effect

Effect types for the sans-IO agent core.

Effects are declarations of intent — the core describes what it wants done, and a runtime interprets these effects against the real world.

Two effects cover the entire agent loop: CallProvider — send messages to the LLM ExecuteTools — run tool calls

Types

Effect

</>

An effect request from the pure core. The runtime interprets these.

pub type Effect {
  CallProvider(
    messages: List(message.Message),
    tools: List(tool_definition.ToolDefinition),
  )
  ExecuteTools(calls: List(message.ToolCall))
}

Constructors

CallProvider(
  messages: List(message.Message),
  tools: List(tool_definition.ToolDefinition),
)

Send messages and tool definitions to the LLM provider.

```
ExecuteTools(calls: List(message.ToolCall))
```
Execute a list of tool calls. The runtime feeds the results back as an AgentMsg.ToolResults message.