cloudos-cli 2.44.0__tar.gz → 2.45.0__tar.gz

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudos_cli
-Version: 2.44.0
+Version: 2.45.0
 Summary: Python package for interacting with CloudOS
 Home-page: https://github.com/lifebit-ai/cloudos-cli
 Author: David Piñeyro
@@ -370,6 +370,8 @@ Executing run...
 	Your job took 420 seconds to complete successfully.
 ```
 
+When there are duplicated `--workflow-name` in the platform, the flag `--last` can be added, and it will use the latest import of that pipeline in the workspace, based on the date. For example, the pipeline `lifebit-process` was imported on May 23 2025 and again on May 30 2025, with the `--last` flag, it will use the import of May 30 of 2025.
+
 #### Send a bash job to CloudOS (sequential sample processing)
 
 A bash job can be sent to CloudOS using the command `bash` and the subcommand `job`. In this case, the `--workflow-name` must be a bash job already

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/README.md

@@ -335,6 +335,8 @@ Executing run...
 	Your job took 420 seconds to complete successfully.
 ```
 
+When there are duplicated `--workflow-name` in the platform, the flag `--last` can be added, and it will use the latest import of that pipeline in the workspace, based on the date. For example, the pipeline `lifebit-process` was imported on May 23 2025 and again on May 30 2025, with the `--last` flag, it will use the import of May 30 of 2025.
+
 #### Send a bash job to CloudOS (sequential sample processing)
 
 A bash job can be sent to CloudOS using the command `bash` and the subcommand `job`. In this case, the `--workflow-name` must be a bash job already

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli/__main__.py

@@ -238,6 +238,9 @@ def configure(ctx, profile, make_default):
 @click.option('--workflow-name',
               help='The name of a CloudOS workflow or pipeline.',
               required=True)
+@click.option('--last',
+              help=('When the workflows are duplicated, use the latest imported workflow (by date).'),
+              is_flag=True)
 @click.option('--job-config',
               help=('A config file similar to a nextflow.config file, ' +
                     'but only with the parameters to use with your job.'))
@@ -370,6 +373,7 @@ def run(ctx,
         workspace_id,
         project_name,
         workflow_name,
+        last,
         job_config,
         parameter,
         git_commit,
@@ -488,8 +492,8 @@ def run(ctx,
     if verbose:
         print('\t...Detecting workflow type')
     cl = Cloudos(cloudos_url, apikey, cromwell_token)
-    workflow_type = cl.detect_workflow(workflow_name, workspace_id, verify_ssl)
-    is_module = cl.is_module(workflow_name, workspace_id, verify_ssl)
+    workflow_type = cl.detect_workflow(workflow_name, workspace_id, verify_ssl, last)
+    is_module = cl.is_module(workflow_name, workspace_id, verify_ssl, last)
     if execution_platform == 'hpc' and workflow_type == 'wdl':
         raise ValueError(f'The workflow {workflow_name} is a WDL workflow. ' +
                          'WDL is not supported on HPC execution platform.')
@@ -529,7 +533,7 @@ def run(ctx,
         print('\t...Preparing objects')
     j = jb.Job(cloudos_url, apikey, None, workspace_id, project_name, workflow_name,
                mainfile=wdl_mainfile, importsfile=wdl_importsfile,
-               repository_platform=repository_platform, verify=verify_ssl)
+               repository_platform=repository_platform, verify=verify_ssl, last=last)
     if verbose:
         print('\tThe following Job object was created:')
         print('\t' + str(j))
@@ -2056,6 +2060,9 @@ def remove_profile(ctx, profile):
 @click.option('--workflow-name',
               help='The name of a CloudOS workflow or pipeline.',
               required=True)
+@click.option('--last',
+              help=('When the workflows are duplicated, use the latest imported workflow (by date).'),
+              is_flag=True)
 @click.option('-p',
               '--parameter',
               multiple=True,
@@ -2136,6 +2143,7 @@ def run_bash_job(ctx,
                  workspace_id,
                  project_name,
                  workflow_name,
+                 last,
                  parameter,
                  job_name,
                  do_not_save_logs,
@@ -2203,7 +2211,7 @@ def run_bash_job(ctx,
 
     j = jb.Job(cloudos_url, apikey, None, workspace_id, project_name, workflow_name,
                mainfile=None, importsfile=None,
-               repository_platform=repository_platform, verify=verify_ssl)
+               repository_platform=repository_platform, verify=verify_ssl, last=last)
 
     if job_queue is not None:
         batch = True
@@ -2291,6 +2299,9 @@ def run_bash_job(ctx,
 @click.option('--workflow-name',
               help='The name of a CloudOS workflow or pipeline.',
               required=True)
+@click.option('--last',
+              help=('When the workflows are duplicated, use the latest imported workflow (by date).'),
+              is_flag=True)
 @click.option('-p',
               '--parameter',
               multiple=True,
@@ -2410,6 +2421,7 @@ def run_bash_array_job(ctx,
                        workspace_id,
                        project_name,
                        workflow_name,
+                       last,
                        parameter,
                        job_name,
                        do_not_save_logs,
@@ -2512,7 +2524,7 @@ def run_bash_array_job(ctx,
 
     j = jb.Job(cloudos_url, apikey, None, workspace_id, project_name, workflow_name,
                mainfile=None, importsfile=None,
-               repository_platform=repository_platform, verify=verify_ssl)
+               repository_platform=repository_platform, verify=verify_ssl, last=last)
 
     # retrieve columns
     r = j.retrieve_cols_from_array_file(

cloudos_cli-2.45.0/cloudos_cli/_version.py

@@ -0,0 +1 @@
+__version__ = '2.45.0'

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli/clos.py

@@ -10,6 +10,7 @@ from cloudos_cli.utils.cloud import find_cloud
 from cloudos_cli.utils.errors import BadRequestException, JoBNotCompletedException, NotAuthorisedException
 from cloudos_cli.utils.requests import retry_requests_get, retry_requests_post, retry_requests_put
 import pandas as pd
+from cloudos_cli.utils.last_wf import youngest_workflow_id_by_name
 
 # GLOBAL VARS
 JOB_COMPLETED = 'completed'
@@ -462,7 +463,7 @@ class Cloudos:
         return df
 
     def get_workflow_list(self, workspace_id, verify=True, get_all=True,
-                          page=1, page_size=10, max_page_size=1000,
+                          page=1, page_size=10, max_page_size=100,
                           archived_status=False):
         """Get all the workflows from a CloudOS workspace.
 
@@ -570,7 +571,7 @@ class Cloudos:
             df = df_full.loc[:, present_columns]
         return df
 
-    def detect_workflow(self, workflow_name, workspace_id, verify=True):
+    def detect_workflow(self, workflow_name, workspace_id, verify=True, last=False):
         """Detects workflow type: nextflow or wdl.
 
         Parameters
@@ -590,14 +591,14 @@ class Cloudos:
             The workflow type detected
         """
         # get list with workflow types
-        wt_all = self.workflow_content_query(workspace_id, workflow_name, verify=verify, query="workflowType")
+        wt_all = self.workflow_content_query(workspace_id, workflow_name, verify=verify, query="workflowType", last=last)
         # make unique
         wt = list(dict.fromkeys(wt_all))
         if len(wt) > 1:
             raise ValueError(f'More than one workflow type detected for {workflow_name}: {wt}')
         return str(wt[0])
 
-    def is_module(self, workflow_name, workspace_id, verify=True):
+    def is_module(self, workflow_name, workspace_id, verify=True, last=False):
         """Detects whether the workflow is a system module or not.
 
         System modules use fixed queues, so this check is important to
@@ -620,7 +621,7 @@ class Cloudos:
             True, if the workflow is a system module, false otherwise.
         """
         # get a list of all groups
-        group = self.workflow_content_query(workspace_id, workflow_name, verify=verify, query="group")
+        group = self.workflow_content_query(workspace_id, workflow_name, verify=verify, query="group", last=last)
 
         module_groups = ['system-tools',
                          'data-factory-data-connection-etl',
@@ -636,7 +637,7 @@ class Cloudos:
             return False
 
     def get_project_list(self, workspace_id, verify=True, get_all=True,
-                         page=1, page_size=10, max_page_size=1000):
+                         page=1, page_size=10, max_page_size=100):
         """Get all the project from a CloudOS workspace.
 
         Parameters
@@ -915,8 +916,8 @@ class Cloudos:
 
         return project_id
 
-    def get_workflow_content(self, workspace_id, workflow_name, verify=True):
-        """Retrieve the workflow content from API.
+    def get_workflow_max_pagination(self, workspace_id, workflow_name, verify=True):
+        """Retrieve the workflows max pages from API.
 
         Parameters
         ----------
@@ -931,8 +932,8 @@ class Cloudos:
 
         Returns
         -------
-        dict
-            The server response containing workflow details.
+        int
+            The server response with max pagination for workflows.
 
         Raises
         ------
@@ -944,24 +945,82 @@ class Cloudos:
             "Content-type": "application/json",
             "apikey": self.apikey
         }
+        # determine pagination, there might be a lot with the same name
         url = f"{self.cloudos_url}/api/v3/workflows?teamId={workspace_id}&search={workflow_name}"
         response = retry_requests_get(url, headers=headers, verify=verify)
         if response.status_code >= 400:
             raise BadRequestException(response)
-        content = json.loads(response.content)
-        return content
+        pag_content = json.loads(response.content)
+        max_pagination = pag_content["paginationMetadata"]["Pagination-Count"]
+        if max_pagination == 0:
+            raise ValueError(f'No workflow found with name: {workflow_name} in workspace: {workspace_id}')
 
-    def workflow_content_query(self, workspace_id, workflow_name, verify=True, query="workflowType"):
+        return max_pagination
 
-        content = self.get_workflow_content(workspace_id, workflow_name, verify=verify)
+    def get_workflow_content(self, workspace_id, workflow_name, verify=True, last=False, max_page_size=100):
+        """Retrieve the workflow content from API.
+
+        Parameters
+        ----------
+        workspace_id : str
+            The CloudOS workspace ID to search for the workflow.
+        workflow_name : str
+            The name of the workflow to search for.
+        verify : [bool | str], optional
+            Whether to use SSL verification or not. Alternatively, if
+            a string is passed, it will be interpreted as the path to
+            the SSL certificate file. Default is True.
+
+        Returns
+        -------
+        dict
+            The server response containing workflow details.
+
+        Raises
+        ------
+        BadRequestException
+            If the request to retrieve the project fails with a status code
+            indicating an error.
+        """
+        headers = {
+            "Content-type": "application/json",
+            "apikey": self.apikey
+        }
+        max_pagination = self.get_workflow_max_pagination(workspace_id, workflow_name, verify=verify)
+
+        # get all the matching content
+        if max_pagination > max_page_size:
+            content = {"workflows": []}
+            for page_start in range(0, max_pagination, max_page_size):
+                page_size = min(max_page_size, max_pagination - page_start)
+                url = f"{self.cloudos_url}/api/v3/workflows?teamId={workspace_id}&search={workflow_name}&pageSize={page_size}&page={page_start // max_page_size + 1}"
+                response = retry_requests_get(url, headers=headers, verify=verify)
+                # keep structure as a dict
+                content["workflows"].extend(json.loads(response.content).get("workflows", []))
+        else:
+            url = f"{self.cloudos_url}/api/v3/workflows?teamId={workspace_id}&search={workflow_name}&pageSize={max_pagination}"
+            response = retry_requests_get(url, headers=headers, verify=verify)
+            # return all content
+            content = json.loads(response.content)
+
+        if response.status_code >= 400:
+            raise BadRequestException(response)
 
         # check for duplicates
         wf = [wf.get("name") for wf in content.get("workflows", []) if wf.get("name") == workflow_name]
 
-        if len(wf) == 0:
-            raise ValueError(f'No workflow found with name: {workflow_name}')
-        if len(wf) > 1:
-            raise ValueError(f'More than one workflow found with name: {workflow_name}')
+        if len(wf) == 0 or len(content["workflows"]) == 0:
+            raise ValueError(f'No workflow found with name: {workflow_name} in workspace: {workspace_id}')
+        if len(wf) > 1 and not last:
+            raise ValueError(f'More than one workflow found with name: {workflow_name}. ' + \
+                             "To run the last imported workflow use '--last' flag.")
+        else:
+            content = youngest_workflow_id_by_name(content, workflow_name)
+        return content
+
+    def workflow_content_query(self, workspace_id, workflow_name, verify=True, query="workflowType", last=False):
+
+        content = self.get_workflow_content(workspace_id, workflow_name, verify=verify, last=last)
 
         # use 'query' to look in the content
         return [wf.get(query) for wf in content.get("workflows", []) if wf.get("name") == workflow_name]

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli/jobs/job.py

@@ -52,6 +52,7 @@ class Job(Cloudos):
     workspace_id: str
     project_name: str
     workflow_name: str
+    last: bool = False
     verify: Union[bool, str] = True
     mainfile: str = None
     importsfile: str = None
@@ -148,7 +149,7 @@ class Job(Cloudos):
             raise ValueError('Your specified resource is not supported. ' +
                              f'Use one of the following: {allowed_resources}')
         if resource == 'workflows':
-            content = self.get_workflow_content(workspace_id, name, verify=verify)
+            content = self.get_workflow_content(workspace_id, name, verify=verify, last=self.last)
             for element in content["workflows"]:
                 if (element["name"] == name and element["workflowType"] == "docker" and
                         not element["archived"]["status"]):

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli/utils/__init__.py

@@ -9,5 +9,6 @@ from .cloud import find_cloud
 from .cloud import find_cloud
 from .array_job import is_valid_regex, is_glob_pattern, is_probably_regex, classify_pattern, generate_datasets_for_project, get_file_or_folder_id
 from .details import get_path
+from .last_wf import youngest_workflow_id_by_name
 
-__all__ = ['errors', 'requests', 'resources', 'cloud', 'details', 'array_job']
+__all__ = ['errors', 'requests', 'resources', 'cloud', 'details', 'array_job', 'last_wf']

cloudos_cli-2.45.0/cloudos_cli/utils/last_wf.py

@@ -0,0 +1,60 @@
+from datetime import datetime, timezone
+
+
+def _parse_iso8601_z(dt_str):
+    """
+    Parse an ISO8601 timestamp string that may end with 'Z' (UTC).
+    Returns a timezone-aware datetime, or None if parsing fails.
+    """
+    if not dt_str:
+        return None
+    if dt_str.endswith('Z'):
+        dt_str = dt_str[:-1] + '+00:00'
+    try:
+        return datetime.fromisoformat(dt_str)
+    except ValueError:
+        return None
+
+
+def youngest_workflow_id_by_name(content, target_name, ignore_case=False, return_workflow=True):
+    """
+    Find the most recently created workflow whose .name matches `target_name`.
+    
+    Parameters
+    ----------
+    content : dict
+        API response dict containing top-level "workflows".
+    target_name : str
+        Name to match.
+    ignore_case : bool, default False
+        If True, case-insensitive comparison.
+    return_workflow : bool, default False
+        If True, return the whole workflow dict; else return its _id.
+    
+    Returns
+    -------
+    str | dict | None
+        _id (default), full workflow dict (if return_workflow=True), or None if no match.
+    """
+    workflows = content.get('workflows') or []
+    if ignore_case:
+        target_cmp = target_name.lower()
+        matches = [wf for wf in workflows if wf.get('name', '').lower() == target_cmp]
+    else:
+        matches = [wf for wf in workflows if wf.get('name') == target_name]
+    
+    if not matches:
+        return None
+    
+    def sort_key(wf):
+        created = _parse_iso8601_z(wf.get('createdAt'))
+        updated = _parse_iso8601_z(wf.get('updatedAt'))
+        # Prefer createdAt; fall back to updatedAt; else epoch 0
+        return created or updated or datetime.fromtimestamp(0, tz=timezone.utc)
+    
+    youngest = max(matches, key=sort_key)
+    # keep structure as dictionary, will return inner dictionary just for the selected workflow
+    youngest_d = {"workflows":[ youngest ]}
+    youngest_id = youngest.get('_id')
+
+    return youngest_d if return_workflow else youngest_id

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudos_cli
-Version: 2.44.0
+Version: 2.45.0
 Summary: Python package for interacting with CloudOS
 Home-page: https://github.com/lifebit-ai/cloudos-cli
 Author: David Piñeyro
@@ -370,6 +370,8 @@ Executing run...
 	Your job took 420 seconds to complete successfully.
 ```
 
+When there are duplicated `--workflow-name` in the platform, the flag `--last` can be added, and it will use the latest import of that pipeline in the workspace, based on the date. For example, the pipeline `lifebit-process` was imported on May 23 2025 and again on May 30 2025, with the `--last` flag, it will use the import of May 30 of 2025.
+
 #### Send a bash job to CloudOS (sequential sample processing)
 
 A bash job can be sent to CloudOS using the command `bash` and the subcommand `job`. In this case, the `--workflow-name` must be a bash job already

{cloudos_cli-2.44.0 → cloudos_cli-2.45.0}/cloudos_cli.egg-info/SOURCES.txt

@@ -28,6 +28,7 @@ cloudos_cli/utils/array_job.py
 cloudos_cli/utils/cloud.py
 cloudos_cli/utils/details.py
 cloudos_cli/utils/errors.py
+cloudos_cli/utils/last_wf.py
 cloudos_cli/utils/requests.py
 cloudos_cli/utils/resources.py
 tests/__init__.py

cloudos_cli-2.44.0/cloudos_cli/_version.py

@@ -1 +0,0 @@
-__version__ = '2.44.0'