Repository navigation
Deepen JiuwenSwarm knowledge and improve init/retrieval workflow - #290
Merged
Merged
Conversation
tzhouam
changed the title
tzhouam
changed the title
tzhouam
marked this pull request as ready for review
October 2, 2026 16:39
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
tzhouam
added a commit
that referenced
this pull request
Oct 2, 2026
…R review results (#294) JiuwenSwarm’s knowledge recognition and file coverage do not measure PR-review accuracy. Add a Chinese comparison of original author documents and the merged PR #290 knowledge base, plus a reproducible isolated GLM‑5.3 A/B evaluation. The study freezes source/document hashes and actual PR merge bases, runs 12 PRs × two contexts × three repeats through subscribed Zcode with 13 workers, and uses separate Codex source auditing and anonymous scoring. Closed read-only tools enforce source boundaries and the cumulative two-page/6,000-character document budget. Complete native traces and a 3,612-file hash index remain outside Git; the checked-in JSON is about 70 KB. Results: 72 terminal trials, 55 valid reviews, 12 successful independent scoring calls. On six comparable primary PRs, conditional precision is 69.12% for author docs versus 76.76% for the knowledge base. Primary completion falls from 21/24 to 15/24; paired native time averages 426.33 versus 416.77 seconds. Rate limits and protocol failures prevent a causal acceleration or overall-benefit claim. Recall is limited to two primary PRs with independently confirmed issues; four older forks are exploratory. Validation: 3,033 local tests passed, 17 skipped; 135 evaluation fixtures, knowledge/wiki validation, documentation links/citations/SPEC, CLI/doctor and installed-wheel smoke checks. Independent code/report audits passed. Code CI passed before report publication; final delivery CI is checked on this PR. Report: `eval/knowledge-depth/jiuwenswarm-original-docs-comparison-cn-20261003.md`. Reproduction: `eval/jiuwenswarm_ab_README.md`.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
JiuwenSwarm 的知识原先偏向规则，功能深度只有 173/553 项。本 PR 改进 init/deepen、检索和认可记录审计，并将知识补到 552/553（99.82%）：207 项 strict、345 项轻量认可。固定分母为 79 功能 × 7 维度，上游固定在
f0a69728c96b5961d993449f1a901cbd2f4dac5b。本轮针对上一检查点的 63 项缺口补齐 62 项。六个维度为 79/79，设计取舍为 78/79；全部维度超过 90%，第一方生产文件结构覆盖维持 2043/2199（92.91%）。原 490 项生效区块及认可绑定保持不变，原 172 项仍生效；退役 artifacts/flow 原文和证明继续保存在历史归档。
尚未全部补齐：
im-feishu/tradeoffs仍未知。 其四轮候选仍声称每次文本更新至少等待完整 debounce 延时，源码中已有 flush 任务可以使用剩余窗口，无法支持该保证。保留最后拒绝原因及所有调用，未重置计数或生成缺失证明。验证知识也不代表上游测试已经执行或通过。中文对比及 PR 评审影响报告
验证：完整本地测试 2898 通过、17 跳过；知识校验器回归 69 通过；源码与实际原生审批绑定 552 项、237 项检索验收、全部 62 个新增区块独立内容复查通过；文档链接、引用、93 项 SPEC 及知识校验均通过。最终提交
58279d334cd827adb631891a760bb14efe376420的 push 与 PR 两组完整 CI 均通过；认可门槛和独立复审已通过，唯一未知项如上披露。