Updates

docs/harness-integration.md

@@ -33,8 +33,11 @@ tool permissions to confirmation gates, and translates harness events into the
 D-Bus protocol. The harness cwd is the per-user agent workspace
 (`$XDG_DATA_HOME/jarvis/workspace`, default `~/.local/share/jarvis/workspace`),
 seeded from `vendor/agent-harness/agent-workspace` (`SOUL.md`, `IDENTITY.md`,
-`AGENTS.md`, `USER.md`, `MEMORY.md`, `BOOTSTRAP.md`, `PERSONA.md`). Voice turns inline those
-files. A first-run `BOOTSTRAP.md` ritual stays open until the agent overwrites
+`AGENTS.md`, `USER.md`, `MEMORY.md`, `BOOTSTRAP.md`, `PERSONA.md`). Voice turns
+inline workspace files into the system prompt. Settings **How they should act**
+notes are injected as a `## Acting` block in that system prompt only; they are
+not also inlined from `PERSONA.md`, and they override `SOUL.md` / `IDENTITY.md`
+for name and character. A first-run `BOOTSTRAP.md` ritual stays open until the agent overwrites
 it with `# completed`. Computer-use tools are custom harness tools backed by
 `computer-use/`; the computer-use layer never owns planning.
 

docs/settings.md

@@ -86,7 +86,7 @@ and WebP quality tune observation detail and processing cost.
 ### Identity
 
 - **Assistant name** — `assistantName`, default `"Jarvis"`. What to call the assistant in the tray HUD, spoken prompt, and workspace `IDENTITY.md`. Up to 32 characters. Apply writes the name without restarting `jarvisd`; the current conversation is reset so the new name takes effect.
-- **How they should act** — `assistantPrompt`, default `""`. Optional extra personality instructions (tone, habits, always/never). Shown as a multiline field under the name. Apply writes `PERSONA.md` and resets the conversation. Spoken safety rules still win. Up to 4000 characters.
+- **How they should act** — `assistantPrompt`, default `""`. Optional character instructions (tone, habits, always/never). Shown as a multiline field under the name. Apply writes `PERSONA.md` for the workspace copy and puts the notes in the **system prompt only**, where they override `SOUL.md` / `IDENTITY.md` for name and character. Speakable-text rules still apply so replies can be read aloud. Up to 4000 characters.
 
 ### Speech
 
@@ -151,7 +151,7 @@ and WebP quality tune observation detail and processing cost.
 
 ### Chat model
 
-- **Chat model profile** — `modelProfile`, default `"laptop-16gb"`. Requires a daemon restart. GPU inference remains required. Choices: `laptop-8gb`, `laptop-8gb-mm` (Qwen3.5 2B, vision), `laptop-16gb`, `desktop-gpu`.
+- **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`.
 - **Custom chat model** — `chatModel`, default `""`. Advanced: overrides the profile. Empty uses the profile model. Requires restart.
 
 ### Agent limits