Updates
Rolling release / release (push) Successful in 8m31s

This commit is contained in:
2026-09-13 22:24:14 -04:00
parent 1ca4224377
commit a097adf4eb
62 changed files with 2707 additions and 957 deletions
+13
View File
@@ -81,6 +81,12 @@ and Observe and control permits input within an explicit temporary grant.
Changing mode, duration, or budget revokes existing access. Screenshot dimensions
and WebP quality tune observation detail and processing cost.
Camera access is off by default. Press **Allow now** to start a temporary
grant; Jarvis can then capture one webcam still per `webcam` tool call. Apply
**Camera access** if you want the feature remembered. Turning that switch off
and applying, or changing device or duration, revokes an active grant. Stills
are wiped from `/tmp/jarvis-webcam` on revoke. This is not desktop ScreenCast.
## Complete daemon setting reference
### Identity
@@ -149,6 +155,13 @@ and WebP quality tune observation detail and processing cost.
- **Screenshot maximum edge (pixels)** — `screenshotMaxEdge`, default `1280`. Larger screenshots preserve detail but take more memory. Range: 6402560.
- **Screenshot quality (%)** — `screenshotQuality`, default `70`. Higher WebP quality preserves more text detail. Range: 3095.
### Camera
- **Camera access** — `webcamEnabled`, default `false`. Off by default. Press Allow now to start a grant even if this is off. Apply this switch if you want the feature remembered. Turning it off and applying revokes an active grant.
- **Camera device** — `webcamDevice`, default `""`. System default follows PipeWire. Refresh the list after connecting a camera.
- **Camera grant duration (minutes)** — `webcamGrantMinutes`, default `3`. Camera access expires automatically. Changing this revokes an active grant. Range: 115.
- **Camera still maximum edge (pixels)** — `webcamMaxEdge`, default `720`. Larger stills preserve detail but take more memory. Range: 3201280.
### Chat model
- **Chat model profile** — `modelProfile`, default `"laptop-16gb"`. Requires a daemon restart. GPU inference remains required. Choices: `laptop-4gb-mm` (Qwen3.5 0.8B, vision), `laptop-8gb`, `laptop-8gb-mm` (Qwen3.5 2B, vision), `laptop-16gb`, `desktop-gpu`.