The agent runtime (SPEC §7D) as OTP.

Handles are GenServers under a runtime-owned DynamicSupervisor; the six verbs (spawn/post/wake/wait/interrupt/close) are the GenServer protocol; a Run is a monitored process; the global turn gate is a monitoring semaphore wrapped around the LLM HTTP call ONLY — injected through the client's first-class :transport seam (§8 Gap 2), so it composes against a real base_url.

The runtime owns the cross-cutting infrastructure (§7D lifecycle obligations):

• ONE ConversationStore for every handle (conversation id = the handle's deterministic id) — transcripts genuinely survive turns and durable resume reads real history;
• ONE MetricsRegistry shared by every handle's client — no per-turn client processes leak;
• an injectable clock (Toolnexus.Agents.Clock) for every timer/timeout;
• the handle table (root + parent links), rebuildable by walking snapshots.

All owned processes are linked to the runtime process and stopped by shutdown/1. Downward traversal (close/2, list/1, resume/2) runs in the CALLER's process — from outside the tree — per the rootward-call discipline documented on Toolnexus.Agents.Handle.

Options

• :registry — map of agent name → definition (see Toolnexus.Agents.registry/1)
• :transport — the LLM transport function (see Toolnexus.Client :transport); the runtime wraps it with the turn gate
• :in_process — a model running IN THIS PROCESS (ADR 0030): a bare generate function (see Toolnexus.Client.create_in_process/1), the semantic counterpart to :transport, for a host whose model is an Elixir function rather than a wire endpoint. Internally this is turned into a transport by calling the SAME Toolnexus.Client.in_process_transport/1 export create_in_process/1 uses — no duplicated adapter — and wrapped by the identical turn gate as :transport. Mutually exclusive with :transport and :llm; new/1 raises ArgumentError at construction time if more than one is set (never resolved by precedence).
• :llm — client settings shared by every handle: %{base_url, style, model, api_key, retries} (agent model: "inherit" resolves to llm.model)
• :max_concurrent_turns — global turn-gate width (default 8)
• :inbox_cap — bounded-inbox size (default 8)
• :shutdown_ms — graceful-close budget for a running turn (default 200)
• :clock — Toolnexus.Agents.Clock.t() (default: the real clock)
• :store — a ConversationStore struct (default: runtime-owned in-memory)