aiden-runtime 4.0.1 → 4.1.0

package/README.md

@@ -8,7 +8,7 @@
 
 Autonomous AI Engine
 
-19 providers · 68 skills · 42 tools · 8 channels · AGPL-3.0
+19 providers · 68 skills · 42 tools · 9 channels · AGPL-3.0
 
 Windows · Linux · WSL · macOS (API Mode)
 
@@ -93,7 +93,7 @@ Local-first · Self-healing routing · Browser & terminal control · Persistent
   <img src="https://img.shields.io/badge/providers-19-f97316?style=for-the-badge" alt="19 providers" />
   <img src="https://img.shields.io/badge/skills-68-43853d?style=for-the-badge" alt="68 skills" />
   <img src="https://img.shields.io/badge/tools-42-blueviolet?style=for-the-badge" alt="42 tools" />
-  <img src="https://img.shields.io/badge/channels-8-5865f2?style=for-the-badge" alt="8 channels" />
+  <img src="https://img.shields.io/badge/channels-9-5865f2?style=for-the-badge" alt="9 channels" />
   <img src="https://img.shields.io/badge/offline-Ollama-22c55e?style=for-the-badge" alt="offline" />
   <img src="https://img.shields.io/badge/OAuth-Claude%20Pro%20%2B%20ChatGPT%20Plus-9333ea?style=for-the-badge" alt="OAuth subscriptions" />
   <img src="https://img.shields.io/badge/local--first-yes-00aaaa?style=for-the-badge" alt="local-first" />
@@ -103,13 +103,14 @@ Local-first · Self-healing routing · Browser & terminal control · Persistent
   <a href="https://aiden.taracod.com"><b>Website</b></a> &nbsp;·&nbsp;
   <a href="https://aiden.taracod.com/contact"><b>Contact</b></a> &nbsp;·&nbsp;
   <a href="https://discord.gg/gMZ3hUnQTm"><b>Discord</b></a> &nbsp;·&nbsp;
-  <a href="https://github.com/taracodlabs/aiden-releases/releases/latest"><b>Download</b></a>
+  <a href="https://github.com/taracodlabs/aiden-releases/releases/latest"><b>Download</b></a> &nbsp;·&nbsp;
+  <a href="https://www.amazon.in/Omega-Shiva-Deore-ebook/dp/B0GX33VWZC/"><b>Book</b></a>
 </p>
 
 ---
 
-> **v4.0.0 "REWRITE" — clean-room core · 19 providers · single-loop agent · cron scheduler · neofetch boot card · OAuth subscriptions · honest failures**
-> v4 is a from-scratch rewrite: every adapter, every prompt slot, every loop. Provider OAuth (Claude Pro, ChatGPT Plus) routes to subscription quota instead of pay-as-you-go. Sub-second provider fallback. 28 slash commands. See [changelog](#changelog) below.
+> **v4.1.0 — multi-channel autonomous engine · Telegram + MCP server + subagent fanout · voice CLI · hardened cron · skill mining · structured markdown rendering · cross-platform CI**
+> v4.1 turns Aiden into a multi-surface agent: a `ChannelAdapter`-shaped Telegram bot (text / voice / photo / PDF / groups / admin), an MCP server exposing 24 tools + the full skill catalog to Claude Desktop, parallel subagent fanout across `groq`/`together`, REPL voice mode (PTT + continuous), an auto-mining pipeline that proposes new skills from successful workflows, and a deep REPL polish layer (custom `@inquirer/core` prompt, autosuggest, sectioned boot card, sharp ASCII corners, theme detection). Linux/macOS/Windows × Node 20/22 CI matrix. See [changelog](#changelog) below.
 
 ---
 
@@ -328,9 +329,12 @@ We're shipping honest. Things that work, things that don't:
 - Subagent fanout / parallel agent swarm — single-loop only; deferred to v4.x
 - OCR — not bundled (vision-loop screen capture works, but no Tesseract)
 - Full agentskills.io ecosystem install — held pending license review
-- Telegram channel adapter — Discord/Slack/WhatsApp/Email/Webhook/Twilio/iMessage/Signal working
 - Docker sandbox backend — dropped in v4 rewrite
 
+**Landed in v4.1:**
+
+- Telegram channel adapter (DM polling + per-chat memory) — see [docs/channels/telegram.md](docs/channels/telegram.md)
+
 **Beta features:**
 
 - OAuth providers — provider-side gates may apply, use API keys as fallback
@@ -441,7 +445,7 @@ Multi-layer memory visualised — every conversation, task, and learned pattern
 | **68 bundled skills** | Composable workflows each with a `SKILL.md` prompt, optional helper scripts, and tool requirements. Includes: GitHub PR/issue workflows, NSE / Upstox / Zerodha trading, Censys / Shodan / VirusTotal lookups, Windows Defender / Task Scheduler, Docker management, YouTube content tools, ASCII art, and more. |
 | **6-layer memory** | `MEMORY.md` (declarative facts), conversation/session/workspace memory, semantic search (BM25 + embeddings), learning memory (`LESSONS.md`), structured user profile. Dirty-bit invalidation rebuilds the prompt when files change mid-session. |
 | **Voice** | Edge TTS / Windows SAPI text-to-speech, speech-to-text helpers. |
-| **Channel adapters** | Discord, Slack, WhatsApp, Email (IMAP+SMTP), Webhook, Twilio SMS, iMessage (macOS), Signal — any channel triggers the same agent loop. |
+| **Channel adapters** | Discord, Slack, Telegram, WhatsApp, Email (IMAP+SMTP), Webhook, Twilio SMS, iMessage (macOS), Signal — any channel triggers the same agent loop. |
 | **Computer use** | Screenshot capture, screen-state vision loop, browser automation. Mouse/keyboard automation partial. |
 | **Cron scheduler** | Persistent recurring tasks via the `croner` engine. Atomic state writes, output capture, 5/6-field cron + `@daily`/`@hourly` shortcodes. |
 | **Plugins** | Three bundled plugins: Chrome DevTools Protocol bridge, Claude Pro OAuth, ChatGPT Plus OAuth. Plugin system with permission-state machine (pending-grant / loaded / suspended). |

package/config/hardware.json

@@ -1,9 +1,9 @@
 {
   "gpu": "NVIDIA GeForce GTX 1060 6GB",
   "vramGB": 6,
-  "ramGB": 32,
+  "ramGB": 16,
   "platform": "windows",
   "cudaAvailable": true,
   "appleSilicon": false,
-  "detectedAt": "2026-05-03T13:08:55.885Z"
+  "detectedAt": "2026-05-07T19:19:32.778Z"
 }

package/dist/api/server.js

@@ -132,7 +132,11 @@ const aidenIdentity_1 = require("../core/aidenIdentity");
 const eventBus_1 = require("../core/eventBus");
 const workflowTracker_1 = require("../core/workflowTracker");
 const hooks_1 = require("../core/hooks");
-const telegramBot_1 = require("../core/telegramBot");
+// Phase v4.1-1 — Telegram migrated to the standard ChannelAdapter
+// pattern. The legacy raw-fetch TelegramBot class in core/telegramBot.ts
+// is retained only for its `TelegramConfig` shape, still consumed by
+// the dashboard settings endpoint below.
+const telegram_1 = require("../core/channels/telegram");
 const callbackSystem_1 = require("../core/callbackSystem");
 const memoryDistiller_1 = require("../core/memoryDistiller");
 const failureAnalyzer_1 = require("../core/failureAnalyzer");
@@ -157,7 +161,6 @@ const email_1 = require("../core/channels/email");
 const dashboard_1 = require("./dashboard");
 // —— Sprint 25: module-level WebSocket clients registry (shared between createApiServer routes and startApiServer WS setup)
 let wsBroadcastClients = new Set();
-let activeTelegramBot = null;
 const lastExchangeBySession = new Map();
 // ── Bookmarklet — clip selected text from any page ────────────
 const BOOKMARKLET = `javascript:void(fetch('http://localhost:4200/api/clip',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({content:window.getSelection().toString()||document.title,source:window.location.href,title:document.title})}).then(()=>alert('Clipped!')))`;
@@ -2737,13 +2740,10 @@ function createApiServer() {
             };
             cfg.telegram = newTg;
             (0, index_1.saveConfig)(cfg);
-            // Restart bot if running, or start if newly enabled
-            if (activeTelegramBot) {
-                activeTelegramBot.stop();
-                activeTelegramBot = null;
-            }
-            // Note: full restart handled on next server restart — live reload intentionally omitted
-            // to avoid async complexity inside a sync express handler
+            // Phase v4.1-1: live reload remains intentionally omitted — config
+            // is persisted, channelManager picks it up on the next server boot.
+            // (Live restart through `channelManager.restart('telegram')` could
+            // land in Phase 2 once env-var → config bridging is wired.)
             res.json({ ok: true });
         }
         catch (e) {
@@ -6185,56 +6185,53 @@ function startApiServer(portArg) {
             console.log(`[AgentShield] ✅ Scan complete — risk score ${scan.riskScore}/100`);
         }
     }).catch((e) => console.error('[AgentShield] Scan failed:', e.message));
-    // ── Telegram Bot ─────────────────────────────────────────────
+    // ── Channel adapters (all 9 channels) ───────────────────────────
+    // Phase v4.1-1 — Telegram is now a first-class ChannelAdapter,
+    // gated on `TELEGRAM_BOT_TOKEN` like the other env-driven channels.
+    //
+    // Back-compat bridge: users who configured Telegram via the
+    // dashboard (Settings → Channels → Telegram) wrote their token into
+    // the YAML config, not the environment. Promote it to
+    // `process.env.TELEGRAM_BOT_TOKEN` before adapter construction so
+    // their bot keeps working after the Phase 1 migration. Env always
+    // wins if it is already set.
     try {
         const tgCfg = (0, index_1.loadConfig)().telegram;
-        if (tgCfg?.enabled && tgCfg?.botToken) {
-            const startupTime = Date.now();
-            activeTelegramBot = new telegramBot_1.TelegramBot(tgCfg);
-            activeTelegramBot.startPolling(async (chatId, text) => {
-                // ── Bot commands ─────────────────────────────────────
-                if (text === '/start') {
-                    return `👋 Hey! I'm Aiden, your personal AI.\n\nYour chat ID is: \`${chatId}\`\nAdd this to Aiden Settings → Channels → Telegram → Allowed Chat IDs.\n\nThen just message me anything — I can research, code, manage files, check stocks, and more.`;
-                }
-                if (text === '/help') {
-                    return `🤖 Aiden Commands:\n\nJust type naturally — I understand:\n• "Check NIFTY price"\n• "Research top AI tools"\n• "Write a Python script for..."\n• "What's the weather in Mumbai?"\n• "Schedule a reminder for 5pm"\n\n/status — Check Aiden health\n/stop — Cancel current task`;
-                }
-                if (text === '/status') {
-                    const uptimeSec = Math.floor((Date.now() - startupTime) / 1000);
-                    const uptimeStr = uptimeSec > 3600
-                        ? `${Math.floor(uptimeSec / 3600)}h ${Math.floor((uptimeSec % 3600) / 60)}m`
-                        : `${Math.floor(uptimeSec / 60)}m ${uptimeSec % 60}s`;
-                    const activeCfg = (0, index_1.loadConfig)();
-                    const provider = activeCfg.model?.active || 'unknown';
-                    const semStats = semanticMemory_1.semanticMemory.getStats();
-                    return `✅ Aiden is online\nMode: auto\nProvider: ${provider}\nMemory: ${semStats.total} entries\nUptime: ${uptimeStr}`;
-                }
-                // ── Normal message — route through unified gateway ──────
-                return await gateway_1.gateway.routeMessage({
-                    channel: 'telegram',
-                    channelId: chatId,
-                    userId: `telegram_${chatId}`,
-                    text,
-                    timestamp: Date.now(),
-                });
-            }).catch((e) => console.error('[Telegram] Polling error:', e.message));
-            // Register Telegram delivery so gateway.deliver() / broadcast() can send back
-            const _tgBot = activeTelegramBot;
-            (0, telegramBot_1.registerTelegramCallbacks)(_tgBot);
-            gateway_1.gateway.registerChannel('telegram', async (msg) => {
-                await _tgBot.sendMessage(msg.channelId, msg.text);
-                return true;
-            });
-            console.log('[Telegram] Bot connected and polling');
+        if (tgCfg?.enabled &&
+            typeof tgCfg.botToken === 'string' &&
+            tgCfg.botToken.length > 0 &&
+            !process.env.TELEGRAM_BOT_TOKEN) {
+            process.env.TELEGRAM_BOT_TOKEN = tgCfg.botToken;
         }
-        else {
-            console.log('[Telegram] Bot disabled or no token configured — skipping');
+        if (tgCfg?.allowedChatIds?.length &&
+            !process.env.TELEGRAM_ALLOWED_CHATS) {
+            process.env.TELEGRAM_ALLOWED_CHATS = tgCfg.allowedChatIds.join(',');
         }
     }
+    catch {
+        // Config read failure is non-fatal — adapter falls through to env-only.
+    }
+    // Phase v4.1-1.3a — attach a `serve`-mode logger so adapter / gateway
+    // diagnostics emit as NDJSON to stdout (systemd / docker capture) and
+    // mirror to <root>/logs/aiden.log. Singleton attach happens once
+    // before any startAll / register call has a chance to log.
+    try {
+        // eslint-disable-next-line @typescript-eslint/no-var-requires
+        const { resolveAidenPaths } = require('../core/v4/paths');
+        // eslint-disable-next-line @typescript-eslint/no-var-requires
+        const { createBootLogger } = require('../core/v4/logger');
+        const paths = resolveAidenPaths();
+        const { logger: serveLogger } = createBootLogger({
+            mode: 'serve',
+            logsDir: paths.logsDir,
+        });
+        gateway_1.gateway.attachLogger(serveLogger.child('gateway'));
+        manager_1.channelManager.attachLogger(serveLogger.child('channels'));
+    }
     catch (e) {
-        console.error('[Telegram] Failed to start bot:', e.message);
+        // Logger wiring is best-effort during boot; never block the server.
+        console.error('[ChannelManager] Logger wiring failed:', e?.message);
     }
-    // ── Channel adapters (all 9 channels) ───────────────────────────
     manager_1.channelManager.register(new discord_1.DiscordAdapter());
     manager_1.channelManager.register(new slack_1.SlackAdapter());
     manager_1.channelManager.register(new webhook_1.WebhookAdapter(app));
@@ -6243,6 +6240,7 @@ function startApiServer(portArg) {
     manager_1.channelManager.register(new twilio_1.TwilioAdapter(app));
     manager_1.channelManager.register(new imessage_1.IMessageAdapter());
     manager_1.channelManager.register(new email_1.EmailAdapter());
+    manager_1.channelManager.register(new telegram_1.TelegramAdapter());
     manager_1.channelManager.startAll().catch((e) => console.error('[ChannelManager] Startup error:', e.message));
     return app;
 }