Expand description
Agent<I, T, Ms, Ml, Sk> and the per-turn pipeline.
The agent holds an InferenceClient (an abstraction over a
ModelRunner from atomr-infer); strategies are generic so the
hot path is monomorphized. A BoxedAgent form is provided for
config-driven instantiation.
Modules§
- providers
- Provider runtime back-ends, gated by per-provider features.
Wrap any of these
Runnertypes inLocalRunnerClientto use them as anInferenceClient.
Structs§
- Agent
- Generic agent. Strategy types are monomorphized for the hot
path; a
BoxedAgentform (usingBox<dyn>for each slot) is produced fromAgentSpec. - Agent
Ref - Public, type-erased handle to an agent. Implements
Callable, so an agent can be passed wherever any executable unit is expected (workflow steps, team routing targets). - Agent
Spec - Static, serializable description of an agent. Used by the
registry and Python config;
Agent::from_specmaterializes the runtime form. - Local
Runner Client - Wrap any
ModelRunner(includingMockRunner) as anInferenceClient. Single-runner concurrency is bounded by the internal mutex; production setups should use theEngineCoreActorfromatomr-infer-runtimeinstead. - Logging
Middleware - Middleware
Stack - Convenience container — registered middlewares + helpers to run them.
- Rate
Limit Middleware - Redaction
Middleware - Tool
Error Recovery Middleware - Turn
Result
Enums§
Traits§
- Agent
Middleware - Inference
Client - Implemented by anything the agent can use to drive an inference request. The provider matters for tool-call delta parsing.