-
编码期测试的 DB 时序从「DROP+CREATE 空库 → Flyway 从零重建 → seed」 改为「mysqldump 复制源库→一次性副本 → Flyway 只 apply 本轮新迁移 → 跑测试 → 绿后晋升新迁移到源库 → 无论红绿删副本」。 - 新模板 scripts/drop-test-db.mjs(删副本,硬拒删源库)、 scripts/promote-to-source.mjs(移植 flyway 历史行+重放迁移到源库; 跨 lane 串行由编排层 testGate 起栈互斥保证,文件锁兜底同树重跑) - setup-test-db:DROP 空库 → 复制源库到副本;test.mjs:try/finally 删副本 + 绿后晋升 + 串行缺省显式导出副本名 <schema>__test - 命名约定(5 脚本共享):COPY = env > marker > <source>__test, 每脚本 COPY===SOURCE 即拒绝;application*.yml 占位缺省改为副本名 - 新 lib/bootstrap-source-flyway.mjs:db-init 建源库+apply V1+写 checksum 与 Flyway 一致的历史行(Plan 期无 app 可起,手算 CRC32); db-init B 段三步换一次 bootstrap 调用 - coding.mjs 各闸时序对齐;globalTeardown 只 kill 不删副本(teardown 删副本会让其后的 promote 查不到副本历史而静默跳过晋升);行为门/ seed 契约允许清单补 drop-test-db;前端 testGate 补收尾删副本 - 模板测试重写 + 新增 drop/promote/bootstrap 测试(133 全绿,全离线) 已知残留:bootstrap 手算 Flyway checksum 未真机验证(若不一致首次 起后端报 checksum mismatch,改 flywayChecksum 一处即可);演示种子 固定主键区间 1000–9999 与源库真实自增数据增长存在长期碰撞风险。
-
前端段开头一次性 Playwright headless 渲染 prototype/**/*.html 本身: 截图归档为可视化基线 + 跑原型自带交互点击冒烟 + 捕获 JS/console 错误。 与行为门正交(Preview 测静态原型、Behavior 测实现)。硬门:渲染失败 / 脚本未捕获异常(jsErrors)→仲裁(只许 retry/halt),halt 即停下等人工回 plan/add-req 修原型后重跑(coding 不改原型源码);console.error advisory; 环境未就绪(Playwright/浏览器缺失)才 retry→仲裁降级;无 prototype/ 跳过。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
让前端不依赖后端的工作与后端波次并发,所有真后端测试延后。5 类改动: - tddPrompt/verifyPrompt 加 feStage:jsdom 模式只处理 jsdom 任务、只跑 vitest、 硬禁 e2e 命令;e2e 模式只补延后的 e2e 任务。新增 fe-code-done/<FE> 中间 tag。 - featureLoop 加 feStage 分流:jsdom 跳 review 打 fe-code-done;e2e/all 走 review→req-done。新增 runFrontendPhase1(前端 worktree,不调 phase()、不 merge/milestone、永不 throw)。 - 主循环:frontendOverlap 开时把 frontend-phase 从波次图剔除、起 phase1 与后端 波次并发;屏障后 reconcile(merge default→frontend-phase)+ 标准 runModule(feStage=e2e) 主根全栈跑 phase2。后端未全 done / phase1 halt → phase2 延后、产物保留 resume,绝不新增 halt 点。 - coding-start SKILL.md + README:开关说明,缺省不传(同 features 闸纪律)。 重叠期前端无栈/无固定端口/无 DB,补 8/9/10 不变量与端口/lane 安全全保住。 缺省关时 feStage 恒 all、新分支不激活、新编排整段跳过,现行行为零变化。 语法门通过。设计真值见 docs/superpowers/plans/2026-06-15-frontend-overlap-jsdom.md。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
下文"派 Agent 子会话跑测试 / 主会话绝不直接跑测试"护栏的真实意图 = 测试执行与主推理流隔离、只回收结构化结果。本运行环境若无 Agent/Task 派发 工具,则以 Bash run_in_background 隔离后台子进程作为该子会话的物理实现 (输出重定向到 .tmp/ 日志,只读回 {command,exit_code,passed/failed} 摘要), 已满足护栏意图,故绝不因"缺派发工具"halt(非硬事实缺失、retry 不改变工具面)。 仍禁止在主推理流内联同步跑测试并把全文 stdout 读进上下文。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> -
rule 1 翻转:docs/02 § 二 列出顺序只是排版次序、不构成依赖;order 边 仅在 docs/06(或 REQ 卡)显式声明"X 必先于 Y"时才加。明确堵死本次实测的 误读——对已完成模块的 fk/api 证据绝不构成两个待跑模块间的 order 理由 (scheduler 曾拿 PUR→BAC[fk] 当借口给 PUR←SAL 加链式 order 边)。两个待跑 模块间无 fk/api/seed/共享表/docs 显式约束 → 不加边、落同一波并行(默认而非例外)。 保守偏置同步收窄:"不确定"仅指怀疑真实依赖却证据不全,绝不把"docs/02 里 靠后"当不确定理由——否则该"最高优先级"段会盖过 rule 1。 实测背景(xlyClaude13):待跑 PUR/SAL/USR 表归属不相交、彼此无真实依赖, 旧提示却链式 order 串成 USR→SAL→PUR,每波仅 1 ready,maxWidth=3 形同虚设。 修复后三者应进同一波 3 路并行。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
- 调度:scheduler 子代理只输出依赖边+证据(宁串勿并),JS 做完整性校验 + Kahn 拓扑波次;frontend-phase 由 JS 硬规则依赖全部后端 - 隔离:lane worktree(独立 index)+ lane 测试库(ERP_TEST_DB_SCHEMA)+ migration 版本段(maxV 全局并集)+ 起栈互斥锁(Seed/testGate) - 执行:波次 parallel + milestone/RESUME 主根互斥 + halt 波次边界收敛 + 图状 pending(blockedBy);runModule 永不 throw - feature 级:spec 预生成(写盘不 commit、末端统一提交)+ 后端 REQ 批并行(准入闸=文件集两两不相交∧不改 schema,冲突即弃分支串行重跑) - 穿线:模块作用域 prompt/runner 经 ctx(c) 取根,ROOT 仅主根专属操作;decisions 记账 per-module sink 取代全局水位线 - 降级原则:任何并行机制失败一律 fail-open 回串行,零新增 halt 点;parallel 缺省/modules:false 与原行为一行不差
-
- bestEffortAction(prompt, {label, phase, okMsg, failTag, errTag}):收敛 recordResume / ensureLedgerBaseline 逐行同构的 try/catch 包裹(失败/异常只 log 绝不阻断主流程; ≠ runAction:不经 adjudicate、绝不 halt)。日志文案与重构前逐字一致(errTag 区分 失败/异常两条前缀),返回布尔供水位线判断。 - decisionDigestMd helper 消除决策摘要模板的字节级双份拷贝;flushedCount 水位线 (仅 per-module flush 成功才推进)使 loop-end 条目只补「未被逐模块条目覆盖的增量」 ——N 模块全绿不再每条决策在 RESUME.md 写两遍;flush 失败时 loop-end 兜底补记保留。 - add-req 步骤 0/1 合并为单次 scan(scan 输出本就同时含 ledgerExists 与 new/changed/removed,重复扫描纯冗余);删步骤 6 无操作性说明尾句。 -
- auto-continue.sh:sentinel 检测只认 transcript 的 assistant 行(修自匹配 bug—— block reason 自带 [ERP-HALT] 字面量、下次 Stop 命中自己,钩子实际只能续跑一次); 窗口 60→200 行,兜住「横幅在前、诊断在后」的回合;删 4000B 字节增长启发式 (与 PostToolUse 清零重复且方向性错误——纯文字空转一轮也超 4000B,上限永远到不了); reason 文案去掉对已删 skill 链的指挥与 [ERP-HALT] 字面量。 - [ERP-HALT] 补全到全部刻意停下点(合计 12 处打印点):add-req 4 处(前置拦截/ 基线停下/空增量/完成横幅)、coding-start 步骤 1/2、plan 阶段 5 处(plan-start 终结闸 / downstream-gen A5 / db-design-gen 审阅 / scope-lock 骨架 / project-init 安装失败);coding-start :130 说明文字去字面量防误触发。 - StopFailure:官方语义为「输出与退出码被忽略、无 decision 控制」(无法在钩子层 自动续跑;核实于 2026-06-11 code.claude.com/docs/en/hooks.md)。接线 log-stop-failure.sh:记录中断时间与 error_type 到 $TMPDIR/erp-stopfailure.log, 供人工/外部 watcher 据此续跑。 - coding.mjs preflight:起跑线按 docs/04 § 零探测 node/JDK/DB 客户端/测试入口, 工具链缺失带安装/配置命令的诊断 halt——不再拖到 test-gate 才爆、白跑几十分钟编码。
-
任何 halt 的原因必须直达终端,而不是埋在 Workflow 返回值/RESUME.md/TypeError 里: - haltError():HALT 抛出前先 log(/workflows 进度叙述行可见)。启动期 4 处 (invalid-projectRoot / assertSafeId / router-violation×2)换用;模块循环 catch 补 「⛔ HALT — 模块 <id>:<原因>」;loop-end 补最终状态 log(halt 模块/原因/待跑清单)。 - agent() null 防御:断网/机器休眠时子代理返回 null,不再以 TypeError 形态 halt—— adjudicate null→确定性默认 retry;runStage/runAction null→经仲裁重试(上限 ADJUDICATE_MAX);其余 32 处直调点换 agentR()(null→带 label 的诊断 halt); flipDocs08Checkbox 保持裸 agent + null 容忍,守住其「绝不 halt」契约。 - coding-start 步骤 6:Workflow 通知返回后第一段输出必须是 halt/完成横幅 (halt 原因全文不许截断或转述 + 已完成/pending 清单 + [ERP-HALT] 终止标记)。
-
P1#2 — validate-ddl 支持增量 migration: - parseDDL 新增第三遍 mergeAlterStatements:ALTER TABLE ADD COLUMN / ADD [UNIQUE] INDEX|KEY / ADD PRIMARY KEY 并入对应表(仅追加式, MODIFY/CHANGE/DROP/RENAME 不处理;并集与文件顺序无关)。 - CLI 接受多个 DDL 文件:node validate-ddl docs/03 sql/migrations/V*.sql, CREATE + 各 V_n 的 ALTER ADD 并集 ↔ docs/03 累积 SSoT 做 4 维比对。 - add-req SKILL 新增「增量 DDL 校验(fail-closed)」闸门,替换原「多 migration 不适用」说明。 - 7 个新测试(含 DEFAULT 字面量里的 ALTER 文本不被误吃);52/52 通过。 P1#3 — coding 首跑自动建需求台账基线: - coding-start 透传 pluginRoot;coding.mjs ensureLedgerBaseline() 首跑若 .req-ledger.json 缺失则 commit 基线(幂等、best-effort、缺 pluginRoot 静默跳过), 使日后 /add-req 能识别增量、免空跑。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
P0 — add-req 从不 git-commit 自己的产物,导致工作树脏、coding-start 起 coding.mjs 时撞「工作树必须干净」前置(HALT 或被误并进功能分支): - 步骤 0 基线:写 .req-ledger.json 后 git add+commit - 步骤 6:把本次全部增量产物(docs/01/02/03/05/08 + sql/migrations/V_n + .req-ledger.json) 在当前(默认)分支统一 git commit,并用 status --porcelain 复核工作树干净 P1#1 — RESUME.md 原先只在主循环末尾写,硬中断(进程被杀)到不了写入点 → 本次运行零 handoff: - 每个模块 runMilestone 落定后即 best-effort 追加一条「✅ 模块完成」(含本模块自主决策摘要), 按 decStart 水位线切出本模块决策;使硬中断也能复盘已完成到哪、各模块做过哪些假设 - loop-end 的 halt / 全完成汇总条目保留(halt 原因是 per-milestone 无法捕获的) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
中断/halt 后重跑能复盘上次状态,不只恢复进度。编码阶段保持全自动静默不变。 - coding.mjs:新增 resumeJournalPromptM + recordResume(best-effort,写失败绝不阻断/ 掩盖主流程)。主循环结束(halt 或全完成)时向 docs/superpowers/RESUME.md 追加一条: halt 原因 + 本次自主默认假设(decisions 摘要) + 待跑模块 + 下一步 - coding-start:新增步骤 3.5,重跑时读 RESUME.md 末尾条目向用户复盘上次 halt/完成状态 - 进度真值仍是 git tag(milestone/req-done)+ committed 工件——硬中断后 Router 据此续跑; RESUME.md 补的是跨会话会丢失的「为何停/做过哪些假设」定向信息(GSD continue-here.md 类比) - 硬中断(进程被杀)到不了写入点:那种情况无 halt 原因可记,且 tag+工件已够续跑,无信息损失 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
标准列:每表 7 列(新增 iOrder/sMemo;sId/sBrandsId/sSubsidiaryId 改 varchar(50) NOT NULL),从表额外 +sParentId 共 8 列。docs-03 模板 + A3 渲染规则 + A4 DDL 默认值翻译(CURRENT_TIMESTAMP / DEFAULT '1111111111' / iOrder app-assigned)。 去外键:A3 不再推导 FK 约束(改语义引用关系,无 ON DELETE/ON UPDATE,应用层维护一致性);A4 DDL 不生成 ALTER ADD FOREIGN KEY;validate-ddl 移除外键维度 5→4 维(表/列/类型/索引),单测 45 pass/0 fail;coding.mjs 种子/sentinel「FK 有序」→「按语义引用有序」(保留先被引用方后引用方/不可悬空)。 注:db-design-gen 的 docs/06 读取清单/步骤B 两条 bullet 与本区域改动同处一个 diff hunk,随本提交落入(实属 docs/06 feature 的 A3 接入)。
-
- A2 skeleton-gen 末尾新增 step F:创建空白 docs/06-实现策略.md,QA 闸循环至用户确认填完才进 A3(原 F 进入 A3 顺延为 G) - A3 db-design-gen 读取清单 + 步骤B + 参考接入 docs/06 - A5 downstream-gen docs/02 构建顺序 / docs/05 端点 + 参考接入 docs/06 - coding.mjs deriveSpecPrompt(前端+后端)把 docs/06 作为 spec 收集上下文
-
- 子模块代码:大写短码(USR/ROLE) → 大驼峰英文名、不限长度(UserInfo/Role) - 功能名:英文大写 [A-Z0-9_]/下划线(PWD_RESET) → 大驼峰 [A-Za-z0-9]/直接拼接(PwdReset) - 模块代码不变(大写短码 USR);结构仍 <模块代码>-<子模块代码>-<功能名> 恒 3 段 - 规范示例统一 USR-USR-LOGIN → USR-UserInfo-Login;docs-01 五列示例行同步 - 同步 7 文件:README/coding.mjs/scope-lock/docs-01/CLAUDE/plan-start/docs-04
-
- index 模板:三列 → 五列(模块代码/模块名称/子模块代码/子模块名称/核心功能点),一行一个子模块 - 卡片文件名:REQ-XXX-NNN.md → <req_id>.md,req_id 恒 3 段(如 USR-USR-LOGIN),功能名由 CC 据核心功能点推断(英文大写、[A-Z0-9_]、多词下划线、子模块内唯一),保持文件名==req_id 不变量 - scope-lock:五列解析 + 按模块代码聚合建目录 + req_id 生成规则;E.1 glob 改 */*.md 跳过 _module.md - db-design-gen/downstream-gen:REQ-*.md glob 同步;docs/05 结构检查锚点 ### REQ- → 三级标题端点段 - CLAUDE/docs-04 模板 commit 后缀、plan-start 示例、coding.mjs 提示词文案(238/1322)、README 同步 - docs-08 checkbox 文本与 scope-lock Edit 锚点逐字节同步;流程/闸门/tag 机制零改动
-
行为门 v3(docs/design/2026-06-05-frontend-behavior-stage-gate.md): - 行为验收从 per-FE review approve 子门迁回阶段末尾一次(phase Behavior, featureLoop 后、testGate 前),保留 fix 循环(BEHAVIOR_STAGE_MAX=3 轮, fix 后全量前端单测复验再重跑门) - req-done/<FE> 语义降为「仅静态 review 过」;行为绿改由 reportPrompt 校验 阶段级证据(module-reports/frontend-phase-behavior-r*-a*.md 最后一份非 RED) - build-failed 取消「兄弟未实现」短路(阶段末尾全 FE 已实现);断言作用域 = 全部 FE spec「行为验收作用域」小节并集,缺小节记 scope-missing 阻断 green - 新增样式层 styleIssues(颜色 token 比对 + layout sanity 共 6 kind), 降维并入 behaviorHard 与交互硬问题同口径 fix;环境仲裁透传 riders 计数 前端测试目录隔离(对齐后端 src/main↔src/test 物理分离): - 锁定约定:单测 frontend/tests/** 镜像 src/(smoke 归 tests/__smoke__/ 且 以 .test.* 结尾),e2e 在 frontend/e2e/,frontend/src/ 禁任何测试产物; vitest include 统一限定 tests/**/*.test.* - 五层防线:docs-04 模板 §2.1 锁定约定 / planPrompt+tddPrompt 硬护栏 / fe-skeleton 单测基线 / code-reviewer 新增第 8 维「测试文件隔离」 - legacy 守卫:frontend/src/ 内已存在 colocated 测试时绝不收窄 include (防旧单测静默停跑),骨架幂等检测同步豁免,留人工迁移 经两轮多代理对抗审计(34 agents),确认项均已修复。
-
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
- coding.mjs: per-module Seed stage after backend testGate (generate sql/seed/NN__<module>.sql, cold-stack verify with PK-range COUNT reconciliation); behavior gate step2 -> 5-step ordering (demo seed before sentinel, sentinel fixed >=100000 range); fe-skeleton adds Playwright globalSetup e2e baseline (seed + admin storageState); fe tdd e2e assertion constraints - skeleton-gen: new scripts-seed-demo-data-template.mjs (mysql CLI, _demo_seed_history idempotency ledger, offline-validatable, atomic apply+ledger batch) + lib offline tests (93/93 green) - db-init: B.3 re-clean DB after DDL smoke apply (hand schema back to Flyway, avoid missing-history-table error); fix step-D typo - docs-04/CLAUDE templates: data baseline & demo-seed conventions (PK ranges 1-999 init / 1000-9999 seed / >=100000 sentinel)
-
…rd, coverage reconciliation, testdb halt) Post-implementation multi-agent review (6 dims + per-finding adversarial verify) found the control-flow sound and the goal mostly-achieved; this lands the three deterministic, low-risk fixes among the confirmed findings. - build-failed short-circuit (must-fix): behaviorSubGate now validates the LLM's classification before green-by-skip — requires non-empty rootCausePath AND no interaction/sentinel hard issues riding along; a "dirty" build-failed goes through adjudicate(allowContinue:false) retry/halt instead of silently approving. The skeleton (lazy router + FeStub) makes legit sibling-unimpl build breaks rare, so a build-failed is more likely a real in-FE shared-code regression — the boundary comment §107-108 claimed load-bearing but had zero JS enforcement. - coverage reconciliation backstop (§3.6): empty-coverage only guarded ==0; now 0<routesReached<routesPlanned with the shortfall unexplained by route-level coverageGaps -> adjudicate(allowContinue:false). Closes the partial-coverage false-green. Counts route-level reasons only; over-counting can only suppress the gate, never false-halt. - test-DB guard direct-halt now implemented: TESTDB_GUARD_MARK in envError.detail + behaviorTestDbGuardTripped -> immediate HALT on the first result, honoring step2's "no retry, no adjudication" promise (previously prompt-only; a guard trip wrongly entered the generic stack-not-ready retry path, ~5 redundant setup-test-db.mjs runs). Left as accepted design trade-offs (documented in design §12): self-attested whitelist/route scope, soft-by-source non-data text, disabled-control should-work recovery limited to submit buttons. Verified: SYNTAX_OK (wrapped check), 87/87 lib tests pass, no time/random builtins. v2 design doc updated (§3/5/6.2/6.3 + new §12).
-
Replaces the phase-level read-only behavior-gate with a per-FE acceptance dimension: each FE is approved only when the code-reviewer approves AND runtime behavior verification is green. Behavior defects (dead control / sentinel text mismatch) become fixable must-fix that drive verify->fix->re-verify, not halts. - reviewWithFixLoop (frontend only, via if(fe)): at the approve gate, behaviorSubGate boots this FE's full stack + seeds sentinels, enumerates this FE's routes, two-tier asserts. Hard issues with a locator -> fixPrompt -> functional reverify -> next behaviorRound; soft text (i18n/literal/semantic) -> adjudicate(continue); behaviorRound bounded by BEHAVIOR_FE_MAX=3, env race by BEHAVIOR_ATTEMPT_MAX=2. Backend featureLoop branch unchanged. - New runFrontendSkeleton stage (before featureLoop(frontend)): App shell + full lazy router + FeStub placeholders + shared nav, so the app is buildable at every mid-phase point; tdd swaps FeStub->real component per FE. Idempotent via fe-skeleton-done tag. - BEHAVIOR_GATE_SCHEMA gains build-failed envError kind (sibling-FE-unimpl short-circuit, not a bug) + locator-not-resolvable coverage reason; deriveSpec emits a per-FE route-scope section, reviewer validates it. - Removed phase-level runBehaviorGate + 'Behavior' phase; kept phase-level testGate (regression). REVIEW_HARD_ROUNDS 8->10. - Safety: test-DB naming guard pushed into scripts-setup-test-db.mjs template (fail-closed unless name contains test/_dev/_local or ALLOW_NONTEST_DROP=1) + 3 tests. - agentType stays erp-workflow:code-reviewer. v1 design doc marked SUPERSEDED; v2 design at docs/design/2026-06-02-frontend-behavior-in-review-loop.md. Verified: wrapped syntax check SYNTAX_OK, 87/87 lib tests pass, no orphan refs, no time/random builtins, top-level return intact. Not yet run end-to-end against a real ERP project.
-
New 'Behavior' stage between Gate and Milestone, frontend-phase only, after testGate green and before report/milestone. Verifies every interactive control actually works and every text region shows the right content, independent of the tests the tdd agent wrote. - BEHAVIOR_GATE_SCHEMA / behaviorGateContract() / behaviorGatePrompt() / runBehaviorGate(); reportPrompt now gates the milestone on behavior-gate evidence (frontend-phase-behavior-gate-r*.md, last attempt must be non-RED). - Two-tier failure: interaction defects (incl. binding-garbage) flake-retry once then hard-halt via adjudicate(allowContinue:false); text issues split by source (sentinel=objective -> no continue; i18n/literal/semantic=adjudicable). Convergence loop re-runs the env + interaction hard gates after any text-layer retry so a refreshed result can't slip a green past the hard gates. - Full-stack seeded run: test-DB name guard (deterministic halt, not adjudicated), strict 4-phase ordering (empty DB -> boot backend so Flyway builds schema -> seed -> boot frontend), auth bootstrap via storageState, router-config-driven route discovery, ephemeral .tmp/behavior-gate runner with finally teardown, type-legal per-field-unique sentinels. - agentType uses the plugin-namespaced 'erp-workflow:code-reviewer' (a bare 'code-reviewer' is ambiguous with feature-dev:code-reviewer); README + agents/code-reviewer.md aligned (frontmatter name: stays bare). - Design: docs/design/2026-06-02-frontend-behavior-gate.md. README + coding-start banner updated.
-
缺值类(A)改为 stage 自主决策继续并登记 decisions[];结构违约/重试耗尽(B/C)经新增 adjudicate() 仲裁 retry/continue/halt(runStage/runAction 包装,ADJUDICATE_MAX=3);dirty 工作树自主恢复(带分支护栏, 非功能分支/越界改动仍 halt)。review 软5/硬8 轮;docs/08 checkbox 降级为纯可视化(req-done tag 为真值)。 硬边界保持: merge 冲突 / invalid-projectRoot / assertSafeId 注入护栏 / 红色测试绝不 continue 跳过 (verify/reverify/tdd/report allowContinue:false)。JS HALT throw 37->26。
-
- docs-04 template: remove § 2.5 样式与主题 (tokens live in src/styles/tokens.css) + § 3.5 配置与安全 (config in config-vars.yaml, rules in docs/07→now config-vars header) - styles-tokens-template.css: fix 3 stale docs/06 refs missed in the earlier docs/06 removal (greps had excluded *.css) → self-contained '色值单一来源 / SSoT' - coding.mjs: frontend ref §一 前端架构 → §二 前端规范 (§一 is 后端); backend drop frontend §2.1 → §1.2 分层; 样式/色值 → tokens.css; remove docs/07 from value-lookup order
-
- delete docs-09-structure-template.md (its § 二/§ 三 dir layout duplicated docs/04 § 1.2/2.1; § 四 docs-tree was a self-referential maintenance trap; § 五 overlapped docs/04) - skeleton-gen B.1 now generates only docs/07; B.2 captures backend/frontend dir layout into docs/04 § 1.2/2.1; frontmatter/checkbox/参考 drop docs/09 - coding.mjs (6 refs): file placement -> docs/04 § 1.2/2.1; frontend root -> frontend/ convention; cross-module path->module -> docs/08 § 二 路径: field - CLAUDE-template rule #2 -> docs/04 § 1.2/2.1; docs-08 checkbox + README A2/template-table drop docs/09
-
- C.1: stop generating sql/migrations/.gitkeep (A4 db-init's Write V1 creates the dir); README A2 drops 'create empty migrations dir' - precedence rule: on color conflict, tokens.css wins over prototype (prototype = structure/layout/interaction; tokens.css = color) — encoded in skeleton-gen note, coding.mjs frontend stage, code-reviewer § Design Tokens
-
- delete frontend-scope-lock skill + docs/06 templates (static + module-pagelist) - A5 downstream-gen gains prototype/ gate + FE-list derivation -> docs/08 § 三 - plan-start: drop A6 dispatch row, gate 5->4 items; coding-start A0~A6 -> A0~A5 - Design Tokens single source = src/styles/tokens.css (code-reviewer, coding.mjs) - plugin.json skills 9->8; docs-09 tree drops 06-UI; docs-08 drops A6 section
-
The TAG_REPORT_FRESHNESS_SCHEMA + checkTagReportFreshPromptM + the post-`tag.exists` freshness branch in runMilestone existed to detect "tag points at a commit whose § ⑫ is still {{milestone_tag}}". Per the original comments, this only catches historical leftovers from the pre-fix tag → § ⑫ ordering; the same fix reversed the order so the runtime guard is no longer load-bearing. ~25 lines of branchy defensive code that the source-level fix already prevents. If a pre-fix repo has stale milestone tags, delete them with `git tag -d milestone/<id>` and re-run coding-start. -
Independent Claude + Codex review of the working-tree diff surfaced 23 issues; all applied in-place across three domains. workflows/coding.mjs (9): - spec/plan/verify/review prompts now git-commit their artifacts (closes milestone-dirty-worktree halt risk) - CHECKBOX_STATE_SCHEMA requires `state` + defensive guard in reviewWithFixLoop - writeDocs08FieldPromptM scopes edits to module via line anchor - assertSafeId guards Router output (module/REQ/FE ids) - featureLoop captures reviewWithFixLoop's return value - dateFromArtifactPath rejects impossible dates (9999-99-99 etc.) - terminal HALT review-unresolved message disambiguated - updated comment on top-level `return` (ESM vs node --check) lib/validate-ddl.mjs + tests (10): - extractType preserves unsigned/signed modifiers - KEY/INDEX fallthrough no longer creates spurious 'KEY' columns - FOREIGN KEY REFERENCES accepts schema-qualified `db.table` - index keys normalized to name:kind:cols (UNIQUE-aware) - FK keys include ON DELETE action (defaults to RESTRICT) - CREATE TEMPORARY TABLE parsed - parseForeignKeyBullet/parseIndexBullet reject prose bullets - +10 regression tests (62 total, all pass) - merge-gitignore.mjs docstring synced to implementation skills/ (4): - docs-06 template header: § 一~二 → § 一~三 - downstream-gen §A steps renumbered 1-7 (was 1,3,4,5,6,7,8) - docs-08 initial template adds tokens.css checkbox - coding-start drops "已在后台启动" wording (Workflow is synchronous)
-
- 新增 scope-lock/templates/config-vars-template.yaml:非敏感项目级配置 (包名/端口/前端包名/初始账号)+ secrets_ref 键名引用 .env.local; A1 E.2 锁定。docs/07 改为只记规则/约定不记具体值。 - 连带更新 skeleton-gen / plan-start 闸门 2 / frontend-scope-lock / CLAUDE-template / README / docs-06·07 模板对齐新的配置分层与 docs/06 小节编号。 - lib 修复(含回归测试): - apply-ddl: 抽出 resolveDbConfig,DB_SCHEMA 为契约 schema 键,缺库名 fail-closed (M1) - render: 用 Object.hasOwn 拒绝原型链继承键,guard process.argv[1] - validate-ddl: 解析 ### 索引/### 外键 bullet (C2)、剥 SQL 注释防幽灵表 (L4)、PRIMARY 归一化 - coding.mjs: Router 把全部前端 FE 聚合为单一末尾 frontend-phase 模块; 新增 branchSetupPrompt 功能分支生命周期 (C1);diff 区间改三点 diff;fix 后复跑 verify。
-
The autonomous build changed it to `export default` to satisfy `node --check`, but Workflow scripts run in an async wrapper where top-level `return` is the result contract (alongside `export const meta`). `export default` would be a dead module export and the per-module result summary would be lost.