ft-scout 9.0.5 → 9.0.7

package/.firebase/hosting.d2Vi.cache

@@ -1,8 +1,9 @@
-web_cli.html,1789281384143,d251153dac472e4e4ea21d00f881b575e81a63822da13006e720c376cfbe24af
-styles.css,1789281384145,f1c7c32071cbb851d4f0a3023375765c3a5630106878c5fcad8456adb98e138a
-ScoutFavicon.png,1786186569805,41a9ca9abf7acd2976e78c72a72285b49cc0e64b2b5eeb2c2b88c69628fc618a
-authentication.html,1789281384176,678dbfb5438ff13b0a6f8d759c1af77d5aac926ff44ea7815f181e80674d183a
-app.js,1789281384176,f281ff2c345623a652af75a4db565bb35377bfd452a5e5af940c362c65d2f52f
-admin.html,1789281384176,72bb3b4ab7dbbe6ff32bfb5a51e8c79ef0bece4e2f1fc91218296df17e9b34f4
-paid_plans.html,1789283167535,0708329edc4938577250c92fb1a294d09ea38778b8edec990b0b80adc839e49f
-index.html,1789282851111,f7812b28faad4cc0ebf3062272dfadc297ab257d3d73ff254b69780e5401934a
+web_cli.html,1789281384143,d251153dac472e4e4ea21d00f881b575e81a63822da13006e720c376cfbe24af
+styles.css,1789281384145,f1c7c32071cbb851d4f0a3023375765c3a5630106878c5fcad8456adb98e138a
+ScoutFavicon.png,1786186569805,41a9ca9abf7acd2976e78c72a72285b49cc0e64b2b5eeb2c2b88c69628fc618a
+paid_plans.html,1789283167535,0708329edc4938577250c92fb1a294d09ea38778b8edec990b0b80adc839e49f
+index.html,1789282851111,f7812b28faad4cc0ebf3062272dfadc297ab257d3d73ff254b69780e5401934a
+authentication.html,1789281384176,678dbfb5438ff13b0a6f8d759c1af77d5aac926ff44ea7815f181e80674d183a
+app.js,1789284464838,bfddc8f457e7a68a6ff158425cd5b23132e8e15700c7ecd22850fbe0455ff7c0
+admin.html,1789281384176,72bb3b4ab7dbbe6ff32bfb5a51e8c79ef0bece4e2f1fc91218296df17e9b34f4
+oauth.html,1789285036283,f53de5de706d1ce49d2af18e07e1fce39f01fe6a5c65ce525ba678809a1c5bfb

package/AUTONOMOUS_FEATURES.md

@@ -0,0 +1,192 @@
+# 🚀 Scout Autonomous Agent — Features & Architecture Guide
+
+Scout is an advanced, multi-modal autonomous agent platform built directly into FT-CLI. It bridges traditional developer terminal workflows with modern web automation and full operating-system desktop control (GUI).
+
+---
+
+## 📑 Table of Contents
+
+1. [Architectural Overview](#architectural-overview)
+2. [Desktop & Computer-Use (GUI Control)](#1-desktop--computer-use-gui-control)
+3. [Browser Automation & Web Scraping](#2-browser-automation--web-scraping)
+4. [Multi-Step Planning & Cognitive Scratchpad](#3-multi-step-planning--cognitive-scratchpad)
+5. [Action Verification & Self-Healing Engine](#4-action-verification--self-healing-engine)
+6. [Safety & Human-in-the-Loop Risk Classifier](#5-safety--human-in-the-loop-risk-classifier)
+7. [Developer & Workspace Baseline Operations](#6-developer--workspace-baseline-operations)
+8. [Subscription Tier Capabilities (Free vs Pro / Enterprise)](#subscription-tier-capabilities)
+
+---
+
+## Architectural Overview
+
+Scout executes a continuous **Perceive ➔ Plan ➔ Act ➔ Verify ➔ Recover** operational loop:
+
+```mermaid
+flowchart TD
+    Goal[User High-Level Objective] --> Planner[TaskPlanner & DAG Decomposition]
+    Planner --> Scratchpad[Cognitive Scratchpad & State Checkpoint]
+    Scratchpad --> SelectTool[Tool Selection Hierarchy]
+    SelectTool --> RiskCheck{RiskClassifier & Safety Gate}
+    RiskCheck -- High/Critical Risk --> Approval[ApprovalManager: Human Confirmation]
+    Approval -- Approved --> Dispatcher[Agent Runtime Dispatcher]
+    RiskCheck -- Low/Medium Risk --> Dispatcher
+    Dispatcher --> Execute[Execution: Native Computer / Browser / CLI Tools]
+    Execute --> Verify[ActionVerifier: Post-Execution Verification]
+    Verify -- Success --> Checkpoint[Save Task State & Next Step]
+    Verify -- Failure --> Recovery[Error Recovery Strategy: Retry / Alternative]
+    Recovery --> Dispatcher
+    Checkpoint --> Done{All Steps Complete?}
+    Done -- No --> Scratchpad
+    Done -- Yes --> Complete[Task Complete Notification]
+```
+
+---
+
+## 1. 🖥️ Desktop & Computer-Use (GUI Control)
+
+Scout provides deep operating system control powered by the high-performance native `scout_driver.exe` engine (Win32 API interop) and Node.js controller integration (`SystemComputerController`).
+
+### Core Features
+
+- **Multi-Monitor Screen Perception:**
+  - `computer_screenshot` / `screenshot`: Captures high-resolution screen frames to perceive visible windows, buttons, and visual state.
+- **Precision Mouse Automation:**
+  - `computer_click`: Sends left, right, or middle mouse clicks to exact screen coordinates `(x, y)`.
+  - `computer_double_click`: Opens files, selects words, or triggers desktop shortcuts via double-click.
+  - `computer_mouse_move`: Translates the cursor smoothly or instantly across display bounds.
+  - `computer_mouse_down` & `computer_mouse_up`: Granular mouse button holds and releases for complex interactions.
+  - `computer_drag`: Drags items from `(fromX, fromY)` to destination coordinates `(toX, toY)`.
+  - `computer_scroll`: Dispatches vertical and horizontal mouse-wheel scroll deltas.
+- **Keyboard & Shortcut Dispatch:**
+  - `computer_type`: Emits text strings directly into focused input controls or editor windows.
+  - `computer_key_press`: Presses single functional keys (Enter, Escape, Tab, Backspace, Arrow keys, etc.).
+  - `computer_hotkey`: Emits multi-key chords (e.g. `["Control", "s"]` to save, `["Alt", "F4"]` to close, `["Alt", "Tab"]` to switch tasks).
+- **Application & Window Orchestration:**
+  - `computer_open_app`: Launches desktop applications (VS Code, Notepad, File Explorer, Terminal, etc.).
+  - `computer_close_app`: Gracefully terminates or closes targeted desktop processes and windows.
+  - `computer_switch_window`: Brings specific applications into foreground focus by matching title or process.
+  - `computer_inspect_ui`: Enumerates active open desktop windows and highlights the current foreground window.
+  - `computer_wait`: Pauses execution (100ms - 30,000ms) to allow GUI windows, animations, and transitions to settle.
+  - `computer_diagnostic`: Collects display resolution, DPI scaling metrics, and driver connection status.
+
+---
+
+## 2. 🌐 Browser Automation & Web Scraping
+
+Implemented in [`browserController.ts`](file:///c:/Users/rishi/FT-CLI/bin/src/engine/browser/browserController.ts), Scout includes an intelligent browser automation controller capable of navigating websites, analyzing semantic DOM trees, and extracting data.
+
+### Core Features
+
+- **Page Navigation & State:**
+  - `browser_navigate`: Loads HTTP/HTTPS URLs, handles navigation history, and constructs interactive DOM trees.
+  - `browser_inspect`: Discovers interactive elements (links, buttons, form fields) and assigns lightweight reference IDs (e.g., `[ref=1]`).
+- **Web Form Interaction:**
+  - `browser_click`: Clicks web elements identified by CSS selector, visible label text, or ref ID.
+  - `browser_type`: Enters query strings or credentials into active form fields and textareas.
+  - `browser_select`: Selects options from dropdown menus (`<select>`) by visible text or value.
+  - `browser_scroll`: Scrolls viewport up or down to trigger infinite scroll or lazy-loaded assets.
+- **Data Scraping & File Downloads:**
+  - `browser_content`: Strips out HTML markup and extracts clean structured text, tables, and article content.
+  - `browser_screenshot`: Captures a visual snapshot of the current web page viewport.
+  - `browser_download`: Automatically downloads invoices, reports, PDFs, or files from web links and saves them directly to the workspace `downloads/` directory.
+
+#### Example Implementation (`browserController.ts`):
+```typescript
+// Content Extraction & Document Download
+public async extract_content(selector?: string): Promise<BrowserActionResult> {
+    const page = this.mockPages.get(this.currentUrl);
+    const text = page
+        ? page.html.replace(/<[^>]+>/g, ' ').replace(/\s+/g, ' ').trim()
+        : `Content of ${this.currentUrl}`;
+    return { success: true, output: text, url: this.currentUrl, title: this.currentTitle };
+}
+
+public async download_file(urlOrSelector: string, destPath?: string): Promise<BrowserActionResult> {
+    // Discovers links, downloads files, and writes to workspace disk
+    const fileName = path.basename(targetUrl).includes('.') ? path.basename(targetUrl) : 'downloaded_invoice.pdf';
+    const finalPath = destPath ? path.resolve(this.workspaceDir, destPath) : path.resolve(this.workspaceDir, 'downloads', fileName);
+    fs.mkdirSync(path.dirname(finalPath), { recursive: true });
+    // Stream data and persist to disk...
+}
+```
+
+---
+
+## 3. 🧠 Multi-Step Planning & Cognitive Scratchpad
+
+Complex tasks require structured reasoning, plan tracking, and persistent state across agent steps.
+
+- **Dynamic Task Planning (`TaskPlanner`):**
+  - Parses open-ended goals into structured steps with explicit dependencies.
+  - Dynamically adapts when intermediate steps succeed, fail, or reveal new context.
+- **Cognitive Scratchpad Memory (`scratchpad`):**
+  - Exclusive to **Pro & Enterprise** tiers.
+  - Provides working memory via `write`, `read`, `append`, and `clear` operations.
+  - Persisted locally to `.ft/scratchpad.md` to prevent LLM context overflow during long executions.
+- **Task State Checkpoints (`TaskStateManager`):**
+  - Saves full task execution histories and artifact logs to `.ft/tasks/<task_id>.json`.
+  - Enables clean task resumption, history reviews, and rollback capabilities.
+
+---
+
+## 4. 🔍 Action Verification & Self-Healing Engine
+
+Scout doesn't simply fire tools and assume success. Every action is verified through [`actionVerifier.ts`](file:///c:/Users/rishi/FT-CLI/bin/src/engine/actionVerifier.ts).
+
+### Verification Types
+1. `file_exists`: Verifies target file is present on the filesystem and contains non-empty contents.
+2. `app_active`: Verifies that an opened application is running and holds foreground focus.
+3. `url_matches`: Verifies the browser navigated to the expected target domain/path.
+4. `element_exists`: Confirms targeted DOM elements rendered on the page.
+
+### Autonomous Recovery Strategy
+When verification fails:
+- **`RETRY`**: Re-attempts the action if caused by transient loading latency.
+- **`ALTERNATIVE`**: Selects a secondary tool or selector if the primary approach is blocked.
+- **`ABORT`**: Gracefully yields to the user if irreversible roadblocks occur.
+
+### Intent Preservation
+If a user requests GUI action (e.g. *"Open Notepad and type my notes"*), Scout strictly honors the intent and will **not** cheat by performing silent background file writes unless explicitly permitted.
+
+---
+
+## 5. 🛡️ Safety & Human-in-the-Loop Risk Classifier
+
+Implemented in [`safety.ts`](file:///c:/Users/rishi/FT-CLI/bin/src/engine/safety.ts), Scout protects user systems from accidental disruption or destructive operations.
+
+| Risk Level | Triggering Tools / Patterns | Behavior |
+| :--- | :--- | :--- |
+| **LOW** | `read_file`, `browser_inspect`, `computer_screenshot`, `file_info` | Auto-executed silently. |
+| **MEDIUM** | `write_file`, `edit_file`, `browser_type`, `browser_click` | Executed with standard logging. |
+| **HIGH** | `computer_close_app`, destructive hotkeys (`Alt+F4`), process termination | **Execution pauses.** Modal/CLI prompt requires user approval. |
+| **CRITICAL** | System-wide deletion (`rmdir /s /q`, formatting), registry edits | **Blocked / Strict explicit consent required.** |
+
+---
+
+## 6. 💼 Developer & Workspace Baseline Operations
+
+In addition to autonomous GUI and web tools, Scout provides a full suite of developer tools:
+
+- **File Operations:** `read_file`, `write_file`, `edit_file`, `multi_edit_file`, `file_info`.
+- **Search & Inspection:** `grep_search`, `glob_search`, `tree_view`, `list_dir`.
+- **Command & Version Control:** `run_command`, `git_diff`.
+- **Interaction:** `ask_user`, `task_completed`.
+
+---
+
+## Subscription Tier Capabilities
+
+| Feature Capability | Free Tier | Pro Plan | Enterprise Plan |
+| :--- | :---: | :---: | :---: |
+| **Code Reading & File Editing** | ✅ Full | ✅ Full | ✅ Full |
+| **File / Directory Creation** | ✅ Full | ✅ Full | ✅ Full |
+| **Terminal & Build Commands** | ✅ Full | ✅ Full | ✅ Full |
+| **AI Cognitive Scratchpad** | ❌ Blocked | ✅ Full | ✅ Full |
+| **Autonomous Browser Automation** | ❌ Blocked | ✅ Full | ✅ Full |
+| **Autonomous Computer & GUI Control** | ❌ Blocked | ✅ Full | ✅ Full |
+| **Multi-App System Automation** | ❌ Blocked | ✅ Full | ✅ Full |
+| **Dedicated Concurrency & Support** | Community | Priority | 24/7 Dedicated |
+
+---
+
+*Authored by Front Terrain Engineering. For upgrades or enterprise deployment, visit [https://scout.frontterrain.com](https://scout.frontterrain.com).*

package/README.md

@@ -1,4 +1,4 @@
-# scout (FrontTerrain CLI v9.0.5)
+# scout (FrontTerrain CLI v9.0.7)
 
 **FrontTerrain (`scout`)** — The Autonomous AI Principal Software Engineer & Codebase Co-Pilot in your terminal.
 
@@ -228,37 +228,67 @@ Scout is built as a high-agency autonomous operator capable of operating externa
 
 ## Scout Autonomous Tool Registry
 
-### Computer & Application Control Tools
-| Tool | Description |
-|---|---|
-| `computer_screenshot` | Capture display screen image and inspect active foreground window |
-| `computer_click` | Move cursor and click mouse at coordinate (left, right, middle) |
-| `computer_double_click` | Double-click mouse at specified screen coordinate |
-| `computer_type` | Ensure target window focus and type text keystrokes via OS keyboard |
-| `computer_key_press` | Press individual keyboard key (`enter`, `tab`, `escape`, `backspace`) |
-| `computer_hotkey` | Trigger key combination (`["ctrl", "s"]`, `["alt", "tab"]`) |
-| `computer_open_app` | Launch desktop application (Notepad, Excel, Chrome, Terminal) and focus window |
-| `computer_switch_window` | Switch foreground active window to target application |
-| `computer_inspect_ui` | Inspect active window coordinates, title, and UI state |
-
-### Workspace & Engineering Tools
-| Tool | Description |
-|---|---|
-| `read_file` | Read content & line ranges of workspace files |
-| `write_file` | Create new files or overwrite existing source code |
-| `edit_file` | Search & replace exact target code snippets |
-| `multi_edit_file` | Apply batch snippet replacements in a single atomic tool call |
-| `run_command` | Execute live terminal commands (`npm test`, `tsc`, `pytest`) |
-| `list_dir` | List contents of workspace directories |
-| `tree_view` | Generate visual ASCII directory tree structures for workspace paths |
-| `file_info` | Get file metadata, exact line counts, size, & modification timestamps |
-| `grep_search` | String/regex pattern search across entire codebase |
-| `glob_search` | Filter workspace files by file glob patterns |
-| `fetch_url` | Fetch web API documentation, specs, or external web URLs |
-| `git_diff` | Query uncommitted workspace git diff directly inside execution loop |
-| `ask_user` | Request missing secret credentials or API keys |
-| `speak_text` | Read text phrases out loud using Text-to-Speech (TTS) voice synthesis |
-| `task_completed` | Conclude autonomous goal execution with verification and report |
+> 📘 **Full Architecture & Specifications**: For complete deep-dive documentation, flowcharts, and schemas, see [AUTONOMOUS_FEATURES.md](./AUTONOMOUS_FEATURES.md).
+
+### Desktop & Computer-Use Control Tools
+| Tool | Description | Tier Availability |
+|---|---|:---:|
+| `computer` | Unified multi-action desktop dispatcher (click, drag, type, hotkey, open, etc.) | Pro / Enterprise |
+| `computer_screenshot` | Capture display screen image and inspect active foreground window | Pro / Enterprise |
+| `computer_click` | Move cursor and click mouse at coordinate (left, right, middle) | Pro / Enterprise |
+| `computer_double_click` | Double-click mouse at specified screen coordinate | Pro / Enterprise |
+| `computer_right_click` | Right-click mouse at screen coordinate to open context menus | Pro / Enterprise |
+| `computer_mouse_move` | Move mouse cursor to specific display (x, y) coordinates | Pro / Enterprise |
+| `computer_mouse_down` | Hold down mouse button for drag operations | Pro / Enterprise |
+| `computer_mouse_up` | Release mouse button | Pro / Enterprise |
+| `computer_drag` | Drag mouse cursor from `(fromX, fromY)` to `(toX, toY)` | Pro / Enterprise |
+| `computer_scroll` | Scroll vertical or horizontal mouse wheel deltas | Pro / Enterprise |
+| `computer_type` | Ensure target window focus and type text keystrokes via OS keyboard | Pro / Enterprise |
+| `computer_key_press` | Press individual keyboard key (`enter`, `tab`, `escape`, `backspace`) | Pro / Enterprise |
+| `computer_hotkey` | Trigger key combination (`["ctrl", "s"]`, `["alt", "f4"]`, `["alt", "tab"]`) | Pro / Enterprise |
+| `computer_open_app` | Launch desktop application (Notepad, Excel, Chrome, Terminal) and focus window | Pro / Enterprise |
+| `computer_close_app` | Gracefully close application or window by title/executable | Pro / Enterprise |
+| `computer_switch_window` | Switch foreground active window to target application | Pro / Enterprise |
+| `computer_inspect_ui` | Inspect active window coordinates, title, and UI state | Pro / Enterprise |
+| `computer_wait` | Pause execution to allow desktop applications or animations to settle | Pro / Enterprise |
+| `computer_diagnostic` | Retrieve system display resolution, DPI scaling, and Scout driver health | Pro / Enterprise |
+
+### Browser Automation & Web Scraping Tools
+| Tool | Description | Tier Availability |
+|---|---|:---:|
+| `browser_navigate` | Open URL, handle navigation history, and construct semantic DOM tree | Pro / Enterprise |
+| `browser_inspect` | Inspect clickable buttons, links, inputs, and assign element ref IDs (`[ref=1]`) | Pro / Enterprise |
+| `browser_click` | Click element by CSS selector, visible label text, or ref ID | Pro / Enterprise |
+| `browser_type` | Type text strings into active form fields and search inputs | Pro / Enterprise |
+| `browser_select` | Choose option from dropdown `<select>` menus by value or visible text | Pro / Enterprise |
+| `browser_scroll` | Scroll webpage up or down to load lazy-loaded elements | Pro / Enterprise |
+| `browser_content` | Extract clean, structured visible text and tabular data from page | Pro / Enterprise |
+| `browser_screenshot` | Capture visual viewport image of active browser page | Pro / Enterprise |
+| `browser_download` | Automatically download web files, invoices, PDFs to workspace `downloads/` | Pro / Enterprise |
+
+### Cognitive Scratchpad & Reasoning Tools
+| Tool | Description | Tier Availability |
+|---|---|:---:|
+| `scratchpad` | Private working memory for multi-step plans, hypotheses, and state (`write`, `read`, `append`, `clear`) | Pro / Enterprise |
+
+### Workspace & Engineering Tools (Developer Baseline)
+| Tool | Description | Tier Availability |
+|---|---|:---:|
+| `read_file` | Read content & line ranges of workspace files | All Tiers (Free, Pro, Enterprise) |
+| `write_file` | Create new files or overwrite existing source code | All Tiers (Free, Pro, Enterprise) |
+| `edit_file` | Search & replace exact target code snippets | All Tiers (Free, Pro, Enterprise) |
+| `multi_edit_file` | Apply batch snippet replacements in a single atomic tool call | All Tiers (Free, Pro, Enterprise) |
+| `run_command` | Execute live terminal commands (`npm test`, `tsc`, `pytest`) | All Tiers (Free, Pro, Enterprise) |
+| `list_dir` | List contents of workspace directories | All Tiers (Free, Pro, Enterprise) |
+| `tree_view` | Generate visual ASCII directory tree structures for workspace paths | All Tiers (Free, Pro, Enterprise) |
+| `file_info` | Get file metadata, exact line counts, size, & modification timestamps | All Tiers (Free, Pro, Enterprise) |
+| `grep_search` | String/regex pattern search across entire codebase | All Tiers (Free, Pro, Enterprise) |
+| `glob_search` | Filter workspace files by file glob patterns | All Tiers (Free, Pro, Enterprise) |
+| `fetch_url` | Fetch web API documentation, specs, or external web URLs | All Tiers (Free, Pro, Enterprise) |
+| `git_diff` | Query uncommitted workspace git diff directly inside execution loop | All Tiers (Free, Pro, Enterprise) |
+| `ask_user` | Request missing secret credentials or API keys | All Tiers (Free, Pro, Enterprise) |
+| `speak_text` | Read text phrases out loud via ElevenLabs AI Human Voice (Pro/Enterprise) or Windows SAPI5 (Free) | All Tiers (Free, Pro, Enterprise) |
+| `task_completed` | Conclude autonomous goal execution with verification and report | All Tiers (Free, Pro, Enterprise) |
 
 ---
 
@@ -273,11 +303,17 @@ Scout is built for uninterrupted autonomy across multiple LLM providers:
 
 ---
 
-## Dual Interaction Modes (Text & Voice)
+## Conversational Voice Co-Pilot & Audio Engine
 
-When starting interactive sessions in `scout agent`, `scout init` (ask mode), or `scout search`, Scout presents interactive options:
-1. **Text Interaction**: Standard command/prompt input -> Text response in terminal.
-2. **Audio Interaction**: Voice command input via microphone Speech-to-Text (STT) -> Text response + Audio response spoken out loud via Text-to-Speech (TTS).
+When starting interactive sessions in `scout agent` (`-V` or `--voice`), `scout init` (ask mode), or `scout search`, Scout presents full two-way audio dialogue:
+
+1. **Native C# High-Performance Audio Capture**: Built-in standalone Win32 `waveIn` audio recording engine (`scout_audio_recorder.exe`) compiled directly via native Windows toolchain without requiring Python or external heavy runtime dependencies.
+2. **Real-Time Voice Activity Detection (VAD)**: Intelligent RMS audio power monitoring with a 2.5-second silence debounce cutoff, allowing developers to speak natural multi-sentence thoughts without mid-sentence interruptions.
+3. **Groq Whisper STT with Developer Vocabulary Hints**: Lightning-fast speech-to-text powered by `whisper-large-v3-turbo` with technical prompt biasing (e.g., *Scout, Chrome, Notepad, VS Code, TypeScript, Python*) to prevent mishearing developer commands.
+4. **Ultra-Realistic ElevenLabs Human Voice TTS**:
+   - **Pro & Enterprise Tiers**: Full access to **ElevenLabs AI Voice Synthesis** (`eleven_turbo_v2_5`, PCM 24kHz / WAV container) delivering human-quality, natural speech dialogue.
+   - **Developer Free Tier**: Fully supported with local Windows SAPI5 speech synthesis (zero API billing cost).
+5. **Conversational Co-Pilot Persona**: Instant spoken acknowledgment (e.g., *"On it! Opening Chrome for you."*) and warm conversational completion summaries rather than dry robotic execution logs.
 
 ---
 
@@ -287,7 +323,7 @@ Inside an active `scout agent` interactive session, type any slash command to tr
 
 - `/help` — Display comprehensive guide to all 15 tools and interactive slash commands.
 - `/voice` — Activate microphone Speech-to-Text (STT) listener to speak your prompt into CLI.
-- `/speak <text>` — Read entered text out loud via Text-to-Speech (TTS) voice synthesis.
+- `/speak <text>` — Read entered text out loud via ElevenLabs AI (Pro/Enterprise) or SAPI5 (Free).
 - `/tree [dir]` — Render an interactive visual directory tree of any workspace folder.
 - `/status` or `/stats` — View real-time session telemetry (steps executed, tool call count, modified files, elapsed time, branch info).
 - `/test [cmd]` — Auto-detect and run project verification test suite directly inside session context.
@@ -301,12 +337,18 @@ Inside an active `scout agent` interactive session, type any slash command to tr
 
 ---
 
-## What's New in v9.0.5
-- **Autonomous Computer-Use & Desktop App Operator**: Native desktop application control (Notepad, Excel, VS Code, Browser) with full mouse, keyboard, hotkey, and window focus management across Windows, macOS, and Linux.
+## What's New in v9.0.7
+- **Ultra-Realistic ElevenLabs AI Voice Engine**: Integrated human-grade voice synthesis via ElevenLabs for Pro and Enterprise subscribers, bringing lifelike conversational audio feedback directly to the CLI co-pilot.
+- **Native C# Audio Recorder with Real-Time VAD**: Standalone Win32 `waveIn` audio recording binary (`scout_audio_recorder.exe`) with RMS energy detection and 2.5s silence debounce cutoff.
+- **Zero-Latency Groq Whisper STT**: Integrated Groq `whisper-large-v3-turbo` with specialized developer vocabulary hints to eliminate speech recognition errors.
+- **Intelligent Single-Step App Intent Engine (`checkSimpleAppAction`)**: Natural language comprehension for desktop app commands across English and Hinglish (e.g., *"open chrome"*, *"chrome open kar do"*, *"launch vscode"*), terminating immediately on Step 1 without unnecessary repository file exploration.
+- **Autonomous Computer-Use & Desktop App Operator**: Native desktop application control (Notepad, Excel, VS Code, Browser) with full mouse, keyboard, hotkey, and window focus management across Windows, macOS, and Linux powered by the native `scout_driver.exe` engine.
+- **Autonomous Browser Automation & Document Download Engine**: Fully automated web browsing (`browser_navigate`, `browser_inspect`, `browser_click`, `browser_type`, `browser_select`, `browser_scroll`, `browser_content`, `browser_screenshot`, `browser_download`) with DOM extraction and automatic file downloads to `downloads/`.
+- **Cognitive Scratchpad & Working Memory (`scratchpad`)**: Long-horizon multi-step reasoning memory (`write`, `read`, `append`, `clear`) saved to `.ft/scratchpad.md`, keeping model context concise and focused.
 - **Strict Execution Intent Alignment (`USER INTENT > TOOL CONVENIENCE`)**: Differentiates between outcome and execution requirements; strictly blocks silent filesystem shortcuts when application interaction is requested.
 - **Bounded Computer Recovery Loop**: Structured action feedback (`{ success, action, error, recoverable }`) with automated re-observation, window refocusing, and retries.
 - **Action Verifier & Anti-Substitute Path Rejection**: Verifies true destination (resolving Windows OneDrive/Desktop and `~/Desktop`) and rejects substitute files created in the workspace root.
-- **Interactive Web Dashboard & Sync Server (`scout dashboard`)**: Launch a local web GUI to visually inspect repository maps, audit logs, plan details, and live agent controls.
+- **Interactive Web Dashboard & Sync Server (`scout dashboard`)**: Launch a local web GUI to visually inspect repository maps, audit logs, plan details, live agent controls, and subscription tiers.
 - **Developer Authentication Guard (`scout login` / `signup` / `auth`)**: Unified account management with Firebase and Holosene token authentication, securing command execution and session persistence.
 - **Quota & Subscription Management (`scout quota` / `plan`)**: Easily inspect real-time usage quotas, track billing renewal cycles, switch between tiers, or configure BYOK (Bring-Your-Own-Key) access.
 - **Automated Model Benchmark Suite (`scout benchmark`)**: Run live end-to-end latency and throughput benchmarks (tokens/sec) across all configured LLM providers (Nemotron, Qwen, Gemini, GPT).

package/bin/src/commands/agent.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"agent.d.ts","sourceRoot":"","sources":["agent.ts"],"names":[],"mappings":"AA6BA,MAAM,WAAW,YAAY;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,MAAM,GAAG,QAAQ,GAAG,KAAK,CAAC;IACpC,WAAW,EAAE,MAAM,CAAC;CACvB;AAKD,wBAAgB,cAAc,CAAC,MAAM,EAAE,YAAY,EAAE,QAKpD;AAED,wBAAgB,cAAc,IAAI,YAAY,EAAE,CAO/C;AAED,MAAM,WAAW,YAAY;IACzB,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,MAAM,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC5B,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,KAAK,CAAC,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAAC;IACpC,GAAG,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,GAAG,SAAS,CAAC;IACpC,IAAI,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC3B,GAAG,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IACzB,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,SAAS,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC/B,UAAU,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAChC,KAAK,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC3B,QAAQ,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC9B,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,MAAM,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC7B,GAAG,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC1B,KAAK,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC5B,MAAM,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;CAC/B;AAED,wBAAgB,wBAAwB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAsDlE;AAED,wBAAgB,uBAAuB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAG3E;AAED,MAAM,WAAW,gBAAgB;IAC7B,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,UAAU,GAAG,QAAQ,GAAG,QAAQ,GAAG,MAAM,GAAG,MAAM,GAAG,KAAK,CAAC;IACvE,UAAU,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAChC,WAAW,CAAC,EAAE,MAAM,EAAE,GAAG,SAAS,CAAC;CACtC;AAED,wBAAgB,qBAAqB,CAAC,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,GAAG,gBAAgB,CAoF5F;AAED,wBAAgB,yBAAyB,CACrC,UAAU,EAAE,MAAM,EAClB,aAAa,EAAE,MAAM,GAAG,SAAS,EACjC,SAAS,EAAE,MAAM,EAAE,GACpB,MAAM,EAAE,CAgGV;AAED,wBAAsB,iBAAiB,CAAC,cAAc,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,GAAG,MAAM,CAAC,CAMxF;AAED,wBAAsB,WAAW,CAAC,SAAS,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,YAAY,iBA4nC3E"}
+{"version":3,"file":"agent.d.ts","sourceRoot":"","sources":["agent.ts"],"names":[],"mappings":"AA6BA,MAAM,WAAW,YAAY;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,MAAM,GAAG,QAAQ,GAAG,KAAK,CAAC;IACpC,WAAW,EAAE,MAAM,CAAC;CACvB;AA6CD,wBAAgB,cAAc,CAAC,MAAM,EAAE,YAAY,EAAE,QAKpD;AAED,wBAAgB,cAAc,IAAI,YAAY,EAAE,CAO/C;AAED,MAAM,WAAW,YAAY;IACzB,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,MAAM,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC5B,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,KAAK,CAAC,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAAC;IACpC,GAAG,CAAC,EAAE,MAAM,GAAG,MAAM,EAAE,GAAG,SAAS,CAAC;IACpC,IAAI,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC3B,GAAG,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IACzB,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,SAAS,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC/B,UAAU,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAChC,KAAK,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC3B,QAAQ,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC9B,IAAI,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAC1B,MAAM,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC7B,GAAG,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC1B,KAAK,CAAC,EAAE,OAAO,GAAG,SAAS,CAAC;IAC5B,MAAM,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;CAC/B;AAED,wBAAgB,wBAAwB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAsDlE;AAED,wBAAgB,uBAAuB,CAAC,OAAO,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAG3E;AAED,MAAM,WAAW,gBAAgB;IAC7B,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,UAAU,GAAG,QAAQ,GAAG,QAAQ,GAAG,MAAM,GAAG,MAAM,GAAG,KAAK,CAAC;IACvE,UAAU,CAAC,EAAE,MAAM,GAAG,SAAS,CAAC;IAChC,WAAW,CAAC,EAAE,MAAM,EAAE,GAAG,SAAS,CAAC;CACtC;AAED,wBAAgB,qBAAqB,CAAC,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,GAAG,gBAAgB,CAoF5F;AAED,wBAAgB,yBAAyB,CACrC,UAAU,EAAE,MAAM,EAClB,aAAa,EAAE,MAAM,GAAG,SAAS,EACjC,SAAS,EAAE,MAAM,EAAE,GACpB,MAAM,EAAE,CAgGV;AAED,wBAAsB,iBAAiB,CAAC,cAAc,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,GAAG,MAAM,CAAC,CAMxF;AAED,wBAAsB,WAAW,CAAC,SAAS,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,YAAY,iBA+nC3E"}

package/bin/src/commands/agent.js

@@ -18,6 +18,44 @@ import { promisify } from 'util';
 const execAsync = promisify(exec);
 const FT_DIR = path.join(process.cwd(), '.ft', 'scout');
 const SCAN_CACHE = path.join(FT_DIR, 'scan-report.json');
+function getConversationalAcknowledgment(goal) {
+    const lower = goal.toLowerCase().trim();
+    if (/^(hi|hello|hey|sup|namaste)/i.test(lower)) {
+        return "Hey there! How can I help you today?";
+    }
+    if (lower.startsWith('open ') || lower.startsWith('launch ')) {
+        const app = goal.slice(5).trim();
+        return `On it! Opening ${app} for you.`;
+    }
+    if (lower.startsWith('close ') || lower.startsWith('kill ')) {
+        const app = goal.slice(6).trim();
+        return `Sure, closing ${app}.`;
+    }
+    if (lower.startsWith('create ') || lower.startsWith('make ')) {
+        return "Understood! Getting started on creating that.";
+    }
+    if (lower.startsWith('fix ') || lower.startsWith('debug ')) {
+        return "Let's track that down. Inspecting the issue now.";
+    }
+    if (lower.startsWith('run ') || lower.startsWith('test ')) {
+        return "Running that right away.";
+    }
+    const cleanGoal = goal.replace(/["'`]/g, '');
+    const shortGoal = cleanGoal.length > 30 ? cleanGoal.slice(0, 30) + '...' : cleanGoal;
+    return `Got it! Working on ${shortGoal}.`;
+}
+function formatConversationalClosing(summary) {
+    let text = summary.trim();
+    text = text.replace(/^(execution|task|action)\s*(completed|finished|summary)?\s*:\s*/i, '');
+    text = text.replace(/^mock execution completed successfully for goal:\s*"[^"]*"\.?\s*/i, '');
+    text = text.replace(/`[^`]+`/g, (m) => m.replace(/`/g, ''));
+    text = text.replace(/\[[^\]]+\]/g, '');
+    text = text.replace(/\s+/g, ' ').trim();
+    if (!text.endsWith('.') && !text.endsWith('!') && !text.endsWith('?')) {
+        text += '.';
+    }
+    return text;
+}
 export function saveScanReport(issues) {
     if (!fs.existsSync(FT_DIR)) {
         fs.mkdirSync(FT_DIR, { recursive: true });
@@ -342,6 +380,8 @@ ${chalk.cyan('/exit')}        - Exit session
             if (transcript && transcript.trim()) {
                 rawGoal = transcript.trim();
                 safeNote(` Voice Command Received: "${chalk.bold.green(rawGoal)}"`, ' Scout STT Input');
+                const ack = getConversationalAcknowledgment(rawGoal);
+                speakText(ack, { async: true });
             }
             else {
                 safeNote(chalk.yellow('No speech transcript detected or listener timed out.'), ' Scout Audio Interaction');
@@ -1087,8 +1127,9 @@ ${execResult.summary}
  `.trim();
         safeNote(renderMarkdown(teardownMd), ' Scout Execution Teardown Report');
         if (isAudioMode && execResult?.summary) {
-            safeNote(` Speaking summary response out loud...`, ' Scout Audio Output');
-            await speakText(execResult.summary);
+            safeNote(` Speaking conversational response out loud...`, ' Scout Audio Output');
+            const spokenClosing = formatConversationalClosing(execResult.summary);
+            await speakText(spokenClosing);
         }
         if (modifiedFiles.length === 0)
             continue;