fluxflow-cli 1.1.3 → 1.1.5

package/README.md

@@ -1,14 +1,35 @@
-# 🌌 Flux Flow (`fluxflow-cli`)
-![Flux Flow Logo](https://github.com/KushalRoyChowdhury/fluxflow-cli/blob/main/fluxflow.png)
+# 🌊 Flux Flow
+![Flux Flow Hero](./fluxflow.png)
 
-### *The High-Fidelity Agentic Terminal for the Flux Era.*
+**A Beautiful, Autonomous Terminal AI Agent**
 
-**Flux Flow** is not just another CLI—it's a high-speed, sassy, and goal-oriented CLI AI Agent powered by the latest Gemini/Gemma frontier models. Designed for developers who demand a premium UI/UX while managing complex file-system tasks, web research, and autonomous workflows.
+Flux Flow is an advanced, fully autonomous AI agent that lives directly in your terminal. Built with Node.js and [Ink](https://github.com/vadimdemedes/ink) (React for interactive command-line apps), it provides a highly responsive, component-based UI powered by a sophisticated dual-model AI architecture.
+
+Whether you need a conversational partner or an autonomous developer that can write code, run shell commands, and read your project files, Flux Flow adapts to your needs.
 
 ---
 
-## 🚀 Instant Ignition (No Setup Required)
-You don't even need to install it. Just fire up your terminal and run:
+## ✨ Features
+
+- **Responsive Terminal UI**: A gorgeous, reactive interface built with React and Ink, featuring multi-line input, status bars, modals, and diff views.
+- **Dual-Model Architecture**: A primary agent interacts with you and executes tasks, while a silent background "Janitor" model handles chat summarization and long-term memory extraction without blocking the main UI.
+- **Two Operating Modes**:
+  - **Flux (Dev Mode)**: Full system access. The agent can read/write files, execute shell commands, and run autonomous agentic loops (up to 45 iterations) to solve complex coding tasks.
+  - **Flow (Chat Mode)**: Focused on conversation and web research, with limited agentic loops for faster response times.
+- **Advanced Memory System**: Features both temporary session context and persistent, cross-session user memories encrypted locally on your machine.
+- **Agentic Tooling**: Built-in tools for smart file patching, web scraping, web searching, and terminal execution.
+- **Autonomous Project Alignment**: Automatically detects and adheres to project-specific instructions in `Agent.md`, `Skills.md`, and `Fluxflow.md` for high-fidelity coding standards and complex workflows.
+- **Customizable "Thinking" Levels**: Adjust the depth of the model's reasoning process (from Minimal to Max).
+- **High-Reliability Fallback**: Automatic failover to a lighter, high-concurrency model (Gemini 3.1 Flash Lite) during peak traffic to ensure 100% session persistence.
+
+## 🚀 Quick Start
+
+### Prerequisites
+- [Node.js](https://nodejs.org/) (v18 or higher recommended)
+- `npm`, `yarn`, or `pnpm`
+
+### Via NPM (Global & Instant)
+You can run the agent instantly or install it globally for high-speed access:
 
 ```bash
 # Run instantly (Zero Setup)
@@ -16,56 +37,44 @@ npx fluxflow-cli
 
 # OR Install Globally
 npm install -g fluxflow-cli
-fluxflow-cli
+fluxflow
 ```
 
-*The agent will prompt you for your Gemini API Key on the first run and store it securely in an XOR-encrypted vault.*
+### From Source (Local Development)
+1. Clone the repository and install dependencies:
+   ```bash
+   git clone <repository-url>
+   cd Flux-Flow
+   npm install
+   ```
 
----
+2. Start the agent:
+   ```bash
+   npm start
+   ```
 
-## ✨ Why Flux Flow?
+## 📖 Documentation
 
-### 🎨 **Premium Visual Sovereignty**
-Experience a terminal UI that feels alive. Built with **Ink** and **React**, Flux Flow features:
-- **Dynamic Status Bar**: Real-time telemetry showing your "Neural Headroom" (token usage), Thinking Level, and Session ID.
-- **Archived Terminal Flow**: See execution outputs transform from live elements into permanent conversation records.
-- **Rich Aesthetics**: High-contrast, sleek design with smooth transitions and micro-animations.
+To keep this README concise, detailed information about specific components of Flux Flow has been split into separate documents:
 
-### 🧠 **The Dual-Intelligence System**
-- **Flux Mode (Dev)**: High-speed, agentic problem solving with a 50-turn persistent loop for massive coding tasks.
-- **Flow Mode (Chat)**: Optimized for deep research, high-quality conversation, and web-assisted reasoning.
+- **[Architecture & Design](./ARCHITECTURE.md)**: Deep dive into the React/Ink rendering, the Agentic Loop, and the Janitor background process.
+- **[Agent Tools & Capabilities](./TOOLS.md)**: A comprehensive list of the tools available to the agent (e.g., File I/O, Execution, Web tools).
+- **[UI & Interaction Features](./UI_FEATURES.md)**: Details on commands, thinking levels, and human-in-the-loop verification.
 
-### 🛡️ **Digital Fortress Governance**
-Security isn't an afterthought; it's a boundary.
-- **External Path Hardlock**: Restricts the agent to your Current Working Directory (CWD) unless you explicitly unlock it.
-- **Human-in-the-Loop (HITL)**: Every file write and terminal command requires your high-fidelity approval.
-- **XOR Vaulting**: All local session histories, memories, and API keys are obfuscated and encrypted at rest.
-- **Adaptive Failover**: Automatic multi-stage retry logic with high-concurrency fallback model switching (Gemini 3.1 Flash Lite) during peak API congestion.
+## 🔒 Security & Privacy
 
-### 🧹 **The Background Janitor**
-While you move at high speed, the Janitor follows behind—refining session titles, compressing data, and ensuring your context window remains at absolute peak performance.
+Flux Flow runs entirely locally on your machine.
+- **Global Storage**: All history, memories, and API keys are stored securely in your home directory at `~/.fluxflow`. Sensitive data is encrypted.
+- **Nuclear Reset**: Use the `/reset` command to instantly purge all logs, secrets, and settings from the global storage directory.
+- **Configurable Boundaries**: In Flux mode, file access can be strictly confined to the Current Working Directory, or expanded globally via settings.
+- **API Keys**: You supply your own Gemini/Google AI Studio API keys.
 
----
-
-## 🛠️ Key Capabilities
-- **Deep File-System Interaction**: Edit, move, and refactor code across multiple files with atomic precision.
-- **Real-Time Web Intelligence**: Autonomous web-searching via DuckDuckGo for live news and technical research.
-- **Autonomous Project Alignment**: Automatically detects and adheres to project-specific instructions in `Agent.md`, `Skills.md`, and `Fluxflow.md` for high-fidelity alignment with your coding standards and custom workflows.
-- **High-Reliability Fallback**: Automatic failover to a lighter, high-concurrency model during peak traffic to ensure zero session loss.
-- **Persistent Memory**: The agent learns from your preferences and project requirements across sessions.
-
----
-
-## ⚙️ Configuration
-Type `/settings` in-app to live-configure:
-- **Thinking Level**: Low, Medium, or High (Deep-Reasoning).
-- **Auto-Execution**: For ultimate high-speed flow (Advanced users only).
-- **Security Perimeter**: Toggle External Workspace access.
-
----
+## 🛠️ Built With
 
-## 🏁 License
-MIT © 2026 Flux Flow Team.
+- **[React](https://react.dev/) & [Ink](https://github.com/vadimdemedes/ink)**: For the interactive CLI rendering.
+- **[@google/genai](https://www.npmjs.com/package/@google/genai)**: The core AI SDK powering the agent's intelligence.
+- **[chalk](https://www.npmjs.com/package/chalk) & [gradient-string](https://www.npmjs.com/package/gradient-string)**: For terminal styling and aesthetics.
+- **[fs-extra](https://www.npmjs.com/package/fs-extra)**: For robust file system operations.
 
 ---
-*Forged with ⚡ and 🧬. Welcome to the FluxFlow.*
+*Created as a demonstration of highly capable AI tooling.*

package/dist/fluxflow.js

@@ -215,7 +215,7 @@ var StatusBar = React3.memo(({ mode, thinkingLevel, tokens = "0.0k", tokensTotal
     },
     /* @__PURE__ */ React3.createElement(Box3, null, /* @__PURE__ */ React3.createElement(Text3, { color: modeColor, bold: true }, modeIcon, " ", mode.toUpperCase()), /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, " \u2502 "), /* @__PURE__ */ React3.createElement(Text3, { color: "magenta" }, "\u{1F9E0} ", thinkingLevel)),
     /* @__PURE__ */ React3.createElement(Box3, { flexGrow: 1, justifyContent: "center", paddingX: 2 }, /* @__PURE__ */ React3.createElement(Text3, { color: "gray", dimColor: true }, "\u{1F4C1} "), /* @__PURE__ */ React3.createElement(Text3, { color: "blue", dimColor: true, italic: true }, process.cwd())),
-    /* @__PURE__ */ React3.createElement(Box3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, "MEM: "), /* @__PURE__ */ React3.createElement(Text3, { color: memStatus === "ON" ? "green" : "red" }, memStatus), /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, " \u2502 "), /* @__PURE__ */ React3.createElement(Text3, { color: "blue" }, " Tokens ", tokensTotal > 1e3 ? `${(tokensTotal / 1e3).toFixed(1)}k` : tokensTotal, " (", Math.round(tokens / 254e3 * 100), "%)"), /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, " \u2502 "), /* @__PURE__ */ React3.createElement(Text3, { color: "dim" }, "ID: ", chatId, " "))
+    /* @__PURE__ */ React3.createElement(Box3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, "MEM: "), /* @__PURE__ */ React3.createElement(Text3, { color: memStatus === "ON" ? "green" : "red" }, memStatus), /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, " \u2502 "), /* @__PURE__ */ React3.createElement(Text3, { color: "blue" }, tokensTotal > 1e3 ? `${(tokensTotal / 1e3).toFixed(1)}k` : tokensTotal, " (", Math.round(tokens / 254e3 * 100), "%)"), /* @__PURE__ */ React3.createElement(Text3, { color: "gray" }, " \u2502 "), /* @__PURE__ */ React3.createElement(Text3, { color: "dim" }, chatId, " "))
   );
 });
 var StatusBar_default = StatusBar;
@@ -1861,7 +1861,7 @@ var emojiSpace = (baseSpaces = 2) => {
 // src/app.jsx
 var SESSION_START_TIME = Date.now();
 var CHANGELOG_URL = "https://fluxflow-cli.onrender.com/changelog.html";
-var versionFluxflow = "1.1.3";
+var versionFluxflow = "1.1.5";
 var updatedOn = "2026-04-27";
 var ResolutionModal = ({ data, onResolve, onEdit }) => /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column", borderStyle: "round", borderColor: "magenta", paddingX: 2, paddingY: 1, width: "100%" }, /* @__PURE__ */ React9.createElement(Text9, { color: "magenta", bold: true, underline: true }, "\u{1F7E3} STEERING HINT RESOLUTION"), /* @__PURE__ */ React9.createElement(Text9, { marginTop: 1 }, "The agent already finished the task (turn: finish) before your hint was consumed."), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1, backgroundColor: "#222", paddingX: 1, width: "100%" }, /* @__PURE__ */ React9.createElement(Text9, { italic: true, color: "gray" }, '"', data, '"')), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { color: "cyan" }, "How would you like to proceed?")), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(
   CommandMenu,

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "fluxflow-cli",
-	"version": "1.1.3",
+	"version": "1.1.5",
 	"description": "A high-fidelity agentic terminal assistant for the Flux Era.",
 	"keywords": [
 		"ai",