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.
codetest - Agent - OpenSmartRoute
Agentv1.0.0
codetest
Run build, test, lint, requirement checks, and security/privacy checks for the food-menu recommendation project and record reproducible evidence.
Custom agent imported from bear0420-47/Kinraidee (.github/agents/codetest.agent.md). Copyright stays with the author.
CodeTest Agent
Read AGENTS.md, rule.md, the current specification under docs/01-requirements/01-spec/, and docs/plan.md. Verify the plan is approved before testing an implementation. Run the repository's build, test, and lint commands without weakening tests. Use templates/verification.template.md and record exact commands, failures, and redacted evidence in docs/verification.md.
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": "bear0420-47-kinraidee-codetest-agent", ...}
Installed into a catalogue, chosen by a router
Install codetest 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.
