ADF dispatch: unattended long runs require a machine-checkable acceptance criterion and a known-answer control run
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 35/100
- Issue 类型
- 功能
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- rust
调研方向
Start by locating the task and agent definitions, the spawner, and loop detection referenced in the proposal and issue #3080. Trace how unattended dispatch is selected, then verify that missing fields and a failing control run are rejected before the real task, while acceptance progress can inform long-run detection.
由索引模型根据 Issue 内容生成。
描述
Proposal
A dispatch rule for ADF: a task may run unattended for a long period only if it has (a) a machine-checkable acceptance criterion and (b) a control run on a case with a known answer, executed through the same pipeline before the real run. Tasks without both stay attended or tightly bounded (open-ended refactors, issue triage).
Why
Anthropic's nine-loop computation ran overnight on nothing but "keep going" prompts and produced a correct frontier result. Our runaway-loop failures have the same shape and the opposite outcome. The difference was not the model. The task carried its own oracle:
- an eight-loop control run, checked against the published result;
- exact arithmetic repeated modulo three primes;
- two representations cross-checked on all 107,053 nonzero coefficients;
- an independent group reproducing part of the result.
The loop detector should treat "long and making verifiable progress" differently from "long and repeating itself". A passing control run plus a checkable criterion is what makes that distinction possible.
Tasks
- Add an
acceptancefield (the command or check) and acontrolfield (a known-answer case) to the task and agent definitions used for long or unattended dispatch. - Spawner: refuse unattended mode when either field is missing, or when the control run fails.
- Loop detection (#3080): use progress against the acceptance check as a signal that a long run is still productive.
Acceptance
- An unattended dispatch without both fields is rejected, with a clear message.
- A deliberately broken pipeline is caught by its control run before the real task starts.
Source
https://www.anthropic.com/research/yes-claude-can-do-nine-loops ; result page https://smsharma.io/cosmic-nine-loops/
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
- 30 天内合并 PR
- 3
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
terraphim/terraphim-ai 的其他 Issue
-
terraphim_rlm: require a per-sub-result verification plan (recheck / control / independent route)未关闭
难度 4/5 3-5 天 新手友好度 48/100
terraphim/terraphim-ai#969 · 1 条评论 ·
-
难度 5/5 一周以上 新手友好度 35/100
terraphim/terraphim-ai#967 ·
-
难度 4/5 3-5 天 新手友好度 48/100
terraphim/terraphim-ai#966 ·
-
难度 5/5 一周以上 新手友好度 30/100
terraphim/terraphim-ai#965 · 2 条评论 ·
-
难度 5/5 一周以上 新手友好度 25/100
terraphim/terraphim-ai#885 ·
查看 terraphim/terraphim-ai 的全部 Issue
相似的 Issue
-
llm translation
难度 2/5 1-3 小时 新手友好度 76/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 77/100
CybercentreCanada/sawp#13 ·
-
area: backend type: enhancement
难度 2/5 1-3 小时 新手友好度 61/100
armadavalor/WinKnife#6 ·
-
难度 2/5 1-3 小时 新手友好度 68/100
-
难度 2/5 1-3 小时 新手友好度 78/100
5omeOtherGuy/phaseone#870 ·
维护者通常 1 天内回复