根本原因: codex 的 imagegen 技能預設把圖存在 ~/.codex/generated_images/<會話id>/, 是否複製進 .tgcodex-outbox/ 全靠模型遵守 prompt 規則,偶爾會漏, 導致 bot 回「畫好了」但沒附圖。 修法: 每輪結束除了交件匣,另掃描該會話的 generated_images 目錄,把本輪 (mtime 在輪次時間窗內)新生成的圖一併傳出;以檔案內容 MD5 去重, 交件匣有複製過的不會重複傳。generated_images 原檔保留(後續編輯可能要用)。 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
42 lines
866 B
JSON
42 lines
866 B
JSON
{
|
|
"name": "telegram-codex-bot",
|
|
"version": "0.1.9",
|
|
"description": "Telegram bot powered by the local Codex CLI — zero-dependency, pm2-managed, with a built-in PM2 web viewer",
|
|
"license": "MIT",
|
|
"type": "commonjs",
|
|
"publishConfig": {
|
|
"registry": "https://jianmiau.ddns.net/api/packages/AI/npm/"
|
|
},
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "ssh://git@jianmiau.ddns.net:8022/AI/telegram-codex-bot.git"
|
|
},
|
|
"main": "src/index.js",
|
|
"bin": {
|
|
"telegram-codex-bot": "bin/cli.js",
|
|
"tgcodex": "bin/cli.js"
|
|
},
|
|
"files": [
|
|
"bin/",
|
|
"src/",
|
|
"README.md",
|
|
"LICENSE"
|
|
],
|
|
"engines": {
|
|
"node": ">=18"
|
|
},
|
|
"scripts": {
|
|
"start": "node bin/cli.js web",
|
|
"dev": "node --watch src/web/server.js"
|
|
},
|
|
"keywords": [
|
|
"telegram",
|
|
"bot",
|
|
"codex",
|
|
"codex-cli",
|
|
"pm2",
|
|
"ai",
|
|
"agent"
|
|
]
|
|
}
|