From 608cb7b1dd9581b0901f076d27426ea1b9aa7abc Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 13:17:27 +0300 Subject: [PATCH 01/11] feat: convert hello-world to ASE eval (minimal - no evals.json) Co-authored-by: Cursor --- submissions/hello-world/metadata.yaml | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/submissions/hello-world/metadata.yaml b/submissions/hello-world/metadata.yaml index 238c9fe..ea65b66 100644 --- a/submissions/hello-world/metadata.yaml +++ b/submissions/hello-world/metadata.yaml @@ -1,12 +1,8 @@ name: hello-world description: "Create a file with specific content -- minimal smoke-test submission" persona: general -version: "0.1.3" +version: "0.1.4" tags: - smoke-test - trivial -cpus: 1 -memory_mb: 512 -storage_mb: 1024 -experiment: - n_trials: 1 +eval_engine: ase From 32c4aedc470f8b6b68805ccc5b06cc2f267ac3b3 Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 13:24:19 +0300 Subject: [PATCH 02/11] trigger: re-run pipeline Co-authored-by: Cursor From a37f9270aca62e9117cda3c4beebfacb6b591df2 Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 13:26:37 +0300 Subject: [PATCH 03/11] feat: add hello-world-minimal ASE submission (no evals.json) Co-authored-by: Cursor --- submissions/hello-world-minimal/metadata.yaml | 8 ++++++++ submissions/hello-world-minimal/skills/SKILL.md | 13 +++++++++++++ 2 files changed, 21 insertions(+) create mode 100644 submissions/hello-world-minimal/metadata.yaml create mode 100644 submissions/hello-world-minimal/skills/SKILL.md diff --git a/submissions/hello-world-minimal/metadata.yaml b/submissions/hello-world-minimal/metadata.yaml new file mode 100644 index 0000000..e80e66e --- /dev/null +++ b/submissions/hello-world-minimal/metadata.yaml @@ -0,0 +1,8 @@ +name: hello-world-minimal +description: "Create a file with specific content -- ASE smoke-test (no evals.json)" +persona: general +version: "0.1.0" +tags: + - smoke-test + - ase +eval_engine: ase diff --git a/submissions/hello-world-minimal/skills/SKILL.md b/submissions/hello-world-minimal/skills/SKILL.md new file mode 100644 index 0000000..4836731 --- /dev/null +++ b/submissions/hello-world-minimal/skills/SKILL.md @@ -0,0 +1,13 @@ +# Hello World Skill + +A trivial file-creation skill used as a smoke test for the ABEvalFlow pipeline. + +## What the agent must do + +Given an instruction to create a file with specific content, the agent should +produce the correct file at the correct path with the exact expected content. + +## Evaluation criteria + +- File exists at the specified path +- File content matches the expected string exactly (including punctuation) From bac5d01a16eee6307161d7a6db561dc1b4fac0ae Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 14:06:03 +0300 Subject: [PATCH 04/11] trigger: re-run with ASE evals generation support Co-authored-by: Cursor From 1e3dcacd12ef8fc2171c1e3ae4b5705ba0cc675c Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 14:10:31 +0300 Subject: [PATCH 05/11] trigger: use feature branch for pipeline code Co-authored-by: Cursor From 5832c744c86aaf64022c7e52c37402a8728118c1 Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 14:15:16 +0300 Subject: [PATCH 06/11] fix: add YAML frontmatter to SKILL.md Co-authored-by: Cursor --- submissions/hello-world-minimal/skills/SKILL.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/submissions/hello-world-minimal/skills/SKILL.md b/submissions/hello-world-minimal/skills/SKILL.md index 4836731..eed9419 100644 --- a/submissions/hello-world-minimal/skills/SKILL.md +++ b/submissions/hello-world-minimal/skills/SKILL.md @@ -1,3 +1,8 @@ +--- +name: hello-world +description: A trivial file-creation skill for smoke testing +--- + # Hello World Skill A trivial file-creation skill used as a smoke test for the ABEvalFlow pipeline. From d5bb9ddfc124e895c440a6ad0c50a7f1adb6514e Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 15:14:33 +0300 Subject: [PATCH 07/11] trigger: test immediate security upload Co-authored-by: Cursor From a3c875e04509bf102bc33257b33ee920438bc9db Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 15:19:59 +0300 Subject: [PATCH 08/11] trigger: test with updated security-scan task Co-authored-by: Cursor From 9ada5ed6f7097155ebbf11cf70f1b9c515ebd0b2 Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 15:26:34 +0300 Subject: [PATCH 09/11] trigger: fix minio secret keys Co-authored-by: Cursor From 9f4b189fb7dc5acbe69d23b18cdcc58bb02f4a6b Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 15:30:28 +0300 Subject: [PATCH 10/11] trigger: test with advisory semantic review Co-authored-by: Cursor From b60a0fef883815692cc58c66756b184c31f4dde4 Mon Sep 17 00:00:00 2001 From: gziv Date: Mon, 1 Jun 2026 15:36:21 +0300 Subject: [PATCH 11/11] trigger: test with fixed env vars and DB secret Co-authored-by: Cursor