@xulthekl/team-flow 0.57.0 → 0.59.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/always/phase-guard.md +1 -1
- package/.claude-plugin/marketplace.json +3 -3
- package/.claude-plugin/plugin.json +2 -2
- package/.codex-plugin/plugin.json +2 -2
- package/.cursor-plugin/marketplace.json +2 -2
- package/.cursor-plugin/plugin.json +2 -2
- package/.github/plugin/marketplace.json +2 -2
- package/AGENTS.md +27 -7
- package/CHANGELOG.md +86 -0
- package/GEMINI.md +1 -1
- package/HANDOFF.md +2 -2
- package/INSTALL.md +10 -10
- package/README.md +9 -7
- package/agents/code-reviewer.md +3 -0
- package/agents/cross-change-consistency-checker.md +34 -6
- package/agents/release-archivist.md +6 -0
- package/docs/README_en.md +1 -1
- package/docs/platform-matrix.md +1 -1
- package/docs/release-checklist.md +1 -1
- package/docs/usage-guide.md +2 -2
- package/gemini-extension.json +2 -2
- package/hooks/session-start +2 -2
- package/llms.txt +1 -1
- package/package.json +2 -2
- package/plugin.json +2 -2
- package/scripts/check-version-consistency.mjs +34 -4
- package/scripts/guard/checks/dp3-approved.mjs +1 -1
- package/scripts/guard/guard.mjs +7 -1
- package/scripts/lib/cmd-state.mjs +9 -6
- package/skills/architecture-design/templates/conventions/frontend-patterns.md +7 -0
- package/skills/build-executor/SKILL.md +2 -0
- package/skills/build-executor/implementer-prompt.md +19 -0
- package/skills/build-executor/task-reviewer-prompt.md +51 -5
- package/skills/clean-code/SKILL.md +116 -0
- package/skills/clean-code/references/judgement-cases.md +83 -0
- package/skills/clean-code/references/shared-layer-rules.md +50 -0
- package/skills/code-reviewer/SKILL.md +10 -0
- package/skills/code-reviewer/code-reviewer-prompt.md +68 -2
- package/skills/decision-surrogate/SKILL.md +87 -0
- package/skills/decision-surrogate/references/decision-points.md +87 -0
- package/skills/decision-surrogate/references/onboarding.md +79 -0
- package/skills/decision-surrogate/references/protocols.md +116 -0
- package/skills/workflow-orchestrator/references/s5-monitoring.md +8 -4
- package/skills/workflow-start/SKILL.md +4 -0
- package/templates/conventions/glaf4-compliant/java-testing.md +3 -3
- package/templates/conventions/js-testing.md +1 -1
- package/templates/conventions/python-testing.md +1 -1
- package/.zcode/hooks.json +0 -8
- package/.zcode/rules/phase-guard.mdc +0 -33
- package/.zcode/skills/workflow-start/SKILL.md +0 -175
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "team-flow",
|
|
3
|
-
"description": "Unified workflow plugin: team-flow + compound-engineering core subset + architecture-design + prototype + workflow-orchestrator + workflow-bootstrap + e2e + session-handoff + workflow-feedback + business-analysis.
|
|
3
|
+
"description": "Unified workflow plugin: team-flow + compound-engineering core subset + architecture-design + prototype + workflow-orchestrator + workflow-bootstrap + e2e + session-handoff + workflow-feedback + business-analysis. 28 skills + 17 agents, one install.",
|
|
4
4
|
"owner": {
|
|
5
5
|
"name": "LT",
|
|
6
6
|
"url": "https://github.com/LT"
|
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
"plugins": [
|
|
9
9
|
{
|
|
10
10
|
"name": "team-flow",
|
|
11
|
-
"description": "8-state spec workflow + compound global compounding + architecture-design (4A/DDD) + local HTML prototype + product-level orchestration + bootstrap + e2e + session handoff + workflow feedback + independent business analysis.
|
|
12
|
-
"version": "0.
|
|
11
|
+
"description": "8-state spec workflow + compound global compounding + architecture-design (4A/DDD) + local HTML prototype + product-level orchestration + bootstrap + e2e + session handoff + workflow feedback + independent business analysis. 28 skills + 17 agents with embedded TDD, SDD, code review, debugging, delta spec sync, and design-system-driven prototyping.",
|
|
12
|
+
"version": "0.59.0",
|
|
13
13
|
"source": "./",
|
|
14
14
|
"author": {
|
|
15
15
|
"name": "LT",
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "team-flow",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact) + design-system (design tokens + component contract + AI primer + showcase) + test-strategy (test strategy design) + project-initialize (new service onboarding).
|
|
3
|
+
"version": "0.59.0",
|
|
4
|
+
"description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact) + design-system (design tokens + component contract + AI primer + showcase) + test-strategy (test strategy design) + project-initialize (new service onboarding). 28 skills + 17 agents, one install.",
|
|
5
5
|
"source": "./",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "LT",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "team-flow",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.59.0",
|
|
4
4
|
"description": "Spec-first workflow that bridges OpenSpec-style planning and Superpowers-style execution discipline.",
|
|
5
5
|
"author": {
|
|
6
6
|
"name": "MageByte",
|
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
"interface": {
|
|
27
27
|
"displayName": "team-flow",
|
|
28
28
|
"shortDescription": "Spec-first workflow with guarded execution.",
|
|
29
|
-
"longDescription": "A self-contained Codex workflow plugin with
|
|
29
|
+
"longDescription": "A self-contained Codex workflow plugin with 28 skills for intent exploration, planning artifacts, execution contracts, TDD execution, review gates, systematic debugging, closure, delta spec sync, and independent business analysis.",
|
|
30
30
|
"developerName": "MageByte",
|
|
31
31
|
"category": "Developer Tools",
|
|
32
32
|
"composerIcon": "./assets/icon.svg",
|
|
@@ -5,13 +5,13 @@
|
|
|
5
5
|
},
|
|
6
6
|
"metadata": {
|
|
7
7
|
"description": "Unified workflow plugin marketplace for Cursor (team-flow: team-flow + compound + architecture-design + prototype).",
|
|
8
|
-
"version": "0.
|
|
8
|
+
"version": "0.59.0"
|
|
9
9
|
},
|
|
10
10
|
"plugins": [
|
|
11
11
|
{
|
|
12
12
|
"name": "team-flow",
|
|
13
13
|
"source": ".",
|
|
14
|
-
"description": "Unified workflow plugin: team-flow + compound-engineering core subset + architecture-design + prototype + business-analysis.
|
|
14
|
+
"description": "Unified workflow plugin: team-flow + compound-engineering core subset + architecture-design + prototype + business-analysis. 28 skills + 17 agents."
|
|
15
15
|
}
|
|
16
16
|
]
|
|
17
17
|
}
|
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "team-flow",
|
|
3
3
|
"displayName": "team-flow",
|
|
4
|
-
"description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact).
|
|
5
|
-
"version": "0.
|
|
4
|
+
"description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking) + business-analysis (independent requirement/scenario artifact). 28 skills + 17 agents, one install.",
|
|
5
|
+
"version": "0.59.0",
|
|
6
6
|
"author": {
|
|
7
7
|
"name": "LT",
|
|
8
8
|
"url": "https://github.com/LT"
|
|
@@ -6,13 +6,13 @@
|
|
|
6
6
|
},
|
|
7
7
|
"metadata": {
|
|
8
8
|
"description": "Unified workflow plugins and skills for AI coding agents (team-flow: team-flow + compound + architecture-design + prototype).",
|
|
9
|
-
"version": "0.
|
|
9
|
+
"version": "0.59.0"
|
|
10
10
|
},
|
|
11
11
|
"plugins": [
|
|
12
12
|
{
|
|
13
13
|
"name": "team-flow",
|
|
14
14
|
"description": "Unified workflow with planning artifacts, execution contracts, TDD, review gates, systematic debugging, delta spec sync, architecture-design, independent business analysis, and local HTML prototyping.",
|
|
15
|
-
"version": "0.
|
|
15
|
+
"version": "0.59.0",
|
|
16
16
|
"source": ".",
|
|
17
17
|
"author": {
|
|
18
18
|
"name": "LT",
|
package/AGENTS.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# AGENTS.md · team-flow
|
|
2
2
|
|
|
3
|
-
> team-flow 统一插件 = **team-flow**(spec 驱动开发)+ **compound-engineering 核心子集**(全局复利)+ **architecture-design**(4A+DDD 增量设计)+ **prototype**(本地 HTML 原型)+ **e2e**(AC 驱动 Playwright E2E)+ **workflow-orchestrator**(产品级编排)+ **workflow-bootstrap
|
|
3
|
+
> team-flow 统一插件 = **team-flow**(spec 驱动开发)+ **compound-engineering 核心子集**(全局复利)+ **architecture-design**(4A+DDD 增量设计)+ **prototype**(本地 HTML 原型)+ **e2e**(AC 驱动 Playwright E2E)+ **workflow-orchestrator**(产品级编排)+ **workflow-bootstrap**(既有项目接入)。一次安装,十三套能力协同(28 skills + 17 agents),支持 9 安装面(Claude Code, Cursor, OpenAI Codex CLI/App, GitHub Copilot CLI, Gemini CLI, OpenCode, WorkBuddy, Trae, ima-copilot)。
|
|
4
4
|
|
|
5
5
|
## What This Is
|
|
6
6
|
|
|
@@ -12,7 +12,7 @@
|
|
|
12
12
|
|
|
13
13
|
### 身份与依赖关系
|
|
14
14
|
|
|
15
|
-
- **team-flow**(本插件):Claude Code / Cursor 等宿主的插件实体(`plugin.json` name = `team-flow`),包含
|
|
15
|
+
- **team-flow**(本插件):Claude Code / Cursor 等宿主的插件实体(`plugin.json` name = `team-flow`),包含 28 个 skills + 17 个 agents + hooks + templates
|
|
16
16
|
- **@xulthekl/team-flow**(npm 底座包):team-flow 的 CLI 工具层(`package.json` name = `@xulthekl/team-flow`,bin = `tf` / `team-flow`),提供状态机、校验、复利 CLI 等运行时能力
|
|
17
17
|
- 关系:team-flow 插件 **包含** @xulthekl/team-flow npm 包作为底座(同一仓库、同一版本)。skills 中的 `tf ...` 调用的是已全局安装的 @xulthekl/team-flow CLI,版本由 session-start hook 自动同步
|
|
18
18
|
- 历史身份(已废弃):`spec-superflow`(npm 包名,0.11.0 后停止发布)/ `ssf`(CLI 前缀)/ `.spec-superflow.yaml`(状态文件)—— 详见设计增强方案 v0.9 §27
|
|
@@ -33,11 +33,11 @@ node --test tests/e2e.test.mjs --test-name-pattern="parseDeltaSpec"
|
|
|
33
33
|
npm run validate
|
|
34
34
|
```
|
|
35
35
|
|
|
36
|
-
##
|
|
36
|
+
## 能力概览(十三套合一,28 skills)
|
|
37
37
|
|
|
38
|
-
### 1. team-flow(底座,
|
|
38
|
+
### 1. team-flow(底座,11 skills)
|
|
39
39
|
spec 驱动开发过程。8 态变更机:`exploring → specifying → bridging → approved-for-build → executing → closing`(另有 `debugging` 侧路径 + `abandoned` 终态)。
|
|
40
|
-
- `workflow-start` 启动 / `need-explorer` 需求探索 / `spec-writer` 写 spec / `contract-builder` 构建执行契约 / `build-executor` TDD 实现 / `code-reviewer` 代码审查 / `spec-merger` 合并 delta spec / `release-archivist` 发布归档 / `bug-investigator` bug 调查
|
|
40
|
+
- `workflow-start` 启动 / `need-explorer` 需求探索 / `spec-writer` 写 spec / `contract-builder` 构建执行契约 / `build-executor` TDD 实现 / `code-reviewer` 代码审查 / `spec-merger` 合并 delta spec / `release-archivist` 发布归档 / `bug-investigator` bug 调查 / `test-strategy` 测试设计方法论(预加载)/ `clean-code` 代码结构质量判据(预加载,v0.58.0)
|
|
41
41
|
|
|
42
42
|
### 2. compound-engineering 核心子集(6 skills,全局复利)
|
|
43
43
|
- `ce-brainstorm` 需求头脑风暴 / `ce-plan` PRD 规划 / `ce-compound` 全局复利回写 / `ce-strategy` 策略锚点(`STRATEGY.md`) / `ce-ideate` 设计创意 / `ce-proof` 验证证明
|
|
@@ -90,6 +90,21 @@ spec 驱动开发过程。8 态变更机:`exploring → specifying → bridgin
|
|
|
90
90
|
- 支持多轮单问澄清、待办记录、新增/更新模式,写入前必须阻塞用户确认
|
|
91
91
|
- 不进入核心工作流,作为独立外挂工具运行
|
|
92
92
|
|
|
93
|
+
### 11. design-system(1 skill,项目级设计系统,v0.19.0)
|
|
94
|
+
- 设计系统独立创建与维护,产出落 `.team-flow/design-system/`(base 品牌共享层 + B端/C端变体 + primer + 预览画廊)
|
|
95
|
+
- 三条创建入口:交互式(LLM 推荐 + 用户确认)/ 内置模板库导入(registry.json 参考库)/ 从既有代码逆向建库(create-from-code)
|
|
96
|
+
- 支持独立调用或 prototype skill 内部编排调用
|
|
97
|
+
|
|
98
|
+
### 12. project-initialize(1 skill,项目初始化引导,v0.45.0)
|
|
99
|
+
- 工作空间代码服务为空时触发:识别需初始化 → 引导架构选择(glaf4 体系 / 前端分离 / 单体微服务 / 拆分)→ 服务命名确认 → 创建服务子目录 → 委托初始化骨架
|
|
100
|
+
- glaf4 体系走 glaf4-dev 的 PROJECT_INITIALIZE 模式;非 glaf4 走内置引导(B1.5 骨架生成)
|
|
101
|
+
- 由 ARCH 后 Pre-check 服务初始化检测触发(缺失时引导接入)
|
|
102
|
+
|
|
103
|
+
### 13. decision-surrogate(1 skill,夜间决策替身,v0.59.0 新增,**可选启用**)
|
|
104
|
+
- 用户离席期间接管 team-flow 决策点:睡前布置任务并逐点预授权 → 夜间经 Orca 派 worker 跑工作流 → 裁决可代答的点、其余 HOLD 等用户 → 早上交付决策过程汇总
|
|
105
|
+
- 依赖**个人资产**:`~/.claude/lt-preferences/` 决策偏好库 + 替身 home(各成员自建)
|
|
106
|
+
- **不进任何默认流程**,需要的成员独立启用;设计文档见工作区 `docs/plan/decision-surrogate-design.md`
|
|
107
|
+
|
|
93
108
|
## 全局产物结构(Discoverability —— 设计/开发前先检索)
|
|
94
109
|
|
|
95
110
|
```
|
|
@@ -174,7 +189,7 @@ STRATEGY.md CONCEPTS.md 产品策略(BA) / 领域词汇
|
|
|
174
189
|
全局作为下一 change / 下一 PRD 版本的 grounding → 闭环
|
|
175
190
|
```
|
|
176
191
|
|
|
177
|
-
## Skills 索引(
|
|
192
|
+
## Skills 索引(28 个)
|
|
178
193
|
|
|
179
194
|
| Skill | 归属 | 用途 |
|
|
180
195
|
|---|---|---|
|
|
@@ -184,6 +199,7 @@ STRATEGY.md CONCEPTS.md 产品策略(BA) / 领域词汇
|
|
|
184
199
|
| contract-builder | team-flow | 构建执行契约 |
|
|
185
200
|
| build-executor | team-flow | TDD 实现 |
|
|
186
201
|
| test-strategy | team-flow | 测试设计方法论(design_method 三级分层 + 对抗验证 + 复杂度分级,v0.12 §41) |
|
|
202
|
+
| clean-code | team-flow | 代码结构质量判据(机械阈值 + 审查必答项 + 增量归因边界 + 共享层判定,v0.58.0) |
|
|
187
203
|
| code-reviewer | team-flow | 代码审查 |
|
|
188
204
|
| spec-merger | team-flow | 合并 delta spec |
|
|
189
205
|
| release-archivist | team-flow | 发布归档 |
|
|
@@ -204,6 +220,7 @@ STRATEGY.md CONCEPTS.md 产品策略(BA) / 领域词汇
|
|
|
204
220
|
| workflow-feedback | 工作流反馈 | 工作流问题结构化记录(v0.16.0) |
|
|
205
221
|
| business-analysis | 独立业务分析 | 将任意输入整理为 requirement/vN/business-analysis.md(独立外挂,v0.44.0) |
|
|
206
222
|
| project-initialize | 项目初始化引导 | 工作空间代码服务为空时:架构选择(glaf4/前端分离/单体微服务/拆分)→ 服务命名确认 → 创建服务子目录 → 委托初始化(glaf4 走 glaf4-dev,非 glaf4 走内置引导)(v0.45.0) |
|
|
223
|
+
| decision-surrogate | 夜间决策替身(**可选启用**) | 用户离席期间接管 team-flow 决策点:睡前逐点预授权 → 夜间经 Orca 派 worker → 裁决可代答点、其余 HOLD → 早上交付决策汇总;依赖个人偏好库与替身 home(v0.59.0) |
|
|
207
224
|
|
|
208
225
|
### 触发域分层(v0.12.0 新增)
|
|
209
226
|
|
|
@@ -214,11 +231,14 @@ STRATEGY.md CONCEPTS.md 产品策略(BA) / 领域词汇
|
|
|
214
231
|
| 接入层 | workflow-bootstrap | "初始化/接入/分析代码库" | 一次性,触发词独特,无冲突 |
|
|
215
232
|
| 产品级(唯一入口) | **workflow-orchestrator** | 新的产品级需求("新需求/从头开始/我有个想法/做一个XX") | 拥有所有"产品级新需求"触发词,内部路由到 ce-brainstorm/ce-plan |
|
|
216
233
|
| 变更级(唯一入口) | workflow-start | change 上下文内的操作(.team-flow.yaml) | 有强上下文约束,与产品级天然隔离 |
|
|
217
|
-
| 步骤级 - 独立工具 | ce-ideate, ce-strategy, ce-compound, ce-proof, architecture-design, prototype, e2e, session-handoff, workflow-feedback, **business-analysis** | 各自独特触发词 | 无冲突,可独立触发;business-analysis
|
|
234
|
+
| 步骤级 - 独立工具 | ce-ideate, ce-strategy, ce-compound, ce-proof, architecture-design, prototype, e2e, session-handoff, workflow-feedback, **business-analysis**, **decision-surrogate** | 各自独特触发词 | 无冲突,可独立触发;business-analysis 不进入核心工作流;**decision-surrogate 为可选启用**(个人替身,不进任何默认流程) |
|
|
218
235
|
| 步骤级 - 受限独立 | ce-brainstorm, ce-plan | 可独立触发,但产品级新需求应走 orchestrator | description 中标注路由指导 |
|
|
219
236
|
| 步骤级 - 仅路由 | need-explorer, spec-writer, contract-builder, build-executor, code-reviewer, spec-merger, release-archivist, bug-investigator | 仅由 workflow-start 路由 | 不独立触发 |
|
|
237
|
+
| 内部方法论(预加载)| test-strategy, clean-code | 无触发词——仅经 agent `skills:` 字段预加载,或由派发模板内联 | 不独立触发;判据真相源,执行处为派发模板(`user-invocable: false`)|
|
|
220
238
|
|
|
221
239
|
> **规则**:新增 skill 时必须在此表登记所属层级。产品级新需求触发词归 workflow-orchestrator 独占。
|
|
240
|
+
>
|
|
241
|
+
> **新增 skill 的完整登记清单(v0.58.0 补,防「修复未传播」)**——需同步 **6 处**:① 本触发域分层表;② 上方**能力概览**的对应套枚举与组数;③ `README.md` 的「N 套能力」标题 + 枚举 + **首段摘要行**("一次安装,N 套能力协同"易被遗忘,v0.58.0 实测残留 2 处);④ 各 host manifest 的 skills 计数(`.claude-plugin/` / `.cursor-plugin/` / `.codex-plugin/` / `gemini-extension.json` / `package.json`);⑤ `AGENTS.md` 的 Skills 索引表;⑥ 工作区 `CLAUDE.md`。`npm run check-versions --fix` **只覆盖其中一部分**(v0.58.0 实测漏 13+ 处),其余须人工核对。
|
|
222
242
|
|
|
223
243
|
### Agents 索引(v0.7 新增,v0.47.0 增至 17 个)
|
|
224
244
|
|
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,92 @@ All notable changes to `team-flow` will be documented in this file.
|
|
|
4
4
|
|
|
5
5
|
The format loosely follows Keep a Changelog.
|
|
6
6
|
|
|
7
|
+
## [0.59.0] - 2026-09-12
|
|
8
|
+
|
|
9
|
+
### Added(decision-surrogate 决策替身 —— 第 28 个 skill,可选启用)
|
|
10
|
+
|
|
11
|
+
设计来源:`docs/plan/decision-surrogate-design.md` **v4.1**(P1.5 完整档三轮对抗验证,收官 0 Critical;P4 修订见其变更记录;附录 A 如实记账 18 真闭合 / 5 表面闭合 / 1 未采纳)。**不进任何默认流程**——需要的成员独立启用。
|
|
12
|
+
|
|
13
|
+
**新增 `decision-surrogate` skill**(第 28 个):用户离席期间扮演决策代理——睡前布置任务并逐点预授权,夜间经 Orca orchestration 派 worker 跑 team-flow 工作流,裁决**可代答**的决策点、其余一律 HOLD 等用户,早上交付决策过程汇总。
|
|
14
|
+
|
|
15
|
+
**代答权限三分**(9 个 DP 门 + 5 个确认点):无条件代答 1(DP-0)/条件代答 6(DP-1/2/3/4/G4/E2E)/挂起 7(DP-A 架构门禁、DP-5/6/7、G5、Code Landing、S3.5 publish)。DP-3 条件代答须**同时满足四条件**才批准。
|
|
16
|
+
|
|
17
|
+
**夜间红线**(用户确认):允许 worktree 内本地提交;禁止 push/发布/删除/改契约范围外接口/任何对外发送/自行发明任务方向/Code Landing。
|
|
18
|
+
|
|
19
|
+
**关键设计决策**(均有实证依据):
|
|
20
|
+
|
|
21
|
+
- **HOLD 不写任何决策点字段**:`dp_N_result` 是门禁判据(`dp-gate-passed` 只校验非空),写入 HOLD 值会让 change 呈现"已批准"假象;而 `dp_{1,2,3,5,6,7}_decisions` / `_confirmed` 共 12 个字段 **不可落盘**(`dp_0_*` 除外)——它们在 `SETTABLE_FIELDS` 白名单内但 `writeState` 无序列化分支,`tf state set` **回显 ✅ 却零写入**(P4 亲测)。HOLD 的持久锚点 = escalation 消息 + 替身决策日志 + change 的 `state` 仍停在门禁前。
|
|
22
|
+
- **禁止 AskUserQuestion 是硬要求**:P0 实证 `orca terminal send` 返回 `agent_prompt_stalled`——worker 一旦弹出 TUI 模态,**没有任何自动化手段能救它**(设计文档附录 D 通道实证)。
|
|
23
|
+
- **不做「沉默即同意」**:`ask` 超时不产生默认裁决,保留 message_id 待恢复;HOLD 是主要形态,不得静默放行。
|
|
24
|
+
- **`observation.agentWait` 是健康态**(worker 等待人工应答),非故障——避免误判失败而重启。
|
|
25
|
+
- **未验证机制不写定论**:worker 遵循 task spec 是靠运行时约束的行为,每次任务须核对早报与**决策日志 + change 的 `state` 位置**是否一致(字段能否落盘须实测,勿据白名单推断)。
|
|
26
|
+
|
|
27
|
+
**Phase 0 首次接入**:9 项环境探测矩阵(Orca CLI/runtime/orchestration 开关/协调者锚点/可用项目/项目空间判据/偏好库/替身 home/机器不休眠),缺项给**具体引导命令**而非笼统报错;偏好库初始化三档(交互式 5 分钟 8 题/从既有资产提炼/历史会话挖掘)。
|
|
28
|
+
|
|
29
|
+
**三个 references**:`onboarding.md`(探测矩阵 + 偏好库与 home 初始化)/`decision-points.md`(代答权限 + 三档处置 + 红线)/`protocols.md`(授权书模板、worker task spec 模板、HOLD 六步协议、决策日志与早报格式)。
|
|
30
|
+
|
|
31
|
+
### Fixed
|
|
32
|
+
|
|
33
|
+
- **guard 安全档位倒置**(`scripts/guard/guard.mjs`):full 工作流的 `bridging:approved-for-build` 原只挂 `dp-gate-passed`(仅要求 `dp_3_result` 非空),而**取值严格校验**的 `dp3-approved` 只挂在 hotfix → 更重要的 full 反而用弱校验。后果:任何能写 `dp_3_result` 的主体(如夜间替身按早期设计写入 HOLD 值)都能让 change 呈现"已批准"假象,在无真实批准的前提下跨过 DP-3 硬门。修复:full 该转换补挂 `dp3-approved`(取值须以 `approved` 开头)。
|
|
34
|
+
- **`dp3-approved` 失败文案漂移**(`scripts/guard/checks/dp3-approved.mjs:10`):滞留 "before hotfix build",而该维度自本轮起同时守护 full → 改为 "before build"。
|
|
35
|
+
- **12 个「白名单内但不可落盘」的字段已移除**(`scripts/lib/cmd-state.mjs`):`dp_{1,2,3,5,6,7}_decisions` / `_confirmed` 在旧 `SETTABLE_FIELDS` 内,但 `writeState` 无序列化分支 → `tf state set` **回显成功却零写入**(静默假成功;全仓零消费者,实测确认)。移除后写入即报 `⛔ Field ... is not settable`。`dp_0_decisions` / `dp_0_confirmed` 保留(二者确有序列化分支)。
|
|
36
|
+
- **`.zcode/` 残留目录删除 + `.gitignore` 加规则**:该目录是 2026-07-30(v0.27.0)在插件仓库根调试 `install-zcode` 时留下的产物,被 `git add -A` 一并提交;其 `hooks.json` 含**本机绝对路径**,且只有 1 个 skill,与「28 skills」口径冲突。
|
|
37
|
+
|
|
38
|
+
### Fixed(横展:skills 计数漂移)
|
|
39
|
+
|
|
40
|
+
- **`INSTALL.md` 7 处**(`:342` `:367` `:390` `:465` `:531` `:686` `:797`)全部写「9 个 skill」——`install-workbuddy --dry-run` 实证输出 `Skills: 28`;qoder/cline/pi 走共享 `scripts/lib/install.mjs` 的 `copySkillsWithRoot`(只过滤目录、无名字过滤),同样部署全部。**危害**:`:390` 等处是安装验证步骤,照 9 数会误判安装失败。
|
|
41
|
+
- **`docs/platform-matrix.md:5`**「9 个 skill」→ 28。
|
|
42
|
+
- **`docs/usage-guide.md:39`**「24 个 skills + 15 个 agents」→ 28/17(该文件 `:3` 上轮已改计数却漏了 `:39`,典型**修复未传播**);`:3` 版本锚点 → v0.59.0(该文件不在 `check-version-consistency.mjs` 扫描面内,无门禁兜底)。
|
|
43
|
+
- **`HANDOFF.md` 有意不改**(7 处过期计数):该文件已在 v0.53.0 标注作废、保留供追溯,当轮 CHANGELOG 记录过决策——「只改几行会造成'已同步'假象」,故维持作废横幅、不同步数字。
|
|
44
|
+
|
|
45
|
+
### Added(机械门禁)
|
|
46
|
+
|
|
47
|
+
- **full 模式 DP-3 取值门测试**(`tests/lib/guard.test.mjs` 新增 3 个):维度已挂载/HOLD 值被拒/approved 值放行。**反向验证**:临时移除该维度 → 正好 3 个测试变红、其余 34 个不受影响(门禁自证有效,而非"改了门禁测试仍全绿")。
|
|
48
|
+
- **`check-version-consistency` 扫描面扩展 + `--fix` 嵌套写回修复**(`scripts/check-version-consistency.mjs`):计数检查由 4 个文件扩至 **9 条 JSON manifest + 7 条文档规则**(新纳 usage-guide / platform-matrix / release-checklist;INSTALL.md 用 3 条精确规则,**不得用全局替换**——那会误改 `:797` 的「其余 27 个」= count-1)。同时修复 `--fix` 的真实缺陷:原实现只写顶层键,遇到新增的嵌套路径(`plugins[0].description`、`interface.longDescription`)会把父级整体覆盖成字符串 → **毁文件**;改为按完整路径回溯写回,路径不可写时显式报错而非静默跳过。
|
|
49
|
+
- **`tests/lib/check-version-consistency.test.mjs`(新增 5 个测试)**:覆盖面锁定 + **行为验证**(改错 → 必须检出 → `--fix` 修复 → 结构完好 → 还原)。**反向验证**:把 `--fix` 改回旧实现 → 恰好嵌套路径测试变红、其余 4 个不受影响。
|
|
50
|
+
|
|
51
|
+
### Changed
|
|
52
|
+
|
|
53
|
+
- **skills 计数 27 → 28 同步(子仓库 12 处 + 工作区 CLAUDE.md)**:宿主 manifest 6 处(`.claude-plugin/` ×2、`.cursor-plugin/` ×2、`.codex-plugin/plugin.json`、`gemini-extension.json`)、`plugin.json`、`package.json`、`README.md`(含「十二套」→「十三套」)、`AGENTS.md`(能力概览第 13 节 + Skills 索引 + 触发域分层)、`docs/usage-guide.md`、`docs/release-checklist.md`。
|
|
54
|
+
|
|
55
|
+
## [0.58.0] - 2026-09-12
|
|
56
|
+
|
|
57
|
+
### Added(clean-code 结构判据能力)
|
|
58
|
+
|
|
59
|
+
设计来源:`docs/plan/clean-code-integration-design.md` **v1.3**(P1.5 标准档两轮对抗验证:第一轮 26 条 / 第二轮 18 条,收官 0 Critical;P4 三路验证——plugin-validator + skill-reviewer + 实证探针两轮)。
|
|
60
|
+
|
|
61
|
+
**新增 `clean-code` skill**(第 27 个 skill,`user-invocable: false`):代码结构质量的判据集,供 `build-executor` / `code-reviewer` 预加载。**判据三分**:① 可机械判定项(魔法值 **Critical**;函数长度 / 嵌套深度 / 参数个数 / 命名形式 **Minor**)② 审查必答项(单一职责、DRY——**不给阈值**,但必须回答并给理由)③ 沿用既有清单项(错误处理 / 边界 / YAGNI,本 skill 不涉及)。
|
|
62
|
+
|
|
63
|
+
**关键设计决策**(均有实测依据):
|
|
64
|
+
|
|
65
|
+
- **不给「单一职责」设阈值**:实测反证——37 行的 `validateFrontSystemSecret`(通体卫语句、单层抽象)与 54 行的 `handleDelivery`(三卫语句 + switch)可读性均良好,任何「抽象层级计数」规则都无法在这一对同类样本上复现判定,该规则已废。
|
|
66
|
+
- **判据内联、不做引用**:由模板派发的 `general-purpose` 子代理不继承 Skills,且 `scripts/lib/cmd-runtime.mjs` 的 ASSETS 白名单只含两个 build-executor 模板——三处判据**必须内联**,写成引用必然断链(子代理读不到)。
|
|
67
|
+
- **增量归因边界**:只判本次 diff 触及的代码单元;存量命中一律降 Minor 并在审查报告登记「存量待整改」。
|
|
68
|
+
- **判例集**:`references/judgement-cases.md` 收录 6 组真实判例(正例 `P1`/`P2`、反例 `N3`,及 `N1`/`N2`/`N4` 的例外说明),防止判据退化成新的直觉。
|
|
69
|
+
|
|
70
|
+
**新增 Dim 5「同构横展完整性」**(`cross-change-consistency-checker` 4 → 5 维度):检测本 change 处置的代码模式是否在其**全部**出现位置都已处置。**模式驱动**而非仓名驱动(实测缺口常跨同构组:4 个仓分属 `bff-emp-*` 与 `adapter-emp-*`,缺口恰在组间);含**真空对照**(零命中须显式报告「模式未命中,需人工确认」,不得记 CLEAN)。单 change 场景的调用点补在 `workflow-start` 的 `executing → closing` 关口——此前该 agent 仅在 S5(change ≥ 2)被调度,**该场景下 Dim 5 永不触发**。
|
|
71
|
+
|
|
72
|
+
### Changed(判据接线与口径统一)
|
|
73
|
+
|
|
74
|
+
- 三处派发模板内联结构判据:`implementer-prompt.md`(自检)、`task-reviewer-prompt.md`、`code-reviewer-prompt.md`(含必答项输出容器 + example 演示 Critical 落位与 fail 联动)。
|
|
75
|
+
- `code-reviewer/SKILL.md`:Step 3 加结构判据小节;**修正 verdict 口径矛盾**——`tf execution review --verdict` 只接受 `pass|fail`,`PASS_WITH_WARNINGS` 在二值 receipt 中无法表达,故 **Important 亦须阻断**(与三处模板一致)。此前「FAIL 仅 Critical」是四处口径中唯一的异类。
|
|
76
|
+
- `agents/code-reviewer.md`:`skills:` 加 `clean-code`;verdict 段补 receipt 映射。
|
|
77
|
+
- `agents/release-archivist.md`:新增 closing 时的「结构判据未覆盖」标注条件(glaf4-delegation 且契约未声明该条款时)。
|
|
78
|
+
- `skills/architecture-design/templates/conventions/frontend-patterns.md`:补前端魔法值约束——此前后端有全局硬约束、**前端无任何等价约束**(实测同一 change 内 21 处前端硬编码业务码被审查降级为 Minor)。
|
|
79
|
+
|
|
80
|
+
### Fixed
|
|
81
|
+
|
|
82
|
+
- **源头模板 5 处裸 `references/` 引用**(`templates/conventions/js-testing.md:247`、`python-testing.md:319`、`glaf4-compliant/java-testing.md:329,342,353`):目标文件真实存在于插件侧 `skills/test-strategy/references/`,但裸相对路径在项目内不可达。P3 横展检查发现——原计划只修下游产物(emp-auth 4 处),**未修源头**会让每个新接入项目继承同一缺陷。
|
|
83
|
+
- **skills 计数残留 13+ 处**:`check-versions --fix` 只覆盖 4 个文件的单一模式,宿主 manifest(`.cursor-plugin/` / `.codex-plugin/` / `gemini-extension.json`)、`package.json`、`docs/usage-guide.md`、`docs/release-checklist.md`(「9 skills」实为 27)、`AGENTS.md` 底座计数与 `README.md` 枚举均漏改。**工具缺陷已登记**(建议扩展扫描面,或改为从 `skills/` 目录动态派生真值后全仓比对)。
|
|
84
|
+
- 既有登记缺口补齐:`README.md` 枚举(补 `test-strategy` / `project-initialize`,修正「十套」→「十二套」,枚举合计 25 → 27)、`AGENTS.md` 能力概览(补 `design-system` / `project-initialize` 两节 + 新增「内部方法论(预加载)」分层行)。
|
|
85
|
+
- `tests/lib/cmd-install-workbuddy.test.mjs`:`skillNames.length === 26` 硬编码改为健壮断言(验证从 package root 发现 skills + 含已知 skill),消除随 skill 数漂移的脆弱性——该断言并非该测试的核心意图(测试名:`uses the package root by default instead of the caller cwd`)。
|
|
86
|
+
|
|
87
|
+
### Added(机械门禁)
|
|
88
|
+
|
|
89
|
+
`tests/lib/doc-consistency.test.mjs` 新增 **clean-code 判据一致性门禁**:检查真相源(中文)与三处内联副本(英文)的判据锚点与**阈值锚点**(`>20 lines` / `>2 levels` / `parameters >3`)不得漂移;含正例/负例对照(含阈值漂移变异)。**首次运行即抓到一处真实漂移**——`implementer-prompt.md` 写作 `**parameter count** >3`(markdown 加粗致锚点不匹配),与另两处措辞不一致,已统一。
|
|
90
|
+
|
|
91
|
+
**1209/1209 测试**(基线 1200,+9);`npm run lint:skills` 81 issues(其中 5 errors 均为存量行数超标,`clean-code` 0 error)。
|
|
92
|
+
|
|
7
93
|
## [0.57.0] - 2026-09-12
|
|
8
94
|
|
|
9
95
|
### Changed(复利机制 P1 重构;**含 4 项行为变更,升级必读**)
|
package/GEMINI.md
CHANGED
|
@@ -8,7 +8,7 @@ The workflow is self-contained and does not require OpenSpec or Superpowers at r
|
|
|
8
8
|
|
|
9
9
|
|
|
10
10
|
<!-- team-flow-phase-guard-start -->
|
|
11
|
-
# team-flow v0.
|
|
11
|
+
# team-flow v0.59.0 | 阶段: {{state}} | 工作流: {{workflow}}
|
|
12
12
|
当前阶段允许的操作由 workflow-start 路由规则定义。
|
|
13
13
|
禁止跨越 DP gate 进入下一阶段。变更范围以 execution-contract.md 的 Intent Lock 为准。
|
|
14
14
|
<!-- team-flow-phase-guard-end -->
|
package/HANDOFF.md
CHANGED
|
@@ -3,8 +3,8 @@
|
|
|
3
3
|
> ## ⚠️ 本文档已作废(2026-09-10 标注,v0.53.0)
|
|
4
4
|
>
|
|
5
5
|
> 最后更新停留在 **2026-07-28(v0.30.0 时代)**,此后未再维护。已知失准之处至少包括:
|
|
6
|
-
> skill/agent
|
|
7
|
-
>
|
|
6
|
+
> **skill/agent 计数——已完全失准,本文中的任何数字只代表 v0.30.0 时点,请以 `AGENTS.md` / `plugin.json` 为准**;
|
|
7
|
+
> closing 回写链顺序(此处 `arch-merge → prototype-sync`,实际 **`arch-merge → state transition closing → prototype-sync → test-merge`**,v0.53.0 §110 B' 时序前移)等。
|
|
8
8
|
>
|
|
9
9
|
> **权威来源**:`CLAUDE.md` / `AGENTS.md` / `README.md` / `../docs/architecture-api-db-design-enhancement-v0.25.md`。
|
|
10
10
|
> 本文档**仅作历史追溯**,**不得**据其执行流程——照旧顺序执行会触发 `arch-merged` 门禁拒绝(因回写未发生在状态转换之前)。
|
package/INSTALL.md
CHANGED
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
- [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec) — 规划引擎(Schema 验证、Delta Spec、工件解析)
|
|
8
8
|
- [obra/superpowers](https://github.com/obra/superpowers) — 执行纪律(TDD 铁律、SDD、系统化调试、代码审查)
|
|
9
9
|
|
|
10
|
-
当前发布版本:**v0.
|
|
10
|
+
当前发布版本:**v0.59.0**。
|
|
11
11
|
|
|
12
12
|
---
|
|
13
13
|
|
|
@@ -43,7 +43,7 @@
|
|
|
43
43
|
### 安装(推荐:Marketplace)
|
|
44
44
|
|
|
45
45
|
```bash
|
|
46
|
-
/plugin marketplace add http://
|
|
46
|
+
/plugin marketplace add http://172.25.254.5:10080/d40050-gtmc-ai/team-flow.git
|
|
47
47
|
/plugin install team-flow@team-flow
|
|
48
48
|
```
|
|
49
49
|
|
|
@@ -66,7 +66,7 @@
|
|
|
66
66
|
### 本地安装(开发 / 离线)
|
|
67
67
|
|
|
68
68
|
```bash
|
|
69
|
-
git clone http://
|
|
69
|
+
git clone http://172.25.254.5:10080/d40050-gtmc-ai/team-flow.git
|
|
70
70
|
|
|
71
71
|
# 在 Claude Code 中执行:
|
|
72
72
|
/plugin install file:/absolute/path/to/team-flow
|
|
@@ -339,7 +339,7 @@ rm -rf your-project/.agents/skills
|
|
|
339
339
|
|
|
340
340
|
## WorkBuddy
|
|
341
341
|
|
|
342
|
-
WorkBuddy 把 Skill 作为 marketplace 插件管理。安装器把 team-flow 部署为单个插件,包含
|
|
342
|
+
WorkBuddy 把 Skill 作为 marketplace 插件管理。安装器把 team-flow 部署为单个插件,包含 28 个 skill、运行时依赖(scripts/docs/templates/dist/hooks)、phase-guard 规则和 `.codebuddy-plugin/plugin.json` 清单,写入 `~/.workbuddy/plugins/marketplaces/<marketplace>/plugins/team-flow/`。
|
|
343
343
|
|
|
344
344
|
### 安装(推荐:一键脚本)
|
|
345
345
|
|
|
@@ -364,7 +364,7 @@ tf install-workbuddy --dry-run
|
|
|
364
364
|
```text
|
|
365
365
|
~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow/
|
|
366
366
|
├── .codebuddy-plugin/plugin.json ← 插件清单(name, version, skills[])
|
|
367
|
-
├── skills/ ←
|
|
367
|
+
├── skills/ ← 28 个 skill(${CLAUDE_PLUGIN_ROOT} 已重写)
|
|
368
368
|
├── rules/phase-guard.md ← phase-guard 规则(WorkBuddy 自动加载)
|
|
369
369
|
├── scripts/ docs/ templates/ ← 运行时依赖
|
|
370
370
|
├── dist/ hooks/
|
|
@@ -387,7 +387,7 @@ rm -rf ~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow
|
|
|
387
387
|
### 验证
|
|
388
388
|
|
|
389
389
|
```bash
|
|
390
|
-
ls ~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow/skills # 应有
|
|
390
|
+
ls ~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow/skills # 应有 28 个 skill 目录
|
|
391
391
|
cat ~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow/rules/phase-guard.md
|
|
392
392
|
cat ~/.workbuddy/plugins/marketplaces/cb_teams_marketplace/plugins/team-flow/.codebuddy-plugin/plugin.json
|
|
393
393
|
```
|
|
@@ -462,7 +462,7 @@ rm -rf .qoder/skills .qoder/team-flow .qoder/rules/phase-guard.md
|
|
|
462
462
|
### 验证
|
|
463
463
|
|
|
464
464
|
```bash
|
|
465
|
-
ls .qoder/skills # 应有
|
|
465
|
+
ls .qoder/skills # 应有 28 个 skill 目录
|
|
466
466
|
cat .qoder/rules/phase-guard.md
|
|
467
467
|
```
|
|
468
468
|
|
|
@@ -528,7 +528,7 @@ rm -rf .cline/skills .cline/team-flow .clinerules/phase-guard.md
|
|
|
528
528
|
### 验证
|
|
529
529
|
|
|
530
530
|
```bash
|
|
531
|
-
ls .cline/skills # 应有
|
|
531
|
+
ls .cline/skills # 应有 28 个 skill 目录
|
|
532
532
|
cat .clinerules/phase-guard.md
|
|
533
533
|
```
|
|
534
534
|
|
|
@@ -683,7 +683,7 @@ npx team-flow@latest install-pi
|
|
|
683
683
|
```bash
|
|
684
684
|
npx team-flow@latest install-pi
|
|
685
685
|
rm -rf .pi/skills .pi/team-flow
|
|
686
|
-
ls .pi/skills # 应有
|
|
686
|
+
ls .pi/skills # 应有 28 个 skill 目录
|
|
687
687
|
```
|
|
688
688
|
|
|
689
689
|
> Pi 无 phase-guard 规则自动注入,会话中请显式 `用 workflow-start 开始`。
|
|
@@ -794,7 +794,7 @@ Checkpoint 是任务级恢复上下文。`result-ready` handoff 在继续受影
|
|
|
794
794
|
安装后验证:
|
|
795
795
|
|
|
796
796
|
- `workflow-start` skill 已可用
|
|
797
|
-
- 其余
|
|
797
|
+
- 其余 27 个 skill 全部可见
|
|
798
798
|
|
|
799
799
|
## 故障排查
|
|
800
800
|
|
package/README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
# team-flow
|
|
2
2
|
|
|
3
|
-
> 当前版本:`v0.
|
|
3
|
+
> 当前版本:`v0.59.0`
|
|
4
4
|
|
|
5
|
-
> 统一插件:**team-flow**(spec 驱动开发)+ **compound-engineering 核心子集**(全局复利)+ **architecture-design**(4A+DDD 增量设计)+ **prototype**(本地 HTML 原型)+ **e2e**(AC 驱动 E2E)+ **workflow-orchestrator**(产品级编排)+ **workflow-bootstrap
|
|
5
|
+
> 统一插件:**team-flow**(spec 驱动开发)+ **compound-engineering 核心子集**(全局复利)+ **architecture-design**(4A+DDD 增量设计)+ **prototype**(本地 HTML 原型)+ **e2e**(AC 驱动 E2E)+ **workflow-orchestrator**(产品级编排)+ **workflow-bootstrap**(既有项目接入)。一次安装,十三套能力协同(详见下文「十三套能力」)。
|
|
6
6
|
|
|
7
7
|
## 30 秒上手
|
|
8
8
|
|
|
@@ -34,7 +34,7 @@
|
|
|
34
34
|
git clone <your-repo> && <cli> plugin install ./team-flow
|
|
35
35
|
```
|
|
36
36
|
|
|
37
|
-
> 不同宿主 CLI 的安装子命令略有差异(如 Claude Code 为 `/plugin add`,Cursor 为 `plugin install`)。以宿主文档为准;本插件提供单一 `plugin.json`,一次安装即加载全部
|
|
37
|
+
> 不同宿主 CLI 的安装子命令略有差异(如 Claude Code 为 `/plugin add`,Cursor 为 `plugin install`)。以宿主文档为准;本插件提供单一 `plugin.json`,一次安装即加载全部 28 个 skills。
|
|
38
38
|
|
|
39
39
|
## 配置(插件层扩展字段)
|
|
40
40
|
|
|
@@ -70,9 +70,9 @@ specs/<cap>/ 每变更规格:spec.md(learnings.md 归 change 根目
|
|
|
70
70
|
STRATEGY.md CONCEPTS.md 策略 / 领域词汇
|
|
71
71
|
```
|
|
72
72
|
|
|
73
|
-
##
|
|
73
|
+
## 十三套能力(28 skills)
|
|
74
74
|
|
|
75
|
-
- **team-flow**(
|
|
75
|
+
- **team-flow**(11):workflow-start / need-explorer / spec-writer / contract-builder / build-executor / code-reviewer / spec-merger / release-archivist / bug-investigator / test-strategy / clean-code
|
|
76
76
|
- **compound 核心子集**(6):ce-brainstorm / ce-plan / ce-compound / ce-strategy / ce-ideate / ce-proof
|
|
77
77
|
- **architecture-design**(1):architecture-design
|
|
78
78
|
- **prototype**(1):prototype
|
|
@@ -83,6 +83,8 @@ STRATEGY.md CONCEPTS.md 策略 / 领域词汇
|
|
|
83
83
|
- **工作流反馈**(1):workflow-feedback(工作流问题结构化记录,与 ce-compound 互补,v0.16.0)
|
|
84
84
|
- **设计系统**(1):design-system(独立创建/迭代项目级设计系统,用户主导交互,v0.19.0)
|
|
85
85
|
- **业务分析**(1):business-analysis(将任意输入整理为 requirement/vN/business-analysis.md,多轮单问澄清,独立外挂,v0.44.0)
|
|
86
|
+
- **项目初始化**(1):project-initialize(工作空间代码服务为空时的初始化引导:架构选择 → 服务命名 → 创建子目录 → 委托骨架,v0.45.0)
|
|
87
|
+
- **决策替身**(1):decision-surrogate(离席期间接管 team-flow 决策点:睡前逐点预授权 → 夜间经 Orca 派 worker → 裁决可代答点、其余 HOLD → 早上交付决策汇总;依赖个人偏好库与替身 home,**可选启用**,v0.59.0)
|
|
86
88
|
|
|
87
89
|
### 配套 agents(17 个,v0.47.0 增至 17)
|
|
88
90
|
|
|
@@ -95,8 +97,8 @@ Skills 命名保留其来源前缀,作为功能分组的自然标识:
|
|
|
95
97
|
| 前缀 | 来源 | 含义 | Skills |
|
|
96
98
|
|------|------|------|--------|
|
|
97
99
|
| `ce-` | compound-engineering | 产品级思维工具(头脑风暴、计划、策略、复利、创意、验证) | ce-brainstorm, ce-plan, ce-strategy, ce-compound, ce-ideate, ce-proof |
|
|
98
|
-
| 无前缀 | team-flow |
|
|
99
|
-
| 无前缀 | team-flow 新增 |
|
|
100
|
+
| 无前缀 | team-flow | 变更级开发流程工具(状态机、规格、构建、审查、归档、内部方法论) | workflow-start, need-explorer, spec-writer, contract-builder, build-executor, code-reviewer, spec-merger, release-archivist, bug-investigator, test-strategy, clean-code |
|
|
101
|
+
| 无前缀 | team-flow 新增 | 编排/接入/设计/原型/测试/交接/反馈/初始化 | workflow-orchestrator, workflow-bootstrap, architecture-design, prototype, e2e, session-handoff, workflow-feedback, design-system, project-initialize |
|
|
100
102
|
|
|
101
103
|
> `ce-` 前缀来自 compound-engineering 项目,team-flow 整合时保留了这一命名以维持功能分组的可辨识性。这不是命名不一致,而是有意的来源标注。
|
|
102
104
|
|
package/agents/code-reviewer.md
CHANGED
|
@@ -7,6 +7,7 @@ color: blue
|
|
|
7
7
|
tools: ["Read", "Grep", "Glob", "Bash", "Write"]
|
|
8
8
|
skills:
|
|
9
9
|
- code-reviewer
|
|
10
|
+
- clean-code
|
|
10
11
|
---
|
|
11
12
|
|
|
12
13
|
You are an independent Code Reviewer. You review code changes for quality, spec compliance, architecture soundness, and implementation completeness. You write the review report to disk and return a summary.
|
|
@@ -48,6 +49,8 @@ Your preloaded Skill defines severity levels (Critical / Important / Minor) and
|
|
|
48
49
|
- **PASS_WITH_WARNINGS**: No Critical, but Important findings exist
|
|
49
50
|
- **PASS**: No Critical or Important findings
|
|
50
51
|
|
|
52
|
+
**receipt 映射(v0.58.0)**:`tf execution review --verdict` 只接受 `pass | fail`。**PASS → `pass`**;**PASS_WITH_WARNINGS 与 FAIL 均 → `fail`** —— 即 **Important 亦须阻断**。理由:`PASS_WITH_WARNINGS` 在二值 receipt 中无法表达,且三个派发模板(`code-reviewer-prompt.md` / `task-reviewer-prompt.md`)与 `build-executor/SKILL.md` 均要求「Critical/Important findings require a `fail` receipt」。此前本节的「FAIL 仅 Critical」是四处口径中的唯一异类。
|
|
53
|
+
|
|
51
54
|
## Red Lines
|
|
52
55
|
|
|
53
56
|
**DO:**
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: cross-change-consistency-checker
|
|
3
|
-
description: 跨 change 冲突检测。在多 change 并行执行期或 change closing 时,检测共享聚合/实体被多个 change 修改、API 签名变更影响、与全局架构锚点漂移、与原型 testid
|
|
3
|
+
description: 跨 change 冲突检测。在多 change 并行执行期或 change closing 时,检测共享聚合/实体被多个 change 修改、API 签名变更影响、与全局架构锚点漂移、与原型 testid 契约漂移、以及同构横展完整性。直接写冲突报告文件,返回摘要 + 文件路径。
|
|
4
4
|
|
|
5
5
|
|
|
6
6
|
model: inherit
|
|
@@ -22,10 +22,11 @@ You are a checker. You did NOT implement any change. You read all change artifac
|
|
|
22
22
|
| `arch_path` | 全局架构目录(e.g., `docs/architecture/`,含 ARCHITECTURE.md / DATABASE.md) |
|
|
23
23
|
| `product_snapshot_path` | 产品级架构快照 `docs/architecture/iterations/vN/architecture.md`(v0.36.3;聚合注册表唯一事实源,若存在) |
|
|
24
24
|
| `prototype_path` | 全局原型目录(e.g., `prototype/`) |
|
|
25
|
+
| `repo_layout` | 仓库布局映射(v0.58.0,Dim 5 用)。来源:`<项目根>/.team-flow/team-flow.config.json` 的 `repo_layout.repos`(key = 仓路径,value = 描述)。多仓工作区才有;缺失时 Dim 5 跳过并注明 |
|
|
25
26
|
|
|
26
|
-
If `change_dirs` has fewer than 2 entries, Dim 1/2 are skipped (single change has no cross-change conflict). If `arch_path` or `prototype_path` is missing, the corresponding dimension is skipped with a note.
|
|
27
|
+
If `change_dirs` has fewer than 2 entries, Dim 1/2 are skipped (single change has no cross-change conflict). If `arch_path` or `prototype_path` is missing, the corresponding dimension is skipped with a note. Dim 5 requires `repo_layout`.
|
|
27
28
|
|
|
28
|
-
##
|
|
29
|
+
## 5-Dimension Detection
|
|
29
30
|
|
|
30
31
|
### Dimension 1: Shared Aggregate/Entity Mutation
|
|
31
32
|
|
|
@@ -77,6 +78,23 @@ Use `grep` to search for API references across change specs and design docs.
|
|
|
77
78
|
- Change adds UI elements that should have testids per prototype pattern but don't → Minor
|
|
78
79
|
- testid value mismatch between prototype and implementation → Important
|
|
79
80
|
|
|
81
|
+
### Dimension 5: Isomorphic Propagation Completeness (v0.58.0)
|
|
82
|
+
|
|
83
|
+
**Goal**: Detect when a code pattern handled by this change is **not** handled at all of its occurrences — the failure mode where a defect fix is applied to some isomorphic locations but not others.
|
|
84
|
+
|
|
85
|
+
**Why pattern-driven, not repo-name-driven**: isomorphic repos can be recognized by name similarity (longest common prefix + suffix ≥60%, e.g. `bff-emp-` + `users`/`clients` + `identification`), BUT real gaps are often **cross-group** — a v1 case had 4 isomorphic repos split across `bff-emp-*` and `adapter-emp-*`, and the gap lay *between* the groups. Group-based checking would have missed it. Scan by **pattern**, not by repo group.
|
|
86
|
+
|
|
87
|
+
1. **Extract pattern features** from the change's diff: the named structural elements deleted or modified — annotation + constant reference (e.g. `@Cacheable(cacheNames = BO_SYSUSER_USERID)`), method signature, constant name. The pattern MUST contain a named symbol; generic patterns ("all `if` statements") are invalid and MUST be rejected.
|
|
88
|
+
2. **Scan all repos**: `grep` over EVERY repo listed in `repo_layout.repos` (not just isomorphic groups).
|
|
89
|
+
3. **Difference set**: hits NOT within this change's disposition scope = omission candidates. Cite `file:line` for each.
|
|
90
|
+
4. **Reachability grading**:
|
|
91
|
+
- Omission has call sites (reachable) → **Important**
|
|
92
|
+
- Zero call sites (unreachable) → **Minor** (preventive alignment, optional)
|
|
93
|
+
|
|
94
|
+
**Vacuum control (MANDATORY — prevents a vacuous assertion)**: if step 2 yields **zero hits**, do NOT silently report CLEAN. Explicitly report `模式未命中:<pattern> 在全部仓中零出现,需人工确认模式提取是否正确`. Rationale: zero hits cannot distinguish "no omission exists" from "pattern extraction failed" — calling it CLEAN would be a vacuous assertion.
|
|
95
|
+
|
|
96
|
+
**Activation**: only for changes whose nature is defect-fix / rule-alignment / isomorphic sync. Pure new-feature development has no pre-existing pattern to propagate — skip Dim 5 and note the skip.
|
|
97
|
+
|
|
80
98
|
## Detection Process
|
|
81
99
|
|
|
82
100
|
1. **Enumerate changes**: read each change directory's spec/design/tasks files
|
|
@@ -84,7 +102,8 @@ Use `grep` to search for API references across change specs and design docs.
|
|
|
84
102
|
3. **Dim 2**: Extract API surface changes per change, cross-reference dependencies
|
|
85
103
|
4. **Dim 3**: Read architecture anchors **+ 产品级快照聚合注册表**(`product_snapshot_path`,v0.36.3——聚合注册表是唯一事实源,跨 change 冲突检测以它为准),compare each change against them
|
|
86
104
|
5. **Dim 4**: Scan prototype testids, compare against change implementations
|
|
87
|
-
6. **
|
|
105
|
+
6. **Dim 5**: Extract named pattern features from each change's diff, scan EVERY repo in `repo_layout.repos`, compute the difference set, grade by reachability — and apply the vacuum control when the scan yields zero hits
|
|
106
|
+
7. **Aggregate**: collect all findings, grade by severity, produce report
|
|
88
107
|
|
|
89
108
|
## Judgment Criteria
|
|
90
109
|
|
|
@@ -141,6 +160,15 @@ Use `grep` to search for API references across change specs and design docs.
|
|
|
141
160
|
|--------|-------------------|--------|-------|----------|
|
|
142
161
|
| `order-submit-btn` | prototype/order.html:23 | change-1 | Renamed to `submit-order` | Important |
|
|
143
162
|
|
|
163
|
+
## Dim 5: Isomorphic Propagation Completeness
|
|
164
|
+
|
|
165
|
+
| Pattern Feature | Handled In | Omitted At | Reachable | Severity |
|
|
166
|
+
|-----------------|-----------|-----------|-----------|----------|
|
|
167
|
+
| `@Cacheable(cacheNames = BO_SYSUSER_USERID)` return-type mismatch | `bff-…users:47`, `bff-…clients:47` | `adapter-…users:47`, `adapter-…clients:47` | No (0 call sites) | Minor |
|
|
168
|
+
|
|
169
|
+
> Vacuum control: when the repo-wide scan for a pattern yields **zero hits**, write instead —
|
|
170
|
+
> `模式未命中:<pattern> 在全部仓中零出现,需人工确认模式提取是否正确`(不得记为 CLEAN)
|
|
171
|
+
|
|
144
172
|
## Conflict Summary & Suggested Resolution
|
|
145
173
|
|
|
146
174
|
| # | Dim | Changes | Location | Severity | Suggested Resolution |
|
|
@@ -160,7 +188,7 @@ If no conflicts are found, output:
|
|
|
160
188
|
```markdown
|
|
161
189
|
## Result: CLEAN
|
|
162
190
|
|
|
163
|
-
All
|
|
191
|
+
All 5 dimensions checked. No cross-change conflicts detected.
|
|
164
192
|
```
|
|
165
193
|
|
|
166
194
|
## Red Lines
|
|
@@ -174,7 +202,7 @@ All 4 dimensions checked. No cross-change conflicts detected.
|
|
|
174
202
|
|
|
175
203
|
**DON'T:**
|
|
176
204
|
- Modify any change's files — only write the conflict report
|
|
177
|
-
- Report single-change issues as cross-change conflicts (use code-reviewer for that)
|
|
205
|
+
- Report single-change issues as cross-change conflicts (use code-reviewer for that) — **EXCEPTION**: a single change's **cross-repo isomorphic omission** IS in scope (Dim 5). The distinction is repo span: cross-repo → Dim 5; single-repo code quality → code-reviewer
|
|
178
206
|
- Flag shared read-only references as conflicts (two changes READING the same file is fine)
|
|
179
207
|
- Ignore architecture drift because "arch-merge will handle it later" — report it, let the orchestrator decide
|
|
180
208
|
- Fabricate conflicts from vague similarity — require concrete file/symbol evidence
|
|
@@ -47,6 +47,12 @@ writebacks:
|
|
|
47
47
|
summary: "..." # closing summary + any WARNs needing user acceptance
|
|
48
48
|
```
|
|
49
49
|
|
|
50
|
+
## Structural Criteria Coverage Note (v0.58.0)
|
|
51
|
+
|
|
52
|
+
closing 时检查本 change 是否覆盖了结构判据(clean-code):若该 change 走 `glaf4-delegation` 且 `execution-contract.md` 的 `## GLAF4 Delegation` 段**未**包含结构质量验收条款,须在 closing 报告中显式标注「本 change 结构判据未覆盖」。
|
|
53
|
+
|
|
54
|
+
依据:glaf4-dev 的 `production-writer` 只按 `knowledge` 清单读取规范(`resolve-context.mjs` 无项目侧注入通道),故 clean-code 判据无法进入其实施层;审查层仍有效(`glaf4-delegation.md` 明确由 team-flow code-reviewer 审查 base..head),但若契约未声明该条款,审查者亦无据可依。
|
|
55
|
+
|
|
50
56
|
## Red Lines
|
|
51
57
|
|
|
52
58
|
**DO:**
|
package/docs/README_en.md
CHANGED
|
@@ -126,7 +126,7 @@ npm install -g team-flow
|
|
|
126
126
|
|
|
127
127
|
### Version
|
|
128
128
|
|
|
129
|
-
- Current: `v0.
|
|
129
|
+
- Current: `v0.59.0`
|
|
130
130
|
- v0.9.1 highlights: DP-4 execution-mode recommendations, a portable runtime across 17 platforms, and a raw-package smoke with no plugin-root variable.
|
|
131
131
|
- Self-contained — no OpenSpec or Superpowers runtime required
|
|
132
132
|
- Upstream: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec), [obra/superpowers](https://github.com/obra/superpowers)
|
package/docs/platform-matrix.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
team-flow 共支持 **18 个** AI 编程平台。每个平台按三层接入:
|
|
4
4
|
|
|
5
|
-
- **Skills** —
|
|
5
|
+
- **Skills** — 28 个 skill 部署到平台技能目录(`${CLAUDE_PLUGIN_ROOT}` 重写为绝对路径)。
|
|
6
6
|
- **Rules** — phase-guard 规则文件部署到平台规则目录,被平台自动加载为常驻上下文(守卫机制)。
|
|
7
7
|
- **Hooks** — SessionStart 上下文注入钩子(仅在该平台原生支持且已验证时接入)。
|
|
8
8
|
|