fix: format Python files with ruff

_Generated with `cmux`_

Author: ammar-agent

benchmarks/terminal_bench/calculate_timeout.py

@@ -35,18 +35,18 @@ def main():
         default="flag",
         help="Output format: 'seconds' (just the number) or 'flag' (--global-agent-timeout-sec VALUE)",
     )
-    
+
     args = parser.parse_args()
-    
+
     if args.task_ids:
         timeout = get_max_timeout_for_tasks(args.task_ids)
     else:
         # No specific tasks - use conservative default for full suite
         timeout = VERY_SLOW_TIMEOUT
-    
+
     # Apply multiplier
     timeout = int(timeout * args.multiplier)
-    
+
     if args.format == "seconds":
         print(timeout)
     else:

benchmarks/terminal_bench/task_timeouts.py

@@ -10,7 +10,7 @@
 
 Strategy:
 - FAST tasks (< 5 min): Simple file operations, basic commands
-- NORMAL tasks (15 min): Default for most tasks  
+- NORMAL tasks (15 min): Default for most tasks
 - SLOW tasks (30 min): Data processing, model training, complex analysis
 - VERY_SLOW tasks (60 min): Kernel compilation, large builds
 """
@@ -27,7 +27,6 @@
     "build-linux-kernel-qemu": VERY_SLOW_TIMEOUT,  # Failed at 763s
     "build-initramfs-qemu": VERY_SLOW_TIMEOUT,
     "build-tcc-qemu": SLOW_TIMEOUT,
-    
     # SLOW: Data processing, ML training, complex analysis
     "count-dataset-tokens": SLOW_TIMEOUT,  # Anthropic timed out at 808s, OpenAI succeeded at 344s
     "train-fasttext": SLOW_TIMEOUT,  # Timed out at 900s
@@ -36,46 +35,39 @@
     "eval-mteb": SLOW_TIMEOUT,
     "eval-mteb.hard": SLOW_TIMEOUT,
     "reshard-c4-data": SLOW_TIMEOUT,
-    
     # SLOW: QEMU/emulation tasks
     "qemu-startup": SLOW_TIMEOUT,  # Passed at 838s but hit timeout
     "qemu-alpine-ssh": SLOW_TIMEOUT,
     "run-pdp11-code": SLOW_TIMEOUT,
-    
     # SLOW: Complex algorithmic tasks
     "blind-maze-explorer-algorithm": SLOW_TIMEOUT,
     "blind-maze-explorer-algorithm.easy": SLOW_TIMEOUT,
     "blind-maze-explorer-algorithm.hard": SLOW_TIMEOUT,  # Passed at 1200s!
     "path-tracing": SLOW_TIMEOUT,  # Passed at 660s
     "path-tracing-reverse": SLOW_TIMEOUT,  # Timed out at 660s
-    
     # SLOW: Security/crypto tasks that may need brute force
     "crack-7z-hash": SLOW_TIMEOUT,
     "crack-7z-hash.hard": SLOW_TIMEOUT,
     "password-recovery": SLOW_TIMEOUT,
     "security-vulhub-minio": SLOW_TIMEOUT,
-    
     # SLOW: Complex git/code analysis
     "git-workflow-hack": SLOW_TIMEOUT,  # Passed but hit timeout
     "pytorch-model-cli": SLOW_TIMEOUT,  # Passed at 541s
     "swe-bench-astropy-1": SLOW_TIMEOUT,
     "swe-bench-astropy-2": SLOW_TIMEOUT,
     "swe-bench-fsspec": SLOW_TIMEOUT,
     "swe-bench-langcodes": SLOW_TIMEOUT,
-    
     # SLOW: Compilation/code generation
     "gpt2-codegolf": SLOW_TIMEOUT,
     "polyglot-c-py": SLOW_TIMEOUT,
     "polyglot-rust-c": SLOW_TIMEOUT,
     "write-compressor": SLOW_TIMEOUT,
-    
     # SLOW: Complex system tasks
     "cron-broken-network": SLOW_TIMEOUT,
     "oom": SLOW_TIMEOUT,
     "fibonacci-server": SLOW_TIMEOUT,
     "incompatible-python-fasttext.base_with_hint": SLOW_TIMEOUT,
     "extract-safely": SLOW_TIMEOUT,
-    
     # FAST: Simple tasks that should complete quickly
     "hello-world": FAST_TIMEOUT,
     "fix-permissions": FAST_TIMEOUT,
@@ -99,5 +91,5 @@ def get_max_timeout_for_tasks(task_ids: list[str]) -> int:
     """
     if not task_ids:
         return VERY_SLOW_TIMEOUT  # Conservative default for unknown tasks
-    
+
     return max(get_timeout_for_task(task_id) for task_id in task_ids)

benchmarks/terminal_bench/task_timeouts_test.py

@@ -42,15 +42,15 @@ def test_max_timeout_for_tasks():
     # Mix of fast and slow
     tasks = ["hello-world", "count-dataset-tokens"]
     assert get_max_timeout_for_tasks(tasks) == SLOW_TIMEOUT
-    
+
     # Mix of fast, slow, and very slow
     tasks = ["hello-world", "count-dataset-tokens", "build-linux-kernel-qemu"]
     assert get_max_timeout_for_tasks(tasks) == VERY_SLOW_TIMEOUT
-    
+
     # All fast
     tasks = ["hello-world", "simple-web-scraper"]
     assert get_max_timeout_for_tasks(tasks) == FAST_TIMEOUT
-    
+
     # Empty list should return conservative default
     assert get_max_timeout_for_tasks([]) == VERY_SLOW_TIMEOUT
 
@@ -61,6 +61,6 @@ def test_timeout_values():
     assert NORMAL_TIMEOUT == 900  # 15 minutes
     assert SLOW_TIMEOUT == 1800  # 30 minutes
     assert VERY_SLOW_TIMEOUT == 3600  # 60 minutes
-    
+
     # Ensure proper ordering
     assert FAST_TIMEOUT < NORMAL_TIMEOUT < SLOW_TIMEOUT < VERY_SLOW_TIMEOUT