@vierratale/ai 0.1.0-beta.15 → 0.1.0-beta.16

package/README.md

@@ -4,25 +4,16 @@ Intelligent terminal assistant that runs AI models locally and in the cloud.
 
 ## Install
 
-Install requirements and run from source:
-
-```bash
-git clone <your-repo-url>/vierratale-ai.git
-cd vierratale-ai
-
-./install.sh --node   # installs requirements + links the commands
-vierratale             # start chatting
-```
-
-Or run directly from npm:
-
 ```bash
+# From npm
 npm install -g @vierratale/ai
+
+# Or run directly
 npx @vierratale/ai
 ```
 
 The first launch detects and, if needed, installs and starts the local engine
-(**Cortex**), then pulls the model you use.
+(**Cortex** - "secretly" Ollama under the hood), then pulls the model you use.
 
 ## Usage
 
@@ -32,44 +23,32 @@ vierrataleai --provider cortex        # Use local models
 vierrataleai --provider openai        # Use cloud models (OpenAI)
 vierrataleai --provider anthropic     # Use cloud models (Claude)
 vierrataleai --provider gemini        # Use cloud models (Gemini)
-vierrataleai --model VTL-3.7-Ultra   # Use specific model
+vierrataleai --model vierratale-pro   # Use specific model
 ```
 
 ## Models
 
 Local models run through the **Cortex** engine:
 
-| Model | Tier |
-|-------|------|
-| VTL-2.5-Mini | minimal |
-| VTL-2.7-Flash | fast |
-| VTL-2.9-Core | small |
-| VTL-3.2-Orbit | small |
-| VTL-3.1-Plus | balanced |
-| VTL-3.3-Pro | coder |
-| VTL-3.5-Reason | reasoning |
-| VTL-3.7-Ultra | ultra |
-| VTL-4.7-Gusto | balanced |
-| VTL-5.4-Tempo | balanced |
-| VTL-5.2-Pinnacle | pro |
-| VTL-5.9-Sovereign | pro |
+| Model | Backend |
+|-------|---------|
+| vierratale-lite | qwen3:0.6b |
+| vierratale-fast | gemma3:1b |
+| vierratale-small | llama3.2:1b |
+| vierratale-balanced | qwen2.5:1.5b |
+| vierratale-plus | qwen3:1.7b |
+| vierratale-pro | qwen2.5:3b |
 
 Cloud models are available when the matching provider + API key is configured:
 
-| Model | Tier |
-|-------|------|
-| VTL-4.0 | cloud-mini |
-| VTL-4.2-Omni | cloud |
-| VTL-4.5-Plus | cloud-fast |
-| VTL-5.0-Pro | cloud-pro |
-| VTL-6.0-Reason | cloud-lite |
-| VTL-7.0-Omnij | cloud-plus |
-| VTL-8.0-Fabric | cloud-fabric |
-| VTL-9.0-Forge | cloud-forge |
-| VTL-10.0-Singularity | cloud-singularity |
-
-> Legacy `vierratale-*` and old `VRTL-*` model names (e.g. `vierratale-fast`,
-> `vierratale-cloud`) still work and map to the VTL names.
+| Model | Backend |
+|-------|---------|
+| vierratale-cloud-mini | gpt-4o-mini (OpenAI) |
+| vierratale-cloud | gpt-4o (OpenAI) |
+| vierratale-cloud-fast | claude-3-5-haiku-20241022 (Anthropic) |
+| vierratale-cloud-pro | claude-sonnet-4-20250514 (Anthropic) |
+| vierratale-cloud-lite | gemini-2.0-flash (Gemini) |
+| vierratale-cloud-plus | gemini-1.5-pro (Gemini) |
 
 ## Commands
 
@@ -79,8 +58,6 @@ Cloud models are available when the matching provider + API key is configured:
 - `/models` - List available models
 - `/system [text]` - Set a custom system prompt / persona
 - `/search <query>` - Search the web and summarize with AI
-- `/fetch <url>` - Open a link and summarize its content
-- `/log [n|path]` - Show the last n log entries (default 30) or the log file path
 - `/clear` - Clear screen
 - `/new` - Start a new conversation (clear memory)
 - `/quit` - Exit
@@ -88,112 +65,14 @@ Cloud models are available when the matching provider + API key is configured:
 ## Smart Search
 
 Asking a question (Who/What/When/Where/Why/How...?) automatically searches the
-web and summarizes the results with AI. Bare mentions of specific topics also
-trigger a search — e.g. `timun mas from indonesia`, `the legend of roro
-jonggrang`. For example:
+web and summarizes the results with AI. For example:
 
 ```
 > Who is Cristiano Ronaldo?
-> timun mas from indonesia
-```
-
-triggers a live web search and answers from the results. If no web results come
-back, the AI answers from its own knowledge instead of going quiet. Use
-`/search <query>` to force a search explicitly.
-
-Story requests about any subject work the same way — no matter how they're
-phrased (`a story about X`, `the legend of X`, `tell me about X`, `narrate the
-tale of X`, `write X into a txt file`). The subject is pulled out of the
-sentence, searched first, and the reply is saved to a `<subject>.txt` file.
-A generic `tell me a story` (no subject) is told directly from the model — and
-is also saved to a `.txt` file.
-
-Greetings (`hi`, `hello`, `hey`, `good morning`, ...) are answered instantly
-with a short fixed reply — they never reach the model.
-
-## Writing Files
-
-Ask the AI to create code, configs, scripts, web pages, or a whole project. When it
-responds, it lists each file with a `FILE: <path>` header followed by a code
-fence (and `FOLDER: <path>` for empty folders) — just running in the chat writes
-them to your disk in the current working directory. Any file type is supported,
-including JSON config files and HTML pages. Nested folders are created automatically, existing
-files are skipped unless you confirm to overwrite, and nothing is ever written
-outside the working directory.
-
-If the AI ever answers with the code but forgets the `FILE:` header (or writes an
-HTML page without a fence), the assistant rescues it: any `FILE: <path>` line in
-the reply is honored even without a fence, otherwise the request is used to
-infer a filename and the code block is saved anyway. Filename inference covers
-many formats, not just web pages:
-
-| Request contains… | Saved as |
-|--------------------|----------|
-| `html` / `webpage` / `website` / `page` | `index.html` |
-| `css` | `style.css` |
-| `python` / `py` | `script.py` |
-| `flask` / `django` / `fastapi` / `streamlit` / `app` | `app.py` |
-| `javascript` / `js` / `script` | `script.js` |
-| `typescript` / `ts` | `script.ts` |
-| `bash` / `zsh` / `shell` | `script.sh` |
-| `json` / `yaml` / `yml` / `csv` / `sql` | `output.json` / `.yml` / `.csv` / `.sql` |
-
-When the request has no hint at all, the fence language in the reply picks the
-name (```python → `script.py`, ```css → `style.css`, …). Saving also kicks in
-whenever the reply itself contains a `FILE:`/`FOLDER:` line, or when a reply is
-basically just one substantial code block, even if the request phrasing wasn't
-matched.
-
-For file requests, a short format instruction is silently attached to your
-message so the model emits complete `FILE:` blocks with closed fences. And if
-the model ever answers a file request *without any code* (free-style prose,
-interrupted before a fence), nothing is saved and you get a notice telling you
-to ask again — a `.py` file full of chatter is never created.
-
-Example of what the AI emits:
-
-```
-FILE: config.json
-```json
-{
-  "name": "my-app",
-  "port": 3000
-}
 ```
 
-FILE: index.html
-```html
-<!doctype html>
-<html><body>Hello</body></html>
-```
-
-FILE: src/hello.js
-```js
-console.log('Hello VierrataleAI');
-```
-
-## Chat UI
-
-The chat runs in a clean, minimal full-screen interface: your turns are labelled
-`You` and the assistant's `AI`, with plain wrapped text in between. Code blocks
-are the exception — they render inside a green bordered box with their language
-tag (`╭─ html ─╮`), so files stand out at a glance. The latest reply stays pinned
-to the bottom of the terminal while it streams in (no screen flashing), and
-internal search/fetch context stays hidden.
-
-## Automatic Logging
-
-Everything that happens in a session is written automatically to a per-day log
-file in `~/.config/vierrataleai/logs/` (e.g. `vierrataleai-20260101.log`):
-app/session start, every user message, every AI reply, every file write or
-skip, and any errors — with a timestamp. The logs are plain text and safe to
-grep. To inspect them from inside the chat:
-
-```
-/log          # show the last 30 entries
-/log 100      # show the last 100 entries
-/log path     # print the log file path
-```
+triggers a live web search and answers from the results. Use `/search <query>`
+to force a search explicitly.
 
 ## Conversation Memory
 

package/bin/vierrataleai.js

@@ -1,78 +1,3 @@
 #!/usr/bin/env node
-// VierrataleAI launcher + installer.
-//
-// Running without flags starts the assistant and auto-detects dependencies:
-// if the AI engine (ollama) or the model is missing, they are installed first.
-// Running with --install (or --setup / install) additionally creates a global
-// "vierrataleai" / "vierratale" command, then starts the assistant.
-//
-// Installation progress is always the fake animated bar — real engine/model
-// output is deliberately hidden so first-run feels quick and clean.
 import { run } from '../src/cli.js';
-import { Engine } from '../src/engine.js';
-import { Config } from '../src/config.js';
-import { Branding } from '../src/ui/branding.js';
-
-const C = Branding.colors;
-
-const INSTALL_STEPS = [
-  'Checking the AI engine',
-  'Installing dependencies',
-  'Downloading the model',
-  'Linking the vierrataleai command',
-  'Optimizing for this device',
-];
-
-const READY_STEPS = ['Checking engine', 'Installing dependencies', 'Downloading model', 'Optimizing'];
-
-function delay(ms) {
-  return new Promise((r) => setTimeout(r, ms));
-}
-
-async function fakeProgress(steps, work) {
-  const frames = ['▁', '▂', '▃', '▄', '▅', '▆', '▇', '█'];
-  let i = 0;
-  const tty = process.stdout.isTTY;
-  const timer = setInterval(() => {
-    if (!tty) return;
-    i++;
-    const stage = steps[Math.floor((i / 10) % steps.length)];
-    const pct = String(8 + ((i * 7) % 85)).padStart(3, ' ');
-    const bar = frames[i % frames.length];
-    const fillLen = 1 + (i % 20);
-    const fill = '█'.repeat(fillLen) + '░'.repeat(Math.max(0, 20 - fillLen));
-    process.stdout.write(`\r  ${C.accent}${bar}${C.reset} ${C.bold}${pct}%${C.reset} ${C.dim}${stage}${C.reset} [${C.accent}${fill}${C.reset}]`);
-  }, 110);
-  try {
-    return await work;
-  } finally {
-    clearInterval(timer);
-    if (tty) process.stdout.write('\r\x1b[2K');
-    process.stdout.write(`  ${C.success}✔${C.reset} ${C.bold}${C.dim}100%${C.reset} ${C.dim}Ready${C.reset}\n`);
-  }
-}
-
-async function main() {
-  const args = process.argv.slice(2);
-  const doInstall = args.includes('--install') || args.includes('--setup') || args.includes('install');
-  const quick = args.includes('--version') || args.includes('-v') || args.includes('--help') || args.includes('-h');
-
-  Config.load();
-
-  if (doInstall) {
-    console.log(`\n  ${C.bold}${C.primary}${Branding.APP_NAME} ${Branding.VERSION}${C.reset} ${C.dim}— installer${C.reset}\n`);
-    await fakeProgress(INSTALL_STEPS, Engine.ensure());
-    console.log();
-  } else if (!quick) {
-    // Auto-detect: install anything that's missing (engine, model) before starting.
-    await fakeProgress(READY_STEPS, Engine.ensure());
-    console.log();
-  }
-
-  return run();
-}
-
-main().catch((err) => {
-  console.error(err);
-  process.exit(1);
-});
+run();

package/build.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+# Build VierrataleAI Node.js version for packaging
+set -e
+
+cd "$(dirname "$0")"
+
+echo "Installing dependencies..."
+npm install
+
+echo "Testing..."
+node bin/vierrataleai.js --version
+
+echo "Packaging..."
+npm pack
+
+echo "Build complete!"
+echo "To publish: npm publish --tag beta"

package/package.json

@@ -1,31 +1,25 @@
 {
   "name": "@vierratale/ai",
-  "version": "0.1.0-beta.15",
+  "version": "0.1.0-beta.16",
   "description": "VierrataleAI - Intelligent terminal assistant",
   "type": "module",
-  "license": "MIT",
-  "engines": {
-    "node": ">=18"
-  },
   "bin": {
-    "vierrataleai": "./bin/vierrataleai.js",
-    "vierratale": "./bin/vierrataleai.js"
+    "vierrataleai": "./bin/vierrataleai.js"
+  },
+  "main": "./src/index.js",
+  "exports": {
+    ".": "./src/index.js"
   },
   "scripts": {
+    "start": "node bin/vierrataleai.js",
+    "test": "node --test test/",
     "postinstall": "node scripts/postinstall.js"
   },
-  "files": [
-    "bin",
-    "src",
-    "scripts",
-    "LICENSE",
-    "README.md"
-  ],
-  "keywords": [
-    "ai",
-    "chatbot",
-    "terminal",
-    "assistant",
-    "llm"
-  ]
-}
+  "keywords": ["ai", "chatbot", "terminal", "assistant", "llm"],
+  "author": "Vierratale",
+  "license": "MIT",
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "dependencies": {}
+}

package/scripts/postinstall.js

@@ -25,9 +25,9 @@ try {
     execSync('curl -fsSL https://ollama.com/install.sh | sh', { stdio: 'inherit' });
   } else {
     console.log(
-      '\n[vierrataleai] The local engine was not detected.\n' +
+      '\n[vierrataleai] The local engine (ollama) was not detected.\n' +
         '  - Run the CLI: it will attempt to install and start the engine automatically.\n' +
-        '  - Or run ./install.sh (in the project repo) to set up the engine.\n'
+        '  - Or install it yourself: curl -fsSL https://ollama.com/install.sh | sh\n'
     );
   }
 } catch {

package/src/catalog.js

@@ -1,59 +1,16 @@
-// Model catalog. Display names use the opaque VTL branding:
-// VTL-<number>.<name>, e.g. VTL-2.7-Flash, VTL-4.0.
-// The real engine tags are mapped to display names here and kept internal.
 const MODELS = {
-  'qwen3:0.6b': 'VTL-2.5-Mini',
-  'gemma3:1b': 'VTL-2.7-Flash',
-  'llama3.2:1b': 'VTL-2.9-Core',
-  'llama3.2:3b': 'VTL-3.2-Orbit',
-  'qwen2.5:1.5b': 'VTL-3.1-Plus',
-  'qwen2.5-coder:1.5b': 'VTL-3.3-Pro',
-  'qwen3:1.7b': 'VTL-3.5-Reason',
-  'qwen2.5:3b': 'VTL-3.7-Ultra',
-  'gemma3:4b': 'VTL-4.7-Gusto',
-  'phi4-mini': 'VTL-5.4-Tempo',
-  'glm4:9b': 'VTL-5.2-Pinnacle',
-  'qwen3:4b': 'VTL-5.9-Sovereign',
-  'gpt-4o-mini': 'VTL-4.0',
-  'gpt-4o': 'VTL-4.2-Omni',
-  'claude-3-5-haiku-20241022': 'VTL-4.5-Plus',
-  'claude-sonnet-4-20250514': 'VTL-5.0-Pro',
-  'gemini-2.0-flash': 'VTL-6.0-Reason',
-  'gemini-1.5-pro': 'VTL-7.0-Omnij',
-  'kimi-k2.6:cloud': 'VTL-8.0-Fabric',
-  'kimi-k2.7-code:cloud': 'VTL-9.0-Forge',
-  'kimi-k3': 'VTL-10.0-Singularity',
-};
-
-// Legacy display names (older `VRTL-*` and `vierratale-<word>`), accepted
-// everywhere for backwards compatibility (existing config files may contain
-// them). All map onto the current VTL display names.
-const LEGACY_DISPLAY = {
-  'VRTL-1.lite': 'VTL-2.5-Mini',
-  'VRTL-2.fast': 'VTL-2.7-Flash',
-  'VRTL-3.small': 'VTL-2.9-Core',
-  'VRTL-4.balanced': 'VTL-3.1-Plus',
-  'VRTL-4.coder': 'VTL-3.3-Pro',
-  'VRTL-5.plus': 'VTL-3.5-Reason',
-  'VRTL-6.pro': 'VTL-3.7-Ultra',
-  'VRTL-7.cloud-mini': 'VTL-4.0',
-  'VRTL-8.cloud': 'VTL-4.2-Omni',
-  'VRTL-9.cloud-fast': 'VTL-4.5-Plus',
-  'VRTL-10.cloud-pro': 'VTL-5.0-Pro',
-  'VRTL-11.cloud-lite': 'VTL-6.0-Reason',
-  'VRTL-12.cloud-plus': 'VTL-7.0-Omnij',
-  'vierratale-lite': 'VTL-2.5-Mini',
-  'vierratale-fast': 'VTL-2.7-Flash',
-  'vierratale-small': 'VTL-2.9-Core',
-  'vierratale-balanced': 'VTL-3.1-Plus',
-  'vierratale-plus': 'VTL-3.5-Reason',
-  'vierratale-pro': 'VTL-3.7-Ultra',
-  'vierratale-cloud-mini': 'VTL-4.0',
-  'vierratale-cloud': 'VTL-4.2-Omni',
-  'vierratale-cloud-fast': 'VTL-4.5-Plus',
-  'vierratale-cloud-pro': 'VTL-5.0-Pro',
-  'vierratale-cloud-lite': 'VTL-6.0-Reason',
-  'vierratale-cloud-plus': 'VTL-7.0-Omnij',
+  'qwen3:0.6b': 'vierratale-lite',
+  'gemma3:1b': 'vierratale-fast',
+  'llama3.2:1b': 'vierratale-small',
+  'qwen2.5:1.5b': 'vierratale-balanced',
+  'qwen3:1.7b': 'vierratale-plus',
+  'qwen2.5:3b': 'vierratale-pro',
+  'gpt-4o-mini': 'vierratale-cloud-mini',
+  'gpt-4o': 'vierratale-cloud',
+  'claude-3-5-haiku-20241022': 'vierratale-cloud-fast',
+  'claude-sonnet-4-20250514': 'vierratale-cloud-pro',
+  'gemini-2.0-flash': 'vierratale-cloud-lite',
+  'gemini-1.5-pro': 'vierratale-cloud-plus',
 };
 
 const REVERSE = Object.fromEntries(
@@ -61,64 +18,26 @@ const REVERSE = Object.fromEntries(
 );
 
 const LOCAL_MODELS = [
-  'VTL-2.5-Mini',
-  'VTL-2.7-Flash',
-  'VTL-2.9-Core',
-  'VTL-3.2-Orbit',
-  'VTL-3.1-Plus',
-  'VTL-3.3-Pro',
-  'VTL-3.5-Reason',
-  'VTL-3.7-Ultra',
-  'VTL-4.7-Gusto',
-  'VTL-5.4-Tempo',
-  'VTL-5.2-Pinnacle',
-  'VTL-5.9-Sovereign',
+  'vierratale-lite',
+  'vierratale-fast',
+  'vierratale-small',
+  'vierratale-balanced',
+  'vierratale-plus',
+  'vierratale-pro',
 ];
 
 const CLOUD_MODELS = [
-  'VTL-4.0',
-  'VTL-4.2-Omni',
-  'VTL-4.5-Plus',
-  'VTL-5.0-Pro',
-  'VTL-6.0-Reason',
-  'VTL-7.0-Omnij',
-  'VTL-8.0-Fabric',
-  'VTL-9.0-Forge',
-  'VTL-10.0-Singularity',
+  'vierratale-cloud-mini',
+  'vierratale-cloud',
+  'vierratale-cloud-fast',
+  'vierratale-cloud-pro',
+  'vierratale-cloud-lite',
+  'vierratale-cloud-plus',
 ];
 
-const TIERS = {
-  'VTL-2.5-Mini': 'minimal',
-  'VTL-2.7-Flash': 'fast',
-  'VTL-2.9-Core': 'small',
-  'VTL-3.2-Orbit': 'small',
-  'VTL-3.1-Plus': 'balanced',
-  'VTL-3.3-Pro': 'coder',
-  'VTL-3.5-Reason': 'reasoning',
-  'VTL-3.7-Ultra': 'ultra',
-  'VTL-4.7-Gusto': 'balanced',
-  'VTL-5.4-Tempo': 'balanced',
-  'VTL-5.2-Pinnacle': 'pro',
-  'VTL-5.9-Sovereign': 'pro',
-  'VTL-4.0': 'cloud-mini',
-  'VTL-4.2-Omni': 'cloud',
-  'VTL-4.5-Plus': 'cloud-fast',
-  'VTL-5.0-Pro': 'cloud-pro',
-  'VTL-6.0-Reason': 'cloud-lite',
-  'VTL-7.0-Omnij': 'cloud-plus',
-  'VTL-8.0-Fabric': 'cloud-fabric',
-  'VTL-9.0-Forge': 'cloud-forge',
-  'VTL-10.0-Singularity': 'cloud-singularity',
-};
-
 export const Catalog = {
-  // Map any known name (new or legacy) to the current VTL display name.
-  normalize(displayName) {
-    return LEGACY_DISPLAY[displayName] || displayName;
-  },
-
   getRealModel(displayName) {
-    return REVERSE[this.normalize(displayName)] || displayName;
+    return REVERSE[displayName] || displayName;
   },
 
   getDisplayName(realModel) {
@@ -138,23 +57,23 @@ export const Catalog = {
   },
 
   getDefaultModel() {
-    return 'VTL-2.7-Flash';
+    return 'vierratale-fast';
   },
 
   getDefaultCloudModel() {
-    return 'VTL-4.0';
+    return 'vierratale-cloud-mini';
   },
 
   isLocalModel(displayName) {
-    return LOCAL_MODELS.includes(this.normalize(displayName));
+    return LOCAL_MODELS.includes(displayName);
   },
 
   isCloudModel(displayName) {
-    return CLOUD_MODELS.includes(this.normalize(displayName));
+    return CLOUD_MODELS.includes(displayName);
   },
 
   getVendorForCloudModel(displayName) {
-    const real = REVERSE[this.normalize(displayName)];
+    const real = REVERSE[displayName];
     if (real && real.startsWith('claude-')) return 'anthropic';
     if (real && real.startsWith('gemini-')) return 'gemini';
     if (real && real.startsWith('gpt-')) return 'openai';
@@ -162,17 +81,30 @@ export const Catalog = {
   },
 
   getModelInfo(displayName) {
-    const name = this.normalize(displayName);
-    const real = REVERSE[name];
+    const real = REVERSE[displayName];
     if (!real) return null;
-    const isLocal = LOCAL_MODELS.includes(name);
-    const isCloud = CLOUD_MODELS.includes(name);
+    const isLocal = LOCAL_MODELS.includes(displayName);
+    const isCloud = CLOUD_MODELS.includes(displayName);
+    const tiers = {
+      'vierratale-lite': 'minimal',
+      'vierratale-fast': 'fast',
+      'vierratale-small': 'small',
+      'vierratale-balanced': 'balanced',
+      'vierratale-plus': 'plus',
+      'vierratale-pro': 'professional',
+      'vierratale-cloud-mini': 'cloud-mini',
+      'vierratale-cloud': 'cloud',
+      'vierratale-cloud-fast': 'cloud-fast',
+      'vierratale-cloud-pro': 'cloud-pro',
+      'vierratale-cloud-lite': 'cloud-lite',
+      'vierratale-cloud-plus': 'cloud-plus',
+    };
     return {
       displayName,
       realModel: real,
       isLocal,
       isCloud,
-      tier: TIERS[name] || 'unknown',
+      tier: tiers[displayName] || 'unknown',
     };
   },
 };