Version bump to v1.3.0

Fix --extra-index-url is added for different command line switches

README.md

@@ -8,8 +8,8 @@ ML-Ops scheduler & orchestration solution supporting Linux, macOS and Windows**
 [![GitHub license](https://img.shields.io/github/license/allegroai/clearml-agent.svg)](https://img.shields.io/github/license/allegroai/clearml-agent.svg)
 [![PyPI pyversions](https://img.shields.io/pypi/pyversions/clearml-agent.svg)](https://img.shields.io/pypi/pyversions/clearml-agent.svg)
 [![PyPI version shields.io](https://img.shields.io/pypi/v/clearml-agent.svg)](https://img.shields.io/pypi/v/clearml-agent.svg)
-[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/allegroai)](https://artifacthub.io/packages/search?repo=allegroai)
-    
+[![PyPI Downloads](https://pepy.tech/badge/clearml-agent/month)](https://pypi.org/project/clearml-agent/)
+[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/allegroai)](https://artifacthub.io/packages/search?repo=allegroai)    
 </div>
 
 ---

clearml_agent/backend_api/config/default/agent.conf

@@ -83,7 +83,7 @@
         # set the optional priority packages to be installed before the rest of the required packages,
         # In case a package installation fails, the package will be ignored,
         # and the virtual environment process will continue
-        # priority_optional_packages: ["pygobject", ]
+        priority_optional_packages: ["pygobject", ]
 
         # set the post packages to be installed after all the rest of the required packages
         # post_packages: ["horovod", ]

clearml_agent/commands/worker.py

@@ -139,8 +139,8 @@ from clearml_agent.helper.singleton import Singleton
 from clearml_agent.session import Session
 from .events import Events
 
-DOCKER_ROOT_CONF_FILE = "/root/clearml.conf"
-DOCKER_DEFAULT_CONF_FILE = "/root/default_clearml.conf"
+DOCKER_ROOT_CONF_FILE = "/tmp/clearml.conf"  # assuming we can always access/mount this file
+DOCKER_DEFAULT_CONF_FILE = "~/default_clearml.conf"
 
 
 sys_random = random.SystemRandom()
@@ -1109,7 +1109,11 @@ class Worker(ServiceCommandSection):
             if w.id.startswith(worker_name) and w.id != self.worker_id]
         gpus = []
         for w in our_workers:
-            gpus += [int(g) for g in w.split(':')[-1].lower().replace('gpu', '').split(',')]
+            for g in w.split(':')[-1].lower().replace('gpu', '').split(','):
+                try:
+                    gpus += [int(g.strip())]
+                except (ValueError, TypeError):
+                    print("INFO: failed parsing GPU int('{}') - skipping".format(g))
         available_gpus = list(set(gpu_indexes) - set(gpus))
 
         return available_gpus
@@ -1120,7 +1124,13 @@ class Worker(ServiceCommandSection):
             raise ValueError("Dynamic GPU allocation is not supported by the ClearML-server")
         available_gpus = [prop["value"] for prop in available_gpus if prop["key"] == 'available_gpus']
         if available_gpus:
-            available_gpus = [int(g) for g in available_gpus[-1].split(',')]
+            gpus = []
+            for g in available_gpus[-1].split(','):
+                try:
+                    gpus += [int(g.strip())]
+                except (ValueError, TypeError):
+                    print("INFO: failed parsing GPU int('{}') - skipping".format(g))
+            available_gpus = gpus
         if not isinstance(gpu_queues, dict):
             gpu_queues = dict(gpu_queues)
 
@@ -1281,12 +1291,9 @@ class Worker(ServiceCommandSection):
             raise ValueError("Running in Docker mode, 'docker' command was not found")
 
         self._worker_tags = kwargs.get('child_report_tags', None)
-        self._impersonate_as_task_owner = kwargs.get('use_owner_token', False)
-        if self._impersonate_as_task_owner:
-            if not self._session.check_min_api_version("2.14"):
-                raise ValueError("Server does not support --use-owner-token option (incompatible API version)")
-            if self._session.feature_set == "basic":
-                raise ValueError("Server does not support --use-owner-token option")
+
+        self._use_owner_token(kwargs.get('use_owner_token', False))
+
         self._standalone_mode = kwargs.get('standalone_mode', False)
         self._services_mode = kwargs.get('services_mode', False)
         # must have docker in services_mode
@@ -1795,7 +1802,7 @@ class Worker(ServiceCommandSection):
     def _apply_extra_configuration(self):
         # store a few things we updated in runtime (TODO: we should list theme somewhere)
         agent_config = self._session.config["agent"].copy()
-        agent_config_keys = ["cuda_version", "cudnn_version", "default_python", "worker_id", "debug"]
+        agent_config_keys = ["cuda_version", "cudnn_version", "default_python", "worker_id", "worker_name", "debug"]
         try:
             self._session.load_vaults()
         except Exception as ex:
@@ -1882,6 +1889,9 @@ class Worker(ServiceCommandSection):
                 base_interpreter=package_api.requirements_manager.get_interpreter(),
                 requirement_substitutions=[OnlyExternalRequirements],
             )
+            # manually update the current state,
+            # for the external git reference chance (in the replace callback)
+            package_api.requirements_manager.update_installed_packages_state(package_api.freeze())
             # make sure we run the handlers
             cached_requirements = \
                 {k: package_api.requirements_manager.replace(requirements[k] or '')
@@ -1992,7 +2002,7 @@ class Worker(ServiceCommandSection):
 
         if entry_point == "clone_task" or entry_point == "reuse_task":
             change = 'ENTRYPOINT if [ ! -s "{trains_conf}" ] ; then ' \
-                     'cp {default_trains_conf} {trains_conf} ; ' \
+                     'cp {default_trains_conf} {trains_conf} && export CLEARML_CONFIG_FILE={trains_conf}; ' \
                      ' fi ; clearml-agent execute --id {task_id} --standalone-mode {clone}'.format(
                         default_trains_conf=DOCKER_DEFAULT_CONF_FILE,
                         trains_conf=DOCKER_ROOT_CONF_FILE,
@@ -2244,6 +2254,9 @@ class Worker(ServiceCommandSection):
                         base_interpreter=package_api.requirements_manager.get_interpreter(),
                         requirement_substitutions=[OnlyExternalRequirements]
                     )
+                    # manually update the current state,
+                    # for the external git reference chance (in the replace callback)
+                    package_api.requirements_manager.update_installed_packages_state(package_api.freeze())
                     # make sure we run the handlers
                     cached_requirements = \
                         {k: package_api.requirements_manager.replace(requirements[k] or '')
@@ -2343,7 +2356,7 @@ class Worker(ServiceCommandSection):
         if ENV_TASK_EXTRA_PYTHON_PATH.get():
             python_path = add_python_path(python_path, ENV_TASK_EXTRA_PYTHON_PATH.get())
         if python_path:
-            os.environ['PYTHONPATH'] = python_path
+            os.environ['PYTHONPATH'] = os.pathsep.join(filter(None, (os.environ.get('PYTHONPATH', None), python_path)))
 
         # check if we want to run as another user, only supported on linux
         if ENV_TASK_EXECUTE_AS_USER.get() and is_linux_platform():
@@ -2367,6 +2380,10 @@ class Worker(ServiceCommandSection):
         if sys.getfilesystemencoding() == 'ascii' and not os.environ.get("PYTHONIOENCODING"):
             os.environ["PYTHONIOENCODING"] = "utf-8"
 
+        # check if we need to update backwards compatible OS environment
+        if not os.environ.get("TRAINS_CONFIG_FILE") and os.environ.get("CLEARML_CONFIG_FILE"):
+            os.environ["TRAINS_CONFIG_FILE"] = os.environ.get("CLEARML_CONFIG_FILE")
+
         print("Starting Task Execution:\n".format(current_task.id))
         exit_code = -1
         try:
@@ -2967,6 +2984,11 @@ class Worker(ServiceCommandSection):
             - a new working directory (replacing the working_dir in the task's script section)
             - a requirements manager instance
         """
+        os.environ["CLEARML_TASK_SCRIPT_ENTRY"] = execution.entry_point
+        os.environ["CLEARML_TASK_WORKING_DIR"] = execution.working_dir
+        os.environ["CLEARML_VENV_PATH"] = str(venv_folder)
+        os.environ["CLEARML_GIT_ROOT"] = git_root
+
         script = os.path.expanduser(os.path.expandvars(script))
 
         try:
@@ -2984,10 +3006,6 @@ class Worker(ServiceCommandSection):
             task.to_dict(), separators=(',', ':'), default=str
         )
         os.environ["CLEARML_CUSTOM_BUILD_OUTPUT"] = script_output_file.name
-        os.environ["CLEARML_TASK_SCRIPT_ENTRY"] = execution.entry_point
-        os.environ["CLEARML_TASK_WORKING_DIR"] = execution.working_dir
-        os.environ["CLEARML_VENV_PATH"] = str(venv_folder)
-        os.environ["CLEARML_GIT_ROOT"] = git_root
 
         try:
             subprocess.check_call([script])
@@ -2999,7 +3017,7 @@ class Worker(ServiceCommandSection):
 
         output = Path(script_output_file.name).read_text()
         if not output:
-            raise SkippedCustomBuildScript("Build script {} is not found".format(script))
+            raise SkippedCustomBuildScript("Build script {} did not return any output".format(script))
 
         try:
             output = json.loads(output)
@@ -3193,6 +3211,10 @@ class Worker(ServiceCommandSection):
                 if standalone_mode:
                     self.package_api = VirtualenvPip(**package_manager_params)
                 else:
+                    if not Path(executable_name).is_file():
+                        executable_name_path = find_executable(executable_name)
+                        print("Interpreter '{}' found at '{}'".format(executable_name, executable_name_path))
+                        executable_name = executable_name_path
                     # we can change it, no one is going to use it anyhow
                     package_manager_params['path'] = None
                     package_manager_params['interpreter'] = executable_name
@@ -3631,7 +3653,7 @@ class Worker(ServiceCommandSection):
                     "{python_single_digit}.$i -m pip --version && " +
                     "export LOCAL_PYTHON=$(which {python_single_digit}.$i) && break ; done",
                     "[ ! -z $LOCAL_PYTHON ] || export CLEARML_APT_INSTALL=\"$CLEARML_APT_INSTALL {python_single_digit}-pip\"",  # noqa
-                    "[ -z \"$CLEARML_APT_INSTALL\" ] || (apt-get update && apt-get install -y $CLEARML_APT_INSTALL)",
+                    "[ -z \"$CLEARML_APT_INSTALL\" ] || (apt-get update -y ; apt-get install -y $CLEARML_APT_INSTALL)",
                 ]
 
             if preprocess_bash_script:
@@ -3672,6 +3694,7 @@ class Worker(ServiceCommandSection):
         base_cmd += (
             (['--name', name] if name else []) +
             ['-v', conf_file+':'+DOCKER_ROOT_CONF_FILE] +
+            ['-e', "CLEARML_CONFIG_FILE={}".format(DOCKER_ROOT_CONF_FILE)] +
             (['-v', host_ssh_cache+':'+mount_ssh] if host_ssh_cache else []) +
             (['-v', host_apt_cache+':'+mount_apt_cache] if host_apt_cache else []) +
             (['-v', host_pip_cache+':'+mount_pip_cache] if host_pip_cache else []) +
@@ -3762,12 +3785,17 @@ class Worker(ServiceCommandSection):
         # patch venv folder to new location
         script_dir = script_dir.replace(venv_folder, new_venv_folder)
         # New command line execution
-        command = RunasArgv('bash', '-c', 'HOME=\"{}\" PATH=\"{}\" PYTHONPATH=\"{}\" TRAINS_CONFIG_FILE={} {}'.format(
-            home_folder,
-            os.environ.get('PATH', '').replace(venv_folder, new_venv_folder),
-            os.environ.get('PYTHONPATH', '').replace(venv_folder, new_venv_folder),
-            user_trains_conf,
-            command.serialize().replace(venv_folder, new_venv_folder)))
+        command = RunasArgv(
+            'bash', '-c',
+            'HOME=\"{}\" PATH=\"{}\" PYTHONPATH=\"{}\" '
+            'TRAINS_CONFIG_FILE={} CLEARML_CONFIG_FILE={} {}'.format(
+                home_folder,
+                os.environ.get('PATH', '').replace(venv_folder, new_venv_folder),
+                os.environ.get('PYTHONPATH', '').replace(venv_folder, new_venv_folder),
+                user_trains_conf, user_trains_conf,
+                command.serialize().replace(venv_folder, new_venv_folder)
+            )
+        )
         command.set_uid(user_uid=user_uid, user_gid=user_uid)
 
         return command, script_dir
@@ -3933,6 +3961,14 @@ class Worker(ServiceCommandSection):
         # type: (str) -> bool
         return re.fullmatch(r"^[a-zA-Z0-9][a-zA-Z0-9_.-]+$", name) is not None
 
+    def _use_owner_token(self, use_owner_token=False):
+        self._impersonate_as_task_owner = use_owner_token
+        if self._impersonate_as_task_owner:
+            if not self._session.check_min_api_version("2.14"):
+                raise ValueError("Server does not support --use-owner-token option (incompatible API version)")
+            if self._session.feature_set == "basic":
+                raise ValueError("Server does not support --use-owner-token option")
+
 
 if __name__ == "__main__":
     pass

clearml_agent/external/requirements_parser/parser.py

@@ -1,6 +1,9 @@
 import os
+import re
 import warnings
 
+from clearml_agent.definitions import PIP_EXTRA_INDICES
+
 from .requirement import Requirement
 
 
@@ -42,9 +45,14 @@ def parse(reqstr, cwd=None):
                     yield requirement
         elif line.startswith('-f') or line.startswith('--find-links') or \
                 line.startswith('-i') or line.startswith('--index-url') or \
-                line.startswith('--extra-index-url') or \
                 line.startswith('--no-index'):
             warnings.warn('Private repos not supported. Skipping.')
+        elif line.startswith('--extra-index-url'):
+            extra_index = line[len('--extra-index-url'):].strip()
+            extra_index = re.sub(r"\s+#.*$", "", extra_index)  # strip comments
+            if extra_index and extra_index not in PIP_EXTRA_INDICES:
+                PIP_EXTRA_INDICES.append(extra_index)
+                print(f"appended {extra_index} to list of extra pip indices")
             continue
         elif line.startswith('-Z') or line.startswith('--always-unzip'):
             warnings.warn('Unused option --always-unzip. Skipping.')

clearml_agent/glue/k8s.py

@@ -18,7 +18,7 @@ from typing import Text, List, Callable, Any, Collection, Optional, Union
 import yaml
 
 from clearml_agent.commands.events import Events
-from clearml_agent.commands.worker import Worker, get_task_container, set_task_container
+from clearml_agent.commands.worker import Worker, get_task_container, set_task_container, get_next_task
 from clearml_agent.definitions import ENV_DOCKER_IMAGE
 from clearml_agent.errors import APIError
 from clearml_agent.helper.base import safe_remove_file
@@ -362,7 +362,7 @@ class K8sIntegration(Worker):
             print('Failed getting number of used pods: {}'.format(ex))
             return -2
 
-    def run_one_task(self, queue: Text, task_id: Text, worker_args=None, **_):
+    def run_one_task(self, queue: Text, task_id: Text, worker_args=None, task_session=None, **_):
         print('Pulling task {} launching on kubernetes cluster'.format(task_id))
         task_data = self._session.api_client.tasks.get_all(id=[task_id])[0]
 
@@ -398,11 +398,19 @@ class K8sIntegration(Worker):
             self.conf_file_content
             or Path(self._session._config_file).read_text()
         ).encode("ascii")
-        create_clearml_conf = "echo '{}' | base64 --decode >> ~/clearml.conf".format(
+
+        create_clearml_conf = ["echo '{}' | base64 --decode >> ~/clearml.conf".format(
             base64.b64encode(
                 hocon_config_encoded
             ).decode('ascii')
-        )
+        )]
+
+        if task_session:
+            create_clearml_conf.append(
+                "export CLEARML_AUTH_TOKEN=$(echo '{}' | base64 --decode)".format(
+                    base64.b64encode(task_session.token.encode("ascii")).decode('ascii')
+                )
+            )
 
         if self.ports_mode:
             print("Kubernetes looking for available pod to use")
@@ -594,19 +602,22 @@ class K8sIntegration(Worker):
                          extra_docker_bash_script=extra_docker_bash_script)
              for line in container_bash_script])
 
-        create_init_script = \
-            "echo '{}' | base64 --decode >> ~/__start_agent__.sh ; " \
+        extra_bash_commands = list(create_clearml_conf or [])
+
+        extra_bash_commands.append(
+            "echo '{}' | base64 --decode >> ~/__start_agent__.sh ; "
             "/bin/bash ~/__start_agent__.sh".format(
                 base64.b64encode(
                     script_encoded.encode('ascii')
                 ).decode('ascii'))
+        )
 
         # Notice: we always leave with exit code 0, so pods are never restarted
         container = self._merge_containers(
             container,
             dict(name=name, image=docker_image,
                  command=['/bin/bash'],
-                 args=['-c', '{} ; {} ; exit 0'.format(create_clearml_conf, create_init_script)])
+                 args=['-c', '{} ; exit 0'.format(' ; '.join(extra_bash_commands))])
         )
 
         if template['spec']['containers']:
@@ -685,7 +696,7 @@ class K8sIntegration(Worker):
             "--",
             "/bin/sh",
             "-c",
-            "{} ; {}".format(create_clearml_conf, container_bash_script.format(
+            "{} ; {}".format(" ; ".join(create_clearml_conf or []), container_bash_script.format(
                 extra_bash_init_cmd=self.extra_bash_init_script or "",
                 extra_docker_bash_script=docker_bash or "",
                 task_id=task_id
@@ -742,14 +753,16 @@ class K8sIntegration(Worker):
 
                 # get next task in queue
                 try:
-                    response = self._session.api_client.queues.get_next_task(queue=queue)
+                    response = get_next_task(
+                        self._session, queue=queue, get_task_info=self._impersonate_as_task_owner
+                    )
                 except Exception as e:
                     print("Warning: Could not access task queue [{}], error: {}".format(queue, e))
                     continue
                 else:
                     try:
-                        task_id = response.entry.task
-                    except AttributeError:
+                        task_id = response["entry"]["task"]
+                    except (KeyError, TypeError, AttributeError):
                         print("No tasks in queue {}".format(queue))
                         continue
                     events_service.send_log_events(
@@ -761,8 +774,26 @@ class K8sIntegration(Worker):
                         level="INFO",
                     )
 
+                    task_session = None
+                    if self._impersonate_as_task_owner:
+                        try:
+                            task_user = response["task_info"]["user"]
+                            task_company = response["task_info"]["company"]
+                        except (KeyError, TypeError, AttributeError):
+                            print("Error: cannot retrieve owner user for the task '{}', skipping".format(task_id))
+                            continue
+
+                        task_session = self.get_task_session(task_user, task_company)
+                        if not task_session:
+                            print(
+                                "Error: Could not login as the user '{}' for the task '{}', skipping".format(
+                                    task_user, task_id
+                                )
+                            )
+                            continue
+
                     self.report_monitor(ResourceMonitor.StatusReport(queues=queues, queue=queue, task=task_id))
-                    self.run_one_task(queue, task_id, worker_params)
+                    self.run_one_task(queue, task_id, worker_params, task_session)
                     self.report_monitor(ResourceMonitor.StatusReport(queues=self.queues))
                     break
             else:
@@ -773,7 +804,7 @@ class K8sIntegration(Worker):
             if self._session.config["agent.reload_config"]:
                 self.reload_config()
 
-    def k8s_daemon(self, queue):
+    def k8s_daemon(self, queue, **kwargs):
         """
         Start the k8s Glue service.
         This service will be pulling tasks from *queue* and scheduling them for execution using kubectl.
@@ -784,8 +815,10 @@ class K8sIntegration(Worker):
 
         :param list(str) queue: queue name to pull from
         """
-        return self.daemon(queues=[ObjectID(name=queue)] if queue else None,
-                           log_level=logging.INFO, foreground=True, docker=False)
+        return self.daemon(
+            queues=[ObjectID(name=queue)] if queue else None,
+            log_level=logging.INFO, foreground=True, docker=False, **kwargs,
+        )
 
     @classmethod
     def get_ssh_server_bash(cls, ssh_port_number):

clearml_agent/helper/package/external_req.py

@@ -95,7 +95,8 @@ class ExternalRequirements(SimpleSubstitution):
                 vcs._set_ssh_url()
                 new_req_line = 'git+{}{}{}'.format(
                     '' if scheme and '://' in vcs.url else scheme,
-                    vcs.url_with_auth, fragment
+                    vcs_url if session.config.get('agent.force_git_ssh_protocol', None) else vcs.url_with_auth,
+                    fragment
                 )
                 if new_req_line != req_line:
                     furl_line = furl(new_req_line)
@@ -174,5 +175,11 @@ class OnlyExternalRequirements(ExternalRequirements):
         # Do not store the skipped requirements
         # mark skip package
         if super(OnlyExternalRequirements, self).match(req):
+            if self.is_already_installed(req):
+                print("No need to reinstall \'{}\' from VCS, "
+                      "the exact same version is already installed".format(req.name))
+                return Text('')
+
             return self._add_vcs_credentials(req, self._session)
+
         return Text('')

clearml_agent/helper/package/priority_req.py

@@ -1,3 +1,4 @@
+import re
 from typing import Text
 
 from .base import PackageManager
@@ -11,13 +12,14 @@ class PriorityPackageRequirement(SimpleSubstitution):
 
     def __init__(self, *args, **kwargs):
         super(PriorityPackageRequirement, self).__init__(*args, **kwargs)
+        self._replaced_packages = {}
         # check if we need to replace the packages:
         priority_packages = self.config.get('agent.package_manager.priority_packages', None)
         if priority_packages:
-            self.__class__.name = priority_packages
+            self.__class__.name = [p.lower() for p in priority_packages]
         priority_optional_packages = self.config.get('agent.package_manager.priority_optional_packages', None)
         if priority_optional_packages:
-            self.__class__.optional_package_names = priority_optional_packages
+            self.__class__.optional_package_names = [p.lower() for p in priority_optional_packages]
 
     def match(self, req):
         # match both Cython & cython
@@ -28,7 +30,9 @@ class PriorityPackageRequirement(SimpleSubstitution):
         Replace a requirement
         :raises: ValueError if version is pre-release
         """
-        if req.name in self.optional_package_names:
+        self._replaced_packages[req.name] = req.line
+
+        if req.name.lower() in self.optional_package_names:
             # noinspection PyBroadException
             try:
                 if PackageManager.out_of_scope_install_package(str(req)):
@@ -39,6 +43,41 @@ class PriorityPackageRequirement(SimpleSubstitution):
         PackageManager.out_of_scope_install_package(str(req))
         return Text(req)
 
+    def replace_back(self, list_of_requirements):
+        """
+        :param list_of_requirements: {'pip': ['a==1.0', ]}
+        :return: {'pip': ['a==1.0', ]}
+        """
+        # if we replaced setuptools, it means someone requested it, and since freeze will not contain it,
+        # we need to add it manually
+        if not self._replaced_packages or "setuptools" not in self._replaced_packages:
+            return list_of_requirements
+
+        try:
+            for k, lines in list_of_requirements.items():
+                # k is either pip/conda
+                if k not in ('pip', 'conda'):
+                    continue
+                for i, line in enumerate(lines):
+                    if not line or line.lstrip().startswith('#'):
+                        continue
+                    parts = [p for p in re.split(r'\s|=|\.|<|>|~|!|@|#', line) if p]
+                    if not parts:
+                        continue
+                    # if we found setuptools, do nothing
+                    if parts[0] == "setuptools":
+                        return list_of_requirements
+
+            # if we are here it means we have not found setuptools
+            # we should add it:
+            if "pip" in list_of_requirements:
+                list_of_requirements["pip"] = [self._replaced_packages["setuptools"]] + list_of_requirements["pip"]
+
+        except Exception as ex:  # noqa
+            return list_of_requirements
+
+        return list_of_requirements
+
 
 class PackageCollectorRequirement(SimpleSubstitution):
     """

clearml_agent/helper/package/pytorch.py

@@ -7,13 +7,14 @@ from furl import furl
 import urllib.parse
 from operator import itemgetter
 from html.parser import HTMLParser
-from typing import Text
+from typing import Text, Optional, Dict
 
 import attr
 import requests
 
 import six
-from .requirements import SimpleSubstitution, FatalSpecsResolutionError, SimpleVersion
+from .requirements import SimpleSubstitution, FatalSpecsResolutionError, SimpleVersion, MarkerRequirement
+from ...external.requirements_parser.requirement import Requirement
 
 OS_TO_WHEEL_NAME = {"linux": "linux_x86_64", "windows": "win_amd64"}
 
@@ -179,6 +180,7 @@ class PytorchRequirement(SimpleSubstitution):
         self.python_version_string = None
         self.python_major_minor_str = None
         self.python = None
+        self._fix_setuptools = None
         self.exceptions = []
         self._original_req = []
 
@@ -318,12 +320,14 @@ class PytorchRequirement(SimpleSubstitution):
                 from pip._internal.commands.show import search_packages_info
                 installed_torch = list(search_packages_info([req.name]))
                 # notice the comparison order, the first part will make sure we have a valid installed package
-                if installed_torch and installed_torch[0]['version'] and \
-                        req.compare_version(installed_torch[0]['version']):
+                installed_torch_version = (getattr(installed_torch[0], 'version', None) or installed_torch[0]['version']) \
+                    if installed_torch else None
+                if installed_torch and installed_torch_version and \
+                        req.compare_version(installed_torch_version):
                     print('PyTorch: requested "{}" version {}, using pre-installed version {}'.format(
-                        req.name, req.specs[0] if req.specs else 'unspecified', installed_torch[0]['version']))
+                        req.name, req.specs[0] if req.specs else 'unspecified', installed_torch_version))
                     # package already installed, do nothing
-                    req.specs = [('==', str(installed_torch[0]['version']))]
+                    req.specs = [('==', str(installed_torch_version))]
                     return '{} {} {}'.format(req.name, req.specs[0][0], req.specs[0][1]), True
         except Exception:
             pass
@@ -364,6 +368,10 @@ class PytorchRequirement(SimpleSubstitution):
             else:
                 print('Trying PyTorch CUDA version {} support'.format(torch_url_key))
 
+        # fix broken pytorch setuptools incompatibility
+        if closest_matched_version and SimpleVersion.compare_versions(closest_matched_version, "<", "1.11.0"):
+            self._fix_setuptools = "setuptools < 59"
+
         if not url:
             url = PytorchWheel(
                 torch_version=fix_version(version),
@@ -504,7 +512,7 @@ class PytorchRequirement(SimpleSubstitution):
                 for i, line in enumerate(lines):
                     if not line or line.lstrip().startswith('#'):
                         continue
-                    parts = [p for p in re.split('\s|=|\.|<|>|~|!|@|#', line) if p]
+                    parts = [p for p in re.split(r'\s|=|\.|<|>|~|!|@|#', line) if p]
                     if not parts:
                         continue
                     for req, new_req in self._original_req:
@@ -526,6 +534,16 @@ class PytorchRequirement(SimpleSubstitution):
 
         return list_of_requirements
 
+    def post_scan_add_req(self):  # type: () -> Optional[MarkerRequirement]
+        """
+        Allows the RequirementSubstitution to add an extra line/requirements after
+        the initial requirements scan is completed.
+        Called only once per requirements.txt object
+        """
+        if self._fix_setuptools:
+            return MarkerRequirement(Requirement.parse(self._fix_setuptools))
+        return None
+
     MAP = {
         "windows": {
             "cuda100": {

clearml_agent/helper/package/requirements.py

@@ -628,10 +628,23 @@ class RequirementsManager(object):
 
         result = list(result)
         # add post scan add requirements call back
+        double_req_set = None
         for h in self.handlers:
-            req = h.post_scan_add_req()
-            if req:
-                result.append(req.tostr())
+            reqs = h.post_scan_add_req()
+            if reqs:
+                if double_req_set is None:
+                    def safe_parse_name(line):
+                        try:
+                            return Requirement.parse(line).name
+                        except:  # noqa
+                            return None
+                    double_req_set = set([safe_parse_name(r) for r in result if r])
+
+                for r in (reqs if isinstance(reqs, (tuple, list)) else [reqs]):
+                    if r and (not r.name or r.name not in double_req_set):
+                        result.append(r.tostr())
+                    elif r:
+                        print("SKIPPING additional auto installed package: \"{}\"".format(r))
 
         return join_lines(result)
 

clearml_agent/helper/repo.py

@@ -529,6 +529,13 @@ class Git(VCS):
         "GIT_SSH_COMMAND": "ssh -oBatchMode=yes",
     }
 
+    def __init__(self, *args, **kwargs):
+        super(Git, self).__init__(*args, **kwargs)
+        try:
+            self.call("config", "--global", "--replace-all", "safe.directory", "*", cwd=self.location)
+        except:  # noqa
+            pass
+
     @staticmethod
     def remote_branch_name(branch):
         return [

clearml_agent/version.py

@@ -1 +1 @@
-__version__ = '1.2.0rc6'
+__version__ = '1.3.0'

docs/clearml.conf

@@ -34,12 +34,12 @@ agent {
     # force_git_ssh_user: git
 
     # unique name of this worker, if None, created based on hostname:process_id
-    # Overridden with os environment: CLEARML_WORKER_NAME
+    # Overridden with os environment: CLEARML_WORKER_ID
     # worker_id: "clearml-agent-machine1:gpu0"
     worker_id: ""
 
     # worker name, replaces the hostname when creating a unique name for this worker
-    # Overridden with os environment: CLEARML_WORKER_ID
+    # Overridden with os environment: CLEARML_WORKER_NAME
     # worker_name: "clearml-agent-machine1"
     worker_name: ""
 

examples/k8s_glue_example.py

@@ -65,6 +65,10 @@ def parse_args():
         help="Limit the maximum number of pods that this service can run at the same time."
              "Should not be used with ports-mode"
     )
+    parser.add_argument(
+        "--use-owner-token", action="store_true", default=False,
+        help="Generate and use task owner token for the execution of each task"
+    )
     return parser.parse_args()
 
 
@@ -87,7 +91,7 @@ def main():
             ssh_port_number=args.ssh_server_port) if args.ssh_server_port else None,
         namespace=args.namespace, max_pods_limit=args.max_pods or None,
     )
-    k8s.k8s_daemon(args.queue)
+    k8s.k8s_daemon(args.queue, use_owner_token=args.use_owner_token)
 
 
 if __name__ == "__main__":

requirements.txt

@@ -8,7 +8,7 @@ psutil>=3.4.2,<5.9.0
 pyhocon>=0.3.38,<0.4.0
 pyparsing>=2.0.3,<2.5.0
 python-dateutil>=2.4.2,<2.9.0
-pyjwt>=1.6.4,<2.1.0
+pyjwt>=2.4.0,<2.5.0
 PyYAML>=3.12,<5.5.0
 requests>=2.20.0,<2.26.0
 six>=1.13.0,<1.16.0

setup.py

@@ -61,6 +61,7 @@ setup(
         'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
         'License :: OSI Approved :: Apache Software License',
     ],