Loading Accelerated Logic…
GA Release

The Multi-Agent WebGPU Engine & Interactions API are now generally available.

Part 23: Settings & Model Organizer Complete Reference

Every provider, every toggle, and every permission explained — what each setting does, where it is stored, and what to change when behavior is not what you expect.

Category: Reference • Read Time: 32 min read • Updated: 2026-11-10

1. The Model Organizer

The Model Organizer is the single place you connect models. Equipped models appear in every model picker across chat, agents, and the standalone tools.

Provider typeNotes
Google GeminiPaste a Gemini API key. Keys are validated live before being saved — a key is not accepted just because it starts with AIzaSy.
OpenAI / Anthropic / Groq / DeepSeek / xAI / etc.Built-in catalog entries; enter the provider key. Proxy/fallback logic mirrors each provider's native API.
Custom OpenAI-compatibleAny endpoint speaking the OpenAI schema (OpenRouter, Together, local servers, Azure-style). Use Discover models to auto-list /models; per-model API keys are supported. Remote endpoints go via the allowlisted proxy; local URLs are called directly.
Custom Anthropic-compatibleAnthropic Messages-API-compatible endpoints, with the anthropic-dangerous-direct-browser-access header and proxy-unreachable direct fallback.
Ollama (local)Set your Ollama URL (default http://127.0.0.1:11434) and launch with OLLAMA_ORIGINS="*" ollama serve so the browser may call it. Connection status is polled and shown inline.
WebLLM / Transformers.jsOpen-weights models run in-browser on WebGPU/WASM. Load once; weights are cached. Switching models unloads the previous engine to free GPU/WASM memory.
Gemini NanoChrome's on-device model; auto-appears in the catalog when supported.
Puter.js (free)Free, proxy-based inference with no key; useful to start immediately (see Part 2).

2. Provider Test Arena

The organizer can run a live prompt against multiple equipped models concurrently per provider and sequentially within a provider (so local single-engine models do not contend), reporting first-token latency and tokens-per-second. Use it to compare real performance before committing a default.

3. Tool Permission Levels

Tool calls can originate in model output, imported files, or MCP responses, so a synchronous confirmation sits at the final dispatch point and cannot be bypassed by an alternate agent loop.

  • Permission levels control which tools run automatically, which ask first, and which are blocked. Write-class tools (file writes, commits, external actions) are classified separately from read-only ones.
  • Built-in vs external. The built-in web-search and GitHub connector tools are distinguished from external MCP servers by server identity; an external server cannot impersonate a built-in tool by naming it github_*.
  • AI memory and skill directives. Creation proposals require the corresponding aiCanCreateSkills or aiCanCreateMemories setting and a separate Keep click in the chat review card; proposals expire after 60 seconds and are capped at two per conversation. Deletions require aiCanDeleteSkills or aiCanDeleteMemories. All four settings default off.

4. Connectors (GitHub & Google Drive)

GitHub: connect via OAuth (recommended) or paste a Personal Access Token with repo, read:user, user:email scopes. Disconnect fully clears tokens and refresh credentials. You can also open a local folder in read-only mode to browse code without pushing.

Google Drive: used for optional backups of chats, memories, projects, files, and settings (secrets stripped). The access token is session-scoped; sync selectors let you choose exactly which slices back up.

5. Generation & Display Settings

Chat & reasoning

Temperature, max tokens, context window limit, Infinity Mode (repeated self-correction attempts + critic strictness), auto-architecture routing, and vision toggle.

Images

Image-generation behavior and error handling. The current Settings panel does not expose model or provider selection controls; an error card may offer a manual Pollinations retry.

Backup & storage

Drive sync selectors (chats/memories/projects/files/settings/skills), export/import snapshots, and local-folder sandbox quotas.

Display

Theme, Robot Companion visibility, developer-density options, and the EULA/terms acknowledgement.

6. Where Settings Persist

Settings save to IndexedDB and are mirrored to localStorage for fast bootstrapping. API keys are isolated in the credential store; Drive sync stores them only in a separate AES-GCM encrypted vault and its private AppData key record, never in the readable settings document. Signing into the same Google account restores that vault on another device. Changing a setting updates persistence without double-writing, so concurrent edits (such as a background Drive sync) are not clobbered.

7. The Settings Search Bar — a Field Guide

The modal's instant search is the fastest route to any toggle; these are the high-traffic queries and where they land:

ollama
Engine & API → local endpoint URL and connection status
puter
Model Organizer → free Puter.js provider and custom model IDs
fallback
Model Fallbacks — saved order (not applied at request time, Part 8)
temperature
LLM Parameter Engine — sampling controls
infinity
Multi-Agent Systems — critic strictness & max attempts
queue
AI Engine — prompt queue backoff interval (0–60s)
aiCanCreate
AI Permissions — skill/memory creation & deletion gates (default off)
sync
Google Drive Cloud — per-slice sync selectors
purge
Local Backup & Export — irreversible workspace wipe

Search matches labels and keywords — if a query comes up empty, try a synonym ("clear" for purge, "delete" for remove) before hunting through tabs.

8. Three Reference Configurations to Steal

The New User (zero cost, zero risk)

Default AL Router Fast + Puter models; Drive backup off; AI create/delete permissions all off; Auto Router on; 25–30 new chats before evaluating anything. Spend nothing, learn the product, upgrade deliberately.

The Working Developer (daily driver)

Groq direct key for speed, one OpenRouter key for depth, Ollama for confidential code; Drive sync on for chats+skills+memories with a monthly restore drill (Part 17); AI skill creation on with Keep-review habit; Multi for builds, Single for everything else; fallback order saved but switched manually on failure; weekly snapshot export.

The Locked-Down Professional (privacy-first)

WebLLM / Transformers.js / Gemini Nano / local Ollama only; cloud providers disabled or keyed to a personal paid account; memories off or minimal; Drive sync off — snapshot exports to encrypted local disk; all AI permissions off; sandbox-first workflows; clearing routine after each session on shared networks.

9. The Provider Test Arena — Running It and Reading It Right

Numbers that look comparable are not always comparable. A sound protocol:

  1. Use one fixed canary prompt — the same task shape across all your equipped models (e.g. "Explain CRDTs to a senior Go engineer in 250 words") so differences come from the model, not the ask.
  2. Mind the execution pattern. Providers run concurrently across providers but sequentially within a provider — local engines and same-vendor models don't contend, but your timing conclusions should come from separate providers on separate runs, never from one shared benchmark morning.
  3. Read TPS with its denominator. Tokens/sec on a 40-token answer vs a 900-token code task are different populations — compare like with like, or use first-token latency for the "does it feel alive" judgment.
  4. Latency vs. quality are different axes. The arena will rank a tiny fast model above a slower strong one on speed — pick your default per task class, not per leaderboard.
  5. Re-run after provider events. Degradation, new model drops, and quota resets all scramble yesterday's ranking.

10. A Concrete Walkthrough: The Write-Tool Ask-First Flow

What actually happens when an agent wants to write through the GitHub connector mid-task:

  1. The model emits a tool call for github_create_or_update_file (or similar write-class built-in).
  2. The dispatch gate intercepts it. Write-class classification happens before execution; the call never reaches GitHub yet. Read-class built-ins in the same run proceed unimpeded.
  3. A confirmation card appears above the composer summarizing the target repo, path, and action. This is not a toast you can fat-finger past — it blocks until you decide.
  4. Approve → the call executes and the result streams back into the run; deny → the model receives a refusal it can react to (usually: propose a plan instead, or ask you for explicit instruction); ignore → the card expires and the tool never runs.
  5. Audit afterward: the run's activity trace records the attempt and its resolution — review it when you let an unattended batch touch anything write-class.

Defaults exist for a reason: creation/deletion of skills and memories, plus all write-class tool calls, start ungranted. Grant narrowly, watch the first few executions, then decide whether to keep the ask-first friction.