sankalp/DevGen
1
0 Fork 0
Code Issues Pull Requests 8 Actions Packages Projects Releases 12 Wiki Activity

refactor(devgen): enhance AI commit message sanitization

Browse Source 
The `sanitize_ai_commit_message` function has been significantly improved to better handle AI-generated commit messages, including support for bolded headers, more robust header detection, and a fallback mechanism for non-conventional messages.

**Enhancements & Refinements:**
- Added comprehensive docstring explaining the function's purpose and behavior
- Improved regex pattern to match conventional commit headers with optional bolding (e.g., **feat: ...**)
- Added case-insensitive matching for commit types
- Implemented a state-based approach with `found_header` flag for clearer logic
- Added automatic removal of bold markers (**) from headers
- Introduced fallback behavior to return the first non-empty line if no conventional header is found
- Improved code structure with better variable naming and comments
- Added early return for empty input strings

**Bug Fixes:**
- Fixed potential issue where the function could return empty strings for non-conventional messages
- Resolved edge case handling for messages without proper headers
```
This commit is contained in:
sankalp committed 2025-12-24 23:29:45 +05:45
1 parent fe7da77ed6
commit d373f95388
3 files changed
+124 -37
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

devgen/modules/commit_generator.py
+77 -17
View File
@@ -26,6 +26,20 @@ class CommitEngineError(Exception):
pass
# Token Optimization Constants
MAX_DIFF_SIZE = 8000 # Maximum characters for a single group diff
IGNORE_PATTERNS = [
"uv.lock",
"package-lock.json",
"pnpm-lock.yaml",
"yarn.lock",
"composer.lock",
"Gemfile.lock",
"poetry.lock",
]
class CommitEngine:
"""
Engine for generating AI-powered commit messages.
@@ -72,6 +86,7 @@ class CommitEngine:
def detect_changes(self) -> List[str]:
"""Detects changed, deleted, or untracked files."""
try:
# Get modified, deleted and untracked files
out = run_git_command(
[
"git",
@@ -82,7 +97,15 @@ class CommitEngine:
"--exclude-standard",
]
)
return [f.strip() for f in out.split("\n") if f.strip()]
files = [f.strip() for f in out.split("\n") if f.strip()]
# Also get staged files (in case of a previous failed run)
staged_out = run_git_command(["git", "diff", "--name-only", "--cached"])
staged_files = [f.strip() for f in staged_out.split("\n") if f.strip()]
# Combine and deduplicate
all_files = list(set(files + staged_files))
return all_files
except subprocess.CalledProcessError as e:
msg = f"Git command failed: {' '.join(e.cmd)}\nError: {e.stderr.strip()}"
self.logger.error(msg)
@@ -98,11 +121,38 @@ class CommitEngine:
return groups
def generate_diff(self, files: List[str]) -> str:
"""Generates diff for specific files."""
"""Generates diff for specific files, with truncation for token optimization."""
try:
return run_git_command(
["git", "--no-pager", "diff", "--staged", "--", *files]
)
# Filter out very large metadata files that don't need full diffs
summary_info = []
files_to_diff = []
for f in files:
if any(p in f for p in IGNORE_PATTERNS):
summary_info.append(f"[METADATA UPDATED] {f}")
else:
files_to_diff.append(f)
diff = ""
if files_to_diff:
diff = run_git_command(
["git", "--no-pager", "diff", "--staged", "--", *files_to_diff]
)
full_content = "\n".join(summary_info + [diff]).strip()
# Truncate if too large
if len(full_content) > MAX_DIFF_SIZE:
self.logger.info(
f"Truncating diff from {len(full_content)} to {MAX_DIFF_SIZE} chars"
)
half = MAX_DIFF_SIZE // 2
return (
full_content[:half]
+ "\n\n... [DIFF TRUNCATED FOR TOKEN OPTIMIZATION] ...\n\n"
+ full_content[-half:]
)
return full_content
except subprocess.CalledProcessError as e:
msg = f"Git command failed: {' '.join(e.cmd)}\nError: {e.stderr.strip()}"
self.logger.error(msg)
@@ -239,20 +289,30 @@ class CommitEngine:
return True
msg = self.generate_message(group, diff, cache)
if not msg:
self.logger.error(f"Empty message for {group}")
try:
if not msg:
self.logger.error(f"Empty message for {group}")
self._reset_group(files)
return False
if self.dry_run:
self._log_dry_run(group, msg)
self._reset_group(files)
else:
self.commit_staged(msg)
return True
except Exception as e:
self.logger.error(f"Failed to process group {group}: {e}")
self._reset_group(files)
return False
if self.dry_run:
self._log_dry_run(group, msg)
try:
run_git_command(["git", "reset", "HEAD", "--", *files])
except subprocess.CalledProcessError:
pass
else:
self.commit_staged(msg)
return True
def _reset_group(self, files: List[str]):
"""Unstages files for a group."""
try:
run_git_command(["git", "reset", "HEAD", "--", *files])
except subprocess.CalledProcessError:
pass # Ignore reset errors
def execute(self):
"""Main execution method."""
devgen/templates/commit/commit_message.j2
+9 -10
View File
@@ -1,15 +1,14 @@
Analyze the following git diff for the directory `{{ group_name }}` and generate a detailed semantic release commit message4. Format the output as:
1. A summary title in semantic release format (type(scope): summary) — scope can be the directory or 'root'.
2. A short summary paragraph if needed.
3. Bullet points listing the main changes, grouped as 'New Features', 'Enhancements & Refinements', and 'Bug Fixes' if relevant. Use bold for feature/section names.
Analyze the following git diff for `{{ group_name }}` and generate a semantic commit message.
Format:
1. Title: `<type>(<scope>): <summary>` (scope is `{{ group_name }}` or `root`).
2. Optional short summary.
3. Bullet points: `New Features`, `Enhancements`, `Bug Fixes`. Use **bold** for section names.
{% if use_emoji %}
4. Use appropriate emojis for the commit type and sections (e.g., 🚀 for features, 🐛 for bugs).
4. Use emojis (e.g., 🚀, 🐛).
{% else %}
4. Do NOT use any emojis in the commit message.
4. No emojis.
{% endif %}
Output only the commit message, don't include explanations or extra text.
Here is the git diff for `{{ group_name }}`:
Output ONLY the message.
Diff for `{{ group_name }}`:
{{ diff_text }}
devgen/utils.py
+38 -10
View File
@@ -31,25 +31,53 @@ def is_file_recent(file_path: Path | str, max_age_minutes: int = 120) -> bool:
def sanitize_ai_commit_message(raw_text: str) -> str:
"""
Cleans up the AI-generated commit message.
It looks for a conventional commit header and extracts everything from there.
It handles bolded headers and common AI prefixes.
"""
if not raw_text:
return ""
lines = raw_text.strip().split("\n")
cleaned_lines = []
in_block = False
# Regex for conventional commit header
# Regex for conventional commit header (including optional bolding)
# Examples:
# - feat(root): summary
# - **fix: bug fix**
# - chore(deps)!: breaking change
header_pattern = re.compile(
r"^(feat|fix|chore|refactor|docs|style|test|build|ci)(\(.*\))?!?: .*"
r"^(\*\*)?(feat|fix|chore|refactor|docs|style|test|build|ci)(\(.*\))?!?: .*",
re.IGNORECASE
)
cleaned_lines = []
found_header = False
for line in lines:
stripped = line.strip()
if in_block:
if header_pattern.match(stripped) or "**Sponsor**" in line:
if not found_header:
if header_pattern.match(stripped):
found_header = True
# Remove bolding if present
clean_line = stripped.replace("**", "").strip()
cleaned_lines.append(clean_line)
else:
# If we hit another header or a known separator, we stop (optional, but keep for now)
if "**Sponsor**" in line:
break
cleaned_lines.append(line)
elif header_pattern.match(stripped):
in_block = True
cleaned_lines.append(line)
return "\n".join(cleaned_lines).strip() if cleaned_lines else ""
if cleaned_lines:
return "\n".join(cleaned_lines).strip()
# Fallback: if no conventional commit header found, just take the first non-empty line
# to avoid failing completely, but log a warning if possible.
for line in lines:
if line.strip():
return line.strip()
return ""
def parse_markdown_sections(