Question: should the Model Pool's judge go free, or be skipped, while the OpenRouter balance is low?
维护者通常 1 天内回复
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
- go
调研方向
Read internal/credits/credits.go for LowCreditsUSD and Reading.Low, then inspect Candidates in internal/pool/judge/judge.go and the judge loop in cmd/codeaf/poolrecord.go. Review the low-credit guidance in internal/manual/chat/openrouter-credits.md and models-and-costs.md. Done requires a maintainer decision among the three options, matching behavior, and documentation that explains what happens to judges when credit is low.
由索引模型根据 Issue 内容生成。
描述
A question for a ruling, not a defect. Nothing here behaves differently from how it was written. #1440 made a new situation possible, and nobody has decided how the Model Pool's judge should behave in it.
What is true today
- #1440 (merged into
devasf101ad2e7) reads the OpenRouter balance. When the account is known to be low (credits.LowCreditsUSD, $0.50 or less remaining), every crew tier the person has not written a model for goes to a free model, so a near-zero account keeps working on free models. - After a task lands, the Model Pool records it and asks a judge model to score the seats that ran it (
cmd/codeaf/poolrecord.go, the loop that callsjudge.Judge). It asks up tojudgeTriescandidates in turn. - The judge is never free.
judge.Candidatesininternal/pool/judge/judge.goleaves out every row whose prompt and completion prices sum to zero, and every id ending in:free. Its comment gives the reason: a free row is rate-limited and answers with a 429 when a judge most needs an answer.
Together: on an account codeaf itself knows is almost out of credit, the task's own work runs on free models, but the judge pass after it still picks the cheapest paid model that qualifies. That call spends from the balance #1440 is trying to protect. When the balance is nearly empty, the call is also likely to fail with a 402 that nobody sees, and the pool then records a failed judge attempt instead of scores.
The options
- A free judge while the balance is low. Drop the free-row exclusion when the reading says
Low, and accept 429s. A judge that fails costs nothing, and the pool already records a failed judge as such. - Skip the judge pass while the balance is low. The landing is recorded unjudged, with a reason such as
balance low. Nothing is spent, and the pool loses those scores. - Keep it paid. The scores are worth the cents. If so, the manual should say that a judge call is paid even when the crew has gone free, and the low-credit notice should not imply that everything is now free.
Whichever is chosen, the words a person reads about low credit (internal/manual/chat/openrouter-credits.md and models-and-cost.md) should say what the judge does.
Where
internal/pool/judge/judge.go:Candidates. Search forA free row is a rate-limited.cmd/codeaf/poolrecord.go: the judge loop. Search forjudge.Candidates(models(), seats, judge.DefaultFloor).internal/credits/credits.go:LowCreditsUSDandReading.Low.
Raised while merging #1440 into santos/dev2 for #1410.
- 主要语言
- Go
- 星标
- 115
- 派生
- 14
- 平均合并
- 9 小时 37 分钟
- 30 天内合并 PR
- 755
环境准备
我们还没有检查这个项目的环境配置文件。先看它的 README,通用步骤见我们的新手贡献指南。
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。
Agent-Field/CodeAF 的其他 Issue
-
area:chat bug sev:papercut
难度 2/5 1-3 小时 新手友好度 86/100
Agent-Field/CodeAF#1592 ·
维护者通常 1 天内回复
-
area:headless bug sev:critical
难度 2/5 1-3 小时 新手友好度 88/100
Agent-Field/CodeAF#1566 · 已指派 1 人 ·
维护者通常 1 天内回复
-
area:chat feature
难度 2/5 1-3 小时 新手友好度 88/100
Agent-Field/CodeAF#1510 ·
维护者通常 1 天内回复
-
area:tests bug
难度 2/5 1-3 小时 新手友好度 82/100
Agent-Field/CodeAF#1489 ·
维护者通常 1 天内回复
-
area:chat bug good first issue sev:papercut
难度 2/5 1-3 小时 新手友好度 78/100
Agent-Field/CodeAF#1470 ·
维护者通常 1 天内回复
查看 Agent-Field/CodeAF 的全部 Issue
相似的 Issue
-
priority: low 🌱 type: enhancement 💅🏼
难度 2/5 半天 新手友好度 84/100
nebari-dev/llm-serving-pack#199 ·
维护者通常 3 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 78/100
-
area/helm kind/bug priority/backlog triage/accepted
难度 2/5 1-3 小时 新手友好度 84/100
lexfrei/cloudflare-tunnel-gateway-controller#889 ·
维护者通常 1 天内回复
-
bug difficulty: beginner documentation good first issue help wanted localization
难度 1/5 1 小时以内 新手友好度 90/100
wavefnd/wave-platform#140 ·
-
compiler/runtime
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复