Struct ScriptedModelClient 

pub struct ScriptedModelClient;

In-process model client used by tests / dev. Inspects the most recent User message in input.messages and either fires a deterministic tool call (if a prior Tool result hasn’t landed yet) or emits a summary text reply (once it has).

Implements stream natively so the agent loop exercises the streaming code path even in tests; the chunk sequence it produces matches what OpenAiCompatibleModelClient would emit for the same logical response.

Trait Implementations

impl Clone for ScriptedModelClient

fn clone(&self) -> ScriptedModelClient

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScriptedModelClient

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

Formats the value using the given formatter.

impl Default for ScriptedModelClient

fn default() -> ScriptedModelClient

Returns the “default value” for a type.

impl ModelClient for ScriptedModelClient

fn stream<'life0, 'async_trait>( &'life0 self, input: ModelTurnInput, ) -> Pin<Box<dyn Future<Output = Result<BoxStream<'static, Result<ModelChunk, ModelClientError>>, ModelClientError>> + Send + 'async_trait>>

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

Stream the model’s response as a sequence of ModelChunks. Production ScriptedModelClient / OpenAiCompatibleModelClient implement this; next() is provided as a folding convenience for callers that don’t need token-level events.

fn next<'life0, 'async_trait>( &'life0 self, input: ModelTurnInput, ) -> Pin<Box<dyn Future<Output = Result<ModelResponse, ModelClientError>> + Send + 'async_trait>>

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

Buffer the stream into a single ModelResponse. Default impl awaits every chunk and then runs collect_model_response. Override only if a provider has a cheaper non-streaming path (none today — even OpenAI’s non-stream call still goes through the same SSE-or-not branch on our side).