Auto-syncs stale docstrings and README when function signatures change. Detects documentation drift after refactors, parameter additions, or return type changes. Dry-run by default — proposes before writing.
87
100%
Does it follow best practices?
Impact
86%
1.59xAverage score across 17 eval scenarios
Passed
No known issues
A developer already updated the docstring for a changed parameter before running the documentation sync. The documentation should be detected as already current, and the parameter entry should not be duplicated when --apply is used.
Extract the following files, then set up the git repository:
=============== FILE: inputs/setup.sh =============== #!/usr/bin/env bash set -euo pipefail git init git config user.email "dev@example.com" git config user.name "Dev" mkdir -p src cat > src/cache.py << 'PYEOF' def fetch(key: str) -> str: """Fetch a cached value by key.
Args:
key: Cache lookup key.
Returns:
Cached value.
"""
return keyPYEOF git add -A && git commit -m "baseline" cat > src/cache.py << 'PYEOF' def fetch(key: str, region: str = "us-east-1") -> str: """Fetch a cached value by key.
Args:
key: Cache lookup key.
region: Cache region to query. Defaults to us-east-1.
Returns:
Cached value.
"""
return keyPYEOF
Sync the documentation in --apply mode and write the results to doc-sync-report.md.
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17