Let the agent iterate on a refactor continually until one of several predefined stop conditions is met, resolving blockers so each run works longer.
/goal GOAL: Complete Refactor Until Stop Conditions Met for a refactoring task: Let the agent iterate on a refactor continually until one of several predefined stop conditions is met, resolving blockers so each run works longer. CONTEXT: - Before editing, read the nearest AGENTS.md/CLAUDE.md, current issue or PLAN.md, and any failing logs already in the repo. - Inspect the target module, call sites, public API, tests, and compatibility notes. - Establish a baseline by running or locating evidence for: `pytest && git status --short`. 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 change public APIs, data formats, or user-visible behavior unless the goal requires it. - Keep behavior characterization tests before large internal changes. DONE WHEN: - The implementation or documentation directly satisfies: Let the agent iterate on a refactor continually until one of several predefined stop conditions is met, resolving blockers so each run works longer. - The verification command or evidence path succeeds: `pytest && git status --short`. - The final diff is scoped to the relevant files and has no unrelated formatting churn. VERIFY: - Run `pytest && git status --short` 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: How to achieve greater code refactoring automation? - OpenAI Community
证据摘要: I suggested we allow Codex to iterate continually until one of numerous stop conditions was met.; source: How to achieve greater code refactoring automation? - OpenAI Community; type: public-forum; verification: pytest && git status --short