car-server-core 0.47.0

Transport-neutral library for the CAR daemon JSON-RPC dispatcher (used by car-server and tokhn-daemon)
docs.rs failed to build car-server-core-0.47.0
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-server-core-0.23.0

car-server-core

Transport-neutral library for the Common Agent Runtime JSON-RPC dispatcher.

What it does

Holds the JSON-RPC dispatcher, per-client session state, and the WebSocket channel plumbing. Used by car-server (the standalone WebSocket binary) and by any future embedder that wants to expose CAR's protocol over a different transport (e.g. tokhn-daemon).

The standalone car-server binary is a thin wrapper that loads ~/.car/env, initializes telemetry, spawns the dream loop, binds a TCP listener, and on each connection calls run_dispatch.

Library boundary contract

This library MUST NOT:

  • spawn the dream loop (caller decides),
  • initialize telemetry (caller decides),
  • load ~/.car/env (caller decides).

Those bootstraps stay in the embedder's main. The contract prevents the dual-memgine bug: if the library silently spawned its own dream loop, embedded users would end up with two memgine engines (the embedder's plus the library's).

Lock primitive

ClientSession.memgine uses Arc<tokio::sync::Mutex<MemgineEngine>> per the "one-wrapper rule" — dispatcher handlers can hold the lock across .await points without risking poisoning, and tokio's Mutex does not poison so a panicking handler does not poison the engine for sibling connections.

Embedder usage

use car_server_core::{ServerState, ServerStateConfig, run_dispatch};

// Build the shared server state.
let state = ServerState::embedded(ServerStateConfig::default()).await?;

// On each accepted WebSocket connection:
tokio::spawn(async move {
    run_dispatch(ws, state.clone()).await;
});

The assistant (car-server-core::assistant)

The flagship batteries-included general agent behind car do — one-shot, REPL, or --serve conversational.

  • A GeneralExecutor (generalizes coder::WorktreeExecutor to any bound Substrate, sharing one bounded run_shell_on) exposing files, a real shell, http_request / web_search, calculate, and durable remember / recall (memgine, ~/.car/memory/assistant.json).
  • Driven through a full Runtime — validator, policy, permission tiers, event log. Sandbox-first (car-sandbox, --network none), with --local / --full-access to widen it.
  • Conversational via the native agent.chat harness (chat::AssistantService, the first native Rust agent-side). Auto-registered in CarHost as car-assistant.
  • Tool descriptions are the single source of truth for what a tool does; the system prompt (assistant::prompt) carries only posture and the rules no def or policy expresses, and never re-enumerates the toolset.
  • A per-turn <runtime-state> block carries live run state — the todo_write task list and the subjects of facts written this run — so state reaches the model whether or not it thinks to recall. It is appended to the last message's content rather than added as a trailing Message::System, because the Anthropic and Gemini handlers fold System messages into the top-level system field and a trailing one would land in the cached prefix and be rewritten every turn. It never enters durable history, and renders nothing when there is nothing to say. Run constants — working directory, approval tier — belong in the system prompt's Environment: sentence instead, which compaction pins; putting them here would re-send them every turn and invite drift from the substrate's own description.

Verified goals

Live surfaces: car do --until, car do --infer-until, agents.chat { goal }, goal.suggest, goal.set / status / clear, declarative-agent goal { check, max_iterations }, and goal_evaluated events. (The macOS Chat verified-goal strip and iOS push-to-talk both ride this path for chat-capable agents.)

The goal loop requires met && grounded. Final-summary operational claims like "tests passed" are cross-checked against same-run tool receipts: an unmatched claim fails a model-judge-dependent verdict closed, while on a deterministic pass it only annotates the reply with a [claim check] note — completion is decided by the receipts, not the prose.

Declarative agents

They advertise capabilities: ["chat"] and are reachable through agents.chat in-daemon, with no spawned child process. Host agents.chat* is WS-only; agent-side FFI exists via registerChatHandler / register_chat_handler and chatEvent / chat_event.

Where it fits

The full method reference is in docs/websocket-protocol.md — that document describes the wire format produced by this crate's dispatcher.