tiger-agent 0.2.2 → 0.2.4

package/README.md

@@ -10,13 +10,20 @@ Made by **AI Research Group, Department of Civil Engineering, KMUTT**
 
 ---
 
-## 🆕 What's New — v0.2.0
+## 🆕 What's New — v0.2.4
+
+- **ClawHub skill install fixed** — `clawhub_install` and `clawhub_search` now work correctly when installed via `npm install -g`
+- **No required API keys** — `tiger onboard` skips providers with no key; any single provider is enough to start
+- **`/limit` Telegram command** — set per-provider daily token limits from chat without restarting
+- **Soul & ownskill refresh fixed** — 24-hour regeneration timer now uses DB timestamps, not file mtime, so reflection appends no longer block the update cycle
+
+### v0.2.0
 
 - **npm global install** — `npm install -g tiger-agent`, no git clone needed
 - **Multi-provider LLM** — 5 providers (Kimi, Z.ai, MiniMax, Claude, Moonshot) with auto-fallback
 - **Daily token limits** — per-provider limits with automatic switching at UTC midnight
 - **`tiger` CLI** — unified command: `tiger onboard`, `tiger start`, `tiger telegram`, `tiger stop`
-- **Telegram `/api` & `/tokens`** — switch providers and monitor usage from chat
+- **Telegram `/api`, `/tokens`, `/limit`** — manage providers and usage from chat
 - **Encrypted secrets** — optional at-rest encryption for API keys
 
 ---
@@ -33,68 +40,94 @@ Made by **AI Research Group, Department of Civil Engineering, KMUTT**
 
 ---
 
+## 📋 Requirements
+
+- Node.js 18+ (20+ recommended)
+- npm
+- Python 3 (for SQLite memory helper)
+
+---
+
 ## 📦 Installation
 
 ```bash
 npm install -g tiger-agent
 ```
 
+All config and runtime data is stored in `~/.tiger/` — nothing written to the npm global directory.
+
 ---
 
 ## 🚀 Quick Start
 
+### 1. Run the setup wizard
+
 ```bash
-tiger onboard     # First-time setup wizard (run once)
-tiger start       # Start CLI chat
+tiger onboard
 ```
 
-CLI exit: `/exit` or `/quit`
+The wizard will ask for:
+- **Active provider** — which LLM to use by default (e.g. `zai`, `claude`)
+- **Fallback order** — comma-separated list tried when the active provider is rate-limited
+- **API keys** — enter only the providers you have keys for; others are skipped automatically
+- **Telegram bot token** — from [@BotFather](https://t.me/BotFather) on Telegram
+- **Daily token limits** — per-provider caps (0 = unlimited); auto-switches on breach
+- **Shell / skill-install** — optional tool permissions
 
-**Telegram bot:**
+Config is saved to `~/.tiger/.env` (mode 600).
 
+### 2. Start
+
+**CLI chat:**
 ```bash
-tiger telegram              # Start in foreground
-tiger telegram --background # Start as background daemon
-tiger stop                  # Stop daemon
-tiger status                # Check daemon status
+tiger start
 ```
+Exit with `/exit` or `/quit`.
 
----
+**Telegram bot (foreground):**
+```bash
+tiger telegram
+```
 
-## 📋 Requirements
+**Telegram bot (background daemon):**
+```bash
+tiger telegram --background   # start
+tiger status                  # check if running
+tiger stop                    # stop
+```
 
-- Node.js 18+ (20+ recommended)
-- npm
-- Python 3 (for SQLite memory helper)
+Logs: `~/.tiger/logs/telegram.out.log`
 
 ---
 
 ## 🎮 Run Modes
 
-| Mode | Command | Use Case |
-|------|---------|----------|
+| Mode | Command | Description |
+|------|---------|-------------|
 | **CLI** | `tiger start` | Interactive terminal chat |
 | **Telegram** | `tiger telegram` | Telegram bot (foreground) |
-| **Background** | `tiger telegram --background` | 24/7 daemon |
-| **Stop** | `tiger stop` | Kill background daemon |
-| **Status** | `tiger status` | Check if daemon is running |
-
-Background logs: `~/.tiger/logs/telegram-supervisor.log`
+| **Background** | `tiger telegram --background` | 24/7 daemon with auto-restart |
+| **Stop** | `tiger stop` | Stop background daemon |
+| **Status** | `tiger status` | Check daemon status |
+| **Onboard** | `tiger onboard` | Re-run setup wizard |
 
 ---
 
-## 🔧 Setup Wizard
+## 🔧 Setup Wizard Details
 
-`tiger onboard` creates and configures:
+`tiger onboard` writes `~/.tiger/.env` with all settings. You can re-run it at any time to update config.
 
-- `~/.tiger/.env` — settings and provider config
-- `~/.tiger/.env.secrets` — API keys (mode 600, gitignored)
+| Wizard prompt | What it sets |
+|---------------|-------------|
+| Active provider | `ACTIVE_PROVIDER` |
+| Fallback order | `PROVIDER_ORDER` |
+| API keys | `ZAI_API_KEY`, `CLAUDE_API_KEY`, etc. |
+| Telegram token | `TELEGRAM_BOT_TOKEN` |
+| Token limits | `ZAI_TOKEN_LIMIT`, `CLAUDE_TOKEN_LIMIT`, etc. |
+| Shell tool | `ALLOW_SHELL` |
+| Skill install | `ALLOW_SKILL_INSTALL` |
 
-Setup options:
-- Choose LLM provider and API keys
-- Persistent vs temporary vector DB
-- Optional `sqlite-vec` acceleration
-- Optional encrypted secrets file
+> **Tip:** You can also edit `~/.tiger/.env` directly and restart the bot to apply changes.
 
 ---
 
@@ -233,6 +266,27 @@ Without it, Tiger falls back to cosine similarity in Python — slower but fully
 | **Skills** | `list_skills`, `load_skill`, `clawhub_search`, `clawhub_install` |
 | **Orchestration** | `run_sub_agents` |
 
+### ClawHub Skills
+
+Tiger can search and install skills from [ClawHub](https://clawhub.dev) — a community registry of reusable agent skills. The `clawhub` CLI is bundled with Tiger, no separate install needed.
+
+Enable skill install in `~/.tiger/.env`:
+
+```env
+ALLOW_SKILL_INSTALL=true
+```
+
+Then just ask Tiger in chat:
+
+```
+Search for a web search skill on clawhub
+Install the web-search skill
+```
+
+Skills are installed to `~/.tiger/skills/` and loaded automatically on demand.
+
+> **Note:** `ALLOW_SKILL_INSTALL=true` must be set during `tiger onboard` or added manually to `~/.tiger/.env`.
+
 ---
 
 ## 🔒 Security

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tiger-agent",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "description": "Cognitive AI agent with persistent memory, multi-provider LLM, and Telegram bot",
   "type": "commonjs",
   "main": "src/cli.js",

package/src/agent/reflectionAgent.js

@@ -1,7 +1,7 @@
 const fs = require('fs');
 const path = require('path');
 const { chatCompletion, embedText } = require('../llmClient');
-const { dataDir, embeddingsEnabled } = require('../config');
+const { dataDir, embeddingsEnabled, reflectionUpdateHours } = require('../config');
 const { addMemory, getMeta, setMeta, getMessagesSince, getRecentMessagesAll } = require('./db');
 
 const REFLECTION_META_KEY = 'memory_reflection_last_run_ts';
@@ -80,7 +80,7 @@ function appendHuman2Update(filePath, payload, stampIso) {
   for (const w of payload.successfulWorkflows) lines.push(`- Workflow: ${w}`);
   if (!lines.length) return;
   const block = `\n## Update ${stampIso}\n${lines.join('\n')}\n`;
-  fs.writeFileSync(full, `${existing.trimEnd()}\n${block}`, 'utf8');
+  fs.writeFileSync(full, `${existing.trimEnd()}${block}`, 'utf8');
 }
 
 async function generateReflection(rows, sinceIso, untilIso) {
@@ -123,9 +123,20 @@ async function generateReflection(rows, sinceIso, untilIso) {
   };
 }
 
+function shouldRunReflectionCycle(lastRunTs) {
+  if (!lastRunTs) return true;
+  const hoursPassed = (nowTs() - lastRunTs) / (60 * 60 * 1000);
+  return hoursPassed >= reflectionUpdateHours;
+}
+
 async function maybeRunReflectionCycle({ force = false } = {}) {
   const startedAt = nowTs();
   const lastRunTs = Number(getMeta(REFLECTION_META_KEY, 0) || 0);
+
+  if (!force && !shouldRunReflectionCycle(lastRunTs)) {
+    return { ok: true, skipped: true, reason: 'not_yet_due' };
+  }
+
   const rows = lastRunTs
     ? getMessagesSince(lastRunTs, MAX_MESSAGE_SCAN)
     : getRecentMessagesAll(Math.min(MAX_MESSAGE_SCAN, 240));
@@ -185,6 +196,7 @@ async function maybeRunReflectionCycle({ force = false } = {}) {
   }
 
   setMeta(REFLECTION_META_KEY, startedAt);
+  console.log(`[ReflectionCycle] Completed at ${stampIso} (${rows.length} messages processed)`);
   return { ok: true, skipped: false, at: stampIso };
 }
 

package/src/agent/reflectionScheduler.js

@@ -8,14 +8,30 @@ function startReflectionScheduler() {
 
   const everyMs = Math.max(1, Number(reflectionUpdateHours || 12)) * 60 * 60 * 1000;
 
+  console.log(`[ReflectionScheduler] Starting with interval: ${reflectionUpdateHours || 12} hours (${everyMs}ms)`);
+
   // Kick one asynchronous check on startup.
-  maybeRunReflectionCycle().catch(() => {});
+  maybeRunReflectionCycle().catch((err) => {
+    console.error('[ReflectionScheduler] Startup check failed:', err.message);
+  });
 
   intervalHandle = setInterval(() => {
-    maybeRunReflectionCycle().catch(() => {});
+    console.log('[ReflectionScheduler] Running scheduled reflection cycle...');
+    maybeRunReflectionCycle().catch((err) => {
+      console.error('[ReflectionScheduler] Scheduled cycle failed:', err.message);
+    });
   }, everyMs);
 }
 
+function stopReflectionScheduler() {
+  if (intervalHandle) {
+    clearInterval(intervalHandle);
+    intervalHandle = null;
+    console.log('[ReflectionScheduler] Stopped');
+  }
+}
+
 module.exports = {
-  startReflectionScheduler
+  startReflectionScheduler,
+  stopReflectionScheduler
 };

package/src/agent/skills.js

@@ -4,7 +4,8 @@ const { execFile } = require('child_process');
 const { promisify } = require('util');
 
 const execFileAsync = promisify(execFile);
-const localClawhubBin = path.resolve(process.cwd(), 'node_modules', '.bin', 'clawhub');
+// Resolve clawhub from the package's own node_modules (works for both global and local installs)
+const localClawhubBin = path.resolve(__dirname, '..', '..', 'node_modules', '.bin', 'clawhub');
 
 function listSkills(baseDir) {
   if (!fs.existsSync(baseDir)) return [];

package/src/agent/toolbox.js

@@ -7,7 +7,8 @@ const { listSkills, loadSkill, clawhubSearch, clawhubInstall } = require('./skil
 const { runSubAgentBatch } = require('./subAgent');
 
 const execAsync = promisify(exec);
-const skillsDir = path.resolve('./skills');
+const rootDir = process.env.TIGER_HOME || process.cwd();
+const skillsDir = path.resolve(rootDir, 'skills');
 
 function toAbsolutePath(inputPath) {
   return path.resolve(String(inputPath || '.'));
@@ -113,7 +114,7 @@ async function clawhubSearchTool(args = {}) {
   return clawhubSearch({
     query: args.query,
     limit: args.limit,
-    workdir: args.workdir || process.cwd(),
+    workdir: args.workdir || rootDir,
     dir: args.dir || 'skills',
     timeout_ms: args.timeout_ms
   });
@@ -124,7 +125,7 @@ async function clawhubInstallTool(args = {}) {
     slug: args.slug,
     version: args.version,
     force: args.force,
-    workdir: args.workdir || process.cwd(),
+    workdir: args.workdir || rootDir,
     dir: args.dir || 'skills',
     timeout_ms: args.timeout_ms
   });