# Changelog

## 1.1.0 - 2026-06-28

- Switch the provider from the `openai-completions` adapter to `anthropic-messages` (`authHeader: true`), matching the gateway's native endpoint.
- Map reasoning onto Anthropic adaptive thinking: pi thinking levels translate to Umans effort levels (pi `xhigh` reaches Umans `max`), models that can't disable thinking keep it on, and unsigned thinking blocks are preserved instead of being downgraded to text.
- Clamp max output tokens below `max_completion_tokens` so requests never trip the gateway's hard-cap 400.
- Register gateway-handoff vision models (`supports_vision: "via-handoff"`, e.g. `umans-glm-5.2`) with image input; the gateway runs the handoff server-side. Previously these were text-only. If your media proxy skips models that already report image support, it will now leave these images to the gateway.
- Skip deprecated models from the catalog.
- Add `selfcheck.ts` (`npm test`) covering the registration logic.

## 1.0.1 - 2026-06-26

- Clarify the README and npm description: this package is provider-only, with no bundled tools or vision proxy.

## 1.0.0 - 2026-06-26

Initial release.

- Registers Umans as a pi provider under the `openai-completions` adapter.
- Fetches the Umans model catalog from `GET /v1/models/info` on startup.
- Registers tool-capable models with context, reasoning, and image-input metadata.
- Adds a subscription-style `/login` flow that points to the Umans API-key page and stores the pasted key; also honours the `UMANS_API_KEY` environment variable.
- Adds `/umans-models` to list available Umans models.