Use `/goal` to improve benchmark coverage and persist the command in history.
/goal GOAL: Complete Improve Benchmark Coverage for a project with failing or missing verification gates: Use `/goal` to improve benchmark coverage and persist the command in history. CONTEXT: - Before editing, read the nearest AGENTS.md/CLAUDE.md, current issue or PLAN.md, and any failing logs already in the repo. - Inspect test suites, lint config, CI logs, coverage reports, and failing output. - Establish a baseline by running or locating evidence for: `cargo test -p codex-tui goal_slash_command -- --nocapture`. CONSTRAINTS: - Keep the scope limited to this goal; do not expand into unrelated cleanup. - Do not weaken tests, delete assertions, or mask errors to make verification pass. - Respect the repository's AGENTS.md/CLAUDE.md instructions and existing patterns. - Do not weaken lint, typecheck, or test rules to create a green result. - Fix production or fixture causes before changing expectations. DONE WHEN: - The implementation or documentation directly satisfies: Use `/goal` to improve benchmark coverage and persist the command in history. - The verification command or evidence path succeeds: `cargo test -p codex-tui goal_slash_command -- --nocapture`. - The final diff is scoped to the relevant files and has no unrelated formatting churn. VERIFY: - Run `cargo test -p codex-tui goal_slash_command -- --nocapture` or the closest repo-local equivalent if the exact command is not available. - Capture before/after evidence for the behavior, metric, report, or artifact involved. - If verification cannot run locally, stop and report the missing dependency instead of guessing success. OUTPUT: - Summarize changed files, key decisions, verification output, and remaining risks. - Include any follow-up that is required for production rollout or human review. STOP RULES: - Pause if secrets, production access, stakeholder decisions, or destructive data operations are required. - Pause after three failed fix attempts on the same symptom and challenge the root-cause hypothesis. - Do not mark the goal complete until the current repository state has been audited against DONE WHEN.
原始来源: openai/codex PR 21860
证据摘要: /goal improve benchmark coverage; source: openai/codex PR 21860; type: github-pr; verification: cargo test -p codex-tui goal_slash_command -- --nocapture