aeat.adapters.outbound.llm._client module¶

Async-first public LLM client.

Coordinates LLMRequest inputs, LLMCache lookup/write-through, UsageRecorder accounting, and concrete LLMProvider adapters before returning an LLMResponse.

class LLMClient(*, settings=None, cache=None, usage_recorder=None, run_telemetry_recorder=None, prompt_registry=None, caller='aeat.adapters.outbound.llm.client', prompt_id='adhoc', adapter_override=None)[source]¶

Bases: object

Public async-first LLM completion entry point.

Parameters:

settings (Settings | None) – Optional Settings override used for provider selection and defaults.
cache (LLMCache | None) – Optional LLMCache implementation override.
usage_recorder (UsageRecorder | None) – Optional UsageRecorder override.
run_telemetry_recorder (LLMRunTelemetryRecorder | None) – Optional LLMRunTelemetryRecorder override.
prompt_registry (PromptRegistry | None) – Optional PromptRegistry override.
caller (str) – Stable caller identifier recorded in usage logs.
prompt_id (str) – Stable prompt identifier recorded in usage logs.
adapter_override (_ProviderAdapter | None) – Optional _ProviderAdapter override for tests and controlled flows.

async complete(request)[source]¶

Complete a prompt request.

Parameters:: request (LLMRequest) – Structured LLMRequest.
Return type:: LLMResponse
Returns:: A LLMResponse enriched with cache and cost metadata.
Raises:: Exception – Re-raised after logging when the LLM provider adapter fails.