Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

terraphim_rlm: require a per-sub-result verification plan (recheck / control / independent route)

未关闭
#969 1 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
48/100
Issue 类型
功能
描述清晰度
描述清楚
活跃度
活跃
技术栈
rust
领域
ai, testing-qa

调研方向

Start with the RLM design doc and the rlm_* sub-call result definitions, then inspect the RLM test suite and executor paths. Done means the design states the verification requirement, results carry the accepted verified_by values with gated refusal of none, and a control test fails when execution is skipped or silently falls back.

由索引模型根据 Issue 内容生成。

描述

Proposal

Make a verification plan for each sub-result a design requirement for terraphim_rlm decompositions. Decomposition alone does not make a long recursive run trustworthy. Every sub-call that produces a result the parent relies on should declare how that result is checked, for example:

  • an exact or deterministic re-check (a recomputation, test, schema or invariant);
  • a known-answer control instance run through the same path;
  • an independent second route, where it is cheap.

Why

The nine-loop computation (Anthropic, 2026-09-25) is a budget-bounded, decomposable, long-running job of exactly the kind RLM targets. The result was trusted because of its checks, not because of the run itself: an eight-loop control checked against the published value, exact arithmetic modulo several primes, and a cross-check between two representations. The open bugs #3405 (the Firecracker stub reports exit 0 when no VM ran) and #3406 (silent fallback to LocalExecutor) are the failure class this guards against. A sandbox that reports success when nothing ran passes every check except a known-answer control.

Acceptance

  • The RLM design doc states the requirement.
  • rlm_* sub-call results carry a verified_by field: none, recheck, control or independent. The parent can refuse results marked none for gated outputs.
  • At least one control instance in the RLM test suite fails loudly when the executor does not actually run code (covers #3405 and #3406).

Mirror of Gitea terraphim/terraphim-ai# (source of truth).

主要语言
Rust
星标
65
派生
5
平均合并
1 小时 17 分钟
30 天内合并 PR
2

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

terraphim/terraphim-ai 的其他 Issue

查看 terraphim/terraphim-ai 的全部 Issue

相似的 Issue

更多 Rust Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。