meerkat-architecturelisted

# Meerkat Internal Architecture Meerkat is a library-first agent runtime. The execution pipeline is shared across all surfaces. Understanding crate ownership, trait contracts, the DSL-authoritative machine system, and the runtime control plane is essential for making changes that don't break architectural invariants. This file is a lean navigator. Load the specific reference under `references/` when working on that domain. ## Core Principles 1. **Infrastructure, not application** — the agent loop is a composable primitive with no opinions about prompts, tools, or output. 2. **Trait contracts own the architecture** — `meerkat-core` defines contracts; implementations live in satellite crates. 3. **Surfaces are skins, not authorities** — CLI, REST, RPC, MCP, WASM route through shared substrate and factory seams. Runtime semantics (keep-alive, input admission, drain lifecycle, commit boundaries) are owned by the shared runtime control plane (`MeerkatMachine` in `meerkat-runtime`); runtime-backed surfaces lower into it, they do not own it. 4. **Composition over configuration** — optional components are `Option<Arc<dyn Trait>>`, not feature-flagged defaults. 5. **Runtime conforms to catalog-generated machines** — the runtime follows the verified DSL model, not the other way around. Production bridge modules import/invoke catalog-owned DSL bodies; they do not author competing machine semantics. 6. **Mob is the only multi-agent runtime path** — no separate sub-agent substrate. Us