Scaleway Generative APIs
The Scaleway Generative APIs provider uses provider key scaleway and the HPD-Agent.Providers.Scaleway package. It is backed by HPD's shared OpenAI-compatible chat-completions client, so ModelName is a Scaleway Generative APIs chat model id.
Set an API key:
export SCW_SECRET_KEY="..."The default endpoint is https://api.scaleway.ai/v1/, which sends chat requests to chat/completions. Pass endpoint to WithScaleway(...), set Endpoint in ClientProviderConfig, or use SCALEWAY_ENDPOINT / SCALEWAY_BASE_URL / SCW_ENDPOINT / SCW_BASE_URL when you need a compatible proxy or custom base URL.
Use fluent chat setup first:
using HPD.Agent;
using HPD.Agent.Providers.Scaleway;
var agent = await new AgentBuilder()
.WithScaleway(model: "qwen3.5-397b-a17b")
.BuildAsync();
var result = await agent.RunAsync("Write one sentence about Scaleway Generative APIs setup.");
Console.WriteLine(result.Text);The equivalent Clients.Chat shape is:
{
"Clients": {
"Chat": {
"ProviderKey": "scaleway",
"ModelName": "qwen3.5-397b-a17b"
}
}
}Runtime Chat Options
Use ChatRunConfig for shared model-call behavior such as temperature, top-p, max output tokens, stop sequences, response format, tools, tool mode, seed, and generic reasoning options. Put agent-level defaults in ClientProviderConfig.ChatDefaults or .WithChatDefaults(...); use AgentRunConfig.Chat for per-run or per-session overrides.
Caveats
The default endpoint targets Scaleway serverless Generative APIs. Dedicated deployments use deployment-specific base URLs, so pass endpoint for those.
This provider currently registers the chat family only. Other endpoint families, if the upstream service exposes them, are deferred until HPD has dedicated provider-family support for that surface.
Chat uses HPD's shared OpenAI-compatible chat-completions client. It supports token streaming, function tools, response format and tool mode, seed, max output tokens, top-p, temperature, and stop sequences where the selected model supports them.
Validation checks model and endpoint configuration. Runtime chat options are applied through ChatDefaults and AgentRunConfig.Chat. Missing credentials fail at BuildAsync() before a live provider call.