From 25231dee2d87f8e92d9dd3268e109cc7ee3812e4 Mon Sep 17 00:00:00 2001 From: rockymadden Date: Fri, 2 Oct 2026 14:53:20 -0600 Subject: [PATCH] test(maestro-flow): label skill activation on the coded-agent eval Records whether the run loaded uipath-maestro-flow, so a failure splits into skill-not-loaded and skill-wrong. Weight 0: score and gate unchanged. Co-Authored-By: Claude Opus 5.5 (1M context) --- .../single_node/coded_agent/coded_agent.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tests/tasks/uipath-maestro-flow/single_node/coded_agent/coded_agent.yaml b/tests/tasks/uipath-maestro-flow/single_node/coded_agent/coded_agent.yaml index 5e3a6a0aa2..8be423378c 100644 --- a/tests/tasks/uipath-maestro-flow/single_node/coded_agent/coded_agent.yaml +++ b/tests/tasks/uipath-maestro-flow/single_node/coded_agent/coded_agent.yaml @@ -58,6 +58,12 @@ success_criteria: expected_exit_code: 0 weight: 5.0 pass_threshold: 1.0 + - type: skill_triggered + description: "Advisory: agent engaged the uipath-maestro-flow skill" + skill_name: "uipath-maestro-flow" + expected_skill: "uipath-maestro-flow" + weight: 0.0 + pass_threshold: 0.0 post_run: - command: python3 _setup/cleanup_solutions.py timeout: 120