ci: Create Github Action to Automate CODEOWNER update

.github/workflows/update-codeowners.yml

@@ -0,0 +1,114 @@
+name: Update CODEOWNERS
+
+on:
+  schedule:
+    # Run weekly on Monday at 00:00 UTC
+    - cron: '0 0 * * 1'
+  workflow_dispatch: # Allow manual triggering
+  # NOTE(Zihao): debugging only, remove later
+  pull_request:
+    branches:
+      - main
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  update-codeowners:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - name: Checkout repository
+        uses: actions/[email protected]
+        with:
+          fetch-depth: 0 # Fetch full history for accurate analysis
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Run CODEOWNERS analyzer
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          python scripts/codeowner_analyzer.py \
+            --output .github/CODEOWNERS \
+            --depth 3 \
+            --min-commits 1 \
+            --days-back 180 \
+            --top-n 5 \
+            --no-api
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          # Check if CODEOWNERS file is new (unstaged) or has changes
+          if git ls-files --error-unmatch .github/CODEOWNERS >/dev/null 2>&1; then
+            # File is tracked, check for changes
+            if git diff --quiet .github/CODEOWNERS; then
+              echo "changed=false" >> $GITHUB_OUTPUT
+              echo "No changes detected in CODEOWNERS"
+            else
+              echo "changed=true" >> $GITHUB_OUTPUT
+              echo "Changes detected in CODEOWNERS"
+            fi
+          else
+            # File is untracked (newly created)
+            echo "changed=true" >> $GITHUB_OUTPUT
+            echo "CODEOWNERS file is new"
+          fi
+
+      - name: Create Pull Request
+        if: steps.check_changes.outputs.changed == 'true'
+        uses: peter-evans/create-pull-request@v7
+        with:
+          token: ${{ secrets.FLASHINFER_GITHUB_TOKEN }}
+          commit-message: |
+            chore: update CODEOWNERS based on git history
+
+            Auto-generated CODEOWNERS update based on commit activity over the last 365 days.
+
+            🤖 Generated with [Claude Code](https://claude.com/claude-code)
+
+            Co-Authored-By: Claude <[email protected]>
+          branch: auto-update-codeowners
+          base: main
+          delete-branch: true
+          title: 'chore: Update CODEOWNERS'
+          body: |
+            ## Summary
+
+            This PR updates the CODEOWNERS file based on git commit history analysis from the last 365 days.
+
+            ## Changes
+
+            - Updated `.github/CODEOWNERS` with current code ownership based on:
+              - Commit frequency
+              - File coverage
+              - Commit recency
+
+            ## How to Review
+
+            1. Review the changes to `.github/CODEOWNERS`
+            2. Verify that the assigned owners are appropriate for each module
+            3. Make manual adjustments if needed before merging
+
+            ## Notes
+
+            - This is an automated PR generated weekly
+            - Minimum commits threshold: 2
+            - Analysis period: 365 days
+            - Directory depth: 3 levels
+
+            ---
+
+            🤖 This PR was automatically generated by the [update-codeowners workflow](.github/workflows/update-codeowners.yml)
+          labels: |
+            automated
+            maintenance
+          assignees: |
+
+          reviewers: |

scripts/codeowner_analyzer.py

@@ -31,6 +31,8 @@ def __init__(
         github_token: Optional[str] = None,
         use_api: bool = True,
         allowed_users: Optional[List[str]] = None,
+        max_depth: int = 3,
+        top_n_owners: int = 3,
     ):
         """
         Initialize the code owners analyzer.
@@ -43,10 +45,14 @@ def __init__(
             github_token: Optional GitHub API token for higher rate limits
             use_api: Whether to use GitHub API for email lookups (default: True)
             allowed_users: Optional list of GitHub usernames to include (filters out others)
+            max_depth: Maximum directory depth for module detection (default: 3)
+            top_n_owners: Number of top owners to include in CODEOWNERS file (default: 3)
         """
         self.repo_path = Path(repo_path).resolve()
         self.min_commits = min_commits
         self.days_back = days_back
+        self.max_depth = max_depth
+        self.top_n_owners = top_n_owners
         self.module_owners: DefaultDict[str, DefaultDict[str, int]] = defaultdict(
             lambda: defaultdict(int)
         )
@@ -439,8 +445,10 @@ def get_modules(self) -> List[str]:
 
             if file_ext in relevant_extensions:
                 # Add the directory and all parent directories as modules
+                # Limited by max_depth
                 path_parts = Path(dir_path).parts
-                for i in range(1, len(path_parts) + 1):
+                max_parts = min(len(path_parts), self.max_depth)
+                for i in range(1, max_parts + 1):
                     module = "/".join(path_parts[:i])
                     if not self.should_exclude(module):
                         modules.add(module)
@@ -654,10 +662,10 @@ def generate_codeowners_file(
 
             for module, data in results.items():
                 if data["owners"]:
-                    # Take top 3 owners or those with ownership score > 0.1
+                    # Take top N owners or those with ownership score > 0.1
                     top_owners = [
                         owner
-                        for owner in data["owners"][:3]
+                        for owner in data["owners"][: self.top_n_owners]
                         if owner["ownership_score"] > 0.1
                     ]
 
@@ -773,6 +781,18 @@ def main() -> int:
         "--allowed-users-file",
         help="File containing allowed GitHub usernames, one per line",
     )
+    parser.add_argument(
+        "--depth",
+        type=int,
+        default=3,
+        help="Maximum directory depth for module detection (default: 3)",
+    )
+    parser.add_argument(
+        "--top-n",
+        type=int,
+        default=3,
+        help="Number of top owners to include in CODEOWNERS file (default: 3)",
+    )
 
     args = parser.parse_args()
 
@@ -811,6 +831,8 @@ def main() -> int:
             github_token=args.github_token,
             use_api=not args.no_api,
             allowed_users=allowed_users,
+            max_depth=args.depth,
+            top_n_owners=args.top_n,
         )
     except ValueError as e:
         print(f"Error: {e}", file=sys.stderr)