bookworm-smart-assistant/hooks/route-interceptor-bundle.js

#!/usr/bin/env node
/**
 * UserPromptSubmit Hook: 路由注入主管道 (v5.2 Neural Gateway)
 *
 * 处理流程:
 *   1. 解析用户 prompt
 *   2. 意图分类 → 三级分流 (simple/medium/complex)
 *   3. 运行路由引擎 (BM25 + 上下文融合)
 *   4. 生成 [BWR] 指令注入 additionalContext
 *   5. 写入 route-state-current.json (供下游 hook 消费)
 *
 * stdin: { session_id, transcript_path, cwd, prompt, hook_event_name }
 * stdout: JSON { hookSpecificOutput: { additionalContext } }
 * 退出码: 0 (始终放行)
 *
 * [P2-7] skills-index-lite.json mtime 缓存: 避免每次路由调用都重复 JSON.parse
 *
 * 性能预算: < 2000ms 总计
 */

const fs = require('fs');
const path = require('path');
const crypto = require('crypto');
let safeAppendJsonl;
try { ({ safeAppendJsonl } = require('./lib/safe-append.js')); } catch { safeAppendJsonl = () => {}; }

let readStdin;
try { readStdin = require('./lib/read-stdin.js'); } catch { readStdin = () => Promise.resolve(''); }

// === P3-1 BUNDLE: preload routing deps (fail-open: 模块缺失时降级为空路由) ===
let runRouteEngine, loadSkillsIndex, _engineRequire;
let buildBWRDirective, _EXEMPT;
let _writeRouteState;
let _routingReady = true;
try {
  ({ runRouteEngine, loadSkillsIndex, safeRequire: _engineRequire } = require('../scripts/route-engine.js'));
  ({ buildBWRDirective, MUST_INVOKE_EXEMPT_INTENTS: _EXEMPT } = require('../scripts/bwr-builder.js'));
  ({ writeRouteState: _writeRouteState } = require('../scripts/route-state.js'));
} catch (e) {
  _routingReady = false;
  runRouteEngine = () => ({ skill: null, confidence: 0, candidates: [] });
  loadSkillsIndex = () => [];
  _engineRequire = () => null;
  buildBWRDirective = () => '[BWR:skip] routing modules unavailable';
  _EXEMPT = [];
  _writeRouteState = () => {};
  process.stderr.write('[route-interceptor] WARN: routing modules not found, degraded to skip mode: ' + (e.message || '') + '\n');
}

// H13: 意图分类器立即加载 (每次必用)
const _preloaded = {};
try { _preloaded['intent-classifier.js'] = require('../scripts/intent-classifier.js'); } catch {}
// 次要模块 — 首次访问时延迟加载
function _getLazy(name) {
  if (!_preloaded[name]) {
    try { _preloaded[name] = require('../scripts/' + name); } catch { _preloaded[name] = null; }
  }
  return _preloaded[name];
}

// 动态检测 Claude 配置根目录

const CLAUDE_ROOT = require('./lib/root.js');
const DEBUG_DIR = path.join(CLAUDE_ROOT, 'debug');
const SCRIPTS_DIR = path.join(CLAUDE_ROOT, 'scripts');
const STATE_FILE = path.join(DEBUG_DIR, 'route-state-current.json');
const SESSION_LOCK = path.join(DEBUG_DIR, 'session-active.lock');
let _currentSessionId = null;

// MUST_INVOKE 豁免白名单 (来源: bwr-builder.js)
const MUST_INVOKE_EXEMPT_INTENTS = _EXEMPT;

/**
 * 日志脱敏
 */
const sanitizePrompt = (() => {
  try { return require('../scripts/sanitize.js').sanitize; }
  catch { return (text) => text || ''; }
})();

// === 会话首次激活横幅 (v5.3) ===
// 返回 null (非首条消息) 或横幅文本 (首条消息, 注入 additionalContext)
function showActivationBanner(sessionId) {
  // 检查是否已有同 session 的锁文件
  try {
    if (fs.existsSync(SESSION_LOCK)) {
      const lock = JSON.parse(fs.readFileSync(SESSION_LOCK, 'utf8'));
      if (lock.sessionId === sessionId) return null; // 同会话，不重复显示
    }
  } catch {}

  // 写入新会话锁
  try {
    if (!fs.existsSync(DEBUG_DIR)) fs.mkdirSync(DEBUG_DIR, { recursive: true });
    fs.writeFileSync(SESSION_LOCK, JSON.stringify({ sessionId, ts: new Date().toISOString() }));
  } catch {}

  // 从 stats-compiled.json 读取系统指标 (唯一真相源)
  let skillCount = 0, hookCount = 0, mcpCount = 0, agentCount = 0, sysVersion = 'v5.9';
  try {
    const stats = JSON.parse(fs.readFileSync(path.join(CLAUDE_ROOT, 'stats-compiled.json'), 'utf8'));
    const s = stats.summary || {};
    skillCount = s.skills || 0;
    hookCount = s.hooks || 0;
    mcpCount = s.mcp || 0;
    agentCount = s.agents || 0;
    sysVersion = stats.version || 'v5.9';
  } catch {
    // stats-compiled.json 不存在时回退扫描 (P2-7: 使用 mtime 缓存加载)
    try {
      const idx = loadSkillsIndex(path.join(CLAUDE_ROOT, 'skills-index-lite.json'));
      if (idx) skillCount = idx.skills ? idx.skills.length : 0;
    } catch {}
    try {
      const sJson = JSON.parse(fs.readFileSync(path.join(CLAUDE_ROOT, 'settings.json'), 'utf8'));
      mcpCount = Object.keys(sJson.mcpServers || {}).length;
    } catch {}
    try {
      hookCount = fs.readdirSync(path.join(CLAUDE_ROOT, 'hooks')).filter(f => f.endsWith('.js')).length;
    } catch {}
    try {
      agentCount = fs.readdirSync(path.join(CLAUDE_ROOT, 'agents')).filter(f => f.endsWith('.md')).length;
    } catch {}
  }
  // 从 route-stats.json 读取活跃技能数 (真实用户查询命中过的技能)
  let activeSkillCount = 0;
  try {
    const statsFile = path.join(DEBUG_DIR, 'route-stats.json');
    if (fs.existsSync(statsFile)) {
      const routeStats = JSON.parse(fs.readFileSync(statsFile, 'utf8'));
      activeSkillCount = Object.keys(routeStats.stats || {}).length;
    }
  } catch {}

  // /* ROUTE-ACC-3D-V1 */ near-3-day route accuracy
  let routeAccuracy3d = 'N/A';
  try {
    const cutoff = Date.now() - 3 * 86400 * 1000;
    const files = fs.readdirSync(DEBUG_DIR).filter(function(f){return /^route-\d{4}-\d{2}-\d{2}\.jsonl$/.test(f);});
    let total = 0, hit = 0;
    for (const f of files) {
      const lines = fs.readFileSync(path.join(DEBUG_DIR, f), 'utf8').split('\n');
      for (const L of lines) {
        if (!L) continue;
        try {
          const j = JSON.parse(L);
          const ts = new Date(j.ts).getTime();
          if (!Number.isFinite(ts) || ts < cutoff) continue;
          /* ROUTE-ACC-3D-V2-FILTER */
          const q = (j.query || '').trim();
          if (q.length <= 3 || q.startsWith('[Image') || !q) continue;
          if (j.topResult === 'none' && (!j.candidates || j.candidates.length === 0)) continue;
          total++;
          if (j.topConfidence && j.topConfidence > 0) hit++;
        } catch {}
      }
    }
    if (total > 0) routeAccuracy3d = (hit / total * 100).toFixed(1) + '%';
  } catch {}

  const now = new Date();
  const ts = `${now.getFullYear()}-${String(now.getMonth()+1).padStart(2,'0')}-${String(now.getDate()).padStart(2,'0')} ${String(now.getHours()).padStart(2,'0')}:${String(now.getMinutes()).padStart(2,'0')}`;

  // 纯数据上下文 (不含任何指令, 显示规则在 CLAUDE.md 中定义)
  const banner = [
    `[BOOKWORM_SESSION_START]`,
    `version: ${sysVersion}`,
    `skills: ${skillCount}`,
    `agents: ${agentCount}`,
    `hooks: ${hookCount}`,
    `mcp: ${mcpCount}`,
    `active_skills: ${activeSkillCount}/${skillCount}`,
    `route_accuracy_3d: ${routeAccuracy3d}`,
    `timestamp: ${ts}`,
  ].join('\n');

  return banner;
}

// === Phase 0 宪法拆分: 核心函数委托到独立模块 ===
// runRouteEngine → scripts/route-engine.js
// buildBWRDirective → scripts/bwr-builder.js
// writeRouteState + appendRouteLog → scripts/route-state.js

function safeRequire(modulePath) {
  const basename = path.basename(modulePath);
  if (_preloaded[basename] !== undefined) return _preloaded[basename] || null;
  try { return require(modulePath); } catch { return null; }
}

// runRouteEngine: 薄代理 → scripts/route-engine.js (宪法 2.2 拆分)
// buildBWRDirective: 薄代理 → scripts/bwr-builder.js
// writeRouteState: 薄代理 → scripts/route-state.js (注入 sessionId)

function writeRouteState(traceId, prompt, intent, routing) {
  return _writeRouteState(traceId, prompt, intent, routing, _currentSessionId);
}

// === 主流程 ===
function main() {
  // v5.9: 硬 timeout 保护 — 超过 2000ms 强制退出并返回无路由建议
  const HARD_TIMEOUT_MS = 2000; // [PERF v6.1] 从 2500→2000ms
  const timeoutTimer = setTimeout(() => {
    // 超时时静默退出，等同于无路由建议 (fallback 到 developer-expert)
    process.exit(0);
  }, HARD_TIMEOUT_MS);
  // 允许 Node.js 在 timer 未触发时正常退出
  if (timeoutTimer.unref) timeoutTimer.unref();

  readStdin({ maxSize: 256 * 1024 }).then(input => {
    try {
    const prompt = input.prompt;
    const cwd = input.cwd || process.cwd();

      if (!prompt || typeof prompt !== 'string' || prompt.trim().length === 0) {
        process.exit(0);
        return;
      }

      // XC14 修复: task-notification 系统消息提前退出，不写 route-state-current.json
      // appendRouteLog 已有同类过滤，但 writeRouteState 调用早于它，state 文件会被污染
      if (prompt.includes('<task-notification>')) {
        process.exit(0);
        return;
      }

      // v5.3: 会话首次激活横幅 (返回横幅文本或 null)
      const sessionId = (typeof input.session_id === 'string' && input.session_id.length >= 8) ? input.session_id : 'transient-' + process.pid; // H4 修复: session_id 无效时用进程级标识
      _currentSessionId = sessionId; // RL-V01: 同步到模块级变量供 writeRouteState 使用
      const bannerText = showActivationBanner(sessionId);

      // === Phase 0: 逃生舱命令检测 (在 /skill-name 检测之前) ===
      const escapeMatch = prompt.trim().match(/^\/(force|checks|reset)(?:\s+(.*))?$/i);
      if (escapeMatch) {
        try {
          const { isEnabled } = require('../scripts/feature-flags.js');
          const userOverrides = require('../scripts/user-overrides.js');
          const cmd = escapeMatch[1].toLowerCase();
          const arg = (escapeMatch[2] || '').trim();
          let message = '';

          if (cmd === 'force' && isEnabled('escape-hatch-force')) {
            userOverrides.setForce(arg || undefined);
            message = `[BWR:override] Force mode ON${arg ? ` (skill: ${arg})` : ''} — next routing will be bypassed`;
          } else if (cmd === 'checks' && isEnabled('escape-hatch-checks')) {
            const enabled = arg.toLowerCase() !== 'off';
            userOverrides.setChecks(enabled);
            message = enabled
              ? '[BWR:override] Quality checks ON'
              : '[BWR:override] Quality checks OFF (1h expiry)';
          } else if (cmd === 'reset' && isEnabled('escape-hatch-reset')) {
            userOverrides.resetAll();
            message = '[BWR:override] All overrides cleared';
          }

          if (message) {
            const ctx = bannerText ? bannerText + '\n\n' + message : message;
            const output = {
              hookSpecificOutput: {
                hookEventName: 'UserPromptSubmit',
                additionalContext: ctx,
              },
            };
            process.stdout.write(JSON.stringify(output));
            process.exit(0);
            return;
          }
        } catch {}
      }

      // Warning#3 优化: 一次性读取 STATE_FILE，供隐式反馈检测 + simple 继承共享
      let _cachedPrevState = null;
      try {
        if (fs.existsSync(STATE_FILE)) {
          _cachedPrevState = JSON.parse(fs.readFileSync(STATE_FILE, 'utf8'));
        }
      } catch {}

      // P1-4: Skill 隐式反馈检测 — 上一轮 Skill 调用后用户是否表示不满
      try {
        if (_cachedPrevState) {
          const prevTs = _cachedPrevState.ts ? new Date(_cachedPrevState.ts).getTime() : 0;
          const elapsed = Date.now() - prevTs;
          if (elapsed < 3 * 60 * 1000 && _cachedPrevState.routing && _cachedPrevState.routing.primary) {
            // R2#1 修复: 仅匹配 prompt 前 30 字符，避免技术描述中的词误触发
            // LV-06: 使用更精确的短语匹配，减少 "不对称"/"是不是" 等误判
            const head = prompt.slice(0, 30).toLowerCase();
            const negativeSignals = /^(不对|不是|换个|错了|重来|不要|别用|不行|太差)|^(no|not what|wrong|try again)/;
            const positiveSignals = /^(很好|不错|对的|好的|可以|继续)|^(exactly|perfect|great|yes)/;
            const isNegative = negativeSignals.test(head);
            const isPositive = positiveSignals.test(head) && !isNegative;
            if (isNegative || isPositive) {
              const feedbackFile = path.join(DEBUG_DIR, 'skill-implicit-feedback.jsonl');
              safeAppendJsonl(feedbackFile, {
                ts: new Date().toISOString(),
                prevTraceId: _cachedPrevState.traceId,
                prevSkill: _cachedPrevState.routing.primary,
                prevConfidence: _cachedPrevState.routing.confidence,
                signal: isNegative ? 'negative' : 'positive',
                promptSnippet: sanitizePrompt(prompt.slice(0, 100)),
              });
            }
          }
        }
      } catch {}

      // 用户显式调用 /skill-name → 直接放行不干预
      if (/^\/[\w-]+/.test(prompt.trim())) {
        // 即使是显式调用，首条消息也要输出横幅
        if (bannerText) {
          const output = {
            hookSpecificOutput: {
              hookEventName: 'UserPromptSubmit',
              additionalContext: bannerText,
            },
          };
          process.stdout.write(JSON.stringify(output));
        }
        process.exit(0);
        return;
      }

      // 生成 traceId
      const traceId = crypto.randomUUID().slice(0, 8);

      // 意图分类
      const intentClassifier = safeRequire(path.join(SCRIPTS_DIR, 'intent-classifier.js'));
      let intent;
      if (intentClassifier) {
        intent = intentClassifier.classifyIntent(prompt);
      } else {
        intent = { intents: ['general'], modifiers: [], entities: [], complexity: 'medium' };
      }

      // 三级分流 + 斧二(短查询继承) + 斧四(图片继承)
      let routing;
      let inherited = false;

      // 斧四: 图片/附件查询检测 — [Image #N] 模式自动继承上轮 (占 none 的 24.3%)
      // v6.5.2: 移除 ^ 锚定，支持 "检查[Image #1]..." 等非行首位置
      const isImageQuery = /\[Image\s*#?\d+\]/.test(prompt);

      // 继承尝试函数 (simple + 斧二 + 斧四 共用)
      const INHERIT_WINDOW_MS = 5 * 60 * 1000;
      function tryInherit() {
        if (!_cachedPrevState) return null;
        const prevTs = _cachedPrevState.ts ? new Date(_cachedPrevState.ts).getTime() : 0;
        const elapsed = Date.now() - prevTs;
        if (
          elapsed > INHERIT_WINDOW_MS ||
          !_cachedPrevState.routing?.primary ||
          _cachedPrevState.routing.primary === 'none'
        ) return null;
        const prevRouting = _cachedPrevState.routing;
        return {
          primary: prevRouting.primary,
          candidates: (prevRouting.candidates || []).map(c => ({
            ...c,
            confidence: Math.round(c.confidence * 0.7 * 100) / 100,
          })),
          confidence: Math.round((prevRouting.confidence || 0) * 0.7 * 100) / 100,
          chain: prevRouting.chain || [],
          // 宪法 13.1: 继承路由保留 mustInvoke 标记
          _inheritedMustInvoke: _cachedPrevState.mustInvoke || false,
        };
      }

      if (isImageQuery) {
        // 斧四: 图片查询 → 强制继承上轮，不走 TF-IDF
        routing = tryInherit() || { primary: 'none', candidates: [], confidence: 0, chain: [] };
        inherited = routing.primary !== 'none';
      } else if (intent.complexity === 'simple') {
        // simple: 继承上一次路由 (continue/select/confirm + general/explain)
        const inheritResult = tryInherit();
        if (inheritResult && inheritResult.primary !== 'none') {
          routing = inheritResult;
          inherited = true;
        } else {
          // v6.5.2 追问兜底: CJK 3-14 字的 general 查询继承失败时走 TF-IDF
          // 避免 "再美化一下"/"系统自检" 等追问直接 none
          const cjkCount = (prompt.match(/[\u4e00-\u9fff\u3400-\u4dbf]/g) || []).length;
          const isPureSimple = intent.intents.some(i => i === 'confirm' || i === 'select' || i === 'continue');
          if (!isPureSimple && cjkCount >= 3 && cjkCount < 15) {
            routing = null; // 落到 TF-IDF 路由引擎
          } else {
            routing = { primary: 'none', candidates: [], confidence: 0, chain: [] };
          }
        }
      } else if (intent.complexity === 'medium') {
        // 斧二: medium 短查询尝试继承 (V-03: CJK 独立阈值)
        // CJK 字符数 < 6 且前轮有效 → 继承; 否则走 TF-IDF
        const cjkCount = (prompt.match(/[\u4e00-\u9fff\u3400-\u4dbf]/g) || []).length;
        const isShortCJK = cjkCount > 0 && cjkCount < 6 && prompt.length < 20;
        if (isShortCJK) {
          const inheritResult = tryInherit();
          // 继承质量门控: 衰减后置信度 >= 0.5 才继承
          if (inheritResult && inheritResult.confidence >= 0.5) {
            routing = inheritResult;
            inherited = true;
          }
        }
      }

      if (!routing) {
        // medium / complex: 运行完整路由引擎
        routing = runRouteEngine(prompt, cwd, intent);

        // v5.3: 会话级路由记忆 — 注入会话偏好加成
        const sessionMemory = safeRequire(path.join(SCRIPTS_DIR, 'session-memory.js'));
        if (sessionMemory && routing.candidates.length > 0) {
          try {
            const sessionId = sessionMemory.getSessionId();
            for (const c of routing.candidates) {
              const boost = sessionMemory.getSessionBoost(sessionId, c.name);
              if (boost > 0) c.confidence = Math.min(1.0, c.confidence + boost);
            }
            // 重新排序并更新 primary
            routing.candidates.sort((a, b) => b.confidence - a.confidence);
            if (routing.candidates[0]) {
              routing.primary = routing.candidates[0].name;
              routing.confidence = routing.candidates[0].confidence;
            }
          } catch {}
        }

        // v5.3: A/B 实验 — 低置信差时随机探索
        const abTest = safeRequire(path.join(SCRIPTS_DIR, 'route-ab-test.js'));
        if (abTest && routing.candidates.length >= 2) {
          try {
            const top2 = routing.candidates.slice(0, 2);
            if (abTest.shouldExperiment(top2)) {
              const { selected, experiment } = abTest.selectVariant(top2[0].name, top2[1].name);
              routing.primary = selected;
              routing.experiment = experiment; // 记录实验信息供审计
            }
          } catch {}
        }

        // v5.3: 记录技能使用到会话记忆
        if (sessionMemory && routing.primary && routing.primary !== 'none') {
          try {
            sessionMemory.recordSessionSkill(sessionMemory.getSessionId(), routing.primary);
          } catch {}
        }
      }

      // 写入 route-state
      writeRouteState(traceId, prompt, intent, routing);
      // [P2-1] SHADOW_HAIKU_v1
      try {
        var _ffp = path.join(CLAUDE_ROOT, '.bookworm-features.json');
        var _shOk = true;
        try { if (fs.existsSync(_ffp)) { var _f = JSON.parse(fs.readFileSync(_ffp, 'utf8')); if (_f.shadow_haiku_route === false) _shOk = false; } } catch {}
        if (_shOk) {
          var _shLog = path.join(CLAUDE_ROOT, 'debug', 'shadow-route-log.jsonl');
          try { fs.mkdirSync(path.dirname(_shLog), { recursive: true }); } catch {}
          var _shEntry = {
            ts: new Date().toISOString(), tid: traceId,
            ph: prompt.slice(0, 200), pl: prompt.length,
            it: intent ? { i: intent.intents, c: intent.complexity } : null,
            p: routing.primary, cf: routing.confidence,
            t5: (routing.candidates || []).slice(0, 5).map(function(c) { return { n: c.name, c: c.confidence }; }),
            d: routing.domain || null,
            fr: (routing._firedRules || []).map(function(r) { return r.id || r.rule || ''; }).filter(Boolean).slice(0, 5),
            ih: inherited, cs: routing._coldStartApplied || false,
          };
          fs.appendFileSync(_shLog, JSON.stringify(_shEntry) + '\n');
        }
      } catch {}

      // GH-6: 路由决策 trace event (提升 trace 覆盖率)
      try {
        const sessionTrace = require('../scripts/session-trace.js');
        sessionTrace.appendTraceEvent('route-interceptor-bundle', 'route-decision', {
          traceId, primary: routing.primary, confidence: routing.confidence
        });
      } catch {}

      // 构建 [BWR] 指令
      const directive = buildBWRDirective(traceId, intent, routing, inherited);

      // 输出 additionalContext (横幅 + 路由指令)
      const fullContext = bannerText ? bannerText + '\n\n' + directive : directive;
      const output = {
        hookSpecificOutput: {
          hookEventName: 'UserPromptSubmit',
          additionalContext: fullContext,
        },
      };

      // 写入 stdout (JSON 格式供 Claude Code 消费)
      process.stdout.write(JSON.stringify(output));
    } catch (e) {
      try { process.stderr.write('[route-err] ' + (e.message || '') + '\n'); } catch {}
      // 异常时静默放行
    }

    process.exit(0);
  }).catch(() => { clearTimeout(timeoutTimer); process.exit(0); });
}

// 模块导出 (供测试)
if (typeof module !== 'undefined') {
  module.exports = {
    detectClaudeRoot: CLAUDE_ROOT,
    runRouteEngine,
    buildBWRDirective,
    writeRouteState,
    showActivationBanner,
    safeRequire,
    loadSkillsIndex,
  };
}

if (require.main === module) {
  main();
}