Crate simple_agent_type 

Core type definitions, async provider traits, and configuration types for SimpleAgents.

No HTTP client or networking code — but includes async-trait for provider interfaces and config types that read from the environment (e.g. TelemetryConfig::from_env).

Architecture

SimpleAgents follows a trait-based architecture:

• Provider: Async trait for LLM provider implementations

Main Types

• [Message]: Role-based conversation messages
• [CompletionRequest]: Unified request format
• [CompletionResponse]: Unified response format
• [ApiKey]: Secure API key handling

Example

use simple_agent_type::prelude::*;

// Create a request
let request = CompletionRequest::builder()
    .model("gpt-4")
    .message(Message::user("Hello!"))
    .temperature(0.7)
    .build()
    .unwrap();

// Access request properties
assert_eq!(request.model, "gpt-4");
assert_eq!(request.messages.len(), 1);

Features

• Type Safety: Strong types prevent common errors
• Transparency: All transformations tracked via [CoercionFlag]
• Security: API keys never logged ([ApiKey])
• Validation: Early validation with clear errors
• Async: All traits use async_trait

Re-exports

pub use error::HealingError;

pub use error::ProviderError;

pub use error::Result;

pub use error::SimpleAgentsError;

pub use error::ValidationError;

pub use telemetry::ApiFormat;

pub use telemetry::OtelProtocol;

pub use telemetry::TelemetryConfig;

pub use telemetry::TraceContext;

Modules

coercion

Coercion types for tracking response healing.

error

Error types for SimpleAgents.

message

Message types for LLM interactions.

prelude

Prelude module for convenient imports.

provider

Provider trait and types.

request

Request types for LLM completions.

response

Response types for LLM completions.

telemetry

Telemetry and tracing configuration types. Telemetry and tracing configuration types for OpenTelemetry integration.

tool

Tool calling types for function/tool integrations.

validation

Validation types for sensitive data.