Review economics
yihong0618/bilingual_book_maker
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.7× the time to merge of the rest.
≥8%
Attributed
a floor
8
Attributed PRs
92
Other PRs
100
Read
Attributed — the latest 5
#547 fix(md): --use_context 并行分节按 worker 份额划分，单一 H1 / 无标题文档也能并行
0 reviews · 8h to merge
#544 fix(openai): 将目标语言写入结构化输出 schema
0 reviews · 4.1d to merge
#543 fix: verify JSON schema support in OpenAI probes instead of assuming it
0 reviews · 18h to merge
#538 feat(md): structure-aware Markdown book translation
0 reviews · 8h to merge
#542 fix(gemini): skip empty paragraphs in batch translation
0 reviews · 4.5d to merge
The rest — the latest 5
#548 test(epub): add parallel correctness baseline
0 reviews · 0h to merge
#537 Add bilingual PDF output layouts
0 reviews · 13.5d to merge
#536 fix: Gemini model lists are stale, causing StopIteration crash on default usage
0 reviews · 2h to merge
#528 Improvement: translate with sentence-by-sentence mode (for EPUB)
0 reviews · 25.2d to merge
#531 避免当使用 --provider 参数时 options.model 为 None 导致的 AttributeError
0 reviews · 0h to merge
How this was measured
8% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; 1 PR came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 174 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code, OpenAI Codex.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read yihong0618/bilingual_book_maker weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on yihong0618/bilingual_book_maker — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository