# dexter-666/jarvis-ia architecture

> Architecture diagram of the GitHub repository dexter-666/jarvis-ia, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-05-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dexter-666/jarvis-ia
- Repository: https://github.com/dexter-666/jarvis-ia

## Overview

1. **Overall shape**
   - This is a Windows desktop assistant built around a central Python entrypoint (`main.py`) that orchestrates a local UI, voice input, task execution, and a set of capability modules under `actions/`.
   - The repo is not a generic library; it is a tightly integrated desktop agent with OS automation, LLM-backed reasoning, and persistent local state.

2. **Runtime and platform boundary**
   - The architecture is strongly Windows-oriented: the README and filenames point to hotkeys, Win32 calls, `pycaw`, `pygetwindow`, `psutil`, `WMI`, and `winreg`.
   - Startup is handled through desktop launchers (`Iniciar JARVIS Beta.vbs`, `launchers/start_jarvis_beta.bat`) and installation scripts (`Instalar_JARVIS.bat`, `install.py`), which indicates a local, user-machine deployment model rather than a server app.

3. **Main orchestration layer**
   - `main.py` is the probable top-level coordinator for bootstrapping the assistant.
   - `agent/task_queue.py` suggests asynchronous or serialized task handling, likely used to decouple user input from action execution and prevent concurrent conflicts across automation modules.

4. **Interaction channels**
   - The assistant appears to accept at least three primary input paths:
     - **Voice** via Vosk model assets in `config/vosk_model/`
     - **Global hotkey** activation (`Insert`) for immediate microphone capture
     - **UI interaction** via PyQt6, including a holographic/Glassmorphism interface
   - `actions/native_ui.py` and `actions/visual_click.py` imply that UI interaction is both visual and action-driven, not just text-based.

5. **Speech and local recognition**
   - The bundled Vosk model under `config/vosk_model/` implies offline speech recognition is a core subsystem, not an optional add-on.
   - This matters architecturally because speech input can be processed locally before any LLM or cloud service is involved, reducing latency and dependency on internet connectivity.

6. **LLM and reasoning boundary**
   - `actions/openrouter_agent.py` is the clearest indicator of a cloud LLM integration path, likely used for general reasoning, planning, or natural-language interpretation.
   - `core/prompt.txt` and `beta_config.py` likely define the assistant’s persona, behavior rules, and model/runtime settings.
   - The design suggests a split between **local orchestration** and **remote model inference**.

7. **Capability modules as plugins**
   - The `actions/` directory is the main functional surface area and reads like a plugin layer.
   - Key modules indicate distinct domains:
     - `browser_control.py`, `web_navigation.py` for browser and web automation
     - `terminal_agent.py` for shell/command execution
     - `document_creator.py`, `document_manager.py`, `smart_file_organizer.py` for file/document workflows
     - `whatsapp.py`, `unified_communications.py` for outbound messaging
     - `contextual_control.py`, `proactive_automation.py` for environment-aware automation
     - `screen_vision.py`, `visual_click.py` for vision-based interaction
     - `self_edit.py`, `tool_creator.py`, `auto_programmer.py` for code generation and self-extension

8. **Self-modifying / code-generation path**
   - The README explicitly describes autonomous programming in a sandbox, and the file names confirm that through `auto_programmer.py`, `self_edit.py`, and `tool_creator.py`.
   - Architecturally, this is a high-risk boundary: generated code appears to be created, tested, and then conditionally integrated into the assistant’s capability set.
   - For an architecture diagram, this should be shown as a separate “dynamic skill generation” subsystem connected to the action registry, not part of the normal request path.

9. **Environment awareness and proactive behavior**
   - `contextual_control.py` and `proactive_automation.py` imply the assistant can inspect current system state and take actions without an explicit command.
   - The README mentions volume, brightness, energy, and Focus Assist control, so the assistant likely observes foreground window/context and then decides whether to adjust system behavior.

10. **File and document workflow**
   - `document_manager.py` and `document_creator.py` point to content handling for creating, opening, viewing, and editing documents.
   - `smart_file_organizer.py` adds a classification/deduplication layer, with the README mentioning exact duplicate removal via `MD5`.
   - This subsystem likely sits between the assistant and the local filesystem, with a focus on user data management.

11. **Memory and persistent state**
   - There are multiple local persistence locations:
     - `memory/long_term.json` for longer-lived memory or preferences
     - `config/user_profile.json` for user-specific configuration
     - `config/morning_brief_state.json` and `config/vision_guardian_state.json` for feature state
   - This indicates the assistant is stateful across sessions and likely uses local JSON as a lightweight persistence layer rather than a database.

12. **Configuration and secrets**
   - `config/api_keys.example.json` shows external service credentials are expected but kept out of source control.
   - `config/accessibility_config.json` suggests accessibility and UI-behavior tuning are separated from code.
   - `sitecustomize.py` may be used to inject environment/runtime tweaks early in Python startup.

13. **Communications integration**
   - `actions/unified_communications.py` is a central boundary for outward messaging, with README support for email, Telegram, Discord, and WhatsApp.
   - This is a distinct integration layer from core reasoning: the assistant decides what to send, and this module handles channel-specific delivery.

14. **What the diagram should emphasize**
   - Show a central assistant core receiving input from voice, hotkey, and UI.
   - Route requests through a task queue / orchestrator.
   - Branch from there into capability modules in `actions/`.
   - Separate local state/config/memory from cloud LLM calls and from OS-level automation.
   - Highlight the self-programming path as its own special subsystem because it can create or modify capabilities at runtime.

Main entry points: [`main.py`](https://github.com/dexter-666/jarvis-ia/blob/main/main.py) (Main), [`agent/task_queue.py`](https://github.com/dexter-666/jarvis-ia/blob/main/agent/task_queue.py) (Task Queue), [`actions/auto_programmer.py`](https://github.com/dexter-666/jarvis-ia/blob/main/actions/auto_programmer.py) (Auto Programmer), [`actions/native_ui.py`](https://github.com/dexter-666/jarvis-ia/blob/main/actions/native_ui.py) (Native UI)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_runtime["Runtime"]
  node_sitecustomize["Site Custom<br/>runtime-hook<br/>[sitecustomize.py]"]
end

subgraph group_control["Control Flow"]
  node_main_py["Main<br/>entrypoint<br/>[main.py]"]
  node_task_queue["Task Queue<br/>scheduler<br/>[task_queue.py]"]
  node_native_ui["Native UI<br/>[native_ui.py]"]
  node_openrouter_agent["LLM Agent<br/>cloud-llm"]
  node_voice_model[("Vosk Model<br/>speech-model")]
end

subgraph group_capabilities["Capabilities"]
  node_contextual_control["Context Control<br/>system-awareness"]
  node_proactive_automation["Proactive Auto<br/>automation"]
  node_browser_control["Browser Control<br/>web-automation<br/>[browser_control.py]"]
  node_web_navigation["Web Navigation<br/>[web_navigation.py]"]
  node_terminal_agent["Terminal Agent<br/>shell-exec<br/>[terminal_agent.py]"]
  node_document_manager["Doc Manager<br/>document-workflow"]
  node_document_creator["Doc Creator<br/>content-generation"]
  node_smart_file_organizer["File Organizer<br/>filesystem"]
  node_screen_vision["Screen Vision<br/>computer-vision<br/>[screen_vision.py]"]
  node_visual_click["Visual Click<br/>ui-automation<br/>[visual_click.py]"]
  node_communications["Comms Hub<br/>messaging"]
  node_whatsapp["WhatsApp<br/>channel-adapter<br/>[whatsapp.py]"]
  node_auto_programmer["Auto Programmer<br/>code-gen<br/>[auto_programmer.py]"]
  node_self_edit["Self Edit<br/>self-modification<br/>[self_edit.py]"]
  node_tool_creator["Tool Creator<br/>plugin-builder<br/>[tool_creator.py]"]
end

subgraph group_state["State & Config"]
  node_memory[("Long Memory<br/>persistent-state<br/>[long_term.json]")]
  node_user_profile["User Profile<br/>config-state<br/>[user_profile.json]"]
  node_feature_state["Feature State<br/>state-files"]
  node_vision_state["Vision State<br/>state-files"]
  node_accessibility["Accessibility<br/>settings"]
  node_api_keys["API Keys<br/>secrets-template"]
  node_prompt["Prompt<br/>persona<br/>[prompt.txt]"]
  node_bootstrap["Bootstrap<br/>runtime-config<br/>[beta_config.py]"]
end

subgraph group_packaging["Packaging"]
  node_launcher_vbs["VBS Launcher<br/>startup-script"]
  node_launcher_bat["Batch Launcher<br/>startup-script"]
  node_installer_bat["Install Script<br/>installer"]
  node_installer_py["Installer<br/>[install.py]"]
  node_vosk_downloader["Vosk Downloader<br/>setup-tool<br/>[download_vosk.py]"]
end

node_launcher_vbs -->|"start"| node_main_py
node_launcher_bat -->|"start"| node_main_py
node_installer_bat -->|"delegates"| node_installer_py
node_installer_py -->|"prepares"| node_vosk_downloader
node_main_py -->|"dispatch"| node_task_queue
node_main_py -->|"renders"| node_native_ui
node_main_py -->|"loads"| node_voice_model
node_main_py -->|"calls"| node_openrouter_agent
node_main_py -->|"inspects"| node_contextual_control
node_main_py -->|"triggers"| node_proactive_automation
node_main_py -->|"reads/writes"| node_memory
node_main_py -->|"reads/writes"| node_user_profile
node_main_py -->|"reads/writes"| node_feature_state
node_main_py -->|"reads/writes"| node_vision_state
node_main_py -->|"configures"| node_prompt
node_main_py -->|"configures"| node_bootstrap
node_main_py -->|"hooks"| node_sitecustomize
node_task_queue -->|"executes"| node_browser_control
node_task_queue -->|"executes"| node_web_navigation
node_task_queue -->|"executes"| node_terminal_agent
node_task_queue -->|"executes"| node_document_manager
node_task_queue -->|"executes"| node_document_creator
node_task_queue -->|"executes"| node_smart_file_organizer
node_task_queue -->|"executes"| node_screen_vision
node_task_queue -->|"executes"| node_visual_click
node_task_queue -->|"executes"| node_communications
node_communications -->|"adapts"| node_whatsapp
node_task_queue -->|"executes"| node_auto_programmer
node_auto_programmer -->|"creates"| node_tool_creator
node_auto_programmer -->|"patches"| node_self_edit
node_screen_vision -->|"feeds"| node_visual_click
node_contextual_control -->|"drives"| node_proactive_automation
node_native_ui -->|"submits"| node_task_queue
node_voice_model -->|"submits"| node_task_queue

click node_main_py "https://github.com/dexter-666/jarvis-ia/blob/main/main.py"
click node_task_queue "https://github.com/dexter-666/jarvis-ia/blob/main/agent/task_queue.py"
click node_native_ui "https://github.com/dexter-666/jarvis-ia/blob/main/actions/native_ui.py"
click node_openrouter_agent "https://github.com/dexter-666/jarvis-ia/blob/main/actions/openrouter_agent.py"
click node_voice_model "https://github.com/dexter-666/jarvis-ia/tree/main/config/vosk_model"
click node_contextual_control "https://github.com/dexter-666/jarvis-ia/blob/main/actions/contextual_control.py"
click node_proactive_automation "https://github.com/dexter-666/jarvis-ia/blob/main/actions/proactive_automation.py"
click node_browser_control "https://github.com/dexter-666/jarvis-ia/blob/main/actions/browser_control.py"
click node_web_navigation "https://github.com/dexter-666/jarvis-ia/blob/main/actions/web_navigation.py"
click node_terminal_agent "https://github.com/dexter-666/jarvis-ia/blob/main/actions/terminal_agent.py"
click node_document_manager "https://github.com/dexter-666/jarvis-ia/blob/main/actions/document_manager.py"
click node_document_creator "https://github.com/dexter-666/jarvis-ia/blob/main/actions/document_creator.py"
click node_smart_file_organizer "https://github.com/dexter-666/jarvis-ia/blob/main/actions/smart_file_organizer.py"
click node_screen_vision "https://github.com/dexter-666/jarvis-ia/blob/main/actions/screen_vision.py"
click node_visual_click "https://github.com/dexter-666/jarvis-ia/blob/main/actions/visual_click.py"
click node_communications "https://github.com/dexter-666/jarvis-ia/blob/main/actions/unified_communications.py"
click node_whatsapp "https://github.com/dexter-666/jarvis-ia/blob/main/actions/whatsapp.py"
click node_auto_programmer "https://github.com/dexter-666/jarvis-ia/blob/main/actions/auto_programmer.py"
click node_self_edit "https://github.com/dexter-666/jarvis-ia/blob/main/actions/self_edit.py"
click node_tool_creator "https://github.com/dexter-666/jarvis-ia/blob/main/actions/tool_creator.py"
click node_memory "https://github.com/dexter-666/jarvis-ia/blob/main/memory/long_term.json"
click node_user_profile "https://github.com/dexter-666/jarvis-ia/blob/main/config/user_profile.json"
click node_feature_state "https://github.com/dexter-666/jarvis-ia/blob/main/config/morning_brief_state.json"
click node_vision_state "https://github.com/dexter-666/jarvis-ia/blob/main/config/vision_guardian_state.json"
click node_accessibility "https://github.com/dexter-666/jarvis-ia/blob/main/config/accessibility_config.json"
click node_api_keys "https://github.com/dexter-666/jarvis-ia/blob/main/config/api_keys.example.json"
click node_prompt "https://github.com/dexter-666/jarvis-ia/blob/main/core/prompt.txt"
click node_bootstrap "https://github.com/dexter-666/jarvis-ia/blob/main/beta_config.py"
click node_launcher_vbs "https://github.com/dexter-666/jarvis-ia/blob/main/Iniciar JARVIS Beta.vbs"
click node_launcher_bat "https://github.com/dexter-666/jarvis-ia/blob/main/launchers/start_jarvis_beta.bat"
click node_installer_bat "https://github.com/dexter-666/jarvis-ia/blob/main/Instalar_JARVIS.bat"
click node_installer_py "https://github.com/dexter-666/jarvis-ia/blob/main/install.py"
click node_vosk_downloader "https://github.com/dexter-666/jarvis-ia/blob/main/download_vosk.py"
click node_sitecustomize "https://github.com/dexter-666/jarvis-ia/blob/main/sitecustomize.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_sitecustomize toneBlue
class node_main_py,node_task_queue,node_native_ui,node_openrouter_agent,node_voice_model toneAmber
class node_contextual_control,node_proactive_automation,node_browser_control,node_web_navigation,node_terminal_agent,node_document_manager,node_document_creator,node_smart_file_organizer,node_screen_vision,node_visual_click,node_communications,node_whatsapp,node_auto_programmer,node_self_edit,node_tool_creator toneMint
class node_memory,node_user_profile,node_feature_state,node_vision_state,node_accessibility,node_api_keys,node_prompt,node_bootstrap toneRose
class node_launcher_vbs,node_launcher_bat,node_installer_bat,node_installer_py,node_vosk_downloader toneIndigo
```

## Components

### Runtime

Desktop assistant entrypoints and startup scripts

- [Site Custom](https://github.com/dexter-666/jarvis-ia/blob/main/sitecustomize.py): runtime-hook · Early Python startup customization hook · `sitecustomize.py`

### Control Flow

Core orchestration and input handling

- [Main](https://github.com/dexter-666/jarvis-ia/blob/main/main.py): entrypoint · Primary Python bootstrap and orchestration entrypoint · `main.py`
- [Task Queue](https://github.com/dexter-666/jarvis-ia/blob/main/agent/task_queue.py): scheduler · Serialized or asynchronous task dispatch for assistant actions · `agent/task_queue.py`
- [Native UI](https://github.com/dexter-666/jarvis-ia/blob/main/actions/native_ui.py): ui · Desktop interface and user interaction layer · `actions/native_ui.py`
- [LLM Agent](https://github.com/dexter-666/jarvis-ia/blob/main/actions/openrouter_agent.py): cloud-llm · Remote reasoning and natural-language planning via OpenRouter · `actions/openrouter_agent.py`
- [Vosk Model](https://github.com/dexter-666/jarvis-ia/tree/main/config/vosk_model): speech-model · Offline speech recognition assets for local voice input · `config/vosk_model`

### Capabilities

Action modules that perform work

- [Context Control](https://github.com/dexter-666/jarvis-ia/blob/main/actions/contextual_control.py): system-awareness · Inspects foreground state and environment before acting · `actions/contextual_control.py`
- [Proactive Auto](https://github.com/dexter-666/jarvis-ia/blob/main/actions/proactive_automation.py): automation · Event- or state-driven automation without explicit prompts · `actions/proactive_automation.py`
- [Browser Control](https://github.com/dexter-666/jarvis-ia/blob/main/actions/browser_control.py): web-automation · Controls browser sessions and page interactions · `actions/browser_control.py`
- [Web Navigation](https://github.com/dexter-666/jarvis-ia/blob/main/actions/web_navigation.py): navigation · Browser/page traversal and web workflows · `actions/web_navigation.py`
- [Terminal Agent](https://github.com/dexter-666/jarvis-ia/blob/main/actions/terminal_agent.py): shell-exec · Runs shell commands and terminal workflows · `actions/terminal_agent.py`
- [Doc Manager](https://github.com/dexter-666/jarvis-ia/blob/main/actions/document_manager.py): document-workflow · Open, manage, and manipulate local documents · `actions/document_manager.py`
- [Doc Creator](https://github.com/dexter-666/jarvis-ia/blob/main/actions/document_creator.py): content-generation · Creates documents and formatted output files · `actions/document_creator.py`
- [File Organizer](https://github.com/dexter-666/jarvis-ia/blob/main/actions/smart_file_organizer.py): filesystem · Classifies, deduplicates, and organizes local files · `actions/smart_file_organizer.py`
- [Screen Vision](https://github.com/dexter-666/jarvis-ia/blob/main/actions/screen_vision.py): computer-vision · Visual perception of the desktop for interaction support · `actions/screen_vision.py`
- [Visual Click](https://github.com/dexter-666/jarvis-ia/blob/main/actions/visual_click.py): ui-automation · Coordinates click-based interaction using visual targets · `actions/visual_click.py`
- [Comms Hub](https://github.com/dexter-666/jarvis-ia/blob/main/actions/unified_communications.py): messaging · Unified outbound messaging across email and chat channels · `actions/unified_communications.py`
- [WhatsApp](https://github.com/dexter-666/jarvis-ia/blob/main/actions/whatsapp.py): channel-adapter · WhatsApp-specific messaging integration · `actions/whatsapp.py`
- [Auto Programmer](https://github.com/dexter-666/jarvis-ia/blob/main/actions/auto_programmer.py): code-gen · Generates new code or tools in a sandboxed flow · `actions/auto_programmer.py`
- [Self Edit](https://github.com/dexter-666/jarvis-ia/blob/main/actions/self_edit.py): self-modification · Applies or prepares assistant code changes · `actions/self_edit.py`
- [Tool Creator](https://github.com/dexter-666/jarvis-ia/blob/main/actions/tool_creator.py): plugin-builder · Creates new capability modules or tools · `actions/tool_creator.py`

### State & Config

Persistent local data and runtime settings

- [Long Memory](https://github.com/dexter-666/jarvis-ia/blob/main/memory/long_term.json): persistent-state · Long-lived preferences and remembered context · `memory/long_term.json`
- [User Profile](https://github.com/dexter-666/jarvis-ia/blob/main/config/user_profile.json): config-state · User-specific settings and profile data · `config/user_profile.json`
- [Feature State](https://github.com/dexter-666/jarvis-ia/blob/main/config/morning_brief_state.json): state-files · Persistent feature flags and runtime state snapshots · `config/morning_brief_state.json`
- [Vision State](https://github.com/dexter-666/jarvis-ia/blob/main/config/vision_guardian_state.json): state-files · Persistent state for vision guardian behavior · `config/vision_guardian_state.json`
- [Accessibility](https://github.com/dexter-666/jarvis-ia/blob/main/config/accessibility_config.json): settings · Accessibility and UI behavior configuration · `config/accessibility_config.json`
- [API Keys](https://github.com/dexter-666/jarvis-ia/blob/main/config/api_keys.example.json): secrets-template · Template for external service credentials · `config/api_keys.example.json`
- [Prompt](https://github.com/dexter-666/jarvis-ia/blob/main/core/prompt.txt): persona · Assistant behavior and instruction prompt · `core/prompt.txt`
- [Bootstrap](https://github.com/dexter-666/jarvis-ia/blob/main/beta_config.py): runtime-config · Assistant runtime settings and startup configuration · `beta_config.py`

### Packaging

Install and launch helpers

- [VBS Launcher](https://github.com/dexter-666/jarvis-ia/blob/HEAD/Iniciar%20JARVIS%20Beta.vbs): startup-script · Windows desktop launcher for assistant startup · `Iniciar JARVIS Beta.vbs`
- [Batch Launcher](https://github.com/dexter-666/jarvis-ia/blob/main/launchers/start_jarvis_beta.bat): startup-script · Batch launcher for local startup · `launchers/start_jarvis_beta.bat`
- [Install Script](https://github.com/dexter-666/jarvis-ia/blob/main/Instalar_JARVIS.bat): installer · Windows installation helper · `Instalar_JARVIS.bat`
- [Installer](https://github.com/dexter-666/jarvis-ia/blob/main/install.py): installer · Python installation and setup helper · `install.py`
- [Vosk Downloader](https://github.com/dexter-666/jarvis-ia/blob/main/download_vosk.py): setup-tool · Downloads or prepares the local speech model · `download_vosk.py`

## Connections

- VBS Launcher → Main: start · Windows launcher starts the assistant
- Batch Launcher → Main: start · Batch launcher starts the assistant
- Install Script → Installer: delegates · Windows installer script invokes Python setup
- Installer → Vosk Downloader: prepares · Setup can fetch or prepare the speech model
- Main → Task Queue: dispatch · Main runtime hands work to the task queue
- Main → Native UI: renders · Bootstraps the desktop UI
- Main → Vosk Model: loads · Initializes offline speech recognition assets
- Main → LLM Agent: calls · Routes reasoning or planning to the cloud LLM agent
- Main → Context Control: inspects · Reads system context before executing actions
- Main → Proactive Auto: triggers · Schedules or launches proactive behaviors
- Main → Long Memory: reads/writes · Uses long-term memory across sessions
- Main → User Profile: reads/writes · Loads and persists user preferences
- Main → Feature State: reads/writes · Persists assistant feature state
- Main → Vision State: reads/writes · Persists vision-related state
- Main → Prompt: configures · Uses the prompt as behavior guidance
- Main → Bootstrap: configures · Reads runtime settings and model parameters
- Main → Site Custom: hooks · Applies early Python runtime customization
- Task Queue → Browser Control: executes · Serializes browser automation tasks
- Task Queue → Web Navigation: executes · Dispatches navigation work
- Task Queue → Terminal Agent: executes · Dispatches shell and command tasks
- Task Queue → Doc Manager: executes · Dispatches document management work
- Task Queue → Doc Creator: executes · Dispatches document creation work
- Task Queue → File Organizer: executes · Dispatches file organization work
- Task Queue → Screen Vision: executes · Dispatches visual analysis tasks
- Task Queue → Visual Click: executes · Dispatches vision-guided UI actions
- Task Queue → Comms Hub: executes · Dispatches outbound communications
- Comms Hub → WhatsApp: adapts · Channel-specific WhatsApp delivery
- Task Queue → Auto Programmer: executes · Dispatches dynamic code-generation tasks
- Auto Programmer → Tool Creator: creates · Builds new tools or capability modules
- Auto Programmer → Self Edit: patches · Produces or applies assistant code changes
- Screen Vision → Visual Click: feeds · Vision output informs click targeting
- Context Control → Proactive Auto: drives · Environment awareness feeds proactive actions
- Native UI → Task Queue: submits · UI-originated commands enter the task queue
- Vosk Model → Task Queue: submits · Transcribed voice commands enter the task queue
