From 96078d783780926ea8a6f848c47552d9cb9eafc4 Mon Sep 17 00:00:00 2001 From: Niels Bantilan Date: Thu, 30 Jul 2026 16:36:47 -0400 Subject: [PATCH] ci(evals): run on the flyte-agent-plugins-evals project (was flytesnacks) Point the demo.hosted eval runs at the dedicated flyte-agent-plugins-evals project instead of the shared flytesnacks project. The driver reads task.project from evals/config/flyte.yaml, so this switches both the flyte-evals CI job and local runs. Co-Authored-By: Claude Opus 4.8 (1M context) --- evals/config/flyte.yaml | 2 +- evals/workflows/eval_wf.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/evals/config/flyte.yaml b/evals/config/flyte.yaml index 7c2a860..b16d6b5 100644 --- a/evals/config/flyte.yaml +++ b/evals/config/flyte.yaml @@ -7,5 +7,5 @@ image: builder: remote task: org: demo - project: flytesnacks + project: flyte-agent-plugins-evals domain: development diff --git a/evals/workflows/eval_wf.py b/evals/workflows/eval_wf.py index 178019b..b978850 100644 --- a/evals/workflows/eval_wf.py +++ b/evals/workflows/eval_wf.py @@ -1,7 +1,7 @@ """Flyte orchestration of the flyte-agent-plugin eval harness. -Runs on demo.hosted.unionai.cloud (org demo / project flytesnacks / domain -development, remote image builder — see evals/config/flyte.yaml). The workflow +Runs on demo.hosted.unionai.cloud (org demo / project flyte-agent-plugins-evals / +domain development, remote image builder — see evals/config/flyte.yaml). The workflow expands the scenario matrix, fans out one action per (scenario x harness) via `flyte.map`, then aggregates verdicts into a scorecard.