Crate car_engine 

Core runtime engine for Common Agent Runtime.

The runtime loop:

1. Receive a proposal (batch of actions from a model)
2. Build a DAG from state_dependencies
3. Execute each level (concurrent if no ABORT actions, sequential otherwise)
4. Validate, execute with idempotency + timeout + retry, commit
5. On abort: rollback state to pre-proposal snapshot

Re-exports

pub use agent_basics::entries as agent_basic_entries;

pub use agent_capability::AgentCapabilityRegistry;

pub use builtin_agents::agent_metadata;

pub use builtin_agents::format_capability_payload;

pub use builtin_agents::register_builtins;

pub use builtin_agents::BuiltinAgent;

pub use builtin_agents::CapabilityPayloadError;

pub use builtin_agents::BUILTIN_AGENTS;

pub use authz::AllowAllPermissions;

pub use authz::AuthzDecision;

pub use authz::AuthzPipeline;

pub use authz::AuthzResult;

pub use authz::AuthzStage;

pub use authz::PermissionHandler;

pub use authz::Restriction;

pub use cache::ResultCache;

pub use capabilities::CapabilitySet;

pub use checkpoint::Checkpoint;

pub use mcp::McpServer;

pub use mcp::McpServerConfig;

pub use mcp::McpToolExecutor;

pub use mcp::McpToolInfo;

pub use rate_limit::RateLimit;

pub use rate_limit::RateLimiter;

pub use registry::ToolEntry;

pub use registry::ToolPermission;

pub use registry::ToolRegistry;

pub use registry::ToolSource;

pub use scope::RuntimeScope;

pub use subprocess::SubprocessTool;

pub use subprocess::SubprocessToolExecutor;

pub use voice_turn::dispatch_voice_turn;

pub use voice_turn::dispatch_voice_turn_sidecar_only;

pub use voice_turn::dispatch_voice_turn_sidecar_only_with_classifier;

pub use voice_turn::dispatch_voice_turn_sidecar_only_with_telemetry;

pub use voice_turn::dispatch_voice_turn_with_telemetry;

pub use voice_turn::DirectDataFetcher;

pub use voice_turn::SidecarResult;

pub use voice_turn::VoiceTelemetry;

pub use voice_turn::VoiceTurnControl;

pub use voice_turn::VoiceTurnError;

pub use voice_turn::VoiceTurnHandle;

Modules

agent_basics

agent_capability

Agent capability registry — maps capability id → agents that implement it.

authz

Authorization pipeline for tool execution.

builtin_agents

Built-in agent vocabulary — single source of truth across FFI surfaces.

cache

Cross-proposal result cache for tool call results.

capabilities

Per-agent capability permissions for the Common Agent Runtime.

checkpoint

Checkpoint and resume support for the Common Agent Runtime.

mcp

MCP (Model Context Protocol) server integration.

rate_limit

Token bucket rate limiter for tool calls with backpressure support.

registry

Canonical tool registry — single source of truth for tool identity.

scope

RuntimeScope — per-execution caller identity surface for the multi-tenant work tracked in Parslee-ai/car#187.

subprocess

Subprocess tool executor — runs tools as external processes via stdin/stdout JSON-RPC.

voice_turn

Two-track voice turn orchestration.

Structs

CostBudget

Budget constraints for proposal execution.

FailedActionSummary

Summary of a failed action, included in ReplanContext.

ReplanConfig

Configuration for the replan loop.

ReplanContext

Context provided to the replan callback so the model can generate an alternative.

Runtime

Common Agent Runtime — deterministic execution layer.

Constants

CANCELED_PREFIX

Prefix on the error field of an ActionResult that distinguishes “the user pulled the plug” from “earlier abort cascaded.” The ActionStatus itself is Skipped in both cases (introducing a new variant ripples through every IR consumer + FFI binding); the prefix lets callers like the A2A bridge tell the cases apart without string-matching a magic literal.

Traits

ReplanCallback

Callback trait for replanning failed proposals. Implement this to let the runtime ask the model for an alternative plan when a proposal aborts.

ToolExecutor

Trait for tool execution. Implement this to provide tools to the runtime.

Functions

format_tool_result

Format a tool result for feeding back to a model.