fix: only trigger script with CODE label (#3707)

Hocnonsense · web-flow · commit 2d01f8c281ca · 2025-09-04T20:53:54.000+02:00
This PR is inspired by #3706, resolves issues #3456 and #3474, and addresses the concern raised in #3148 (comment) In brief, commit e502312 made changes so that the modification time (mtime) of script and notebook files no longer triggers a rerun of the workflow, later, commit e8a0b83 reversed this, making mtime changes always trigger reruns -- even when RerunTrigger.CODE is not specified in `--rerun-triggers`. This created an undesirable situation: legitimate and common scenarios (e.g., copying scripts or pulling them from a Git repository) could unnecessarily trigger reruns — as reported in #3474. To make the behavior more intuitive, the `outputs_older_than_script_or_notebook` condition should take precedence over metadata checks. However, this condition should still be governed by the presence of `RerunTrigger.CODE`. ### QC  * [x] The PR contains a test case for the changes or the changes are already covered by an existing test case. * [ ] The documentation (`docs/`) is updated to reflect the changes or this is not necessary (e.g. if the change does neither modify the language nor the behavior or functionalities of Snakemake).  ## Summary by CodeRabbit * **Bug Fixes** * Code-change reruns now only run when the CODE rerun trigger is enabled; code-change detection correctly accumulates signals from multiple sources to avoid missed or spurious reruns. * **Tests** * Added an MTIME-triggered rerun test validating that outputs retain timestamps when only input mtimes change. * **Chores** * Fixed a test import path and broadened connectivity error handling to include timeouts.
diff --git a/src/snakemake/dag.py b/src/snakemake/dag.py
@@ -1452,15 +1452,15 @@ async def updated_input():
                             # for determining any other changes than file modification dates, as it will
                             # change after evaluating the input function of the job in the second pass.
 
-                            # The list comprehension is needed below in order to
-                            # collect all the async generator items before
-                            # applying any().
-                            reason.code_changed = any(
-                                [
-                                    f
-                                    async for f in job.outputs_older_than_script_or_notebook()
-                                ]
-                            )
+                            if RerunTrigger.CODE in self.workflow.rerun_triggers:
+                                # Always check script/notebook mtime unless CODE trigger is disabled.
+                                # Short-circuit on first older output to avoid building a list.
+                                reason.code_changed = False
+                                async for (
+                                    _
+                                ) in job.outputs_older_than_script_or_notebook():
+                                    reason.code_changed = True
+                                    break
                             if not self.workflow.persistence.has_metadata(job):
                                 reason.no_metadata = True
                             elif self.workflow.persistence.has_outdated_metadata(job):
diff --git a/tests/common.py b/tests/common.py
@@ -13,7 +13,7 @@
 from os.path import join
 import tempfile
 import hashlib
-import urllib
+import urllib.request
 import pytest
 import glob
 import subprocess
@@ -50,7 +50,7 @@ def is_connected():
     try:
         urllib.request.urlopen("http://www.google.com", timeout=1)
         return True
-    except urllib.request.URLError:
+    except (urllib.request.URLError, TimeoutError):
         return False
 
 
diff --git a/tests/tests.py b/tests/tests.py
@@ -498,7 +498,27 @@ def test_empty_include():
 
 
 def test_script_python():
-    run(dpath("test_script_py"))
+    tmpdir = run(dpath("test_script_py"), cleanup=False)
+    # update timestamp of script
+    os.utime(os.path.join(tmpdir, "scripts/test_explicit_import.py"))
+    outfile_path = os.path.join(tmpdir, "explicit_import.py.out")
+    outfile_timestamp_orig = os.path.getmtime(outfile_path)
+    # won't update output without trigger CODE
+    run(
+        dpath("test_script_py"),
+        cleanup=False,
+        tmpdir=tmpdir,
+        shellcmd="snakemake -c1 --rerun-triggers mtime",
+    )
+    assert outfile_timestamp_orig == os.path.getmtime(outfile_path)
+    run(
+        dpath("test_script_py"),
+        cleanup=False,
+        tmpdir=tmpdir,
+        shellcmd="snakemake -c1",
+    )
+    assert outfile_timestamp_orig != os.path.getmtime(outfile_path)
+    # shutil.rmtree(tmpdir, ignore_errors=ON_WINDOWS)
 
 
 @skip_on_windows  # Test relies on perl
