-
…yml 占位约定 + Flyway out-of-order；env/marker 双缺省行为一字不变
-
…层 return），包裹后检查；.tmp/ 入 gitignore
-
- 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。 -
- mergeAlterStatements 对 MODIFY/CHANGE/RENAME/ALTER/DROP（除 DROP FOREIGN KEY， 外键维度已移除故对称放行）登记 unsupportedAlters；CLI 非空即 exit 1 并列出子句。 此前静默跳过导致「migration 改了列但 docs/03 未同步」绿灯假阳性——恰是闸门最该抓 的场景。未 CREATE 的表同样登记（检测先于 if(!t) 跳过）。parseDDL(text, opts) 不传 收集器时行为不变（向后兼容）。 - parseDDL 三遍扫描统一单一抹除底稿（剥注释+抹字面量一次完成，REGEX-3 全覆盖； blankStringLiterals 长度不变故偏移可复用）；顺带修掉第一遍在未抹除底稿上扫描、 字面量内 "CREATE TABLE ghost(...)" 产出幽灵表的缺口。 - 测试 52→58：全部拒绝臂参数化覆盖（RENAME/ALTER COLUMN/DROP INDEX/DROP PRIMARY KEY）、混合 ADD+MODIFY（ADD 仍并入且登记）、CLI exit-1 冒烟（spawnSync）、幽灵表 回归、DROP FOREIGN KEY 容忍。 - add-req SKILL.md 闸门说明同步硬拒语义，消掉悬空的「见 P2」引用。
-
- 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）。
-
cb9da34e 转 coding.mjs Workflow 时把 auto-continue Stop 钩子连同 17 个旧 coding 子技能一起删了，导致逐 REQ 手动编码会话每个 REQ 完就停下问 continue。 本提交恢复该机制： - hooks/scripts/auto-continue.sh（Stop）：回合中途结束默认 block 并喂「继续 推进」，使各 REQ 子任务连跑、用户无需手敲 continue；仅当 transcript 出现 [ERP-HALT] 或连续空转达上限(8)/无 >4000B 增长时放行停下。 - hooks/scripts/reset-stall-counter.sh（PostToolUse）：有工具调用即清零空转 计数，真推进时无限续跑。 - hooks/hooks.json：接线 Stop + PostToolUse（不含已删的 log-cross-module.sh）。 - coding-start 步骤5「Workflow 已启动」横幅补 [ERP-HALT]：Workflow 转后台后 主循环干净停下等通知，不被钩子误推去重启 coding-start。 - .gitattributes：强制 *.sh / hooks.json 用 LF，避免 autocrlf 把 CRLF 注入 shebang 与钩子输出的 JSON。 钩子在会话启动时加载，需重启已运行会话才生效（开发仓即运行源，无需 commit 即生效，commit 仅为持久化）。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
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>
-
初始 Plan 完结后追加/修改需求时，只跑增量、不必整仓重跑。 - lib/req-ledger.mjs（+单测）：对 docs/01 REQ 卡 + docs/08 §三 FE 行算 sha256 内容哈希， 对比 .req-ledger.json，scan/commit 出 new/changed/removed/unchanged - skills/plan/add-req：新增 user-invocable 增量入口。基线→检测→校验真实数据→ A3-delta(写 V_n migration + 同步 docs/03，永不改 V1)→A5-delta(docs/05/02/08)→ 作废 changed 单元的 req-done/milestone tag→提交台账。Router 无需改动，缺 tag 即重跑 - 变更识别靠内容哈希（非仅 tag 缺失）：改过的老 REQ 也能认出并作废其 req-done， 否则 Router 会跳过它——OpenSpec delta 思路的零依赖落地 - 首跑无台账则先建基线，避免把存量误当新增重跑整仓 - plugin.json 注册第 9 个 skill + 版本 0.2.0→0.3.0；CLAUDE 模板 Schema 演化补增量 V_n 规约 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
-
- bInvalid(是否作废)/sFormId(界面ID) 由主表专属审核列移入基础标准列,所有表(含从表)均含;主表专属审核列减为 bCheck/tCheckDate/sCheckPerson/sStatus(4列) - 主表渲染 15 列顺序与基线一致(4 审核列插在 bInvalid 与 sFormId 之间);从表 10→12;bInvalid 仍钉死裸 bit - db-design 步骤B 要求1 新增: 金额/数量小数列统一 decimal(18,6)(REQ 明确要求可偏离) - 同步 header/table 模板 + db-design C.1/C.2 + db-init A.1 + README A3 - 审计(多代理)+validate-ddl 实测均通过(decimal(18,6)/bit 4维一致;bit(1)负例正确 fail)
-
- 基础标准列(所有表)新增 sMakePerson(varchar50,制单人,app-assigned) / tUpdateDate(datetime DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP) - 主表(表清单第一张)无条件 +6 审核列: bInvalid/bCheck(bit) tCheckDate(datetime) sCheckPerson(审核人)/sStatus/sFormId(varchar50); 全 NOT NULL 无 SQL 默认 app-assigned - 从表 sParentId 不变(紧随 sId); 匈牙利前缀图例加 b=bit - 同步 header/table 模板 + db-design C.1/C.2 + db-init A.1 DDL 译法 + README A3 - db-init 钉死 bInvalid/bCheck 裸写 bit(禁 bit(1)) 对齐 validate-ddl 不归一化 BIT 长度(audit D5-1)
-
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）。
-
- coding-start / plan-start：去掉已失效的「git 就绪由本入口预检/校验」表述（git 闸已移入 coding.mjs 运行时） - skeleton-gen：删除「A2 不再单独出 docs/06/07/09」「原 docs/09 并入」等历史演进注释 - downstream-gen：描述去掉「A6 已并入此处」历史包袱 - CLAUDE-template：补全被截断的 migration 规约残句（旧 V_n.sql 保持原样、永不回改） - README：修正悬空的「🧭 通用工作准则」引用、删「4 条通用准则」、模板计数 26→19、coding-start git 就绪描述
-
- 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>
-
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.
-
…n-check + projectRoot git 就绪（默认分支/工作树干净/功能分支创建与合并）改由 coding.mjs runBranchSetup 运行时把守； 入口只校验 Plan 完成态（docs/08 §一 全勾）并取 projectRoot 绝对路径传入 Workflow。 相应收窄 allowed-tools（去掉 git status/branch/checkout 授权）。
-
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。
-
validate-ddl now recognizes the db-init A.1 DDL form (CREATE TABLE → CREATE INDEX → ALTER TABLE ADD FK), so schemas with out-of-body indexes/ FKs no longer report false-positive index/FK diffs. Adds a second parse pass (mergeStandaloneIndexes / mergeStandaloneForeignKeys), string-literal blanking so DEFAULT/COMMENT text isn't mistaken for real DDL, backtick non-ASCII identifier support across all matchers (H3), and shared index- column normalization (strip backtick / prefix-length / ASC|DESC) on both docs and DDL sides. Chinese 主键/唯一 index labels map to PRIMARY/UNIQUE. apply-ddl resolves mysql2 from the target project dir (not the plugin), rejects 【人工填写】 credential placeholders before connecting, and exits 2 on missing config/DDL paths. setup-test-db template validates schema as an ASCII identifier before interpolating it into DROP/CREATE. db-init gains a B.1 toolchain precheck (mysql2 module + mysql client) before any DROP.
-
- db-design-gen: drop unused `AskUserQuestion` grant (the A0 convention- confirm step was removed; conventions are now fixed in step B). Update the stale README A3 row that still described the dropped AskUserQuestion flow. - downstream-gen: drop unused `Skill` grant (terminal A step — it stops for /plan-start, never dispatches). - skeleton-gen: QA banner 产出清单 referenced docs/07, which was removed (the skill itself states A2 no longer emits docs/06/07/09) → drop it. - project-init: align description with body + README — dependency check is auto-install-then-stop, not give-instructions-and-stop.
-
- check 1 grep set: remove `待补` — it is used nowhere as a placeholder convention (real tokens are 【人工填写：…】 / TBD(...) / {{...}}), so it matched nothing. - replace the inaccurate "(与 scope-lock E.1 同集合)" note: this terminal gate greps a superset (`{{` + `TBD` + `【人工填写`) precisely because the TBD(A3/A5 自动补) placeholders legitimately deferred at A1 must be resolved by now — explaining the value-add over E.1 instead of claiming false parity. -
- docs/10 was generated once at A5 and never read back by any skill, workflow, or gate (the `acceptance` hits elsewhere are the per-REQ card field, unrelated). Removing it costs the pipeline nothing. - delete docs-10-header-template.md; drop step E + its checkbox, banner entry, description mention, and reference-list entry from the skill; renumber old step F → E. - drop the docs/10 checkbox from docs-08-initial-template.md. - update README (A5 flow line, A5 table row, template-table row).
-
- docs-05 header: collapse the `## 全局约定` block (response-format JSON + auth/pagination placeholders) into a single pointer to docs/04 (the conventions SSoT). Also fixes a broken ref — it cited "docs/04 § 1.4 错误码段位", but § 1.4 is 统一响应格式 and no such section exists. - docs-02: remove the free-form `## 三、关键说明 {{notes}}` filler section (the skill defines no source for it). -
- resolveDbConfig only ever received the 5 DB_* keys dbEnvFromConfig emits; the MYSQL_*/DB_PASS/DB_NAME fallbacks had no producer (dead speculative generality, a dotenv-era leftover). Remove them. - collapse the config → DB_* env-shape → connection two-hop: resolveDbConfig now reads config.database.{host,port,user,password,schema} directly, and dbEnvFromConfig is removed. - CLI contract (node apply-ddl.mjs <configPath> <ddlPath>), the only caller via db-init, is unchanged. - rewrite tests to the parsed-config shape; drop the alias-only tests. 53 pass.