Skip to main content

Crate nachalnik_providers

Crate nachalnik_providers 

Source
Expand description

Providers for the nachalnik agent runtime: somebody else’s HTTP API, read carefully.

The runtime ships no provider and never will: it has no network, and a kernel that opened a socket would have an opinion about who you talk to. Without this crate every adopter would write the same streamed HTTP client before asking a model anything.

Everything in here is an Endpoint: an address, a key, a model identifier, a listing, and something to say when the server is slow. What splits the crate in two is whether the model behind it answers in turns.

A Dialect does. It implements nachalnik::Provider, so a kernel can be handed one and a session is what comes out. There are three, each behind the feature of the same name, and openai is on by default:

  • openai - POST /chat/completions, choices[].delta, tool calls assembled from fragments. What OpenRouter, ollama, vLLM, LM Studio, Together and most of the rest speak. With OpenAiCompatible::responses, OpenAI’s Responses API instead: ordered items, and a reasoning model’s thinking sealed and sent back rather than redone every turn.
  • gemini - Google’s own generateContent: candidates[].content.parts, whole calls, and ordered thought parts, which is the dialect nachalnik::Content::Blocks was built for.
  • anthropic - Anthropic’s Messages API: typed blocks, whole calls whose arguments stream in fragments, and signed thinking that has to go back as it came. OpenRouter speaks it too.

An Endpoint that is not a Dialect answers something other than a turn, and there is no kernel in its path at all:

  • system1 - System One models, behind the system1 feature: any of the ones OpenRouter serves, or a self-hosted engine answering the same route. Typed questions put to a state and answered with probabilities: no text, no tool calls, nothing to stream. It is for the decisions a program makes around a conversation rather than the conversation itself.
let provider = Arc::new(OpenAiCompatible::new(
    "openai/gpt-5",
    "https://openrouter.ai/api/v1",
    std::env::var("OPENROUTER_API_KEY")?,
));
provider.probe().await;

let kernel = Kernel::new(Config::default());
kernel.set_provider(provider);

note: nothing in this crate reads the environment. Where requests go, which key pays and what limit to measure against are the caller’s to decide and say: a library that quietly picked up OPENAI_API_KEY would spend somebody’s money on a variable exported for another reason. OpenAiCompatible::new takes the address and the key, and OpenAiCompatible::with_context_limit a limit to use instead of the advertised one.

note: every dialect reports fragments through a nachalnik::DeltaSink and prints nothing: the screen belongs to whoever owns it.

Re-exports§

pub use crate::anthropic::Anthropic;
pub use crate::gemini::Gemini;
pub use crate::openai::OpenAiCompatible;
pub use crate::system1::SystemOne;

Modules§

anthropic
Anthropic’s Messages API dialect: an assistant turn is an ordered list of typed blocks.
conformance
A suite any provider can be held to, whichever of the dialects it speaks.
gemini
Google’s dialect: an assistant turn is an ordered list of parts.
openai
A Provider that speaks the OpenAI chat-completions dialect over HTTP, streamed.
system1
System One models: typed questions put to a state, answered with numbers. Client speaks to any of them.

Structs§

Attribution
The app a request is being made on behalf of, for an endpoint that keeps a ranking of them.
Published
What an endpoint publishes about one parameter beyond its name; see Dialect::published.

Traits§

Dialect
An Endpoint whose model answers in turns: the wire format a conversation is carried in.
Endpoint
The half of a model’s service its user drives, not the kernel’s.

Functions§

install_crypto
Installs the rustls cryptographic provider, and does nothing if already installed.
is_openrouter
Whether an address is OpenRouter’s. Takes a whole URL or a bare authority.
out_of_quota
Whether an error means an account is out of free requests for the day, rather than having hit a momentary upstream limit.
same_model
Whether a listed identifier names the model being asked about, allowing for the decorations a listing adds: Google’s models/ prefix and ollama’s implicit :latest tag.
too_long
Reads a server’s complaint that a request was longer than the model takes, against what the caller already knows the model takes.