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
{
"context": "Tests whether the agent proceeds to check for body-only documentation drift even when scripts/get_diff.sh exits with code 1 (no signature changes found). The function signature is unchanged so the script reports nothing — but the body changed and the docstring is now stale (says 'two conditions' when there are now four).",
"type": "weighted_checklist",
"checklist": [
{
"name": "Stale docstring updated",
"description": "src/validator.py docstring no longer says 'two conditions' OR the doc-sync-report.md shows it was updated to reflect the four validation conditions",
"max_score": 30
},
{
"name": "Body-only drift detected",
"description": "doc-sync-report.md contains an entry for validate_password indicating a docstring update — the agent did NOT stop after seeing no contract changes",
"max_score": 30
},
{
"name": "Not stopped at script exit",
"description": "The report does NOT say 'No contract changes detected' as a final conclusion that stops processing — it proceeds to detect the body-only drift",
"max_score": 45
},
{
"name": "Unified report format",
"description": "doc-sync-report.md contains '## Doc Sync Report' as a top-level heading",
"max_score": 45
}
]
}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