Type stubs for chardet - Universal encoding detector for Python
Agent Success
Agent success rate when using this tile
65%
Improvement
Agent success rate improvement when using this tile compared to baseline
0.97x
Baseline
Agent success rate without this tile
67%
{
"context": "Assesses how well the solution leverages typeshed's metadata utilities to read stub dependency metadata and expand recursive requirements while producing the sorted external requirement list requested in the spec.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Path helpers",
"description": "Locates METADATA.toml via ts_utils.paths helpers such as metadata_path or distribution_path instead of manual path assembly.",
"max_score": 15
},
{
"name": "Dependency parsing",
"description": "Parses stub requirements through ts_utils.metadata.read_dependencies or read_metadata rather than hand-reading TOML so requirement objects and validation come from the package.",
"max_score": 20
},
{
"name": "Recursive expansion",
"description": "Expands transitive stub dependencies using ts_utils.metadata.get_recursive_requirements (or equivalent package entry point) instead of reimplementing recursion manually.",
"max_score": 30
},
{
"name": "Stub vs external split",
"description": "Keeps stub packages separate from external ones using PackageDependencies.typeshed_pkgs and .external_pkgs, emitting only external requirement strings as the spec requires.",
"max_score": 20
},
{
"name": "Extras handling",
"description": "Honors the extras argument by drawing optional requirements from package metadata (e.g., via read_metadata or parsed extras) and running get_recursive_requirements for those selections before merging results.",
"max_score": 15
}
]
}tessl i tessl/pypi-types-chardet@4.0.0docs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9