Review economics
labring/FastGPT
Read from the 100 most recently merged pull requests ·
Pull requests with attributed agent authorship took only 0.8× the reviews submitted of the rest.
≥2%
Attributed
a floor
4
Attributed PRs
96
Other PRs
100
Read
Attributed — the latest 4
#7436 fix(dataset): export index and metadata columns in exportAll
1 reviews · 0h to merge
#7026 revert: rollback openapi app docs to previous version
2 reviews · 0h to merge
#7348 fix: add .js extension to dayjs plugin imports for ESM compatibility
1 reviews · 19h to merge
#7327 fix(outlink/wechat): 空响应时续链延迟 10s，避免热循环刷屏
0 reviews · 1h to merge
The rest — the latest 5
#7452 Account verification
2 reviews · 23h to merge
#7435 fix(sandbox): handle OpenSandbox PVC lifecycle races and UID preconditions
1 reviews · 2.1d to merge
#7458 fix(account-verify): ui
3 reviews · 1h to merge
#7459 fix(agent): decouple file upload settings from model capabilities
1 reviews · 0h to merge
#7448 fix(mcp): avoid duplicating headers in SSE fallback
0 reviews · 23h to merge
How this was measured
2% 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; 22 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 3236 merged PRs — the rest have not been analyzed yet.
Detected: OpenAI Codex, Claude Code, Cursor agent, GitHub Copilot coding agent.
“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 labring/FastGPT 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 labring/FastGPT — 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