Jesse ZhangandClaude Opus 4.8
30983f0e7d
- AGENTS.md: public contributor/agent guide (two-file rule, model-centric ids, one-entry-per-harness, bilingual notes, screenshot proof) - PR template: require a generation proof screenshot; drop the manual update-registry step; add id-naming and no-README-edit checks - CI: PRs only run validate-data; pushes to main auto-regenerate and commit the README registry (contents:write on that job, [skip ci], no loop) - README/update-registry: reflect auto-synced registry; fix stale 'two cases' -> three (mythos-craft, pelican-cycling, skeleton-watch); link AGENTS.md Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2.3 KiB
2.3 KiB
产出说明 / Run info
- 模型 / Model:
- 厂商 / Vendor:
- 运行环境 / Harness（如 ChatGPT Web、Claude Code、Codex CLI、AntiGravity…，这是工具不是模型）:
- 思考配额 / Thinking effort（如 Max、High、xhigh、Extended Pro、Thinking…）:
- 是否一次生成 / One-shot?（是/否；若有修复请在 note 里说明 / if fixed, document it in the note）
生成凭证截图 / Proof screenshot (required)
请贴一张生成过程截图：你的 harness / IDE 中能看到模型名 + 思考配额正在产出本产物， 作为「确实用了这套 harness + 模型 + effort」的凭证。 Please attach a screenshot of the generation showing the model name + effort in your harness/IDE.
自查 / Checklist
- 只改了两类文件：
outputs/<artifactDir>/<case-id>.<ext>+models/<model-id>.json/ only the artifact + its JSON - 没有手改
README.md/README.en.md（注册表合并后由 CI 自动同步）/ did not hand-edit the README registry (auto-synced after merge) - 模型 id 用短横线、以模型命名（非 harness），如
deepseek-v4-flash-reasonix/ dash-case id named after the model, not the harness harness与effort如实填写（站点据此生成 metadata 与品牌 icon）/harnessandeffortare accurate- 每条 run 的
note双语（zh + en，zh 先，无 emoji）填了来历 / bilingualnote, zh first, no emojis - 同一模型换 Harness 或思考配额是新建一个 JSON 条目 / a different harness or effort = a NEW json entry
contributor是我的 GitHub 用户名 /contributoris my GitHub username- 已贴生成凭证截图 / attached the proof screenshot above
- 本地
bun scripts/validate-data.ts通过 /bun scripts/validate-data.tspasses locally