diff --git a/evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py b/evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py
index f08ee73eee8a..f2fc46095db4 100755
--- a/evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py
+++ b/evaluation/benchmarks/swe_bench/scripts/eval/summarize_outputs.py
@@ -3,11 +3,11 @@
 import glob
 import json
 import os
+import random
 from collections import Counter
 
-import pandas as pd
-import random
 import numpy as np
+import pandas as pd
 
 from openhands.events.serialization import event_from_dict
 from openhands.events.utils import get_pairs_from_events
@@ -20,12 +20,11 @@
 ]
 
 
-def get_bootstrap_accuracy_error_bars(values: float | int | bool, num_samples: int = 1000, p_value=0.05) -> tuple[float, float]:
+def get_bootstrap_accuracy_error_bars(
+    values: float | int | bool, num_samples: int = 1000, p_value=0.05
+) -> tuple[float, float]:
     sorted_vals = np.sort(
-        [
-            np.mean(random.sample(values, len(values) // 2))
-            for _ in range(num_samples)
-        ]
+        [np.mean(random.sample(values, len(values) // 2)) for _ in range(num_samples)]
     )
     bottom_idx = int(num_samples * p_value / 2)
     top_idx = int(num_samples * (1.0 - p_value / 2))
@@ -118,7 +117,9 @@ def process_file(file_path):
         'resolved': {
             'count': num_resolved,
             'percentage': (num_resolved / num_lines * 100) if num_lines > 0 else 0,
-            'ci': tuple(x * 100 for x in get_bootstrap_accuracy_error_bars(resolved_arr)),
+            'ci': tuple(
+                x * 100 for x in get_bootstrap_accuracy_error_bars(resolved_arr)
+            ),
         },
         'empty_patches': {
             'count': num_empty_patch,
diff --git a/frontend/src/i18n/translation.json b/frontend/src/i18n/translation.json
index 670a0e93f547..f7ee8f4959d6 100644
--- a/frontend/src/i18n/translation.json
+++ b/frontend/src/i18n/translation.json
@@ -2009,7 +2009,7 @@
     "en": "Running a bash command"
   },
   "ACTION_MESSAGE$RUN_IPYTHON": {
-    "en": "Running a Jupyter command"
+    "en": "Running a Python command"
   },
   "ACTION_MESSAGE$READ": {
     "en": "Reading the contents of a file"
@@ -2027,7 +2027,7 @@
     "en": "Ran a bash command"
   },
   "OBSERVATION_MESSAGE$RUN_IPYTHON": {
-    "en": "Ran a Jupyter command"
+    "en": "Ran a Python command"
   },
   "OBSERVATION_MESSAGE$READ": {
     "en": "Read the contents of a file"
diff --git a/pyproject.toml b/pyproject.toml
index d97b9f8ee318..980a889c7141 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -100,6 +100,7 @@ reportlab = "*"
 [tool.coverage.run]
 concurrency = ["gevent"]
 
+
 [tool.poetry.group.runtime.dependencies]
 jupyterlab = "*"
 notebook = "*"
@@ -129,6 +130,7 @@ ignore = ["D1"]
 [tool.ruff.lint.pydocstyle]
 convention = "google"
 
+
 [tool.poetry.group.evaluation.dependencies]
 streamlit = "*"
 whatthepatch = "*"