From c1602587c1da679ee47bb5f47cac7b492a32b7f4 Mon Sep 17 00:00:00 2001
From: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
Date: Tue, 2 Jun 2026 13:07:05 -0700
Subject: [PATCH] fix(tests): drop module-level test calls that break
 local_testing collection (#29520)

* fix(tests): drop module-level test calls that break local_testing collection

Several files in tests/local_testing invoked their test functions at module
scope (e.g. test_register_model.py ran test_update_model_cost_via_completion()
at the bottom of the file). Those calls execute during pytest collection, so
they fire real network requests at import time. test_register_model.py's call
hit an OpenAI 429 and raised, turning into a collection error.

A collection error aborts the whole session for every job that globs
tests/local_testing/**/test_*.py, which is why unrelated jobs like
langfuse_logging_unit_tests (-k langfuse) and litellm_assistants_api_testing
(-k assistants) both failed even though neither touches register_model;
the -k filter only applies after collection.

pytest discovers and runs these test_* functions on its own, so the top-level
calls were dead and harmful. Removes them from test_register_model.py,
test_wandb.py, test_lunary.py, and test_multiple_deployments.py, and adds a
regression test that scans the directory for module-level test invocations.

* test(local_testing): skip unparseable files in module-scope invocation guardrail

A syntax error in any tests/local_testing file would make ast.parse raise an
unhandled SyntaxError, so the guardrail itself would crash with a confusing
traceback instead of its assertion message. Such a file already fails pytest
collection on its own, which is the clearer signal, so the guardrail now skips
files it cannot parse and stays focused on detecting module-scope test calls.
Reads files as utf-8 for deterministic behavior across platforms.
---
 tests/local_testing/test_lunary.py            |  3 --
 .../test_multiple_deployments.py              |  3 --
 .../test_no_top_level_test_invocations.py     | 36 +++++++++++++++++++
 tests/local_testing/test_register_model.py    |  3 --
 tests/local_testing/test_wandb.py             |  3 --
 5 files changed, 36 insertions(+), 12 deletions(-)
 create mode 100644 tests/local_testing/test_no_top_level_test_invocations.py

diff --git a/tests/local_testing/test_lunary.py b/tests/local_testing/test_lunary.py
index d181d24c782..0dbae1b817f 100644
--- a/tests/local_testing/test_lunary.py
+++ b/tests/local_testing/test_lunary.py
@@ -26,9 +26,6 @@ def test_lunary_logging():
         print(e)
 
 
-test_lunary_logging()
-
-
 def test_lunary_template():
     import lunary
 
diff --git a/tests/local_testing/test_multiple_deployments.py b/tests/local_testing/test_multiple_deployments.py
index f7276d4f14e..72bfd5012c1 100644
--- a/tests/local_testing/test_multiple_deployments.py
+++ b/tests/local_testing/test_multiple_deployments.py
@@ -49,6 +49,3 @@ def test_multiple_deployments():
     except Exception as e:
         traceback.print_exc()
         pytest.fail(f"An exception occurred: {e}")
-
-
-test_multiple_deployments()
diff --git a/tests/local_testing/test_no_top_level_test_invocations.py b/tests/local_testing/test_no_top_level_test_invocations.py
new file mode 100644
index 00000000000..eb1d836a18d
--- /dev/null
+++ b/tests/local_testing/test_no_top_level_test_invocations.py
@@ -0,0 +1,36 @@
+import ast
+from pathlib import Path
+
+LOCAL_TESTING_DIR = Path(__file__).parent
+
+
+def _top_level_test_invocations(tree):
+    invocations = []
+    for node in tree.body:
+        if not isinstance(node, ast.Expr) or not isinstance(node.value, ast.Call):
+            continue
+        func = node.value.func
+        name = getattr(func, "id", None) or getattr(func, "attr", None)
+        if name and name.startswith("test_"):
+            invocations.append((name, node.lineno))
+    return invocations
+
+
+def test_no_module_level_test_invocations():
+    offenders = []
+    for path in sorted(LOCAL_TESTING_DIR.rglob("*.py")):
+        try:
+            tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
+        except SyntaxError:
+            continue
+        for name, lineno in _top_level_test_invocations(tree):
+            offenders.append(
+                f"{path.relative_to(LOCAL_TESTING_DIR)}:{lineno} calls {name}()"
+            )
+
+    assert not offenders, (
+        "Test functions are invoked at module scope, so they run during pytest "
+        "collection (making network calls and erroring collection for every job "
+        "that globs this directory). Remove these calls; pytest collects test "
+        "functions automatically:\n" + "\n".join(offenders)
+    )
diff --git a/tests/local_testing/test_register_model.py b/tests/local_testing/test_register_model.py
index 6b170798874..635fd79abff 100644
--- a/tests/local_testing/test_register_model.py
+++ b/tests/local_testing/test_register_model.py
@@ -60,6 +60,3 @@ def test_update_model_cost_via_completion():
         assert litellm.model_cost["gpt-3.5-turbo"]["output_cost_per_token"] == 0.4
     except Exception as e:
         pytest.fail(f"An error occurred: {e}")
-
-
-test_update_model_cost_via_completion()
diff --git a/tests/local_testing/test_wandb.py b/tests/local_testing/test_wandb.py
index 6cdca40492f..58a9c9f5ddf 100644
--- a/tests/local_testing/test_wandb.py
+++ b/tests/local_testing/test_wandb.py
@@ -51,9 +51,6 @@ def test_wandb_logging_async():
         pass
 
 
-test_wandb_logging_async()
-
-
 def test_wandb_logging():
     try:
         response = completion(