Crate harness_loop 

ReAct agent loop with self-correction.

Minimal v0.0.1 implementation:

• Applies guides once at the start.
• Sends Context (with tools) to the model.
• Dispatches each returned tool call via ToolRegistry.
• Runs Sensor::SelfCorrect sensors after each action; auto-fix patches are applied directly to the world, blocking signals are fed back to the model.
• Stops when the model returns no tool calls, or when policy.max_iters is hit.

Re-exports

pub use learning::*;

pub use memory_layer::*;

pub use profile_guide::*;

pub use recall_layer::*;

pub use registry::*;

pub use replay::*;

pub use subagent::*;

Modules

learning

Self-evolving learning loop for crate::AgentLoop.

memory_layer

Long-term-memory wiring for crate::AgentLoop.

profile_guide

Opt-in Guide that renders harness_core::UserProfile into the agent’s system prompt.

recall_layer

Cross-session recall wiring for crate::AgentLoop.

registry

A tiny name-keyed tool registry used by AgentLoop.

replay

Session record + replay (DESIGN.md §15 v0.2+).

subagent

Subagent: an isolated agent loop spawned from a parent.

Structs

AgentLoop

The agent loop.

Enums

Outcome

Where a run finished. Marked #[non_exhaustive] so future fields don’t break downstream matches — always include .. when destructuring.

Functions

apply_patches

Apply auto-fix patches; return short descriptions of those that succeeded.

is_default_safe_fix

Audit #7: default safelist for FixPatch::RunCommand.