Crate molo_agent 

Agent runtime, memory, channels, and tool registry for molo.

Re-exports

pub use agent::Agent;

pub use agent::AgentConfig;

pub use agent::AgentError;

pub use agent::AgentEvent;

pub use agent::AgentKernel;

pub use agent::MessageChunk;

pub use agent::ReActAgent;

pub use agent::ReActAgentBuilder;

pub use agent::ReActEvent;

pub use agent::StructuredOutcome;

pub use agent::StructuredValidator;

pub use agent::TypedAgent;

pub use event_channel::BroadcastEventChannel;

pub use event_channel::EventChannel;

pub use event_channel::EventChannelStats;

pub use event_channel::EventReceiver;

pub use event_channel::MpscEventChannel;

pub use memory::Budget;

pub use memory::CharTokenCounter;

pub use memory::InMemoryMemory;

pub use memory::Memory;

pub use memory::MemoryError;

pub use memory::SummarizeStrategy;

pub use memory::TokenCounter;

pub use memory::TrimResult;

pub use memory::TrimStrategy;

pub use memory::WindowDrop;

pub use memory::WindowMemory;

pub use message_channel::CliMessageChannel;

pub use message_channel::BroadcastChannel;

pub use message_channel::BroadcastReceiver;

pub use message_channel::ChannelError;

pub use message_channel::IncomingMessage;

pub use message_channel::MessageChannel;

pub use message_channel::MpscChannel;

pub use message_channel::WatchChannel;

pub use message_channel::WatchReceiver;

pub use tool::MissingTools;

pub use tool::RegistryError;

pub use tool::ToolRegistry;

Modules

agent

Agents: reasoning loops.

effect

Effect protocol: side-effect requests and observations.

event_channel

Observation channels: the Agent publishes process events internally, and the environment / UI side subscribes.

memory

Memory: manages the agent’s context.

message

Conversation messages.

message_channel

MessageChannel: a message transport channel between an Agent and the outside world (a human or another Agent).

observability

Lightweight observability record types.

provider

Provider: the interface for communicating with an LLM.

run

Structured run protocol shared by agent implementations and callers.

tool

Tool registry support for agent runtimes.

Macros

react_agent

Convenience assembly macro: registers a list of tools (possibly heterogeneous) with automatic boxing, creating a ToolRegistry internally. The system prompt is optional (omitted = no system prompt). Six arms:

Structs

Artifact

A handle to an artifact produced by a run.

CancellationToken

A token which can be used to signal a cancellation request to one or more tasks.

ChatRequest

A single conversation request.

ChatResponse

The reply to one conversation.

DisplayOutput

Output intended for host/UI display.

EffectObservation

Observation returned to an agent after an effect request is governed and executed by an outer harness.

EffectOutput

Output produced by an executed effect.

EffectRequest

Request for an outer harness to govern and execute a side effect.

EffectSource

Source tool call that produced an effect request.

FakeProvider

A programmable fake Provider — a script is a sequence of per-turn replies, consumed in order by chat / stream_chat.

ImageContent

Raw image data carried in a ContentBlock::Image.

ModelObservation

Successful provider response observed by a step-wise agent kernel.

ModelOptions

Model options for one conversation.

ModelRequest

Provider request emitted by a step-wise agent kernel.

ProviderCapabilities

Provider capability metadata used by hosts and conformance tests.

ProviderRequestContext

Request-scoped provider context.

RetryPolicy

Retry policy (with defaults; Default is “exponential backoff + jitter, 3 attempts”).

RetryProvider

Retry wrapper: implements Provider and retries inner failures per RetryPolicy.

RunContext

Execution controls and host-owned metadata for one run.

RunOutput

Structured result of one non-streaming run.

RunRequest

Input and model parameters for one run.

RunSummary

Execution summary for one run.

SharedState

Shared state: a heterogeneous container accessed by type.

ToolCall

A tool call requested by the model.

ToolContext

Context passed to a tool call.

ToolNamespace

Namespace assigned to a tool by the host application or extension layer.

ToolOutput

Model-visible output produced by a tool.

ToolPolicy

Tool policy metadata declared by the tool author.

ToolSchema

The definition of a tool.

ToolSource

Host-facing metadata describing where a provider-visible tool came from.

TypedRunOutput

Typed-output result paired with the raw structured run output.

Usage

Token usage for one conversation.

Enums

AgentAction

Next action requested by a step-wise agent kernel.

Backoff

Backoff strategy: how long to wait after each failure before the next attempt.

ContentBlock

A content block within a message.

DisplayFormat

Display output format.

EffectKind

Kind of side effect requested by an agent.

EffectStatus

Terminal status of an executed effect.

FakeReply

One turn of reply from the script.

FinishReason

Why the model ended its reply.

Message

A single message in a conversation.

Observation

Observation fed back to a step-wise agent kernel.

ProviderError

Why a Provider call failed.

Retryable

Retry judgment: which errors are worth retrying.

RiskLevel

Request-declared risk level.

SideEffectLevel

Declared side-effect level for a tool.

StreamEvent

An event in a streamed conversation reply.

ToolError

Reasons a tool call fails.

ToolMemoryPolicy

Memory handling policy for model-visible tool/effect output.

ToolNamespaceKind

Kind of tool namespace.

ToolResult

Result of a tool call.

ToolTrustLevel

Trust level assigned to a tool source.

UserInput

User input accepted by a run.

Traits

Provider

The interface for chatting with an LLM.

Tool

A tool an agent can invoke.

Type Aliases

RunMetadata

Request, context, or output metadata for one run.

Attribute Macros

async_trait