Enable commit check via env var

spacy/cli/project/remote_storage.py

@@ -7,7 +7,8 @@ import tarfile
 from pathlib import Path
 
 from .._util import get_hash, get_checksum, download_file, ensure_pathy
-from ...util import make_tempdir, get_minor_version
+from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var
+from ...git_info import GIT_VERSION
 from ... import about
 
 if TYPE_CHECKING:
@@ -130,7 +131,8 @@ def get_command_hash(
     currently installed packages, whatever environment variables have been marked
     as relevant, and the command.
     """
-    spacy_v = get_minor_version(about.__version__)
+    check_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
+    spacy_v = GIT_VERSION if check_commit else get_minor_version(about.__version__)
     dep_checksums = [get_checksum(dep) for dep in sorted(deps)]
     hashes = [spacy_v, site_hash, env_hash] + dep_checksums
     hashes.extend(cmd)

spacy/cli/project/run.py

@@ -7,7 +7,8 @@ import srsly
 from ... import about
 from ...git_info import GIT_VERSION
 from ...util import working_dir, run_command, split_command, is_cwd, join_command
-from ...util import SimpleFrozenList, is_minor_version_match
+from ...util import SimpleFrozenList, is_minor_version_match, ENV_VARS
+from ...util import check_bool_env_var
 from .._util import PROJECT_FILE, PROJECT_LOCK, load_project_config, get_hash
 from .._util import get_checksum, project_cli, Arg, Opt, COMMAND
 
@@ -64,9 +65,10 @@ def project_run(
                 err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
                 err_kwargs = {"exits": 1} if not dry else {}
                 msg.fail(err, err_help, **err_kwargs)
+        check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
         with working_dir(project_dir) as current_dir:
             msg.divider(subcommand)
-            rerun = check_rerun(current_dir, cmd)
+            rerun = check_rerun(current_dir, cmd, check_spacy_commit=check_spacy_commit)
             if not rerun and not force:
                 msg.info(f"Skipping '{cmd['name']}': nothing changed")
             else:

spacy/util.py

@@ -73,6 +73,7 @@ logger = logging.getLogger("spacy")
 
 class ENV_VARS:
     CONFIG_OVERRIDES = "SPACY_CONFIG_OVERRIDES"
+    PROJECT_USE_GIT_VERSION = "SPACY_PROJECT_USE_GIT_VERSION"
 
 
 class registry(thinc.registry):
@@ -1342,3 +1343,16 @@ def is_cython_func(func: Callable) -> bool:
         cls_func = vars(sys.modules[func.__module__])[func.__qualname__.split(".")[0]]
         return hasattr(cls_func, attr)
     return False
+
+
+def check_bool_env_var(env_var: str) -> bool:
+    """Convert the value of an environment variable to a boolean. Add special
+    check for "0" (falsy) and consider everything else truthy, except unset.
+
+    env_var (str): The name of the environment variable to check.
+    RETURNS (bool): Its boolean value.
+    """
+    value = os.environ.get(env_var, False)
+    if value == "0":
+        return False
+    return bool(value)