principles-disciple 1.80.0 → 1.82.0

package/templates/langs/en/skills/pd-mentor/SKILL.md

@@ -25,16 +25,13 @@ I'm your intelligent mentor, helping you understand and use all features of Prin
 
 | Command | Purpose | Use Case |
 |---------|---------|----------|
-| `/pd-init` | Initialize strategy and OKRs | New project startup |
-| `/pd-okr` | Objectives and Key Results management | Weekly/monthly review |
+| `/pd-init` | Initialize strategy | New project startup |
 | `/pd-bootstrap` | Environment tool scan and upgrade | Tool upgrade |
 | `/pd-research` | Initiate tool upgrade research | Deep research |
 | `/pd-thinking` | Manage mental models and candidates | Metacognition |
 | `/pd-evolve` | Execute full evolution loop | Bug fix |
-| `/pd-daily` | Configure and send evolution daily report | Daily review |
 | `/pd-evolution-status` | View trust score and security stage | Permission check |
 | `/pd-status` | View system status (GFI and Pain Dictionary) | Health check |
-| `/pd-grooming` | Workspace digital cleanup | Entropy reduction |
 | `/pd-help` | Get interactive command guidance | This skill |
 
 ---
@@ -46,7 +43,7 @@ I'm your intelligent mentor, helping you understand and use all features of Prin
 **Trigger**: User says "I just created a new project" or similar
 
 **Recommended Flow**:
-1. `/pd-init` - Establish strategic vision and OKR framework
+1. `/pd-init` - Establish strategic vision
 2. `/pd-bootstrap` - Scan environment tools, get capability list
 3. `/pd-thinking` - Establish project's mental model baseline
 
@@ -71,26 +68,14 @@ I'm your intelligent mentor, helping you understand and use all features of Prin
 **Trigger**: User says "what did I do today", "check progress", "give me a report"
 
 **Recommended Flow**:
-1. `/pd-daily` - Send today's evolution report
-2. `/pd-evolution-status` - View current trust score
-3. `/pd-okr` - Check OKR alignment
+1. `/pd-evolution-status` - View current trust score
+2. `/pd-status` - Check GFI and Pain Dictionary status
 
-**Script**: "Daily report in hand, evolution I command. Let me help you review today's achievements."
+**Script**: "Let me help you review the current system status."
 
 ---
 
-### Scenario 4: Messy Workspace
-
-**Trigger**: User says "project is too messy", "too many files", "need to organize"
-
-**Recommended Flow**:
-1. `/pd-grooming` - Start workspace cleanup
-
-**Script**: "Digital cleanliness is a virtue. Let me help you reduce entropy."
-
----
-
-### Scenario 5: Permission or Security Related
+### Scenario 4: Permission or Security Related
 
 **Trigger**: User says "not enough permissions", "blocked", "security level"
 
@@ -186,8 +171,8 @@ For complex scenarios, combine multiple skills:
 | Scenario | Combined Flow |
 |----------|---------------|
 | Major refactor | `/pd-evolve` → `deductive-audit` → execute |
-| System optimization | `/pd-status` → `evolve-system` → `root-cause` |
-| Project review | `/pd-daily` → `/pd-okr` → `reflection-log` |
+| System optimization | `/pd-status` → `root-cause` → optimize |
+| Project review | `/pd-evolution-status` → `/pd-status` → `reflection-log` |
 
 ### Internal Skill Calls
 

package/templates/langs/zh/core/BOOTSTRAP.md

@@ -162,20 +162,7 @@ memory/
 
 如果用户同意，**执行以下命令：**
 
-### 1. 熵减巡检（每天凌晨 2 点）
-
-**功能：** 每天清理工作区临时文件，保持项目整洁。
-
-```bash
-openclaw cron add --name "pd-grooming-daily" \
-  --cron "0 2 * * *" --tz "UTC" \
-  --session isolated \
-  --light-context \
-  --no-deliver \
-  --message '执行 pd-grooming 技能：检查工作区根目录，清理临时文件和数字垃圾。严格遵循安全红线，不要删除业务代码。'
-```
-
-### 2. 环境健康检查（每 4 小时）
+### 1. 环境健康检查（每 4 小时）
 
 **功能：** 验证核心工具（rg, node, python）是否可用，异常时告警。
 
@@ -220,7 +207,7 @@ openclaw cron add --name "weekly-governance" \
   --cron "0 0 * * 0" --tz "UTC" \
   --session isolated \
   --timeout 300000 \
-  --message '执行周治理：1) 验证 CURRENT_FOCUS.md 声称（PR 合并？文档存在？测试通过？），2) 更新 WEEK_STATE.json 指标，3) 记录到 WEEK_EVENTS.jsonl，4) 如果任务队列为空，从 OKR 推导任务并通知用户'
+  --message '执行周治理：1) 验证 CURRENT_FOCUS.md 声称（PR 合并？文档存在？测试通过？），2) 更新 WEEK_STATE.json 指标，3) 记录到 WEEK_EVENTS.jsonl，4) 如果任务队列为空，提醒用户规划下一阶段任务'
 ```
 
 **JSON 配置参考：**

package/templates/langs/zh/skills/bootstrap-tools/SKILL.md

@@ -46,7 +46,7 @@ disable-model-invocation: true
             ## Environment Capabilities
             Check @.state/SYSTEM_CAPABILITIES.json for high-performance tools (e.g., ripgrep, ast-grep) available in this environment. Use them!
             ```
-          - 提示用户运行 `/manage-okr` 或 `/admin diagnose` 以让 Agent 感知新能力。
+          - 提示用户运行 `/pd-status` 或 `/admin diagnose` 以让 Agent 感知新能力。
 ## 核心原则
 - **喜新厌旧**: 敢于推荐新工具替代旧工具（如推荐 `pnpm` 替 `npm`，推荐 `vitest` 替 `jest`），但要说明理由。
 - **安全第一**: 在安装前必须获得用户明确授权。

package/templates/langs/zh/skills/init-strategy/SKILL.md

@@ -51,4 +51,4 @@ disable-model-invocation: true
 ```
 
 ## 结项
-完成写入后，提示用户：“✅ 战略锚点已锁定。建议运行 `/manage-okr` 进行季度/迭代级的任务拆解。”
+完成写入后，提示用户：”✅ 战略锚点已锁定。建议运行 `/pd-status` 查看系统状态，或使用 `/pd-bootstrap` 扫描环境工具。”

package/templates/langs/zh/skills/pd-mentor/SKILL.md

@@ -25,16 +25,13 @@ disable-model-invocation: true
 
 | 命令 | 用途 | 适用场景 |
 |------|------|----------|
-| `/pd-init` | 初始化战略与OKR | 新项目启动 |
-| `/pd-okr` | 目标与关键结果管理 | 周/月度复盘 |
+| `/pd-init` | 初始化战略 | 新项目启动 |
 | `/pd-bootstrap` | 环境工具扫描与升级 | 装备升级 |
 | `/pd-research` | 发起工具升级研究 | 深度调研 |
 | `/pd-thinking` | 管理思维模型与候选方案 | 元认知管理 |
 | `/pd-evolve` | 执行完整进化循环 | 问题修复 |
-| `/pd-daily` | 配置并发送进化日报 | 日常查看 |
 | `/pd-evolution-status` | 查看EP等级与安全状态 | 状态查询 |
 | `/pd-status` | 查看系统状态（GFI和痛苦词典） | 健康检查 |
-| `/pd-grooming` | 工作区数字大扫除 | 熵减维护 |
 | `/pd-help` | 获取交互式命令引导 | 本技能 |
 
 ---
@@ -71,26 +68,14 @@ disable-model-invocation: true
 **触发条件**: 用户说"今天干了什么"、"看看进度"、"汇报一下"
 
 **推荐流程**:
-1. `/pd-daily` - 发送今日进化日报
-2. `/pd-evolution-status` - 查看当前信任积分
-3. `/pd-okr` - 检查 OKR 对齐情况
+1. `/pd-evolution-status` - 查看当前信任积分
+2. `/pd-status` - 查看 GFI 和痛苦词典状态
 
-**话术**: "日报在手，进化我有。让我帮你回顾今天的成果。"
+**话术**: "让我帮你回顾一下系统状态。"
 
 ---
 
-### 场景 4: 工作区太乱
-
-**触发条件**: 用户说"项目太乱了"、"文件一堆"、"需要整理"
-
-**推荐流程**:
-1. `/pd-grooming` - 启动工作区大扫除
-
-**话术**: "数字洁癖是一种美德。让我帮你熵减。"
-
----
-
-### 场景 5: 权限或安全相关
+### 场景 4: 权限或安全相关
 
 **触发条件**: 用户说"权限不够"、"被拦截了"、"安全等级"
 
@@ -186,8 +171,8 @@ disable-model-invocation: true
 | 场景 | 组合流程 |
 |------|----------|
 | 大型重构 | `/pd-evolve` → `deductive-audit` → 执行 |
-| 系统优化 | `/pd-status` → `evolve-system` → `root-cause` |
-| 项目复盘 | `/pd-daily` → `/pd-okr` → `reflection-log` |
+| 系统优化 | `/pd-status` → `root-cause` → 优化实施 |
+| 项目复盘 | `/pd-evolution-status` → `/pd-status` → `reflection-log` |
 
 ### 内部技能调用
 

package/tests/commands/strategy.test.ts

@@ -1,9 +1,9 @@
 import { describe, it, expect } from 'vitest';
-import { handleInitStrategy, handleManageOkr } from '../../src/commands/strategy';
+import { handleInitStrategy } from '../../src/commands/strategy';
 
 describe('Slash Commands Hook', () => {
   it('should handle /init-strategy command', () => {
-    const mockCtx = { 
+    const mockCtx = {
         workspaceDir: '/mock/workspace',
         commandBody: '/init-strategy',
         channel: 'cli',
@@ -16,19 +16,4 @@ describe('Slash Commands Hook', () => {
     expect(result).toBeDefined();
     expect(result.text).toContain('Strategy Initialization');
   });
-
-  it('should handle /manage-okr command', () => {
-    const mockCtx = { 
-        workspaceDir: '/mock/workspace',
-        commandBody: '/manage-okr',
-        channel: 'cli',
-        isAuthorizedSender: true,
-        config: {} as any
-    };
-
-    const result = handleManageOkr(mockCtx as any);
-
-    expect(result).toBeDefined();
-    expect(result.text).toContain('OKR Management');
-  });
-});
+});

package/tests/service/correction-observer-service.test.ts

@@ -0,0 +1,331 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+import { WorkspaceContext } from '../../src/core/workspace-context.js';
+
+const mockLearner = {
+  getStore: vi.fn(() => ({ keywords: [{ term: 'wrong', weight: 0.5, hitCount: 3, truePositiveCount: 1, falsePositiveCount: 2 }] })),
+};
+
+const mockDb = {
+  listRecentSessions: vi.fn(() => [{ sessionId: 'session-1' }]),
+  listUserTurnsForSession: vi.fn(() => [{ rawExcerpt: 'User said wrong input', correctionDetected: true, correctionCue: 'wrong' }]),
+};
+
+const mockOptimizationService = {
+  buildTrajectoryHistory: vi.fn(async () => [
+    { sessionId: 'session-1', timestamp: 'now', term: 'wrong', userMessage: '' }
+  ]),
+  applyResult: vi.fn(),
+};
+
+vi.mock('../../src/core/correction-cue-learner.js', () => ({
+  CorrectionCueLearner: { get: vi.fn(() => mockLearner) },
+}));
+
+vi.mock('../../src/core/trajectory.js', () => ({
+  TrajectoryRegistry: {
+    get: vi.fn(() => mockDb),
+    clear: vi.fn(),
+  },
+}));
+
+vi.mock('../../src/service/keyword-optimization-service.js', () => ({
+  KeywordOptimizationService: { get: vi.fn(() => mockOptimizationService) },
+}));
+
+const mockDispatch = vi.fn().mockResolvedValue({
+  updated: true,
+  summary: 'Keyword store optimized',
+  updates: { wrong: { action: 'update', weight: 0.4, reasoning: 'slightly high FP' } }
+});
+
+const mockRegister = vi.fn();
+
+vi.mock('@principles/core/runtime-v2', () => {
+  return {
+    WorkflowFunnelLoader: class {
+      getFunnel = vi.fn(() => ({
+        policy: {
+          runtimeKind: 'pi-ai',
+          provider: 'anthropic',
+          model: 'anthropic/claude-3-5-sonnet',
+          apiKeyEnv: 'ANTHROPIC_API_KEY',
+          timeoutMs: 30000,
+        }
+      }));
+    },
+    PiAiRuntimeAdapter: class {},
+    CorrectionObserver: class {},
+    AgentScheduler: class {
+      register = mockRegister;
+      dispatch = mockDispatch;
+    }
+  };
+});
+
+import { CorrectionObserverService, runCorrectionObserverCycle } from '../../src/service/correction-observer-service.js';
+import { safeRmDir } from '../test-utils.js';
+
+describe('CorrectionObserverService — Independent Service (PRI-293)', () => {
+  beforeEach(() => {
+    vi.useFakeTimers();
+    vi.clearAllMocks();
+  });
+
+  afterEach(() => {
+    vi.useRealTimers();
+    CorrectionObserverService.stop?.({} as any);
+  });
+
+  it('has correct service id', () => {
+    expect(CorrectionObserverService.id).toBe('principles-correction-observer');
+  });
+
+  it('starts and schedules periodic cycles', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-obs-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    try {
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      expect(logger.info).toHaveBeenCalledWith(
+        expect.stringContaining('[PD:CorrectionObserver] Starting')
+      );
+
+      await vi.advanceTimersByTimeAsync(10_000);
+      for (let i = 0; i < 20; i++) {
+        await Promise.resolve();
+      }
+
+      expect(mockRegister).toHaveBeenCalled();
+      expect(mockDispatch).toHaveBeenCalledWith('correction-observer', expect.objectContaining({
+        parentSessionId: 'correction-observer-service',
+        workspaceDir,
+        recentMessages: ['User said wrong input'],
+      }));
+
+      expect(mockOptimizationService.applyResult).toHaveBeenCalledWith(expect.objectContaining({
+        updated: true,
+        summary: 'Keyword store optimized',
+      }));
+    } finally {
+      CorrectionObserverService.stop?.({} as any);
+      safeRmDir(workspaceDir);
+    }
+  });
+
+  it('stops cleanly and cancels pending timer', () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-obs-stop-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    try {
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      CorrectionObserverService.stop?.({} as any);
+
+      vi.advanceTimersByTime(30_000);
+
+      expect(mockDispatch).not.toHaveBeenCalled();
+    } finally {
+      safeRmDir(workspaceDir);
+    }
+  });
+
+  it('does not reschedule after stop during active cycle (P2 fix)', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-obs-race-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    let cycleResolve: () => void;
+    const cyclePromise = new Promise<void>(r => { cycleResolve = r; });
+    mockDispatch.mockImplementationOnce(async () => {
+      cycleResolve!();
+      return { updated: false, summary: 'in-flight' };
+    });
+
+    try {
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      await vi.advanceTimersByTimeAsync(10_000);
+      await cyclePromise;
+
+      CorrectionObserverService.stop?.({} as any);
+
+      vi.advanceTimersByTime(15 * 60 * 1000 * 2);
+
+      expect(mockDispatch).toHaveBeenCalledTimes(1);
+    } finally {
+      CorrectionObserverService.stop?.({} as any);
+      safeRmDir(workspaceDir);
+    }
+  });
+
+  it('logs structured reason when workspaceDir is missing (ERR-002)', () => {
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    CorrectionObserverService.start({
+      workspaceDir: undefined as any,
+      logger,
+      config: { get: () => undefined },
+    } as any);
+
+    expect(logger.warn).toHaveBeenCalledWith(
+      expect.stringContaining('workspaceDir not found')
+    );
+  });
+
+  it('double start same workspace only dispatches one loop (P1 fix)', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-dbl-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const logger1 = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+    const logger2 = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    try {
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger: logger1,
+        config: { get: () => undefined },
+      } as any);
+
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger: logger2,
+        config: { get: () => undefined },
+      } as any);
+
+      expect(logger2.info).toHaveBeenCalledWith(
+        expect.stringContaining('Already started')
+      );
+
+      await vi.advanceTimersByTimeAsync(10_000);
+      for (let i = 0; i < 20; i++) {
+        await Promise.resolve();
+      }
+
+      expect(mockDispatch).toHaveBeenCalledTimes(1);
+    } finally {
+      CorrectionObserverService.stop?.({} as any);
+      safeRmDir(workspaceDir);
+    }
+  });
+
+  it('stop after double start cancels all timers and allows clean restart', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-stopdbl-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    try {
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      CorrectionObserverService.stop?.({} as any);
+
+      vi.advanceTimersByTime(30_000);
+
+      expect(mockDispatch).not.toHaveBeenCalled();
+
+      CorrectionObserverService.start({
+        workspaceDir,
+        stateDir,
+        logger,
+        config: { get: () => undefined },
+      } as any);
+
+      expect(logger.info).toHaveBeenCalledWith(
+        expect.stringContaining('[PD:CorrectionObserver] Starting')
+      );
+    } finally {
+      CorrectionObserverService.stop?.({} as any);
+      safeRmDir(workspaceDir);
+    }
+  });
+});
+
+describe('runCorrectionObserverCycle — Independent Execution', () => {
+  it('skips cycle when no recent sessions exist', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-cycle-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const wctx = WorkspaceContext.fromHookContext({ workspaceDir });
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    mockDb.listRecentSessions.mockReturnValueOnce([]);
+
+    try {
+      await runCorrectionObserverCycle(wctx, logger as any);
+
+      expect(logger.info).toHaveBeenCalledWith(
+        expect.stringContaining('No recent sessions found')
+      );
+      expect(mockDispatch).not.toHaveBeenCalled();
+    } finally {
+      safeRmDir(workspaceDir);
+    }
+  });
+
+  it('logs structured error on cycle failure (ERR-002)', async () => {
+    const workspaceDir = fs.mkdtempSync(path.join(os.tmpdir(), 'pd-corr-err-'));
+    const stateDir = path.join(workspaceDir, '.state');
+    fs.mkdirSync(stateDir, { recursive: true });
+
+    const wctx = WorkspaceContext.fromHookContext({ workspaceDir });
+    const logger = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
+
+    mockDb.listRecentSessions.mockImplementationOnce(() => {
+      throw new Error('DB connection failed');
+    });
+
+    try {
+      await runCorrectionObserverCycle(wctx, logger as any);
+
+      expect(logger.warn).toHaveBeenCalledWith(
+        expect.stringContaining('Correction observer cycle failed')
+      );
+    } finally {
+      safeRmDir(workspaceDir);
+    }
+  });
+});