gnome-jarvis/docs/capabilities.md

Capability catalog

Capabilities are exposed through harness tools and report their real runtime state. A capability can be registered while unavailable because its model is not downloaded, does not fit the selected GPU profile, or requires hardware that is not present.

Domain	Tools	Execution owner	Typical permission
Conversation	chat, plan, summarize, rewrite, code	Harness + QVAC master	read
Retrieval	embed, remember, ask-my-files, workspaces	QVAC master + local stores	read/write
Vision	screenshot, look-at-this, ocr, what-is-this, webcam	Portal + QVAC master	read
Speech	dictate, transcribe-file, meeting, speak, clone-voice	PipeWire + QVAC master	read/write
Language	translate, relay-voice	QVAC master	read
Media	imagine, edit-image, make-video, compose	Job runner + QVAC master	write
Training	teach-me	Isolated job + QVAC master	dangerous
Lab	bci, robot, world	Explicit lab adapters	read/write/dangerous
Search	web_search, google_search, fetch_page, web_fetch, wiki_search, hn_search, code_search, browser	Playwright Chromium sidecar	read (no extra keys)
Desktop	launch, focus, window, clipboard, media, settings	GNOME/GIO/D-Bus	read/write
Computer use	cu.observe, cu.find, cu.act, cu.click, cu.type, cu.key	CU session	computer-use

flowchart TB
  J((Jarvis))
  J --> C[Conversation\nchat · plan · code · summarize]
  J --> M[Memory\nembeddings · RAG · batch]
  J --> P[Perception\nscreenshot · OCR · webcam]
  J --> V[Voice\nwake · ASR · TTS · translation]
  J --> W[Search\nweb_search · fetch_page · browser]
  J --> G[Media\nimage · video · music]
  J --> D[Desktop\nGNOME · AT-SPI · computer use]
  J --> L[Lab\nLoRA · BCI · VLA · ABot-World]

All QVAC-facing capabilities use the master allowlist and scheduler. The UI must show unavailable reasons instead of hiding a feature or claiming that a job ran.