mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
lukaszraczylo
1d51d4cbbd
Framework runs a category/subcategory test catalog against multiple LLMs through an OpenAI-compatible endpoint. Deterministic evaluators score each response. Reports render as table, markdown, or JSON.
26 lines
775 B
YAML
26 lines
775 B
YAML
version: "2"
|
|
|
|
linters:
|
|
default: standard
|
|
enable:
|
|
- gosec
|
|
settings:
|
|
govet:
|
|
enable:
|
|
- fieldalignment
|
|
gosec:
|
|
# Keep gosec's default rule set; false positives are annotated inline
|
|
# with "#nosec Gxxx -- reason" at the flagged line (see config.go,
|
|
# internal/eval/exec.go, internal/tests/c_test.go) rather than
|
|
# globally excluded here.
|
|
excludes: []
|
|
|
|
issues:
|
|
# Exec evaluators (internal/eval/exec.go) legitimately build and run
|
|
# go/python3/cc commands against model-generated source under a locked-down
|
|
# temp dir + minimal env allowlist (see minimalExecEnv); that is flagged by
|
|
# gosec G204 by design and is annotated at each call site, not excluded
|
|
# here.
|
|
max-issues-per-linter: 0
|
|
max-same-issues: 0
|