myaiforone 1.1.35 → 1.1.36
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/docs/user-guide.md +50 -3
- package/package.json +1 -1
package/docs/user-guide.md
CHANGED
|
@@ -241,7 +241,7 @@ Opened by **+ New Agent** button or clicking an agent's Config button. Has 6 sta
|
|
|
241
241
|
| **Description** | Short description of the agent's purpose. |
|
|
242
242
|
| **Instructions (CLAUDE.md)** | System prompt written to the agent's CLAUDE.md file. Multi-line textarea. |
|
|
243
243
|
| **Agent Class** | Dropdown: Standard, Builder, Platform, Gym. |
|
|
244
|
-
| **Executor** | Dropdown: Platform Default, Claude, Ollama models, or cloud providers — OpenAI, Grok (xAI), Gemini, Groq, Together, Mistral (when multi-model is enabled). Format: `provider:model` (e.g., `openai:gpt-4o`, `gemini:gemini-2.5-flash`, `grok:grok-3`). Overrides the service-level default executor for this agent. |
|
|
244
|
+
| **Executor** | Dropdown: Platform Default, Claude, Ollama models, or cloud providers — OpenAI, Grok (xAI), Gemini, Groq, Together, Mistral, Venice (when multi-model is enabled). Format: `provider:model` (e.g., `openai:gpt-4o`, `gemini:gemini-2.5-flash`, `grok:grok-3`, `venice:llama-3.3-70b`). Overrides the service-level default executor for this agent. |
|
|
245
245
|
|
|
246
246
|
#### Organization Entries
|
|
247
247
|
Each agent can belong to multiple organizations. Per entry:
|
|
@@ -1318,6 +1318,7 @@ Each account row shows:
|
|
|
1318
1318
|
| **Groq** | `groq:<model>` | `groq` | `groq:llama-3.3-70b-versatile` |
|
|
1319
1319
|
| **Together** | `together:<model>` | `together` | `together:meta-llama/Llama-3.3-70B-Instruct` |
|
|
1320
1320
|
| **Mistral** | `mistral:<model>` | `mistral` | `mistral:mistral-large-latest` |
|
|
1321
|
+
| **Venice** | `venice:<model>` | `venice` | `venice:llama-3.3-70b`, `venice:mistral-31-24b` |
|
|
1321
1322
|
|
|
1322
1323
|
API keys are stored in `config.json` under `service.providerKeys` (e.g., `{ "openai": "sk-...", "xai": "xai-...", "google": "AIza..." }`). Set them in Admin → Settings → Provider Keys.
|
|
1323
1324
|
|
|
@@ -1334,7 +1335,7 @@ API keys are stored in `config.json` under `service.providerKeys` (e.g., `{ "ope
|
|
|
1334
1335
|
| Set provider API keys | `PUT /api/config/service` | `update_service_config` |
|
|
1335
1336
|
| | **Body:** `{ providerKeys: { openai: "sk-...", xai: "xai-..." } }` | **Params:** `{ providerKeys: { ... } }` |
|
|
1336
1337
|
| Test provider API key | `POST /api/config/provider-test` | `test_provider` |
|
|
1337
|
-
| | **Body:** `{ provider: "openai" }` — tests the configured key for that provider | **Params:** `provider` (string: openai, grok, gemini, groq, together, mistral) |
|
|
1338
|
+
| | **Body:** `{ provider: "openai" }` — tests the configured key for that provider | **Params:** `provider` (string: openai, grok, gemini, groq, together, mistral, venice) |
|
|
1338
1339
|
| Proxy Ollama tag list | `GET /api/ollama-proxy?url=<ollamaUrl>/api/tags` | — (internal) |
|
|
1339
1340
|
| | **Query:** `url` — only `/api/tags` proxy is allowed | N/A — used by the Settings UI to list local Ollama models |
|
|
1340
1341
|
|
|
@@ -1379,7 +1380,7 @@ API keys are stored in `config.json` under `service.providerKeys` (e.g., `{ "ope
|
|
|
1379
1380
|
- **Save & Verify button** — saves the key to `config.json` and verifies against the licensing server immediately. Agents unblock without restart.
|
|
1380
1381
|
- **Verify Only button** — checks current license status without saving
|
|
1381
1382
|
|
|
1382
|
-
**License popup:** If no valid license is configured, a full-screen modal appears on page load (all pages except Admin) prompting the user to enter their license key. The key is saved and verified inline — no restart needed.
|
|
1383
|
+
**License popup:** If no valid license is configured, a full-screen modal appears on page load (all pages except Admin) prompting the user to enter their license key. The key is saved and verified inline — no restart needed. The modal also shows a **"Don't have a key? Generate one here"** link pointing to the AI Gym download page (skip to Step 4) for users who haven't yet obtained a license.
|
|
1383
1384
|
|
|
1384
1385
|
**Behavior:**
|
|
1385
1386
|
|
|
@@ -1418,6 +1419,19 @@ API keys are stored in `config.json` under `service.providerKeys` (e.g., `{ "ope
|
|
|
1418
1419
|
| Test SaaS connection | `POST /api/saas/test` | `test_saas_connection` |
|
|
1419
1420
|
| | **Body:** `{ baseUrl?, apiKey? }` | **Params:** `baseUrl?`, `apiKey?` |
|
|
1420
1421
|
|
|
1422
|
+
### Desktop Shortcut
|
|
1423
|
+
|
|
1424
|
+
During first-time setup (`/setup`), MyAIforOne automatically creates a branded desktop shortcut with the MyAIforOne `A` logomark icon:
|
|
1425
|
+
|
|
1426
|
+
| Platform | File | What it does |
|
|
1427
|
+
|----------|------|--------------|
|
|
1428
|
+
| **macOS** | `~/Desktop/MyAIforOne.app` | Opens `http://localhost:4888` in your browser |
|
|
1429
|
+
| **Windows** | `~/Desktop/MyAIforOne.lnk` | Opens `http://localhost:4888` in your browser |
|
|
1430
|
+
|
|
1431
|
+
The shortcut is created silently — no confirmation required. It assumes the service is already running (via launchd on macOS or Task Scheduler on Windows). Double-clicking while the service is stopped will open the browser to a "connection refused" page until the service starts.
|
|
1432
|
+
|
|
1433
|
+
> The shortcut is created once during setup and is not recreated on updates. If deleted, re-run `/setup` or create it manually.
|
|
1434
|
+
|
|
1421
1435
|
### Status Indicator Section
|
|
1422
1436
|
- **Description:** "Show a live status dot in your menu bar (Mac) or system tray (Windows)"
|
|
1423
1437
|
- **Install xbar Plugin button** (macOS only) — installs the status bar indicator
|
|
@@ -1456,6 +1470,39 @@ Documentation cards:
|
|
|
1456
1470
|
| Get changelog | `GET /api/changelog` | `get_changelog` |
|
|
1457
1471
|
| | | *(no params)* |
|
|
1458
1472
|
|
|
1473
|
+
## 7.5 Platform Updates
|
|
1474
|
+
|
|
1475
|
+
**Tab:** Updates
|
|
1476
|
+
|
|
1477
|
+
Check the installed version of MyAIforOne and update to the latest release with one click.
|
|
1478
|
+
|
|
1479
|
+
### Version Status Card
|
|
1480
|
+
|
|
1481
|
+
| Field | Description |
|
|
1482
|
+
|-------|-------------|
|
|
1483
|
+
| **Installed version** | The currently running `myaiforone` npm package version (e.g., `1.1.34`) |
|
|
1484
|
+
| **Latest version** | The latest published version from the npm registry |
|
|
1485
|
+
| **Status badge** | **Up to date** (green) or **Update available** (cyan) |
|
|
1486
|
+
|
|
1487
|
+
- Version comparison uses semver — a dev build (`1.1.34-dev`) will not falsely show as outdated.
|
|
1488
|
+
- Latest version is fetched from the npm registry with a 5-second timeout; if unreachable, the card shows "Unable to check".
|
|
1489
|
+
|
|
1490
|
+
### Update Button
|
|
1491
|
+
|
|
1492
|
+
- **Label:** "Update to vX.X.X"
|
|
1493
|
+
- **Visible:** Only when an update is available
|
|
1494
|
+
- **Confirmation dialog:** Shown before update begins — "This will update MyAIforOne to vX.X.X and restart the service. Continue?"
|
|
1495
|
+
- **What it does:** Runs `npx myaiforone@latest --yes` in the background, then restarts the service. The page reloads automatically after restart.
|
|
1496
|
+
|
|
1497
|
+
> **Note:** The update runs as the same user that started the service. Ensure the user has npm write permissions.
|
|
1498
|
+
|
|
1499
|
+
| Action | API | MCP |
|
|
1500
|
+
|--------|-----|-----|
|
|
1501
|
+
| Check version | `GET /api/version` | — |
|
|
1502
|
+
| | Returns `{ current, latest, updateAvailable }` | |
|
|
1503
|
+
| Run update | `POST /api/update` | — |
|
|
1504
|
+
| | Triggers `npx myaiforone@latest` + service restart | |
|
|
1505
|
+
|
|
1459
1506
|
---
|
|
1460
1507
|
|
|
1461
1508
|
# 8. Monitor
|