3 Commits

Include renames

Author	SHA1	Message	Date
spacedandy-agents-simplex	78e136c2a3	ci: compare the directory count's text size with the description's by their ink in the desktop smoke test	2026-10-15 17:22:46 +00:00
spacedandy-agents-simplex	51bcb8fdf6	ci: let Claude run the full desktop search after a scripted setup, with Haiku 5.5 on Claude Code 2.1.296 ... The prompt runs the whole plan with the toolbar at the bottom and, at the top, only the checks the layouts render differently.	2026-10-15 16:15:27 +00:00
spacedandy-agents-simplex	77003aae68	ci: let Claude Code repeat the desktop directory search on [claude-test] pushes ... A claude job (environment app-sim-claude, only on workflow_dispatch or a head commit with [claude-test]) starts its own test backend, builds the patched app, runs the scripted onboarding, and gives claude -p (pinned 2.1.292, Claude Haiku 5.5, at most 60 turns and 4 USD) the same search in both layouts to do with the ui helper, reading screenshots. Claude gets Bash, Read and Write only: a PreToolUse hook lets through nothing but single ui commands, credentials are scrubbed from its subprocesses, files are limited to its output directory, no MCP. The job passes when Claude reports CLAUDE-TEST: PASS, and uploads its report, screenshots, transcript and usage (turns, tokens, cost estimated at API prices).	2026-10-15 11:50:50 +00:00