docs(project): add master branch 4-week rolling commit analysis report

[Copilot]

Adds a date-stamped commit analysis report for ralf003/zeroclaw master, built from real GitHub API data (1,400 unique commits across 15 pages). Also ships a reusable helper script for reproducible re-runs.

Summary

• Base branch target: master
• Problem: No structured analysis of recent commit activity existed in the repo docs.
• Why it matters: Provides a reproducible, on-record snapshot of contributor activity trends and maintainer load for the project's active development period.
• What changed: Added docs/commit-analysis-2026-04-08.md (full report) and scripts/commit_weekly_stats.py (reusable stats script).
• What did not change: No runtime Rust code, config schema, CI workflows, or existing docs modified.

Label Snapshot (required)

• Risk label: risk: low
• Size label: size: S
• Scope labels: docs, scripts
• Module labels: N/A
• Contributor tier label: (auto-managed)
• If any auto-label is incorrect, note requested correction: N/A

Change Metadata

• Change type: docs
• Primary scope: docs

Linked Issue

• Closes #
• Related #
• Depends on #
• Supersedes #

Supersede Attribution (required when Supersedes # is used)

N/A — does not supersede any prior PR.

• Superseded PRs + authors: N/A
• Integrated scope by source PR: N/A
• Co-authored-by trailers added: No
• If No, explain why: No prior PR superseded.
• Trailer format check: N/A

Validation Evidence (required)

# Rust checks skipped — docs/script only change, no Rust source modified
npx markdownlint-cli2 docs/commit-analysis-2026-04-08.md
# → 0 errors

• Evidence provided: markdownlint clean pass; CodeQL Python scan: 0 alerts; automated code review: no comments.
• Intentionally skipped: cargo fmt/clippy/test — zero Rust files changed.

Security Impact (required)

• New permissions/capabilities? No
• New external network calls? No (script requires explicit invocation; not imported anywhere)
• Secrets/tokens handling changed? No
• File system access scope changed? No

Privacy and Data Hygiene (required)

• Data-hygiene status: pass
• Redaction/anonymization notes: Report uses GitHub public login names (chumyin, theonlyhennygod, etc.) — all are publicly visible contributor identities already present in the repository commit history. No private emails, tokens, or PII committed.
• Neutral wording confirmation: Analysis language is system/project-scoped; no identity-specific personal language.

Compatibility / Migration

• Backward compatible? Yes
• Config/env changes? No
• Migration needed? No

i18n Follow-Through (required when docs or user-facing wording changes)

• i18n follow-through triggered? No
• Rationale: This is a standalone date-stamped analysis report (docs/commit-analysis-2026-04-08.md), not a navigation entry point, runtime-contract reference, or hub README. It does not alter docs/SUMMARY.md, README*, or any localized runtime-contract doc. No locale parity update is required per the docs governance contract.

Human Verification (required)

• Verified scenarios: API data completeness (15 pages, 1,400 deduplicated commits); date range coverage (2026-02-13..2026-03-08); weekly bucket assignment; bot/merge exclusion logic; Top 10 author counts cross-checked against raw page data.
• Edge cases checked: Strict 4-week window from report date (2026-03-12..2026-04-08) correctly shows 0 commits and is documented with explanation; Chummy/chumyin identity deduplication noted in methodology.
• What was not verified: Script network execution against a live token (logic verified via equivalent inline Python during analysis).

Side Effects / Blast Radius (required)

• Affected subsystems/workflows: None — additive docs/scripts only.
• Potential unintended effects: None.
• Guardrails/monitoring for early detection: N/A.

Agent Collaboration Notes (recommended)

• Agent tools used: GitHub MCP list_commits (15 pages × 100 commits), Python analysis inline.
• Workflow summary: Fetched full commit history → deduped by SHA → computed rolling 7-day windows → generated per-week totals, bot counts, author counts, Top 10 tables → wrote report and helper script.
• Verification focus: Data completeness, date boundary correctness, bot detection accuracy.
• Confirmation: naming + architecture boundaries followed per AGENTS.md + CONTRIBUTING.md: Yes.

Rollback Plan (required)

• Fast rollback: git revert <commit> — pure file addition, zero side effects.
• Feature flags: None.
• Observable failure symptoms: N/A (docs only).

Risks and Mitigations

• None.

Original prompt

在 ralf003/zeroclaw 仓库新增一份文档，内容为：对 master 分支最近 4 周（28 天，以当前日期为基准，向前滚动 7 天一周）提交(commit)情况的分析报告，包括以下内容：

1. 统计方法说明：说明如何划分周区间、如何收集数据（API、本地 git log 均可）、排除哪些无关 commit（如 bot/merge），如何判定作者身份。
2. 提交统计表格：每周（以 7 天为 1 周，最近 4 周）的提交总数、当周有提交的作者数、当周 commit 数最多的前 10 位作者及其当周 commit 数，表格以 Markdown 格式展现，时间区间用 YYYY-MM-DD..YYYY-MM-DD。
3. 简要分析总结：例如活跃度趋势、top 作者贡献特征、是否有明显主力作者等。
4. 附：如有辅助分析脚本，给出用法示例或附录链接。

说明：你可以结合脚本与 API 结果，生成近 4 周的真实数据；如有数据获取受限，可以模拟一份合理表格，但要在文档中注明。

The following is the prior conversation context from the user's chat exploration (may be truncated):

User: 请分析zeroclaw分支 近4周的commit提交情况，形成一个表格，每周的commit提交数，有贡献的作者数目，前10名作者当周提交的commit数

Assistant: 目前**无法按“近 4 周”给出准确的周度统计表：GitHub 的 commits API 分页最多每页 100 条，而你这个仓库 master 分支最近提交非常密集，我在仅抓取前 200 条（page=1~2）**的情况下，还没拿到每个 commit 的提交时间 commit.author.date（工具返回内容里只有 html_url/author 等摘要字段），因此无法可靠地把提交归档到每周并统计“每周提交数 / 作者数 / Top10 作者”。

不过我已经确认了两点关键信息：

1. 你提到的 zeroclaw 分支 不存在；仓库目前可见分支返回的是 master。
2. master 分支提交量很大，需要继续翻页并且需要拿到每条 commit 的时间字段，才能做“近 4 周”周报。

我需要你确认 1 个问题（选一个口径）

你说的“每周”想按哪种周口径统计？

• A) 自然周（周一~周日，按你所在时区；你提供的当前日期是 2026-04-08，周三）
• B) 滚动 7 天为一周（近 28 天切成 4 段：0-6 / 7-13 / 14-20 / 21-27 天）

回复我 A 或 B 即可。

同时给你一个“继续获取更多提交”的入口

由于 API 结果分页限制，想覆盖近 4 周，需要继续拉取更多页。你也可以直接在 GitHub UI 里查看更早的提交列表（从我已拉取的接口参数构造）：

https://github.com/ralf003/zeroclaw/commits/master?per_page=100

只要你确认了周口径（A/B），我下一步会继续把 master 分支提交分页拉全到覆盖 2026-03-12 ~ 2026-04-08（近 28 天），然后输出你要的表格（每周：commit 数、作者数、Top10 作者及其当周 commit 数）。

User: 1、B) 滚动 7 天为一周 2、你可以自己形成一些skill来完成我的任务，我刚刚的任务不是特别复杂“请分析zeroclaw分支 近4周的commit提交情况，形成一个表格，每周的commit提交数，有贡献的作者数目，前10名作者当周提交的commit数”

Assistant: 我这边已经发起了相应的工具调用来继续完成“按滚动 7 天统计近 4 周 master 分支 commits 并输出表格”的分析/实现流程，现在需要等待你在弹窗里确认/允许该工具调用后，我才能继续执行并给出最终的周度统计表格结果。

User: @copilot Accepted Confirmation: Confirm agent session

Assistant: 我已经开始着手处理：会在 ralf003/zeroclaw 仓库里补充一个可复用的统计脚本（按你选的 B：滚动 7 天为一周），自动拉取/遍历最近 28 天（4×7 天）的提交记录，并输出你要的 每周 commit 数、作者数、当周 Top10 作者 commit 数 的 Markdown 表格。

你可以在下面这个任务链接里跟踪进度（包含实现与最终表格产出方式）：

data:
    - title: '[WIP] Add reusable commit statistics script for the last 28 days'
      repository: ralf003/zeroclaw
      url: https://github.com/copilot/tasks/pull/PR_kwDORhj8Pc7Qu3OQ?session_id=0e4bc609-b2cf-40b2-9fc4-8c9dda3271da
      state: queued

User: 请输出文档：“分析zeroclaw分支 近4周的commit提交情况，形成一个表格，每周的commit提交数，有贡献的作者数目，前10名作者当周提交的commit数”

Assistant: 我正在为你补充一份详细文档，涵盖对 zeroclaw（即 master 分支）近 4 周（28 天，按滚动 7 天为一周）commit 情况的统计表格，并附分析说明与用法示例。
你可稍后在仓库直接获取此文档，或者在进度任务链接中跟踪报告产出与内容完善。如果你需要提前查看模板样例，请告知。

This pull request was created from Copilot chat.