> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lilfella.app/llms.txt
> Use this file to discover all available pages before exploring further.

# The model layer

> Current model providers, protocols, credentials, selection, and network boundaries.

> The model proposes work and writes answers; the harness and engine own execution and checks.

## Definition

The model layer is Fella's replaceable connection to a chat model. Changing it does not change workspace ingestion, the built-in tool implementations, or deterministic verification.

The model receives prompts, registered tool schemas, and selected tool results. It does not receive a direct filesystem, database, or Tauri API.

## Architecture

Fella currently ships these provider registry entries:

| Provider          | Authentication | Wire protocol     |
| ----------------- | -------------- | ----------------- |
| OpenAI            | API key        | OpenAI-compatible |
| Vercel AI Gateway | API key        | OpenAI-compatible |
| xAI (Grok)        | API key        | OpenAI-compatible |
| Ollama Cloud      | API key        | Ollama            |
| OpenRouter        | API key        | OpenAI-compatible |
| Custom endpoint   | API key        | OpenAI-compatible |

Fella is BYOK-only and starts the connection flow on Ollama Cloud. Ollama Cloud
uses Ollama's API shape at a hosted endpoint; it is not an OpenAI-compatible
provider. The custom option expects an OpenAI-compatible API root.

Some registry rows describe embedding endpoints, but Fella does not currently use embeddings for document retrieval.

## Flow

Use `/login` to view and authenticate supported providers. Use `/model` to inspect or change the active provider, base URL, and model; where supported, Fella fetches the service's current model list.

```text filename="fella commands" theme={null}
/login
/login ollama-cloud
/model
/model gemma4:31b
```

For a custom endpoint:

```text filename="fella commands" theme={null}
/model provider custom
/model base_url https://example.com/v1
/model key YOUR_API_KEY
/model YOUR_MODEL_ID
```

Each tab can select a model. Provider authentication is stored at the application level rather than inside a conversation.

## Behavior

Ollama connections use `/api/chat`; OpenAI-compatible connections use `/chat/completions`. Both stream output into the same harness, which assembles tool calls, executes them through the registry, and returns results in later turns. Transient provider failures retry with backoff.

Provider API keys are kept in `auth.json` under Fella's application data directory, with mode `0600` on platforms that support it. Secret-bearing configuration commands are redacted from conversation transcripts. The inert `/mcp` command stores no connector tokens and makes no network request.

Document search remains local and direct through `grep_files` and `read_file`, so it works even when the provider has no embeddings endpoint.

The wire choice is independent of which hosted service you choose:

```rust theme={null}
let response = if self.is_openai() {
    self.chat_openai(messages, tools, on_retry, on_delta).await?
} else {
    self.chat_ollama(messages, tools, on_retry, on_delta).await?
};
```

That is why Ollama Cloud uses the Ollama wire, while OpenAI, Vercel AI Gateway,
xAI, OpenRouter, and custom endpoints use the OpenAI-compatible wire. The
streamed response is normalized before it reaches `agent::run`; provider-specific
framing does not leak into the tool loop.

## Limits

* With a hosted or custom provider, prompts and tool results sent for the conversation leave the machine and are subject to that provider's policies.
* The inert `/mcp` command does not create a connector or make a separate network request.
* `run_python` is local execution inside the embedded WASM guest. The guest has no filesystem, network, environment, or subprocess capability; the prompt describes the boundary, while the host ABI enforces it.
* Provider model catalogs and default model IDs can change. `/model` is the source of the active service's available models when listing is supported.
* The model can make reasoning and tool-selection mistakes regardless of provider. Deterministic checks cover evidence consistency, not every semantic error.

## Next steps

<CardGroup cols={2}>
  <Card title="The harness" icon="workflow" href="/concepts/harness">
    See how provider output enters the tool loop.
  </Card>

  <Card title="Privacy and security" icon="shield-check" href="/developer-platform/using-fella/privacy">
    Review provider, credential, and local-execution boundaries.
  </Card>

  <Card title="Using Fella" icon="folder-open" href="/developer-platform/using-fella">
    Configure a workspace and ask a first question.
  </Card>
</CardGroup>