feat: add OrcaRouter as a named remote provider preset - #1
Open
armyluki-wq wants to merge 1 commit into
Open
Conversation
Adds OrcaRouter to the desktop remote-provider preset dropdown alongside Zhipu AI and OpenAI. Selecting the preset fills the OpenAI-compatible base URL and the orcarouter/auto adaptive router model, so users can connect the gateway as a first-class provider instead of a custom base URL. Includes offscreen preset coverage for the dialog. Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
ModelForge 3.x lets desktop users manage remote OpenAI-compatible model services on the unified Models page, where named presets (Zhipu AI, OpenAI) make first-class providers one click away. This PR adds OrcaRouter to that preset list.
Selecting OrcaRouter in the provider dialog fills:
OrcaRouterhttps://api.orcarouter.ai/v1orcarouter/auto(OrcaRouter's adaptive router that picks the cheapest live model for each request)Responses API(recommended), matching the other presetsUsers keep getting the backend's encrypted-key handling,
/modelsverification, and Responses→Chat Completions fallback — OrcaRouter just becomes a first-class named provider instead of an anonymous custom base URL.Why
OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents. Like OpenRouter, it exposes a provider/model namespace across many models — but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding
orcarouteras a first-class provider means ModelForge users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL.It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.
Changes
client/pyside6/components/provider_dialog.py— add theOrcaRouterpreset entry and the field-fill handler, mirroring the existingOpenAIpreset wiring.tests/test_provider_presets.py— new offscreen preset coverage asserting the preset is listed and fills name/base_url/model/protocol correctly.Verification
ruff checkon both changed files: clean.tests/test_remote_provider_protocol.py,tests/test_remote_provider_verification.py,tests/test_model_readiness_service.py(13 passed).OpenAIRuntime, responses-first):GET /v1/models→ 200 with 203 models includingorcarouter/auto; chat and streaming round-trips both returned 200 through the Responses API.Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter
I'm an engineer on the OrcaRouter team.