From 78acf84f2769d09605248f885c85eaa276ec5641 Mon Sep 17 00:00:00 2001 From: Nitsu45 Date: Wed, 21 Oct 2026 08:31:09 +0200 Subject: [PATCH] Prepare Bug20 qualified-review regression instead of Bug17 --- ...qualified-review-20261021-preparation.json | 38 +++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 docs/test-results/token-usage/bug20-qualified-review-20261021-preparation.json diff --git a/docs/test-results/token-usage/bug20-qualified-review-20261021-preparation.json b/docs/test-results/token-usage/bug20-qualified-review-20261021-preparation.json new file mode 100644 index 0000000..5c43eb8 --- /dev/null +++ b/docs/test-results/token-usage/bug20-qualified-review-20261021-preparation.json @@ -0,0 +1,38 @@ +{ + "format": "viano-test-preparation", + "format_version": 1, + "recorded_date": "2026-10-21", + "run": "bug20-qualified-review-20261021", + "case_id": "BUG-000020", + "package_id": "trial-qualified-review-BUG-000020-20261021", + "code_commit": "a33cee0cf86595baa03919d7530f3ac5107ebf06", + "configuration_sha256": { + "config/llm.early-review.local.toml": "ff3296f9a902e4e67861929e584d3629d76edd0d77898c3817ae7f44f50d7ef0", + "config/project.local.toml": "235016a23be2d8aa7aed7f450fd77792ccbf0fb9b24c05b65d4771782249f5e3", + "config/investigation.bounded.toml": "b3693a0eab479b67af1049dd0725e8d8e18b30d70eea176fa6c30a7bba723cf9" + }, + "inputs": [ + { + "name": "BUG-000020-20261008-130429.tar.gz", + "sha256": "a3ddbde9d046dbbe65354ca8bababc78a689e0a10e0935fb1f109d3a92d75c7e" + }, + { + "name": "WOWSRC-BUG-000020-20261008-130446.tar.gz", + "sha256": "ee82031e2a085e2da1db348a298a9f8defdb866796917277a2a98c8890551d6d" + } + ], + "account_eur": { + "last_confirmed": 13.37, + "new_run_start_confirmed": false + }, + "storage_bytes_before_preparation": 11646616228, + "storage_limit_bytes": 20000000000, + "replaces_preparation": "bug17-qualified-review-20261021; user corrected intended regression case; Bug17 not executed", + "test_goal": "Bug20 functional regression with qualified diagnosis and coding caveats. Evaluate missing-spawn diagnosis, suitable coding/template and human handoff, observed validation requirements, retained uncertainty, tokens/corrections/cost.", + "expected_prompt_versions": [ + "diagnosis_v8 or diagnosis_early_v8", + "change_request_v9" + ], + "prepared_state": "VALIDATED", + "paid_api_calls": 0 +}