@lzhzzzzwill/cofos 1.0.0

package/README.md

@@ -0,0 +1,112 @@
+# COFOS CLI
+
+一个本地 LLM 聊天 CLI：3D 立体欢迎界面 + Hugging Face 模型对话。
+
+```bash
+npx cofos
+```
+
+```
+╭─────────────────────────────────────────────────────────╮
+│   ██████╗     ██████╗    ███████╗    ██████╗  ███████╗ │
+│  ██╔════╝    ██╔═══██╗   ██╔════╝   ██╔═══██╗ ██╔════╝ │
+│  ██║         ██║   ██║   ███████╗   ██║   ██║ ███████╗ │
+│  ██║         ██║   ██║   ██╔════╝   ██║   ██║ ╚════██║ │
+│  ╚██████╗    ╚██████╔╝   ██║        ╚██████╔╝ ███████║ │
+│   ╚═════╝     ╚═════╝    ╚═╝         ╚═════╝  ╚══════╝ │
+│    ░░░░░░░     ░░░░░░░    ░░░         ░░░░░░░  ░░░░░░░  │  ← 3D shadow
+│                    Welcome to COFOS CLI — local LLM chat  │
+│              Type  /help  for commands  ·  /exit  to quit│
+╰─────────────────────────────────────────────────────────╯
+  cofos > What is a MOF material?
+[Model streams response...]
+  cofos > Tell me more about its applications.
+```
+
+## 快速开始
+
+```bash
+# 直接运行
+npx cofos
+
+# 或本地
+git clone <repo> && cd demo && npm link
+cofos
+```
+
+首次运行会自动安装 Python 依赖并下载模型（约 30-60 秒）。
+
+## 命令
+
+| 命令 | 说明 |
+|------|------|
+| `/help` | 显示帮助 |
+| `/exit` | 退出 |
+| `/clear` | 清屏重新显示欢迎界面 |
+| `/info` | 显示模型和版本信息 |
+| `/model <id>` | 切换 Hugging Face 模型 |
+
+## 项目结构
+
+```
+├── package.json          # npm 包配置，bin → cofos
+├── requirements.txt      # Python 依赖：transformers + torch
+├── .gitignore
+├── bin/
+│   └── cofos.js          # Node.js CLI：3D 前端 + 子进程管理
+└── scripts/
+    └── chat.py           # Python 推理：加载模型、生成回复
+```
+
+## 架构概览
+
+```
+终端                          Node.js (cofos.js)                    Python (chat.py)
+ │                                │                                      │
+ │  cofos                         │                                      │
+ │────────────────────────────────>│                                      │
+ │                                │  spawn python3 scripts/chat.py       │
+ │                                │──────────────────────────────────────>│
+ │                                │                                      │ 加载模型
+ │                                │  stdout ← ===READY===                │
+ │                                │<──────────────────────────────────────│
+ │  显示 3D 欢迎界面 + 提示符     │                                      │
+ │<───────────────────────────────│                                      │
+ │                                │                                      │
+ │  用户输入 "What is MOF?"      │                                      │
+ │────────────────────────────────>│                                      │
+ │                                │  stdin → "What is MOF?"              │
+ │                                │──────────────────────────────────────>│
+ │                                │                                      │ 生成 token
+ │                                │  stdout ← 流式 token                 │
+ │  流式显示回复                 │<──────────────────────────────────────│
+ │<───────────────────────────────│                                      │
+ │                                │  stdout ← \n===DONE===\n             │
+ │                                │<──────────────────────────────────────│
+ │  显示 "cofos >" 等待下一条    │                                      │
+ │<───────────────────────────────│                                      │
+```
+
+## 技术栈
+
+| 层 | 技术 | 职责 |
+|----|------|------|
+| CLI 前端 | Node.js (ESM) | 终端 UI、子进程管理、管道通信 |
+| 模型后端 | Python + transformers | 模型加载、token 生成、流式输出 |
+| 模型 | SmolLM2-360M-Instruct (HF) | 对话推理 |
+| 通信 | stdin/stdout 管道 | 进程间消息传递 |
+| 分發 | npm | 包管理、全局命令、npx |
+
+## 依赖
+
+- Node.js ≥ 18
+- Python 3.8+
+- 首次运行需联网（下载模型，~360MB）
+
+## 开发
+
+```bash
+npm link          # 注册全局命令
+cofos             # 启动
+npm run start     # 或直接 node ./bin/cofos.js
+```

package/bin/cofos.js

@@ -0,0 +1,183 @@
+#!/usr/bin/env node
+import { spawn, spawnSync } from "node:child_process";
+import { createInterface } from "node:readline";
+import { existsSync } from "node:fs";
+import { dirname, join, resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const root = resolve(__dirname, "..");
+const chatScript = join(root, "scripts", "chat.py");
+const reqFile = join(root, "requirements.txt");
+
+/* ─── ANSI ─── */
+const R = "\x1b[0m", B = "\x1b[1m", D = "\x1b[2m";
+const C = "\x1b[96m", W = "\x1b[97m", G = "\x1b[90m";
+
+/* ─── 3D COFOS art ─── */
+const C_ = [" ██████╗ ","██╔════╝ ","██║      ","██║      ","╚██████╗ "," ╚═════╝ "];
+const O_ = [" ██████╗ ","██╔═══██╗","██║   ██║","██║   ██║","╚██████╔╝"," ╚═════╝ "];
+const F_ = ["███████╗ ","██╔════╝ ","███████╗ ","██╔════╝ ","██║      ","╚═╝      "];
+const S_ = [" ██████╗ ","██╔════╝ ","███████╗ ","╚════██║ ","███████║ ","╚══════╝ "];
+const ART = C_.map((_, i) => [C_[i], O_[i], F_[i], O_[i], S_[i]].join("   "));
+const ART_W = ART[0].length;
+
+function shadow() {
+  let s = "  ";
+  for (const ch of ART[ART.length - 1]) s += ch !== " " ? "░" : " ";
+  return G + D + s.slice(0, -2) + "  " + R;
+}
+
+function vis(t) { return t.replace(/\x1b\[[0-9;]*m/g, "").length; }
+function fw() { return Math.max((process.stdout.columns || 100) - 2, 50); }
+
+function top(w)  { return "╭" + "─".repeat(w) + "╮"; }
+function bot(w)  { return "╰" + "─".repeat(w) + "╯"; }
+function sep(w)  { return "├" + "─".repeat(w) + "┤"; }
+function emp(w)  { return "│" + " ".repeat(w) + "│"; }
+function cnt(t, w) {
+  const n = vis(t);
+  if (n >= w - 1) return "│" + t.slice(0, w) + "│";
+  const s = w - n, l = Math.floor(s / 2), r = s - l;
+  return "│" + " ".repeat(l) + t + " ".repeat(r) + "│";
+}
+
+function render() {
+  console.clear();
+  const w = fw();
+  const l = [];
+  l.push(top(w)); l.push(emp(w));
+  if (w >= ART_W + 2) {
+    for (const r of ART) l.push(cnt(C + B + r + R, w));
+    l.push(cnt(shadow(), w));
+  } else {
+    l.push(cnt(C + B + "  ██████╗  ██████╗  ███████╗  ██████╗  ███████╗  " + R, w));
+    l.push(cnt(G + D + "  ░░░░░░╝  ░░░░░░╝  ░░░░░░░╝  ░░░░░░╝  ░░░░░░░╝  " + R, w));
+  }
+  l.push(emp(w));
+  l.push(sep(w));
+  l.push(emp(w));
+  l.push(cnt(W + B + "Welcome to COFOS CLI — local LLM chat" + R, w));
+  l.push(emp(w));
+  l.push(cnt(G + "Type  /help  for commands  ·  /exit  to quit" + R, w));
+  l.push(emp(w));
+  l.push(bot(w));
+  console.log(l.join("\n"));
+}
+
+/* ─── helpers ─── */
+
+function cmdExist(c) { return spawnSync(c, ["--version"], { encoding: "utf-8", stdio: "pipe" }).status === 0; }
+function findPy() { return cmdExist("python3") ? "python3" : cmdExist("python") ? "python" : null; }
+
+function ensureDeps(py) {
+  console.log("[cofos] Checking Python dependencies …");
+  if (spawnSync(py, ["-c", "import transformers, torch; print('ok')"], { encoding: "utf-8", stdio: "pipe" }).status === 0) return;
+  console.log("[cofos] Installing Python dependencies (first run, may take a while) …");
+  const r = spawnSync(py, ["-m", "pip", "install", "-r", reqFile], { encoding: "utf-8", stdio: "inherit" });
+  if (r.status !== 0) { console.error("[cofos] Failed to install Python dependencies."); process.exit(1); }
+}
+
+/* ─── main ─── */
+
+function main() {
+  if (process.argv.includes("-h") || process.argv.includes("--help")) {
+    console.log("\n  COFOS CLI — local LLM chat\n  Usage:  cofos\n"); process.exit(0);
+  }
+
+  render();
+
+  const py = findPy();
+  if (!py) { console.error("[cofos] Python not found."); process.exit(1); }
+  if (!existsSync(chatScript)) { console.error("[cofos] Missing script:", chatScript); process.exit(1); }
+  ensureDeps(py);
+
+  console.log("  Loading model … (30–60 s on first run)\n");
+
+  const proc = spawn(py, [chatScript], { stdio: ["pipe", "pipe", "inherit"], encoding: "utf-8" });
+
+  let buf = "", ready = false, generating = false, closed = false;
+  const inputQ = [];
+  const rl = createInterface({ input: process.stdin });
+  rl.on("line", (l) => { inputQ.push(l); });
+
+  proc.stdout.on("data", (chunk) => {
+    try {
+      buf += chunk;
+      if (!ready) {
+        const i = buf.indexOf("===READY===");
+        if (i !== -1) {
+          ready = true;
+          buf = buf.slice(i + 10);
+          if (buf[0] === "\n") buf = buf.slice(1);
+          drain();
+        }
+        return;
+      }
+      if (!generating) return;
+      const i = buf.indexOf("\n===DONE===");
+      if (i !== -1) {
+        process.stdout.write(buf.slice(0, i));
+        buf = buf.slice(i + 11);
+        if (buf[0] === "\n") buf = buf.slice(1);
+        generating = false;
+        console.log("");
+        drain();
+      } else {
+        const k = 10;
+        if (buf.length > k) { process.stdout.write(buf.slice(0, -k)); buf = buf.slice(-k); }
+      }
+    } catch (_) {}
+  });
+
+  proc.on("error", (e) => { console.error("[cofos] Python error:", e.message); process.exit(1); });
+  proc.on("exit", (c) => {
+    closed = true;
+    if (c && c !== 0) console.error("[cofos] Python exited with code", c);
+    try { rl.close(); } catch (_) {}
+    process.exit(c ?? 0);
+  });
+
+  function drain() {
+    while (inputQ.length) {
+      const line = inputQ.shift();
+      if (handle(line)) return;
+    }
+    ask();
+  }
+
+  function ask() {
+    if (closed) return;
+    try { rl.question(C + "  cofos " + R, handle); } catch (_) {}
+  }
+
+  function handle(input) {
+    input = input.trim();
+    if (!input) { ask(); return; }
+
+    if (/^\/(exit|quit)$/.test(input)) { proc.stdin.write("/exit\n"); proc.stdin.end(); return; }
+    if (/^\/(help)$/.test(input)) {
+      console.log("\n  Commands:\n    /help    Show help\n    /exit    Exit\n    /clear   Clear screen\n    /info    Model info\n    /model   Switch model\n");
+      ask(); return;
+    }
+    if (/^\/(clear)$/.test(input)) { render(); console.log(""); ask(); return; }
+    if (/^\/(info)$/.test(input)) {
+      console.log("\n  COFOS CLI — v1.0.0");
+      console.log("  Model: HuggingFaceTB/SmolLM2-360M-Instruct");
+      console.log("  Backend: transformers + PyTorch\n");
+      ask(); return;
+    }
+    if (/^\/model\s/.test(input)) {
+      const m = input.slice(7).trim();
+      console.log("[cofos] Switching model to", m);
+      proc.stdin.write(input + "\n");
+      generating = true;
+      return;
+    }
+
+    generating = true;
+    proc.stdin.write(input + "\n");
+  }
+}
+
+main();

package/package.json

@@ -0,0 +1,29 @@
+{
+  "name": "@lzhzzzzwill/cofos",
+  "version": "1.0.0",
+  "description": "A local LLM chat CLI with a 3D stereoscopic welcome screen.",
+  "type": "module",
+  "bin": {
+    "cofos": "bin/cofos.js"
+  },
+  "files": [
+    "bin",
+    "scripts",
+    "requirements.txt"
+  ],
+  "scripts": {
+    "start": "node ./bin/cofos.js",
+    "test": "node ./bin/cofos.js --help"
+  },
+  "keywords": [
+    "cli",
+    "cofos",
+    "llm",
+    "chat",
+    "huggingface"
+  ],
+  "license": "MIT",
+  "engines": {
+    "node": ">=18"
+  }
+}

package/requirements.txt

@@ -0,0 +1,2 @@
+transformers>=4.40.0
+torch

package/scripts/chat.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+"""Persistent chat: loads an LLM once, reads prompts from stdin, streams to stdout."""
+import sys
+from threading import Thread
+
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    TextIteratorStreamer,
+)
+
+MODEL_ID = "HuggingFaceTB/SmolLM2-360M-Instruct"
+
+
+def main() -> None:
+    model_id = sys.argv[1] if len(sys.argv) > 1 else MODEL_ID
+
+    print(f"[chat] Loading {model_id} …", file=sys.stderr, flush=True)
+    print(f"[chat] 30–60 s on first run (model download).", file=sys.stderr, flush=True)
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    if tokenizer.pad_token_id is None:
+        tokenizer.pad_token_id = tokenizer.eos_token_id
+
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id, dtype="float32", low_cpu_mem_usage=True,
+    )
+    model.eval()
+
+    print("[chat] Ready.", file=sys.stderr, flush=True)
+    print("===READY===", flush=True)
+
+    messages: list[dict] = []
+
+    for raw in sys.stdin:
+        line = raw.strip("\r\n")
+        if not line or line == "/exit":
+            break
+        if line.startswith("/model "):
+            mid = line[len("/model "):].strip()
+            tokenizer = AutoTokenizer.from_pretrained(mid)
+            if tokenizer.pad_token_id is None:
+                tokenizer.pad_token_id = tokenizer.eos_token_id
+            model = AutoModelForCausalLM.from_pretrained(
+                mid, dtype="float32", low_cpu_mem_usage=True,
+            )
+            model.eval()
+            print("===DONE===", flush=True)
+            continue
+
+        messages.append({"role": "user", "content": line})
+        prompt = tokenizer.apply_chat_template(
+            messages, tokenize=False, add_generation_prompt=True,
+        )
+        inputs = tokenizer(prompt, return_tensors="pt")
+
+        streamer = TextIteratorStreamer(
+            tokenizer, skip_prompt=True, skip_special_tokens=True,
+        )
+
+        gen_kw = dict(
+            input_ids=inputs.input_ids,
+            attention_mask=inputs.attention_mask,
+            streamer=streamer,
+            max_new_tokens=512,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.05,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+
+        Thread(target=model.generate, kwargs=gen_kw).start()
+
+        reply = ""
+        for tok in streamer:
+            sys.stdout.write(tok)
+            sys.stdout.flush()
+            reply += tok
+
+        messages.append({"role": "assistant", "content": reply})
+        print("\n===DONE===", flush=True)
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except KeyboardInterrupt:
+        pass
+    except Exception as e:
+        print(f"[chat] Error: {e}", file=sys.stderr)
+        sys.exit(1)