Providers
Omegon treats provider authentication as a runtime boundary, not just a login convenience. The active provider affects routing, allowed entry points, quota semantics, and what the operator sees in the engine footer.
Current provider auth modes
| Provider / mode | Configure | Allowed | Restrictions |
|---|---|---|---|
| Anthropic/Claude API key | export ANTHROPIC_API_KEY="sk-ant-..." | All Omegon entry points, including TUI, prompts, smoke, and cleave. | Subject to Anthropic API terms, quota, and model limits. |
| Anthropic/Claude OAuth / subscription | omegon login anthropic or /login anthropic | Interactive TUI sessions. |
Omegon hard-blocks headless and automated entry points for this credential class.
If you want prompts, smoke tests, cleave, or unattended automation, use
ANTHROPIC_API_KEY instead.
|
| OpenAI API | export OPENAI_API_KEY="sk-..." | All supported Omegon entry points. | Subject to OpenAI billing, quota, and model limits. |
| OpenAI/Codex OAuth | omegon login openai-codex or /login openai-codex | Supported Codex-backed Omegon flows, including interactive work and supported automation. |
The engine footer may show a selected model such as gpt-5.4 while the limit row
shows an upstream bucket name such as GPT-5.3-Codex-Spark. That limit row is provider
telemetry, not a second model selector.
|
| Ollama | export OLLAMA_HOST="http://127.0.0.1:11434" | All supported local-model workflows. | Local inference only; no external account auth. |
| GitHub Models (coming soon) | Official PAT configuration will be documented when the integration ships. | Planned support. | Not available yet. |
| Copilot seat (coming soon) | Seat-based auth will be documented when the integration ships. | Planned support. | Not available yet. |
Runtime identity honesty
Omegon now keeps provider identity explicit in operator-facing surfaces:
- Anthropic/Claude means Anthropic-backed execution
- OpenAI API means API-key execution against OpenAI's API surfaces
- OpenAI/Codex means the ChatGPT/Codex OAuth-backed route
The footer's model row shows the selected runtime model. The limit row, when present, shows upstream provider quota telemetry. Those are intentionally different fields.
Anthropic subscription boundary
Anthropic/Claude subscription auth is the one credential class with a hard Omegon runtime boundary. Interactive TUI use is allowed. Headless and automated paths are blocked.
The consumer terms page is here: anthropic.com/legal/consumer-terms
Practical guidance
- If you want to work in the TUI by hand, Anthropic/Claude OAuth is a valid path.
- If you want unattended or scripted automation, configure
ANTHROPIC_API_KEY. - If you want GPT-family routing without API-key setup, try
omegon login openai-codex. - If you want local-only inference, use Ollama.
- If you want predictable automation with commercial API terms, prefer API-key-backed providers.
How this fits the rest of Omegon
The provider layer feeds the TUI, slash commands, smoke paths, and cleave orchestration. That means auth mode affects not just model access, but which entry points Omegon can honestly and safely expose.