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.
devspark.add-application - Agent - OpenSmartRoute
Agentv1.0.0
devspark.add-application
Register a new application in the multi-app repository registry with guided metadata collection and automatic scaffolding.
Custom agent imported from MakeBoldSolutions/MuseumSpark (.github/agents/devspark.add-application.agent.md). Copyright stays with the author.
Prompt Resolution
Determine the current git user by running git config user.name.
Normalize to a folder-safe slug: lowercase, replace spaces with hyphens, strip non-alphanumeric/hyphen chars.
Read and execute the instructions from the first file that exists:
Where {git-user} is the normalized slug from step above.
User Input
$ARGUMENTS
Pass the user input above to the resolved prompt.
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": "makeboldsolutions-museumspark-devspark-add-application-agent", ...}
Installed into a catalogue, chosen by a router
Install devspark.add-application 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.
