executorlib 1.9.1__tar.gz → 1.9.3__tar.gz

executorlib-1.9.3/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

{executorlib-1.9.1 → executorlib-1.9.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: executorlib
-Version: 1.9.1
+Version: 1.9.3
 Summary: Up-scale python functions for high performance computing (HPC) with executorlib.
 Project-URL: Homepage, https://github.com/pyiron/executorlib
 Project-URL: Documentation, https://executorlib.readthedocs.io
@@ -50,18 +50,18 @@ Requires-Python: <3.14,>3.9
 Requires-Dist: cloudpickle<=3.1.2,>=2.0.0
 Requires-Dist: pyzmq<=27.1.0,>=25.0.0
 Provides-Extra: all
-Requires-Dist: h5py<=3.15.1,>=3.6.0; extra == 'all'
+Requires-Dist: h5py<=3.16.0,>=3.6.0; extra == 'all'
 Requires-Dist: ipython<=9.9.0,>=7.33.0; extra == 'all'
 Requires-Dist: mpi4py<=4.1.1,>=3.1.4; extra == 'all'
 Requires-Dist: networkx<=3.6.1,>=2.8.8; extra == 'all'
-Requires-Dist: pydantic<=2.12.5,>=2.5.3; extra == 'all'
+Requires-Dist: pydantic<=2.13.4,>=2.5.3; extra == 'all'
 Requires-Dist: pygraphviz<=1.14,>=1.10; extra == 'all'
-Requires-Dist: pysqa==0.3.5; extra == 'all'
+Requires-Dist: pysqa==0.4.1; extra == 'all'
 Provides-Extra: cache
-Requires-Dist: h5py<=3.15.1,>=3.6.0; extra == 'cache'
+Requires-Dist: h5py<=3.16.0,>=3.6.0; extra == 'cache'
 Provides-Extra: cluster
-Requires-Dist: h5py<=3.15.1,>=3.6.0; extra == 'cluster'
-Requires-Dist: pysqa==0.3.5; extra == 'cluster'
+Requires-Dist: h5py<=3.16.0,>=3.6.0; extra == 'cluster'
+Requires-Dist: pysqa==0.4.1; extra == 'cluster'
 Provides-Extra: graph
 Requires-Dist: networkx<=3.6.1,>=2.8.8; extra == 'graph'
 Requires-Dist: pygraphviz<=1.14,>=1.10; extra == 'graph'
@@ -72,7 +72,7 @@ Requires-Dist: pygraphviz<=1.14,>=1.10; extra == 'graphnotebook'
 Provides-Extra: mpi
 Requires-Dist: mpi4py<=4.1.1,>=3.1.4; extra == 'mpi'
 Provides-Extra: validation
-Requires-Dist: pydantic<=2.12.5,>=2.5.3; extra == 'validation'
+Requires-Dist: pydantic<=2.13.4,>=2.5.3; extra == 'validation'
 Description-Content-Type: text/markdown
 
 # executorlib
@@ -221,23 +221,25 @@ as hierarchical job scheduler within the allocations.
   * [SLURM with Flux](https://executorlib.readthedocs.io/en/latest/3-hpc-job.html#slurm-with-flux)
   * [Flux](https://executorlib.readthedocs.io/en/latest/3-hpc-job.html#flux)
 * [Application](https://executorlib.readthedocs.io/en/latest/application.html)
-  * [GPAW](https://executorlib.readthedocs.io/en/latest/5-1-gpaw.html)
-  * [Quantum Espresso](https://executorlib.readthedocs.io/en/latest/5-2-quantum-espresso.html)
+  * [GPAW](https://executorlib.readthedocs.io/en/latest/4-1-gpaw.html)
+  * [Quantum Espresso](https://executorlib.readthedocs.io/en/latest/4-2-quantum-espresso.html)
 * [Trouble Shooting](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html)
   * [Filesystem Usage](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#filesystem-usage)
   * [Firewall Issues](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#firewall-issues)
   * [Message Passing Interface](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#message-passing-interface)
+  * [Test Coverage for Integration Tests](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#test-coverage-for-integration-tests)
   * [Python Version](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#python-version)
   * [Resource Dictionary](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#resource-dictionary)
   * [SSH Connection](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#ssh-connection)
-* [Support & Contribution](https://executorlib.readthedocs.io/en/latest/4-developer.html)
-  * [Issues](https://executorlib.readthedocs.io/en/latest/4-developer.html#issues)
-  * [Pull Requests](https://executorlib.readthedocs.io/en/latest/4-developer.html#pull-requests)
-  * [License](https://executorlib.readthedocs.io/en/latest/4-developer.html#license)
-  * [Modules](https://executorlib.readthedocs.io/en/latest/4-developer.html#modules)
-  * [Interface Class Hierarchy](https://executorlib.readthedocs.io/en/latest/4-developer.html#interface-class-hierarchy)
-  * [Test Environment](https://executorlib.readthedocs.io/en/latest/4-developer.html#test-environment)
-  * [Communication](https://executorlib.readthedocs.io/en/latest/4-developer.html#communication)
-  * [External Libraries](https://executorlib.readthedocs.io/en/latest/4-developer.html#external-libraries)
-  * [External Executables](https://executorlib.readthedocs.io/en/latest/4-developer.html#external-executables)
+* [Support & Contribution](https://executorlib.readthedocs.io/en/latest/5-developer.html)
+  * [Issues](https://executorlib.readthedocs.io/en/latest/5-developer.html#issues)
+  * [Pull Requests](https://executorlib.readthedocs.io/en/latest/5-developer.html#pull-requests)
+  * [License](https://executorlib.readthedocs.io/en/latest/5-developer.html#license)
+  * [Modules](https://executorlib.readthedocs.io/en/latest/5-developer.html#modules)
+  * [Interface Class Hierarchy](https://executorlib.readthedocs.io/en/latest/5-developer.html#interface-class-hierarchy)
+  * [Execution Flow](https://executorlib.readthedocs.io/en/latest/5-developer.html#execution-flow)
+  * [Test Environment](https://executorlib.readthedocs.io/en/latest/5-developer.html#test-environment)
+  * [Communication](https://executorlib.readthedocs.io/en/latest/5-developer.html#communication)
+  * [External Libraries](https://executorlib.readthedocs.io/en/latest/5-developer.html#external-libraries)
+  * [External Executables](https://executorlib.readthedocs.io/en/latest/5-developer.html#external-executables)
 * [Interface](https://executorlib.readthedocs.io/en/latest/api.html)

{executorlib-1.9.1 → executorlib-1.9.3}/README.md

@@ -144,23 +144,25 @@ as hierarchical job scheduler within the allocations.
   * [SLURM with Flux](https://executorlib.readthedocs.io/en/latest/3-hpc-job.html#slurm-with-flux)
   * [Flux](https://executorlib.readthedocs.io/en/latest/3-hpc-job.html#flux)
 * [Application](https://executorlib.readthedocs.io/en/latest/application.html)
-  * [GPAW](https://executorlib.readthedocs.io/en/latest/5-1-gpaw.html)
-  * [Quantum Espresso](https://executorlib.readthedocs.io/en/latest/5-2-quantum-espresso.html)
+  * [GPAW](https://executorlib.readthedocs.io/en/latest/4-1-gpaw.html)
+  * [Quantum Espresso](https://executorlib.readthedocs.io/en/latest/4-2-quantum-espresso.html)
 * [Trouble Shooting](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html)
   * [Filesystem Usage](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#filesystem-usage)
   * [Firewall Issues](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#firewall-issues)
   * [Message Passing Interface](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#message-passing-interface)
+  * [Test Coverage for Integration Tests](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#test-coverage-for-integration-tests)
   * [Python Version](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#python-version)
   * [Resource Dictionary](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#resource-dictionary)
   * [SSH Connection](https://executorlib.readthedocs.io/en/latest/trouble_shooting.html#ssh-connection)
-* [Support & Contribution](https://executorlib.readthedocs.io/en/latest/4-developer.html)
-  * [Issues](https://executorlib.readthedocs.io/en/latest/4-developer.html#issues)
-  * [Pull Requests](https://executorlib.readthedocs.io/en/latest/4-developer.html#pull-requests)
-  * [License](https://executorlib.readthedocs.io/en/latest/4-developer.html#license)
-  * [Modules](https://executorlib.readthedocs.io/en/latest/4-developer.html#modules)
-  * [Interface Class Hierarchy](https://executorlib.readthedocs.io/en/latest/4-developer.html#interface-class-hierarchy)
-  * [Test Environment](https://executorlib.readthedocs.io/en/latest/4-developer.html#test-environment)
-  * [Communication](https://executorlib.readthedocs.io/en/latest/4-developer.html#communication)
-  * [External Libraries](https://executorlib.readthedocs.io/en/latest/4-developer.html#external-libraries)
-  * [External Executables](https://executorlib.readthedocs.io/en/latest/4-developer.html#external-executables)
+* [Support & Contribution](https://executorlib.readthedocs.io/en/latest/5-developer.html)
+  * [Issues](https://executorlib.readthedocs.io/en/latest/5-developer.html#issues)
+  * [Pull Requests](https://executorlib.readthedocs.io/en/latest/5-developer.html#pull-requests)
+  * [License](https://executorlib.readthedocs.io/en/latest/5-developer.html#license)
+  * [Modules](https://executorlib.readthedocs.io/en/latest/5-developer.html#modules)
+  * [Interface Class Hierarchy](https://executorlib.readthedocs.io/en/latest/5-developer.html#interface-class-hierarchy)
+  * [Execution Flow](https://executorlib.readthedocs.io/en/latest/5-developer.html#execution-flow)
+  * [Test Environment](https://executorlib.readthedocs.io/en/latest/5-developer.html#test-environment)
+  * [Communication](https://executorlib.readthedocs.io/en/latest/5-developer.html#communication)
+  * [External Libraries](https://executorlib.readthedocs.io/en/latest/5-developer.html#external-libraries)
+  * [External Executables](https://executorlib.readthedocs.io/en/latest/5-developer.html#external-executables)
 * [Interface](https://executorlib.readthedocs.io/en/latest/api.html)

{executorlib-1.9.1 → executorlib-1.9.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [build-system]
 requires = [
-    "hatchling>=1.27.0,<=1.28.0",
+    "hatchling>=1.27.0,<=1.29.0",
     "hatch-vcs==0.5.0",
     "cloudpickle>=2.0.0,<=3.1.2",
     "pyzmq>=25.0.0,<=27.1.0",
@@ -40,7 +40,7 @@ Documentation = "https://executorlib.readthedocs.io"
 Repository = "https://github.com/pyiron/executorlib"
 
 [project.optional-dependencies]
-cache = ["h5py>=3.6.0,<=3.15.1"]
+cache = ["h5py>=3.6.0,<=3.16.0"]
 graph = [
     "pygraphviz>=1.10,<=1.14",
     "networkx>=2.8.8,<=3.6.1",
@@ -52,17 +52,17 @@ graphnotebook = [
 ]
 mpi = ["mpi4py>=3.1.4,<=4.1.1"]
 cluster = [
-    "pysqa==0.3.5",
-    "h5py>=3.6.0,<=3.15.1",
+    "pysqa==0.4.1",
+    "h5py>=3.6.0,<=3.16.0",
 ]
 validation = [
-    "pydantic>=2.5.3,<=2.12.5",
+    "pydantic>=2.5.3,<=2.13.4",
 ]
 all = [
     "mpi4py>=3.1.4,<=4.1.1",
-    "pysqa==0.3.5",
-    "h5py>=3.6.0,<=3.15.1",
-    "pydantic>=2.5.3,<=2.12.5",
+    "pysqa==0.4.1",
+    "h5py>=3.6.0,<=3.16.0",
+    "pydantic>=2.5.3,<=2.13.4",
     "pygraphviz>=1.10,<=1.14",
     "networkx>=2.8.8,<=3.6.1",
     "ipython>=7.33.0,<=9.9.0",

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '1.9.1'
-__version_tuple__ = version_tuple = (1, 9, 1)
+__version__ = version = '1.9.3'
+__version_tuple__ = version_tuple = (1, 9, 3)
 
 __commit_id__ = commit_id = None

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/executor/flux.py

@@ -51,11 +51,11 @@ class FluxJobExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
-                              *`slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
+                              * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
         flux_executor (flux.job.FluxExecutor): Flux Python interface to submit the workers to flux
         flux_executor_nesting (bool): Provide hierarchically nested Flux job scheduler inside the submitted function.
@@ -154,7 +154,7 @@ class FluxJobExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -283,11 +283,11 @@ class FluxClusterExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
-                              *`slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
+                              * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
         pysqa_config_directory (str, optional): path to the pysqa config directory (only for pysqa based backend).
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
         hostname_localhost (boolean): use localhost instead of the hostname to establish the zmq connection. In the
@@ -380,7 +380,7 @@ class FluxClusterExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -417,7 +417,7 @@ class FluxClusterExecutor(BaseExecutor):
             "cwd": None,
             "openmpi_oversubscribe": openmpi_oversubscribe,
             "slurm_cmd_args": [],
-            "run_time_limit": None,
+            "run_time_max": None,
         }
         if resource_dict is None:
             resource_dict = {}
@@ -540,11 +540,11 @@ def create_flux_executor(
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
-                              *`slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
+                              * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
         flux_executor (flux.job.FluxExecutor): Flux Python interface to submit the workers to flux
         flux_executor_nesting (bool): Provide hierarchically nested Flux job scheduler inside the submitted function.

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/executor/single.py

@@ -50,8 +50,8 @@ class SingleNodeExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
                               * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
@@ -145,7 +145,7 @@ class SingleNodeExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -259,8 +259,8 @@ class TestClusterExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
                               * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
@@ -350,7 +350,7 @@ class TestClusterExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -479,8 +479,8 @@ def create_single_node_executor(
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
                               * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/executor/slurm.py

@@ -52,11 +52,11 @@ class SlurmClusterExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
-                              *`slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
+                              * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
         pysqa_config_directory (str, optional): path to the pysqa config directory (only for pysqa based backend).
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
         hostname_localhost (boolean): use localhost instead of the hostname to establish the zmq connection. In the
@@ -149,7 +149,7 @@ class SlurmClusterExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -293,11 +293,11 @@ class SlurmJobExecutor(BaseExecutor):
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
-                              *`slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
+                              * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
         hostname_localhost (boolean): use localhost instead of the hostname to establish the zmq connection. In the
                                       context of an HPC cluster this essential to be able to communicate to an
@@ -390,7 +390,7 @@ class SlurmJobExecutor(BaseExecutor):
                                                       - do not allow other tasks to use the same compute node.
                                   * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                           multiple tasks in one file.
-                                  * run_time_limit (int): the maximum time the execution of the submitted Python
+                                  * run_time_max (int): the maximum time the execution of the submitted Python
                                                         function is allowed to take in seconds.
                                   * priority (int): the queuing system priority assigned to a given Python function to
                                                     influence the scheduling.
@@ -518,8 +518,8 @@ def create_slurm_executor(
                                                   do not allow other tasks to use the same compute node.
                               * error_log_file (str): path to the error log file, primarily used to merge the log of
                                                       multiple tasks in one file.
-                              * run_time_limit (int): the maximum time the execution of the submitted Python function is
-                                                      allowed to take in seconds.
+                              * run_time_max (int): the maximum time the execution of the submitted Python function is
+                                                    allowed to take in seconds.
                               * priority (int): the queuing system priority assigned to a given Python function to
                                                 influence the scheduling.
                               * slurm_cmd_args (list): Additional command line arguments for the srun call (SLURM only)

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/standalone/command.py

@@ -126,7 +126,7 @@ def generate_slurm_command(
     openmpi_oversubscribe: bool = False,
     slurm_cmd_args: Optional[list[str]] = None,
     pmi_mode: Optional[str] = None,
-    run_time_limit: Optional[int] = None,
+    run_time_max: Optional[int] = None,
 ) -> list[str]:
     """
     Generate the command list for the SLURM interface.
@@ -141,7 +141,7 @@ def generate_slurm_command(
         openmpi_oversubscribe (bool, optional): Whether to oversubscribe the cores. Defaults to False.
         slurm_cmd_args (list[str], optional): Additional command line arguments. Defaults to [].
         pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
-        run_time_limit (int): The maximum runtime in seconds for each task. Default: None
+        run_time_max (int): The maximum runtime in seconds for each task. Default: None
 
     Returns:
         list[str]: The generated command list.
@@ -161,8 +161,8 @@ def generate_slurm_command(
         command_prepend_lst += ["--exact"]
     if openmpi_oversubscribe:
         command_prepend_lst += ["--oversubscribe"]
-    if run_time_limit is not None:
-        command_prepend_lst += ["--time=" + str(run_time_limit // 60 + 1)]
+    if run_time_max is not None:
+        command_prepend_lst += ["--time=" + str(run_time_max // 60 + 1)]
     if slurm_cmd_args is not None and len(slurm_cmd_args) > 0:
         command_prepend_lst += slurm_cmd_args
     return command_prepend_lst

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/standalone/validate.py

@@ -23,9 +23,10 @@ class ResourceDictValidation(BaseModel):
     num_nodes: Optional[int] = None
     exclusive: Optional[bool] = None
     error_log_file: Optional[str] = None
-    run_time_limit: Optional[int] = None
+    run_time_max: Optional[int] = None
     priority: Optional[int] = None
     slurm_cmd_args: Optional[list[str]] = None
+    submission_template: Optional[str] = None
 
     if HAS_PYDANTIC:
 

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/file/backend.py

@@ -45,15 +45,22 @@ def backend_write_file(file_name: str, output: Any, runtime: float) -> None:
     """
     file_name_out = os.path.splitext(file_name)[0][:-2]
     os.rename(file_name, file_name_out + "_r.h5")
-    if "result" in output:
-        dump(
-            file_name=file_name_out + "_r.h5",
-            data_dict={"output": output["result"], "runtime": runtime},
-        )
-    else:
+    try:
+        if "result" in output:
+            dump(
+                file_name=file_name_out + "_r.h5",
+                data_dict={"output": output["result"], "runtime": runtime},
+            )
+        else:
+            dump(
+                file_name=file_name_out + "_r.h5",
+                data_dict={"error": output["error"], "runtime": runtime},
+            )
+    except Exception as serialize_error:
+        # Serialization failed — store the error so the job is not stuck
         dump(
             file_name=file_name_out + "_r.h5",
-            data_dict={"error": output["error"], "runtime": runtime},
+            data_dict={"error": serialize_error, "runtime": runtime},
         )
     os.rename(file_name_out + "_r.h5", file_name_out + "_o.h5")
 

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/file/spawner_pysqa.py

@@ -1,4 +1,5 @@
 import os
+from subprocess import CalledProcessError
 from typing import Optional
 
 from pysqa import QueueAdapter
@@ -69,7 +70,7 @@ def execute_with_pysqa(
             "command": " ".join(command),
             "dependency_list": [str(qid) for qid in task_dependent_lst],
             "working_directory": os.path.abspath(cwd),
-            "run_time_max": resource_dict.get("run_time_limit"),
+            "run_time_max": resource_dict.get("run_time_max"),
         }
         if "cwd" in resource_dict:
             del resource_dict["cwd"]
@@ -90,8 +91,14 @@ def execute_with_pysqa(
             )
         submit_kwargs.update(resource_dict)
         set_current_directory_in_environment()
-        queue_id = qa.submit_job(**submit_kwargs)
-        dump(file_name=file_name, data_dict={"queue_id": queue_id})
+        try:
+            queue_id = qa.submit_job(**submit_kwargs)
+        except (ValueError, CalledProcessError) as error:
+            dump(file_name=file_name, data_dict={"error": error})
+            file_name_out = os.path.splitext(file_name)[0][:-2]
+            os.rename(file_name_out + "_i.h5", file_name_out + "_o.h5")
+        else:
+            dump(file_name=file_name, data_dict={"queue_id": queue_id})
     return queue_id
 
 

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/interactive/blockallocation.py

@@ -1,7 +1,7 @@
 import queue
 import random
 from concurrent.futures import Future
-from threading import Event, Thread
+from threading import Event, Lock, Thread
 from typing import Callable, Optional
 
 from executorlib.standalone.command import get_interactive_execute_command
@@ -83,6 +83,8 @@ class BlockAllocationTaskScheduler(TaskSchedulerBase):
         self_id = random.getrandbits(128)
         self._self_id = self_id
         _interrupt_bootup_dict[self._self_id] = False
+        alive_workers = [max_workers]
+        alive_workers_lock = Lock()
         bootup_events = [Event() for _ in range(self._max_workers)]
         bootup_events[0].set()
         self._set_process(
@@ -99,6 +101,8 @@ class BlockAllocationTaskScheduler(TaskSchedulerBase):
                             if worker_id + 1 < self._max_workers
                             else None
                         ),
+                        "alive_workers": alive_workers,
+                        "alive_workers_lock": alive_workers_lock,
                     },
                 )
                 for worker_id in range(self._max_workers)
@@ -227,6 +231,8 @@ def _execute_multiple_tasks(
     restart_limit: int = 0,
     bootup_event: Optional[Event] = None,
     next_bootup_event: Optional[Event] = None,
+    alive_workers: Optional[list] = None,
+    alive_workers_lock: Optional[Lock] = None,
     **kwargs,
 ) -> None:
     """
@@ -258,6 +264,9 @@ def _execute_multiple_tasks(
         bootup_event (Event): Event to wait on before submitting the job to the scheduler, ensuring workers are
                               submitted in worker_id order.
         next_bootup_event (Event): Event to signal after job submission, unblocking the next worker.
+        alive_workers (list): Single-element list [N] tracking how many worker threads are still alive. Shared across
+                              all worker threads; decremented when a worker is permanently dead.
+        alive_workers_lock (Lock): Lock protecting alive_workers from concurrent modification.
     """
     if bootup_event is not None:
         bootup_event.wait()
@@ -279,11 +288,13 @@ def _execute_multiple_tasks(
     )
     restart_counter = 0
     while True:
-        if not interface.status and restart_counter > restart_limit:
-            interface.status = True  # no more restarts
-            interface_initialization_exception = ExecutorlibSocketError(
-                "SocketInterface crashed during execution."
+        if not interface.status and restart_counter >= restart_limit:
+            _drain_dead_worker(
+                future_queue=future_queue,
+                alive_workers=alive_workers,
+                alive_workers_lock=alive_workers_lock,
             )
+            break
         elif not interface.status:
             interface.bootup()
             interface_initialization_exception = _set_init_function(
@@ -321,6 +332,47 @@ def _execute_multiple_tasks(
                 task_done(future_queue=future_queue)
 
 
+def _drain_dead_worker(
+    future_queue: queue.Queue,
+    alive_workers: Optional[list] = None,
+    alive_workers_lock: Optional[Lock] = None,
+) -> None:
+    """Handle a permanently dead worker by recycling or failing its tasks.
+
+    If healthy workers remain, tasks are recycled back into the shared queue
+    so they can be picked up. If all workers are dead, tasks are failed
+    immediately with ExecutorlibSocketError. In both cases, the worker's
+    shutdown message is consumed to prevent hangs in shutdown().
+    """
+    if alive_workers is not None and alive_workers_lock is not None:
+        with alive_workers_lock:
+            if alive_workers[0] > 0:
+                alive_workers[0] -= 1
+    while True:
+        try:
+            task_dict = future_queue.get(timeout=1)
+        except queue.Empty:
+            continue
+        if "shutdown" in task_dict and task_dict["shutdown"]:
+            task_done(future_queue=future_queue)
+            break
+        elif "fn" in task_dict and "future" in task_dict:
+            if alive_workers is not None and alive_workers_lock is not None:
+                with alive_workers_lock:
+                    has_healthy_workers = alive_workers[0] > 0
+            else:
+                has_healthy_workers = False
+            if has_healthy_workers:
+                future_queue.put(task_dict)
+                task_done(future_queue=future_queue)
+            else:
+                f = task_dict.pop("future")
+                f.set_exception(
+                    ExecutorlibSocketError("SocketInterface crashed during execution.")
+                )
+                task_done(future_queue=future_queue)
+
+
 def _set_init_function(
     interface: SocketInterface,
     init_function: Optional[Callable] = None,

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/interactive/spawner_flux.py

@@ -44,7 +44,7 @@ class FluxPythonSpawner(BaseSpawner):
         flux_executor (flux.job.FluxExecutor, optional): The FluxExecutor instance. Defaults to None.
         flux_executor_nesting (bool, optional): Whether to use nested FluxExecutor. Defaults to False.
         flux_log_files (bool, optional): Write flux stdout and stderr files. Defaults to False.
-        run_time_limit (int): The maximum runtime in seconds for each task. Default: None
+        run_time_max (int): The maximum runtime in seconds for each task. Default: None
     """
 
     def __init__(
@@ -62,7 +62,7 @@ class FluxPythonSpawner(BaseSpawner):
         flux_executor: Optional[flux.job.FluxExecutor] = None,
         flux_executor_nesting: bool = False,
         flux_log_files: bool = False,
-        run_time_limit: Optional[int] = None,
+        run_time_max: Optional[int] = None,
     ):
         super().__init__(
             cwd=cwd,
@@ -80,7 +80,7 @@ class FluxPythonSpawner(BaseSpawner):
         self._flux_log_files = flux_log_files
         self._priority = priority
         self._future = None
-        self._run_time_limit = run_time_limit
+        self._run_time_max = run_time_max
 
     def bootup(
         self,
@@ -131,8 +131,8 @@ class FluxPythonSpawner(BaseSpawner):
         if self._cwd is not None:
             jobspec.cwd = self._cwd
             os.makedirs(self._cwd, exist_ok=True)
-        if self._run_time_limit is not None:
-            jobspec.duration = self._run_time_limit
+        if self._run_time_max is not None:
+            jobspec.duration = self._run_time_max
         file_prefix = "flux_" + str(self._worker_id)
         if self._flux_log_files and self._cwd is not None:
             jobspec.stderr = os.path.join(self._cwd, file_prefix + ".err")

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/interactive/spawner_pysqa.py

@@ -32,7 +32,7 @@ class PysqaSpawner(BaseSpawner):
         pmi_mode: Optional[str] = None,
         config_directory: Optional[str] = None,
         backend: Optional[str] = None,
-        run_time_limit: Optional[int] = None,
+        run_time_max: Optional[int] = None,
         **kwargs,
     ):
         """
@@ -52,7 +52,7 @@ class PysqaSpawner(BaseSpawner):
             pmi_mode (str, optional): PMI interface to use (OpenMPI v5 requires pmix) default is None
             config_directory (str, optional): path to the pysqa config directory (only for pysqa based backend).
             backend (str): name of the backend used to spawn tasks.
-            run_time_limit (int): The maximum runtime in seconds for each task. Default: None
+            run_time_max (int): The maximum runtime in seconds for each task. Default: None
         """
         super().__init__(
             cwd=cwd,
@@ -71,7 +71,7 @@ class PysqaSpawner(BaseSpawner):
         self._pysqa_submission_kwargs = kwargs
         self._process: Optional[int] = None
         self._queue_adapter: Optional[QueueAdapter] = None
-        self._run_time_limit = run_time_limit
+        self._run_time_max = run_time_max
 
     def bootup(
         self,
@@ -195,7 +195,7 @@ class PysqaSpawner(BaseSpawner):
             command=" ".join(self.generate_command(command_lst=command_lst)),
             working_directory=working_directory,
             cores=int(self._cores * self._threads_per_core),
-            run_time_max=self._run_time_limit,
+            run_time_max=self._run_time_max,
             **self._pysqa_submission_kwargs,
         )
 
@@ -238,6 +238,8 @@ def create_pysqa_block_allocation_scheduler(
     cores_per_worker = executor_kwargs.get("cores", 1)
     if "cwd" in executor_kwargs and executor_kwargs["cwd"] is not None:
         executor_kwargs["cwd"] = os.path.abspath(executor_kwargs["cwd"])
+    elif cache_directory is not None:
+        executor_kwargs["cwd"] = os.path.abspath(cache_directory)
     if cache_directory is not None:
         executor_kwargs["cache_directory"] = os.path.abspath(cache_directory)
     else:

{executorlib-1.9.1 → executorlib-1.9.3}/src/executorlib/task_scheduler/interactive/spawner_slurm.py

@@ -32,7 +32,7 @@ class SrunSpawner(SubprocessSpawner):
         openmpi_oversubscribe: bool = False,
         slurm_cmd_args: Optional[list[str]] = None,
         pmi_mode: Optional[str] = None,
-        run_time_limit: Optional[int] = None,
+        run_time_max: Optional[int] = None,
     ):
         """
         Srun interface implementation.
@@ -48,7 +48,7 @@ class SrunSpawner(SubprocessSpawner):
             openmpi_oversubscribe (bool, optional): Whether to oversubscribe the cores. Defaults to False.
             slurm_cmd_args (list[str], optional): Additional command line arguments. Defaults to [].
             pmi_mode (str): PMI interface to use (OpenMPI v5 requires pmix) default is None
-            run_time_limit (int): The maximum runtime in seconds for each task. Default: None
+            run_time_max (int): The maximum runtime in seconds for each task. Default: None
         """
         super().__init__(
             cwd=cwd,
@@ -62,7 +62,7 @@ class SrunSpawner(SubprocessSpawner):
         self._num_nodes = num_nodes
         self._exclusive = exclusive
         self._pmi_mode = pmi_mode
-        self._run_time_limit = run_time_limit
+        self._run_time_max = run_time_max
 
     def generate_command(self, command_lst: list[str]) -> list[str]:
         """
@@ -84,7 +84,7 @@ class SrunSpawner(SubprocessSpawner):
             openmpi_oversubscribe=self._openmpi_oversubscribe,
             slurm_cmd_args=self._slurm_cmd_args,
             pmi_mode=self._pmi_mode,
-            run_time_limit=self._run_time_limit,
+            run_time_max=self._run_time_max,
         )
         return super().generate_command(
             command_lst=command_prepend_lst + command_lst,

executorlib-1.9.1/.gitignore

@@ -1,5 +0,0 @@
-*.pyc
-.DS_Store
-.coverage
-.idea/
-.vscode/