diff --git a/dev/playwright_agent/playwright_agent.py b/dev/playwright_agent/playwright_agent.py
index 867eb2103..3493e893d 100644
--- a/dev/playwright_agent/playwright_agent.py
+++ b/dev/playwright_agent/playwright_agent.py
@@ -4,13 +4,13 @@
import argparse
import asyncio
+from dataclasses import dataclass
import json
import math
import os
import time
-import uuid
-from dataclasses import dataclass
from typing import Any, Dict, List
+import uuid
from dotenv import load_dotenv
from mcp import ClientSession, StdioServerParameters
diff --git a/dev/swebench/logs.py b/dev/swebench/logs.py
index 8cec9359f..bedf963ad 100644
--- a/dev/swebench/logs.py
+++ b/dev/swebench/logs.py
@@ -1,10 +1,10 @@
import logging
from logging import Handler, LogRecord
-import litellm
from langfuse import Langfuse
from langfuse.decorators import langfuse_context
from langfuse.types import SpanLevel
+import litellm
from sweagent.agent.agents import DefaultAgent
from sweagent.run.hooks.apply_patch import SaveApplyPatchHook
diff --git a/dev/swebench/rollout.py b/dev/swebench/rollout.py
index 2622d7b01..c0b1ed184 100644
--- a/dev/swebench/rollout.py
+++ b/dev/swebench/rollout.py
@@ -1,11 +1,9 @@
import asyncio
-import json
from http.client import RemoteDisconnected
+import json
from pathlib import Path
from typing import Any, Literal, overload
-import modal
-import requests
from aiolimiter import AsyncLimiter
from config import get_config
from eval import eval_instance
@@ -13,7 +11,9 @@
from instances import Instance
from langfuse.decorators import observe
from logs import setup_agent_logger
+import modal
from pydantic import BaseModel
+import requests
from requests import adapters as requests_adapters
from requests.exceptions import ConnectionError, ConnectTimeout, SSLError
from run import run
diff --git a/dev/swebench/sandbox/test.py b/dev/swebench/sandbox/test.py
index 371e36fe7..9c210b5aa 100644
--- a/dev/swebench/sandbox/test.py
+++ b/dev/swebench/sandbox/test.py
@@ -1,5 +1,5 @@
-import pytest
from dotenv import load_dotenv
+import pytest
from ..instances import as_instances_iter, get_filtered_swe_smith_instances_df
from .new import new_sandbox
diff --git a/dev/swebench/train.ipynb b/dev/swebench/train.ipynb
index 2f96b1ef5..44f2fed2b 100644
--- a/dev/swebench/train.ipynb
+++ b/dev/swebench/train.ipynb
@@ -36,8 +36,8 @@
"source": [
"import os\n",
"\n",
- "import nest_asyncio\n",
"from dotenv import load_dotenv\n",
+ "import nest_asyncio\n",
"\n",
"# PREPARE ENVIRONMENT\n",
"os.environ[\"MODAL_IMAGE_BUILDER_VERSION\"] = \"2024.10\"\n",
@@ -60,8 +60,8 @@
"metadata": {},
"outputs": [],
"source": [
- "import torch\n",
"from rollout import ModelConfig\n",
+ "import torch\n",
"\n",
"import art\n",
"from art.local import LocalBackend\n",
diff --git a/dev/tau-bench/analyze_model_errors.py b/dev/tau-bench/analyze_model_errors.py
index 7bde8743a..14b86549d 100644
--- a/dev/tau-bench/analyze_model_errors.py
+++ b/dev/tau-bench/analyze_model_errors.py
@@ -2,13 +2,13 @@
import argparse
import asyncio
+from datetime import datetime
import json
import os
-from datetime import datetime
from typing import Any, Dict, List
-import litellm
from dotenv import load_dotenv
+import litellm
from litellm import provider_list
# Import evaluate_model and rollout functions from run_rl
diff --git a/dev/tau-bench/auto_error_identification.py b/dev/tau-bench/auto_error_identification.py
index ecf422f46..09dbfd90f 100644
--- a/dev/tau-bench/auto_error_identification.py
+++ b/dev/tau-bench/auto_error_identification.py
@@ -1,9 +1,9 @@
# Copyright Sierra
import argparse
-import json
from concurrent.futures import ThreadPoolExecutor
from enum import Enum
+import json
from typing import Any, Dict, List
from pydantic import BaseModel
diff --git a/dev/tau-bench/benchmark_rl.py b/dev/tau-bench/benchmark_rl.py
index fa318970d..2feef2069 100644
--- a/dev/tau-bench/benchmark_rl.py
+++ b/dev/tau-bench/benchmark_rl.py
@@ -2,13 +2,13 @@
import argparse
import asyncio
+from datetime import datetime
import json
import os
-from datetime import datetime
from typing import Any, Dict, List
-import litellm
from dotenv import load_dotenv
+import litellm
from litellm import provider_list
# Import evaluate_model and rollout functions from run_rl
diff --git a/dev/tau-bench/run.ipynb b/dev/tau-bench/run.ipynb
index a55ce6668..1872352dc 100644
--- a/dev/tau-bench/run.ipynb
+++ b/dev/tau-bench/run.ipynb
@@ -37,11 +37,11 @@
"metadata": {},
"outputs": [],
"source": [
- "import torch\n",
"from dotenv import load_dotenv\n",
"from run import RunConfig\n",
"from run_rl import train\n",
"from tau_bench.types import TauBenchPolicyConfig, TauBenchTrainingConfig\n",
+ "import torch\n",
"\n",
"import art\n",
"\n",
diff --git a/dev/tau-bench/run_training.py b/dev/tau-bench/run_training.py
index bae334fa0..3ac733933 100644
--- a/dev/tau-bench/run_training.py
+++ b/dev/tau-bench/run_training.py
@@ -4,8 +4,8 @@
import textwrap
import traceback
-import sky
from dotenv import dotenv_values
+import sky
from sky import ClusterStatus
from tau_bench.types import RunConfig, TauBenchPolicyConfig, TauBenchTrainingConfig
diff --git a/dev/tau-bench/tau_bench/envs/airline/tools/book_reservation.py b/dev/tau-bench/tau_bench/envs/airline/tools/book_reservation.py
index f4195b8ab..2f342492c 100644
--- a/dev/tau-bench/tau_bench/envs/airline/tools/book_reservation.py
+++ b/dev/tau-bench/tau_bench/envs/airline/tools/book_reservation.py
@@ -1,7 +1,7 @@
# Copyright Sierra
-import json
from copy import deepcopy
+import json
from typing import Any, Dict, List
from tau_bench.envs.tool import Tool
diff --git a/dev/tau-bench/tau_bench/envs/airline/tools/update_reservation_flights.py b/dev/tau-bench/tau_bench/envs/airline/tools/update_reservation_flights.py
index b31fa92cd..ffd050190 100644
--- a/dev/tau-bench/tau_bench/envs/airline/tools/update_reservation_flights.py
+++ b/dev/tau-bench/tau_bench/envs/airline/tools/update_reservation_flights.py
@@ -1,7 +1,7 @@
# Copyright Sierra
-import json
from copy import deepcopy
+import json
from typing import Any, Dict, List
from tau_bench.envs.tool import Tool
diff --git a/dev/tau-bench/tau_bench/envs/base.py b/dev/tau-bench/tau_bench/envs/base.py
index a54bc5226..54c035e16 100644
--- a/dev/tau-bench/tau_bench/envs/base.py
+++ b/dev/tau-bench/tau_bench/envs/base.py
@@ -1,7 +1,7 @@
# Copyright Sierra
-import random
from hashlib import sha256
+import random
from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Type, Union
from tau_bench.envs.tool import Tool
diff --git a/dev/tau-bench/tau_bench/model_utils/api/cache.py b/dev/tau-bench/tau_bench/model_utils/api/cache.py
index 2735eed3e..e8bed50d4 100644
--- a/dev/tau-bench/tau_bench/model_utils/api/cache.py
+++ b/dev/tau-bench/tau_bench/model_utils/api/cache.py
@@ -1,9 +1,9 @@
+from collections import defaultdict
import functools
import hashlib
import inspect
-import threading
-from collections import defaultdict
from multiprocessing import Lock
+import threading
from typing import Any, Callable, TypeVar
from pydantic import BaseModel
diff --git a/dev/tau-bench/tau_bench/model_utils/api/exception.py b/dev/tau-bench/tau_bench/model_utils/api/exception.py
index 40b424514..73713b75a 100644
--- a/dev/tau-bench/tau_bench/model_utils/api/exception.py
+++ b/dev/tau-bench/tau_bench/model_utils/api/exception.py
@@ -1,7 +1,7 @@
+from concurrent.futures import ThreadPoolExecutor
import json
import os
import time
-from concurrent.futures import ThreadPoolExecutor
from typing import Any, Callable, TypeVar
from tau_bench.model_utils.model.exception import ModelError, Result
diff --git a/dev/tau-bench/tau_bench/rl_utils.py b/dev/tau-bench/tau_bench/rl_utils.py
index b94a6d77c..ce0f31c98 100644
--- a/dev/tau-bench/tau_bench/rl_utils.py
+++ b/dev/tau-bench/tau_bench/rl_utils.py
@@ -1,8 +1,8 @@
+from datetime import datetime
import os
import time
-import uuid
-from datetime import datetime
from typing import Any, Dict, List, Optional
+import uuid
from langfuse import Langfuse
from openai import AsyncOpenAI
diff --git a/dev/tau-bench/tau_bench/run.py b/dev/tau-bench/tau_bench/run.py
index 663b2ad76..987506f3f 100644
--- a/dev/tau-bench/tau_bench/run.py
+++ b/dev/tau-bench/tau_bench/run.py
@@ -1,14 +1,14 @@
# Copyright Sierra
+from concurrent.futures import ThreadPoolExecutor
+from datetime import datetime
import json
+from math import comb
import multiprocessing
import os
import random
import traceback
-import warnings
-from concurrent.futures import ThreadPoolExecutor
-from datetime import datetime
-from math import comb
from typing import Any, Dict, List
+import warnings
from langfuse import Langfuse
from litellm import provider_list
diff --git a/dev/yes-no-maybe-vision/train.ipynb b/dev/yes-no-maybe-vision/train.ipynb
index 46d29c726..939c47aca 100644
--- a/dev/yes-no-maybe-vision/train.ipynb
+++ b/dev/yes-no-maybe-vision/train.ipynb
@@ -34,9 +34,9 @@
"metadata": {},
"outputs": [],
"source": [
- "import openai\n",
"from dotenv import load_dotenv\n",
"from generate_images import generate_yes_no_maybe_prompts, save_prompt_images\n",
+ "import openai\n",
"\n",
"import art\n",
"from art.local import LocalBackend\n",
diff --git a/dev/yes-no-maybe.ipynb b/dev/yes-no-maybe.ipynb
index b18d83265..11e060b93 100644
--- a/dev/yes-no-maybe.ipynb
+++ b/dev/yes-no-maybe.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@@ -12,30 +12,9 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": null,
"metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n"
- ],
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
"source": [
"%%html\n",
"