added a new command lint

Author: wenting-zhao

baselines/agents.py

@@ -58,7 +58,7 @@ def run(
             fnames=fnames,
             auto_lint=auto_lint,
             auto_test=auto_test,
-            lint_cmds=lint_cmd,
+            lint_cmds={"python": lint_cmd},
             test_cmd=test_cmd,
             io=io,
         )

baselines/commit0_utils.py

@@ -242,3 +242,38 @@ def args2string(agent_config: AgentConfig) -> str:
         result_list.append(f"{key}-{value}")
     concatenated_string = "__".join(result_list)
     return concatenated_string
+
+
+def get_changed_files(repo: git.Repo) -> list[str]:
+    """
+    Get a list of files that were changed in the latest commit of the provided Git repository.
+
+    Args:
+        repo (git.Repo): An instance of GitPython's Repo object representing the Git repository.
+
+    Returns:
+        list[str]: A list of filenames (as strings) that were changed in the latest commit.
+    """
+    latest_commit = repo.head.commit
+    # Get the list of files changed in the latest commit
+    files_changed = latest_commit.stats.files
+    return list(files_changed.keys())
+
+def get_lint_cmd(repo: git.Repo, use_lint_info: bool) -> str:
+    """
+    Generate a linting command based on whether to include files changed in the latest commit.
+
+    Args:
+        repo (git.Repo): An instance of GitPython's Repo object representing the Git repository.
+        use_lint_info (bool): A flag indicating whether to include changed files in the lint command.
+
+    Returns:
+        str: The generated linting command string. If `use_lint_info` is True, the command includes
+             the list of changed files. If False, returns an empty string.
+    """
+    lint_cmd = "python -m commit0 lint "
+    if use_lint_info:
+        lint_cmd += " ".join(get_changed_files(repo))
+    else:
+        lint_cmd = ""
+    return lint_cmd

baselines/configs/agent.yaml

@@ -11,6 +11,6 @@ agent_config:
   use_repo_info: false
   use_unit_tests_info: false
   use_spec_info: false
-  use_lint_info: false
+  use_lint_info: true
   pre_commit_config_path: .pre-commit-config.yaml
   run_tests: false

baselines/run_agent.py

@@ -9,6 +9,7 @@
     create_branch,
     get_message,
     get_target_edit_files,
+    get_lint_cmd,
 )
 from baselines.agents import AiderAgents
 from typing import Optional, Type
@@ -63,8 +64,6 @@ def run_agent_for_repo(
             f"{repo_path} is not a git repo. Check if base_dir is correctly specified."
         )
 
-    target_edit_files = get_target_edit_files(repo_path)
-
     if agent_config.agent_name == "aider":
         agent = AiderAgents(agent_config.max_iteration, agent_config.model_name)
     else:
@@ -81,24 +80,20 @@ def run_agent_for_repo(
     # TODO: ask user for permission
     if latest_commit.hexsha != example["base_commit"]:
         local_repo.git.reset("--hard", example["base_commit"])
+    target_edit_files = get_target_edit_files(repo_path)
 
     with DirContext(repo_path):
         if commit0_config is None or agent_config is None:
             raise ValueError("Invalid input")
 
         message = get_message(agent_config, repo_path, example["test"]["test_dir"])
-
-        if agent_config.use_lint_info:
-            lint_cmd = "pre-commit run --config ../../.pre-commit-config.yaml --files"
-        else:
-            lint_cmd = ""
-
         if agent_config.run_tests:
             # when unit test feedback is available, iterate over test files
             for test_file in test_files:
                 test_cmd = f"python -m commit0 test {repo_path} {run_id} {test_file}"
                 test_file_name = test_file.replace(".py", "").replace("/", "__")
                 log_dir = RUN_AIDER_LOG_DIR / "with_tests" / test_file_name
+                lint_cmd = get_lint_cmd(local_repo, agent_config.use_lint_info)
 
                 agent.run(
                     message,
@@ -112,6 +107,7 @@ def run_agent_for_repo(
             for f in target_edit_files:
                 file_name = f.replace(".py", "").replace("/", "__")
                 log_dir = RUN_AIDER_LOG_DIR / "no_tests" / file_name
+                lint_cmd = get_lint_cmd(local_repo, agent_config.use_lint_info)
 
                 agent.run(message, "", lint_cmd, [f], log_dir)
 

commit0/__main__.py

@@ -3,6 +3,7 @@
 import commit0.harness.build
 import commit0.harness.setup
 import commit0.harness.evaluate
+import commit0.harness.lint
 import commit0.harness.save
 import copy
 import sys
@@ -141,6 +142,9 @@ def main() -> None:
             config.num_cpus,
             config.num_workers,
         )
+    elif command == "lint":
+        files = sys.argv[1:]
+        commit0.harness.lint.main(config.base_dir, files)
     elif command == "save":
         if len(sys.argv) != 5:
             raise ValueError(

commit0/harness/constants.py

@@ -40,6 +40,7 @@ class Files(TypedDict):
     "get-tests",
     "evaluate",
     "evaluate-reference",
+    "lint",
     "save",
 ]
 # repo splits

commit0/harness/lint.py

@@ -0,0 +1,45 @@
+import subprocess
+import sys
+from pathlib import Path
+
+
+config = \
+"""repos:
+# Standard hooks
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.3.0
+  hooks:
+  - id: check-case-conflict
+  - id: mixed-line-ending
+
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.6.1
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format
+
+- repo: https://github.com/RobertCraigie/pyright-python
+  rev: v1.1.376
+  hooks:
+    - id: pyright"""
+
+
+def main(base_dir: str, files: list[str]) -> None:
+    config_file = Path(".commit0.pre-commit-config.yaml")
+    if not config_file.is_file():
+        config_file.write_text(config)
+    command = ['pre-commit', 'run', '--config', config_file, '--files'] + files
+    try:
+        result = subprocess.run(command, capture_output=True, text=True, check=True)
+        print(result.stdout)
+        sys.exit(result.returncode)
+    except subprocess.CalledProcessError as e:
+        raise Exception(f"Pre-commit checks failed\n{e.output}")
+    except FileNotFoundError as e:
+        raise FileNotFoundError("Error: pre-commit command not found. Is it installed?")
+    except Exception as e:
+        raise Exception(f"An unexpected error occurred: {e}")