[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

scripts/bug_gen_modal.py

@@ -523,7 +523,7 @@ async def acquire(self):
     image=generator_image,
     secrets=[
         modal.Secret.from_name("GITHUB_TOKEN"),
-        modal.Secret.from_name("PORTKEY_API_KEY")
+        modal.Secret.from_name("PORTKEY_API_KEY"),
     ],
     timeout=MODAL_TIMEOUT,
     volumes={LOGS_MOUNT_PATH: logs_volume},  # Mount volume for direct writes
@@ -1885,11 +1885,11 @@ def issue_gen_remote(
     # Set up paths
     volume_root = Path(LOGS_MOUNT_PATH) / language
     task_insts_dir = volume_root / "task_insts"
-    
+
     # Resolve task instances file (it may have a hash suffix like repo__name.abcdef.json)
     task_insts_file = None
     repo_sanitized = repo.replace("/", "__")
-    
+
     if task_insts_dir.exists():
         for filename in os.listdir(task_insts_dir):
             # Check for exact match or match with suffix
@@ -1961,6 +1961,7 @@ def issue_gen_remote(
         instances_processed = 0
         if issue_gen_file.exists():
             import json
+
             with open(issue_gen_file) as f:
                 data = json.load(f)
                 instances_processed = len(data)
@@ -1973,6 +1974,7 @@ def issue_gen_remote(
 
     except Exception as e:
         import traceback
+
         return {
             "success": False,
             "repo": repo,
@@ -1996,9 +1998,9 @@ async def run_issue_gen_phase_async(
         issue_gen_workers: Number of workers per repo
         issue_gen_redo: Whether to regenerate existing issues
     """
-    print(f"\n{'='*80}")
+    print(f"\n{'=' * 80}")
     print(f"ISSUE GENERATION PHASE")
-    print(f"{'='*80}")
+    print(f"{'=' * 80}")
     print(f"Processing {len(repos)} repositories...")
     print(f"Config: {issue_gen_config}")
     print(f"Workers per repo: {issue_gen_workers}")
@@ -2015,14 +2017,15 @@ async def run_issue_gen_phase_async(
         },
         order_outputs=False,
     ):
-
         results.append(result)
 
         # Print progress
         completed = len(results)
         if result["success"]:
             instances = result.get("instances_processed", 0)
-            print(f"  [{completed}/{len(repos)}] {result['repo']}: ✓ ({instances} instances)")
+            print(
+                f"  [{completed}/{len(repos)}] {result['repo']}: ✓ ({instances} instances)"
+            )
         else:
             error = result.get("error", "Unknown error")
             print(f"  [{completed}/{len(repos)}] {result['repo']}: ✗ {error}")
@@ -2031,9 +2034,13 @@ async def run_issue_gen_phase_async(
 
     # Summary
     success = sum(1 for r in results if r["success"])
-    total_instances = sum(r.get("instances_processed", 0) for r in results if r["success"])
+    total_instances = sum(
+        r.get("instances_processed", 0) for r in results if r["success"]
+    )
 
-    print(f"\nIssue generation complete: {success}/{len(repos)} repos processed successfully.")
+    print(
+        f"\nIssue generation complete: {success}/{len(repos)} repos processed successfully."
+    )
     print(f"Total instances with issues: {total_instances}\n")
 
 

swesmith/issue_gen/generate.py

@@ -69,6 +69,7 @@
 logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
 logger = logging.getLogger(__name__)
 
+
 class PortkeyModelConfig(BaseModel):
     model_name: str
     model_kwargs: dict[str, Any] = {}
@@ -83,7 +84,7 @@ def __init__(self, *, config_class: type = PortkeyModelConfig, **kwargs):
             raise ImportError(
                 "The portkey-ai package is required to use PortkeyModel. Please install it with: pip install portkey-ai"
             )
-        
+
         self.config = config_class(**kwargs)
         self.cost = 0.0
         self.n_calls = 0
@@ -124,7 +125,10 @@ def _query(self, messages: list[dict[str, str]], **kwargs):
 
     def query(self, messages: list[dict[str, str]], **kwargs) -> Any:
         # Simple adapter to match what generate.py expects (return an object with choices and usage for cost)
-        response = self._query([{"role": msg["role"], "content": msg["content"]} for msg in messages], **kwargs)
+        response = self._query(
+            [{"role": msg["role"], "content": msg["content"]} for msg in messages],
+            **kwargs,
+        )
         return response
 
 
@@ -167,12 +171,17 @@ def __init__(
 
         # Initialize Portkey model if needed
         self.portkey_model = None
-        if self.model.startswith("portkey/") or self.config.get("provider") == "portkey":
+        if (
+            self.model.startswith("portkey/")
+            or self.config.get("provider") == "portkey"
+        ):
             self.portkey_model = PortkeyModel(
                 model_name=self.model.replace("portkey/", ""),
                 provider=self.config.get("provider", "openai"),
-                litellm_model_name_override=self.config.get("litellm_model_name_override", ""),
-                **settings.get("portkey_kwargs", {})
+                litellm_model_name_override=self.config.get(
+                    "litellm_model_name_override", ""
+                ),
+                **settings.get("portkey_kwargs", {}),
             )
 
         data_smith = [x for x in load_dataset(HF_DATASET, split="train")]
@@ -365,18 +374,23 @@ def jinja_shuffle(seq):
 
         # Generate n_instructions completions containing problem statements
         if self.portkey_model:
-            response = self.portkey_model.query(messages, n=self.n_instructions, stream=False)
+            response = self.portkey_model.query(
+                messages, n=self.n_instructions, stream=False
+            )
         else:
             response = completion(
-                model=self.model, messages=messages, n=self.n_instructions, temperature=0
+                model=self.model,
+                messages=messages,
+                n=self.n_instructions,
+                temperature=0,
             )
 
         model_for_cost = self.model
         if self.portkey_model and self.portkey_model.config.litellm_model_name_override:
             model_for_cost = self.portkey_model.config.litellm_model_name_override
-        
+
         cost = completion_cost(response, model=model_for_cost)
-            
+
         metadata["cost"] = (0 if "cost" not in metadata else metadata["cost"]) + cost
 
         # Extract problem statements from response