The adaptive-runs manual says a conversation cannot start a run
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 3/5
- 预计耗时
- 1-2 天
- 新手友好度
- 84/100
- Issue 类型
- 文档
- 描述清晰度
- 描述清楚
- 活跃度
- 活跃
- 技术栈
- go
- 领域
- cli, documentation, testing-qa
调研方向
Start with the quoted section at internal/manual/chat/adaptive-runs.md:265 and run codeaf manual "can a conversation start a run" to reproduce the denial. Read internal/session/task_run_belt.go:573 to confirm the conversation allowance path. Update the manual and change entry, then verify the e2e response and retrieval probe meet the listed acceptance checks.
由索引模型根据 Issue 内容生成。
描述
Found on santos/dev2 at 008363c98 (#1410). It reaches dev when #1410 merges.
What happened
adaptive-runs.md, in "What one costs and what happens when the money runs out", says:
The default tank is **$100.00** when nobody named a figure. **You cannot name one from a
conversation**, because a conversation cannot start a run at all — a run's cap is settled by
whatever started it.
On the default belt a conversation's /task does start a run, and that run is capped by the conversation's own allowance. So the reason the page gives is false, and a person asking whether a conversation can start a run is told no.
Replication
Deterministic (no model). Run codeaf manual "can a conversation start a run"; the retrieved adaptive-runs section gives the quoted denial. Inspect the /task run setup with the belt switch unset: it passes the conversation's allowance into the run specification.
Where
internal/manual/chat/adaptive-runs.md:265 carries the quoted claim at 008363c98. internal/session/task_run_belt.go:573 sets the run's limit for a conversation.
The fix
Limit the $100 statement to the headless door it describes, and say plainly that /task starts a conversation run under the conversation's allowance.
Acceptance
- e2e:
codeaf manual "can a conversation start a run"answers yes and names the relevant allowance. - Unit: a retrieval probe reaches that corrected section.
- Record the former denial in the change entry's
invalidates.
- 主要语言
- Go
- 星标
- 115
- 派生
- 14
- 平均合并
- 9 小时 38 分钟
- 30 天内合并 PR
- 749
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 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
-
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
-
area:chat bug good first issue sev:papercut
难度 2/5 1-3 小时 新手友好度 85/100
Agent-Field/CodeAF#1469 ·
维护者通常 1 天内回复
-
area:chat bug sev:papercut
难度 2/5 1-3 小时 新手友好度 88/100
Agent-Field/CodeAF#1468 ·
维护者通常 1 天内回复
查看 Agent-Field/CodeAF 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 84/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 92/100
GoogleCloudPlatform/k8s-config-connector#13462 ·
维护者通常 1 天内回复
-
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
-
难度 2/5 1-3 小时 新手友好度 84/100
microsoft/TypeScript#64453 ·
维护者通常 1 天内回复
-
OpenAI-compatible endpoint: response ids have only 999 possible values (chatcmpl-rand.Intn(999))未关闭
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