V1.10.0-alpha · 4 层自检 + 精髓库三重防线 + 字体粗细#31
Merged
Conversation
主宪章 §33 自检铁律(L1+L2+L3+L4):
- L1 frontmatter lint(无 LLM):runtime/healthcheck/agent_smoke.py + pre-push hook
- L2 CI mock e2e(stub LLM,0 成本):selftest-mock job 每 push
- L3 真 LLM(~$4/release):tagent doctor --agents --probe + tagent selftest --e2e
- L4 周自检(~$16/月):.github/workflows/selftest-weekly.yml 周一 03:00 UTC main 真 LLM
- pre-tag hook(scripts/git-pre-tag.sh):卡 git tag v1.x,7 天内必有 L3 log
CLI 扩:
- tagent doctor --agents [--probe]:L1 + 可选 L3 LLM ping 16 agent
- tagent selftest --e2e [--strict] [--pass-threshold]:整体 e2e
- LLMClient.complete():plain text completion(probe 用)
主宪章 §34 精髓库三重防线:
- .gitignore 加 _精髓库/ + **/_精髓库/
- pre-commit hook forbid-essence-library(diff --cached 含路径即 reject)
- CI file-count job 双校验
主宪章 §35 字体粗细统一:
- docs/STYLE.md(10 条样式约定:标题深度 ≤3 / **bold** 仅 3 场景 / 中英空格 / 表格/代码块/emoji 边界)
- markdownlint MD001+MD036 规则文档化,V1.11 一次性批改现存违规
补 INDEX(招 4):docs/INDEX.md + examples/INDEX.md + profiles/INDEX.md + scripts/INDEX.md
新模块:runtime/healthcheck/{agent_smoke,llm_probe,__init__,INDEX}.py
新 fixture:examples/_smoke_prd.md(触发完整 16 agent DAG)
烟测:
- L1 OK agents=16/16 skills=32/≥25
- L2 stub e2e ✓ PASS 7/8 ok (88%, tolerant ≥80%)
- pre-commit 全过
版本 V1.9.0-alpha → V1.10.0-alpha
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
docs/STYLE.md(10 条样式约定)tagent doctor --agents [--probe]+tagent selftest --e2e [--strict]complete_json)Why
用户提出每个 agent 必须通过最简自检 + 整体项目落地;字体粗细统一;精髓库防误入。用户曾要求 CI 真跑(A+B+C),被 push back(API key 暴露 + $600/月 + March of Nines),改让步方案 L1+L2+L3+L4 = $24/月。
Test plan
OK agents=16/16 skills=32/≥25(无 LLM)✓ PASS 7/8 ok (88%, tolerant ≥80%)forbid-essence-library)Known issues(V1.11 修)