car-planner 0.24.1

Proposal scoring and search for Common Agent Runtime
docs.rs failed to build car-planner-0.24.1
Please check the build logs for more information.
See Builds for ideas on how to fix a failed build, or Metadata for how to configure docs.rs builds.
If you believe this is docs.rs' fault, open an issue.
Visit the last successful build: car-planner-0.23.0

car-planner

Proposal scoring and search for Common Agent Runtime.

What it does

Sits between the model and car-engine: scores N candidate proposals using static verification + cost estimation, picks the best, and provides fallback ordering for replan scenarios.

Inspired by MARS (budget-aware MCTS) — uses verify() + simulate() as the evaluation function, not LLM calls. Pure Rust, zero inference cost.

Usage

use car_planner::{Planner, PlannerConfig, ScoredProposal};

let planner = Planner::new(PlannerConfig::default());
let candidates = vec![proposal_a, proposal_b, proposal_c];
let ranked = planner.rank(&candidates, Some(&state), Some(&tools));
let best = &ranked[0]; // highest score first

Where it fits

If you already have N candidate proposals, use this directly. If you also need CAR to generate the candidates via inference, use car-active-planner, which composes inference with this ranker. Exposed to FFI consumers as the standalone rank_proposals function.