From d3620dce9f188992809d31cd772826f458eb47d0 Mon Sep 17 00:00:00 2001 From: Federico Bartoli Date: Sat, 26 Sep 2026 09:00:32 +0200 Subject: [PATCH] test(evals): count the slash-command path in every plugin eval tool_used grader --- evals/plugin/code-review-fires/graders/skill-fired.md | 2 +- evals/plugin/code-review-stays-quiet/graders/not-fired.md | 2 +- evals/plugin/code-review-stays-quiet/graders/tdd-fired.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/evals/plugin/code-review-fires/graders/skill-fired.md b/evals/plugin/code-review-fires/graders/skill-fired.md index b3d99df0..37da62c3 100644 --- a/evals/plugin/code-review-fires/graders/skill-fired.md +++ b/evals/plugin/code-review-fires/graders/skill-fired.md @@ -1,5 +1,5 @@ --- type: tool_used tool: Skill -input_match: '"skill"\s*:\s*"(?:[\w-]+:)?code-review-and-quality"' +input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(code-review-and-quality|review)"' --- diff --git a/evals/plugin/code-review-stays-quiet/graders/not-fired.md b/evals/plugin/code-review-stays-quiet/graders/not-fired.md index c27388ab..097f5674 100644 --- a/evals/plugin/code-review-stays-quiet/graders/not-fired.md +++ b/evals/plugin/code-review-stays-quiet/graders/not-fired.md @@ -1,7 +1,7 @@ --- type: tool_used tool: Skill -input_match: '"skill"\s*:\s*"(?:[\w-]+:)?code-review-and-quality"' +input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(code-review-and-quality|review)"' min: 0 max: 0 arm: both diff --git a/evals/plugin/code-review-stays-quiet/graders/tdd-fired.md b/evals/plugin/code-review-stays-quiet/graders/tdd-fired.md index b4a41394..ca279cd0 100644 --- a/evals/plugin/code-review-stays-quiet/graders/tdd-fired.md +++ b/evals/plugin/code-review-stays-quiet/graders/tdd-fired.md @@ -1,6 +1,6 @@ --- type: tool_used tool: Skill -input_match: '"skill"\s*:\s*"(?:[\w-]+:)?test-driven-development"' +input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(test-driven-development|test)"' arm: with-only ---