From 392d63a5379a340faad9967bd747004be5eacc1a Mon Sep 17 00:00:00 2001 From: garrytan Date: Tue, 29 Sep 2026 19:14:54 +0000 Subject: [PATCH] ci(image): pin Claude Code 2.1.284 so the eval model is recognized 2.1.251 logs [claude-code:unrecognized_model] for claude-fable-5-1, the eval capture/judge default. 2.1.284 does not. The gate PTY smoke subset (plan-ceo/plan-devex plan-mode, plan-mode-no-op) parses on the new TUI; plan-design-review-plan-mode passed at 293 s on 2.1.284 and timed out at 300 s on 2.1.251 on the same tree. --- .github/docker/Dockerfile.ci | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/docker/Dockerfile.ci b/.github/docker/Dockerfile.ci index 4dc207e6b..0c4ca9a73 100644 --- a/.github/docker/Dockerfile.ci +++ b/.github/docker/Dockerfile.ci @@ -93,7 +93,13 @@ RUN curl --retry 5 --retry-delay 5 --retry-connrefused -fsSL https://bun.sh/inst # skillify HOME discovery on 2.1.237, guard/freeze hooks on 2.1.162). # Bump deliberately, via a PR that runs the PTY gate against the new TUI. # test/ci-image-cli-pin.test.ts fails the free suite if this pin is removed. -RUN npm i -g @anthropic-ai/claude-code@2.1.251 +# 2.1.284 (from 2.1.251, 2026-09-29): 2.1.251 logs +# [claude-code:unrecognized_model] for the eval model claude-fable-5-1; +# 2.1.284 recognizes it. Local canary: the gate PTY smoke subset parsed on +# both TUIs (7/8 pass on 2.1.284, 8/8 on 2.1.251; the one red was the model +# still in WebSearch at 300 s), and plan-design-review-plan-mode passed at +# 293 s on 2.1.284 where 2.1.251 timed out at 300 s. +RUN npm i -g @anthropic-ai/claude-code@2.1.284 # Playwright system deps (Chromium) — needed for browse E2E tests RUN npx playwright install-deps chromium