bookworm-smart-assistant/hooks/token-saver-dispatcher.js

361 lines
13 KiB
JavaScript
Raw Normal View History

#!/usr/bin/env node
/**
* token-saver-dispatcher.js - TSE 6-in-1 unified dispatcher
* Modes: model-advisor | read-guard | bash-limiter | post-output-guard | mcp-tracker | session-report
* Usage: node token-saver-dispatcher.js --mode=<handler>
* Behavior: fail-open (all paths)
*/
'use strict';
const fs = require('fs');
const path = require('path');
const CLAUDE_ROOT = require('./lib/root.js');
const readStdin = require('./lib/read-stdin.js');
const STATE_DIR = path.join(CLAUDE_ROOT, 'session-state');
const MODE = (process.argv.find(a => a.startsWith('--mode=')) || '').slice(7);
if (!MODE) process.exit(0);
/* ── Shared State IO ── */
function stateLoad(file) {
const p = path.join(STATE_DIR, file);
try { return fs.existsSync(p) ? JSON.parse(fs.readFileSync(p, 'utf8')) : null; } catch { return null; }
}
function stateSave(file, data) {
try {
if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
const p = path.join(STATE_DIR, file);
const tmp = p + '.tmp.' + process.pid;
fs.writeFileSync(tmp, JSON.stringify(data, null, 2), 'utf8');
fs.renameSync(tmp, p);
} catch {}
}
function purgeOld(obj, ttlMs) {
const cutoff = Date.now() - ttlMs;
for (const k of Object.keys(obj)) {
if (typeof obj[k] === 'number' && obj[k] < cutoff) delete obj[k];
else if (obj[k] && typeof obj[k] === 'object' && obj[k].ts && obj[k].ts < cutoff) delete obj[k];
}
}
// [P2-2] CJK_TOKEN_FIX_v1
function estimateFileTokens(filePath, fileSize) {
try {
var fd = fs.openSync(filePath, 'r');
var buf = Buffer.alloc(4096);
var n = fs.readSync(fd, buf, 0, 4096, 0);
fs.closeSync(fd);
if (n < 50) return Math.round(fileSize / 3.5);
var cjkBytes = 0;
for (var i = 0; i < n; i++) {
if (buf[i] >= 0xE4 && buf[i] <= 0xED) cjkBytes += 3;
}
var ratio = cjkBytes / n;
var bpt = ratio >= 0.40 ? 2.2 : ratio >= 0.15 ? 2.8 : 3.5;
return Math.round(fileSize / bpt);
} catch { return Math.round(fileSize / 3.5); }
}
function estimateStringTokens(str) {
var len = str.length;
if (len < 50) return Math.round(len / 4);
var sampleLen = Math.min(len, 2000);
var cjk = 0;
for (var i = 0; i < sampleLen; i++) {
var c = str.charCodeAt(i);
if ((c >= 0x3400 && c <= 0x9FFF) || (c >= 0xAC00 && c <= 0xD7AF)) cjk++;
}
var ratio = cjk / sampleLen;
var tokPerChar = ratio * 1.5 + (1 - ratio) * 0.25;
return Math.round(len * tokPerChar);
}
function emit(eventName, opts) {
if (!opts) opts = {};
var out = { continue: true };
if (opts.suppress) out.suppressOutput = true;
var hso = { hookEventName: eventName };
if (opts.ctx) hso.additionalContext = opts.ctx;
if (opts.input) hso.updatedInput = opts.input;
out.hookSpecificOutput = hso;
process.stdout.write(JSON.stringify(out));
}
/* ── model-advisor (UserPromptSubmit) ── */
var SIMPLE_RE = [
/^(查找|搜索|找到?|在哪|哪个文件)/, /^(翻译|translate)\b/i,
/^(格式化|format)\b/i, /^(解释|explain|what is|what does)\b/i,
/^(列出|list|show)\b/i, /^(帮我看|看一下|看看)/,
/^(改个?名|rename)\b/i, /^(运行|run|execute)\s+(test|build|lint)\b/i,
];
var COMPLEX_RE = [
/(架构|architecture|设计方案|system design)/i,
/(全面审计|comprehensive audit|全栈审计)/i,
/(从零开始|from scratch|end.to.end)/i,
/(重构整个|refactor the entire|重新设计)/i,
/(安全审查|security review|红队|red.team)/i,
/(性能优化方案|performance optimization plan)/i,
/(对比分析|comparative analysis|trade.off)/i,
];
function handleModelAdvisor(hd) {
var prompt = hd.prompt || '';
var sid = hd.session_id || 'u';
var p = prompt.trim();
if (!p || p.length < 3) return;
var level = null;
for (var i = 0; i < SIMPLE_RE.length; i++) { if (SIMPLE_RE[i].test(p)) { level = 'simple'; break; } }
if (!level) for (var i = 0; i < COMPLEX_RE.length; i++) { if (COMPLEX_RE[i].test(p)) { level = 'complex'; break; } }
if (!level && p.length < 25) level = 'simple';
if (!level) return;
var state = stateLoad('tse-model-advisor.json') || {};
var ss = state[sid] || { a: {}, ts: Date.now() };
if (ss.a[level]) return;
ss.a[level] = true; ss.ts = Date.now();
state[sid] = ss;
purgeOld(state, 86400000);
stateSave('tse-model-advisor.json', state);
var msg = level === 'simple'
? '[TSE\xb7MODEL_ADVISOR] 简单任务检测。如当前是 Opus, 建议 /model sonnet 或 /model haiku 以节省 5 倍额度。子 Agent 请指定 model: "haiku"。'
: '[TSE\xb7MODEL_ADVISOR] 复杂任务检测。Opus 适合规划阶段。建议: 方案确定后切回 Sonnet 执行, 子 Agent 用 Sonnet/Haiku。';
emit('UserPromptSubmit', { suppress: true, ctx: msg });
}
/* ── read-guard (PreToolUse:Read) ── */
function handleReadGuard(hd) {
if (hd.tool_name !== 'Read') return;
var input = hd.tool_input || {};
if (!input.file_path) return;
if (input.offset !== undefined || input.limit !== undefined || input.pages !== undefined) return;
var fileSize = 0;
try { fileSize = fs.statSync(input.file_path).size; } catch { return; }
if (fileSize < 10000) return;
var state = stateLoad('tse-read-guard.json') || {};
var now = Date.now();
var key = input.file_path.replace(/[\\\/\:]/g, '_');
if (state[key] && (now - state[key]) < 180000) return;
state[key] = now;
purgeOld(state, 600000);
stateSave('tse-read-guard.json', state);
var estLines = Math.round(fileSize * 30 / 1000);
var estTokens = estimateFileTokens(input.file_path, fileSize);
var bn = path.basename(input.file_path);
var msg = fileSize >= 35000
? '[TSE\xb7READ_GUARD] ⚠️ 大文件: ' + bn + ' ≈' + estLines + '行 (' + estTokens + ' tokens)\n你必须使用 offset+limit 分段读取。如需全文分析, 委托 Agent 子进程。'
: '[TSE\xb7READ_GUARD] 提示: ' + bn + ' ≈' + estLines + '行 (' + estTokens + ' tokens). 建议用 offset+limit 分段。';
emit('PreToolUse', { ctx: msg });
}
/* ── bash-limiter (PreToolUse:Bash) ── */
var VIEW_RE = [
/\bcat\s+\S+/, /\bdocker\s+logs\b/, /\bjournalctl\b/, /\bdmesg\b/,
/\bps\s+aux/, /\bfind\s+\//, /\bls\s+-[^\s]*R/, /\btree\b/,
/\bsqlite3\b.*\.dump/, /\bnpm\s+ls\b/, /\bpip\s+(list|freeze)\b/,
/\bdpkg\s+-l/, /\bsystemctl\s+list/,
];
var SKIP_RE = [
/\|\s*head\b/, /\|\s*tail\b/, /\|\s*grep\b/, /\|\s*awk\b/,
/\|\s*sed\b/, /\|\s*wc\b/, /[>]/,
/\bgit\s+(push|pull|fetch|clone|rebase|merge|commit)/,
/\bnpm\s+(install|run|build|test)/, /\bpnpm\s/,
/\bdocker\s+(build|run|push|compose)/, /\bssh\b/, /\bscp\b/,
/\bcurl\b/, /\bwget\b/, /\bmake\b/, /\bcargo\b/, /\bgo\s+(build|run|test)/,
];
function handleBashLimiter(hd) {
if (hd.tool_name !== 'Bash') return;
var cmd = (hd.tool_input || {}).command || '';
if (!cmd || cmd.length < 5) return;
for (var i = 0; i < SKIP_RE.length; i++) { if (SKIP_RE[i].test(cmd)) return; }
var match = false;
for (var i = 0; i < VIEW_RE.length; i++) { if (VIEW_RE[i].test(cmd)) { match = true; break; } }
if (!match) return;
var limit = /\bfind\s+\/|journalctl|tree\s+\/|\.dump/.test(cmd) ? 80 : 150;
emit('PreToolUse', {
input: { command: cmd + ' 2>&1 | head -' + limit, description: (hd.tool_input || {}).description },
ctx: '[TSE\xb7BASH_LIMITER] 输出已截断至 ' + limit + ' 行。需完整输出请 > file 重定向。'
});
}
/* ── post-output-guard (PostToolUse:Read|Bash) ── */
function handlePostOutputGuard(hd) {
var tn = hd.tool_name;
if (tn !== 'Read' && tn !== 'Bash') return;
var out = hd.tool_output;
if (!out || typeof out !== 'string' || out.length < 5000) return;
var state = stateLoad('tse-post-output-guard.json') || {};
var now = Date.now();
if (state[tn] && (now - state[tn]) < 60000) return;
state[tn] = now;
purgeOld(state, 600000);
stateSave('tse-post-output-guard.json', state);
var len = out.length;
var tokens = estimateStringTokens(out);
var cr = len >= 15000;
var msg;
if (tn === 'Read') {
msg = cr
? '[TSE\xb7POST_GUARD] Read ' + len + ' chars (' + tokens + ' tokens). 仅提取与当前任务直接相关的信息。不要在回复中重复完整文件内容。如需多次引用,记下行号用 offset+limit 精确读取。'
: '[TSE\xb7POST_GUARD] Read ' + len + ' chars. 聚焦相关段落,避免引用大段原文。';
} else {
msg = cr
? '[TSE\xb7POST_GUARD] Bash ' + len + ' chars (' + tokens + ' tokens). 聚焦错误/警告行和最终状态,忽略冗余日志。如需完整分析,写入文件后分段读取。'
: '[TSE\xb7POST_GUARD] Bash ' + len + ' chars. 聚焦关键输出行,跳过冗余信息。';
}
emit('PostToolUse', { ctx: msg });
}
/* ── mcp-tracker (PostToolUse:mcp__) ── */
function handleMcpTracker(hd) {
var tn = hd.tool_name || '';
if (!tn.startsWith('mcp__')) return;
var parts = tn.split('__');
if (parts.length < 3) return;
var server = parts[1];
var method = parts.slice(2).join('__');
var state = stateLoad('tse-mcp-usage.json') || {
version: 1, servers: {}, totalCalls: 0, trackingSince: new Date().toISOString()
};
state.totalCalls = (state.totalCalls || 0) + 1;
state.lastCall = new Date().toISOString();
if (!state.servers[server]) {
state.servers[server] = { count: 0, tools: {}, firstSeen: new Date().toISOString() };
}
state.servers[server].count++;
state.servers[server].lastUsed = new Date().toISOString();
state.servers[server].tools[method] = (state.servers[server].tools[method] || 0) + 1;
stateSave('tse-mcp-usage.json', state);
if (state.totalCalls % 20 === 0) {
var active = Object.keys(state.servers);
var summary = active.map(function(k) { return k + '(' + state.servers[k].count + ')'; }).join(', ');
emit('PostToolUse', {
ctx: '[TSE\xb7MCP_TRACKER] MCP 调用统计 (累计 ' + state.totalCalls + ' 次, ' + active.length + ' 个活跃服务器)\n活跃: ' + summary + '\n建议: 运行 /mcp-prune 检查零调用 MCP 服务器并考虑禁用以减少启动延迟。'
});
}
}
/* ── session-report (Stop) ── */
function handleSessionReport(hd) {
var tp = hd.transcript_path;
if (!tp || !fs.existsSync(tp)) return;
var stat = fs.statSync(tp);
if (stat.size > 20 * 1024 * 1024 || stat.size < 100) return;
var lines = fs.readFileSync(tp, 'utf8').split('\n').filter(Boolean);
var m = {
rounds: 0, compacts: 0, toolCalls: 0, mcpCalls: 0, agentCalls: 0,
largeOutputs: 0, tseReadGuard: 0, tseBashLimiter: 0, tsePostGuard: 0,
reads: 0, edits: 0, bashes: 0, models: {}
};
for (var i = 0; i < lines.length; i++) {
var obj;
try { obj = JSON.parse(lines[i]); } catch { continue; }
var content = (obj && obj.message && obj.message.content) || (obj && obj.content);
var role = obj && obj.message && obj.message.role;
var model = obj && obj.model;
if (role === 'assistant') m.rounds++;
if (model) m.models[model] = (m.models[model] || 0) + 1;
if (!Array.isArray(content)) {
if (typeof content === 'string') {
countTse(content, m);
if (content.indexOf('PreCompact') !== -1) m.compacts++;
}
continue;
}
for (var j = 0; j < content.length; j++) {
var part = content[j];
if (!part) continue;
if (part.type === 'tool_use') {
m.toolCalls++;
var nm = part.name || '';
if (nm.startsWith('mcp__')) m.mcpCalls++;
if (nm === 'Agent') m.agentCalls++;
if (nm === 'Read') m.reads++;
if (nm === 'Edit' || nm === 'Write') m.edits++;
if (nm === 'Bash') m.bashes++;
}
if (part.type === 'tool_result') {
var txt = typeof part.content === 'string' ? part.content : '';
if (txt.length > 5000) m.largeOutputs++;
}
var t = part.text || (typeof part === 'string' ? part : '');
if (typeof t === 'string') {
countTse(t, m);
if (t.indexOf('PreCompact') !== -1) m.compacts++;
}
}
}
var score = 80;
score -= Math.min(m.compacts * 8, 24);
score -= Math.min(m.largeOutputs * 2, 20);
score -= Math.max(0, Math.floor((m.rounds - 40) * 0.5));
if (m.agentCalls > 0) score += 10;
if (m.tseReadGuard + m.tseBashLimiter > 0 && m.tseReadGuard + m.tseBashLimiter < 8) score += 5;
score = Math.max(0, Math.min(100, score));
var grade = score >= 90 ? 'A' : score >= 80 ? 'B' : score >= 70 ? 'C' : score >= 60 ? 'D' : 'F';
var report = { ts: new Date().toISOString(), sid: hd.session_id || 'unknown', score: score, grade: grade, metrics: m };
if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
fs.appendFileSync(path.join(STATE_DIR, 'tse-efficiency-log.jsonl'), JSON.stringify(report) + '\n', 'utf8');
}
function countTse(text, m) {
if (text.indexOf('READ_GUARD') !== -1) m.tseReadGuard++;
if (text.indexOf('BASH_LIMITER') !== -1) m.tseBashLimiter++;
if (text.indexOf('POST_GUARD') !== -1) m.tsePostGuard++;
}
/* ── Main ── */
(async () => {
try {
var maxSize = MODE === 'session-report' ? 128 * 1024
: MODE === 'post-output-guard' ? 2 * 1024 * 1024
: 512 * 1024;
var hd = await readStdin({ maxSize: maxSize });
switch (MODE) {
case 'model-advisor': handleModelAdvisor(hd); break;
case 'read-guard': handleReadGuard(hd); break;
case 'bash-limiter': handleBashLimiter(hd); break;
case 'post-output-guard': handlePostOutputGuard(hd); break;
case 'mcp-tracker': handleMcpTracker(hd); break;
case 'session-report': handleSessionReport(hd); break;
}
process.exit(0);
} catch { process.exit(0); }
})();