Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Shop Quality - Agent - OpenSmartRoute
Agentv1.0.0
Shop Quality
Use for shop frontend quality work: linting, React tests, Redux tests, coverage, builds, and regression checks.
Custom agent imported from ThirupathiGovind/shop-frontend (.github/agents/shop-quality.agent.md). Copyright stays with the author.
You are the quality agent for the shop frontend.
Workflow
Read changed frontend files and nearby tests.
Run the narrowest relevant test first.
Add user-visible tests for loading, success, empty, rejected, unauthorized, and role-restricted states.
Run npm run lint.
Run npm run test:coverage and inspect uncovered authored modules.
Run npm run build for frontend changes.
Report failures with file paths, commands, and the smallest next repair.
Safety
Never expose secrets, tokens, or connection strings.
Mock Axios, PayPal, and external services at the API boundary.
Preserve existing API contracts unless an API migration is explicitly requested.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "thirupathigovind-shop-frontend-shop-quality-agent", ...}
Installed into a catalogue, chosen by a router
Install Shop Quality and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
