terminal-bench-loop

原文涵盖的主题

• Terminal-Bench Loop
• When to use
• When NOT to use
• Three invariants you must preserve
• Inputs
• Issue topology
• Procedure
• 0. Read the current execution contract

A repeatable operating skill for driving one Terminal-Bench problem to a passing smoke through Paperclip, with explicit issue topology, bounded runs, board-gated product fixes, and worktree continuity. This skill is operational + diagnostic, not engineering. It coordinates issues, artifacts, and approvals around a Terminal-Bench loop. It does not authorize code changes — every accepted product fix lands as a separate implementation child issue after a board confirmation. Canonical execution model: read doc/execution-semantics.md before starting a loop or moving any loop issue. Every loop issue must rest in a state the doc allows: terminal (done/cancelled), explicitly live (active run / queued wake), explicitly waiting (inreview with participant/interaction/approval), or explicit recovery/blocker (blocked with blockedByIssueIds and a named owner). Trigger on an assignment whose title or body matches any of: "run Terminal-Bench in a loop", "loop \ through Paperclip" "drive Terminal-Bench fix-git", "iterate on Terminal-Bench until it passes" "Terminal-Bench smoke loop", "bench loop", "smoke loop on \ " An attached link to a Terminal-Bench loop parent issue, plus a request to do anothe

这里只展示节选，请以完整原文和当前要求为准。