llm4s-docs/org.llm4s/org.llm4s.llmconnect/BaseLifecycleLLMClient

BaseLifecycleLLMClient

org.llm4s.llmconnect.BaseLifecycleLLMClient

@Stable

trait BaseLifecycleLLMClient extends LLMClient, MetricsRecording

Mixin trait providing standard lifecycle management and metrics wrapping for LLMClient implementations.

Tracks whether the client has been closed via an AtomicBoolean and provides:

validateNotClosed — a pre-check returning Left(ConfigurationError) once closed.
close() — an idempotent close that delegates to releaseResources() exactly once.
completeWithMetrics — combines lifecycle validation with metrics recording for Completion results, eliminating boilerplate in complete / streamComplete.

Concrete clients mix in this trait, supply providerName and modelName, and optionally override releaseResources() to free provider-specific resources (HTTP clients, SDK connections, etc.).

Attributes

Graph
Supertypes: trait MetricsRecording

trait LLMClient

trait AutoCloseable

class Object

trait Matchable

class Any
Show all
Known subtypes: class AnthropicClient

class BedrockClient

class GeminiClient

class OllamaClient

class OpenAIClient

class OpenAICompatibleClient

class CohereClient

class DeepSeekClient

class MistralClient

class OpenRouterClient

class ZaiClient

class VertexAIClient

class WatsonXClient
Show all

Members list

Value members

Abstract methods

Human-readable label used in the "already closed" error message.

Attributes

The model identifier forwarded to the metrics collector.

Attributes

Metrics label for this provider (e.g. "openai", "anthropic").

Attributes

Concrete methods

Releases resources and closes connections to the LLM provider.

Call when the client is no longer needed. After calling close(), the client should not be used. Default implementation is a no-op; override if managing resources like connections or thread pools.

Attributes

Definition Classes: LLMClient -> AutoCloseable

Validates that the client is open, executes the operation, and records standard completion metrics (latency, token usage, estimated cost).

Use this in complete and streamComplete implementations to avoid repeating the lifecycle-check + metrics-wrapping boilerplate.

An interrupted call - one that throws InterruptedException, or fails while the thread is interrupted - is returned as Left(CancelledError) with the interrupt flag kept, whatever the provider SDK did with it. A call made with the flag already set returns Left(CancelledError) at once, without running operation: an SDK that ignores the flag would otherwise send the (billed) request anyway.

Value parameters

operation: The provider-specific completion logic to execute. Called only when the client is open and the thread is not interrupted.

Attributes

Returns: The completion result with metrics recorded as a side-effect.

Hook for releasing provider-specific resources. Called at most once, inside close(). The default is a no-op.

Attributes

Inherited methods

Sends the conversation and parses the response into a typed value using the provided schema.

Sets ResponseFormat.JsonSchema on the options. OpenAI, Azure OpenAI and Gemini enforce the schema at generation time, as does Ollama 0.5 or later through its format field. Requesty and the OpenAI-compatible providers (including Cohere) send it as response_format, but whether it is enforced is up to the server - for Requesty, a router, the backend model it routes to: one that ignores the field returns unconstrained text. Anthropic falls back to a best-effort system-prompt instruction, which is not schema-enforced. Clients that do not read responseFormat (watsonx, Bedrock) send no schema at all. Because models may wrap JSON in markdown code fences or surround it with prose, the response is normalised (fence stripped, first balanced {...} or [...] extracted) before being deserialised with uPickle into the expected type A.

The reply is '''not''' validated against the schema: it is only deserialised. A constraint the reader does not check - an enum, a numeric or string bound, additionalProperties = false (extra keys are ignored) - can be violated by a reply that still returns Right(A). Check such constraints on the result yourself.

The schema is derived with strict = true, which lists '''every''' property as required, including a property declared optional with required = false. Only responseFormat is overridden: every other option you pass is forwarded unchanged to complete, where the provider client may adjust or drop options the model does not support, as for any other complete call. name and strict on the format are left at their defaults ("response" and true); call complete with your own ResponseFormat.JsonSchema to set them.

Type parameters

A: target type; must have a corresponding upickle.default.Reader[A]

Value parameters

conversation: conversation history
options: additional completion options (default: CompletionOptions())
reader: implicit uPickle reader for deserialising the JSON into A
schema: JSON-Schema description of the expected response object

Attributes

Returns: Right(A) on success. Left(ValidationError) with field structured_output when the reply is not JSON, is JSON null, or cannot be deserialised as A; any other Left is the provider call's own error, returned unchanged
Inherited from:: LLMClient

Calculates available token budget for prompts after accounting for completion reserve and headroom.

Formula: (contextWindow - reserveCompletion) * (1 - headroom)

Headroom provides a safety margin for tokenization variations and message formatting overhead.

Value parameters

headroom: safety margin as percentage of prompt budget (default: HeadroomPercent.Standard ~10%)

Attributes

Returns: maximum tokens available for prompt content
Inherited from:: LLMClient

Validates client configuration and connectivity to the LLM provider.

May perform checks such as verifying API credentials, testing connectivity, and validating configuration. Default implementation returns success; override for provider-specific validation.

Attributes

Returns: Right(()) if validation succeeds, Left(LLMError) with details on failure
Inherited from:: LLMClient

Executes operation and records metrics for the call.

Latency and outcome (success or classified error) are recorded for every call regardless of result. Token counts and cost are recorded only on success — a Left result emits an org.llm4s.metrics.Outcome.Error event whose kind is derived from the org.llm4s.error.LLMError subtype via ErrorKind.fromLLMError.

Value parameters

extractCost: Extracts the pre-computed cost (USD) from a successful result; return None to skip cost recording.
extractUsage: Extracts prompt/completion token counts from a successful result; return None to skip token recording.
model: Model identifier forwarded to the collector.
operation: The LLM call to time and observe.
provider: Provider label forwarded to the collector (e.g. "openai").

Attributes

Returns: The result of operation, unchanged.
Inherited from:: MetricsRecording

Inherited and Abstract methods

Executes a blocking completion request and returns the full response.

Sends the conversation to the LLM and waits for the complete response. Use when you need the entire response at once or when streaming is not required.

Value parameters

conversation: conversation history including system, user, assistant, and tool messages
options: configuration including temperature, max tokens, tools, etc. (default: CompletionOptions())

Attributes

Returns: Right(Completion) with the model's response, or Left(LLMError) on failure
Inherited from:: LLMClient

Returns the maximum context window size supported by this model in tokens.

The context window is the total tokens (prompt + completion) the model can process in a single request, including all conversation messages and the generated response.

Attributes

Returns: total context window size in tokens (e.g., 4096, 8192, 128000)
Inherited from:: LLMClient

Returns the number of tokens reserved for the model's completion response.

This value is subtracted from the context window when calculating available tokens for prompts. Corresponds to the max_tokens or completion token limit configured for the model.

Attributes

Returns: number of tokens reserved for completion
Inherited from:: LLMClient

The org.llm4s.metrics.MetricsCollector that receives timing, token, and cost events.

Injected by each concrete provider client. Defaults to MetricsCollector.noop in all public constructors, so callers that do not need metrics do not pay an allocation cost.

Attributes

Inherited from:: MetricsRecording

Executes a streaming completion request, invoking a callback for each chunk as it arrives.

Streams the response incrementally, calling onChunk for each token/chunk received. Enables real-time display of responses. Returns the final accumulated completion on success.

Value parameters

conversation: conversation history including system, user, assistant, and tool messages
onChunk: callback invoked for each chunk; called synchronously, avoid blocking operations
options: configuration including temperature, max tokens, tools, etc. (default: CompletionOptions())

Attributes

Returns: Right(Completion) with the complete accumulated response, or Left(LLMError) on failure
Inherited from:: LLMClient

In this article

Generated with