties rate-limit automated checks.
+    "hashicorp.com": {429},
+    "developer.hashicorp.com": {429},
+    "terraform.io": {429},
+    "www.terraform.io": {429},
+}
+
 # Default policies for troublesome domains that frequently rate-limit automated traffic.
 # These defaults can be extended via CLI flags.
 DEFAULT_IGNORE_429_DOMAINS = {
@@ -96,6 +122,37 @@
 )
 
 
+def is_exception_status(cleaned_url: str, status_code: int) -> bool:
+    """
+    Return True if (cleaned_url, status_code) should be treated as valid based
+    on configured exemptions.
+
+    Rules:
+      - Exact-URL exemptions: compared after stripping any trailing slash.
+      - Domain exemptions: suffix match against the URL hostname.
+    """
+    if not cleaned_url.startswith(("http://", "https://")):
+        return False
+
+    # Exact URL exemptions (normalize by removing trailing slash)
+    normalized = cleaned_url.rstrip("/")
+    allowed = EXEMPT_URL_STATUS.get(normalized)
+    if allowed and status_code in allowed:
+        return True
+
+    # Domain exemptions
+    try:
+        host = urlparse(cleaned_url).hostname or ""
+    except Exception:
+        host = ""
+
+    for domain, codes in EXEMPT_DOMAIN_STATUS.items():
+        if host.endswith(domain) and status_code in codes:
+            return True
+
+    return False
+
+
 def find_markdown_files(directory: str) -> List[str]:
     """Find all markdown files in the given directory and its subdirectories."""
     markdown_files = []
@@ -334,7 +391,11 @@ def check_link_validity(
                 cleaned_url, timeout=timeout, allow_redirects=True
             )
 
-        # Soft-pass 429 for configured domains
+        # Check configured exception rules (domain- and URL-specific)
+        if is_exception_status(cleaned_url, response.status_code):
+            return (url, True, None, response.status_code)
+
+        # Also check for 429 soft-pass for configured domains (backward compatibility)
         if response.status_code == 429 and ignore_429:
             return (
                 url,

src/zenml/models/v2/core/pipeline_run.py

@@ -207,32 +207,6 @@ class PipelineRunResponseBody(ProjectScopedResponseBody):
         default=None,
         title="The reason for the status of the pipeline run.",
     )
-    stack: Optional["StackResponse"] = Field(
-        default=None, title="The stack that was used for this run."
-    )
-    pipeline: Optional["PipelineResponse"] = Field(
-        default=None, title="The pipeline this run belongs to."
-    )
-    build: Optional["PipelineBuildResponse"] = Field(
-        default=None, title="The pipeline build that was used for this run."
-    )
-    schedule: Optional["ScheduleResponse"] = Field(
-        default=None, title="The schedule that was used for this run."
-    )
-    code_reference: Optional["CodeReferenceResponse"] = Field(
-        default=None, title="The code reference that was used for this run."
-    )
-    snapshot_id: Optional[UUID] = Field(
-        default=None, title="The snapshot that was used for this run."
-    )
-    trigger_execution: Optional["TriggerExecutionResponse"] = Field(
-        default=None, title="The trigger execution that triggered this run."
-    )
-    model_version_id: Optional[UUID] = Field(
-        title="The ID of the model version that was "
-        "configured by this pipeline run explicitly.",
-        default=None,
-    )
 
     model_config = ConfigDict(protected_namespaces=())
 
@@ -290,10 +264,6 @@ class PipelineRunResponseMetadata(ProjectScopedResponseMetadata):
         description="DEPRECATED: Template used for the pipeline run.",
         deprecated=True,
     )
-    source_snapshot_id: Optional[UUID] = Field(
-        default=None,
-        description="Source snapshot used for the pipeline run.",
-    )
     is_templatable: bool = Field(
         default=False,
         description="Whether a template can be created from this run.",
@@ -304,6 +274,25 @@ class PipelineRunResponseResources(ProjectScopedResponseResources):
     """Class for all resource models associated with the pipeline run entity."""
 
     snapshot: Optional["PipelineSnapshotResponse"] = None
+    source_snapshot: Optional["PipelineSnapshotResponse"] = None
+    stack: Optional["StackResponse"] = Field(
+        default=None, title="The stack that was used for this run."
+    )
+    pipeline: Optional["PipelineResponse"] = Field(
+        default=None, title="The pipeline this run belongs to."
+    )
+    build: Optional["PipelineBuildResponse"] = Field(
+        default=None, title="The pipeline build that was used for this run."
+    )
+    schedule: Optional["ScheduleResponse"] = Field(
+        default=None, title="The schedule that was used for this run."
+    )
+    code_reference: Optional["CodeReferenceResponse"] = Field(
+        default=None, title="The code reference that was used for this run."
+    )
+    trigger_execution: Optional["TriggerExecutionResponse"] = Field(
+        default=None, title="The trigger execution that triggered this run."
+    )
     model_version: Optional[ModelVersionResponse] = None
     tags: List[TagResponse] = Field(
         title="Tags associated with the pipeline run.",
@@ -387,78 +376,6 @@ def status(self) -> ExecutionStatus:
         """
         return self.get_body().status
 
-    @property
-    def stack(self) -> Optional["StackResponse"]:
-        """The `stack` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().stack
-
-    @property
-    def pipeline(self) -> Optional["PipelineResponse"]:
-        """The `pipeline` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().pipeline
-
-    @property
-    def build(self) -> Optional["PipelineBuildResponse"]:
-        """The `build` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().build
-
-    @property
-    def schedule(self) -> Optional["ScheduleResponse"]:
-        """The `schedule` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().schedule
-
-    @property
-    def trigger_execution(self) -> Optional["TriggerExecutionResponse"]:
-        """The `trigger_execution` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().trigger_execution
-
-    @property
-    def code_reference(self) -> Optional["CodeReferenceResponse"]:
-        """The `schedule` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().code_reference
-
-    @property
-    def snapshot_id(self) -> Optional["UUID"]:
-        """The `snapshot_id` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().snapshot_id
-
-    @property
-    def model_version_id(self) -> Optional[UUID]:
-        """The `model_version_id` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_body().model_version_id
-
     @property
     def run_metadata(self) -> Dict[str, MetadataType]:
         """The `run_metadata` property.
@@ -568,15 +485,6 @@ def template_id(self) -> Optional[UUID]:
         """
         return self.get_metadata().template_id
 
-    @property
-    def source_snapshot_id(self) -> Optional[UUID]:
-        """The `source_snapshot_id` property.
-
-        Returns:
-            the value of the property.
-        """
-        return self.get_metadata().source_snapshot_id
-
     @property
     def is_templatable(self) -> bool:
         """The `is_templatable` property.
@@ -595,6 +503,69 @@ def snapshot(self) -> Optional["PipelineSnapshotResponse"]:
         """
         return self.get_resources().snapshot
 
+    @property
+    def source_snapshot(self) -> Optional["PipelineSnapshotResponse"]:
+        """The `source_snapshot` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().source_snapshot
+
+    @property
+    def stack(self) -> Optional["StackResponse"]:
+        """The `stack` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().stack
+
+    @property
+    def pipeline(self) -> Optional["PipelineResponse"]:
+        """The `pipeline` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().pipeline
+
+    @property
+    def build(self) -> Optional["PipelineBuildResponse"]:
+        """The `build` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().build
+
+    @property
+    def schedule(self) -> Optional["ScheduleResponse"]:
+        """The `schedule` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().schedule
+
+    @property
+    def trigger_execution(self) -> Optional["TriggerExecutionResponse"]:
+        """The `trigger_execution` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().trigger_execution
+
+    @property
+    def code_reference(self) -> Optional["CodeReferenceResponse"]:
+        """The `schedule` property.
+
+        Returns:
+            the value of the property.
+        """
+        return self.get_resources().code_reference
+
     @property
     def model_version(self) -> Optional[ModelVersionResponse]:
         """The `model_version` property.