@xulthekl/team-flow 0.37.0 → 0.39.0
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 +1 -1
- package/.claude-plugin/plugin.json +1 -1
- package/.codex-plugin/plugin.json +1 -1
- package/.cursor-plugin/marketplace.json +1 -1
- package/.cursor-plugin/plugin.json +1 -1
- package/.github/plugin/marketplace.json +2 -2
- package/CHANGELOG.md +39 -0
- package/GEMINI.md +1 -1
- package/INSTALL.md +1 -1
- package/README.md +1 -1
- package/agents/architecture-reviewer.md +16 -6
- package/agents/change-split-auditor.md +11 -6
- package/agents/code-reviewer.md +7 -6
- package/agents/cross-change-consistency-checker.md +11 -6
- package/agents/prd-completeness-reviewer.md +11 -6
- package/agents/prototype-reviewer.md +11 -6
- package/docs/README_en.md +1 -1
- package/docs/solutions/INDEX.md +1 -0
- package/docs/solutions/cross-phase/2026-08-06-no-summary.md +17 -0
- package/gemini-extension.json +1 -1
- package/hooks/session-start +2 -2
- package/llms.txt +1 -1
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/scripts/lib/test-matrix-export.mjs +5 -0
- package/scripts/lib/test-merge.mjs +130 -93
- package/skills/build-executor/implementer-prompt.md +3 -1
- package/skills/ce-brainstorm/references/prototype-loop.md +2 -2
- package/skills/code-reviewer/SKILL.md +4 -3
- package/skills/code-reviewer/code-reviewer-prompt.md +2 -2
- package/skills/contract-builder/SKILL.md +6 -4
- package/skills/prototype/SKILL.md +3 -3
- package/skills/prototype/references/orchestration-flow.md +2 -2
- package/skills/release-archivist/SKILL.md +16 -6
- package/skills/spec-writer/SKILL.md +1 -1
- package/skills/test-strategy/SKILL.md +2 -1
- package/skills/test-strategy/references/design-methods-detail.md +1 -0
- package/skills/test-strategy/references/test-quality-rules.md +1 -0
- package/skills/workflow-feedback/SKILL.md +10 -0
- package/skills/workflow-feedback/references/feedback-template.md +7 -1
- package/skills/workflow-orchestrator/references/s2-prd-prototype-loop.md +2 -2
- package/skills/workflow-start/SKILL.md +1 -1
|
@@ -84,6 +84,16 @@ argument-hint: "[问题简述] [--category <分类>] [--severity <P0-P3>]"
|
|
|
84
84
|
- 涉及的 skill / agent / CLI 命令
|
|
85
85
|
- 涉及的产物路径
|
|
86
86
|
|
|
87
|
+
**环境版本采集**(写入 feedback frontmatter 的 `environment` 字段):
|
|
88
|
+
|
|
89
|
+
| 字段 | 采集命令 | 说明 |
|
|
90
|
+
|------|---------|------|
|
|
91
|
+
| `plugin_version` | `cat team-flow/package.json \| grep '"version"' \| head -1` | team-flow 插件版本 |
|
|
92
|
+
| `node_version` | `node -v` | Node.js 运行时版本 |
|
|
93
|
+
| `npm_version` | `npm -v` | npm 版本 |
|
|
94
|
+
| `platform` | `uname -s \| tr '[:upper:]' '[:lower:]'` | 操作系统平台 |
|
|
95
|
+
| `shell` | `basename "$SHELL"` | 当前 shell |
|
|
96
|
+
|
|
87
97
|
### Step 3:结构化记录
|
|
88
98
|
|
|
89
99
|
按 `references/feedback-template.md` 格式输出:
|
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
```yaml
|
|
9
9
|
---
|
|
10
10
|
type: workflow-feedback
|
|
11
|
-
version:
|
|
11
|
+
version: 2
|
|
12
12
|
created_at: <ISO 8601>
|
|
13
13
|
category: <skill-trigger | sop-flow | artifact-quality | state-management | agent-quality | cli-command | ux-interaction | performance | cross-platform | documentation>
|
|
14
14
|
severity: <P0 | P1 | P2 | P3>
|
|
@@ -16,6 +16,12 @@ status: open
|
|
|
16
16
|
related_skill: <skill-name | null>
|
|
17
17
|
related_phase: <S1-S5 | change-level | null>
|
|
18
18
|
related_requirement: <req-id | null>
|
|
19
|
+
environment:
|
|
20
|
+
plugin_version: <team-flow 插件版本>
|
|
21
|
+
node_version: <Node.js 版本>
|
|
22
|
+
npm_version: <npm 版本>
|
|
23
|
+
platform: <darwin | linux | win32>
|
|
24
|
+
shell: <zsh | bash | powershell>
|
|
19
25
|
---
|
|
20
26
|
```
|
|
21
27
|
|
|
@@ -106,8 +106,8 @@ tf solutions capture --phase prd --domain <domain> --type pitfall --severity <se
|
|
|
106
106
|
|
|
107
107
|
## 原型自动评审(§17.10)
|
|
108
108
|
|
|
109
|
-
**实现形式**:独立 `prototype-reviewer` agent
|
|
110
|
-
- tools: Read, Bash, Grep, Glob
|
|
109
|
+
**实现形式**:独立 `prototype-reviewer` agent(对齐 code-reviewer 模式)。
|
|
110
|
+
- tools: Read, Bash, Grep, Glob, Write(直接写审查报告文件)
|
|
111
111
|
- 独立上下文运行,未参与 PRD/原型产出(规避锚定效应)
|
|
112
112
|
- 两阶段检查:Pre-check(Bash 结构化预检,D1/D4 机械化)+ Deep-check(LLM 六维度语义对比,D2/D3/D5/D6 标注为「建议级,误报可被人工推翻」)
|
|
113
113
|
|
|
@@ -78,7 +78,7 @@ Guard: `arch_design_decision` in `.team-flow.yaml` is `null` → must run before
|
|
|
78
78
|
> **⛔ 串行约束(v0.30.0)**:四步严格串行。**修复子代理(architecture-design)完成前 MUST NOT dispatch 审查子代理(architecture-reviewer)**——并行会使审查跑在修复之前、误报"全部未修复"FAIL(来源:workflow-feedback 2026-08-01)。并行白名单:仅多个独立 change 的工作可并行;修复→审查、设计→审查必须串行。
|
|
79
79
|
|
|
80
80
|
1. **Dispatch**: `architecture-design` as sub-agent(**输入含 `docs/architecture/iterations/<vN>/architecture.md` 产品级架构快照**,v0.36.0——变更级只引用产品级聚合注册表,不重定义)→ returns `decision` + `reason` + `artifacts`。**⛔ 记录子代理 ID**(后续循环修正和 DP-A 调整必须通过此 ID 恢复,禁止启动新子代理)
|
|
81
|
-
2. **Auto-review** (decision=required 时触发): 校验产物文件存在且非空 → dispatch `architecture-reviewer` sub-agent(**记录子代理 ID
|
|
81
|
+
2. **Auto-review** (decision=required 时触发): 校验产物文件存在且非空 → dispatch `architecture-reviewer` sub-agent(**记录子代理 ID**,agent 会直接写审查报告到 `changes/<name>/architecture/auto-review.md`)→ FAIL 则通过 **SendMessage 恢复原 architecture-design 子代理**修正(≤3 轮 + 收敛检测,不收敛转人工)
|
|
82
82
|
3. **Reasonableness check + state write**: PASS/PASS_WITH_WARNINGS → write `arch_design_decision` + `arch_review_*` to yaml; skipped + brief 含架构关键词 → BLOCK; required + artifacts 缺失 → BLOCK; required + auto-review FAIL → BLOCK
|
|
83
83
|
4. **DP-A 用户确认门(v0.29.0 §37)**: 输出架构决策摘要 → AskUserQuestion 确认 → 需要调整时**必须通过 SendMessage 恢复原子代理**修改(禁止主代理直接修改,禁止启动新子代理)→ 修改后 SendMessage 恢复原 reviewer 重新 auto-review → 回到本步骤重新确认。含项目规范变更提示(advisory)。详见 `references/routing-rules.md`「Step 4: DP-A」
|
|
84
84
|
|