# Configuration Reference

Configuration is layered from environment, global user settings, project settings, and active TUI state.

## Common Environment Variables

| Variable | Purpose |
| --- | --- |
| `OMNIUS_HOST` | Bind host and port, for example `0.0.0.0:11435` |
| `OMNIUS_REST_API_KEY` | Single admin bearer token for the Omnius REST API |
| `OMNIUS_REST_API_KEYS` | Multi-key REST auth: `key:scope:owner:rpm:tpd:max_jobs` |
| `OMNIUS_PROVIDER_API_KEY` | Upstream model-provider bearer token |
| `OMNIUS_MODEL_API_KEY` | Alternate upstream model-provider bearer token |
| `OMNIUS_UPSTREAM_API_KEY` | Compatibility upstream provider token |
| `OMNIUS_API_KEY` | Legacy fallback for provider auth and legacy REST auth |
| `OMNIUS_API_KEYS` | Legacy multi-key REST auth |
| `OMNIUS_ACCESS` | Network access policy for the daemon |
| `OMNIUS_DAEMON` | Start in daemon mode when set to `1` |
| `OMNIUS_FORCE_NO_THINK` | Force `think: false` for Qwen-style backends |
| `OMNIUS_THINK_AUTO` | Enable opt-in automatic thinking mode trigger |
| `OMNIUS_ASR_CUDA_VISIBLE_DEVICES` | Exact CUDA GPU index or UUID used for managed ASR activation; multi-device masks are rejected (Jetson's integrated GPU is `0`) |
| `OMNIUS_VIBEVOICE_PYTHON` | Host Python used to create the VibeVoice venv; its CUDA-enabled Torch is inherited with `--system-site-packages` |
| `OMNIUS_VIBEVOICE_ATTN` | VibeVoice attention implementation (`sdpa` by default; use a host-supported implementation) |
| `OMNIUS_VIBEVOICE_MAX_NEW_TOKENS` | Explicit VibeVoice structured-transcript generation ceiling (default `32768`) |
| `OMNIUS_AUDIO_PYTHON` | Preferred JetPack CPython 3.10 interpreter containing vendor CUDA Torch; bounded workspace discovery is used when unset |
| `OMNIUS_AUDIO_AUTO_SETUP` | Set to `0` to disable daemon-owned acoustic, speaker, and semantic audio setup |
| `OMNIUS_SEMANTIC_AUDIO_AUTO_SETUP` | Set to `0` to disable CLAP setup specifically; JetPack default is enabled |
| `OMNIUS_VISION_AUTO_SETUP` | Set to `0` to disable managed OpenCLIP provisioning on JetPack |
| `OMNIUS_VISION_PYTHON` | Explicit vendor CUDA Python for the isolated OpenCLIP runtime |
| `OMNIUS_NEMO_SPEECH_BIN` | Optional existing CUDA-enabled NeMo-Speech.cpp binary; otherwise live diarization builds the pinned source revision |
| `OMNIUS_DIARIZATION_AUTO_SETUP` | Set to `0` to disable managed diarizer provisioning; live Sortformer defaults on for JetPack |
| `OMNIUS_HF_TOKEN` | Setup-only Hugging Face token for gated Community-1 download; never persisted or passed to inference |
| `OMNIUS_PYANNOTE_TERMS_ACCEPTED` | Set to `1` only after accepting Community-1 terms; permits gated daemon bootstrap when a token is present |

## Provider Key Precedence

For an upstream inference request, Omnius resolves one credential in this
exact order:

```text
OMNIUS_PROVIDER_API_KEY
  → OMNIUS_MODEL_API_KEY
  → OMNIUS_UPSTREAM_API_KEY
  → OMNIUS_API_KEY
  → VLLM_API_KEY
  → persisted endpoint configuration
```

The first defined value wins. `OMNIUS_REST_API_KEY` and
`OMNIUS_REST_API_KEYS` authenticate callers to the Omnius daemon; they are not
upstream provider credentials.

Linux installations load optional daemon-only overrides from
`~/.config/omnius/daemon.env`. The postinstall creates this file with mode
`0600` and the systemd unit references it with an optional `EnvironmentFile`.
This is the appropriate place for `OMNIUS_AUDIO_PYTHON` or a setup-only gated
model token; credentials do not need to be embedded in the unit or sent in a
REST request.

## Provider Protocol

Known provider presets select one of `ollama`, `openai-chat`, or
`anthropic-messages`. Custom endpoint configuration must include an explicit
protocol. If a legacy endpoint can be identified unambiguously from its known
provider or saved backend type, Omnius migrates it; otherwise the endpoint
remains saved but disabled until a protocol is selected.

## Runtime State

Project runtime state:

```text
.omnius/
  settings.json
  jobs/
  context/
  sponsor/
  scoped-personality/
  telegram-creative/
```

User-global state may live under `~/.omnius/`, including runtime API keys and voice clone references.

The persisted `asrEngine` and `asrModel` settings select one exact entry from
the canonical ASR registry. Selection is not readiness: clients should inspect
`GET /v1/asr/status` before treating a backend as active. Managed VibeVoice
runtime state is stored below `~/.omnius/runtimes/asr/`; its Hugging Face
weights use the unified model cache rather than the project or npm package.

## Auth Key Format

```text
key:scope:owner:rpm:tpd:max_jobs
```

Scopes:

- `read`
- `run`
- `admin`

Rate and concurrency fields are optional.