feat!: set the mode directly in the client (#287)

CHANGELOG.md

@@ -10,6 +10,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Changed
 
 - Algo categories are not checked anymore in local mode. Validations based on inputs and outputs are sufficient.
+- BREAKING CHANGE: the backend type is now set in the Client, the env variable `DEBUG_SPAWNER` is not used anymore. Default value is deployed (#287)
+
+API before
+
+```sh
+export DEBUG_SPAWNER=subprocess
+```
+
+```python
+client = substra.Client(debug=True)
+```
+
+API after
+
+```python
+client = substra.Client(backend_type=substra.BackendType.LOCAL_SUBPROCESS)
+```
 
 ### Removed
 

Makefile

@@ -1,14 +1,14 @@
-.PHONY: pyclean doc test
+.PHONY: pyclean doc test doc-cli doc-sdk
 
 pyclean:
 	find . -type f -name "*.py[co]" -delete
 	find . -type d -name "__pycache__" -delete
 	rm -rf build/ dist/ *.egg-info
 
-doc-cli:
+doc-cli: pyclean
 	python bin/generate_cli_documentation.py
 
-doc-sdk:
+doc-sdk: pyclean
 	python bin/generate_sdk_documentation.py
 	python bin/generate_sdk_schemas_documentation.py
 	python bin/generate_sdk_schemas_documentation.py --models --output-path='references/sdk_models.md'

references/sdk.md

@@ -2,7 +2,7 @@
 
 # Client
 ```text
-Client(url: Optional[str] = None, token: Optional[str] = None, retry_timeout: int = 300, insecure: bool = False, debug: bool = False)
+Client(url: Union[str, NoneType] = None, token: Union[str, NoneType] = None, retry_timeout: int = 300, insecure: bool = False, backend_type: substra.sdk.schemas.BackendType = <BackendType.REMOTE: 'deployed'>)
 ```
 
 Create a client
@@ -21,11 +21,14 @@ Defaults to 5 minutes.
  - `insecure (bool, optional)`: If True, the client can call a not-certified backend. This is
 for development purposes.
 Defaults to False.
- - `debug (bool, optional)`: Whether to use the default or debug mode.
-In debug mode, new assets are created locally but can access assets from
-the deployed Substra platform. The platform is in read-only mode.
-Defaults to False.
-Additionally, you can set the environment variable `DEBUG_SPAWNER` to `docker` if you want the tasks to
+ - `backend_type (schemas.BackendType, optional)`: Which mode to use. Defaults to deployed.
+In deployed mode, assets are registered on a deployed platform which also executes the tasks.
+In local mode (subprocess or docker), if no URL is given then all assets are created locally and tasks are
+executed locally.
+In local mode (subprocess or docker), if a URL is given then the mode is a hybrid one: new assets are
+created locally but can access assets from the deployed Substra platform. The platform is in read-only mode
+and tasks are executed locally.
+The local mode is either docker or subprocess mode: `docker` if you want the tasks to
 be executed in containers (default) or `subprocess` to execute them in Python subprocesses (faster,
 experimental: The `Dockerfile` commands are not executed, requires dependencies to be installed locally).
 ## backend_mode
@@ -384,7 +387,7 @@ algorithm.
  - `pathlib.Path`: Path of the downloaded model
 ## from_config_file
 ```text
-from_config_file(profile_name: str = 'default', config_path: Union[str, pathlib.Path] = '~/.substra', tokens_path: Union[str, pathlib.Path] = '~/.substra-tokens', token: Optional[str] = None, retry_timeout: int = 300, debug: bool = False)
+from_config_file(profile_name: str = 'default', config_path: Union[str, pathlib.Path] = '~/.substra', tokens_path: Union[str, pathlib.Path] = '~/.substra-tokens', token: Union[str, NoneType] = None, retry_timeout: int = 300, backend_type: substra.sdk.schemas.BackendType = <BackendType.REMOTE: 'deployed'>)
 ```
 
 Returns a new Client configured with profile data from configuration files.
@@ -401,10 +404,17 @@ Defaults to '~/.substra-tokens'.
 instead of any token found at tokens_path). Defaults to None.
  - `retry_timeout (int, optional)`: Number of seconds before attempting a retry call in case
 of timeout. Defaults to 5 minutes.
- - `debug (bool, required)`: Whether to use the default or debug mode. In debug mode, new assets are
-created locally but can get remote assets. The deployed platform is in
-read-only mode.
-Defaults to False.
+ - `backend_type (schemas.BackendType, optional)`: Which mode to use. Defaults to deployed.
+In deployed mode, assets are registered on a deployed platform which also executes the tasks.
+In local mode (subprocess or docker), if no URL is given then all assets are created locally and tasks
+are executed locally.
+In local mode (subprocess or docker), if a URL is given then the mode is a hybrid one: new assets are
+created locally but can access assets from the deployed Substra platform. The platform is in read-only
+mode and tasks are executed locally.
+The local mode is either docker or subprocess mode: `docker` if you want the tasks to
+be executed in containers (default) or `subprocess` to execute them in Python subprocesses (faster,
+experimental: The `Dockerfile` commands are not executed, requires dependencies to be installed
+locally).
 
 **Returns:**
 

substra/__init__.py

@@ -1,9 +1,9 @@
 from substra.__version__ import __version__
-from substra.sdk import BackendType
 from substra.sdk import Client
 from substra.sdk import exceptions
 from substra.sdk import models
 from substra.sdk import schemas
+from substra.sdk.schemas import BackendType
 
 __all__ = [
     "__version__",

substra/sdk/__init__.py

@@ -1,7 +1,7 @@
 from substra.sdk import models
 from substra.sdk import schemas
 from substra.sdk.client import Client
-from substra.sdk.config import BackendType
+from substra.sdk.schemas import BackendType
 from substra.sdk.utils import retry_on_exception
 
 __all__ = [

substra/sdk/backends/__init__.py

@@ -1,11 +1,13 @@
+from substra.sdk import schemas
 from substra.sdk.backends.local.backend import Local
 from substra.sdk.backends.remote.backend import Remote
 
 _BACKEND_CHOICES = {
-    "remote": Remote,
-    "local": Local,
+    schemas.BackendType.REMOTE: Remote,
+    schemas.BackendType.LOCAL_DOCKER: Local,
+    schemas.BackendType.LOCAL_SUBPROCESS: Local,
 }
 
 
 def get(name, *args, **kwargs):
-    return _BACKEND_CHOICES[name.lower()](*args, **kwargs)
+    return _BACKEND_CHOICES[name](*args, **kwargs, backend_type=name)

substra/sdk/backends/base.py

@@ -1,6 +1,6 @@
 import abc
 
-from substra.sdk.config import BackendType
+from substra.sdk.schemas import BackendType
 
 
 class BaseBackend(abc.ABC):

substra/sdk/backends/local/backend.py

@@ -1,6 +1,5 @@
 import copy
 import logging
-import os
 import shutil
 import typing
 import warnings
@@ -23,7 +22,6 @@
 from substra.sdk.backends import base
 from substra.sdk.backends.local import compute
 from substra.sdk.backends.local import dal
-from substra.sdk.config import BackendType
 
 logger = logging.getLogger(__name__)
 
@@ -35,23 +33,17 @@ class Local(base.BaseBackend):
 
     org_counter = 1
 
-    def __init__(self, backend, *args, **kwargs):
+    def __init__(self, backend, backend_type, *args, **kwargs):
         self._local_worker_dir = Path.cwd() / "local-worker"
         self._local_worker_dir.mkdir(exist_ok=True)
 
-        self._debug_spawner = BackendType(os.getenv("DEBUG_SPAWNER", BackendType.LOCAL_DOCKER))
-        if self._debug_spawner == BackendType.LOCAL_SUBPROCESS:
-            logger.info(
-                "Environment variable DEBUG_SPAWNER is set to subprocess: "
-                "running Substra tasks with Python subprocess"
-            )
-
+        self._execution_mode = backend_type
         # create a store to abstract the db
         self._db = dal.DataAccess(backend, local_worker_dir=self._local_worker_dir)
         self._worker = compute.Worker(
             self._db,
             local_worker_dir=self._local_worker_dir,
-            debug_spawner=self._debug_spawner,
+            debug_spawner=self._execution_mode,
         )
 
         self._org_id = f"MyOrg{Local.org_counter}MSP"
@@ -76,9 +68,9 @@ def temp_directory(self):
         return self._db.tmp_dir
 
     @property
-    def backend_mode(self) -> BackendType:
+    def backend_mode(self) -> schemas.BackendType:
         """Get the backend mode"""
-        return self._debug_spawner
+        return self._execution_mode
 
     def login(self, username, password):
         self._db.login(username, password)

substra/sdk/backends/local/compute/spawner/__init__.py

@@ -1,7 +1,7 @@
 from substra.sdk.backends.local.compute.spawner.base import BaseSpawner
 from substra.sdk.backends.local.compute.spawner.docker import Docker
 from substra.sdk.backends.local.compute.spawner.subprocess import Subprocess
-from substra.sdk.config import BackendType
+from substra.sdk.schemas import BackendType
 
 __all__ = ["BaseSpawner", "Docker", "Subprocess"]
 

substra/sdk/backends/remote/backend.py

@@ -12,7 +12,6 @@
 from substra.sdk import schemas
 from substra.sdk.backends import base
 from substra.sdk.backends.remote import rest_client
-from substra.sdk.config import BackendType
 
 logger = logging.getLogger(__name__)
 
@@ -30,14 +29,15 @@ def _find_asset_field(data, field):
 
 
 class Remote(base.BaseBackend):
-    def __init__(self, url, insecure, token, retry_timeout):
+    def __init__(self, url, insecure, token, retry_timeout, backend_type):
         self._client = rest_client.Client(url, insecure, token)
         self._retry_timeout = retry_timeout or DEFAULT_RETRY_TIMEOUT
+        assert backend_type == self.backend_mode
 
     @property
-    def backend_mode(self) -> BackendType:
+    def backend_mode(self) -> schemas.BackendType:
         """Get the backend mode: deployed"""
-        return BackendType.DEPLOYED
+        return schemas.BackendType.REMOTE
 
     def login(self, username, password):
         return self._client.login(username, password)

substra/sdk/client.py

@@ -49,7 +49,7 @@ def wrapper(*args, **kwargs):
     return wrapper
 
 
-class Client(object):
+class Client:
     """Create a client
 
     Args:
@@ -66,11 +66,14 @@ class Client(object):
         insecure (bool, optional): If True, the client can call a not-certified backend. This is
             for development purposes.
             Defaults to False.
-        debug (bool, optional): Whether to use the default or debug mode.
-            In debug mode, new assets are created locally but can access assets from
-            the deployed Substra platform. The platform is in read-only mode.
-            Defaults to False.
-            Additionally, you can set the environment variable `DEBUG_SPAWNER` to `docker` if you want the tasks to
+        backend_type (schemas.BackendType, optional): Which mode to use. Defaults to deployed.
+            In deployed mode, assets are registered on a deployed platform which also executes the tasks.
+            In local mode (subprocess or docker), if no URL is given then all assets are created locally and tasks are
+            executed locally.
+            In local mode (subprocess or docker), if a URL is given then the mode is a hybrid one: new assets are
+            created locally but can access assets from the deployed Substra platform. The platform is in read-only mode
+            and tasks are executed locally.
+            The local mode is either docker or subprocess mode: `docker` if you want the tasks to
             be executed in containers (default) or `subprocess` to execute them in Python subprocesses (faster,
             experimental: The `Dockerfile` commands are not executed, requires dependencies to be installed locally).
     """
@@ -81,39 +84,48 @@ def __init__(
         token: Optional[str] = None,
         retry_timeout: int = DEFAULT_RETRY_TIMEOUT,
         insecure: bool = False,
-        debug: bool = False,
+        backend_type: schemas.BackendType = schemas.BackendType.REMOTE,
     ):
         self._retry_timeout = retry_timeout
         self._token = token
 
         self._insecure = insecure
         self._url = url
 
-        self._backend = self._get_backend(debug)
+        self._backend = self._get_backend(backend_type)
 
-    def _get_backend(self, debug: bool):
+    def _get_backend(self, backend_type: schemas.BackendType):
         # Three possibilities:
-        # - debug is False: get a remote backend
-        # - debug is True and no url is defined: fully local backend
-        # - debug is True and url is defined: local backend that connects to
-        #                           a remote backend (read-only)
-        backend = None
-        if (debug and self._url) or not debug:
-            backend = backends.get(
-                "remote",
+        # - deployed: get a deployed backend
+        # - subprocess/docker and no url is defined: fully local backend
+        # - subprocess/docker and url is defined: local backend that connects to
+        #                           a deployed backend (read-only)
+        if backend_type == schemas.BackendType.REMOTE:
+            return backends.get(
+                schemas.BackendType.REMOTE,
                 url=self._url,
                 insecure=self._insecure,
                 token=self._token,
                 retry_timeout=self._retry_timeout,
             )
-        if debug:
-            # Hybrid mode: the local backend also connects to
-            # a remote backend in read-only mode.
+        if backend_type in [schemas.BackendType.LOCAL_DOCKER, schemas.BackendType.LOCAL_SUBPROCESS]:
+            backend = None
+            if self._url:
+                backend = backends.get(
+                    schemas.BackendType.REMOTE,
+                    url=self._url,
+                    insecure=self._insecure,
+                    token=self._token,
+                    retry_timeout=self._retry_timeout,
+                )
             return backends.get(
-                "local",
+                backend_type,
                 backend,
             )
-        return backend
+        raise exceptions.SDKException(
+            f"Unknown value for the execution mode: {backend_type}, "
+            f"valid values are: {schemas.BackendType.__members__.values()}"
+        )
 
     @property
     def temp_directory(self):
@@ -124,7 +136,7 @@ def temp_directory(self):
             return self._backend.temp_directory
 
     @property
-    def backend_mode(self) -> cfg.BackendType:
+    def backend_mode(self) -> schemas.BackendType:
         """Get the backend mode: deployed,
         local and which type of local mode
 
@@ -155,7 +167,7 @@ def from_config_file(
         tokens_path: Union[str, pathlib.Path] = cfg.DEFAULT_TOKENS_PATH,
         token: Optional[str] = None,
         retry_timeout: int = DEFAULT_RETRY_TIMEOUT,
-        debug: bool = False,
+        backend_type: schemas.BackendType = schemas.BackendType.REMOTE,
     ):
         """Returns a new Client configured with profile data from configuration files.
 
@@ -171,10 +183,17 @@ def from_config_file(
                 instead of any token found at tokens_path). Defaults to None.
             retry_timeout (int, optional): Number of seconds before attempting a retry call in case
                 of timeout. Defaults to 5 minutes.
-            debug (bool): Whether to use the default or debug mode. In debug mode, new assets are
-                created locally but can get remote assets. The deployed platform is in
-                read-only mode.
-                Defaults to False.
+            backend_type (schemas.BackendType, optional): Which mode to use. Defaults to deployed.
+                In deployed mode, assets are registered on a deployed platform which also executes the tasks.
+                In local mode (subprocess or docker), if no URL is given then all assets are created locally and tasks
+                are executed locally.
+                In local mode (subprocess or docker), if a URL is given then the mode is a hybrid one: new assets are
+                created locally but can access assets from the deployed Substra platform. The platform is in read-only
+                mode and tasks are executed locally.
+                The local mode is either docker or subprocess mode: `docker` if you want the tasks to
+                be executed in containers (default) or `subprocess` to execute them in Python subprocesses (faster,
+                experimental: The `Dockerfile` commands are not executed, requires dependencies to be installed
+                locally).
 
         Returns:
             Client: The new client.
@@ -193,7 +212,7 @@ def from_config_file(
             retry_timeout=retry_timeout,
             url=profile["url"],
             insecure=profile["insecure"],
-            debug=debug,
+            backend_type=backend_type,
         )
 
     @logit