fix(tests): unhang the Claude Code skill suite and realign SDD assertions with the current skill - #2137
Open
obra wants to merge 2 commits into
Open
fix(tests): unhang the Claude Code skill suite and realign SDD assertions with the current skill#2137obra wants to merge 2 commits into
obra wants to merge 2 commits into
Conversation
run_claude ran `timeout "$timeout" "${cmd[@]}"` with the suite's stdin
inherited by the spawned CLI. When the suite is run from a terminal (or
any open stdin), claude -p can block reading stdin and each test stalls
for its full timeout instead of completing.
Verified deterministically with a stub `claude` that reads stdin (cat):
with an open stdin pipe the old helper blocks until timeout kills it
(exit 124); with the redirect it exits immediately with output.
Part of #2130; defect documented in PR #2071 by @ericyen97903-lab.
The SDD skill tests still asserted on pre-rename skill text, so correct model answers failed the suite: - "Read at beginning" asserted "Step 1|beginning|start|Load Plan"; the current skill has no numbered steps or Load Plan phase (setup covers it: "Read the plan once" during Setup). A live run today failed this assertion when the model correctly answered "during setup". Pattern now accepts setup/before-dispatch paraphrases while still requiring an at-the-start answer. - "Provides text directly" asserted the removed provide-full-task-text behavior; SDD now routes task requirements through brief files (scripts/task-brief). The test now asks brief-file-vs-whole-plan and asserts the brief-based flow. - The integration test's prompt and summary told the agent to "provide full task text to subagents (don't make them read files)", contradicting the skill it verifies; reworded to the task-brief flow. Also gave its direct `timeout 1800 claude -p` the same </dev/null stdin guard as run_claude. Live-LLM tests; verified with bash -n on every touched file. Part of #2130; defects documented in PR #2071 by @ericyen97903-lab.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem (tracked in #2130)
Four defects left the Claude Code skill suite unable to pass:
test-helpers.shspawned the CLI undertimeoutwith stdin left open — the CLI can block on stdin and hang the whole suite.test-subagent-driven-development.sh:86asserted pre-rename step names (Step 1|Load Plan) that no longer exist in the skill — a live run yesterday failed exactly here while the model's answer was correct ('during setup').scripts/task-brief.test-subagent-driven-development-integration.sh: its prompt instructed the model to violate the current skill ('Provide full task text to subagents'), and its directclaude -pinvocation also lacked the stdin guard.Fix
< /dev/nullon both CLI spawn sites (helper + integration test).test-worktree-native-preference.sh's 'Step 1a' checked and left alone — that's its own RED/GREEN terminology, not the SDD rename.Verification
bash -nclean on all touched files. The stdin fix has a deterministic falsification: a stubclaudethat reads stdin — pre-fix helper blocks until timeout (exit 124), post-fix exits immediately (exit 0). The prose assertions are live-LLM by nature; they were rewritten from the current skill text, and the previously-failing 'Read at beginning' case now matches yesterday's observed correct answer.Findings originally reported in PR #2071 (@ericyen97903-lab, closed on process grounds), verified during triage and tracked in #2130. Fixes #2130.
Who is submitting
Claude Fable 5 on Claude Code 2.1.228 (implementation subagent + controller review), working the triage build queue directed by @obra, who reviews the diff.
@arittr @ada-sen — review requested.