feat: document OrcaRouter wiring for run-deep-swe - #4
Open
nissrin2020ali-ux wants to merge 1 commit into
Open
Conversation
Add OrcaRouter as a drop-in OpenAI-compatible gateway for the DeepSWE benchmark, mirroring the existing OpenRouter wiring in run-deep-swe. OrcaRouter exposes the same vendor/model slug namespace and bearer auth, so pointing OPENROUTER_API_BASE at api.orcarouter.ai/v1 routes the same pier commands through it. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
run-deep-swelets this repo's users score any model on the DeepSWE coding-agent benchmark. The skill already documents the OpenRouter wiring end-to-end — the part that takes the most trial and error. Some of those users route through OrcaRouter instead.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 orcarouter as a first-class provider means this project's users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL.
Since OrcaRouter mirrors the same
vendor/modelslug namespace and bearer auth as OpenRouter, the fix is a small one: point the base URL athttps://api.orcarouter.ai/v1and the existingpiercommands route through OrcaRouter unchanged.What this PR does
Adds an "OrcaRouter wiring (drop-in, same slug namespace)" section to
skills/agent-orchestration/run-deep-swe/SKILL.mdthat mirrors the existing OpenRouter section's vocabulary:OPENROUTER_API_BASE=https://api.orcarouter.ai/v1so Route B (LiteLLM prefix) routesopenrouter/<slug>through OrcaRouter.orcarouter/auto,orcarouter/fusion, andorcarouter/freerouting models alongside the mirrored vendor slugs./v1/modelsendpoint.descriptionfrontmatter so the skill triggers on "via OrcaRouter" phrasing too.Verification
GET /v1/modelsandPOST /v1/chat/completionsagainsthttps://api.orcarouter.ai/v1both return HTTP 200 using a bearer key, with the samevendor/modelid shape the skill already assumes.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.
Questions or suggestions welcome. Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter
I'm an engineer on the OrcaRouter team.