AIWARLIVE
← Command board

Claude Code — Field Evidence

githubUnverified
Claude Code · Claude Code · complaint
Field note
huangruiteng/loopx — Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executable todos, evidence logs, and verifiable handoffs.
collected 2026-07-15original 2026-07-15

Does this shift the US–China race?

Be the first to call it

Community reactions

Quoted from public discussions · not endorsed
Add issue-fix candidate dedupe preflight ## Summary - Add an explicit provider-neutral candidate preflight before Issue Fix patch planning. - Reconcile compact domain state, all-state numeric closing references, and current-revision-verified semantic implementation evidence. - Su
@huangruiteng · GitHub · ▲ 3 · 1h ago · read →
Queue reviewer notifications outside delivery windows ## Summary - add an optional provider-neutral reviewer-notification delivery window - queue compact public-safe receipts without provider calls outside the window - persist queued state in the existing issue-fix PR…
@huangruiteng · GitHub · ▲ 2 · 51m ago · read →
refactor(benchmark): retire prompt-polling treatment routes ## Summary - remove the legacy prompt-polling and blind-loop pseudo-treatment routes from launchable SkillsBench and Harbor/Terminal-Bench execution paths - fail closed on retired Harbor polling kwargs and prevent…
@huangruiteng · GitHub · ▲ 2 · 3h ago · read →
Impact on the index
Usage limits · major
US -50
Directional contribution — before recency decay and per-type diminishing returns. How it works →
Source ↗

Related Front

US vs ChinaLikely
U.S. FrontiervsChina Open-Weight

Likely — capability gap narrowing on common tasks

Letters from the Front

Be the first to file a report.