From 510053d16f89f463b7b22a0dbef1b576c3b0a810 Mon Sep 17 00:00:00 2001 From: garrytan Date: Fri, 23 Oct 2026 17:53:08 +0000 Subject: [PATCH] v1.91.183.0 fix(evals): a rejected API key is INFRA, never 131 assertion reds and reruns (#3361) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- CHANGELOG.md | 2 +- VERSION | 2 +- agents-digest/gstack-AGENTS.md | 2 +- package.json | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 11c892529..3ede054fe 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Changelog -## [Unreleased] +## [1.91.183.0] - 2026-10-23 **A rejected API key no longer turns a gate into 131 assertion reds and 131 reruns.** Train gate run 39696775546 ran with a rejected `ANTHROPIC_API_KEY`. Every case failed on a 401 before the model ran, and the report counted them as assertion failures. Rule 16 then reran all 131 cases with the same key. A trial whose provider rejected the run's credentials is now INFRA: the gate never reruns it, the verdict counts it under INFRA, and its failure line reads `credentials rejected: Invalid API key · …`. A real assertion failure that only mentions a key keeps its class and is still rerun. diff --git a/VERSION b/VERSION index 1f6481848..ac9268334 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.91.182.0 +1.91.183.0 diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md index 275434383..c433d5206 100644 --- a/agents-digest/gstack-AGENTS.md +++ b/agents-digest/gstack-AGENTS.md @@ -1,4 +1,4 @@ -# gstack digest v1.91.182.0 — regenerate/re-copy after upgrading gstack +# gstack digest v1.91.183.0 — regenerate/re-copy after upgrading gstack Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed for agent hosts without a full skill install. The full skills add workflows, diff --git a/package.json b/package.json index 86dbd66d0..ff3635537 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "gstack", - "version": "1.91.182", + "version": "1.91.183", "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.", "license": "MIT", "type": "module",