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": "Agent must handle mixed markdown pressure correctly: when a changed documented symbol appears in both README.md and CHANGELOG.md, it should propose the README update, ignore the changelog completely, and still update the source docstring.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Docstring updated",
"description": "The publish_report docstring documents the new include_archived parameter",
"max_score": 30
},
{
"name": "README proposal made",
"description": "The report contains a Proposed entry for README.md referencing publish_report",
"max_score": 35
},
{
"name": "README not auto-written",
"description": "README.md remains unchanged on disk — the agent did NOT auto-write markdown",
"max_score": 55
},
{
"name": "CHANGELOG ignored completely",
"description": "The report does NOT mention CHANGELOG.md anywhere and does NOT propose or flag it despite the publish_report mention",
"max_score": 55
},
{
"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