First Try: QVAC (QuantumVerse Automatic Computer)

2026-07-30 13:42:14 -04:00
parent f52168feb9
commit 32928f19bd
27 changed files with 2893 additions and 2 deletions
@@ -0,0 +1,89 @@
+# QVAC (local AI)
+
+The **QVAC** tab is an on-device assistant for the connected agent. Models run on your desktop; the agent only answers metrics tools over P2P.
+
+## First-time setup
+
+1. Open **QVAC** in the sidebar.
+2. **Continue** through the welcome screen.
+3. Review the system check (RAM, whether `@qvac/sdk` is installed).
+4. Pick a **model profile**:
+   - **Lite** — smallest download
+   - **Recommended** — best default (tool calling)
+   - **Strong** — larger model if you have RAM to spare
+5. **Download & load** (or continue in tools-only mode if the SDK is not installed).
+
+Re-run setup anytime with **Setup** in the QVAC header.
+
+## Using chat
+
+- Type a question or click a sample prompt.
+- Answers use live tools (`host_snapshot`, charts, anomalies, processes).
+- Tool chips under a reply show which RPCs ran.
+- **Unload** frees model memory (weights stay on disk).
+- **New chat** clears the conversation.
+
+### Good questions
+
+- “Summarize host health right now”
+- “Any open alerts or anomalies?”
+- “List charts related to disk”
+- “Why might CPU be high?” (uses CPU summary + snapshot)
+
+### Requires a connected agent
+
+Connect from the **Connect** tab first. If offline, tools return a clear error instead of inventing numbers.
+
+## Tools-only vs full QVAC
+
+| Mode | When | Behavior |
+|------|------|----------|
+| Full QVAC | `@qvac/sdk` installed + model loaded | Local Qwen (or other profile) + tools |
+| Tools-only | SDK missing or load failed | Grounded formatting of RPC results, no LLM |
+
+```bash
+npm i @qvac/sdk
+```
+
+Then re-run **Setup** in the QVAC tab.
+
+## Settings
+
+**Settings → QVAC**:
+
+- Default model profile
+- Inject local knowledge (guide + chart catalog into prompts)
+- Idle unload (minutes) — free RAM when idle; weights stay on disk
+
+## Settings
+
+**Settings → QVAC**:
+
+| Preference | Effect |
+|------------|--------|
+| Default model profile | Lite / Recommended / Strong / Tool-tiny (used on next Setup) |
+| Inject local knowledge | Keyword RAG over user-guide snippets + chart catalog |
+| Idle unload (minutes) | Unload model from RAM after inactivity (`0` = never) |
+| Open QVAC tab | Jump to the chat view |
+
+## Tools available to chat
+
+| Tool | Purpose |
+|------|---------|
+| `host_snapshot` | Live health + KPIs |
+| `search_charts` / `summarize_chart` / `query_metric` | Catalog + time series |
+| `list_anomalies` / `list_alerts` | Anomaly / alert state |
+| `list_processes` | Top processes (when enabled on agent) |
+| `query_logs` | Journal / anomaly / audit lines |
+| `fleet_health` / `storage_info` | Fleet + retention |
+| `local_knowledge` | Offline product how-tos |
+| `open_chart` / `open_view` | Navigate the desktop UI |
+| `silence_alert` | Operator only, with confirmation |
+
+## Privacy
+
+- No cloud API keys for this feature.
+- Inference stays on your machine.
+- Agent never loads multi-GB models for the default design.
+
+See also [docs/QVAC.md](../docs/QVAC.md).