Struct OllamaHttpAdapter 

pub struct OllamaHttpAdapter { /* private fields */ }

HTTP adapter that routes to a local Ollama instance via /api/chat.

Implementations

impl OllamaHttpAdapter

pub fn new(config: OllamaConfig) -> Result<Self, LlmError>

Build an adapter from config.

The endpoint URL is validated immediately; returns LlmError::InvalidRequest if the endpoint does not satisfy the loopback-only constraint. The model reference is validated per-call (inside LlmAdapter::complete) because the model is also present on the request.

Trait Implementations

impl Clone for OllamaHttpAdapter

fn clone(&self) -> OllamaHttpAdapter

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for OllamaHttpAdapter

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl LlmAdapter for OllamaHttpAdapter

fn stream_boxed(&self, req: LlmRequest) -> BoxStream<'_>

Override with true Ollama streaming via newline-delimited JSON.

Uses ureq (synchronous) inside spawn_blocking. Because spawn_blocking requires the entire blocking work to complete before returning, all stream lines are collected into a Vec before being yielded. This means backpressure and incremental display require the full response to arrive first.

TODO: replace ureq with an async HTTP client (e.g. reqwest) and drive the response body with tokio::io::AsyncBufReadExt to achieve true line-by-line streaming without buffering the entire response.

fn adapter_id(&self) -> &'static str

Stable, lowercase identifier used in audit envelopes (e.g. "claude", "ollama", "replay"). Constants — implementations MUST NOT vary this per call.

fn complete<'life0, 'async_trait>( &'life0 self, req: LlmRequest, ) -> Pin<Box<dyn Future<Output = Result<LlmResponse, LlmError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Issue a completion call. The adapter is responsible for honouring req.timeout_ms and returning LlmError::Timeout when exceeded.

fn stream( &self, req: LlmRequest, ) -> impl Stream<Item = Result<StreamChunk, LlmError>> + Send

where Self: Sized,

Stream tokens incrementally. Default implementation calls complete and yields the full response as a single chunk — adapters override this for true streaming.