Zachery Aaron Shores-Chmielewski
c42bf5e983
Rename `cargo xtask provisioning-reconciler-demo` to `cargo xtask demo` (CLI dispatch, help, child re-exec argv, launch spec strings, module dir xtask/src/provisioning_demo -> xtask/src/demo). Add iteration-1 data-plane edges, established from Fleet Control: - Fleet Control "edge" button -> POST /control/edge (new ControlCommand::EstablishEdge) -> supervisor actor resolves the node's advertised EndpointAddr (stashed in NodeRuntime by AnnounceActor) and provisions a real outbound EdgeRuntime (arena ring lease, recorder WorkerPort, EDGE_ALPN send pump) in a new edge pump thread. - Node gains EDGE_ALPN, an actor bridge decoding EdgeProvision gossip, and a NodeEdgeAgent that provisions its (single) inbound edge, polls it, mirrors observations onto the node.edge telemetry channel (render-only), and answers EdgeAck gossip which terminates the supervisor's provision retries. Node teardown replaces its inbound on re-provision; supervisor replaces sessions per node and tears them down on node exit/replacement/shutdown. - The edge pump runs on the engine's blocking pool with sole session ownership (commands in, state mirror + feed lines out): the connect handshake blocks its thread and must not run on a Tokio worker or share a lock with the actor. Connects are bounded (10s) so a dead node faults its session instead of wedging edge polling. - iroh-driver: retain_telemetry_connections() opts an application out of the driver-owned TELEMETRY_ALPN ingress so the node's pull server can drain those connections itself (the actor-bridge pump would otherwise claim them). - Dashboard: edges array in the reconciler snapshot, per-node edge badges and edge button in Fleet Control, node_edges render mirror. |
||
|---|---|---|
| .. | ||
| src | ||
| .gitignore | ||
| AGENTS.md | ||
| Cargo.lock | ||
| Cargo.toml | ||
| README.md | ||
dashboard
Read-only HTML/SSE dashboard over incoming telemetry frames.
The crate owns the Axum server, bounded raw frame window, and view registry. Component crates can keep their own view implementations beside their code and register them through DashboardHandle::register_view. The built-in control-plane view is hosted here because worker/actor/message processing is universal to swactor programs.
The control-plane page fuses machine stats and actor stats per node stream: node cards (CPU/GPU/net + actor rollup) → per-node actor roster → per-actor dossier (identity, message diet, sampled message history). The Rust type name is the actor's display name; the address is the unique key. Stale streams (silent beyond the liveness window) render in a separate collapsed pool, superseded life generations are evicted immediately, and the stale pool is hard-capped.
Routes
GET /— fleet control plane (home; same page as/view/fleet)GET /events— raw incoming frames as SSEGET /api/frames— recent raw frame windowGET /api/views— registered view metadataGET /view/telemetry/live— generic live explorer over retained and incoming telemetry framesGET /api/view/telemetry/live— bounded per-stream/channel explorer snapshotGET /view/fleet— fused control-plane page (machine + actors per node)GET /api/view/fleet— live/stale pools with per-node machine and roster snapshotGET /api/view/fleet/detail?stream=<node#life>&actor=<addr>— bounded per-actor dossier detail (diet, history, sampled receipts)
Every page carries the unified top navbar, built from the view registry at serve time — pages include a <!--swactor:nav--> placeholder and the server substitutes the links, so app-registered views appear automatically.
All state is derived from observed frames. The dashboard sends no control signals back to producers.