Allow per-stage model and reasoning selection

未关闭
#29 0 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
5/5
预计耗时
一周以上
新手友好度
48/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
typescript

调研方向

No files, tests, or entry points are named. Start by locating the existing global model and reasoning configuration and the plan, packet review, verification, and composition stage dispatch. Done means stages can override either setting through the proposed configuration while unnamed stages retain the global defaults, with coverage for fallback behavior.

由索引模型根据 Issue 内容生成。

描述

Problem

One model and one reasoning effort apply to every stage of a run. Stage 7 (packet review) dominates the token spend, so the strong model is paid for on work that does not need it.

Measured across runs of 0.5.6 on diffs of 9, 40 and 96 hunks (run.json / telemetry token counts):

stage share of total tokens
planning 1-2%
packet review 85-93%
verification 5-15%

Totals scale with the diff: ~0.9M tokens for 9 hunks, ~4.1M for 40, ~8M for 96. The Anthropic lane at opus/high reasoning uses about 1.7x the tokens of the openai-codex lane for the same diff.

Because the model is global, the only cost control available is to downgrade the packet review as well, which is the one stage where quality is the product.

Proposal

Allow the model and the reasoning effort to be selected per stage, falling back to the current global setting when a stage is not named:

[llm]
model = "..."            # default, unchanged

[llm.stages.plan]
model = "<cheaper model>"
reasoning = "low"

[llm.stages.verify]
reasoning = "medium"

Planning and composition look like the clear candidates for a cheaper model: they are structural work over text the pipeline already produced, and they are 1-2% and a few percent of the spend respectively. Verification is the interesting middle case - it is the main false-positive filter, so the value of a separate knob there is that it can be measured rather than assumed.

Why it matters

Per-stage selection turns "which model do I trust with this repository" into a per-stage question with a measurable answer, instead of one global decision that is paid for on every packet. It is also the prerequisite for anyone to publish a cost/quality curve for the tool.

Related but independent: #11 (grouping more related hunks) reduces the number of packet calls. The two levers compose - fewer calls, and the right model per call.

Happy to test a branch against a range of diff sizes and report tokens, wall time and finding deltas per stage.

主要语言
TypeScript
星标
8
派生
1
平均合并
5 分钟
30 天内合并 PR
2

环境准备

这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。

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。

0xPolygon/codegenie 的其他 Issue

查看 0xPolygon/codegenie 的全部 Issue

相似的 Issue

更多 TypeScript Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。