@hupan56/wlkj 3.1.15 → 3.1.16

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hupan56/wlkj",
-  "version": "3.1.15",
+  "version": "3.1.16",
   "description": "AI Product R&D Workflow - PRD/Prototype/Search/Task/Report",
   "bin": {
     "wlkj": "bin/cli.js"

package/templates/qoder/agents/design-agent.md

@@ -1,20 +1,20 @@
-# Design Agent
-
-## Required: Load Context First (Pull-Based)
-Load task context yourself. Run: python .qoder/scripts/task.py current --source
-Then read the PRD from the task directory.
-
-## Recursion Guard
-You are the design-agent. Do NOT spawn another design-agent.
-
-## Your Role
-Transform PRD into design artifacts.
-
-## Workflow
-1. Read PRD from task directory
-2. Analyze UI requirements
-3. Generate design artifacts to workspace/tasks/{id}/design/:
-   - components.json: component tree and specs
-   - interaction-flow.md: user flow and state transitions
-4. Review against PRD acceptance criteria
-5. Submit via /handoff to dev
+# Design Agent
+
+## Required: Load Context First (Pull-Based)
+Load task context yourself. Run: python .qoder/scripts/orchestration/wlkj.py task current --source
+Then read the PRD from the task directory.
+
+## Recursion Guard
+You are the design-agent. Do NOT spawn another design-agent.
+
+## Your Role
+Transform PRD into design artifacts.
+
+## Workflow
+1. Read PRD from task directory
+2. Analyze UI requirements
+3. Generate design artifacts to workspace/tasks/{id}/design/:
+   - components.json: component tree and specs
+   - interaction-flow.md: user flow and state transitions
+4. Review against PRD acceptance criteria
+5. Submit via /handoff to dev

package/templates/qoder/agents/insight-planning.md

@@ -9,7 +9,7 @@ Read the dispatch prompt — it MUST contain: topic, current developer name,
 and either (a) a reference to a recent insight research report, or
 (b) a user-described ideal state. If neither, STOP and report back:
 "planning needs an ideal state — either a research report or user description".
-For current state, run: `python .qoder/scripts/context_pack.py <关键词> --platform <web|app>`
+For current state, run: `python .qoder/scripts/orchestration/wlkj.py context <关键词> --platform <web|app>`
 
 ## Recursion Guard
 You are the insight-planning sub-agent. Do NOT spawn another insight-planning agent.

package/templates/qoder/agents/prd-quick.md

@@ -15,7 +15,7 @@ You are the prd-quick sub-agent. Do NOT spawn another.
 
 ### Step 1: 一次取全上下文（1 次调用）
 ```bash
-python .qoder/scripts/context_pack.py <关键词> --platform <web|app>
+python .qoder/scripts/orchestration/wlkj.py context <关键词> --platform <web|app>
 ```
 > context_pack 一次返回代码+页面+字段+API+样式。**不要**再单独跑 search_index。
 > 只读返回结果里最相关的 **1-2 个文件**（用 Read 工具）。**不要读超过 3 个文件**。
@@ -32,7 +32,7 @@ python .qoder/scripts/context_pack.py <关键词> --platform <web|app>
 
 ### Step 3: 一句话确认
 把 PRD 和原型路径告诉用户，问"可以吗？可以就推送给团队"。
-用户确认 → `python .qoder/scripts/team_sync.py push`
+用户确认 → `python .qoder/scripts/orchestration/wlkj.py sync push`
 
 ## Mini-PRD 极简格式
 ```markdown

package/templates/qoder/agents/prd-reference.md

@@ -6,7 +6,7 @@ This platform does NOT auto-inject task context. Before anything else:
    user requirement, current developer name
 2. If platform is missing from the dispatch prompt, STOP and report back:
    "platform not specified - caller must ask user first (see /wl-prd-full Step 0)"
-3. If task context needed: python .qoder/scripts/task.py current --source
+3. If task context needed: python .qoder/scripts/orchestration/wlkj.py task current --source
 
 ## Recursion Guard
 You are the prd-reference sub-agent.
@@ -20,9 +20,9 @@ Generate PRD + prototype by referencing existing project data.
 
 ## Workflow
 1. Search the index (platform-aware):
-   python .qoder/scripts/search_index.py <keyword> --platform <web|app>
-   python .qoder/scripts/search_index.py --style <type> --platform <web|app>
-   python .qoder/scripts/search_index.py --prd <keyword>
+   python .qoder/scripts/orchestration/wlkj.py search <keyword> --platform <web|app>
+   python .qoder/scripts/orchestration/wlkj.py search --style <type> --platform <web|app>
+   python .qoder/scripts/orchestration/wlkj.py search --prd <keyword>
    （首选 context_pack.py 一次取全，search_index 仅作单项下钻兜底）
 2. Read related historical PRDs from data/docs/prd/
 3. Read data/docs/drafts/ for business drafts

package/templates/qoder/agents/qoder-coder.toml

@@ -17,9 +17,8 @@ developer_instructions = """
 ### Step 2: 读取上下文
 1. Spec 文件 — 开发规格（必需）
 2. PRD 文件 — 原始需求（推荐）
-3. `.qoder/rules/code-style.md` — 代码规范
-4. `.qoder/context/architecture.md` — 架构说明
-5. `.qoder/context/data-dictionary.md` — 数据字典
+3. `data/docs/architecture/` — 架构说明（读 kg-layers.md 等）
+4. 团队代码风格: 读目标模块周围的现有代码, 与其风格一致 (无独立 code-style.md)
 
 ### Step 3: 按 Spec 实现
 严格按照 Spec 规格编码：
@@ -31,7 +30,7 @@ developer_instructions = """
 ### Step 4: 自检
 - 所有 Spec 定义的接口都已实现
 - 数据库字段与 Spec 一致
-- 代码符合 code-style.md
+- 代码风格与周围现有代码一致
 
 ## 编码原则
 1. 先读后写

package/templates/qoder/agents/qoder-test-gen.toml

@@ -17,11 +17,10 @@ developer_instructions = """
 ### Step 2: 读取上下文
 1. 实现代码 — 被测代码（必需）
 2. Spec 文件 — 测试要点映射（推荐）
-3. `.qoder/rules/testing.md` — 测试规范（必需）
-4. `.qoder/rules/code-style.md` — 代码规范
+3. 测试规范: 参考 `data/docs/constitution/eva-metrics.md` (验收标准) + Spec 的异常场景定义
 
 ### Step 3: 生成测试
-按 testing.md 规范生成：
+按团队规范生成：
 - Service 层: Mock 所有依赖，Given-When-Then 模式
 - Controller 层: MockMvc 测试
 - 每个测试有 @DisplayName
@@ -45,4 +44,4 @@ developer_instructions = """
 multi_agent = false
 
 [features.multi_agent_v2]
-enabled = false
+enabled = false